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

Pull arm64 fixes and clean-ups from Catalin Marinas:
 "Here's a second pull request for this merging window with some
  fixes/clean-ups:

   - __cmpxchg_double*() return type fix to avoid truncation of a long
     to int and subsequent logical "not" in cmpxchg_double()
     misinterpreting the operation success/failure

   - BPF fixes for mod and div by zero

   - Fix compilation with STRICT_MM_TYPECHECKS enabled

   - VDSO build fix without libgcov

   - Some static and __maybe_unused annotations

   - Kconfig clean-up (FRAME_POINTER)

   - defconfig update for CRYPTO_CRC32_ARM64"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: suspend: make hw_breakpoint_restore static
  arm64: mmu: make split_pud and fixup_executable static
  arm64: smp: make of_parse_and_init_cpus static
  arm64: use linux/types.h in kvm.h
  arm64: build vdso without libgcov
  arm64: mark cpus_have_hwcap as __maybe_unused
  arm64: remove redundant FRAME_POINTER kconfig option and force to select it
  arm64: fix R/O permissions of FDT mapping
  arm64: fix STRICT_MM_TYPECHECKS issue in PTE_CONT manipulation
  arm64: bpf: fix mod-by-zero case
  arm64: bpf: fix div-by-zero case
  arm64: Enable CRYPTO_CRC32_ARM64 in defconfig
  arm64: cmpxchg_dbl: fix return value type

arch/arm64/Kconfig

@@ -27,6 +27,7 @@ config ARM64
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
 	select EDAC_SUPPORT
+	select FRAME_POINTER
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST

arch/arm64/Kconfig.debug

@@ -2,10 +2,6 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
-config FRAME_POINTER
-	bool
-	default y
-
 config ARM64_PTDUMP
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL

arch/arm64/configs/defconfig

@@ -224,3 +224,4 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y
 CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
 CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
 CONFIG_CRYPTO_AES_ARM64_NEON_BLK=y
+CONFIG_CRYPTO_CRC32_ARM64=y

arch/arm64/include/asm/atomic_ll_sc.h

@@ -233,7 +233,7 @@ __CMPXCHG_CASE( ,  ,  mb_8, dmb ish,  , l, "memory")
 #undef __CMPXCHG_CASE
 
 #define __CMPXCHG_DBL(name, mb, rel, cl)				\
-__LL_SC_INLINE int							\
+__LL_SC_INLINE long							\
 __LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1,		\
 				      unsigned long old2,		\
 				      unsigned long new1,		\

arch/arm64/include/asm/atomic_lse.h

@@ -387,7 +387,7 @@ __CMPXCHG_CASE(x,  ,  mb_8, al, "memory")
 #define __LL_SC_CMPXCHG_DBL(op)	__LL_SC_CALL(__cmpxchg_double##op)
 
 #define __CMPXCHG_DBL(name, mb, cl...)					\
-static inline int __cmpxchg_double##name(unsigned long old1,		\
+static inline long __cmpxchg_double##name(unsigned long old1,		\
 					 unsigned long old2,		\
 					 unsigned long new1,		\
 					 unsigned long new2,		\

arch/arm64/include/asm/pgtable.h

@@ -80,6 +80,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define _PAGE_DEFAULT		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 

arch/arm64/include/uapi/asm/kvm.h

@@ -32,7 +32,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/psci.h>
-#include <asm/types.h>
+#include <linux/types.h>
 #include <asm/ptrace.h>
 
 #define __KVM_HAVE_GUEST_DEBUG

arch/arm64/kernel/cpufeature.c

@@ -696,7 +696,7 @@ static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
 }
 
 /* Check if we have a particular HWCAP enabled */
-static bool cpus_have_hwcap(const struct arm64_cpu_capabilities *cap)
+static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	bool rc;
 

arch/arm64/kernel/smp.c

@@ -473,7 +473,7 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
  * cpu logical map array containing MPIDR values related to logical
  * cpus. Assumes that cpu_logical_map(0) has already been initialized.
  */
-void __init of_parse_and_init_cpus(void)
+static void __init of_parse_and_init_cpus(void)
 {
 	struct device_node *dn = NULL;
 

arch/arm64/kernel/suspend.c

@@ -41,7 +41,7 @@ void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr,
  * time the notifier runs debug exceptions might have been enabled already,
  * with HW breakpoints registers content still in an unknown state.
  */
-void (*hw_breakpoint_restore)(void *);
+static void (*hw_breakpoint_restore)(void *);
 void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 {
 	/* Prevent multiple restore hook initializations */

arch/arm64/kernel/vdso/Makefile

@@ -15,6 +15,9 @@ ccflags-y := -shared -fno-common -fno-builtin
 ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+
 # Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
 # down to collect2, resulting in silent corruption of the vDSO image.
 ccflags-y += -Wl,-shared

arch/arm64/mm/mmu.c

@@ -146,7 +146,7 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 		if (((addr | next | phys) & ~CONT_MASK) == 0) {
 			/* a block of CONT_PTES  */
 			__populate_init_pte(pte, addr, next, phys,
-					    prot | __pgprot(PTE_CONT));
+					    __pgprot(pgprot_val(prot) | PTE_CONT));
 		} else {
 			/*
 			 * If the range being split is already inside of a
@@ -165,7 +165,7 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (addr != end);
 }
 
-void split_pud(pud_t *old_pud, pmd_t *pmd)
+static void split_pud(pud_t *old_pud, pmd_t *pmd)
 {
 	unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT;
 	pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr);
@@ -447,7 +447,7 @@ static void __init map_mem(void)
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 }
 
-void __init fixup_executable(void)
+static void __init fixup_executable(void)
 {
 #ifdef CONFIG_DEBUG_RODATA
 	/* now that we are actually fully mapped, make the start/end more fine grained */
@@ -691,7 +691,7 @@ void __set_fixmap(enum fixed_addresses idx,
 void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 {
 	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
-	pgprot_t prot = PAGE_KERNEL | PTE_RDONLY;
+	pgprot_t prot = PAGE_KERNEL_RO;
 	int size, offset;
 	void *dt_virt;
 

arch/arm64/net/bpf_jit.h

 /*
  * BPF JIT compiler for ARM64
  *
- * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com>
+ * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com>
  *
  * 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
@@ -35,6 +35,7 @@
 	aarch64_insn_gen_comp_branch_imm(0, offset, Rt, A64_VARIANT(sf), \
 		AARCH64_INSN_BRANCH_COMP_##type)
 #define A64_CBZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, ZERO)
+#define A64_CBNZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, NONZERO)
 
 /* Conditional branch (immediate) */
 #define A64_COND_BRANCH(cond, offset) \

arch/arm64/net/bpf_jit_comp.c

 /*
  * BPF JIT compiler for ARM64
  *
- * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com>
+ * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com>
  *
  * 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
@@ -225,6 +225,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	u8 jmp_cond;
 	s32 jmp_offset;
 
+#define check_imm(bits, imm) do {				\
+	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
+	    (((imm) < 0) && (~(imm) >> (bits)))) {		\
+		pr_info("[%2d] imm=%d(0x%x) out of range\n",	\
+			i, imm, imm);				\
+		return -EINVAL;					\
+	}							\
+} while (0)
+#define check_imm19(imm) check_imm(19, imm)
+#define check_imm26(imm) check_imm(26, imm)
+
 	switch (code) {
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
@@ -258,15 +269,33 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit(A64_UDIV(is64, dst, dst, src), ctx);
-		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-		ctx->tmp_used = 1;
-		emit(A64_UDIV(is64, tmp, dst, src), ctx);
-		emit(A64_MUL(is64, tmp, tmp, src), ctx);
-		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+	{
+		const u8 r0 = bpf2a64[BPF_REG_0];
+
+		/* if (src == 0) return 0 */
+		jmp_offset = 3; /* skip ahead to else path */
+		check_imm19(jmp_offset);
+		emit(A64_CBNZ(is64, src, jmp_offset), ctx);
+		emit(A64_MOVZ(1, r0, 0, 0), ctx);
+		jmp_offset = epilogue_offset(ctx);
+		check_imm26(jmp_offset);
+		emit(A64_B(jmp_offset), ctx);
+		/* else */
+		switch (BPF_OP(code)) {
+		case BPF_DIV:
+			emit(A64_UDIV(is64, dst, dst, src), ctx);
+			break;
+		case BPF_MOD:
+			ctx->tmp_used = 1;
+			emit(A64_UDIV(is64, tmp, dst, src), ctx);
+			emit(A64_MUL(is64, tmp, tmp, src), ctx);
+			emit(A64_SUB(is64, dst, dst, tmp), ctx);
+			break;
+		}
 		break;
+	}
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(A64_LSLV(is64, dst, dst, src), ctx);
@@ -393,17 +422,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit(A64_ASR(is64, dst, dst, imm), ctx);
 		break;
 
-#define check_imm(bits, imm) do {				\
-	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
-	    (((imm) < 0) && (~(imm) >> (bits)))) {		\
-		pr_info("[%2d] imm=%d(0x%x) out of range\n",	\
-			i, imm, imm);				\
-		return -EINVAL;					\
-	}							\
-} while (0)
-#define check_imm19(imm) check_imm(19, imm)
-#define check_imm26(imm) check_imm(26, imm)
-
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
 		jmp_offset = bpf2a64_offset(i + off, i, ctx);