Merge tag 'v4.3.5' into dev-4.3

This is the 4.3.5 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

Documentation/ABI/testing/sysfs-bus-usb

@@ -114,19 +114,21 @@ Description:
 		enabled for the device. Developer can write y/Y/1 or n/N/0 to
 		the file to enable/disable the feature.
 
-What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm
-Date:		June 2015
+What:		/sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1
+		/sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2
+Date:		November 2015
 Contact:	Kevin Strasser <kevin.strasser@linux.intel.com>
+		Lu Baolu <baolu.lu@linux.intel.com>
 Description:
 		If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged
 		in to a xHCI host which supports link PM, it will check if U1
 		and U2 exit latencies have been set in the BOS descriptor; if
-		the check is is passed and the host supports USB3 hardware LPM,
+		the check is passed and the host supports USB3 hardware LPM,
 		USB3 hardware LPM will be enabled for the device and the USB
-		device directory will contain a file named
-		power/usb3_hardware_lpm. The file holds a string value (enable
-		or disable) indicating whether or not USB3 hardware LPM is
-		enabled for the device.
+		device directory will contain two files named
+		power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These
+		files hold a string value (enable or disable) indicating whether
+		or not USB3 hardware LPM U1 or U2 is enabled for the device.
 
 What:		/sys/bus/usb/devices/.../removable
 Date:		February 2012

Documentation/usb/power-management.txt

@@ -537,17 +537,18 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm.
 		can write y/Y/1 or n/N/0 to the file to	enable/disable
 		USB2 hardware LPM manually. This is for	test purpose mainly.
 
-	power/usb3_hardware_lpm
+	power/usb3_hardware_lpm_u1
+	power/usb3_hardware_lpm_u2
 
 		When a USB 3.0 lpm-capable device is plugged in to a
 		xHCI host which supports link PM, it will check if U1
 		and U2 exit latencies have been set in the BOS
 		descriptor; if the check is is passed and the host
 		supports USB3 hardware LPM, USB3 hardware LPM will be
-		enabled for the device and this file will be created.
-		The file holds a string value (enable or disable)
-		indicating whether or not USB3 hardware LPM is
-		enabled for the device.
+		enabled for the device and these files will be created.
+		The files hold a string value (enable or disable)
+		indicating whether or not USB3 hardware LPM U1 or U2
+		is enabled for the device.
 
 	USB Port Power Control
 	----------------------

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 3
-SUBLEVEL = 4
+SUBLEVEL = 5
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

arch/arm/kvm/mmu.c

@@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud)
 	__kvm_flush_dcache_pud(pud);
 }
 
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
  * @kvm:	pointer to kvm structure.
@@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
 
 			/* No need to invalidate the cache for device mappings */
-			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
 				kvm_flush_dcache_pte(old_pte);
 
 			put_page(virt_to_page(pte));
@@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte) &&
-		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+		if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
 			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
@@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_dabt_iswrite(vcpu);
 }
 
-static bool kvm_is_device_pfn(unsigned long pfn)
-{
-	return !pfn_valid(pfn);
-}
-
 /**
  * stage2_wp_ptes - write protect PMD range
  * @pmd:	pointer to pmd entry

arch/arm/net/bpf_jit_32.c

@@ -182,19 +182,6 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 	return fls(ctx->seen & SEEN_MEM);
 }
 
-static inline bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	u32 *ptr;
@@ -206,7 +193,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 static void build_prologue(struct jit_ctx *ctx)
 {
 	u16 reg_set = saved_regs(ctx);
-	u16 first_inst = ctx->skf->insns[0].code;
 	u16 off;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -236,7 +222,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */

arch/arm64/Kconfig

@@ -311,6 +311,27 @@ config ARM64_ERRATUM_832075
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_834220
+	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+	depends on KVM
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 834220 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might report a Stage 2 translation
+	  fault as a the result of a Stage 1 fault for a load crossing
+	  a page boundary when there is a Stage 1 permission or device
+	  memory alignment fault and a Stage 2 translation fault
+
+	  The workaround is to verify that the Stage-1 translation
+	  doesn't generate a fault before handling the Stage-2 fault.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_845719
 	bool "Cortex-A53: 845719: a load might read incorrect data"
 	depends on COMPAT

arch/arm64/include/asm/atomic_ll_sc.h

@@ -211,7 +211,7 @@ __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

@@ -348,7 +348,7 @@ __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/cpufeature.h

@@ -27,8 +27,9 @@
 #define ARM64_HAS_SYSREG_GIC_CPUIF		3
 #define ARM64_HAS_PAN				4
 #define ARM64_HAS_LSE_ATOMICS			5
+#define ARM64_WORKAROUND_834220			6
 
-#define ARM64_NCAPS				6
+#define ARM64_NCAPS				7
 
 #ifndef __ASSEMBLY__
 

arch/arm64/include/asm/kvm_emulate.h

@@ -99,11 +99,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 	*vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
 }
 
+/*
+ * vcpu_reg should always be passed a register number coming from a
+ * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32
+ * with banked registers.
+ */
 static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	if (vcpu_mode_is_32bit(vcpu))
-		return vcpu_reg32(vcpu, reg_num);
-
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
 }
 

arch/arm64/kernel/cpu_errata.c

@@ -74,6 +74,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 			   (1 << MIDR_VARIANT_SHIFT) | 2),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_834220
+	{
+	/* Cortex-A57 r0p0 - r1p2 */
+		.desc = "ARM erratum 834220",
+		.capability = ARM64_WORKAROUND_834220,
+		MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 2),
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
 	/* Cortex-A53 r0p[01234] */

arch/arm64/kernel/head.S

@@ -524,9 +524,14 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 #endif
 
 	/* EL2 debug */
+	mrs	x0, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	x0, x0, #8, #4
+	cmp	x0, #1
+	b.lt	4f				// Skip if no PMU present
 	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
+4:
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr

arch/arm64/kernel/perf_event.c

@@ -1159,9 +1159,6 @@ static void armv8pmu_reset(void *info)
 
 	/* Initialize & Reset PMNC: C and P bits. */
 	armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C);
-
-	/* Disable access from userspace. */
-	asm volatile("msr pmuserenr_el0, %0" :: "r" (0));
 }
 
 static int armv8_pmuv3_map_event(struct perf_event *event)

arch/arm64/kernel/ptrace.c

@@ -58,6 +58,12 @@
  */
 void ptrace_disable(struct task_struct *child)
 {
+	/*
+	 * This would be better off in core code, but PTRACE_DETACH has
+	 * grown its fair share of arch-specific worts and changing it
+	 * is likely to cause regressions on obscure architectures.
+	 */
+	user_disable_single_step(child);
 }
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT

arch/arm64/kernel/setup.c

@@ -558,6 +558,10 @@ static int c_show(struct seq_file *m, void *v)
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
 
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000UL/HZ),
+			   loops_per_jiffy / (5000UL/HZ) % 100);
+
 		/*
 		 * Dump out the common processor features in a single line.
 		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)

arch/arm64/kernel/suspend.c

@@ -1,3 +1,4 @@
+#include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -70,6 +71,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 */
 	local_dbg_save(flags);
 
+	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
 	/*
 	 * mm context saved on the stack, it will be restored when
 	 * the cpu comes out of reset through the identity mapped
@@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 			hw_breakpoint_restore(NULL);
 	}
 
+	unpause_graph_tracing();
+
 	/*
 	 * Restore pstate flags. OS lock and mdscr have been already
 	 * restored, so from this point onwards, debugging is fully

arch/arm64/kvm/hyp.S

@@ -1007,9 +1007,15 @@ el1_trap:
 	b.ne	1f		// Not an abort we care about
 
 	/* This is an abort. Check for permission fault */
+alternative_if_not ARM64_WORKAROUND_834220
 	and	x2, x1, #ESR_ELx_FSC_TYPE
 	cmp	x2, #FSC_PERM
 	b.ne	1f		// Not a permission fault
+alternative_else
+	nop			// Force a Stage-1 translation to occur
+	nop			// and return to the guest if it failed
+	nop
+alternative_endif
 
 	/*
 	 * Check for Stage-1 page table walk, which is guaranteed

arch/arm64/kvm/inject_fault.c

@@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
 	/* Note: These now point to the banked copies */
 	*vcpu_spsr(vcpu) = new_spsr_value;
-	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
 	if (sctlr & (1 << 13))

arch/arm64/mm/mmu.c

@@ -451,6 +451,9 @@ void __init paging_init(void)
 
 	empty_zero_page = virt_to_page(zero_page);
 
+	/* Ensure the zero page is visible to the page table walker */
+	dsb(ishst);
+
 	/*
 	 * TTBR0 is only used for the identity mapping at this stage. Make it
 	 * point to zero page to avoid speculatively fetching new entries.

arch/arm64/mm/proc-macros.S

@@ -62,3 +62,15 @@
 	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
 #endif
 	.endm
+
+/*
+ * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
+ */
+	.macro	reset_pmuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	\tmpreg, \tmpreg, #8, #4
+	cmp	\tmpreg, #1			// Skip if no PMU present
+	b.lt	9000f
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+9000:
+	.endm

arch/arm64/mm/proc.S

@@ -115,6 +115,7 @@ ENTRY(cpu_do_resume)
 	 */
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
+	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	mov	x0, x12
 	dsb	nsh		// Make sure local tlb invalidation completed
 	isb
@@ -153,6 +154,7 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
 	 *

arch/arm64/net/bpf_jit.h

@@ -1,7 +1,7 @@
 /*
  * 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) \