Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "Here's the usual mixed bag of arm64 updates, also including some
  related EFI changes (Acked by Matt) and the MMU gather range cleanup
  (Acked by you).

  Changes include:
   - support for alternative instruction patching from Andre
   - seccomp from Akashi
   - some AArch32 instruction emulation, required by the Android folks
   - optimisations for exception entry/exit code, cmpxchg, pcpu atomics
   - mmu_gather range calculations moved into core code
   - EFI updates from Ard, including long-awaited SMBIOS support
   - /proc/cpuinfo fixes to align with the format used by arch/arm/
   - a few non-critical fixes across the architecture"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (70 commits)
  arm64: remove the unnecessary arm64_swiotlb_init()
  arm64: add module support for alternatives fixups
  arm64: perf: Prevent wraparound during overflow
  arm64/include/asm: Fixed a warning about 'struct pt_regs'
  arm64: Provide a namespace to NCAPS
  arm64: bpf: lift restriction on last instruction
  arm64: Implement support for read-mostly sections
  arm64: compat: align cacheflush syscall with arch/arm
  arm64: add seccomp support
  arm64: add SIGSYS siginfo for compat task
  arm64: add seccomp syscall for compat task
  asm-generic: add generic seccomp.h for secure computing mode 1
  arm64: ptrace: allow tracer to skip a system call
  arm64: ptrace: add NT_ARM_SYSTEM_CALL regset
  arm64: Move some head.text functions to executable section
  arm64: jump labels: NOP out NOP -> NOP replacement
  arm64: add support to dump the kernel page tables
  arm64: Add FIX_HOLE to permanent fixed addresses
  arm64: alternatives: fix pr_fmt string for consistency
  arm64: vmlinux.lds.S: don't discard .exit.* sections at link-time
  ...

1 files changed, 215 insertions, 0 deletions

diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 5279e5733386..09da25bc596f 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -44,6 +44,221 @@ static inline unsigned long __my_cpu_offset(void)
 
 #endif /* CONFIG_SMP */
 
+#define PERCPU_OP(op, asm_op)						\
+static inline unsigned long __percpu_##op(void *ptr,			\
+			unsigned long val, int size)			\
+{									\
+	unsigned long loop, ret;					\
+									\
+	switch (size) {							\
+	case 1:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_1\n"			\
+			"ldxrb	  %w[ret], %[ptr]\n"			\
+			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
+			"stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr] "+Q"(*(u8 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	case 2:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_2\n"			\
+			"ldxrh	  %w[ret], %[ptr]\n"			\
+			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
+			"stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr]  "+Q"(*(u16 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	case 4:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_4\n"			\
+			"ldxr	  %w[ret], %[ptr]\n"			\
+			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
+			"stxr	  %w[loop], %w[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr] "+Q"(*(u32 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	case 8:								\
+		do {							\
+			asm ("//__per_cpu_" #op "_8\n"			\
+			"ldxr	  %[ret], %[ptr]\n"			\
+			#asm_op " %[ret], %[ret], %[val]\n"		\
+			"stxr	  %w[loop], %[ret], %[ptr]\n"		\
+			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
+			  [ptr] "+Q"(*(u64 *)ptr)			\
+			: [val] "Ir" (val));				\
+		} while (loop);						\
+		break;							\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	return ret;							\
+}
+
+PERCPU_OP(add, add)
+PERCPU_OP(and, and)
+PERCPU_OP(or, orr)
+#undef PERCPU_OP
+
+static inline unsigned long __percpu_read(void *ptr, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+	case 1:
+		ret = ACCESS_ONCE(*(u8 *)ptr);
+		break;
+	case 2:
+		ret = ACCESS_ONCE(*(u16 *)ptr);
+		break;
+	case 4:
+		ret = ACCESS_ONCE(*(u32 *)ptr);
+		break;
+	case 8:
+		ret = ACCESS_ONCE(*(u64 *)ptr);
+		break;
+	default:
+		BUILD_BUG();
+	}
+
+	return ret;
+}
+
+static inline void __percpu_write(void *ptr, unsigned long val, int size)
+{
+	switch (size) {
+	case 1:
+		ACCESS_ONCE(*(u8 *)ptr) = (u8)val;
+		break;
+	case 2:
+		ACCESS_ONCE(*(u16 *)ptr) = (u16)val;
+		break;
+	case 4:
+		ACCESS_ONCE(*(u32 *)ptr) = (u32)val;
+		break;
+	case 8:
+		ACCESS_ONCE(*(u64 *)ptr) = (u64)val;
+		break;
+	default:
+		BUILD_BUG();
+	}
+}
+
+static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
+						int size)
+{
+	unsigned long ret, loop;
+
+	switch (size) {
+	case 1:
+		do {
+			asm ("//__percpu_xchg_1\n"
+			"ldxrb %w[ret], %[ptr]\n"
+			"stxrb %w[loop], %w[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u8 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	case 2:
+		do {
+			asm ("//__percpu_xchg_2\n"
+			"ldxrh %w[ret], %[ptr]\n"
+			"stxrh %w[loop], %w[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u16 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	case 4:
+		do {
+			asm ("//__percpu_xchg_4\n"
+			"ldxr %w[ret], %[ptr]\n"
+			"stxr %w[loop], %w[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u32 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	case 8:
+		do {
+			asm ("//__percpu_xchg_8\n"
+			"ldxr %[ret], %[ptr]\n"
+			"stxr %w[loop], %[val], %[ptr]\n"
+			: [loop] "=&r"(loop), [ret] "=&r"(ret),
+			  [ptr] "+Q"(*(u64 *)ptr)
+			: [val] "r" (val));
+		} while (loop);
+		break;
+	default:
+		BUILD_BUG();
+	}
+
+	return ret;
+}
+
+#define _percpu_add(pcp, val) \
+	__percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+
+#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val))
+
+#define _percpu_and(pcp, val) \
+	__percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+
+#define _percpu_or(pcp, val) \
+	__percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+
+#define _percpu_read(pcp) (typeof(pcp))	\
+	(__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp)))
+
+#define _percpu_write(pcp, val) \
+	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))
+
+#define _percpu_xchg(pcp, val) (typeof(pcp)) \
+	(__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)))
+
+#define this_cpu_add_1(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_2(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_4(pcp, val) _percpu_add(pcp, val)
+#define this_cpu_add_8(pcp, val) _percpu_add(pcp, val)
+
+#define this_cpu_add_return_1(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_2(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_4(pcp, val) _percpu_add_return(pcp, val)
+#define this_cpu_add_return_8(pcp, val) _percpu_add_return(pcp, val)
+
+#define this_cpu_and_1(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_2(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_4(pcp, val) _percpu_and(pcp, val)
+#define this_cpu_and_8(pcp, val) _percpu_and(pcp, val)
+
+#define this_cpu_or_1(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_2(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_4(pcp, val) _percpu_or(pcp, val)
+#define this_cpu_or_8(pcp, val) _percpu_or(pcp, val)
+
+#define this_cpu_read_1(pcp) _percpu_read(pcp)
+#define this_cpu_read_2(pcp) _percpu_read(pcp)
+#define this_cpu_read_4(pcp) _percpu_read(pcp)
+#define this_cpu_read_8(pcp) _percpu_read(pcp)
+
+#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
+#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
+
+#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val)
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */