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

Pull arm64 fixes from Will Deacon:

 - Disable software tag-based KASAN when compiling with GCC, as
   functions are incorrectly instrumented leading to a crash early
   during boot

 - Fix pkey configuration for kernel threads when POE is enabled

 - Fix invalid memory accesses in uprobes when targetting load-literal
   instructions

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  kasan: Disable Software Tag-Based KASAN with GCC
  Documentation/protection-keys: add AArch64 to documentation
  arm64: set POR_EL0 for kernel threads
  arm64: probes: Fix uprobes for big-endian kernels
  arm64: probes: Fix simulate_ldr*_literal()
  arm64: probes: Remove broken LDR (literal) uprobe support

5 files changed, 26 insertions, 23 deletions

diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
index 2b09495499c6..014b02897f8e 100644
--- a/arch/arm64/include/asm/uprobes.h
+++ b/arch/arm64/include/asm/uprobes.h
@@ -10,11 +10,9 @@
 #include <asm/insn.h>
 #include <asm/probes.h>
 
-#define MAX_UINSN_BYTES		AARCH64_INSN_SIZE
-
 #define UPROBE_SWBP_INSN	cpu_to_le32(BRK64_OPCODE_UPROBES)
 #define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
-#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+#define UPROBE_XOL_SLOT_BYTES	AARCH64_INSN_SIZE
 
 typedef __le32 uprobe_opcode_t;
 
@@ -23,8 +21,8 @@ struct arch_uprobe_task {
 
 struct arch_uprobe {
 	union {
-		u8 insn[MAX_UINSN_BYTES];
-		u8 ixol[MAX_UINSN_BYTES];
+		__le32 insn;
+		__le32 ixol;
 	};
 	struct arch_probe_insn api;
 	bool simulate;
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 968d5fffe233..3496d6169e59 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -99,10 +99,6 @@ arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api)
 	    aarch64_insn_is_blr(insn) ||
 	    aarch64_insn_is_ret(insn)) {
 		api->handler = simulate_br_blr_ret;
-	} else if (aarch64_insn_is_ldr_lit(insn)) {
-		api->handler = simulate_ldr_literal;
-	} else if (aarch64_insn_is_ldrsw_lit(insn)) {
-		api->handler = simulate_ldrsw_literal;
 	} else {
 		/*
 		 * Instruction cannot be stepped out-of-line and we don't
@@ -140,6 +136,17 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
 	probe_opcode_t insn = le32_to_cpu(*addr);
 	probe_opcode_t *scan_end = NULL;
 	unsigned long size = 0, offset = 0;
+	struct arch_probe_insn *api = &asi->api;
+
+	if (aarch64_insn_is_ldr_lit(insn)) {
+		api->handler = simulate_ldr_literal;
+		decoded = INSN_GOOD_NO_SLOT;
+	} else if (aarch64_insn_is_ldrsw_lit(insn)) {
+		api->handler = simulate_ldrsw_literal;
+		decoded = INSN_GOOD_NO_SLOT;
+	} else {
+		decoded = arm_probe_decode_insn(insn, &asi->api);
+	}
 
 	/*
 	 * If there's a symbol defined in front of and near enough to
@@ -157,7 +164,6 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
 		else
 			scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
 	}
-	decoded = arm_probe_decode_insn(insn, &asi->api);
 
 	if (decoded != INSN_REJECTED && scan_end)
 		if (is_probed_address_atomic(addr - 1, scan_end))
diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c
index 22d0b3252476..b65334ab79d2 100644
--- a/arch/arm64/kernel/probes/simulate-insn.c
+++ b/arch/arm64/kernel/probes/simulate-insn.c
@@ -171,17 +171,15 @@ simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs)
 void __kprobes
 simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
 {
-	u64 *load_addr;
+	unsigned long load_addr;
 	int xn = opcode & 0x1f;
-	int disp;
 
-	disp = ldr_displacement(opcode);
-	load_addr = (u64 *) (addr + disp);
+	load_addr = addr + ldr_displacement(opcode);
 
 	if (opcode & (1 << 30))	/* x0-x30 */
-		set_x_reg(regs, xn, *load_addr);
+		set_x_reg(regs, xn, READ_ONCE(*(u64 *)load_addr));
 	else			/* w0-w30 */
-		set_w_reg(regs, xn, *load_addr);
+		set_w_reg(regs, xn, READ_ONCE(*(u32 *)load_addr));
 
 	instruction_pointer_set(regs, instruction_pointer(regs) + 4);
 }
@@ -189,14 +187,12 @@ simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
 void __kprobes
 simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs)
 {
-	s32 *load_addr;
+	unsigned long load_addr;
 	int xn = opcode & 0x1f;
-	int disp;
 
-	disp = ldr_displacement(opcode);
-	load_addr = (s32 *) (addr + disp);
+	load_addr = addr + ldr_displacement(opcode);
 
-	set_x_reg(regs, xn, *load_addr);
+	set_x_reg(regs, xn, READ_ONCE(*(s32 *)load_addr));
 
 	instruction_pointer_set(regs, instruction_pointer(regs) + 4);
 }
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index d49aef2657cd..a2f137a595fc 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE))
 		return -EINVAL;
 
-	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+	insn = le32_to_cpu(auprobe->insn);
 
 	switch (arm_probe_decode_insn(insn, &auprobe->api)) {
 	case INSN_REJECTED:
@@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	if (!auprobe->simulate)
 		return false;
 
-	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+	insn = le32_to_cpu(auprobe->insn);
 	addr = instruction_pointer(regs);
 
 	if (auprobe->api.handler)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0540653fbf38..3e7c8c8195c3 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -412,6 +412,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 		p->thread.cpu_context.x19 = (unsigned long)args->fn;
 		p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
+
+		if (system_supports_poe())
+			p->thread.por_el0 = POR_EL0_INIT;
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;