diff options
author | Mark Brown <broonie@kernel.org> | 2015-01-23 20:36:05 +0000 |
---|---|---|
committer | Mark Brown <broonie@kernel.org> | 2015-01-23 20:36:05 +0000 |
commit | 15f82fce54b86e159fe5a1d41dcdc89e12b26459 (patch) | |
tree | c42632581244e8428e0623c5f11cd81b983d2eed | |
parent | f1326e0892329b0d58dec467f71f5d94c4d5d5a9 (diff) | |
parent | 9698ac7c353d6f22100c9fa24a830cae6a466cb4 (diff) |
Merge remote-tracking branch 'lsk/v3.10/topic/arm64-misc' into linux-linaro-lsklsk-v3.10-15.01
Conflicts:
arch/arm64/include/asm/proc-fns.h
arch/arm64/kernel/debug-monitors.c
arch/arm64/kernel/psci.c
30 files changed, 442 insertions, 136 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index d64c1a0e9dd0..2cf752060a41 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -18,6 +18,7 @@ config ARM64 select COMMON_CLK select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS + select GENERIC_ALLOCATOR select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CPU_AUTOPROBE diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index e1b0c4601b3e..bb55717c8dad 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -44,4 +44,15 @@ config PID_IN_CONTEXTIDR instructions during context switch. Say Y here only if you are planning to use hardware trace tools with this kernel. +config DEBUG_SET_MODULE_RONX + bool "Set loadable kernel module data as NX and text as RO" + depends on MODULES + help + This option helps catch unintended modifications to loadable + kernel module's text and read-only data. It also prevents execution + of module data. Such protection may interfere with run-time code + patching and dynamic kernel tracing - and they might also protect + against certain classes of kernel exploits. + If in doubt, say "N". + endmenu diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 8a311839e2d7..3e7882c4e034 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -38,7 +38,11 @@ CHECKFLAGS += -D__aarch64__ head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. +ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) +TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}') +else TEXT_OFFSET := 0x00080000 +endif export TEXT_OFFSET GZFLAGS diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index f2defe1c380c..689b6379188c 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -148,4 +148,8 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { } +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); #endif diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 27f54a7cc81b..ec5e41c23429 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -36,15 +36,34 @@ __val; \ }) +#define MIDR_REVISION_MASK 0xf +#define MIDR_REVISION(midr) ((midr) & MIDR_REVISION_MASK) +#define MIDR_PARTNUM_SHIFT 4 +#define MIDR_PARTNUM_MASK (0xfff << MIDR_PARTNUM_SHIFT) +#define MIDR_PARTNUM(midr) \ + (((midr) & MIDR_PARTNUM_MASK) >> MIDR_PARTNUM_SHIFT) +#define MIDR_ARCHITECTURE_SHIFT 16 +#define MIDR_ARCHITECTURE_MASK (0xf << MIDR_ARCHITECTURE_SHIFT) +#define MIDR_ARCHITECTURE(midr) \ + (((midr) & MIDR_ARCHITECTURE_MASK) >> MIDR_ARCHITECTURE_SHIFT) +#define MIDR_VARIANT_SHIFT 20 +#define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) +#define MIDR_VARIANT(midr) \ + (((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT) +#define MIDR_IMPLEMENTOR_SHIFT 24 +#define MIDR_IMPLEMENTOR_MASK (0xff << MIDR_IMPLEMENTOR_SHIFT) +#define MIDR_IMPLEMENTOR(midr) \ + (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) + #define ARM_CPU_IMP_ARM 0x41 #define ARM_CPU_IMP_APM 0x50 -#define ARM_CPU_PART_AEM_V8 0xD0F0 -#define ARM_CPU_PART_FOUNDATION 0xD000 -#define ARM_CPU_PART_CORTEX_A53 0xD030 -#define ARM_CPU_PART_CORTEX_A57 0xD070 +#define ARM_CPU_PART_AEM_V8 0xD0F +#define ARM_CPU_PART_FOUNDATION 0xD00 +#define ARM_CPU_PART_CORTEX_A57 0xD07 +#define ARM_CPU_PART_CORTEX_A53 0xD03 -#define APM_CPU_PART_POTENZA 0x0000 +#define APM_CPU_PART_POTENZA 0x000 #ifndef __ASSEMBLY__ @@ -65,12 +84,12 @@ static inline u64 __attribute_const__ read_cpuid_mpidr(void) static inline unsigned int __attribute_const__ read_cpuid_implementor(void) { - return (read_cpuid_id() & 0xFF000000) >> 24; + return MIDR_IMPLEMENTOR(read_cpuid_id()); } static inline unsigned int __attribute_const__ read_cpuid_part_number(void) { - return (read_cpuid_id() & 0xFFF0); + return MIDR_PARTNUM(read_cpuid_id()); } static inline u32 __attribute_const__ read_cpuid_cachetype(void) diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index a6331e6a92b5..e84ca637af6b 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -33,11 +33,11 @@ /* * The idmap and swapper page tables need some space reserved in the kernel - * image. The idmap only requires a pgd and a next level table to (section) map - * the kernel, while the swapper also maps the FDT and requires an additional - * table to map an early UART. See __create_page_tables for more information. + * image. Both require a pgd and a next level table to (section) map the + * kernel. The the swapper also maps the FDT (see __create_page_tables for + * more information). */ -#define SWAPPER_DIR_SIZE (3 * PAGE_SIZE) +#define SWAPPER_DIR_SIZE (2 * PAGE_SIZE) #define IDMAP_DIR_SIZE (2 * PAGE_SIZE) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 453a179469a3..5279e5733386 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -26,13 +26,13 @@ static inline void set_my_cpu_offset(unsigned long off) static inline unsigned long __my_cpu_offset(void) { unsigned long off; - register unsigned long *sp asm ("sp"); /* * We want to allow caching the value, so avoid using volatile and * instead use a fake stack read to hazard against barrier(). */ - asm("mrs %0, tpidr_el1" : "=r" (off) : "Q" (*sp)); + asm("mrs %0, tpidr_el1" : "=r" (off) : + "Q" (*(const unsigned long *)current_stack_pointer)); return off; } diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7099e3b84778..d86b4d4df1f0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -141,46 +141,51 @@ extern struct page *empty_zero_page; #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -static inline pte_t pte_wrprotect(pte_t pte) +static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { - pte_val(pte) &= ~PTE_WRITE; + pte_val(pte) &= ~pgprot_val(prot); return pte; } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) { - pte_val(pte) |= PTE_WRITE; + pte_val(pte) |= pgprot_val(prot); return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_WRITE)); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_WRITE)); +} + static inline pte_t pte_mkclean(pte_t pte) { - pte_val(pte) &= ~PTE_DIRTY; - return pte; + return clear_pte_bit(pte, __pgprot(PTE_DIRTY)); } static inline pte_t pte_mkdirty(pte_t pte) { - pte_val(pte) |= PTE_DIRTY; - return pte; + return set_pte_bit(pte, __pgprot(PTE_DIRTY)); } static inline pte_t pte_mkold(pte_t pte) { - pte_val(pte) &= ~PTE_AF; - return pte; + return clear_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkyoung(pte_t pte) { - pte_val(pte) |= PTE_AF; - return pte; + return set_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkspecial(pte_t pte) { - pte_val(pte) |= PTE_SPECIAL; - return pte; + return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } static inline void set_pte(pte_t *ptep, pte_t pte) diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h index 0c657bb54597..0d3b0b17e927 100644 --- a/arch/arm64/include/asm/proc-fns.h +++ b/arch/arm64/include/asm/proc-fns.h @@ -34,6 +34,8 @@ extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr); extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); +void cpu_soft_restart(phys_addr_t cpu_reset, + unsigned long addr) __attribute__((noreturn)); #include <asm/memory.h> diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 349448c0caeb..001b764fffa1 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -137,7 +137,7 @@ extern struct task_struct *cpu_switch_to(struct task_struct *prev, ((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1) #define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc) -#define KSTK_ESP(tsk) ((unsigned long)task_pt_regs(tsk)->sp) +#define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk)) /* * Prefetching support diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index 1be62bcb9d47..74a9d301819f 100644 --- a/arch/arm64/include/asm/sparsemem.h +++ b/arch/arm64/include/asm/sparsemem.h @@ -17,7 +17,7 @@ #define __ASM_SPARSEMEM_H #ifdef CONFIG_SPARSEMEM -#define MAX_PHYSMEM_BITS 40 +#define MAX_PHYSMEM_BITS 48 #define SECTION_SIZE_BITS 30 #endif diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 59f151f8241d..70dd1ac01f16 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -69,14 +69,19 @@ struct thread_info { #define init_stack (init_thread_union.stack) /* + * how to get the current stack pointer from C + */ +register unsigned long current_stack_pointer asm ("sp"); + +/* * how to get the thread information struct from C */ static inline struct thread_info *current_thread_info(void) __attribute_const__; static inline struct thread_info *current_thread_info(void) { - register unsigned long sp asm ("sp"); - return (struct thread_info *)(sp & ~(THREAD_SIZE - 1)); + return (struct thread_info *) + (current_stack_pointer & ~(THREAD_SIZE - 1)); } #define thread_saved_pc(tsk) \ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 3796ea6bb734..73f0ce570fb3 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -98,8 +98,8 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, dsb(ish); } -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +static inline void __flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) { unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48; unsigned long addr; @@ -112,7 +112,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, dsb(ish); } -static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) +static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long end) { unsigned long addr; start >>= 12; @@ -126,6 +126,29 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end } /* + * This is meant to avoid soft lock-ups on large TLB flushing ranges and not + * necessarily a performance improvement. + */ +#define MAX_TLB_RANGE (1024UL << PAGE_SHIFT) + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if ((end - start) <= MAX_TLB_RANGE) + __flush_tlb_range(vma, start, end); + else + flush_tlb_mm(vma->vm_mm); +} + +static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + if ((end - start) <= MAX_TLB_RANGE) + __flush_tlb_kernel_range(start, end); + else + flush_tlb_all(); +} + +/* * On AArch64, the cache coherency is handled via the set_pte_at() function. */ static inline void update_mmu_cache(struct vm_area_struct *vma, diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c index 04efea8fe4bc..24fb449bc6aa 100644 --- a/arch/arm64/kernel/cpu_ops.c +++ b/arch/arm64/kernel/cpu_ops.c @@ -30,8 +30,8 @@ const struct cpu_operations *cpu_ops[NR_CPUS]; static const struct cpu_operations *supported_cpu_ops[] __initconst = { #ifdef CONFIG_SMP &smp_spin_table_ops, - &cpu_psci_ops, #endif + &cpu_psci_ops, NULL, }; diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index b33051d501e6..e3b37ee9076a 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -303,20 +303,20 @@ static int brk_handler(unsigned long addr, unsigned int esr, { siginfo_t info; - if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED) - return 0; + if (user_mode(regs)) { + info = (siginfo_t) { + .si_signo = SIGTRAP, + .si_errno = 0, + .si_code = TRAP_BRKPT, + .si_addr = (void __user *)instruction_pointer(regs), + }; - if (!user_mode(regs)) + force_sig_info(SIGTRAP, &info, current); + } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) { + pr_warning("Unexpected kernel BRK exception at EL1\n"); return -EFAULT; + } - info = (siginfo_t) { - .si_signo = SIGTRAP, - .si_errno = 0, - .si_code = TRAP_BRKPT, - .si_addr = (void __user *)instruction_pointer(regs), - }; - - force_sig_info(SIGTRAP, &info, current); return 0; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 50e0cc849b8e..6254f4a28eed 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -38,8 +38,12 @@ #define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET) -#if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000 -#error KERNEL_RAM_VADDR must start at 0xXXX80000 +#if (TEXT_OFFSET & 0xfff) != 0 +#error TEXT_OFFSET must be at least 4KB aligned +#elif (PAGE_OFFSET & 0x1fffff) != 0 +#error PAGE_OFFSET must be at least 2MB aligned +#elif TEXT_OFFSET > 0x1fffff +#error TEXT_OFFSET must be less than 2MB #endif .macro pgtbl, ttb0, ttb1, virt_to_phys @@ -368,10 +372,6 @@ ENTRY(__boot_cpu_mode) .long 0 .popsection - .align 3 -2: .quad . - .quad PAGE_OFFSET - #ifdef CONFIG_SMP .align 3 1: .quad . @@ -597,13 +597,6 @@ __create_page_tables: create_block_map x0, x7, x3, x5, x6 1: /* - * Create the pgd entry for the fixed mappings. - */ - ldr x5, =FIXADDR_TOP // Fixed mapping virtual address - add x0, x26, #2 * PAGE_SIZE // section table address - create_pgd_entry x26, x0, x5, x6, x7 - - /* * Since the page tables have been populated with non-cacheable * accesses (MMU disabled), invalidate the idmap and swapper page * tables again to remove any speculatively loaded cache lines. diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 473e5dbf8f39..dfa6e3e74fdd 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -105,7 +105,7 @@ static bool migrate_one_irq(struct irq_desc *desc) c = irq_data_get_irq_chip(d); if (!c->irq_set_affinity) pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret) + else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) cpumask_copy(d->affinity, affinity); return ret; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 150134bf8738..a82af49bcc51 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -58,36 +58,10 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif -static void setup_restart(void) -{ - /* - * Tell the mm system that we are going to reboot - - * we may need it to insert some 1:1 mappings so that - * soft boot works. - */ - setup_mm_for_reboot(); - - /* Clean and invalidate caches */ - flush_cache_all(); - - /* Turn D-cache off */ - cpu_cache_off(); - - /* Push out any further dirty data, and ensure cache is empty */ - flush_cache_all(); -} - void soft_restart(unsigned long addr) { - typedef void (*phys_reset_t)(unsigned long); - phys_reset_t phys_reset; - - setup_restart(); - - /* Switch to the identity mapping */ - phys_reset = (phys_reset_t)virt_to_phys(cpu_reset); - phys_reset(addr); - + setup_mm_for_reboot(); + cpu_soft_restart(virt_to_phys(cpu_reset), addr); /* Should never get here */ BUG(); } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index e58a67974f98..4d827dd62199 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -251,7 +251,7 @@ static void psci_sys_poweroff(void) * PSCI Function IDs for v0.2+ are well defined so use * standard values. */ -static int psci_0_2_init(struct device_node *np) +static int __init psci_0_2_init(struct device_node *np) { int err, ver; @@ -312,7 +312,7 @@ out_put_node: /* * PSCI < v0.2 get PSCI Function IDs via DT. */ -static int psci_0_1_init(struct device_node *np) +static int __init psci_0_1_init(struct device_node *np) { u32 id; int err; @@ -450,6 +450,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu) return 0; } #endif +#endif #ifdef CONFIG_ARM64_CPU_SUSPEND static int cpu_psci_cpu_suspend(unsigned long index) @@ -465,6 +466,7 @@ static int cpu_psci_cpu_suspend(unsigned long index) const struct cpu_operations cpu_psci_ops = { .name = "psci", +#ifdef CONFIG_SMP .cpu_init = cpu_psci_cpu_init, .cpu_prepare = cpu_psci_cpu_prepare, .cpu_boot = cpu_psci_cpu_boot, @@ -473,9 +475,9 @@ const struct cpu_operations cpu_psci_ops = { .cpu_die = cpu_psci_cpu_die, .cpu_kill = cpu_psci_cpu_kill, #endif +#endif #ifdef CONFIG_ARM64_CPU_SUSPEND .cpu_suspend = cpu_psci_cpu_suspend, #endif }; -#endif diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 8ba6b0fa1753..5cafe0e40cfa 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -660,8 +660,10 @@ static int compat_gpr_get(struct task_struct *target, kbuf += sizeof(reg); } else { ret = copy_to_user(ubuf, ®, sizeof(reg)); - if (ret) + if (ret) { + ret = -EFAULT; break; + } ubuf += sizeof(reg); } @@ -699,8 +701,10 @@ static int compat_gpr_set(struct task_struct *target, kbuf += sizeof(reg); } else { ret = copy_from_user(®, ubuf, sizeof(reg)); - if (ret) - return ret; + if (ret) { + ret = -EFAULT; + break; + } ubuf += sizeof(reg); } diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 55437ba1f5a4..407991bf79f5 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -111,10 +111,9 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) frame.sp = thread_saved_sp(tsk); frame.pc = thread_saved_pc(tsk); } else { - register unsigned long current_sp asm("sp"); data.no_sched_functions = 0; frame.fp = (unsigned long)__builtin_frame_address(0); - frame.sp = current_sp; + frame.sp = current_stack_pointer; frame.pc = (unsigned long)save_stack_trace_tsk; } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 7ffadddb645d..12cd34ff35d0 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -132,7 +132,6 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; - const register unsigned long current_sp asm ("sp"); pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); @@ -145,7 +144,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.pc = regs->pc; } else if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); - frame.sp = current_sp; + frame.sp = current_stack_pointer; frame.pc = (unsigned long)dump_backtrace; } else { /* @@ -156,7 +155,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.pc = thread_saved_pc(tsk); } - printk("Call trace:\n"); + pr_emerg("Call trace:\n"); while (1) { unsigned long where = frame.pc; int ret; @@ -328,17 +327,17 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) void __pte_error(const char *file, int line, unsigned long val) { - printk("%s:%d: bad pte %016lx.\n", file, line, val); + pr_crit("%s:%d: bad pte %016lx.\n", file, line, val); } void __pmd_error(const char *file, int line, unsigned long val) { - printk("%s:%d: bad pmd %016lx.\n", file, line, val); + pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val); } void __pgd_error(const char *file, int line, unsigned long val) { - printk("%s:%d: bad pgd %016lx.\n", file, line, val); + pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val); } void __init trap_init(void) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 84b942612051..ff3bddea482d 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -43,7 +43,7 @@ $(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Assembly rules for the .S files -$(obj-vdso): %.o: %.S +$(obj-vdso): %.o: %.S FORCE $(call if_changed_dep,vdsoas) # Actual build commands diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 3ecb56c624d3..c56179ed2c09 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -1,5 +1,5 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ cache.o copypage.o flush.o \ ioremap.o mmap.o pgd.o mmu.o \ - context.o proc.o + context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index f39a55d58918..eeb1cf3ff299 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/export.h> #include <linux/slab.h> +#include <linux/genalloc.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/of.h> @@ -43,6 +44,54 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, return prot; } +static struct gen_pool *atomic_pool; + +#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K +static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE; + +static int __init early_coherent_pool(char *p) +{ + atomic_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +static void *__alloc_from_pool(size_t size, struct page **ret_page) +{ + unsigned long val; + void *ptr = NULL; + + if (!atomic_pool) { + WARN(1, "coherent pool not initialised!\n"); + return NULL; + } + + val = gen_pool_alloc(atomic_pool, size); + if (val) { + phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); + + *ret_page = phys_to_page(phys); + ptr = (void *)val; + } + + return ptr; +} + +static bool __in_atomic_pool(void *start, size_t size) +{ + return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); +} + +static int __free_from_pool(void *start, size_t size) +{ + if (!__in_atomic_pool(start, size)) + return 0; + + gen_pool_free(atomic_pool, (unsigned long)start, size); + + return 1; +} + static void *__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) @@ -50,7 +99,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (IS_ENABLED(CONFIG_DMA_CMA)) { + if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) { struct page *page; size = PAGE_ALIGN(size); @@ -70,50 +119,54 @@ static void __dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs) { + bool freed; + phys_addr_t paddr = dma_to_phys(dev, dma_handle); + if (dev == NULL) { WARN_ONCE(1, "Use an actual device structure for DMA allocation\n"); return; } - if (IS_ENABLED(CONFIG_DMA_CMA)) { - phys_addr_t paddr = dma_to_phys(dev, dma_handle); - - dma_release_from_contiguous(dev, + freed = dma_release_from_contiguous(dev, phys_to_page(paddr), size >> PAGE_SHIFT); - } else { + if (!freed) swiotlb_free_coherent(dev, size, vaddr, dma_handle); - } } static void *__dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { - struct page *page, **map; + struct page *page; void *ptr, *coherent_ptr; - int order, i; size = PAGE_ALIGN(size); - order = get_order(size); + + if (!(flags & __GFP_WAIT)) { + struct page *page = NULL; + void *addr = __alloc_from_pool(size, &page); + + if (addr) + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + + return addr; + + } ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs); if (!ptr) goto no_mem; - map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA); - if (!map) - goto no_map; /* remove any dirty cache lines on the kernel alias */ __dma_flush_range(ptr, ptr + size); /* create a coherent mapping */ page = virt_to_page(ptr); - for (i = 0; i < (size >> PAGE_SHIFT); i++) - map[i] = page + i; - coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP, - __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false)); - kfree(map); + coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, + __get_dma_pgprot(attrs, + __pgprot(PROT_NORMAL_NC), false), + NULL); if (!coherent_ptr) goto no_map; @@ -132,6 +185,8 @@ static void __dma_free_noncoherent(struct device *dev, size_t size, { void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); + if (__free_from_pool(vaddr, size)) + return; vunmap(vaddr); __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs); } @@ -329,6 +384,67 @@ static struct notifier_block amba_bus_nb = { extern int swiotlb_late_init_with_default_size(size_t default_size); +static int __init atomic_pool_init(void) +{ + pgprot_t prot = __pgprot(PROT_NORMAL_NC); + unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; + struct page *page; + void *addr; + unsigned int pool_size_order = get_order(atomic_pool_size); + + if (dev_get_cma_area(NULL)) + page = dma_alloc_from_contiguous(NULL, nr_pages, + pool_size_order); + else + page = alloc_pages(GFP_DMA, pool_size_order); + + if (page) { + int ret; + void *page_addr = page_address(page); + + memset(page_addr, 0, atomic_pool_size); + __dma_flush_range(page_addr, page_addr + atomic_pool_size); + + atomic_pool = gen_pool_create(PAGE_SHIFT, -1); + if (!atomic_pool) + goto free_page; + + addr = dma_common_contiguous_remap(page, atomic_pool_size, + VM_USERMAP, prot, atomic_pool_init); + + if (!addr) + goto destroy_genpool; + + ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, + page_to_phys(page), + atomic_pool_size, -1); + if (ret) + goto remove_mapping; + + gen_pool_set_algo(atomic_pool, + gen_pool_first_fit_order_align, + (void *)PAGE_SHIFT); + + pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", + atomic_pool_size / 1024); + return 0; + } + goto out; + +remove_mapping: + dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); +destroy_genpool: + gen_pool_destroy(atomic_pool); + atomic_pool = NULL; +free_page: + if (!dma_release_from_contiguous(NULL, page, nr_pages)) + __free_pages(page, pool_size_order); +out: + pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", + atomic_pool_size / 1024); + return -ENOMEM; +} + static int __init swiotlb_late_init(void) { size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT); @@ -343,7 +459,17 @@ static int __init swiotlb_late_init(void) return swiotlb_late_init_with_default_size(swiotlb_size); } -arch_initcall(swiotlb_late_init); + +static int __init arm64_dma_init(void) +{ + int ret = 0; + + ret |= swiotlb_late_init(); + ret |= atomic_pool_init(); + + return ret; +} +arch_initcall(arm64_dma_init); #define PREALLOC_DMA_DEBUG_ENTRIES 4096 diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 81bdd29df3a4..d0f86b74fce6 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -68,6 +68,17 @@ static int __init early_initrd(char *p) } early_param("initrd", early_initrd); +/* + * 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 + * use a DMA offset. + */ +static phys_addr_t max_zone_dma_phys(void) +{ + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); + return min(offset + (1ULL << 32), memblock_end_of_DRAM()); +} + static void __init zone_sizes_init(unsigned long min, unsigned long max) { struct memblock_region *reg; @@ -78,9 +89,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) /* 4GB maximum for 32-bit only capable devices */ if (IS_ENABLED(CONFIG_ZONE_DMA)) { - unsigned long max_dma_phys = - (unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1); - max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT)); + max_dma = PFN_DOWN(max_zone_dma_phys()); zone_size[ZONE_DMA] = max_dma - min; } zone_size[ZONE_NORMAL] = max - max_dma; @@ -135,6 +144,7 @@ static void arm64_memory_present(void) void __init arm64_memblock_init(void) { u64 *reserve_map, base, size; + phys_addr_t dma_phys_limit = 0; /* * Register the kernel text, kernel data, initrd, and initial @@ -171,7 +181,11 @@ void __init arm64_memblock_init(void) } early_init_fdt_scan_reserved_mem(); - dma_contiguous_reserve(0); + + /* 4GB maximum for 32-bit only capable devices */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + dma_phys_limit = max_zone_dma_phys(); + dma_contiguous_reserve(dma_phys_limit); memblock_allow_resize(); memblock_dump_all(); diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index 00d315ae1de9..cf25fa9aa68f 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -98,19 +98,25 @@ void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size) } EXPORT_SYMBOL(ioremap_cache); -#ifndef CONFIG_ARM64_64K_PAGES static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; +#ifndef CONFIG_ARM64_64K_PAGES +static pte_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss; #endif -static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) +static inline pud_t * __init early_ioremap_pud(unsigned long addr) { pgd_t *pgd; - pud_t *pud; pgd = pgd_offset_k(addr); BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); - pud = pud_offset(pgd, addr); + return pud_offset(pgd, addr); +} + +static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) +{ + pud_t *pud = early_ioremap_pud(addr); + BUG_ON(pud_none(*pud) || pud_bad(*pud)); return pmd_offset(pud, addr); @@ -127,13 +133,17 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr) void __init early_ioremap_init(void) { + pgd_t *pgd; + pud_t *pud; pmd_t *pmd; + unsigned long addr = fix_to_virt(FIX_BTMAP_BEGIN); - pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); -#ifndef CONFIG_ARM64_64K_PAGES - /* need to populate pmd for 4k pagesize only */ + pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pud_populate(&init_mm, pud, bm_pmd); + pmd = pmd_offset(pud, addr); pmd_populate_kernel(&init_mm, pmd, bm_pte); -#endif + /* * The boot-ioremap range spans multiple pmds, for which * we are not prepared: diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c new file mode 100644 index 000000000000..75e744e4cec5 --- /dev/null +++ b/arch/arm64/mm/pageattr.c @@ -0,0 +1,96 @@ +/* + * Copyright (c) 2014, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/sched.h> + +#include <asm/pgtable.h> +#include <asm/tlbflush.h> + +struct page_change_data { + pgprot_t set_mask; + pgprot_t clear_mask; +}; + +static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, + void *data) +{ + struct page_change_data *cdata = data; + pte_t pte = *ptep; + + pte = clear_pte_bit(pte, cdata->clear_mask); + pte = set_pte_bit(pte, cdata->set_mask); + + set_pte(ptep, pte); + return 0; +} + +static int change_memory_common(unsigned long addr, int numpages, + pgprot_t set_mask, pgprot_t clear_mask) +{ + unsigned long start = addr; + unsigned long size = PAGE_SIZE*numpages; + unsigned long end = start + size; + int ret; + struct page_change_data data; + + if (!IS_ALIGNED(addr, PAGE_SIZE)) { + addr &= PAGE_MASK; + WARN_ON_ONCE(1); + } + + if (!is_module_address(start) || !is_module_address(end - 1)) + return -EINVAL; + + data.set_mask = set_mask; + data.clear_mask = clear_mask; + + ret = apply_to_page_range(&init_mm, start, size, change_page_range, + &data); + + flush_tlb_kernel_range(start, end); + return ret; +} + +int set_memory_ro(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(PTE_RDONLY), + __pgprot(PTE_WRITE)); +} +EXPORT_SYMBOL_GPL(set_memory_ro); + +int set_memory_rw(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(PTE_WRITE), + __pgprot(PTE_RDONLY)); +} +EXPORT_SYMBOL_GPL(set_memory_rw); + +int set_memory_nx(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(PTE_PXN), + __pgprot(0)); +} +EXPORT_SYMBOL_GPL(set_memory_nx); + +int set_memory_x(unsigned long addr, int numpages) +{ + return change_memory_common(addr, numpages, + __pgprot(0), + __pgprot(PTE_PXN)); +} +EXPORT_SYMBOL_GPL(set_memory_x); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index c3c7b8f83b55..c133ae53ed86 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -69,6 +69,21 @@ ENTRY(cpu_reset) ret x0 ENDPROC(cpu_reset) +ENTRY(cpu_soft_restart) + /* Save address of cpu_reset() and reset address */ + mov x19, x0 + mov x20, x1 + + /* Turn D-cache off */ + bl cpu_cache_off + + /* Push out all dirty data, and ensure cache is empty */ + bl flush_cache_all + + mov x0, x20 + ret x19 +ENDPROC(cpu_soft_restart) + /* * cpu_do_idle() * diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c index 9c36ca9ed1dd..dd302ea3b599 100644 --- a/drivers/base/dma-mapping.c +++ b/drivers/base/dma-mapping.c @@ -287,7 +287,7 @@ void *dma_common_pages_remap(struct page **pages, size_t size, area->pages = pages; - if (map_vm_area(area, prot, pages)) { + if (map_vm_area(area, prot, &pages)) { vunmap(area->addr); return NULL; } |