diff options
author | Alex Shi <alex.shi@linaro.org> | 2017-06-28 22:13:59 +0800 |
---|---|---|
committer | Alex Shi <alex.shi@linaro.org> | 2017-06-28 22:13:59 +0800 |
commit | d87abdcbf8871b5ee58083b3bdf216ba406224b9 (patch) | |
tree | 5a25ee77e6be9107364139f02025ff6d0e50ab98 | |
parent | 428ee0d0d38f2cf5b1c4d584f7b2eee76d7a992e (diff) | |
parent | 89912966d1c4cf3c48f632fdc571232b5b0bdd63 (diff) |
Merge branch 'lsk/kdump/for-v4.4' into linux-linaro-lsk-v4.4
33 files changed, 1587 insertions, 172 deletions
diff --git a/Documentation/devicetree/bindings/chosen.txt b/Documentation/devicetree/bindings/chosen.txt index 6ae9d82d4c37..b5e39af4ddc0 100644 --- a/Documentation/devicetree/bindings/chosen.txt +++ b/Documentation/devicetree/bindings/chosen.txt @@ -52,3 +52,48 @@ This property is set (currently only on PowerPC, and only needed on book3e) by some versions of kexec-tools to tell the new kernel that it is being booted by kexec, as the booting environment may differ (e.g. a different secondary CPU release mechanism) + +linux,usable-memory-range +------------------------- + +This property (arm64 only) holds a base address and size, describing a +limited region in which memory may be considered available for use by +the kernel. Memory outside of this range is not available for use. + +This property describes a limitation: memory within this range is only +valid when also described through another mechanism that the kernel +would otherwise use to determine available memory (e.g. memory nodes +or the EFI memory map). Valid memory may be sparse within the range. +e.g. + +/ { + chosen { + linux,usable-memory-range = <0x9 0xf0000000 0x0 0x10000000>; + }; +}; + +The main usage is for crash dump kernel to identify its own usable +memory and exclude, at its boot time, any other memory areas that are +part of the panicked kernel's memory. + +While this property does not represent a real hardware, the address +and the size are expressed in #address-cells and #size-cells, +respectively, of the root node. + +linux,elfcorehdr +---------------- + +This property (currently used only on arm64) holds the memory range, +the address and the size, of the elf core header which mainly describes +the panicked kernel's memory layout as PT_LOAD segments of elf format. +e.g. + +/ { + chosen { + linux,elfcorehdr = <0x9 0xfffff000 0x0 0x800>; + }; +}; + +While this property does not represent a real hardware, the address +and the size are expressed in #address-cells and #size-cells, +respectively, of the root node. diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index bc4bd5a44b88..b6fe6a885bf8 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to a remote system. Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64, -s390x and arm architectures. +s390x, arm and arm64 architectures. When the system kernel boots, it reserves a small section of memory for the dump-capture kernel. This ensures that ongoing Direct Memory Access @@ -249,6 +249,13 @@ Dump-capture kernel config options (Arch Dependent, arm) AUTO_ZRELADDR=y +Dump-capture kernel config options (Arch Dependent, arm64) +---------------------------------------------------------- + +- Please note that kvm of the dump-capture kernel will not be enabled + on non-VHE systems even if it is configured. This is because the CPU + will not be reset to EL2 on panic. + Extended crashkernel syntax =========================== @@ -312,6 +319,8 @@ Boot into System Kernel any space below the alignment point may be overwritten by the dump-capture kernel, which means it is possible that the vmcore is not that precise as expected. + On arm64, use "crashkernel=Y[@X]". Note that the start address of + the kernel, X if explicitly specified, must be aligned to 2MiB (0x200000). Load the Dump-capture Kernel ============================ @@ -334,6 +343,8 @@ For s390x: - Use image or bzImage For arm: - Use zImage +For arm64: + - Use vmlinux or Image If you are using a uncompressed vmlinux image then use following command to load dump-capture kernel. @@ -377,6 +388,9 @@ For s390x: For arm: "1 maxcpus=1 reset_devices" +For arm64: + "1 maxcpus=1 reset_devices" + Notes on loading the dump-capture kernel: * By default, the ELF headers are stored in ELF64 format to support diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6fba73b6fcc8..703b7f921806 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -598,6 +598,27 @@ config SECCOMP and the task is only allowed to execute a few safe syscalls defined by each seccomp mode. +config KEXEC + depends on PM_SLEEP_SMP + select KEXEC_CORE + bool "kexec system call" + ---help--- + kexec is a system call that implements the ability to shutdown your + current kernel, and to start another kernel. It is like a reboot + but it is independent of the system firmware. And like a reboot + you can start any kernel with it, not just Linux. + +config CRASH_DUMP + bool "Build kdump crash kernel" + help + Generate crash dump after being started by kexec. This should + be normally only set in special crash dump kernels which are + loaded in the main kernel with kexec-tools into a specially + reserved region and then later executed after a crash by + kdump/kexec. + + For more details see Documentation/kdump/kdump.txt + config XEN_DOM0 def_bool y depends on XEN diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 79717faf2161..7dc5e58f7b7a 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -58,6 +58,8 @@ CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 22dda613f9c9..22aabdeacc24 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -155,5 +155,6 @@ int set_memory_ro(unsigned long addr, int numpages); int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); +int set_memory_valid(unsigned long addr, unsigned long size, int enable); #endif diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 8740297dac77..1473fc2f7ab7 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h new file mode 100644 index 000000000000..e17f0529a882 --- /dev/null +++ b/arch/arm64/include/asm/kexec.h @@ -0,0 +1,98 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_KEXEC_H +#define _ARM64_KEXEC_H + +/* Maximum physical address we can use pages from */ + +#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) + +/* Maximum address we can reach in physical address mode */ + +#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL) + +/* Maximum address we can use for the control code buffer */ + +#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL) + +#define KEXEC_CONTROL_PAGE_SIZE 4096 + +#define KEXEC_ARCH KEXEC_ARCH_AARCH64 + +#ifndef __ASSEMBLY__ + +/** + * crash_setup_regs() - save registers for the panic kernel + * + * @newregs: registers are saved here + * @oldregs: registers to be saved (may be %NULL) + */ + +static inline void crash_setup_regs(struct pt_regs *newregs, + struct pt_regs *oldregs) +{ + if (oldregs) { + memcpy(newregs, oldregs, sizeof(*newregs)); + } else { + u64 tmp1, tmp2; + + __asm__ __volatile__ ( + "stp x0, x1, [%2, #16 * 0]\n" + "stp x2, x3, [%2, #16 * 1]\n" + "stp x4, x5, [%2, #16 * 2]\n" + "stp x6, x7, [%2, #16 * 3]\n" + "stp x8, x9, [%2, #16 * 4]\n" + "stp x10, x11, [%2, #16 * 5]\n" + "stp x12, x13, [%2, #16 * 6]\n" + "stp x14, x15, [%2, #16 * 7]\n" + "stp x16, x17, [%2, #16 * 8]\n" + "stp x18, x19, [%2, #16 * 9]\n" + "stp x20, x21, [%2, #16 * 10]\n" + "stp x22, x23, [%2, #16 * 11]\n" + "stp x24, x25, [%2, #16 * 12]\n" + "stp x26, x27, [%2, #16 * 13]\n" + "stp x28, x29, [%2, #16 * 14]\n" + "mov %0, sp\n" + "stp x30, %0, [%2, #16 * 15]\n" + + "/* faked current PSTATE */\n" + "mrs %0, CurrentEL\n" + "mrs %1, SPSEL\n" + "orr %0, %0, %1\n" + "mrs %1, DAIF\n" + "orr %0, %0, %1\n" + "mrs %1, NZCV\n" + "orr %0, %0, %1\n" + /* pc */ + "adr %1, 1f\n" + "1:\n" + "stp %1, %0, [%2, #16 * 16]\n" + : "=&r" (tmp1), "=&r" (tmp2) + : "r" (newregs) + : "memory" + ); + } +} + +#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION) +extern bool crash_is_nosave(unsigned long pfn); +extern void crash_prepare_suspend(void); +extern void crash_post_resume(void); +#else +static inline bool crash_is_nosave(unsigned long pfn) {return false; } +static inline void crash_prepare_suspend(void) {} +static inline void crash_post_resume(void) {} +#endif + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 990124a67eeb..5472251c8e6c 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -33,7 +33,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, - pgprot_t prot); + pgprot_t prot, bool allow_block_mappings); extern void *fixmap_remap_fdt(phys_addr_t dt_phys); #endif diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 2013a4dc5124..1d3ff7e4a6c2 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -16,6 +16,19 @@ #ifndef __ASM_SMP_H #define __ASM_SMP_H +/* Values for secondary_data.status */ + +#define CPU_MMU_OFF (-1) +#define CPU_BOOT_SUCCESS (0) +/* The cpu invoked ops->cpu_die, synchronise it with cpu_kill */ +#define CPU_KILL_ME (1) +/* The cpu couldn't die gracefully and is looping in the kernel */ +#define CPU_STUCK_IN_KERNEL (2) +/* Fatal system error detected by secondary CPU, crash the system */ +#define CPU_PANIC_KERNEL (3) + +#ifndef __ASSEMBLY__ + #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/thread_info.h> @@ -54,11 +67,17 @@ asmlinkage void secondary_start_kernel(void); /* * Initial data for bringing up a secondary CPU. + * @stack - sp for the secondary CPU + * @status - Result passed back from the secondary CPU to + * indicate failure. */ struct secondary_data { void *stack; + long status; }; + extern struct secondary_data secondary_data; +extern long __early_cpu_boot_status; extern void secondary_entry(void); extern void arch_send_call_function_single_ipi(int cpu); @@ -77,5 +96,38 @@ extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); extern void cpu_die(void); +extern void cpu_die_early(void); + +static inline void cpu_park_loop(void) +{ + for (;;) { + wfe(); + wfi(); + } +} + +static inline void update_cpu_boot_status(int val) +{ + WRITE_ONCE(secondary_data.status, val); + /* Ensure the visibility of the status update */ + dsb(ishst); +} + +/* + * If a secondary CPU enters the kernel but fails to come online, + * (e.g. due to mismatched features), and cannot exit the kernel, + * we increment cpus_stuck_in_kernel and leave the CPU in a + * quiesecent loop within the kernel text. The memory containing + * this loop must not be re-used for anything else as the 'stuck' + * core is executing it. + * + * This function is used to inhibit features like kexec and hibernate. + */ +bool cpus_are_stuck_in_kernel(void); + +extern void smp_send_crash_stop(void); +extern bool smp_crash_stop_failed(void); + +#endif /* ifndef __ASSEMBLY__ */ #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 06e6a5238c4c..e6c27b8ce311 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -34,6 +34,11 @@ */ #define HVC_SET_VECTORS 1 +/* + * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine. + */ +#define HVC_SOFT_RESTART 2 + #define BOOT_CPU_MODE_EL1 (0xe11) #define BOOT_CPU_MODE_EL2 (0xe12) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 20bcc2db06bf..96ae961ada72 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -44,7 +44,9 @@ arm64-obj-$(CONFIG_ACPI) += acpi.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o -arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o +arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ + cpu-reset.o +arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 2bb17bd556f8..a506ddc270c0 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -117,6 +117,8 @@ int main(void) DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); BLANK(); + DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); + BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S new file mode 100644 index 000000000000..65f42d257414 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.S @@ -0,0 +1,54 @@ +/* + * CPU reset routines + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/sysreg.h> +#include <asm/virt.h> + +.text +.pushsection .idmap.text, "ax" + +/* + * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for + * cpu_soft_restart. + * + * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @entry: Location to jump to for soft reset. + * arg0: First argument passed to @entry. + * arg1: Second argument passed to @entry. + * arg2: Third argument passed to @entry. + * + * Put the CPU into the same state as it would be if it had been reset, and + * branch to what would be the reset vector. It must be executed with the + * flat identity mapping. + */ +ENTRY(__cpu_soft_restart) + /* Clear sctlr_el1 flags. */ + mrs x12, sctlr_el1 + ldr x13, =SCTLR_ELx_FLAGS + bic x12, x12, x13 + msr sctlr_el1, x12 + isb + + cbz x0, 1f // el2_switch? + mov x0, #HVC_SOFT_RESTART + hvc #0 // no return + +1: mov x18, x1 // entry + mov x0, x2 // arg0 + mov x1, x3 // arg1 + mov x2, x4 // arg2 + br x18 +ENDPROC(__cpu_soft_restart) + +.popsection diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h new file mode 100644 index 000000000000..d4e9ecb264f0 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.h @@ -0,0 +1,34 @@ +/* + * CPU reset routines + * + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_CPU_RESET_H +#define _ARM64_CPU_RESET_H + +#include <asm/virt.h> + +void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry, + unsigned long arg0, unsigned long arg1, unsigned long arg2); + +static inline void __noreturn cpu_soft_restart(unsigned long el2_switch, + unsigned long entry, unsigned long arg0, unsigned long arg1, + unsigned long arg2) +{ + typeof(__cpu_soft_restart) *restart; + + el2_switch = el2_switch && !is_kernel_in_hyp_mode() && + is_hyp_mode_available(); + restart = (void *)virt_to_phys(__cpu_soft_restart); + + cpu_install_idmap(); + restart(el2_switch, entry, arg0, arg1, arg2); + unreachable(); +} + +#endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index eda7d5915fbb..476fb5caa361 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -894,28 +894,6 @@ static u64 __raw_read_system_reg(u32 sys_id) } /* - * Park the CPU which doesn't have the capability as advertised - * by the system. - */ -static void fail_incapable_cpu(char *cap_type, - const struct arm64_cpu_capabilities *cap) -{ - int cpu = smp_processor_id(); - - pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc); - /* Mark this CPU absent */ - set_cpu_present(cpu, 0); - - /* Check if we can park ourselves */ - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) - cpu_ops[cpu]->cpu_die(cpu); - asm( - "1: wfe\n" - " wfi\n" - " b 1b"); -} - -/* * Run through the enabled system capabilities and enable() it on this CPU. * The capabilities were decided based on the available CPUs at the boot time. * Any new CPU should match the system wide status of the capability. If the @@ -943,8 +921,11 @@ void verify_local_cpu_capabilities(void) * If the new CPU misses an advertised feature, we cannot proceed * further, park the cpu. */ - if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) - fail_incapable_cpu("arm64_features", &caps[i]); + if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) { + pr_crit("CPU%d: missing feature: %s\n", + smp_processor_id(), caps[i].desc); + cpu_die_early(); + } if (caps[i].enable) caps[i].enable(NULL); } @@ -952,8 +933,11 @@ void verify_local_cpu_capabilities(void) for (i = 0, caps = arm64_hwcaps; caps[i].matches; i++) { if (!cpus_have_hwcap(&caps[i])) continue; - if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) - fail_incapable_cpu("arm64_hwcaps", &caps[i]); + if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) { + pr_crit("CPU%d: missing HWCAP: %s\n", + smp_processor_id(), caps[i].desc); + cpu_die_early(); + } } } diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c new file mode 100644 index 000000000000..f46d57c31443 --- /dev/null +++ b/arch/arm64/kernel/crash_dump.c @@ -0,0 +1,71 @@ +/* + * Routines for doing kexec-based kdump + * + * Copyright (C) 2017 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/crash_dump.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/memblock.h> +#include <linux/uaccess.h> +#include <asm/memory.h> + +/** + * copy_oldmem_page() - copy one page from old kernel memory + * @pfn: page frame number to be copied + * @buf: buffer where the copied page is placed + * @csize: number of bytes to copy + * @offset: offset in bytes into the page + * @userbuf: if set, @buf is in a user address space + * + * This function copies one page from old kernel memory into buffer pointed by + * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes + * copied or negative error in case of failure. + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, + int userbuf) +{ + void *vaddr; + + if (!csize) + return 0; + + vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB); + if (!vaddr) + return -ENOMEM; + + if (userbuf) { + if (copy_to_user((char __user *)buf, vaddr + offset, csize)) { + memunmap(vaddr); + return -EFAULT; + } + } else { + memcpy(buf, vaddr + offset, csize); + } + + memunmap(vaddr); + + return csize; +} + +/** + * elfcorehdr_read - read from ELF core header + * @buf: buffer where the data is placed + * @csize: number of bytes to read + * @ppos: address in the memory + * + * This function reads @count bytes from elf core header which exists + * on crash dump kernel's memory. + */ +ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) +{ + memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + return count; +} diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4eeb17198cfa..40270c1fa947 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -264,7 +264,7 @@ static bool __init efi_virtmap_init(void) create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr, md->num_pages << EFI_PAGE_SHIFT, - __pgprot(pgprot_val(prot) | PTE_NG)); + __pgprot(pgprot_val(prot) | PTE_NG), true); } return true; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 0ea9a97467a6..6c5595928169 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -36,6 +36,7 @@ #include <asm/pgtable-hwdef.h> #include <asm/pgtable.h> #include <asm/page.h> +#include <asm/smp.h> #include <asm/sysreg.h> #include <asm/thread_info.h> #include <asm/virt.h> @@ -643,7 +644,8 @@ __secondary_switched: msr vbar_el1, x5 isb - ldr_l x0, secondary_data // get secondary_data.stack + adr_l x0, secondary_data + ldr x0, [x0, #CPU_BOOT_STACK] // get secondary_data.stack mov sp, x0 and x0, x0, #~(THREAD_SIZE - 1) msr sp_el0, x0 // save thread_info @@ -652,6 +654,29 @@ __secondary_switched: ENDPROC(__secondary_switched) /* + * The booting CPU updates the failed status @__early_cpu_boot_status, + * with MMU turned off. + * + * update_early_cpu_boot_status tmp, status + * - Corrupts tmp1, tmp2 + * - Writes 'status' to __early_cpu_boot_status and makes sure + * it is committed to memory. + */ + + .macro update_early_cpu_boot_status status, tmp1, tmp2 + mov \tmp2, #\status + str_l \tmp2, __early_cpu_boot_status, \tmp1 + dmb sy + dc ivac, \tmp1 // Invalidate potentially stale cache line + .endm + + .pushsection .data..cacheline_aligned + .align L1_CACHE_SHIFT +ENTRY(__early_cpu_boot_status) + .long 0 + .popsection + +/* * Enable the MMU. * * x0 = SCTLR_EL1 value for turning on the MMU. @@ -669,6 +694,7 @@ ENTRY(__enable_mmu) ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4 cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED b.ne __no_granule_support + update_early_cpu_boot_status 0, x1, x2 msr ttbr0_el1, x25 // load TTBR0 msr ttbr1_el1, x26 // load TTBR1 isb @@ -708,8 +734,12 @@ ENTRY(__enable_mmu) ENDPROC(__enable_mmu) __no_granule_support: + /* Indicate that this CPU can't boot and is stuck in the kernel */ + update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2 +1: wfe - b __no_granule_support + wfi + b 1b ENDPROC(__no_granule_support) __primary_switch: diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 6dd18140ebb8..35a33d705536 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -27,6 +27,7 @@ #include <asm/barrier.h> #include <asm/cacheflush.h> #include <asm/irqflags.h> +#include <asm/kexec.h> #include <asm/memory.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> @@ -100,7 +101,8 @@ int pfn_is_nosave(unsigned long pfn) unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin); unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1); - return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn); + return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)) || + crash_is_nosave(pfn); } void notrace save_processor_state(void) @@ -250,11 +252,17 @@ int swsusp_arch_suspend(void) local_dbg_save(flags); if (__cpu_suspend_enter(&state)) { + /* make the crash dump kernel image visible/saveable */ + crash_prepare_suspend(); + ret = swsusp_save(); } else { /* Clean kernel to PoC for secondary core startup */ __flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START); + /* make the crash dump kernel image protected again */ + crash_post_resume(); + /* * Tell the hibernation core that we've just restored * the memory diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 8727f4490772..d3b5f75e652e 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -71,8 +71,16 @@ el1_sync: msr vbar_el2, x1 b 9f +2: cmp x0, #HVC_SOFT_RESTART + b.ne 3f + mov x0, x2 + mov x2, x4 + mov x4, x1 + mov x1, x3 + br x4 // no return + /* Someone called kvm_call_hyp() against the hyp-stub... */ -2: mov x0, #ARM_EXCEPTION_HYP_GONE +3: mov x0, #ARM_EXCEPTION_HYP_GONE 9: eret ENDPROC(el1_sync) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c new file mode 100644 index 000000000000..481f54a866c5 --- /dev/null +++ b/arch/arm64/kernel/machine_kexec.c @@ -0,0 +1,364 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/page-flags.h> +#include <linux/smp.h> + +#include <asm/cacheflush.h> +#include <asm/cpu_ops.h> +#include <asm/memory.h> +#include <asm/mmu.h> +#include <asm/mmu_context.h> +#include <asm/page.h> + +#include "cpu-reset.h" + +/* Global variables for the arm64_relocate_new_kernel routine. */ +extern const unsigned char arm64_relocate_new_kernel[]; +extern const unsigned long arm64_relocate_new_kernel_size; + +/** + * kexec_image_info - For debugging output. + */ +#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i) +static void _kexec_image_info(const char *func, int line, + const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:%d:\n", func, line); + pr_debug(" kexec kimage info:\n"); + pr_debug(" type: %d\n", kimage->type); + pr_debug(" start: %lx\n", kimage->start); + pr_debug(" head: %lx\n", kimage->head); + pr_debug(" nr_segments: %lu\n", kimage->nr_segments); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + } +} + +void machine_kexec_cleanup(struct kimage *kimage) +{ + /* Empty routine needed to avoid build errors. */ +} + +/** + * machine_kexec_prepare - Prepare for a kexec reboot. + * + * Called from the core kexec code when a kernel image is loaded. + * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus + * are stuck in the kernel. This avoids a panic once we hit machine_kexec(). + */ +int machine_kexec_prepare(struct kimage *kimage) +{ + kexec_image_info(kimage); + + if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) { + pr_err("Can't kexec: CPUs are stuck in the kernel.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * kexec_list_flush - Helper to flush the kimage list and source pages to PoC. + */ +static void kexec_list_flush(struct kimage *kimage) +{ + kimage_entry_t *entry; + + for (entry = &kimage->head; ; entry++) { + unsigned int flag; + void *addr; + + /* flush the list entries. */ + __flush_dcache_area(entry, sizeof(kimage_entry_t)); + + flag = *entry & IND_FLAGS; + if (flag == IND_DONE) + break; + + addr = phys_to_virt(*entry & PAGE_MASK); + + switch (flag) { + case IND_INDIRECTION: + /* Set entry point just before the new list page. */ + entry = (kimage_entry_t *)addr - 1; + break; + case IND_SOURCE: + /* flush the source pages. */ + __flush_dcache_area(addr, PAGE_SIZE); + break; + case IND_DESTINATION: + break; + default: + BUG(); + } + } +} + +/** + * kexec_segment_flush - Helper to flush the kimage segments to PoC. + */ +static void kexec_segment_flush(const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:\n", __func__); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + + __flush_dcache_area(phys_to_virt(kimage->segment[i].mem), + kimage->segment[i].memsz); + } +} + +/** + * machine_kexec - Do the kexec reboot. + * + * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC. + */ +void machine_kexec(struct kimage *kimage) +{ + phys_addr_t reboot_code_buffer_phys; + void *reboot_code_buffer; + bool in_kexec_crash = (kimage == kexec_crash_image); + bool stuck_cpus = cpus_are_stuck_in_kernel(); + + /* + * New cpus may have become stuck_in_kernel after we loaded the image. + */ + BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1))); + WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()), + "Some CPUs may be stale, kdump will be unreliable.\n"); + + reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); + reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys); + + kexec_image_info(kimage); + + pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__, + kimage->control_code_page); + pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, + &reboot_code_buffer_phys); + pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, + reboot_code_buffer); + pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, + arm64_relocate_new_kernel); + pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", + __func__, __LINE__, arm64_relocate_new_kernel_size, + arm64_relocate_new_kernel_size); + + /* + * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use + * after the kernel is shut down. + */ + memcpy(reboot_code_buffer, arm64_relocate_new_kernel, + arm64_relocate_new_kernel_size); + + /* Flush the reboot_code_buffer in preparation for its execution. */ + __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); + flush_icache_range((uintptr_t)reboot_code_buffer, + arm64_relocate_new_kernel_size); + + /* Flush the kimage list and its buffers. */ + kexec_list_flush(kimage); + + /* Flush the new image if already in place. */ + if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE)) + kexec_segment_flush(kimage); + + pr_info("Bye!\n"); + + /* Disable all DAIF exceptions. */ + asm volatile ("msr daifset, #0xf" : : : "memory"); + + /* + * cpu_soft_restart will shutdown the MMU, disable data caches, then + * transfer control to the reboot_code_buffer which contains a copy of + * the arm64_relocate_new_kernel routine. arm64_relocate_new_kernel + * uses physical addressing to relocate the new image to its final + * position and transfers control to the image entry point when the + * relocation is complete. + */ + + cpu_soft_restart(kimage != kexec_crash_image, + reboot_code_buffer_phys, kimage->head, kimage->start, 0); + + BUG(); /* Should never get here. */ +} + +static void machine_kexec_mask_interrupts(void) +{ + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + int ret; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + /* + * First try to remove the active state. If this + * fails, try to EOI the interrupt. + */ + ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + + if (ret && irqd_irq_inprogress(&desc->irq_data) && + chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } +} + +/** + * machine_crash_shutdown - shutdown non-crashing cpus and save registers + */ +void machine_crash_shutdown(struct pt_regs *regs) +{ + local_irq_disable(); + + /* shutdown non-crashing cpus */ + smp_send_crash_stop(); + + /* for crashing cpu */ + crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + + pr_info("Starting crashdump kernel...\n"); +} + +void arch_kexec_protect_crashkres(void) +{ + int i; + + kexec_segment_flush(kexec_crash_image); + + for (i = 0; i < kexec_crash_image->nr_segments; i++) + set_memory_valid( + __phys_to_virt(kexec_crash_image->segment[i].mem), + kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0); +} + +void arch_kexec_unprotect_crashkres(void) +{ + int i; + + for (i = 0; i < kexec_crash_image->nr_segments; i++) + set_memory_valid( + __phys_to_virt(kexec_crash_image->segment[i].mem), + kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1); +} + +#ifdef CONFIG_HIBERNATION +/* + * To preserve the crash dump kernel image, the relevant memory segments + * should be mapped again around the hibernation. + */ +void crash_prepare_suspend(void) +{ + if (kexec_crash_image) + arch_kexec_unprotect_crashkres(); +} + +void crash_post_resume(void) +{ + if (kexec_crash_image) + arch_kexec_protect_crashkres(); +} + +/* + * crash_is_nosave + * + * Return true only if a page is part of reserved memory for crash dump kernel, + * but does not hold any data of loaded kernel image. + * + * Note that all the pages in crash dump kernel memory have been initially + * marked as Reserved in kexec_reserve_crashkres_pages(). + * + * In hibernation, the pages which are Reserved and yet "nosave" are excluded + * from the hibernation iamge. crash_is_nosave() does thich check for crash + * dump kernel and will reduce the total size of hibernation image. + */ + +bool crash_is_nosave(unsigned long pfn) +{ + int i; + phys_addr_t addr; + + if (!crashk_res.end) + return false; + + /* in reserved memory? */ + addr = __pfn_to_phys(pfn); + if ((addr < crashk_res.start) || (crashk_res.end < addr)) + return false; + + if (!kexec_crash_image) + return true; + + /* not part of loaded kernel image? */ + for (i = 0; i < kexec_crash_image->nr_segments; i++) + if (addr >= kexec_crash_image->segment[i].mem && + addr < (kexec_crash_image->segment[i].mem + + kexec_crash_image->segment[i].memsz)) + return false; + + return true; +} + +void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) +{ + unsigned long addr; + struct page *page; + + for (addr = begin; addr < end; addr += PAGE_SIZE) { + page = phys_to_page(addr); + ClearPageReserved(page); + free_reserved_page(page); + } +} +#endif /* CONFIG_HIBERNATION */ + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); +} diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S new file mode 100644 index 000000000000..51b73cdde287 --- /dev/null +++ b/arch/arm64/kernel/relocate_kernel.S @@ -0,0 +1,130 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kexec.h> +#include <linux/linkage.h> + +#include <asm/assembler.h> +#include <asm/kexec.h> +#include <asm/page.h> +#include <asm/sysreg.h> + +/* + * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it. + * + * The memory that the old kernel occupies may be overwritten when coping the + * new image to its final location. To assure that the + * arm64_relocate_new_kernel routine which does that copy is not overwritten, + * all code and data needed by arm64_relocate_new_kernel must be between the + * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end. The + * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec + * control_code_page, a special page which has been set up to be preserved + * during the copy operation. + */ +ENTRY(arm64_relocate_new_kernel) + + /* Setup the list loop variables. */ + mov x17, x1 /* x17 = kimage_start */ + mov x16, x0 /* x16 = kimage_head */ + dcache_line_size x15, x0 /* x15 = dcache line size */ + mov x14, xzr /* x14 = entry ptr */ + mov x13, xzr /* x13 = copy dest */ + + /* Clear the sctlr_el2 flags. */ + mrs x0, CurrentEL + cmp x0, #CurrentEL_EL2 + b.ne 1f + mrs x0, sctlr_el2 + ldr x1, =SCTLR_ELx_FLAGS + bic x0, x0, x1 + msr sctlr_el2, x0 + isb +1: + + /* Check if the new image needs relocation. */ + tbnz x16, IND_DONE_BIT, .Ldone + +.Lloop: + and x12, x16, PAGE_MASK /* x12 = addr */ + + /* Test the entry flags. */ +.Ltest_source: + tbz x16, IND_SOURCE_BIT, .Ltest_indirection + + /* Invalidate dest page to PoC. */ + mov x0, x13 + add x20, x0, #PAGE_SIZE + sub x1, x15, #1 + bic x0, x0, x1 +2: dc ivac, x0 + add x0, x0, x15 + cmp x0, x20 + b.lo 2b + dsb sy + + mov x20, x13 + mov x21, x12 + copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7 + + /* dest += PAGE_SIZE */ + add x13, x13, PAGE_SIZE + b .Lnext + +.Ltest_indirection: + tbz x16, IND_INDIRECTION_BIT, .Ltest_destination + + /* ptr = addr */ + mov x14, x12 + b .Lnext + +.Ltest_destination: + tbz x16, IND_DESTINATION_BIT, .Lnext + + /* dest = addr */ + mov x13, x12 + +.Lnext: + /* entry = *ptr++ */ + ldr x16, [x14], #8 + + /* while (!(entry & DONE)) */ + tbz x16, IND_DONE_BIT, .Lloop + +.Ldone: + /* wait for writes from copy_page to finish */ + dsb nsh + ic iallu + dsb nsh + isb + + /* Start new image. */ + mov x0, xzr + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x17 + +ENDPROC(arm64_relocate_new_kernel) + +.ltorg + +.align 3 /* To keep the 64-bit values below naturally aligned. */ + +.Lcopy_end: +.org KEXEC_CONTROL_PAGE_SIZE + +/* + * arm64_relocate_new_kernel_size - Number of bytes to copy to the + * control_code_page. + */ +.globl arm64_relocate_new_kernel_size +arm64_relocate_new_kernel_size: + .quad .Lcopy_end - arm64_relocate_new_kernel diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 1e33d967c0ae..566f3b9b1588 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -31,7 +31,6 @@ #include <linux/screen_info.h> #include <linux/init.h> #include <linux/kexec.h> -#include <linux/crash_dump.h> #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/interrupt.h> @@ -220,6 +219,12 @@ static void __init request_standard_resources(void) if (kernel_data.start >= res->start && kernel_data.end <= res->end) request_resource(res, &kernel_data); +#ifdef CONFIG_KEXEC_CORE + /* Userspace will find "Crash kernel" region in /proc/iomem. */ + if (crashk_res.end && crashk_res.start >= res->start && + crashk_res.end <= res->end) + request_resource(res, &crashk_res); +#endif } } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index a84623d91410..a1d06fc42048 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -37,6 +37,7 @@ #include <linux/completion.h> #include <linux/of.h> #include <linux/irq_work.h> +#include <linux/kexec.h> #include <asm/alternative.h> #include <asm/atomic.h> @@ -63,16 +64,29 @@ * where to place its SVC stack */ struct secondary_data secondary_data; +/* Number of CPUs which aren't online, but looping in kernel text. */ +int cpus_stuck_in_kernel; enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, IPI_TIMER, IPI_IRQ_WORK, IPI_WAKEUP }; +#ifdef CONFIG_HOTPLUG_CPU +static int op_cpu_kill(unsigned int cpu); +#else +static inline int op_cpu_kill(unsigned int cpu) +{ + return -ENOSYS; +} +#endif + + /* * Boot a secondary CPU, and assign it the specified idle task. * This also gives us the initial stack to use for this CPU. @@ -90,12 +104,14 @@ static DECLARE_COMPLETION(cpu_running); int __cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; + long status; /* * We need to tell the secondary core where to find its stack and the * page tables. */ secondary_data.stack = task_stack_page(idle) + THREAD_START_SP; + update_cpu_boot_status(CPU_MMU_OFF); __flush_dcache_area(&secondary_data, sizeof(secondary_data)); /* @@ -119,6 +135,32 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) } secondary_data.stack = NULL; + status = READ_ONCE(secondary_data.status); + if (ret && status) { + + if (status == CPU_MMU_OFF) + status = READ_ONCE(__early_cpu_boot_status); + + switch (status) { + default: + pr_err("CPU%u: failed in unknown state : 0x%lx\n", + cpu, status); + break; + case CPU_KILL_ME: + if (!op_cpu_kill(cpu)) { + pr_crit("CPU%u: died during early boot\n", cpu); + break; + } + /* Fall through */ + pr_crit("CPU%u: may not have shut down cleanly\n", cpu); + case CPU_STUCK_IN_KERNEL: + pr_crit("CPU%u: is stuck in kernel\n", cpu); + cpus_stuck_in_kernel++; + break; + case CPU_PANIC_KERNEL: + panic("CPU%u detected unsupported configuration\n", cpu); + } + } return ret; } @@ -184,6 +226,9 @@ asmlinkage void secondary_start_kernel(void) */ pr_info("CPU%u: Booted secondary processor [%08x]\n", cpu, read_cpuid_id()); + update_cpu_boot_status(CPU_BOOT_SUCCESS); + /* Make sure the status update is visible before we complete */ + smp_wmb(); set_cpu_online(cpu, true); complete(&cpu_running); @@ -311,6 +356,30 @@ void cpu_die(void) } #endif +/* + * Kill the calling secondary CPU, early in bringup before it is turned + * online. + */ +void cpu_die_early(void) +{ + int cpu = smp_processor_id(); + + pr_crit("CPU%d: will not boot\n", cpu); + + /* Mark this CPU absent */ + set_cpu_present(cpu, 0); + +#ifdef CONFIG_HOTPLUG_CPU + update_cpu_boot_status(CPU_KILL_ME); + /* Check if we can park ourselves */ + if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); +#endif + update_cpu_boot_status(CPU_STUCK_IN_KERNEL); + + cpu_park_loop(); +} + static void __init hyp_mode_check(void) { if (is_hyp_mode_available()) @@ -634,6 +703,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { S(IPI_RESCHEDULE, "Rescheduling interrupts"), S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), S(IPI_IRQ_WORK, "IRQ work interrupts"), S(IPI_WAKEUP, "CPU wake-up interrupts"), @@ -718,6 +788,29 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +#ifdef CONFIG_KEXEC_CORE +static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); +#endif + +static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ +#ifdef CONFIG_KEXEC_CORE + crash_save_cpu(regs, cpu); + + atomic_dec(&waiting_for_crash_ipi); + + local_irq_disable(); + +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); +#endif + + /* just in case */ + cpu_park_loop(); +#endif +} + /* * Main handler for inter-processor interrupts */ @@ -748,6 +841,15 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_CPU_CRASH_STOP: + if (IS_ENABLED(CONFIG_KEXEC_CORE)) { + irq_enter(); + ipi_cpu_crash_stop(cpu, regs); + + unreachable(); + } + break; + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST case IPI_TIMER: irq_enter(); @@ -816,6 +918,39 @@ void smp_send_stop(void) pr_warning("SMP: failed to stop secondary CPUs\n"); } +#ifdef CONFIG_KEXEC_CORE +void smp_send_crash_stop(void) +{ + cpumask_t mask; + unsigned long timeout; + + if (num_online_cpus() == 1) + return; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + + pr_crit("SMP: stopping secondary CPUs\n"); + smp_cross_call(&mask, IPI_CPU_CRASH_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + udelay(1); + + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warning("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(&mask)); +} + +bool smp_crash_stop_failed(void) +{ + return (atomic_read(&waiting_for_crash_ipi) > 0); +} +#endif + /* * not supported here */ @@ -823,3 +958,21 @@ int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } + +static bool have_cpu_die(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + int any_cpu = raw_smp_processor_id(); + + if (cpu_ops[any_cpu]->cpu_die) + return true; +#endif + return false; +} + +bool cpus_are_stuck_in_kernel(void) +{ + bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die()); + + return !!cpus_stuck_in_kernel || smp_spin_tables; +} diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 75728047b60b..b2adff43bdaa 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -29,11 +29,14 @@ #include <linux/gfp.h> #include <linux/memblock.h> #include <linux/sort.h> +#include <linux/of.h> #include <linux/of_fdt.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> #include <linux/swiotlb.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> #include <asm/boot.h> #include <asm/fixmap.h> @@ -75,6 +78,142 @@ static int __init early_initrd(char *p) early_param("initrd", early_initrd); #endif +#ifdef CONFIG_KEXEC_CORE +/* + * reserve_crashkernel() - reserves memory for crash kernel + * + * This function reserves memory area given in "crashkernel=" kernel command + * line parameter. The memory reserved is used by dump capture kernel when + * primary kernel is crashing. + */ +static void __init reserve_crashkernel(void) +{ + unsigned long long crash_base, crash_size; + int ret; + + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + &crash_size, &crash_base); + /* no crashkernel= or invalid value specified */ + if (ret || !crash_size) + return; + + crash_size = PAGE_ALIGN(crash_size); + + if (crash_base == 0) { + /* Current arm64 boot protocol requires 2MB alignment */ + crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT, + crash_size, SZ_2M); + if (crash_base == 0) { + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", + crash_size); + return; + } + } else { + /* User specifies base address explicitly. */ + if (!memblock_is_region_memory(crash_base, crash_size)) { + pr_warn("cannot reserve crashkernel: region is not memory\n"); + return; + } + + if (memblock_is_region_reserved(crash_base, crash_size)) { + pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n"); + return; + } + + if (!IS_ALIGNED(crash_base, SZ_2M)) { + pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n"); + return; + } + } + memblock_reserve(crash_base, crash_size); + + pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + crash_base, crash_base + crash_size, crash_size >> 20); + + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; +} + +static void __init kexec_reserve_crashkres_pages(void) +{ +#ifdef CONFIG_HIBERNATION + phys_addr_t addr; + struct page *page; + + if (!crashk_res.end) + return; + + /* + * To reduce the size of hibernation image, all the pages are + * marked as Reserved initially. + */ + for (addr = crashk_res.start; addr < (crashk_res.end + 1); + addr += PAGE_SIZE) { + page = phys_to_page(addr); + SetPageReserved(page); + } +#endif +} +#else +static void __init reserve_crashkernel(void) +{ +} + +static void __init kexec_reserve_crashkres_pages(void) +{ +} +#endif /* CONFIG_KEXEC_CORE */ + +#ifdef CONFIG_CRASH_DUMP +static int __init early_init_dt_scan_elfcorehdr(unsigned long node, + const char *uname, int depth, void *data) +{ + const __be32 *reg; + int len; + + if (depth != 1 || strcmp(uname, "chosen") != 0) + return 0; + + reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len); + if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells))) + return 1; + + elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, ®); + elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, ®); + + return 1; +} + +/* + * reserve_elfcorehdr() - reserves memory for elf core header + * + * This function reserves the memory occupied by an elf core header + * described in the device tree. This region contains all the + * information about primary kernel's core image and is used by a dump + * capture kernel to access the system memory on primary kernel. + */ +static void __init reserve_elfcorehdr(void) +{ + of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL); + + if (!elfcorehdr_size) + return; + + if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) { + pr_warn("elfcorehdr is overlapped\n"); + return; + } + + memblock_reserve(elfcorehdr_addr, elfcorehdr_size); + + pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n", + elfcorehdr_size >> 10, elfcorehdr_addr); +} +#else +static void __init reserve_elfcorehdr(void) +{ +} +#endif /* CONFIG_CRASH_DUMP */ /* * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It * currently assumes that for memory starting above 4G, 32-bit devices will @@ -166,10 +305,45 @@ static int __init early_mem(char *p) } early_param("mem", early_mem); +static int __init early_init_dt_scan_usablemem(unsigned long node, + const char *uname, int depth, void *data) +{ + struct memblock_region *usablemem = data; + const __be32 *reg; + int len; + + if (depth != 1 || strcmp(uname, "chosen") != 0) + return 0; + + reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len); + if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells))) + return 1; + + usablemem->base = dt_mem_next_cell(dt_root_addr_cells, ®); + usablemem->size = dt_mem_next_cell(dt_root_size_cells, ®); + + return 1; +} + +static void __init fdt_enforce_memory_region(void) +{ + struct memblock_region reg = { + .size = 0, + }; + + of_scan_flat_dt(early_init_dt_scan_usablemem, ®); + + if (reg.size) + memblock_cap_memory_range(reg.base, reg.size); +} + void __init arm64_memblock_init(void) { const s64 linear_region_size = -(s64)PAGE_OFFSET; + /* Handle linux,usable-memory-range property */ + fdt_enforce_memory_region(); + /* * Ensure that the linear region takes up exactly half of the kernel * virtual address space. This way, we can distinguish a linear address @@ -242,6 +416,11 @@ void __init arm64_memblock_init(void) arm64_dma_phys_limit = max_zone_dma_phys(); else arm64_dma_phys_limit = PHYS_MASK + 1; + + reserve_crashkernel(); + + reserve_elfcorehdr(); + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); @@ -355,6 +534,8 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ free_all_bootmem(); + kexec_reserve_crashkres_pages(); + mem_init_print_info(NULL); #define MLK(b, t) b, t, ((t) - (b)) >> 10 diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 8fc302d84e1f..d23342804230 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -21,6 +21,8 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/init.h> +#include <linux/ioport.h> +#include <linux/kexec.h> #include <linux/libfdt.h> #include <linux/mman.h> #include <linux/nodemask.h> @@ -156,29 +158,10 @@ static void split_pud(pud_t *old_pud, pmd_t *pmd) } while (pmd++, i++, i < PTRS_PER_PMD); } -#ifdef CONFIG_DEBUG_PAGEALLOC -static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) -{ - - /* - * If debug_page_alloc is enabled we must map the linear map - * using pages. However, other mappings created by - * create_mapping_noalloc must use sections in some cases. Allow - * sections to be used in those cases, where no pgtable_alloc - * function is provided. - */ - return !pgtable_alloc || !debug_pagealloc_enabled(); -} -#else -static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) -{ - return true; -} -#endif - static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { pmd_t *pmd; unsigned long next; @@ -209,7 +192,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && - block_mappings_allowed(pgtable_alloc)) { + (!pgtable_alloc || allow_block_mappings)) { pmd_t old_pmd =*pmd; pmd_set_huge(pmd, phys, prot); /* @@ -248,7 +231,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { pud_t *pud; unsigned long next; @@ -269,7 +253,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, * For 4K granule only, attempt to put down a 1GB block */ if (use_1G_block(addr, next, phys) && - block_mappings_allowed(pgtable_alloc)) { + (!pgtable_alloc || allow_block_mappings)) { pud_t old_pud = *pud; pud_set_huge(pud, phys, prot); @@ -290,7 +274,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, } } else { alloc_init_pmd(pud, addr, next, phys, prot, - pgtable_alloc); + pgtable_alloc, allow_block_mappings); } phys += next - addr; } while (pud++, addr = next, addr != end); @@ -304,7 +288,8 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, */ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { unsigned long addr, length, end, next; @@ -322,7 +307,8 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc); + alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + (!pgtable_alloc || allow_block_mappings)); phys += next - addr; } while (pgd++, addr = next, addr != end); } @@ -340,9 +326,11 @@ static phys_addr_t late_pgtable_alloc(void) static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, - phys_addr_t (*alloc)(void)) + phys_addr_t (*alloc)(void), + bool allow_block_mappings) { - init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc); + init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc, + allow_block_mappings); } /* @@ -358,16 +346,15 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, - NULL); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, - pgprot_t prot) + pgprot_t prot, bool allow_block_mappings) { __create_pgd_mapping(mm->pgd, phys, virt, size, prot, - late_pgtable_alloc); + late_pgtable_alloc, allow_block_mappings); } static void create_mapping_late(phys_addr_t phys, unsigned long virt, @@ -380,41 +367,49 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, - late_pgtable_alloc); + late_pgtable_alloc, !debug_pagealloc_enabled()); +} + +static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, + phys_addr_t end, pgprot_t prot, + bool allow_block_mappings) +{ + __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, + prot, early_pgtable_alloc, allow_block_mappings); } -static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) +static void __init map_mem(pgd_t *pgd) { unsigned long kernel_start = __pa(_text); unsigned long kernel_end = __pa(_etext); + struct memblock_region *reg; /* * Take care not to create a writable alias for the * read-only text and rodata sections of the kernel image. + * So temporarily mark them as NOMAP to skip mappings in + * the following for-loop */ + memblock_mark_nomap(kernel_start, kernel_end - kernel_start); +#ifdef CONFIG_KEXEC_CORE + if (crashk_res.end) + memblock_mark_nomap(crashk_res.start, + resource_size(&crashk_res)); +#endif - /* No overlap with the kernel text */ - if (end < kernel_start || start >= kernel_end) { - __create_pgd_mapping(pgd, start, __phys_to_virt(start), - end - start, PAGE_KERNEL, - early_pgtable_alloc); - return; - } + /* map all the memory banks */ + for_each_memblock(memory, reg) { + phys_addr_t start = reg->base; + phys_addr_t end = start + reg->size; - /* - * This block overlaps the kernel text mapping. - * Map the portion(s) which don't overlap. - */ - if (start < kernel_start) - __create_pgd_mapping(pgd, start, - __phys_to_virt(start), - kernel_start - start, PAGE_KERNEL, - early_pgtable_alloc); - if (kernel_end < end) - __create_pgd_mapping(pgd, kernel_end, - __phys_to_virt(kernel_end), - end - kernel_end, PAGE_KERNEL, - early_pgtable_alloc); + if (start >= end) + break; + if (memblock_is_nomap(reg)) + continue; + + __map_memblock(pgd, start, end, + PAGE_KERNEL, !debug_pagealloc_enabled()); + } /* * Map the linear alias of the [_text, _etext) interval as @@ -422,25 +417,23 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end * region accessible to subsystems such as hibernate, but * protects it from inadvertent modification or execution. */ - __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start), - kernel_end - kernel_start, PAGE_KERNEL_RO, - early_pgtable_alloc); -} - -static void __init map_mem(pgd_t *pgd) -{ - struct memblock_region *reg; + __map_memblock(pgd, kernel_start, kernel_end, + PAGE_KERNEL_RO, !debug_pagealloc_enabled()); + memblock_clear_nomap(kernel_start, kernel_end - kernel_start); - /* map all the memory banks */ - for_each_memblock(memory, reg) { - phys_addr_t start = reg->base; - phys_addr_t end = start + reg->size; - - if (start >= end) - break; - - __map_memblock(pgd, start, end); +#ifdef CONFIG_KEXEC_CORE + /* + * Use page-level mappings here so that we can shrink the region + * in page granularity and put back unused memory to buddy system + * through /sys/kernel/kexec_crash_size interface. + */ + if (crashk_res.end) { + __map_memblock(pgd, crashk_res.start, crashk_res.end + 1, + PAGE_KERNEL, false); + memblock_clear_nomap(crashk_res.start, + resource_size(&crashk_res)); } +#endif } void mark_rodata_ro(void) @@ -479,7 +472,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(size)); __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, - early_pgtable_alloc); + early_pgtable_alloc, !debug_pagealloc_enabled()); vma->addr = va_start; vma->phys_addr = pa_start; diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index ca6d268e3313..f4e39dbdd36b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -125,6 +125,19 @@ int set_memory_x(unsigned long addr, int numpages) } EXPORT_SYMBOL_GPL(set_memory_x); + +int set_memory_valid(unsigned long addr, int numpages, int enable) +{ + if (enable) + return __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(PTE_VALID), + __pgprot(0)); + else + return __change_memory_common(addr, PAGE_SIZE * numpages, + __pgprot(0), + __pgprot(PTE_VALID)); +} + #ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index b1c22cf18f7d..9ee9973b5c3e 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -16,6 +16,22 @@ #include "efistub.h" +#define EFI_DT_ADDR_CELLS_DEFAULT 2 +#define EFI_DT_SIZE_CELLS_DEFAULT 2 + +static void fdt_update_cell_size(efi_system_table_t *sys_table, void *fdt) +{ + int offset; + + offset = fdt_path_offset(fdt, "/"); + /* Set the #address-cells and #size-cells values for an empty tree */ + + fdt_setprop_u32(fdt, offset, "#address-cells", + EFI_DT_ADDR_CELLS_DEFAULT); + + fdt_setprop_u32(fdt, offset, "#size-cells", EFI_DT_SIZE_CELLS_DEFAULT); +} + efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, unsigned long orig_fdt_size, void *fdt, int new_fdt_size, char *cmdline_ptr, @@ -45,10 +61,18 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, } } - if (orig_fdt) + if (orig_fdt) { status = fdt_open_into(orig_fdt, fdt, new_fdt_size); - else + } else { status = fdt_create_empty_tree(fdt, new_fdt_size); + if (status == 0) { + /* + * Any failure from the following function is non + * critical + */ + fdt_update_cell_size(sys_table, fdt); + } + } if (status != 0) goto fdt_set_fail; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 76b502c6258f..e3d461f19cbc 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -25,6 +25,7 @@ enum { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ + MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ }; struct memblock_region { @@ -82,6 +83,8 @@ bool memblock_overlaps_region(struct memblock_type *type, int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); +int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); +int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); ulong choose_memblock_flags(void); /* Low level functions */ @@ -184,6 +187,11 @@ static inline bool memblock_is_mirror(struct memblock_region *m) return m->flags & MEMBLOCK_MIRROR; } +static inline bool memblock_is_nomap(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_NOMAP; +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); @@ -318,9 +326,12 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -int memblock_is_memory(phys_addr_t addr); +void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size); +void memblock_mem_limit_remove_map(phys_addr_t limit); +bool memblock_is_memory(phys_addr_t addr); +int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); -int memblock_is_reserved(phys_addr_t addr); +bool memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void __memblock_dump_all(void); diff --git a/include/linux/mm.h b/include/linux/mm.h index f0ffa01c90d9..b93d147439f9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2148,14 +2148,18 @@ kernel_map_pages(struct page *page, int numpages, int enable) } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); -#endif /* CONFIG_HIBERNATION */ -#else +#endif /* CONFIG_HIBERNATION */ +#else /* CONFIG_DEBUG_PAGEALLOC */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } -#endif /* CONFIG_HIBERNATION */ -#endif +#endif /* CONFIG_HIBERNATION */ +static inline bool debug_pagealloc_enabled(void) +{ + return false; +} +#endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 99048e501b88..aae5ebf2022b 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -39,6 +39,7 @@ #define KEXEC_ARCH_SH (42 << 16) #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) +#define KEXEC_ARCH_AARCH64 (183 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 diff --git a/mm/memblock.c b/mm/memblock.c index f8fab45bfdb7..843c7d15fe53 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -822,6 +822,29 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); } +/** + * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return 0 on success, -errno on failure. + */ +int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP); +} + +/** + * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return 0 on success, -errno on failure. + */ +int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP); +} /** * __next_reserved_mem_region - next function for for_each_reserved_region() @@ -913,6 +936,10 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags, if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) continue; + /* skip nomap memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) + continue; + if (!type_b) { if (out_start) *out_start = m_start; @@ -1022,6 +1049,10 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags, if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) continue; + /* skip nomap memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) + continue; + if (!type_b) { if (out_start) *out_start = m_start; @@ -1467,15 +1498,16 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void) return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } -void __init memblock_enforce_memory_limit(phys_addr_t limit) +static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; struct memblock_region *r; - if (!limit) - return; - - /* find out max address */ + /* + * translate the memory @limit size into the max address within one of + * the memory memblock regions, if the @limit exceeds the total size + * of those regions, max_addr will keep original value ULLONG_MAX + */ for_each_memblock(memory, r) { if (limit <= r->size) { max_addr = r->base + limit; @@ -1484,6 +1516,22 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) limit -= r->size; } + return max_addr; +} + +void __init memblock_enforce_memory_limit(phys_addr_t limit) +{ + phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == (phys_addr_t)ULLONG_MAX) + return; + /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX); @@ -1491,6 +1539,50 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit) (phys_addr_t)ULLONG_MAX); } +void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) +{ + int start_rgn, end_rgn; + int i, ret; + + if (!size) + return; + + ret = memblock_isolate_range(&memblock.memory, base, size, + &start_rgn, &end_rgn); + if (ret) + return; + + /* remove all the MAP regions */ + for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) + if (!memblock_is_nomap(&memblock.memory.regions[i])) + memblock_remove_region(&memblock.memory, i); + + for (i = start_rgn - 1; i >= 0; i--) + if (!memblock_is_nomap(&memblock.memory.regions[i])) + memblock_remove_region(&memblock.memory, i); + + /* truncate the reserved regions */ + memblock_remove_range(&memblock.reserved, 0, base); + memblock_remove_range(&memblock.reserved, + base + size, (phys_addr_t)ULLONG_MAX); +} + +void __init memblock_mem_limit_remove_map(phys_addr_t limit) +{ + phys_addr_t max_addr; + + if (!limit) + return; + + max_addr = __find_max_addr(limit); + + /* @limit exceeds the total size of the memory, do nothing */ + if (max_addr == (phys_addr_t)ULLONG_MAX) + return; + + memblock_cap_memory_range(0, max_addr); +} + static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; @@ -1509,16 +1601,25 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr return -1; } -int __init memblock_is_reserved(phys_addr_t addr) +bool __init memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } -int __init_memblock memblock_is_memory(phys_addr_t addr) +bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } +int __init_memblock memblock_is_map_memory(phys_addr_t addr) +{ + int i = memblock_search(&memblock.memory, addr); + + if (i == -1) + return false; + return !memblock_is_nomap(&memblock.memory.regions[i]); +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) diff --git a/mm/slab.c b/mm/slab.c index 24a615d42d74..462938fc7cb9 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1670,6 +1670,14 @@ static void kmem_rcu_free(struct rcu_head *head) } #if DEBUG +static bool is_debug_pagealloc_cache(struct kmem_cache *cachep) +{ + if (debug_pagealloc_enabled() && OFF_SLAB(cachep) && + (cachep->size % PAGE_SIZE) == 0) + return true; + + return false; +} #ifdef CONFIG_DEBUG_PAGEALLOC static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, @@ -1703,6 +1711,23 @@ static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr, } *addr++ = 0x87654321; } + +static void slab_kernel_map(struct kmem_cache *cachep, void *objp, + int map, unsigned long caller) +{ + if (!is_debug_pagealloc_cache(cachep)) + return; + + if (caller) + store_stackinfo(cachep, objp, caller); + + kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map); +} + +#else +static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp, + int map, unsigned long caller) {} + #endif static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) @@ -1781,6 +1806,9 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) int size, i; int lines = 0; + if (is_debug_pagealloc_cache(cachep)) + return; + realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; @@ -1846,16 +1874,8 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, void *objp = index_to_obj(cachep, page, i); if (cachep->flags & SLAB_POISON) { -#ifdef CONFIG_DEBUG_PAGEALLOC - if (cachep->size % PAGE_SIZE == 0 && - OFF_SLAB(cachep)) - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 1); - else - check_poison_obj(cachep, objp); -#else check_poison_obj(cachep, objp); -#endif + slab_kernel_map(cachep, objp, 1, 0); } if (cachep->flags & SLAB_RED_ZONE) { if (*dbg_redzone1(cachep, objp) != RED_INACTIVE) @@ -2179,7 +2199,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) else size += BYTES_PER_WORD; } -#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC) /* * To activate debug pagealloc, off-slab management is necessary * requirement. In early phase of initialization, small sized slab @@ -2187,14 +2206,14 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) * to check size >= 256. It guarantees that all necessary small * sized slab is initialized in current slab initialization sequence. */ - if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) && + if (debug_pagealloc_enabled() && (flags & SLAB_POISON) && + !slab_early_init && size >= kmalloc_size(INDEX_NODE) && size >= 256 && cachep->object_size > cache_line_size() && ALIGN(size, cachep->align) < PAGE_SIZE) { cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align); size = PAGE_SIZE; } #endif -#endif /* * Determine if the slab management is 'on' or 'off' slab. @@ -2237,15 +2256,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) if (flags & CFLGS_OFF_SLAB) { /* really off slab. No need for manual alignment */ freelist_size = calculate_freelist_size(cachep->num, 0); - -#ifdef CONFIG_PAGE_POISONING - /* If we're going to use the generic kernel_map_pages() - * poisoning, then it's going to smash the contents of - * the redzone and userword anyhow, so switch them off. - */ - if (size % PAGE_SIZE == 0 && flags & SLAB_POISON) - flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); -#endif } cachep->colour_off = cache_line_size(); @@ -2261,7 +2271,19 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) cachep->size = size; cachep->reciprocal_buffer_size = reciprocal_value(size); - if (flags & CFLGS_OFF_SLAB) { +#if DEBUG + /* + * If we're going to use the generic kernel_map_pages() + * poisoning, then it's going to smash the contents of + * the redzone and userword anyhow, so switch them off. + */ + if (IS_ENABLED(CONFIG_PAGE_POISONING) && + (cachep->flags & SLAB_POISON) && + is_debug_pagealloc_cache(cachep)) + cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); +#endif + + if (OFF_SLAB(cachep)) { cachep->freelist_cache = kmalloc_slab(freelist_size, 0u); /* * This is a possibility for one of the kmalloc_{dma,}_caches. @@ -2488,9 +2510,6 @@ static void cache_init_objs(struct kmem_cache *cachep, for (i = 0; i < cachep->num; i++) { void *objp = index_to_obj(cachep, page, i); #if DEBUG - /* need to poison the objs? */ - if (cachep->flags & SLAB_POISON) - poison_obj(cachep, objp, POISON_FREE); if (cachep->flags & SLAB_STORE_USER) *dbg_userword(cachep, objp) = NULL; @@ -2514,10 +2533,11 @@ static void cache_init_objs(struct kmem_cache *cachep, slab_error(cachep, "constructor overwrote the" " start of an object"); } - if ((cachep->size % PAGE_SIZE) == 0 && - OFF_SLAB(cachep) && cachep->flags & SLAB_POISON) - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 0); + /* need to poison the objs? */ + if (cachep->flags & SLAB_POISON) { + poison_obj(cachep, objp, POISON_FREE); + slab_kernel_map(cachep, objp, 0, 0); + } #else if (cachep->ctor) cachep->ctor(objp); @@ -2736,17 +2756,8 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, set_obj_status(page, objnr, OBJECT_FREE); if (cachep->flags & SLAB_POISON) { -#ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) { - store_stackinfo(cachep, objp, caller); - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 0); - } else { - poison_obj(cachep, objp, POISON_FREE); - } -#else poison_obj(cachep, objp, POISON_FREE); -#endif + slab_kernel_map(cachep, objp, 0, caller); } return objp; } @@ -2873,15 +2884,8 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, if (!objp) return objp; if (cachep->flags & SLAB_POISON) { -#ifdef CONFIG_DEBUG_PAGEALLOC - if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) - kernel_map_pages(virt_to_page(objp), - cachep->size / PAGE_SIZE, 1); - else - check_poison_obj(cachep, objp); -#else check_poison_obj(cachep, objp); -#endif + slab_kernel_map(cachep, objp, 1, 0); poison_obj(cachep, objp, POISON_INUSE); } if (cachep->flags & SLAB_STORE_USER) |