Merge tag 'kvm-arm-for-v4.4-rc3' of...

Merge tag 'kvm-arm-for-v4.4-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-master

KVM/ARM Fixes for v4.4-rc3.

Includes some timer fixes, properly unmapping PTEs, an errata fix, and two
tweaks to the EL2 panic code.

Documentation/IPMI.txt

@@ -587,7 +587,7 @@ used to control it:
 
   modprobe ipmi_watchdog timeout=<t> pretimeout=<t> action=<action type>
       preaction=<preaction type> preop=<preop type> start_now=x
-      nowayout=x ifnum_to_use=n
+      nowayout=x ifnum_to_use=n panic_wdt_timeout=<t>
 
 ifnum_to_use specifies which interface the watchdog timer should use.
 The default is -1, which means to pick the first one registered.
@@ -597,7 +597,9 @@ is the amount of seconds before the reset that the pre-timeout panic will
 occur (if pretimeout is zero, then pretimeout will not be enabled).  Note
 that the pretimeout is the time before the final timeout.  So if the
 timeout is 50 seconds and the pretimeout is 10 seconds, then the pretimeout
-will occur in 40 second (10 seconds before the timeout).
+will occur in 40 second (10 seconds before the timeout). The panic_wdt_timeout
+is the value of timeout which is set on kernel panic, in order to let actions
+such as kdump to occur during panic.
 
 The action may be "reset", "power_cycle", or "power_off", and
 specifies what to do when the timer times out, and defaults to
@@ -634,6 +636,7 @@ for configuring the watchdog:
 	ipmi_watchdog.preop=<preop type>
 	ipmi_watchdog.start_now=x
 	ipmi_watchdog.nowayout=x
+	ipmi_watchdog.panic_wdt_timeout=<t>
 
 The options are the same as the module parameter options.
 

Documentation/i2c/busses/i2c-i801

@@ -32,6 +32,7 @@ Supported adapters:
   * Intel Sunrise Point-LP (PCH)
   * Intel DNV (SOC)
   * Intel Broxton (SOC)
+  * Intel Lewisburg (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller

Documentation/kernel-parameters.txt

@@ -1583,9 +1583,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		hwp_only
 			Only load intel_pstate on systems which support
 			hardware P state control (HWP) if available.
-		no_acpi
-			Don't use ACPI processor performance control objects
-			_PSS and _PPC specified limits.
 
 	intremap=	[X86-64, Intel-IOMMU]
 			on	enable Interrupt Remapping (default)

MAINTAINERS

@@ -2449,7 +2449,9 @@ F:	drivers/firmware/broadcom/*
 
 BROADCOM STB NAND FLASH DRIVER
 M:	Brian Norris <computersforpeace@gmail.com>
+M:	Kamal Dasu <kdasu.kdev@gmail.com>
 L:	linux-mtd@lists.infradead.org
+L:	bcm-kernel-feedback-list@broadcom.com
 S:	Maintained
 F:	drivers/mtd/nand/brcmnand/
 
@@ -2546,7 +2548,7 @@ F:	arch/c6x/
 
 CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS
 M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com
+L:	linux-cachefs@redhat.com (moderated for non-subscribers)
 S:	Supported
 F:	Documentation/filesystems/caching/cachefiles.txt
 F:	fs/cachefiles/
@@ -2929,10 +2931,9 @@ S:	Maintained
 F:	drivers/platform/x86/compal-laptop.c
 
 CONEXANT ACCESSRUNNER USB DRIVER
-M:	Simon Arlott <cxacru@fire.lp0.eu>
 L:	accessrunner-general@lists.sourceforge.net
 W:	http://accessrunner.sourceforge.net/
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/atm/cxacru.c
 
 CONFIGFS
@@ -4409,6 +4410,7 @@ K:	fmc_d.*register
 
 FPGA MANAGER FRAMEWORK
 M:	Alan Tull <atull@opensource.altera.com>
+R:	Moritz Fischer <moritz.fischer@ettus.com>
 S:	Maintained
 F:	drivers/fpga/
 F:	include/linux/fpga/fpga-mgr.h
@@ -4559,7 +4561,7 @@ F:	include/linux/frontswap.h
 
 FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
 M:	David Howells <dhowells@redhat.com>
-L:	linux-cachefs@redhat.com
+L:	linux-cachefs@redhat.com (moderated for non-subscribers)
 S:	Supported
 F:	Documentation/filesystems/caching/
 F:	fs/fscache/
@@ -5711,13 +5713,6 @@ M:	Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar>
 S:	Maintained
 F:	net/ipv4/netfilter/ipt_MASQUERADE.c
 
-IP1000A 10/100/1000 GIGABIT ETHERNET DRIVER
-M:	Francois Romieu <romieu@fr.zoreil.com>
-M:	Sorbica Shieh <sorbica@icplus.com.tw>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/net/ethernet/icplus/ipg.*
-
 IPATH DRIVER
 M:	Mike Marciniszyn <infinipath@intel.com>
 L:	linux-rdma@vger.kernel.org
@@ -6923,13 +6918,21 @@ F:	drivers/scsi/megaraid.*
 F:	drivers/scsi/megaraid/
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
-M:	Amir Vadai <amirv@mellanox.com>
+M: 	Eugenia Emantayev <eugenia@mellanox.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlx4/en_*
 
+MELLANOX ETHERNET DRIVER (mlx5e)
+M:	Saeed Mahameed <saeedm@mellanox.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+W:	http://www.mellanox.com
+Q:	http://patchwork.ozlabs.org/project/netdev/list/
+F:	drivers/net/ethernet/mellanox/mlx5/core/en_*
+
 MELLANOX ETHERNET SWITCH DRIVERS
 M:	Jiri Pirko <jiri@mellanox.com>
 M:	Ido Schimmel <idosch@mellanox.com>
@@ -7901,6 +7904,18 @@ S:	Maintained
 F:	net/openvswitch/
 F:	include/uapi/linux/openvswitch.h
 
+OPERATING PERFORMANCE POINTS (OPP)
+M:	Viresh Kumar <vireshk@kernel.org>
+M:	Nishanth Menon <nm@ti.com>
+M:	Stephen Boyd <sboyd@codeaurora.org>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git
+F:	drivers/base/power/opp/
+F:	include/linux/pm_opp.h
+F:	Documentation/power/opp.txt
+F:	Documentation/devicetree/bindings/opp/
+
 OPL4 DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -9314,7 +9329,6 @@ F:	drivers/i2c/busses/i2c-designware-*
 F:	include/linux/platform_data/i2c-designware.h
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
-M:	Seungwon Jeon <tgih.jun@samsung.com>
 M:	Jaehoon Chung <jh80.chung@samsung.com>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained

Makefile

 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*

arch/arm/boot/dts/imx27.dtsi

@@ -486,7 +486,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024000 0x200>;
 				interrupts = <56>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 0>;
 				status = "disabled";
 			};
@@ -495,7 +498,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024200 0x200>;
 				interrupts = <54>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 1>;
 				dr_mode = "host";
 				status = "disabled";
@@ -505,7 +511,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024400 0x200>;
 				interrupts = <55>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 2>;
 				dr_mode = "host";
 				status = "disabled";
@@ -515,7 +524,6 @@
 				#index-cells = <1>;
 				compatible = "fsl,imx27-usbmisc";
 				reg = <0x10024600 0x200>;
-				clocks = <&clks IMX27_CLK_USB_AHB_GATE>;
 			};
 
 			sahara2: sahara@10025000 {

arch/arm/kvm/arm.c

@@ -563,18 +563,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (vcpu->arch.power_off || vcpu->arch.pause)
 			vcpu_sleep(vcpu);
 
-		/*
-		 * Disarming the background timer must be done in a
-		 * preemptible context, as this call may sleep.
-		 */
-		kvm_timer_flush_hwstate(vcpu);
-
 		/*
 		 * Preparing the interrupts to be injected also
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
 		local_irq_disable();

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(__phys_to_pfn(addr)))
 				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(__phys_to_pfn(addr)))
 			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

@@ -1061,7 +1061,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 	}
 	build_epilogue(&ctx);
 
-	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
+	flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx));
 
 #if __LINUX_ARM_ARCH__ < 7
 	if (ctx.imm_count)

arch/arm64/Kconfig

@@ -316,6 +316,27 @@ 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 the result of a Stage 1 fault for load crossing a
+	  page boundary when there is a permission or device memory
+	  alignment fault at Stage 1 and a translation fault at Stage 2.
+
+	  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/crypto/aes-ce-cipher.c

@@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey);
 static struct crypto_alg aes_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-ce",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),

arch/arm64/include/asm/barrier.h

@@ -64,27 +64,31 @@ do {									\
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1;						\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	}								\
-	___p1;								\
+	__u.__val;							\
 })
 
 #define read_barrier_depends()		do { } while(0)

arch/arm64/include/asm/compat.h

@@ -23,7 +23,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
@@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
+#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {

arch/arm64/include/asm/cpufeature.h

@@ -29,8 +29,9 @@
 #define ARM64_HAS_PAN				4
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
+#define ARM64_WORKAROUND_834220			7
 
-#define ARM64_NCAPS				7
+#define ARM64_NCAPS				8
 
 #ifndef __ASSEMBLY__
 

arch/arm64/include/asm/dma-mapping.h

@@ -18,7 +18,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -26,22 +25,16 @@
 #include <asm/xen/hypervisor.h>
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
-extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops dummy_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
-	if (unlikely(!dev))
-		return dma_ops;
-	else if (dev->archdata.dma_ops)
+	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
-	else if (acpi_disabled)
-		return dma_ops;
 
 	/*
-	 * When ACPI is enabled, if arch_set_dma_ops is not called,
-	 * we will disable device DMA capability by setting it
-	 * to dummy_dma_ops.
+	 * We expect no ISA devices, and all other DMA masters are expected to
+	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
 	return &dummy_dma_ops;
 }

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/include/asm/mmu_context.h

@@ -101,7 +101,7 @@ static inline void cpu_set_default_tcr_t0sz(void)
 #define destroy_context(mm)		do { } while(0)
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.

arch/arm64/include/asm/pgtable.h

@@ -81,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #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_ROX	__pgprot(_PAGE_DEFAULT | 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/kernel/cpu_errata.c

@@ -75,6 +75,15 @@ 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/cpuinfo.c

@@ -30,6 +30,7 @@
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/delay.h>
 
 /*
  * In case the boot CPU is hotpluggable, we record its initial state and
@@ -112,6 +113,10 @@ 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)