aboutsummaryrefslogtreecommitdiff
path: root/arch/arm64/include/asm
diff options
context:
space:
mode:
authorMark Brown <broonie@linaro.org>2014-05-15 20:29:29 +0100
committerMark Brown <broonie@linaro.org>2014-05-15 20:29:29 +0100
commita5d53ad243dc3178fa9001d8ab1f19c63f8debd5 (patch)
tree0139239f56b2dea497a003b4512a4ba849591306 /arch/arm64/include/asm
parent15fdd2469e03d44975d548a73e689a725e76a5ee (diff)
parent8751cf9a6c5f5bf02a2de8a4c025e09b38556df4 (diff)
Merge remote-tracking branch 'lsk/v3.10/topic/arm64-misc' into linux-linaro-lsk
Conflicts: Documentation/arm64/tagged-pointers.txt arch/arm64/Kconfig arch/arm64/boot/dts/Makefile arch/arm64/include/asm/arch_timer.h arch/arm64/include/asm/elf.h arch/arm64/include/asm/spinlock.h arch/arm64/kernel/smp.c
Diffstat (limited to 'arch/arm64/include/asm')
-rw-r--r--arch/arm64/include/asm/cacheflush.h3
-rw-r--r--arch/arm64/include/asm/cmpxchg.h2
-rw-r--r--arch/arm64/include/asm/cputype.h3
-rw-r--r--arch/arm64/include/asm/debug-monitors.h2
-rw-r--r--arch/arm64/include/asm/device.h3
-rw-r--r--arch/arm64/include/asm/elf.h3
-rw-r--r--arch/arm64/include/asm/hwcap.h2
-rw-r--r--arch/arm64/include/asm/memory.h11
-rw-r--r--arch/arm64/include/asm/mmu_context.h6
-rw-r--r--arch/arm64/include/asm/pgtable-2level-hwdef.h4
-rw-r--r--arch/arm64/include/asm/pgtable-2level-types.h2
-rw-r--r--arch/arm64/include/asm/pgtable.h6
-rw-r--r--arch/arm64/include/asm/ptrace.h2
-rw-r--r--arch/arm64/include/asm/spinlock.h83
-rw-r--r--arch/arm64/include/asm/spinlock_types.h10
-rw-r--r--arch/arm64/include/asm/timex.h6
16 files changed, 91 insertions, 57 deletions
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d6ac12e11867..4c60e64a801c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -131,9 +131,6 @@ static inline void __flush_icache_all(void)
#define flush_dcache_mmap_unlock(mapping) \
spin_unlock_irq(&(mapping)->tree_lock)
-#define flush_icache_user_range(vma,page,addr,len) \
- flush_dcache_page(page)
-
/*
* We don't appear to need to do anything here. In fact, if we did, we'd
* duplicate cache flushing elsewhere performed by flush_dcache_page().
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 68d7c932a9c3..c558da59989e 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -179,4 +179,6 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
#define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n))
#define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n))
+#define cmpxchg64_relaxed(ptr,o,n) cmpxchg_local((ptr),(o),(n))
+
#endif /* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index a8053d89512f..e371936b8ab2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -47,11 +47,14 @@
})
#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_A57 0xD070
+#define APM_CPU_PART_POTENZA 0x0000
+
#ifndef __ASSEMBLY__
/*
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7eaa0b302493..a2232d07be9d 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -83,6 +83,8 @@ static inline int reinstall_suspended_bps(struct pt_regs *regs)
}
#endif
+int aarch32_break_handler(struct pt_regs *regs);
+
#endif /* __ASSEMBLY */
#endif /* __KERNEL__ */
#endif /* __ASM_DEBUG_MONITORS_H */
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 0d8453c755a8..cf98b362094b 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -18,6 +18,9 @@
struct dev_archdata {
struct dma_map_ops *dma_ops;
+#ifdef CONFIG_IOMMU_API
+ void *iommu; /* private IOMMU data */
+#endif
};
struct pdev_archdata {
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 212b0b615b4a..01d3aab64b79 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -33,8 +33,6 @@ typedef unsigned long elf_greg_t;
typedef elf_greg_t elf_gregset_t[ELF_NGREG];
typedef struct user_fpsimd_state elf_fpregset_t;
-#define EM_AARCH64 183
-
/*
* AArch64 static relocation types.
*/
@@ -164,7 +162,6 @@ extern unsigned long arch_randomize_brk(struct mm_struct *mm);
#define arch_randomize_brk arch_randomize_brk
#ifdef CONFIG_COMPAT
-#define EM_ARM 40
#ifdef __AARCH64EB__
#define COMPAT_ELF_PLATFORM ("v8b")
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 3a48433dfb57..6cddbb0c9f54 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -44,6 +44,6 @@
extern unsigned int compat_elf_hwcap;
#endif
-extern unsigned int elf_hwcap;
+extern unsigned long elf_hwcap;
#endif
#endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 381f556b664e..9abb57d743b9 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -33,18 +33,23 @@
#define UL(x) _AC(x, UL)
/*
- * PAGE_OFFSET - the virtual address of the start of the kernel image.
+ * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * (VA_BITS - 1))
* VA_BITS - the maximum number of bits for virtual addresses.
* TASK_SIZE - the maximum size of a user space task.
* TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
* The module space lives between the addresses given by TASK_SIZE
* and PAGE_OFFSET - it must be within 128MB of the kernel text.
*/
-#define PAGE_OFFSET UL(0xffffffc000000000)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define VA_BITS (42)
+#else
+#define VA_BITS (39)
+#endif
+#define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1))
#define MODULES_END (PAGE_OFFSET)
#define MODULES_VADDR (MODULES_END - SZ_64M)
#define EARLYCON_IOBASE (MODULES_VADDR - SZ_4M)
-#define VA_BITS (39)
#define TASK_SIZE_64 (UL(1) << VA_BITS)
#ifdef CONFIG_COMPAT
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index e2bc385adb6b..a9eee33dfa62 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,12 +151,6 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
{
unsigned int cpu = smp_processor_id();
-#ifdef CONFIG_SMP
- /* check for possible thread migration */
- if (!cpumask_empty(mm_cpumask(next)) &&
- !cpumask_test_cpu(cpu, mm_cpumask(next)))
- __flush_icache_all();
-#endif
if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
check_and_switch_context(next, tsk);
}
diff --git a/arch/arm64/include/asm/pgtable-2level-hwdef.h b/arch/arm64/include/asm/pgtable-2level-hwdef.h
index 0a8ed3f94e93..2593b490c56a 100644
--- a/arch/arm64/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-2level-hwdef.h
@@ -21,10 +21,10 @@
* 8192 entries of 8 bytes each, occupying a 64KB page. Levels 0 and 1 are not
* used. The 2nd level table (PGD for Linux) can cover a range of 4TB, each
* entry representing 512MB. The user and kernel address spaces are limited to
- * 512GB and therefore we only use 1024 entries in the PGD.
+ * 4TB in the 64KB page configuration.
*/
#define PTRS_PER_PTE 8192
-#define PTRS_PER_PGD 1024
+#define PTRS_PER_PGD 8192
/*
* PGDIR_SHIFT determines the size a top-level page table entry can map.
diff --git a/arch/arm64/include/asm/pgtable-2level-types.h b/arch/arm64/include/asm/pgtable-2level-types.h
index 3c3ca7d361e4..5f101e63dfc1 100644
--- a/arch/arm64/include/asm/pgtable-2level-types.h
+++ b/arch/arm64/include/asm/pgtable-2level-types.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PGTABLE_2LEVEL_TYPES_H
#define __ASM_PGTABLE_2LEVEL_TYPES_H
+#include <asm/types.h>
+
typedef u64 pteval_t;
typedef u64 pgdval_t;
typedef pgdval_t pmdval_t;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b8940733ee30..608ec24f2f52 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -34,7 +34,7 @@
/*
* VMALLOC and SPARSEMEM_VMEMMAP ranges.
*/
-#define VMALLOC_START UL(0xffffff8000000000)
+#define VMALLOC_START (UL(0xffffffffffffffff) << VA_BITS)
#define VMALLOC_END (PAGE_OFFSET - UL(0x400000000) - SZ_64K)
#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K))
@@ -120,7 +120,7 @@ extern struct page *empty_zero_page;
#define pte_none(pte) (!pte_val(pte))
#define pte_clear(mm,addr,ptep) set_pte(ptep, __pte(0))
#define pte_page(pte) (pfn_to_page(pte_pfn(pte)))
-#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + __pte_index(addr))
+#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + pte_index(addr))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr))
@@ -361,7 +361,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#endif
/* Find an entry in the third-level page table.. */
-#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 491bea413fb1..0e7fa4963735 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -172,7 +172,5 @@ extern unsigned long profile_pc(struct pt_regs *regs);
#define profile_pc(regs) instruction_pointer(regs)
#endif
-extern int aarch32_break_trap(struct pt_regs *regs);
-
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 0defa0728a9b..3d5cf064d7a1 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -22,17 +22,10 @@
/*
* Spinlock implementation.
*
- * The old value is read exclusively and the new one, if unlocked, is written
- * exclusively. In case of failure, the loop is restarted.
- *
* The memory barriers are implicit with the load-acquire and store-release
* instructions.
- *
- * Unlocked value: 0
- * Locked value: 1
*/
-#define arch_spin_is_locked(x) ((x)->lock != 0)
#define arch_spin_unlock_wait(lock) \
do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
@@ -41,32 +34,51 @@
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
unsigned int tmp;
+ arch_spinlock_t lockval, newval;
asm volatile(
- " sevl\n"
- "1: wfe\n"
- "2: ldaxr %w0, %1\n"
- " cbnz %w0, 1b\n"
- " stxr %w0, %w2, %1\n"
- " cbnz %w0, 2b\n"
- : "=&r" (tmp), "+Q" (lock->lock)
- : "r" (1)
- : "cc", "memory");
+ /* Atomically increment the next ticket. */
+" prfm pstl1strm, %3\n"
+"1: ldaxr %w0, %3\n"
+" add %w1, %w0, %w5\n"
+" stxr %w2, %w1, %3\n"
+" cbnz %w2, 1b\n"
+ /* Did we get the lock? */
+" eor %w1, %w0, %w0, ror #16\n"
+" cbz %w1, 3f\n"
+ /*
+ * No: spin on the owner. Send a local event to avoid missing an
+ * unlock before the exclusive load.
+ */
+" sevl\n"
+"2: wfe\n"
+" ldaxrh %w2, %4\n"
+" eor %w1, %w2, %w0, lsr #16\n"
+" cbnz %w1, 2b\n"
+ /* We got the lock. Critical section starts here. */
+"3:"
+ : "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
+ : "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
+ : "memory");
}
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
unsigned int tmp;
+ arch_spinlock_t lockval;
asm volatile(
- "2: ldaxr %w0, %1\n"
- " cbnz %w0, 1f\n"
- " stxr %w0, %w2, %1\n"
- " cbnz %w0, 2b\n"
- "1:\n"
- : "=&r" (tmp), "+Q" (lock->lock)
- : "r" (1)
- : "cc", "memory");
+" prfm pstl1strm, %2\n"
+"1: ldaxr %w0, %2\n"
+" eor %w1, %w0, %w0, ror #16\n"
+" cbnz %w1, 2f\n"
+" add %w0, %w0, %3\n"
+" stxr %w1, %w0, %2\n"
+" cbnz %w1, 1b\n"
+"2:"
+ : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+ : "I" (1 << TICKET_SHIFT)
+ : "memory");
return !tmp;
}
@@ -74,9 +86,28 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
asm volatile(
- " stlr %w1, %0\n"
- : "=Q" (lock->lock) : "r" (0) : "memory");
+" stlrh %w1, %0\n"
+ : "=Q" (lock->owner)
+ : "r" (lock->owner + 1)
+ : "memory");
+}
+
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+ return lock.owner == lock.next;
+}
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+ return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+ arch_spinlock_t lockval = ACCESS_ONCE(*lock);
+ return (lockval.next - lockval.owner) > 1;
}
+#define arch_spin_is_contended arch_spin_is_contended
/*
* Write lock implementation.
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 9a494346efed..87692750ed94 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,14 +20,14 @@
# error "please don't include this file directly"
#endif
-/* We only require natural alignment for exclusive accesses. */
-#define __lock_aligned
+#define TICKET_SHIFT 16
typedef struct {
- volatile unsigned int lock;
-} arch_spinlock_t;
+ u16 owner;
+ u16 next;
+} __aligned(4) arch_spinlock_t;
-#define __ARCH_SPIN_LOCK_UNLOCKED { 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED { 0 , 0 }
typedef struct {
volatile unsigned int lock;
diff --git a/arch/arm64/include/asm/timex.h b/arch/arm64/include/asm/timex.h
index b24a31a7e2c9..81a076eb37fa 100644
--- a/arch/arm64/include/asm/timex.h
+++ b/arch/arm64/include/asm/timex.h
@@ -16,14 +16,14 @@
#ifndef __ASM_TIMEX_H
#define __ASM_TIMEX_H
+#include <asm/arch_timer.h>
+
/*
* Use the current timer as a cycle counter since this is what we use for
* the delay loop.
*/
-#define get_cycles() ({ cycles_t c; read_current_timer(&c); c; })
+#define get_cycles() arch_counter_get_cntvct()
#include <asm-generic/timex.h>
-#define ARCH_HAS_READ_CURRENT_TIMER
-
#endif