diff options
Diffstat (limited to 'arch/arm64/kernel')
-rw-r--r-- | arch/arm64/kernel/Makefile | 1 | ||||
-rw-r--r-- | arch/arm64/kernel/armv8_deprecated.c | 11 | ||||
-rw-r--r-- | arch/arm64/kernel/asm-offsets.c | 13 | ||||
-rw-r--r-- | arch/arm64/kernel/cpufeature.c | 1 | ||||
-rw-r--r-- | arch/arm64/kernel/crash_dump.c | 71 | ||||
-rw-r--r-- | arch/arm64/kernel/entry.S | 110 | ||||
-rw-r--r-- | arch/arm64/kernel/head.S | 17 | ||||
-rw-r--r-- | arch/arm64/kernel/hibernate.c | 10 | ||||
-rw-r--r-- | arch/arm64/kernel/machine_kexec.c | 170 | ||||
-rw-r--r-- | arch/arm64/kernel/process.c | 36 | ||||
-rw-r--r-- | arch/arm64/kernel/return_address.c | 1 | ||||
-rw-r--r-- | arch/arm64/kernel/setup.c | 16 | ||||
-rw-r--r-- | arch/arm64/kernel/sleep.S | 3 | ||||
-rw-r--r-- | arch/arm64/kernel/smp.c | 82 | ||||
-rw-r--r-- | arch/arm64/kernel/stacktrace.c | 7 | ||||
-rw-r--r-- | arch/arm64/kernel/suspend.c | 6 | ||||
-rw-r--r-- | arch/arm64/kernel/traps.c | 28 | ||||
-rw-r--r-- | arch/arm64/kernel/vmlinux.lds.S | 5 |
18 files changed, 503 insertions, 85 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 7d66bba..6a7384e 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -50,6 +50,7 @@ arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.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/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index c0ede23..29d2ad8 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -14,7 +14,6 @@ #include <linux/slab.h> #include <linux/sysctl.h> -#include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/insn.h> #include <asm/opcodes.h> @@ -285,10 +284,10 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table) #define __SWP_LL_SC_LOOPS 4 #define __user_swpX_asm(data, addr, res, temp, temp2, B) \ +do { \ + uaccess_enable(); \ __asm__ __volatile__( \ " mov %w3, %w7\n" \ - ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ - CONFIG_ARM64_PAN) \ "0: ldxr"B" %w2, [%4]\n" \ "1: stxr"B" %w0, %w1, [%4]\n" \ " cbz %w0, 2f\n" \ @@ -306,13 +305,13 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table) " .popsection" \ _ASM_EXTABLE(0b, 4b) \ _ASM_EXTABLE(1b, 4b) \ - ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ - CONFIG_ARM64_PAN) \ : "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2) \ : "r" ((unsigned long)addr), "i" (-EAGAIN), \ "i" (-EFAULT), \ "i" (__SWP_LL_SC_LOOPS) \ - : "memory") + : "memory"); \ + uaccess_disable(); \ +} while (0) #define __user_swp_asm(data, addr, res, temp, temp2) \ __user_swpX_asm(data, addr, res, temp, temp2, "") diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index c58ddf8..b3bb7ef 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -36,11 +36,13 @@ int main(void) { DEFINE(TSK_ACTIVE_MM, offsetof(struct task_struct, active_mm)); BLANK(); - DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); - DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); - DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); - DEFINE(TI_TASK, offsetof(struct thread_info, task)); - DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); + DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); + DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); + DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit)); +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); +#endif + DEFINE(TSK_STACK, offsetof(struct task_struct, stack)); BLANK(); DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context)); BLANK(); @@ -123,6 +125,7 @@ int main(void) DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); BLANK(); DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); + DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 3a129d4..af5a1e3 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -47,6 +47,7 @@ unsigned int compat_elf_hwcap2 __read_mostly; #endif DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); +EXPORT_SYMBOL(cpu_hwcaps); DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS); EXPORT_SYMBOL(cpu_hwcap_keys); diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c new file mode 100644 index 0000000..f46d57c --- /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/entry.S b/arch/arm64/kernel/entry.S index b4c7db4..bab8334 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -29,6 +29,8 @@ #include <asm/esr.h> #include <asm/irq.h> #include <asm/memory.h> +#include <asm/ptrace.h> +#include <asm/uaccess.h> #include <asm/thread_info.h> #include <asm/asm-uaccess.h> #include <asm/unistd.h> @@ -91,9 +93,8 @@ .if \el == 0 mrs x21, sp_el0 - mov tsk, sp - and tsk, tsk, #~(THREAD_SIZE - 1) // Ensure MDSCR_EL1.SS is clear, - ldr x19, [tsk, #TI_FLAGS] // since we can unmask debug + ldr_this_cpu tsk, __entry_task, x20 // Ensure MDSCR_EL1.SS is clear, + ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug disable_step_tsk x19, x20 // exceptions when scheduling. mov x29, xzr // fp pointed to user-space @@ -101,15 +102,41 @@ add x21, sp, #S_FRAME_SIZE get_thread_info tsk /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ - ldr x20, [tsk, #TI_ADDR_LIMIT] + ldr x20, [tsk, #TSK_TI_ADDR_LIMIT] str x20, [sp, #S_ORIG_ADDR_LIMIT] mov x20, #TASK_SIZE_64 - str x20, [tsk, #TI_ADDR_LIMIT] + str x20, [tsk, #TSK_TI_ADDR_LIMIT] /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */ .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 stp lr, x21, [sp, #S_LR] + +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + /* + * Set the TTBR0 PAN bit in SPSR. When the exception is taken from + * EL0, there is no need to check the state of TTBR0_EL1 since + * accesses are always enabled. + * Note that the meaning of this bit differs from the ARMv8.1 PAN + * feature as all TTBR0_EL1 accesses are disabled, not just those to + * user mappings. + */ +alternative_if ARM64_HAS_PAN + b 1f // skip TTBR0 PAN +alternative_else_nop_endif + + .if \el != 0 + mrs x21, ttbr0_el1 + tst x21, #0xffff << 48 // Check for the reserved ASID + orr x23, x23, #PSR_PAN_BIT // Set the emulated PAN in the saved SPSR + b.eq 1f // TTBR0 access already disabled + and x23, x23, #~PSR_PAN_BIT // Clear the emulated PAN in the saved SPSR + .endif + + __uaccess_ttbr0_disable x21 +1: +#endif + stp x22, x23, [sp, #S_PC] /* @@ -140,7 +167,7 @@ .if \el != 0 /* Restore the task's original addr_limit. */ ldr x20, [sp, #S_ORIG_ADDR_LIMIT] - str x20, [tsk, #TI_ADDR_LIMIT] + str x20, [tsk, #TSK_TI_ADDR_LIMIT] /* No need to restore UAO, it will be restored from SPSR_EL1 */ .endif @@ -148,6 +175,40 @@ ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter + .endif + +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + /* + * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR + * PAN bit checking. + */ +alternative_if ARM64_HAS_PAN + b 2f // skip TTBR0 PAN +alternative_else_nop_endif + + .if \el != 0 + tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set + .endif + + __uaccess_ttbr0_enable x0 + + .if \el == 0 + /* + * Enable errata workarounds only if returning to user. The only + * workaround currently required for TTBR0_EL1 changes are for the + * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache + * corruption). + */ + post_ttbr0_update_workaround + .endif +1: + .if \el != 0 + and x22, x22, #~PSR_PAN_BIT // ARMv8.0 CPUs do not understand this bit + .endif +2: +#endif + + .if \el == 0 ldr x23, [sp, #S_SP] // load return stack pointer msr sp_el0, x23 #ifdef CONFIG_ARM64_ERRATUM_845719 @@ -163,6 +224,7 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif .endif + msr elr_el1, x21 // set up the return data msr spsr_el1, x22 ldp x0, x1, [sp, #16 * 0] @@ -185,23 +247,20 @@ alternative_else_nop_endif eret // return to kernel .endm - .macro get_thread_info, rd - mrs \rd, sp_el0 - .endm - .macro irq_stack_entry mov x19, sp // preserve the original sp /* - * Compare sp with the current thread_info, if the top - * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and - * should switch to the irq stack. + * Compare sp with the base of the task stack. + * If the top ~(THREAD_SIZE - 1) bits match, we are on a task stack, + * and should switch to the irq stack. */ - and x25, x19, #~(THREAD_SIZE - 1) - cmp x25, tsk - b.ne 9998f + ldr x25, [tsk, TSK_STACK] + eor x25, x25, x19 + and x25, x25, #~(THREAD_SIZE - 1) + cbnz x25, 9998f - this_cpu_ptr irq_stack, x25, x26 + adr_this_cpu x25, irq_stack, x26 mov x26, #IRQ_STACK_START_SP add x26, x25, x26 @@ -429,9 +488,9 @@ el1_irq: irq_handler #ifdef CONFIG_PREEMPT - ldr w24, [tsk, #TI_PREEMPT] // get preempt count + ldr w24, [tsk, #TSK_TI_PREEMPT] // get preempt count cbnz w24, 1f // preempt count != 0 - ldr x0, [tsk, #TI_FLAGS] // get flags + ldr x0, [tsk, #TSK_TI_FLAGS] // get flags tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? bl el1_preempt 1: @@ -446,7 +505,7 @@ ENDPROC(el1_irq) el1_preempt: mov x24, lr 1: bl preempt_schedule_irq // irq en/disable is done inside - ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS + ldr x0, [tsk, #TSK_TI_FLAGS] // get new tasks TI_FLAGS tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ret x24 #endif @@ -676,8 +735,7 @@ ENTRY(cpu_switch_to) ldp x29, x9, [x8], #16 ldr lr, [x8] mov sp, x9 - and x9, x9, #~(THREAD_SIZE - 1) - msr sp_el0, x9 + msr sp_el0, x1 ret ENDPROC(cpu_switch_to) @@ -688,7 +746,7 @@ ENDPROC(cpu_switch_to) ret_fast_syscall: disable_irq // disable interrupts str x0, [sp, #S_X0] // returned x0 - ldr x1, [tsk, #TI_FLAGS] // re-check for syscall tracing + ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for syscall tracing and x2, x1, #_TIF_SYSCALL_WORK cbnz x2, ret_fast_syscall_trace and x2, x1, #_TIF_WORK_MASK @@ -708,14 +766,14 @@ work_pending: #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_on // enabled while in userspace #endif - ldr x1, [tsk, #TI_FLAGS] // re-check for single-step + ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step b finish_ret_to_user /* * "slow" syscall return path. */ ret_to_user: disable_irq // disable interrupts - ldr x1, [tsk, #TI_FLAGS] + ldr x1, [tsk, #TSK_TI_FLAGS] and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending finish_ret_to_user: @@ -748,7 +806,7 @@ el0_svc_naked: // compat entry point enable_dbg_and_irq ct_user_exit 1 - ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks + ldr x16, [tsk, #TSK_TI_FLAGS] // check for syscall hooks tst x16, #_TIF_SYSCALL_WORK b.ne __sys_trace cmp scno, sc_nr // check upper syscall limit diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 332e331..7ee6d74 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -326,14 +326,14 @@ __create_page_tables: * dirty cache lines being evicted. */ adrp x0, idmap_pg_dir - adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE bl __inval_cache_range /* * Clear the idmap and swapper page tables. */ adrp x0, idmap_pg_dir - adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE + adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE 1: stp xzr, xzr, [x0], #16 stp xzr, xzr, [x0], #16 stp xzr, xzr, [x0], #16 @@ -412,7 +412,7 @@ __create_page_tables: * tables again to remove any speculatively loaded cache lines. */ adrp x0, idmap_pg_dir - adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE dmb sy bl __inval_cache_range @@ -428,7 +428,8 @@ ENDPROC(__create_page_tables) __primary_switched: adrp x4, init_thread_union add sp, x4, #THREAD_SIZE - msr sp_el0, x4 // Save thread_info + adr_l x5, init_task + msr sp_el0, x5 // Save thread_info adr_l x8, vectors // load VBAR_EL1 with virtual msr vbar_el1, x8 // vector table address @@ -699,10 +700,10 @@ __secondary_switched: isb 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 + ldr x1, [x0, #CPU_BOOT_STACK] // get secondary_data.stack + mov sp, x1 + ldr x2, [x0, #CPU_BOOT_TASK] + msr sp_el0, x2 mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index d55a7b0..4b10dc1 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -28,6 +28,7 @@ #include <asm/cacheflush.h> #include <asm/cputype.h> #include <asm/irqflags.h> +#include <asm/kexec.h> #include <asm/memory.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> @@ -105,7 +106,8 @@ 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) @@ -289,6 +291,9 @@ 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(); + sleep_cpu = smp_processor_id(); ret = swsusp_save(); } else { @@ -300,6 +305,9 @@ int swsusp_arch_suspend(void) if (el2_reset_needed()) dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end); + /* 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/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index bc96c8a..481f54a 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -9,12 +9,19 @@ * 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" @@ -22,8 +29,6 @@ extern const unsigned char arm64_relocate_new_kernel[]; extern const unsigned long arm64_relocate_new_kernel_size; -static unsigned long kimage_start; - /** * kexec_image_info - For debugging output. */ @@ -64,8 +69,6 @@ void machine_kexec_cleanup(struct kimage *kimage) */ int machine_kexec_prepare(struct kimage *kimage) { - kimage_start = kimage->start; - kexec_image_info(kimage); if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) { @@ -144,11 +147,15 @@ 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(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1)); + 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); @@ -183,7 +190,7 @@ void machine_kexec(struct kimage *kimage) kexec_list_flush(kimage); /* Flush the new image if already in place. */ - if (kimage->head & IND_DONE) + if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE)) kexec_segment_flush(kimage); pr_info("Bye!\n"); @@ -200,13 +207,158 @@ void machine_kexec(struct kimage *kimage) * relocation is complete. */ - cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, - kimage_start, 0); + 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) { - /* Empty routine needed to avoid build errors. */ + 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/process.c b/arch/arm64/kernel/process.c index 01753cd..a98b743 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -45,6 +45,7 @@ #include <linux/personality.h> #include <linux/notifier.h> #include <trace/events/power.h> +#include <linux/percpu.h> #include <asm/alternative.h> #include <asm/compat.h> @@ -322,6 +323,20 @@ void uao_thread_switch(struct task_struct *next) } /* + * We store our current task in sp_el0, which is clobbered by userspace. Keep a + * shadow copy so that we can restore this upon entry from userspace. + * + * This is *only* for exception entry from EL0, and is not valid until we + * __switch_to() a user task. + */ +DEFINE_PER_CPU(struct task_struct *, __entry_task); + +static void entry_task_switch(struct task_struct *next) +{ + __this_cpu_write(__entry_task, next); +} + +/* * Thread switching. */ struct task_struct *__switch_to(struct task_struct *prev, @@ -333,6 +348,7 @@ struct task_struct *__switch_to(struct task_struct *prev, tls_thread_switch(next); hw_breakpoint_thread_switch(next); contextidr_thread_switch(next); + entry_task_switch(next); uao_thread_switch(next); /* @@ -350,27 +366,35 @@ struct task_struct *__switch_to(struct task_struct *prev, unsigned long get_wchan(struct task_struct *p) { struct stackframe frame; - unsigned long stack_page; + unsigned long stack_page, ret = 0; int count = 0; if (!p || p == current || p->state == TASK_RUNNING) return 0; + stack_page = (unsigned long)try_get_task_stack(p); + if (!stack_page) + return 0; + frame.fp = thread_saved_fp(p); frame.sp = thread_saved_sp(p); frame.pc = thread_saved_pc(p); #ifdef CONFIG_FUNCTION_GRAPH_TRACER frame.graph = p->curr_ret_stack; #endif - stack_page = (unsigned long)task_stack_page(p); do { if (frame.sp < stack_page || frame.sp >= stack_page + THREAD_SIZE || unwind_frame(p, &frame)) - return 0; - if (!in_sched_functions(frame.pc)) - return frame.pc; + goto out; + if (!in_sched_functions(frame.pc)) { + ret = frame.pc; + goto out; + } } while (count ++ < 16); - return 0; + +out: + put_task_stack(p); + return ret; } unsigned long arch_align_stack(unsigned long sp) diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index 1718706..12a87f2 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -12,6 +12,7 @@ #include <linux/export.h> #include <linux/ftrace.h> +#include <asm/stack_pointer.h> #include <asm/stacktrace.h> struct return_address_data { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index f534f49..e4e2a5a 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> @@ -224,6 +223,12 @@ 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 } } @@ -291,6 +296,15 @@ void __init setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash(); +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + /* + * Make sure init_thread_info.ttbr0 always generates translation + * faults in case uaccess_enable() is inadvertently called by the init + * thread. + */ + init_task.thread_info.ttbr0 = virt_to_phys(empty_zero_page); +#endif + #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) conswitchp = &vga_con; diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 1bec41b..df67652 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -125,9 +125,6 @@ ENTRY(_cpu_resume) /* load sp from context */ ldr x2, [x0, #CPU_CTX_SP] mov sp, x2 - /* save thread_info */ - and x2, x2, #~(THREAD_SIZE - 1) - msr sp_el0, x2 /* * cpu_do_resume expects x0 to contain context address pointer */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 8507703..11f2890 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> @@ -58,6 +59,9 @@ #define CREATE_TRACE_POINTS #include <trace/events/ipi.h> +DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number); +EXPORT_PER_CPU_SYMBOL(cpu_number); + /* * as from 2.5, kernels no longer have an init_tasks structure * so we need some other way of telling a new secondary core @@ -71,6 +75,7 @@ enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, IPI_TIMER, IPI_IRQ_WORK, IPI_WAKEUP @@ -146,6 +151,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * We need to tell the secondary core where to find its stack and the * page tables. */ + secondary_data.task = idle; 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)); @@ -170,6 +176,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_err("CPU%u: failed to boot: %d\n", cpu, ret); } + secondary_data.task = NULL; secondary_data.stack = NULL; status = READ_ONCE(secondary_data.status); if (ret && status) { @@ -208,7 +215,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) asmlinkage void secondary_start_kernel(void) { struct mm_struct *mm = &init_mm; - unsigned int cpu = smp_processor_id(); + unsigned int cpu; + + cpu = task_cpu(current); + set_my_cpu_offset(per_cpu_offset(cpu)); /* * All kernel threads share the same mm context; grab a @@ -217,8 +227,6 @@ asmlinkage void secondary_start_kernel(void) atomic_inc(&mm->mm_count); current->active_mm = mm; - set_my_cpu_offset(per_cpu_offset(smp_processor_id())); - /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. @@ -718,6 +726,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) */ for_each_possible_cpu(cpu) { + per_cpu(cpu_number, cpu) = cpu; + if (cpu == smp_processor_id()) continue; @@ -745,6 +755,7 @@ 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"), @@ -819,6 +830,29 @@ 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 */ @@ -849,6 +883,15 @@ 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(); @@ -921,6 +964,39 @@ void smp_send_stop(void) cpumask_pr_args(cpu_online_mask)); } +#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 */ diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index c2efddf..8a552a3 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -22,6 +22,7 @@ #include <linux/stacktrace.h> #include <asm/irq.h> +#include <asm/stack_pointer.h> #include <asm/stacktrace.h> /* @@ -128,7 +129,6 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, break; } } -EXPORT_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { @@ -181,6 +181,9 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) struct stack_trace_data data; struct stackframe frame; + if (!try_get_task_stack(tsk)) + return; + data.trace = trace; data.skip = trace->skip; @@ -202,6 +205,8 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) walk_stackframe(tsk, &frame, save_trace, &data); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; + + put_task_stack(tsk); } void save_stack_trace(struct stack_trace *trace) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index bb0cd78..1e3be90 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -47,12 +47,6 @@ void notrace __cpu_suspend_exit(void) cpu_uninstall_idmap(); /* - * Restore per-cpu offset before any kernel - * subsystem relying on it has a chance to run. - */ - set_my_cpu_offset(per_cpu_offset(cpu)); - - /* * PSTATE was not saved over suspend/resume, re-enable any detected * features that might not have been set correctly. */ diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index f228261..7501b40 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -38,6 +38,7 @@ #include <asm/esr.h> #include <asm/insn.h> #include <asm/traps.h> +#include <asm/stack_pointer.h> #include <asm/stacktrace.h> #include <asm/exception.h> #include <asm/system_misc.h> @@ -147,6 +148,9 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) if (!tsk) tsk = current; + if (!try_get_task_stack(tsk)) + return; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -212,6 +216,8 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) stack + sizeof(struct pt_regs)); } } + + put_task_stack(tsk); } void show_stack(struct task_struct *tsk, unsigned long *sp) @@ -227,10 +233,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) #endif #define S_SMP " SMP" -static int __die(const char *str, int err, struct thread_info *thread, - struct pt_regs *regs) +static int __die(const char *str, int err, struct pt_regs *regs) { - struct task_struct *tsk = thread->task; + struct task_struct *tsk = current; static int die_counter; int ret; @@ -245,7 +250,8 @@ static int __die(const char *str, int err, struct thread_info *thread, print_modules(); __show_regs(regs); pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", - TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1); + TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), + end_of_stack(tsk)); if (!user_mode(regs)) { dump_mem(KERN_EMERG, "Stack: ", regs->sp, @@ -264,7 +270,6 @@ static DEFINE_RAW_SPINLOCK(die_lock); */ void die(const char *str, struct pt_regs *regs, int err) { - struct thread_info *thread = current_thread_info(); int ret; oops_enter(); @@ -272,9 +277,9 @@ void die(const char *str, struct pt_regs *regs, int err) raw_spin_lock_irq(&die_lock); console_verbose(); bust_spinlocks(1); - ret = __die(str, err, thread, regs); + ret = __die(str, err, regs); - if (regs && kexec_should_crash(thread->task)) + if (regs && kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); @@ -435,9 +440,10 @@ int cpu_enable_cache_maint_trap(void *__unused) } #define __user_cache_maint(insn, address, res) \ - if (address >= user_addr_max()) \ + if (address >= user_addr_max()) { \ res = -EFAULT; \ - else \ + } else { \ + uaccess_ttbr0_enable(); \ asm volatile ( \ "1: " insn ", %1\n" \ " mov %w0, #0\n" \ @@ -449,7 +455,9 @@ int cpu_enable_cache_maint_trap(void *__unused) " .popsection\n" \ _ASM_EXTABLE(1b, 3b) \ : "=r" (res) \ - : "r" (address), "i" (-EFAULT) ) + : "r" (address), "i" (-EFAULT)); \ + uaccess_ttbr0_disable(); \ + } static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) { diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 1105aab..b8deffa 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -216,6 +216,11 @@ SECTIONS swapper_pg_dir = .; . += SWAPPER_DIR_SIZE; +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + reserved_ttbr0 = .; + . += RESERVED_TTBR0_SIZE; +#endif + _end = .; STABS_DEBUG |