diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt new file mode 100644 index 000000000000..58b71ddf9b60 --- /dev/null +++ b/Documentation/arm64/silicon-errata.txt @@ -0,0 +1,58 @@ + Silicon Errata and Software Workarounds + ======================================= + +Author: Will Deacon +Date : 27 November 2015 + +It is an unfortunate fact of life that hardware is often produced with +so-called "errata", which can cause it to deviate from the architecture +under specific circumstances. For hardware produced by ARM, these +errata are broadly classified into the following categories: + + Category A: A critical error without a viable workaround. + Category B: A significant or critical error with an acceptable + workaround. + Category C: A minor error that is not expected to occur under normal + operation. + +For more information, consult one of the "Software Developers Errata +Notice" documents available on infocenter.arm.com (registration +required). + +As far as Linux is concerned, Category B errata may require some special +treatment in the operating system. For example, avoiding a particular +sequence of code, or configuring the processor in a particular way. A +less common situation may require similar actions in order to declassify +a Category A erratum into a Category C erratum. These are collectively +known as "software workarounds" and are only required in the minority of +cases (e.g. those cases that both require a non-secure workaround *and* +can be triggered by Linux). + +For software workarounds that may adversely impact systems unaffected by +the erratum in question, a Kconfig entry is added under "Kernel +Features" -> "ARM errata workarounds via the alternatives framework". +These are enabled by default and patched in at runtime when an affected +CPU is detected. For less-intrusive workarounds, a Kconfig option is not +available and the code is structured (preferably with a comment) in such +a way that the erratum will not be hit. + +This approach can make it slightly onerous to determine exactly which +errata are worked around in an arbitrary kernel source tree, so this +file acts as a registry of software workarounds in the Linux Kernel and +will be updated when new workarounds are committed and backported to +stable kernels. + +| Implementor | Component | Erratum ID | Kconfig | ++----------------+-----------------+-----------------+-------------------------+ +| ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | +| ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | +| ARM | Cortex-A53 | #824069 | ARM64_ERRATUM_824069 | +| ARM | Cortex-A53 | #819472 | ARM64_ERRATUM_819472 | +| ARM | Cortex-A53 | #845719 | ARM64_ERRATUM_845719 | +| ARM | Cortex-A53 | #843419 | ARM64_ERRATUM_843419 | +| ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +| ARM | Cortex-A57 | #852523 | N/A | +| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| | | | | +| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | +| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt index e63316239938..4199ffecc0ff 100644 --- a/Documentation/features/time/irq-time-acct/arch-support.txt +++ b/Documentation/features/time/irq-time-acct/arch-support.txt @@ -9,7 +9,7 @@ | alpha: | .. | | arc: | TODO | | arm: | ok | - | arm64: | .. | + | arm64: | ok | | avr32: | TODO | | blackfin: | TODO | | c6x: | TODO | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 871f21783866..ffa3c549a4ba 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -70,6 +70,7 @@ config ARM64 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_MEMBLOCK select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS @@ -529,9 +530,6 @@ config HW_PERF_EVENTS config SYS_SUPPORTS_HUGETLBFS def_bool y -config ARCH_WANT_GENERAL_HUGETLB - def_bool y - config ARCH_WANT_HUGE_PMD_SHARE def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index d56ec0715157..e4962f04201e 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -19,7 +19,6 @@ struct alt_instr { void __init apply_alternatives_all(void); void apply_alternatives(void *start, size_t length); -void free_alternatives_memory(void); #define ALTINSTR_ENTRY(feature) \ " .word 661b - .\n" /* label */ \ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 12eff928ef8b..bb7b72734c24 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -193,6 +193,17 @@ lr .req x30 // link register str \src, [\tmp, :lo12:\sym] .endm + /* + * @sym: The name of the per-cpu variable + * @reg: Result of per_cpu(sym, smp_processor_id()) + * @tmp: scratch register + */ + .macro this_cpu_ptr, sym, reg, tmp + adr_l \reg, \sym + mrs \tmp, tpidr_el1 + add \reg, \reg, \tmp + .endm + /* * Annotate a function as position independent, i.e., safe to be called before * the kernel virtual mapping is activated. diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 54efedaf331f..7fc294c3bc5b 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -68,6 +68,7 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); +extern void __clean_dcache_area_pou(void *addr, size_t len); extern long __flush_cache_user_range(unsigned long start, unsigned long end); static inline void flush_cache_mm(struct mm_struct *mm) diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 9ea611ea69df..510c7b404454 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -19,7 +19,6 @@ #define __ASM_CMPXCHG_H #include -#include #include #include diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index ef572206f1c3..8e88a696c9cb 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -2,7 +2,9 @@ #define _ASM_EFI_H #include +#include #include +#include #ifdef CONFIG_EFI extern void efi_init(void); @@ -10,6 +12,8 @@ extern void efi_init(void); #define efi_init() #endif +int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); + #define efi_call_virt(f, ...) \ ({ \ efi_##f##_t *__f; \ @@ -63,6 +67,11 @@ extern void efi_init(void); * Services are enabled and the EFI_RUNTIME_SERVICES bit set. */ +static inline void efi_set_pgd(struct mm_struct *mm) +{ + switch_mm(NULL, mm, NULL); +} + void efi_virtmap_load(void); void efi_virtmap_unload(void); diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index c5534facf941..3c60f37e48ab 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -28,6 +28,8 @@ struct dyn_arch_ftrace { extern unsigned long ftrace_graph_call; +extern void return_to_handler(void); + static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index bb4052e85dba..bbc1e35aa601 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - set_pte_at(mm, addr, ptep, pte); -} -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - ptep_clear_flush(vma, addr, ptep); -} - -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - ptep_set_wrprotect(mm, addr, ptep); -} - -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - return ptep_get_and_clear(mm, addr, ptep); -} - -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - return ptep_set_access_flags(vma, addr, ptep, pte, dirty); -} static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, @@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page *page) clear_bit(PG_dcache_clean, &page->flags); } +extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable); +#define arch_make_huge_pte arch_make_huge_pte +extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); +extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); +extern void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); +extern void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index 8e8d30684392..b77197d941fc 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -1,10 +1,45 @@ #ifndef __ASM_IRQ_H #define __ASM_IRQ_H +#define IRQ_STACK_SIZE THREAD_SIZE +#define IRQ_STACK_START_SP THREAD_START_SP + +#ifndef __ASSEMBLER__ + +#include + #include +#include struct pt_regs; +DECLARE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); + +/* + * The highest address on the stack, and the first to be used. Used to + * find the dummy-stack frame put down by el?_irq() in entry.S, which + * is structured as follows: + * + * ------------ + * | | <- irq_stack_ptr + * top ------------ + * | x19 | <- irq_stack_ptr - 0x08 + * ------------ + * | x29 | <- irq_stack_ptr - 0x10 + * ------------ + * + * where x19 holds a copy of the task stack pointer where the struct pt_regs + * from kernel_entry can be found. + * + */ +#define IRQ_STACK_PTR(cpu) ((unsigned long)per_cpu(irq_stack, cpu) + IRQ_STACK_START_SP) + +/* + * The offset from irq_stack_ptr where entry.S will store the original + * stack pointer. Used by unwind_frame() and dump_backtrace(). + */ +#define IRQ_STACK_TO_TASK_STACK(ptr) (*((unsigned long *)((ptr) - 0x08))) + extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); static inline int nr_legacy_irqs(void) @@ -12,4 +47,14 @@ static inline int nr_legacy_irqs(void) return 0; } +static inline bool on_irq_stack(unsigned long sp, int cpu) +{ + /* variable names the same as kernel/stacktrace.c */ + unsigned long low = (unsigned long)per_cpu(irq_stack, cpu); + unsigned long high = low + IRQ_STACK_START_SP; + + return (low <= sp && sp <= high); +} + +#endif /* !__ASSEMBLER__ */ #endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d6739e836f7b..5c25b831273d 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -90,7 +90,23 @@ /* * Contiguous page definitions. */ -#define CONT_PTES (_AC(1, UL) << CONT_SHIFT) +#ifdef CONFIG_ARM64_64K_PAGES +#define CONT_PTE_SHIFT 5 +#define CONT_PMD_SHIFT 5 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define CONT_PTE_SHIFT 7 +#define CONT_PMD_SHIFT 5 +#else +#define CONT_PTE_SHIFT 4 +#define CONT_PMD_SHIFT 4 +#endif + +#define CONT_PTES (1 << CONT_PTE_SHIFT) +#define CONT_PTE_SIZE (CONT_PTES * PAGE_SIZE) +#define CONT_PTE_MASK (~(CONT_PTE_SIZE - 1)) +#define CONT_PMDS (1 << CONT_PMD_SHIFT) +#define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE) +#define CONT_PMD_MASK (~(CONT_PMD_SIZE - 1)) /* the the numerical offset of the PTE within a range of CONT_PTES */ #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1)) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 63f52b55defe..69d2e2f86bce 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -167,6 +167,16 @@ extern struct page *empty_zero_page; ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) +#define pte_valid_young(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) + +/* + * Could the pte be present in the TLB? We must check mm_tlb_flush_pending + * so that we don't erroneously return false for pages that have been + * remapped as PROT_NONE but are yet to be flushed from the TLB. + */ +#define pte_accessible(mm, pte) \ + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { @@ -217,7 +227,8 @@ static inline pte_t pte_mkspecial(pte_t pte) static inline pte_t pte_mkcont(pte_t pte) { - return set_pte_bit(pte, __pgprot(PTE_CONT)); + pte = set_pte_bit(pte, __pgprot(PTE_CONT)); + return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); } static inline pte_t pte_mknoncont(pte_t pte) @@ -225,6 +236,11 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } +static inline pmd_t pmd_mkcont(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | PMD_SECT_CONT); +} + static inline void set_pte(pte_t *ptep, pte_t pte) { *ptep = pte; @@ -298,7 +314,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, /* * Hugetlb definitions. */ -#define HUGE_MAX_HSTATE 2 +#define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) @@ -664,7 +680,8 @@ extern int kern_addr_valid(unsigned long addr); #include -#define pgtable_cache_init() do { } while (0) +void pgd_cache_init(void); +#define pgtable_cache_init pgd_cache_init /* * On AArch64, the cache coherency is handled via the set_pte_at() function. diff --git a/arch/arm64/include/asm/shmparam.h b/arch/arm64/include/asm/shmparam.h index 4df608a8459e..e368a55ebd22 100644 --- a/arch/arm64/include/asm/shmparam.h +++ b/arch/arm64/include/asm/shmparam.h @@ -21,7 +21,7 @@ * alignment value. Since we don't have aliasing D-caches, the rest of * the time we can safely use PAGE_SIZE. */ -#define COMPAT_SHMLBA 0x4000 +#define COMPAT_SHMLBA (4 * PAGE_SIZE) #include diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index c85e96d174a5..fc9682bfe002 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -26,9 +26,28 @@ * The memory barriers are implicit with the load-acquire and store-release * instructions. */ +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + unsigned int tmp; + arch_spinlock_t lockval; -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + asm volatile( +" sevl\n" +"1: wfe\n" +"2: ldaxr %w0, %2\n" +" eor %w1, %w0, %w0, ror #16\n" +" cbnz %w1, 1b\n" + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ +" stxr %w1, %w0, %2\n" +" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */ + /* LSE atomics */ +" nop\n" +" nop\n") + : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) + : + : "memory"); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 7318f6d54aa9..801a16dbbdf6 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -16,14 +16,19 @@ #ifndef __ASM_STACKTRACE_H #define __ASM_STACKTRACE_H +struct task_struct; + struct stackframe { unsigned long fp; unsigned long sp; unsigned long pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + unsigned int graph; +#endif }; -extern int unwind_frame(struct stackframe *frame); -extern void walk_stackframe(struct stackframe *frame, +extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); +extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 90c7ff233735..abd64bd1f6d9 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -73,10 +73,16 @@ register unsigned long current_stack_pointer asm ("sp"); */ static inline struct thread_info *current_thread_info(void) __attribute_const__; +/* + * struct thread_info can be accessed directly via sp_el0. + */ static inline struct thread_info *current_thread_info(void) { - return (struct thread_info *) - (current_stack_pointer & ~(THREAD_SIZE - 1)); + unsigned long sp_el0; + + asm ("mrs %0, sp_el0" : "=r" (sp_el0)); + + return (struct thread_info *)sp_el0; } #define thread_saved_pc(tsk) \ diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index ab9db0e9818c..d2ee1b21a10d 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -158,9 +158,3 @@ void apply_alternatives(void *start, size_t length) __apply_alternatives(®ion); } - -void free_alternatives_memory(void) -{ - free_reserved_area(__alt_instructions, __alt_instructions_end, - 0, "alternatives"); -} diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 937f5e58a4d3..3e01207917b1 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -62,7 +62,7 @@ struct insn_emulation { }; static LIST_HEAD(insn_emulation); -static int nr_insn_emulated; +static int nr_insn_emulated __initdata; static DEFINE_RAW_SPINLOCK(insn_emulation_lock); static void register_emulation_hooks(struct insn_emulation_ops *ops) @@ -173,7 +173,7 @@ static int update_insn_emulation_mode(struct insn_emulation *insn, return ret; } -static void register_insn_emulation(struct insn_emulation_ops *ops) +static void __init register_insn_emulation(struct insn_emulation_ops *ops) { unsigned long flags; struct insn_emulation *insn; @@ -237,7 +237,7 @@ static struct ctl_table ctl_abi[] = { { } }; -static void register_insn_emulation_sysctl(struct ctl_table *table) +static void __init register_insn_emulation_sysctl(struct ctl_table *table) { unsigned long flags; int i = 0; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0669c63281ea..5c90aa490a2b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -684,7 +684,7 @@ static const struct arm64_cpu_capabilities arm64_hwcaps[] = { {}, }; -static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap) +static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap) { switch (cap->hwcap_type) { case CAP_HWCAP: @@ -729,7 +729,7 @@ static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities * return rc; } -static void setup_cpu_hwcaps(void) +static void __init setup_cpu_hwcaps(void) { int i; const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps; @@ -758,7 +758,8 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, * Run through the enabled capabilities and enable() it on all active * CPUs */ -static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +static void __init +enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { int i; @@ -897,7 +898,7 @@ static inline void set_sys_caps_initialised(void) #endif /* CONFIG_HOTPLUG_CPU */ -static void setup_feature_capabilities(void) +static void __init setup_feature_capabilities(void) { update_cpu_capabilities(arm64_features, "detected feature:"); enable_cpu_capabilities(arm64_features); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4eeb17198cfa..b6abc852f2a1 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -11,317 +11,34 @@ * */ -#include #include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include +#include -#include #include -#include -#include -#include -#include -struct efi_memory_map memmap; - -static u64 efi_system_table; - -static pgd_t efi_pgd[PTRS_PER_PGD] __page_aligned_bss; - -static struct mm_struct efi_mm = { - .mm_rb = RB_ROOT, - .pgd = efi_pgd, - .mm_users = ATOMIC_INIT(2), - .mm_count = ATOMIC_INIT(1), - .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), - .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), - .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), -}; - -static int __init is_normal_ram(efi_memory_desc_t *md) +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { - if (md->attribute & EFI_MEMORY_WB) - return 1; - return 0; -} - -/* - * Translate a EFI virtual address into a physical address: this is necessary, - * as some data members of the EFI system table are virtually remapped after - * SetVirtualAddressMap() has been called. - */ -static phys_addr_t efi_to_phys(unsigned long addr) -{ - efi_memory_desc_t *md; - - for_each_efi_memory_desc(&memmap, md) { - if (!(md->attribute & EFI_MEMORY_RUNTIME)) - continue; - if (md->virt_addr == 0) - /* no virtual mapping has been installed by the stub */ - break; - if (md->virt_addr <= addr && - (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT)) - return md->phys_addr + addr - md->virt_addr; - } - return addr; -} - -static int __init uefi_init(void) -{ - efi_char16_t *c16; - void *config_tables; - u64 table_size; - char vendor[100] = "unknown"; - int i, retval; - - efi.systab = early_memremap(efi_system_table, - sizeof(efi_system_table_t)); - if (efi.systab == NULL) { - pr_warn("Unable to map EFI system table.\n"); - return -ENOMEM; - } - - set_bit(EFI_BOOT, &efi.flags); - set_bit(EFI_64BIT, &efi.flags); + pteval_t prot_val; /* - * Verify the EFI Table + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be + * executable, everything else can be mapped with the XN bits + * set. */ - if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { - pr_err("System table signature incorrect\n"); - retval = -EINVAL; - goto out; - } - if ((efi.systab->hdr.revision >> 16) < 2) - pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff); - - /* Show what we know for posterity */ - c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor), - sizeof(vendor) * sizeof(efi_char16_t)); - if (c16) { - for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = c16[i]; - vendor[i] = '\0'; - early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); - } - - pr_info("EFI v%u.%.02u by %s\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff, vendor); - - table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables; - config_tables = early_memremap(efi_to_phys(efi.systab->tables), - table_size); - if (config_tables == NULL) { - pr_warn("Unable to map EFI config table array.\n"); - retval = -ENOMEM; - goto out; - } - retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables, - sizeof(efi_config_table_64_t), NULL); - - early_memunmap(config_tables, table_size); -out: - early_memunmap(efi.systab, sizeof(efi_system_table_t)); - return retval; -} - -/* - * Return true for RAM regions we want to permanently reserve. - */ -static __init int is_reserve_region(efi_memory_desc_t *md) -{ - switch (md->type) { - case EFI_LOADER_CODE: - case EFI_LOADER_DATA: - case EFI_BOOT_SERVICES_CODE: - case EFI_BOOT_SERVICES_DATA: - case EFI_CONVENTIONAL_MEMORY: - case EFI_PERSISTENT_MEMORY: - return 0; - default: - break; - } - return is_normal_ram(md); -} - -static __init void reserve_regions(void) -{ - efi_memory_desc_t *md; - u64 paddr, npages, size; - - if (efi_enabled(EFI_DBG)) - pr_info("Processing EFI memory map:\n"); - - for_each_efi_memory_desc(&memmap, md) { - paddr = md->phys_addr; - npages = md->num_pages; - - if (efi_enabled(EFI_DBG)) { - char buf[64]; - - pr_info(" 0x%012llx-0x%012llx %s", - paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1, - efi_md_typeattr_format(buf, sizeof(buf), md)); - } - - memrange_efi_to_native(&paddr, &npages); - size = npages << PAGE_SHIFT; - - if (is_normal_ram(md)) - early_init_dt_add_memory_arch(paddr, size); - - if (is_reserve_region(md)) { - memblock_reserve(paddr, size); - if (efi_enabled(EFI_DBG)) - pr_cont("*"); - } - - if (efi_enabled(EFI_DBG)) - pr_cont("\n"); - } - - set_bit(EFI_MEMMAP, &efi.flags); -} - -void __init efi_init(void) -{ - struct efi_fdt_params params; - - /* Grab UEFI information placed in FDT by stub */ - if (!efi_get_fdt_params(¶ms)) - return; - - efi_system_table = params.system_table; - - memblock_reserve(params.mmap & PAGE_MASK, - PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK))); - memmap.phys_map = params.mmap; - memmap.map = early_memremap(params.mmap, params.mmap_size); - if (memmap.map == NULL) { - /* - * If we are booting via UEFI, the UEFI memory map is the only - * description of memory we have, so there is little point in - * proceeding if we cannot access it. - */ - panic("Unable to map EFI memory map.\n"); - } - memmap.map_end = memmap.map + params.mmap_size; - memmap.desc_size = params.desc_size; - memmap.desc_version = params.desc_ver; - - if (uefi_init() < 0) - return; - - reserve_regions(); - early_memunmap(memmap.map, params.mmap_size); -} - -static bool __init efi_virtmap_init(void) -{ - efi_memory_desc_t *md; - - init_new_context(NULL, &efi_mm); - - for_each_efi_memory_desc(&memmap, md) { - pgprot_t prot; - - if (!(md->attribute & EFI_MEMORY_RUNTIME)) - continue; - if (md->virt_addr == 0) - return false; - - pr_info(" EFI remap 0x%016llx => %p\n", - md->phys_addr, (void *)md->virt_addr); - - /* - * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be - * executable, everything else can be mapped with the XN bits - * set. - */ - if (!is_normal_ram(md)) - prot = __pgprot(PROT_DEVICE_nGnRE); - else if (md->type == EFI_RUNTIME_SERVICES_CODE || - !PAGE_ALIGNED(md->phys_addr)) - prot = PAGE_KERNEL_EXEC; - else - prot = PAGE_KERNEL; - - create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr, - md->num_pages << EFI_PAGE_SHIFT, - __pgprot(pgprot_val(prot) | PTE_NG)); - } - return true; -} - -/* - * Enable the UEFI Runtime Services if all prerequisites are in place, i.e., - * non-early mapping of the UEFI system table and virtual mappings for all - * EFI_MEMORY_RUNTIME regions. - */ -static int __init arm64_enable_runtime_services(void) -{ - u64 mapsize; - - if (!efi_enabled(EFI_BOOT)) { - pr_info("EFI services will not be available.\n"); - return 0; - } - - if (efi_runtime_disabled()) { - pr_info("EFI runtime services will be disabled.\n"); - return 0; - } - - pr_info("Remapping and enabling EFI services.\n"); - - mapsize = memmap.map_end - memmap.map; - memmap.map = (__force void *)ioremap_cache(memmap.phys_map, - mapsize); - if (!memmap.map) { - pr_err("Failed to remap EFI memory map\n"); - return -ENOMEM; - } - memmap.map_end = memmap.map + mapsize; - efi.memmap = &memmap; - - efi.systab = (__force void *)ioremap_cache(efi_system_table, - sizeof(efi_system_table_t)); - if (!efi.systab) { - pr_err("Failed to remap EFI System Table\n"); - return -ENOMEM; - } - set_bit(EFI_SYSTEM_TABLES, &efi.flags); - - if (!efi_virtmap_init()) { - pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n"); - return -ENOMEM; - } - - /* Set up runtime services function pointers */ - efi_native_runtime_setup(); - set_bit(EFI_RUNTIME_SERVICES, &efi.flags); - - efi.runtime_version = efi.systab->hdr.revision; + if ((md->attribute & EFI_MEMORY_WB) == 0) + prot_val = PROT_DEVICE_nGnRE; + else if (md->type == EFI_RUNTIME_SERVICES_CODE || + !PAGE_ALIGNED(md->phys_addr)) + prot_val = pgprot_val(PAGE_KERNEL_EXEC); + else + prot_val = pgprot_val(PAGE_KERNEL); + create_pgd_mapping(mm, md->phys_addr, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + __pgprot(prot_val | PTE_NG)); return 0; } -early_initcall(arm64_enable_runtime_services); static int __init arm64_dmi_init(void) { @@ -337,23 +54,6 @@ static int __init arm64_dmi_init(void) } core_initcall(arm64_dmi_init); -static void efi_set_pgd(struct mm_struct *mm) -{ - switch_mm(NULL, mm, NULL); -} - -void efi_virtmap_load(void) -{ - preempt_disable(); - efi_set_pgd(&efi_mm); -} - -void efi_virtmap_unload(void) -{ - efi_set_pgd(current->active_mm); - preempt_enable(); -} - /* * UpdateCapsule() depends on the system being shutdown via * ResetSystem(). diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7ed3d75f6304..1f7f5a2b61bf 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -88,9 +89,12 @@ .if \el == 0 mrs x21, sp_el0 - get_thread_info tsk // Ensure MDSCR_EL1.SS is clear, + 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 disable_step_tsk x19, x20 // exceptions when scheduling. + + mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE .endif @@ -107,6 +111,13 @@ str x21, [sp, #S_SYSCALLNO] .endif + /* + * Set sp_el0 to current thread_info. + */ + .if \el == 0 + msr sp_el0, tsk + .endif + /* * Registers that may be useful after this macro is invoked: * @@ -164,8 +175,44 @@ alternative_endif .endm .macro get_thread_info, rd - mov \rd, sp - and \rd, \rd, #~(THREAD_SIZE - 1) // top of stack + 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. + */ + and x25, x19, #~(THREAD_SIZE - 1) + cmp x25, tsk + b.ne 9998f + + this_cpu_ptr irq_stack, x25, x26 + mov x26, #IRQ_STACK_START_SP + add x26, x25, x26 + + /* switch to the irq stack */ + mov sp, x26 + + /* + * Add a dummy stack frame, this non-standard format is fixed up + * by unwind_frame() + */ + stp x29, x19, [sp, #-16]! + mov x29, sp + +9998: + .endm + + /* + * x19 should be preserved between irq_stack_entry and + * irq_stack_exit. + */ + .macro irq_stack_exit + mov sp, x19 .endm /* @@ -183,10 +230,11 @@ tsk .req x28 // current thread_info * Interrupt handling. */ .macro irq_handler - adrp x1, handle_arch_irq - ldr x1, [x1, #:lo12:handle_arch_irq] + ldr_l x1, handle_arch_irq mov x0, sp + irq_stack_entry blr x1 + irq_stack_exit .endm .text @@ -358,10 +406,10 @@ el1_irq: bl trace_hardirqs_off #endif + get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT - get_thread_info tsk ldr w24, [tsk, #TI_PREEMPT] // get preempt count cbnz w24, 1f // preempt count != 0 ldr x0, [tsk, #TI_FLAGS] // get flags @@ -599,6 +647,8 @@ 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 ret ENDPROC(cpu_switch_to) @@ -626,14 +676,14 @@ ret_fast_syscall_trace: work_pending: tbnz x1, #TIF_NEED_RESCHED, work_resched /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ - ldr x2, [sp, #S_PSTATE] mov x0, sp // 'regs' - tst x2, #PSR_MODE_MASK // user mode regs? - b.ne no_work_pending // returning to kernel enable_irq // enable interrupts for do_notify_resume() bl do_notify_resume b ret_to_user work_resched: +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off // the IRQs are off here, inform the tracing code +#endif bl schedule /* @@ -645,7 +695,6 @@ ret_to_user: and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending enable_step_tsk x1, x2 -no_work_pending: kernel_exit 0 ENDPROC(ret_to_user) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4c46c54a3ad7..acc1afd5c749 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -289,7 +289,7 @@ static struct notifier_block fpsimd_cpu_pm_notifier_block = { .notifier_call = fpsimd_cpu_pm_notifier, }; -static void fpsimd_pm_init(void) +static void __init fpsimd_pm_init(void) { cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block); } diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index c851be795080..ebecf9aa33d1 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -29,12 +29,11 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, /* * Note: - * Due to modules and __init, code can disappear and change, - * we need to protect against faulting as well as code changing. - * We do this by aarch64_insn_*() which use the probe_kernel_*(). - * - * No lock is held here because all the modifications are run - * through stop_machine(). + * We are paranoid about modifying text, as if a bug were to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with aarch64_insn_*() which uses + * probe_kernel_*(), and make sure what we read is what we expected it + * to be before modifying it. */ if (validate) { if (aarch64_insn_read((void *)pc, &replaced)) @@ -93,6 +92,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return ftrace_modify_code(pc, old, new, true); } +void arch_ftrace_update_code(int command) +{ + ftrace_modify_all_code(command); +} + int __init ftrace_dyn_arch_init(void) { return 0; @@ -125,23 +129,20 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, * on other archs. It's unlikely on AArch64. */ old = *parent; - *parent = return_hooker; trace.func = self_addr; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - *parent = old; + if (!ftrace_graph_entry(&trace)) return; - } err = ftrace_push_return_trace(old, self_addr, &trace.depth, frame_pointer); - if (err == -EBUSY) { - *parent = old; + if (err == -EBUSY) return; - } + else + *parent = return_hooker; } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 23cfc08fc8ba..ffe9c2b6431b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -415,15 +415,17 @@ ENDPROC(__create_page_tables) */ .set initial_sp, init_thread_union + THREAD_START_SP __mmap_switched: - adr_l x6, __bss_start - adr_l x7, __bss_stop + // Clear BSS + adr_l x0, __bss_start + mov x1, xzr + adr_l x2, __bss_stop + sub x2, x2, x0 + bl __pi_memset -1: cmp x6, x7 - b.hs 2f - str xzr, [x6], #8 // Clear BSS - b 1b -2: adr_l sp, initial_sp, x4 + mov x4, sp + and x4, x4, #~(THREAD_SIZE - 1) + msr sp_el0, x4 // Save thread_info str_l x21, __fdt_pointer, x5 // Save FDT pointer str_l x24, memstart_addr, x6 // Save PHYS_OFFSET mov x29, #0 @@ -606,6 +608,8 @@ ENDPROC(secondary_startup) ENTRY(__secondary_switched) ldr x0, [x21] // get secondary_data.stack mov sp, x0 + and x0, x0, #~(THREAD_SIZE - 1) + msr sp_el0, x0 // save thread_info mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 9f17ec071ee0..2386b26c0712 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -30,6 +30,9 @@ unsigned long irq_err_count; +/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ +DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16); + int arch_show_interrupts(struct seq_file *p, int prec) { show_ipi_list(p, prec); diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f4bc779e62e8..93e970231ca9 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -30,9 +30,6 @@ #include #include -#define AARCH64_INSN_IMM_MOVNZ AARCH64_INSN_IMM_MAX -#define AARCH64_INSN_IMM_MOVK AARCH64_INSN_IMM_16 - void *module_alloc(unsigned long size) { void *p; @@ -75,15 +72,18 @@ static u64 do_reloc(enum aarch64_reloc_op reloc_op, void *place, u64 val) static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) { - u64 imm_mask = (1 << len) - 1; s64 sval = do_reloc(op, place, val); switch (len) { case 16: *(s16 *)place = sval; + if (sval < S16_MIN || sval > U16_MAX) + return -ERANGE; break; case 32: *(s32 *)place = sval; + if (sval < S32_MIN || sval > U32_MAX) + return -ERANGE; break; case 64: *(s64 *)place = sval; @@ -92,34 +92,23 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) pr_err("Invalid length (%d) for data relocation\n", len); return 0; } - - /* - * Extract the upper value bits (including the sign bit) and - * shift them to bit 0. - */ - sval = (s64)(sval & ~(imm_mask >> 1)) >> (len - 1); - - /* - * Overflow has occurred if the value is not representable in - * len bits (i.e the bottom len bits are not sign-extended and - * the top bits are not all zero). - */ - if ((u64)(sval + 1) > 2) - return -ERANGE; - return 0; } +enum aarch64_insn_movw_imm_type { + AARCH64_INSN_IMM_MOVNZ, + AARCH64_INSN_IMM_MOVKZ, +}; + static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, - int lsb, enum aarch64_insn_imm_type imm_type) + int lsb, enum aarch64_insn_movw_imm_type imm_type) { - u64 imm, limit = 0; + u64 imm; s64 sval; u32 insn = le32_to_cpu(*(u32 *)place); sval = do_reloc(op, place, val); - sval >>= lsb; - imm = sval & 0xffff; + imm = sval >> lsb; if (imm_type == AARCH64_INSN_IMM_MOVNZ) { /* @@ -128,7 +117,7 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, * immediate is less than zero. */ insn &= ~(3 << 29); - if ((s64)imm >= 0) { + if (sval >= 0) { /* >=0: Set the instruction to MOVZ (opcode 10b). */ insn |= 2 << 29; } else { @@ -140,29 +129,13 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, */ imm = ~imm; } - imm_type = AARCH64_INSN_IMM_MOVK; } /* Update the instruction with the new encoding. */ - insn = aarch64_insn_encode_immediate(imm_type, insn, imm); + insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm); *(u32 *)place = cpu_to_le32(insn); - /* Shift out the immediate field. */ - sval >>= 16; - - /* - * For unsigned immediates, the overflow check is straightforward. - * For signed immediates, the sign bit is actually the bit past the - * most significant bit of the field. - * The AARCH64_INSN_IMM_16 immediate type is unsigned. - */ - if (imm_type != AARCH64_INSN_IMM_16) { - sval++; - limit++; - } - - /* Check the upper bits depending on the sign of the immediate. */ - if ((u64)sval > limit) + if (imm > U16_MAX) return -ERANGE; return 0; @@ -267,25 +240,25 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, overflow_check = false; case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G3: /* We're using the top bits so we can't overflow. */ overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_SABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, @@ -302,7 +275,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G0_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G0: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0, @@ -311,7 +284,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G1_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G1: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16, @@ -320,7 +293,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G2_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G2: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32, diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 3aa74830cc69..ff4665462a02 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -164,8 +164,11 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, frame.fp = regs->regs[29]; frame.sp = regs->sp; frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif - walk_stackframe(&frame, callchain_trace, entry); + walk_stackframe(current, &frame, callchain_trace, entry); } unsigned long perf_instruction_pointer(struct pt_regs *regs) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index f75b540bc3b4..88d742ba19d5 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -344,11 +344,14 @@ unsigned long get_wchan(struct task_struct *p) 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(&frame)) + unwind_frame(p, &frame)) return 0; if (!in_sched_functions(frame.pc)) return frame.pc; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..ff7f13239515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -58,6 +58,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index 6c4fd2810ecb..1718706fde83 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -43,8 +43,11 @@ void *return_address(unsigned int level) frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; frame.pc = (unsigned long)return_address; /* dummy */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif - walk_stackframe(&frame, save_return_addr, &data); + walk_stackframe(current, &frame, save_return_addr, &data); if (!data.level) return data.addr; diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index f586f7c875e2..e33fe33876ab 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -173,6 +173,9 @@ ENTRY(cpu_resume) /* load physical address of identity map page table in x1 */ adrp x1, idmap_pg_dir mov sp, x2 + /* save thread_info */ + and x2, x2, #~(THREAD_SIZE - 1) + msr sp_el0, x2 /* * cpu_do_resume expects x0 to contain context physical address * pointer and x1 to contain physical address of 1:1 page tables diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index ccb6078ed9f2..4fad9787ab46 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -17,9 +17,11 @@ */ #include #include +#include #include #include +#include #include /* @@ -35,25 +37,83 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ -int notrace unwind_frame(struct stackframe *frame) +int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) { unsigned long high, low; unsigned long fp = frame->fp; + unsigned long irq_stack_ptr; + + /* + * Use raw_smp_processor_id() to avoid false-positives from + * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping + * task stacks, we can be pre-empted in this case, so + * {raw_,}smp_processor_id() may give us the wrong value. Sleeping + * tasks can't ever be on an interrupt stack, so regardless of cpu, + * the checks will always fail. + */ + irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id()); low = frame->sp; - high = ALIGN(low, THREAD_SIZE); + /* irq stacks are not THREAD_SIZE aligned */ + if (on_irq_stack(frame->sp, raw_smp_processor_id())) + high = irq_stack_ptr; + else + high = ALIGN(low, THREAD_SIZE) - 0x20; - if (fp < low || fp > high - 0x18 || fp & 0xf) + if (fp < low || fp > high || fp & 0xf) return -EINVAL; frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); frame->pc = *(unsigned long *)(fp + 8); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (tsk && tsk->ret_stack && + (frame->pc == (unsigned long)return_to_handler)) { + /* + * This is a case where function graph tracer has + * modified a return address (LR) in a stack frame + * to hook a function return. + * So replace it to an original value. + */ + frame->pc = tsk->ret_stack[frame->graph--].ret; + } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + /* + * Check whether we are going to walk through from interrupt stack + * to task stack. + * If we reach the end of the stack - and its an interrupt stack, + * unpack the dummy frame to find the original elr. + * + * Check the frame->fp we read from the bottom of the irq_stack, + * and the original task stack pointer are both in current->stack. + */ + if (frame->sp == irq_stack_ptr) { + struct pt_regs *irq_args; + unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); + + if (object_is_on_stack((void *)orig_sp) && + object_is_on_stack((void *)frame->fp)) { + frame->sp = orig_sp; + + /* orig_sp is the saved pt_regs, find the elr */ + irq_args = (struct pt_regs *)orig_sp; + frame->pc = irq_args->pc; + } else { + /* + * This frame has a non-standard format, and we + * didn't fix it, because the data looked wrong. + * Refuse to output this frame. + */ + return -EINVAL; + } + } + return 0; } -void notrace walk_stackframe(struct stackframe *frame, +void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) { while (1) { @@ -61,7 +121,7 @@ void notrace walk_stackframe(struct stackframe *frame, if (fn(frame, data)) break; - ret = unwind_frame(frame); + ret = unwind_frame(tsk, frame); if (ret < 0) break; } @@ -112,8 +172,11 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) frame.sp = current_stack_pointer; frame.pc = (unsigned long)save_stack_trace_tsk; } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = tsk->curr_ret_stack; +#endif - walk_stackframe(&frame, save_trace, &data); + walk_stackframe(tsk, &frame, save_trace, &data); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 13339b6ffc1a..59779699a1a4 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,8 +52,11 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.sp = regs->sp; frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = -1; /* no task info */ +#endif do { - int ret = unwind_frame(&frame); + int ret = unwind_frame(NULL, &frame); if (ret < 0) return 0; } while (in_lock_functions(frame.pc)); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index e9b9b5364393..cbedd724f48e 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -146,17 +146,15 @@ 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; + unsigned long irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + int skip; pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); if (!tsk) tsk = current; - if (regs) { - frame.fp = regs->regs[29]; - frame.sp = regs->sp; - frame.pc = regs->pc; - } else if (tsk == current) { + if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; frame.pc = (unsigned long)dump_backtrace; @@ -168,21 +166,49 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.sp = thread_saved_sp(tsk); frame.pc = thread_saved_pc(tsk); } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = tsk->curr_ret_stack; +#endif - pr_emerg("Call trace:\n"); + skip = !!regs; + printk("Call trace:\n"); while (1) { unsigned long where = frame.pc; unsigned long stack; int ret; - dump_backtrace_entry(where); - ret = unwind_frame(&frame); + /* skip until specified stack frame */ + if (!skip) { + dump_backtrace_entry(where); + } else if (frame.fp == regs->regs[29]) { + skip = 0; + /* + * Mostly, this is the case where this function is + * called in panic/abort. As exception handler's + * stack frame does not contain the corresponding pc + * at which an exception has taken place, use regs->pc + * instead. + */ + dump_backtrace_entry(regs->pc); + } + ret = unwind_frame(tsk, &frame); if (ret < 0) break; stack = frame.sp; - if (in_exception_text(where)) + if (in_exception_text(where)) { + /* + * If we switched to the irq_stack before calling this + * exception handler, then the pt_regs will be on the + * task stack. The easiest way to tell is if the large + * pt_regs would overlap with the end of the irq_stack. + */ + if (stack < irq_stack_ptr && + (stack + sizeof(struct pt_regs)) > irq_stack_ptr) + stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); + dump_mem("", "Exception stack", stack, stack + sizeof(struct pt_regs), false); + } } } @@ -456,22 +482,22 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) void __pte_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pte %016lx.\n", file, line, val); + pr_err("%s:%d: bad pte %016lx.\n", file, line, val); } void __pmd_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val); + pr_err("%s:%d: bad pmd %016lx.\n", file, line, val); } void __pud_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pud %016lx.\n", file, line, val); + pr_err("%s:%d: bad pud %016lx.\n", file, line, val); } void __pgd_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val); + pr_err("%s:%d: bad pgd %016lx.\n", file, line, val); } /* GENERIC_BUG traps */ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 71426a78db12..e3928f578891 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -113,7 +113,6 @@ SECTIONS *(.got) /* Global offset table */ } - ALIGN_DEBUG_RO RO_DATA(PAGE_SIZE) EXCEPTION_TABLE(8) NOTES @@ -128,7 +127,6 @@ SECTIONS ARM_EXIT_KEEP(EXIT_TEXT) } - ALIGN_DEBUG_RO_MIN(16) .init.data : { INIT_DATA INIT_SETUP(16) @@ -143,9 +141,6 @@ SECTIONS PERCPU_SECTION(L1_CACHE_BYTES) - . = ALIGN(PAGE_SIZE); - __init_end = .; - . = ALIGN(4); .altinstructions : { __alt_instructions = .; @@ -157,6 +152,8 @@ SECTIONS } . = ALIGN(PAGE_SIZE); + __init_end = .; + _data = .; _sdata = .; RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index cfa44a6adc0a..6df07069a025 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -81,25 +81,31 @@ ENDPROC(__flush_cache_user_range) /* * __flush_dcache_area(kaddr, size) * - * Ensure that the data held in the page kaddr is written back to the - * page in question. + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned and invalidated to the PoC. * * - kaddr - kernel address * - size - size in question */ ENTRY(__flush_dcache_area) - dcache_line_size x2, x3 - add x1, x0, x1 - sub x3, x2, #1 - bic x0, x0, x3 -1: dc civac, x0 // clean & invalidate D line / unified line - add x0, x0, x2 - cmp x0, x1 - b.lo 1b - dsb sy + dcache_by_line_op civac, sy, x0, x1, x2, x3 ret ENDPIPROC(__flush_dcache_area) +/* + * __clean_dcache_area_pou(kaddr, size) + * + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned to the PoU. + * + * - kaddr - kernel address + * - size - size in question + */ +ENTRY(__clean_dcache_area_pou) + dcache_by_line_op cvau, ish, x0, x1, x2, x3 + ret +ENDPROC(__clean_dcache_area_pou) + /* * __inval_cache_range(start, end) * - start - start address of region diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 13bbc3be6f5a..22e4cb4d6f53 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -24,8 +24,9 @@ void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr) { + struct page *page = virt_to_page(kto); copy_page(kto, kfrom); - __flush_dcache_area(kto, PAGE_SIZE); + flush_dcache_page(page); } EXPORT_SYMBOL_GPL(__cpu_copy_user_page); diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 7963aa4b5d28..331c4ca6205c 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -40,7 +40,7 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t 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 size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; static int __init early_coherent_pool(char *p) { @@ -896,7 +896,7 @@ static int __iommu_attach_notifier(struct notifier_block *nb, return 0; } -static int register_iommu_dma_ops_notifier(struct bus_type *bus) +static int __init register_iommu_dma_ops_notifier(struct bus_type *bus) { struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL); int ret; diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index c26b804015e8..46649d6e6c5a 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -34,19 +34,24 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, __flush_icache_all(); } +static void sync_icache_aliases(void *kaddr, unsigned long len) +{ + unsigned long addr = (unsigned long)kaddr; + + if (icache_is_aliasing()) { + __clean_dcache_area_pou(kaddr, len); + __flush_icache_all(); + } else { + flush_icache_range(addr, addr + len); + } +} + static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *kaddr, unsigned long len) { - if (vma->vm_flags & VM_EXEC) { - unsigned long addr = (unsigned long)kaddr; - if (icache_is_aliasing()) { - __flush_dcache_area(kaddr, len); - __flush_icache_all(); - } else { - flush_icache_range(addr, addr + len); - } - } + if (vma->vm_flags & VM_EXEC) + sync_icache_aliases(kaddr, len); } /* @@ -74,13 +79,11 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) if (!page_mapping(page)) return; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) { - __flush_dcache_area(page_address(page), - PAGE_SIZE << compound_order(page)); + if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + sync_icache_aliases(page_address(page), + PAGE_SIZE << compound_order(page)); + else if (icache_is_aivivt()) __flush_icache_all(); - } else if (icache_is_aivivt()) { - __flush_icache_all(); - } } /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 383b03ff38f8..82d607c3614e 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -41,17 +41,289 @@ int pud_huge(pud_t pud) #endif } +static int find_num_contig(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, size_t *pgsize) +{ + pgd_t *pgd = pgd_offset(mm, addr); + pud_t *pud; + pmd_t *pmd; + + *pgsize = PAGE_SIZE; + if (!pte_cont(pte)) + return 1; + if (!pgd_present(*pgd)) { + VM_BUG_ON(!pgd_present(*pgd)); + return 1; + } + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) { + VM_BUG_ON(!pud_present(*pud)); + return 1; + } + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + VM_BUG_ON(!pmd_present(*pmd)); + return 1; + } + if ((pte_t *)pmd == ptep) { + *pgsize = PMD_SIZE; + return CONT_PMDS; + } + return CONT_PTES; +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + size_t pgsize; + int i; + int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize); + unsigned long pfn; + pgprot_t hugeprot; + + if (ncontig == 1) { + set_pte_at(mm, addr, ptep, pte); + return; + } + + pfn = pte_pfn(pte); + hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); + for (i = 0; i < ncontig; i++) { + pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, + pte_val(pfn_pte(pfn, hugeprot))); + set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); + ptep++; + pfn += pgsize >> PAGE_SHIFT; + addr += pgsize; + } +} + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pte_t *pte = NULL; + + pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return NULL; + + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else if (sz == (PAGE_SIZE * CONT_PTES)) { + pmd_t *pmd = pmd_alloc(mm, pud, addr); + + WARN_ON(addr & (sz - 1)); + /* + * Note that if this code were ever ported to the + * 32-bit arm platform then it will cause trouble in + * the case where CONFIG_HIGHPTE is set, since there + * will be no pte_unmap() to correspond with this + * pte_alloc_map(). + */ + pte = pte_alloc_map(mm, NULL, pmd, addr); + } else if (sz == PMD_SIZE) { + if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && + pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } else if (sz == (PMD_SIZE * CONT_PMDS)) { + pmd_t *pmd; + + pmd = pmd_alloc(mm, pud, addr); + WARN_ON(addr & (sz - 1)); + return (pte_t *)pmd; + } + + pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, + sz, pte, pte_val(*pte)); + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); + if (!pgd_present(*pgd)) + return NULL; + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) + return NULL; + + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + return NULL; + + if (pte_cont(pmd_pte(*pmd))) { + pmd = pmd_offset( + pud, (addr & CONT_PMD_MASK)); + return (pte_t *)pmd; + } + if (pmd_huge(*pmd)) + return (pte_t *)pmd; + pte = pte_offset_kernel(pmd, addr); + if (pte_present(*pte) && pte_cont(*pte)) { + pte = pte_offset_kernel( + pmd, (addr & CONT_PTE_MASK)); + return pte; + } + return NULL; +} + +pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable) +{ + size_t pagesize = huge_page_size(hstate_vma(vma)); + + if (pagesize == CONT_PTE_SIZE) { + entry = pte_mkcont(entry); + } else if (pagesize == CONT_PMD_SIZE) { + entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); + } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { + pr_warn("%s: unrecognized huge page size 0x%lx\n", + __func__, pagesize); + } + return entry; +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t pte; + + if (pte_cont(*ptep)) { + int ncontig, i; + size_t pgsize; + pte_t *cpte; + bool is_dirty = false; + + cpte = huge_pte_offset(mm, addr); + ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); + /* save the 1st pte to return */ + pte = ptep_get_and_clear(mm, addr, cpte); + for (i = 1; i < ncontig; ++i) { + /* + * If HW_AFDBM is enabled, then the HW could + * turn on the dirty bit for any of the page + * in the set, so check them all. + */ + ++cpte; + if (pte_dirty(ptep_get_and_clear(mm, addr, cpte))) + is_dirty = true; + } + if (is_dirty) + return pte_mkdirty(pte); + else + return pte; + } else { + return ptep_get_and_clear(mm, addr, ptep); + } +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + pte_t *cpte; + + if (pte_cont(pte)) { + int ncontig, i, changed = 0; + size_t pgsize = 0; + unsigned long pfn = pte_pfn(pte); + /* Select all bits except the pfn */ + pgprot_t hugeprot = + __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ + pte_val(pte)); + + cpte = huge_pte_offset(vma->vm_mm, addr); + pfn = pte_pfn(*cpte); + ncontig = find_num_contig(vma->vm_mm, addr, cpte, + *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) { + changed = ptep_set_access_flags(vma, addr, cpte, + pfn_pte(pfn, + hugeprot), + dirty); + pfn += pgsize >> PAGE_SHIFT; + } + return changed; + } else { + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + } +} + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + if (pte_cont(*ptep)) { + int ncontig, i; + pte_t *cpte; + size_t pgsize = 0; + + cpte = huge_pte_offset(mm, addr); + ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) + ptep_set_wrprotect(mm, addr, cpte); + } else { + ptep_set_wrprotect(mm, addr, ptep); + } +} + +void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + if (pte_cont(*ptep)) { + int ncontig, i; + pte_t *cpte; + size_t pgsize = 0; + + cpte = huge_pte_offset(vma->vm_mm, addr); + ncontig = find_num_contig(vma->vm_mm, addr, cpte, + *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) + ptep_clear_flush(vma, addr, cpte); + } else { + ptep_clear_flush(vma, addr, ptep); + } +} + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else if (ps == (PAGE_SIZE * CONT_PTES)) { + hugetlb_add_hstate(CONT_PTE_SHIFT); + } else if (ps == (PMD_SIZE * CONT_PMDS)) { + hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { - pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); + pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); return 0; } return 1; } __setup("hugepagesz=", setup_hugepagesz); + +#ifdef CONFIG_ARM64_64K_PAGES +static __init int add_default_hugepagesz(void) +{ + if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) + hugetlb_add_hstate(CONT_PMD_SHIFT); + return 0; +} +arch_initcall(add_default_hugepagesz); +#endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 17bf39ac83ba..f3b061e67bfe 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -71,7 +71,7 @@ early_param("initrd", early_initrd); * 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) +static phys_addr_t __init 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()); @@ -120,17 +120,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { - return memblock_is_memory(pfn << PAGE_SHIFT); + return memblock_is_map_memory(pfn << PAGE_SHIFT); } EXPORT_SYMBOL(pfn_valid); #endif #ifndef CONFIG_SPARSEMEM -static void arm64_memory_present(void) +static void __init arm64_memory_present(void) { } #else -static void arm64_memory_present(void) +static void __init arm64_memory_present(void) { struct memblock_region *reg; @@ -360,7 +360,6 @@ void free_initmem(void) { fixup_init(); free_initmem_default(0); - free_alternatives_memory(); } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 873e363048c6..58faeaa7fbdc 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -251,6 +251,14 @@ static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, { unsigned long addr, length, end, next; + /* + * If the virtual and physical address don't have the same offset + * within a page, we cannot map the region as the caller expects. + */ + if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) + return; + + phys &= PAGE_MASK; addr = virt & PAGE_MASK; length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); @@ -280,7 +288,7 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt, + __create_mapping(&init_mm, pgd_offset_k(virt), phys, virt, size, prot, early_alloc); } @@ -301,7 +309,7 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, return; } - return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), + return __create_mapping(&init_mm, pgd_offset_k(virt), phys, virt, size, prot, late_alloc); } @@ -372,6 +380,8 @@ static void __init map_mem(void) if (start >= end) break; + if (memblock_is_nomap(reg)) + continue; if (ARM64_SWAPPER_USES_SECTION_MAPS) { /* @@ -456,6 +466,9 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index cb3ba1b812e7..ae11d4e03d0e 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -46,14 +46,14 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } -static int __init pgd_cache_init(void) +void __init pgd_cache_init(void) { + if (PGD_SIZE == PAGE_SIZE) + return; + /* * Naturally aligned pgds required by the architecture. */ - if (PGD_SIZE != PAGE_SIZE) - pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, - SLAB_PANIC, NULL); - return 0; + pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, + SLAB_PANIC, NULL); } -core_initcall(pgd_cache_init); diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 4c4d93c4bf65..146bd99a7532 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -62,3 +62,25 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * Macro to perform a data cache maintenance for the interval + * [kaddr, kaddr + size) + * + * op: operation passed to dc instruction + * domain: domain used in dsb instruciton + * kaddr: starting virtual address of the region + * size: size of the region + * Corrupts: kaddr, size, tmp1, tmp2 + */ + .macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2 + dcache_line_size \tmp1, \tmp2 + add \size, \kaddr, \size + sub \tmp2, \tmp1, #1 + bic \kaddr, \kaddr, \tmp2 +9998: dc \op, \kaddr + add \kaddr, \kaddr, \tmp1 + cmp \kaddr, \size + b.lo 9998b + dsb \domain + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cacecc4ad3e5..b6f9053ab184 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -139,8 +139,6 @@ ENTRY(cpu_do_switch_mm) ret ENDPROC(cpu_do_switch_mm) - .section ".text.init", #alloc, #execinstr - /* * __cpu_setup * diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index ec379a4164cc..f292917b00e7 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -18,3 +18,6 @@ obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o obj-$(CONFIG_EFI_RUNTIME_WRAPPERS) += runtime-wrappers.o obj-$(CONFIG_EFI_STUB) += libstub/ obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_mem.o + +arm-obj-$(CONFIG_EFI) := arm-init.o arm-runtime.o +obj-$(CONFIG_ARM64) += $(arm-obj-y) diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c new file mode 100644 index 000000000000..9e15d571b53c --- /dev/null +++ b/drivers/firmware/efi/arm-init.c @@ -0,0 +1,209 @@ +/* + * Extensible Firmware Interface + * + * Based on Extensible Firmware Interface Specification version 2.4 + * + * Copyright (C) 2013 - 2015 Linaro Ltd. + * + * 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 +#include +#include +#include +#include +#include + +#include + +struct efi_memory_map memmap; + +u64 efi_system_table; + +static int __init is_normal_ram(efi_memory_desc_t *md) +{ + if (md->attribute & EFI_MEMORY_WB) + return 1; + return 0; +} + +/* + * Translate a EFI virtual address into a physical address: this is necessary, + * as some data members of the EFI system table are virtually remapped after + * SetVirtualAddressMap() has been called. + */ +static phys_addr_t efi_to_phys(unsigned long addr) +{ + efi_memory_desc_t *md; + + for_each_efi_memory_desc(&memmap, md) { + if (!(md->attribute & EFI_MEMORY_RUNTIME)) + continue; + if (md->virt_addr == 0) + /* no virtual mapping has been installed by the stub */ + break; + if (md->virt_addr <= addr && + (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT)) + return md->phys_addr + addr - md->virt_addr; + } + return addr; +} + +static int __init uefi_init(void) +{ + efi_char16_t *c16; + void *config_tables; + size_t table_size; + char vendor[100] = "unknown"; + int i, retval; + + efi.systab = early_memremap(efi_system_table, + sizeof(efi_system_table_t)); + if (efi.systab == NULL) { + pr_warn("Unable to map EFI system table.\n"); + return -ENOMEM; + } + + set_bit(EFI_BOOT, &efi.flags); + if (IS_ENABLED(CONFIG_64BIT)) + set_bit(EFI_64BIT, &efi.flags); + + /* + * Verify the EFI Table + */ + if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { + pr_err("System table signature incorrect\n"); + retval = -EINVAL; + goto out; + } + if ((efi.systab->hdr.revision >> 16) < 2) + pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff); + + /* Show what we know for posterity */ + c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor), + sizeof(vendor) * sizeof(efi_char16_t)); + if (c16) { + for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) + vendor[i] = c16[i]; + vendor[i] = '\0'; + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); + } + + pr_info("EFI v%u.%.02u by %s\n", + efi.systab->hdr.revision >> 16, + efi.systab->hdr.revision & 0xffff, vendor); + + table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables; + config_tables = early_memremap(efi_to_phys(efi.systab->tables), + table_size); + if (config_tables == NULL) { + pr_warn("Unable to map EFI config table array.\n"); + retval = -ENOMEM; + goto out; + } + retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables, + sizeof(efi_config_table_t), NULL); + + early_memunmap(config_tables, table_size); +out: + early_memunmap(efi.systab, sizeof(efi_system_table_t)); + return retval; +} + +/* + * Return true for RAM regions we want to permanently reserve. + */ +static __init int is_reserve_region(efi_memory_desc_t *md) +{ + switch (md->type) { + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: + return 0; + default: + break; + } + return is_normal_ram(md); +} + +static __init void reserve_regions(void) +{ + efi_memory_desc_t *md; + u64 paddr, npages, size; + + if (efi_enabled(EFI_DBG)) + pr_info("Processing EFI memory map:\n"); + + for_each_efi_memory_desc(&memmap, md) { + paddr = md->phys_addr; + npages = md->num_pages; + + if (efi_enabled(EFI_DBG)) { + char buf[64]; + + pr_info(" 0x%012llx-0x%012llx %s", + paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1, + efi_md_typeattr_format(buf, sizeof(buf), md)); + } + + memrange_efi_to_native(&paddr, &npages); + size = npages << PAGE_SHIFT; + + if (is_normal_ram(md)) + early_init_dt_add_memory_arch(paddr, size); + + if (is_reserve_region(md)) { + memblock_mark_nomap(paddr, size); + if (efi_enabled(EFI_DBG)) + pr_cont("*"); + } + + if (efi_enabled(EFI_DBG)) + pr_cont("\n"); + } + + set_bit(EFI_MEMMAP, &efi.flags); +} + +void __init efi_init(void) +{ + struct efi_fdt_params params; + + /* Grab UEFI information placed in FDT by stub */ + if (!efi_get_fdt_params(¶ms)) + return; + + efi_system_table = params.system_table; + + memmap.phys_map = params.mmap; + memmap.map = early_memremap(params.mmap, params.mmap_size); + if (memmap.map == NULL) { + /* + * If we are booting via UEFI, the UEFI memory map is the only + * description of memory we have, so there is little point in + * proceeding if we cannot access it. + */ + panic("Unable to map EFI memory map.\n"); + } + memmap.map_end = memmap.map + params.mmap_size; + memmap.desc_size = params.desc_size; + memmap.desc_version = params.desc_ver; + + if (uefi_init() < 0) + return; + + reserve_regions(); + early_memunmap(memmap.map, params.mmap_size); + memblock_mark_nomap(params.mmap & PAGE_MASK, + PAGE_ALIGN(params.mmap_size + + (params.mmap & ~PAGE_MASK))); +} diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c new file mode 100644 index 000000000000..6ae21e41a429 --- /dev/null +++ b/drivers/firmware/efi/arm-runtime.c @@ -0,0 +1,135 @@ +/* + * Extensible Firmware Interface + * + * Based on Extensible Firmware Interface Specification version 2.4 + * + * Copyright (C) 2013, 2014 Linaro Ltd. + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +extern u64 efi_system_table; + +static struct mm_struct efi_mm = { + .mm_rb = RB_ROOT, + .mm_users = ATOMIC_INIT(2), + .mm_count = ATOMIC_INIT(1), + .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), + .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), + .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), +}; + +static bool __init efi_virtmap_init(void) +{ + efi_memory_desc_t *md; + + efi_mm.pgd = pgd_alloc(&efi_mm); + init_new_context(NULL, &efi_mm); + + for_each_efi_memory_desc(&memmap, md) { + phys_addr_t phys = md->phys_addr; + int ret; + + if (!(md->attribute & EFI_MEMORY_RUNTIME)) + continue; + if (md->virt_addr == 0) + return false; + + ret = efi_create_mapping(&efi_mm, md); + if (!ret) { + pr_info(" EFI remap %pa => %p\n", + &phys, (void *)(unsigned long)md->virt_addr); + } else { + pr_warn(" EFI remap %pa: failed to create mapping (%d)\n", + &phys, ret); + return false; + } + } + return true; +} + +/* + * Enable the UEFI Runtime Services if all prerequisites are in place, i.e., + * non-early mapping of the UEFI system table and virtual mappings for all + * EFI_MEMORY_RUNTIME regions. + */ +static int __init arm_enable_runtime_services(void) +{ + u64 mapsize; + + if (!efi_enabled(EFI_BOOT)) { + pr_info("EFI services will not be available.\n"); + return 0; + } + + if (efi_runtime_disabled()) { + pr_info("EFI runtime services will be disabled.\n"); + return 0; + } + + pr_info("Remapping and enabling EFI services.\n"); + + mapsize = memmap.map_end - memmap.map; + memmap.map = (__force void *)ioremap_cache(memmap.phys_map, + mapsize); + if (!memmap.map) { + pr_err("Failed to remap EFI memory map\n"); + return -ENOMEM; + } + memmap.map_end = memmap.map + mapsize; + efi.memmap = &memmap; + + efi.systab = (__force void *)ioremap_cache(efi_system_table, + sizeof(efi_system_table_t)); + if (!efi.systab) { + pr_err("Failed to remap EFI System Table\n"); + return -ENOMEM; + } + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + + if (!efi_virtmap_init()) { + pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n"); + return -ENOMEM; + } + + /* Set up runtime services function pointers */ + efi_native_runtime_setup(); + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + + efi.runtime_version = efi.systab->hdr.revision; + + return 0; +} +early_initcall(arm_enable_runtime_services); + +void efi_virtmap_load(void) +{ + preempt_disable(); + efi_set_pgd(&efi_mm); +} + +void efi_virtmap_unload(void) +{ + efi_set_pgd(current->active_mm); + preempt_enable(); +} diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 027ca212179f..cffa89b3317b 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -25,6 +25,8 @@ #include #include +#include + struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 3c0467d3688c..c0ddd1b8dca3 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -8,7 +8,7 @@ cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \ -fPIC -fno-strict-aliasing -mno-red-zone \ - -mno-mmx -mno-sse -DDISABLE_BRANCH_PROFILING + -mno-mmx -mno-sse cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS)) cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ @@ -16,7 +16,7 @@ cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt -KBUILD_CFLAGS := $(cflags-y) \ +KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ $(call cc-option,-ffreestanding) \ $(call cc-option,-fno-stack-protector) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 685c262e0be8..b0eb06423d5e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -96,9 +96,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, struct address_space *mapping, pgoff_t idx, unsigned long address); -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); -#endif extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 24daf8fc4d7c..fec66f86eeff 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 +83,7 @@ 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); ulong choose_memblock_flags(void); /* Low level functions */ @@ -184,6 +186,11 @@ 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); @@ -319,6 +326,7 @@ 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); +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_region_reserved(phys_addr_t base, phys_addr_t size); diff --git a/mm/memblock.c b/mm/memblock.c index d300f1329814..07ff069fef25 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -822,6 +822,17 @@ 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); +} /** * __next_reserved_mem_region - next function for for_each_reserved_region() @@ -913,6 +924,10 @@ 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 +1037,10 @@ 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; @@ -1519,6 +1538,15 @@ int __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)