Merge "These changes are a raw update to a vanilla kernel 4.1.10, with the recently announced rt patch patch-4.1.10-rt10.patch. No further changes needed."

10 files changed, 97 insertions, 28 deletions

diff --git a/kernel/arch/arm64/Kconfig b/kernel/arch/arm64/Kconfig
index d555ed3a0..09a41259b 100644
--- a/kernel/arch/arm64/Kconfig
+++ b/kernel/arch/arm64/Kconfig
@@ -103,6 +103,10 @@ config NO_IOPORT_MAP
 config STACKTRACE_SUPPORT
 	def_bool y
 
+config ILLEGAL_POINTER_VALUE
+	hex
+	default 0xdead000000000000
+
 config LOCKDEP_SUPPORT
 	def_bool y
 
@@ -411,6 +415,22 @@ config ARM64_ERRATUM_845719
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_843419
+	bool "Cortex-A53: 843419: A load or store might access an incorrect address"
+	depends on MODULES
+	default y
+	help
+	  This option builds kernel modules using the large memory model in
+	  order to avoid the use of the ADRP instruction, which can cause
+	  a subsequent memory access to use an incorrect address on Cortex-A53
+	  parts up to r0p4.
+
+	  Note that the kernel itself must be linked with a version of ld
+	  which fixes potentially affected ADRP instructions through the
+	  use of veneers.
+
+	  If unsure, say Y.
+
 endmenu
 
 
@@ -581,7 +601,7 @@ config XEN_DOM0
 
 config XEN
 	bool "Xen guest support on ARM64"
-	depends on ARM64 && OF
+	depends on ARM64 && OF && !PREEMPT_RT_FULL
 	select SWIOTLB_XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
diff --git a/kernel/arch/arm64/Makefile b/kernel/arch/arm64/Makefile
index 4d2a92599..81151663e 100644
--- a/kernel/arch/arm64/Makefile
+++ b/kernel/arch/arm64/Makefile
@@ -30,6 +30,10 @@ endif
 
 CHECKFLAGS	+= -D__aarch64__
 
+ifeq ($(CONFIG_ARM64_ERRATUM_843419), y)
+CFLAGS_MODULE	+= -mcmodel=large
+endif
+
 # Default value
 head-y		:= arch/arm64/kernel/head.o
 
diff --git a/kernel/arch/arm64/include/asm/memory.h b/kernel/arch/arm64/include/asm/memory.h
index f800d45ea..44a59c20e 100644
--- a/kernel/arch/arm64/include/asm/memory.h
+++ b/kernel/arch/arm64/include/asm/memory.h
@@ -114,6 +114,14 @@ extern phys_addr_t		memstart_addr;
 #define PHYS_OFFSET		({ memstart_addr; })
 
 /*
+ * The maximum physical address that the linear direct mapping
+ * of system RAM can cover. (PAGE_OFFSET can be interpreted as
+ * a 2's complement signed quantity and negated to derive the
+ * maximum size of the linear mapping.)
+ */
+#define MAX_MEMBLOCK_ADDR	({ memstart_addr - PAGE_OFFSET - 1; })
+
+/*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
  *
diff --git a/kernel/arch/arm64/kernel/debug-monitors.c b/kernel/arch/arm64/kernel/debug-monitors.c
index b056369fd..70654d843 100644
--- a/kernel/arch/arm64/kernel/debug-monitors.c
+++ b/kernel/arch/arm64/kernel/debug-monitors.c
@@ -271,20 +271,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-static DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_SPINLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_add(&hook->node, &break_hook);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_add_rcu(&hook->node, &break_hook);
+	spin_unlock(&break_hook_lock);
 }
 
 void unregister_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&break_hook_lock);
+	synchronize_rcu();
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
@@ -292,11 +293,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 	struct break_hook *hook;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
-	read_lock(&break_hook_lock);
-	list_for_each_entry(hook, &break_hook, node)
+	rcu_read_lock();
+	list_for_each_entry_rcu(hook, &break_hook, node)
 		if ((esr & hook->esr_mask) == hook->esr_val)
 			fn = hook->fn;
-	read_unlock(&break_hook_lock);
+	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
diff --git a/kernel/arch/arm64/kernel/fpsimd.c b/kernel/arch/arm64/kernel/fpsimd.c
index 3dca15634..c31e59fe2 100644
--- a/kernel/arch/arm64/kernel/fpsimd.c
+++ b/kernel/arch/arm64/kernel/fpsimd.c
@@ -157,6 +157,7 @@ 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/kernel/arch/arm64/kernel/head.S b/kernel/arch/arm64/kernel/head.S
index 19f915e8f..36aa31ff2 100644
--- a/kernel/arch/arm64/kernel/head.S
+++ b/kernel/arch/arm64/kernel/head.S
@@ -565,6 +565,11 @@ 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/kernel/arch/arm64/kernel/insn.c b/kernel/arch/arm64/kernel/insn.c
index 924902083..30eb88e5b 100644
--- a/kernel/arch/arm64/kernel/insn.c
+++ b/kernel/arch/arm64/kernel/insn.c
@@ -77,7 +77,7 @@ bool __kprobes aarch64_insn_is_nop(u32 insn)
 	}
 }
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
@@ -124,13 +124,13 @@ static int __kprobes __aarch64_insn_write(void *addr, u32 insn)
 	unsigned long flags = 0;
 	int ret;
 
-	spin_lock_irqsave(&patch_lock, flags);
+	raw_spin_lock_irqsave(&patch_lock, flags);
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
 	ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
 
 	patch_unmap(FIX_TEXT_POKE0);
-	spin_unlock_irqrestore(&patch_lock, flags);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
 
 	return ret;
 }
diff --git a/kernel/arch/arm64/kernel/module.c b/kernel/arch/arm64/kernel/module.c
index 67bf4107f..876eb8df5 100644
--- a/kernel/arch/arm64/kernel/module.c
+++ b/kernel/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/kernel/arch/arm64/kernel/signal32.c b/kernel/arch/arm64/kernel/signal32.c
index c0cff3410..c58aee062 100644
--- a/kernel/arch/arm64/kernel/signal32.c
+++ b/kernel/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);
diff --git a/kernel/arch/arm64/kvm/hyp.S b/kernel/arch/arm64/kvm/hyp.S
index 5befd010e..64f9e60b3 100644
--- a/kernel/arch/arm64/kvm/hyp.S
+++ b/kernel/arch/arm64/kvm/hyp.S
@@ -844,8 +844,6 @@
 	mrs	x3, cntv_ctl_el0
 	and	x3, x3, #3
 	str	w3, [x0, #VCPU_TIMER_CNTV_CTL]
-	bic	x3, x3, #1		// Clear Enable
-	msr	cntv_ctl_el0, x3
 
 	isb
 
@@ -853,6 +851,9 @@
 	str	x3, [x0, #VCPU_TIMER_CNTV_CVAL]
 
 1:
+	// Disable the virtual timer
+	msr	cntv_ctl_el0, xzr
+
 	// Allow physical timer/counter access for the host
 	mrs	x2, cnthctl_el2
 	orr	x2, x2, #3
@@ -947,13 +948,15 @@ ENTRY(__kvm_vcpu_run)
 	// Guest context
 	add	x2, x0, #VCPU_CONTEXT
 
+	// We must restore the 32-bit state before the sysregs, thanks
+	// to Cortex-A57 erratum #852523.
+	restore_guest_32bit_state
 	bl __restore_sysregs
 	bl __restore_fpsimd
 
 	skip_debug_state x3, 1f
 	bl	__restore_debug
 1:
-	restore_guest_32bit_state
 	restore_guest_regs
 
 	// That's it, no more messing around.