Linux-libre 4.2.3-gnupck-4.2.3-gnu

5 files changed, 50 insertions, 22 deletions

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e16351819..8213ca15a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -116,7 +116,7 @@
 	*/
 	.endm
 
-	.macro	kernel_exit, el, ret = 0
+	.macro	kernel_exit, el
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -146,11 +146,7 @@
 	.endif
 	msr	elr_el1, x21			// set up the return data
 	msr	spsr_el1, x22
-	.if	\ret
-	ldr	x1, [sp, #S_X1]			// preserve x0 (syscall return)
-	.else
 	ldp	x0, x1, [sp, #16 * 0]
-	.endif
 	ldp	x2, x3, [sp, #16 * 1]
 	ldp	x4, x5, [sp, #16 * 2]
 	ldp	x6, x7, [sp, #16 * 3]
@@ -613,22 +609,21 @@ ENDPROC(cpu_switch_to)
  */
 ret_fast_syscall:
 	disable_irq				// disable interrupts
+	str	x0, [sp, #S_X0]			// returned x0
 	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
 	cbnz	x2, ret_fast_syscall_trace
 	and	x2, x1, #_TIF_WORK_MASK
-	cbnz	x2, fast_work_pending
+	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
-	kernel_exit 0, ret = 1
+	kernel_exit 0
 ret_fast_syscall_trace:
 	enable_irq				// enable interrupts
-	b	__sys_trace_return
+	b	__sys_trace_return_skipped	// we already saved x0
 
 /*
  * Ok, we need to do extra processing, enter the slow path.
  */
-fast_work_pending:
-	str	x0, [sp, #S_X0]			// returned x0
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
 	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
@@ -652,7 +647,7 @@ ret_to_user:
 	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
 no_work_pending:
-	kernel_exit 0, ret = 0
+	kernel_exit 0
 ENDPROC(ret_to_user)
 
 /*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 44d6f7545..c56956a16 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -158,6 +158,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 void fpsimd_flush_thread(void)
 {
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
+	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index c0ff3ce42..370541162 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -528,6 +528,11 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
 #endif
 
+	/* EL2 debug */
+	mrs	x0, pmcr_el0			// Disable debug access traps
+	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
+	msr	mdcr_el2, x0			// all PMU counters from EL1
+
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
 
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 67bf4107f..876eb8df5 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -332,12 +332,14 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
 					     AARCH64_INSN_IMM_ADR);
 			break;
+#ifndef CONFIG_ARM64_ERRATUM_843419
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
 		case R_AARCH64_ADR_PREL_PG_HI21:
 			ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21,
 					     AARCH64_INSN_IMM_ADR);
 			break;
+#endif
 		case R_AARCH64_ADD_ABS_LO12_NC:
 		case R_AARCH64_LDST8_ABS_LO12_NC:
 			overflow_check = false;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 948f0ad2d..71ef6dc89 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -212,14 +212,32 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 
 /*
  * VFP save/restore code.
+ *
+ * We have to be careful with endianness, since the fpsimd context-switch
+ * code operates on 128-bit (Q) register values whereas the compat ABI
+ * uses an array of 64-bit (D) registers. Consequently, we need to swap
+ * the two halves of each Q register when running on a big-endian CPU.
  */
+union __fpsimd_vreg {
+	__uint128_t	raw;
+	struct {
+#ifdef __AARCH64EB__
+		u64	hi;
+		u64	lo;
+#else
+		u64	lo;
+		u64	hi;
+#endif
+	};
+};
+
 static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 {
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
 	compat_ulong_t magic = VFP_MAGIC;
 	compat_ulong_t size = VFP_STORAGE_SIZE;
 	compat_ulong_t fpscr, fpexc;
-	int err = 0;
+	int i, err = 0;
 
 	/*
 	 * Save the hardware registers to the fpsimd_state structure.
@@ -235,10 +253,15 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 	/*
 	 * Now copy the FP registers. Since the registers are packed,
 	 * we can copy the prefix we want (V0-V15) as it is.
-	 * FIXME: Won't work if big endian.
 	 */
-	err |= __copy_to_user(&frame->ufp.fpregs, fpsimd->vregs,
-			      sizeof(frame->ufp.fpregs));
+	for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) {
+		union __fpsimd_vreg vreg = {
+			.raw = fpsimd->vregs[i >> 1],
+		};
+
+		__put_user_error(vreg.lo, &frame->ufp.fpregs[i], err);
+		__put_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err);
+	}
 
 	/* Create an AArch32 fpscr from the fpsr and the fpcr. */
 	fpscr = (fpsimd->fpsr & VFP_FPSCR_STAT_MASK) |
@@ -263,7 +286,7 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
 	compat_ulong_t magic = VFP_MAGIC;
 	compat_ulong_t size = VFP_STORAGE_SIZE;
 	compat_ulong_t fpscr;
-	int err = 0;
+	int i, err = 0;
 
 	__get_user_error(magic, &frame->magic, err);
 	__get_user_error(size, &frame->size, err);
@@ -273,12 +296,14 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	/*
-	 * Copy the FP registers into the start of the fpsimd_state.
-	 * FIXME: Won't work if big endian.
-	 */
-	err |= __copy_from_user(fpsimd.vregs, frame->ufp.fpregs,
-				sizeof(frame->ufp.fpregs));
+	/* Copy the FP registers into the start of the fpsimd_state. */
+	for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) {
+		union __fpsimd_vreg vreg;
+
+		__get_user_error(vreg.lo, &frame->ufp.fpregs[i], err);
+		__get_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err);
+		fpsimd.vregs[i >> 1] = vreg.raw;
+	}
 
 	/* Extract the fpsr and the fpcr from the fpscr */
 	__get_user_error(fpscr, &frame->ufp.fpscr, err);