Merge 4.4.118 into android-4.4

Changes in 4.4.118
	net: add dst_cache support
	net: replace dst_cache ip6_tunnel implementation with the generic one
	cfg80211: check dev_set_name() return value
	mm,vmscan: Make unregister_shrinker() no-op if register_shrinker() failed.
	xfrm: Fix stack-out-of-bounds read on socket policy lookup.
	xfrm: check id proto in validate_tmpl()
	blktrace: fix unlocked registration of tracepoints
	drm: Require __GFP_NOFAIL for the legacy drm_modeset_lock_all
	Provide a function to create a NUL-terminated string from unterminated data
	selinux: ensure the context is NUL terminated in security_context_to_sid_core()
	selinux: skip bounded transition processing if the policy isn't loaded
	crypto: x86/twofish-3way - Fix %rbp usage
	KVM: x86: fix escape of guest dr6 to the host
	netfilter: x_tables: fix int overflow in xt_alloc_table_info()
	netfilter: x_tables: avoid out-of-bounds reads in xt_request_find_{match|target}
	netfilter: ipt_CLUSTERIP: fix out-of-bounds accesses in clusterip_tg_check()
	netfilter: on sockopt() acquire sock lock only in the required scope
	netfilter: xt_RATEEST: acquire xt_rateest_mutex for hash insert
	net: avoid skb_warn_bad_offload on IS_ERR
	ASoC: ux500: add MODULE_LICENSE tag
	video: fbdev/mmp: add MODULE_LICENSE
	arm64: dts: add #cooling-cells to CPU nodes
	Make DST_CACHE a silent config option
	dn_getsockoptdecnet: move nf_{get/set}sockopt outside sock lock
	staging: android: ashmem: Fix a race condition in pin ioctls
	binder: check for binder_thread allocation failure in binder_poll()
	staging: iio: adc: ad7192: fix external frequency setting
	usbip: keep usbip_device sockfd state in sync with tcp_socket
	usb: build drivers/usb/common/ when USB_SUPPORT is set
	ARM: OMAP2+: Fix SRAM virt to phys translation for save_secure_ram_context
	ARM: AM33xx: PRM: Remove am33xx_pwrdm_read_prev_pwrst function
	ARM: dts: Fix omap4 hang with GPS connected to USB by using wakeupgen
	ARM: dts: am4372: Correct the interrupts_properties of McASP
	perf top: Fix window dimensions change handling
	perf bench numa: Fixup discontiguous/sparse numa nodes
	media: s5k6aa: describe some function parameters
	pinctrl: sunxi: Fix A80 interrupt pin bank
	RDMA/cma: Make sure that PSN is not over max allowed
	scripts/kernel-doc: Don't fail with status != 0 if error encountered with -none
	ipvlan: Add the skb->mark as flow4's member to lookup route
	powerpc/perf: Fix oops when grouping different pmu events
	s390/dasd: prevent prefix I/O error
	gianfar: fix a flooded alignment reports because of padding issue.
	net_sched: red: Avoid devision by zero
	net_sched: red: Avoid illegal values
	btrfs: Fix possible off-by-one in btrfs_search_path_in_tree
	509: fix printing uninitialized stack memory when OID is empty
	dmaengine: ioat: Fix error handling path
	dmaengine: at_hdmac: fix potential NULL pointer dereference in atc_prep_dma_interleaved
	clk: fix a panic error caused by accessing NULL pointer
	ASoC: rockchip: disable clock on error
	spi: sun4i: disable clocks in the remove function
	xfrm: Fix stack-out-of-bounds with misconfigured transport mode policies.
	drm/armada: fix leak of crtc structure
	dmaengine: jz4740: disable/unprepare clk if probe fails
	mm/early_ioremap: Fix boot hang with earlyprintk=efi,keep
	x86/mm/kmmio: Fix mmiotrace for page unaligned addresses
	xen: XEN_ACPI_PROCESSOR is Dom0-only
	hippi: Fix a Fix a possible sleep-in-atomic bug in rr_close
	virtio_balloon: prevent uninitialized variable use
	isdn: icn: remove a #warning
	vmxnet3: prevent building with 64K pages
	gpio: intel-mid: Fix build warning when !CONFIG_PM
	platform/x86: intel_mid_thermal: Fix suspend handlers unused warning
	video: fbdev: via: remove possibly unused variables
	scsi: advansys: fix build warning for PCI=n
	x86/ras/inject: Make it depend on X86_LOCAL_APIC=y
	arm64: define BUG() instruction without CONFIG_BUG
	x86/fpu/math-emu: Fix possible uninitialized variable use
	tools build: Add tools tree support for 'make -s'
	x86/build: Silence the build with "make -s"
	thermal: fix INTEL_SOC_DTS_IOSF_CORE dependencies
	x86: add MULTIUSER dependency for KVM
	x86/platform: Add PCI dependency for PUNIT_ATOM_DEBUG
	scsi: advansys: fix uninitialized data access
	arm64: Kconfig: select COMPAT_BINFMT_ELF only when BINFMT_ELF is set
	ALSA: hda/ca0132 - fix possible NULL pointer use
	reiserfs: avoid a -Wmaybe-uninitialized warning
	ssb: mark ssb_bus_register as __maybe_unused
	thermal: spear: use __maybe_unused for PM functions
	x86/boot: Avoid warning for zero-filling .bss
	scsi: sim710: fix build warning
	drivers/net: fix eisa_driver probe section mismatch
	dpt_i2o: fix build warning
	profile: hide unused functions when !CONFIG_PROC_FS
	md: avoid warning for 32-bit sector_t
	mtd: ichxrom: maybe-uninitialized with gcc-4.9
	mtd: maps: add __init attribute
	mptfusion: hide unused seq_mpt_print_ioc_summary function
	scsi: fdomain: drop fdomain_pci_tbl when built-in
	video: fbdev: sis: remove unused variable
	staging: ste_rmi4: avoid unused function warnings
	fbdev: sis: enforce selection of at least one backend
	video: Use bool instead int pointer for get_opt_bool() argument
	scsi: mvumi: use __maybe_unused to hide pm functions
	SCSI: initio: remove duplicate module device table
	pwc: hide unused label
	usb: musb/ux500: remove duplicate check for dma_is_compatible
	tty: hvc_xen: hide xen_console_remove when unused
	target/user: Fix cast from pointer to phys_addr_t
	driver-core: use 'dev' argument in dev_dbg_ratelimited stub
	fbdev: auo_k190x: avoid unused function warnings
	amd-xgbe: Fix unused suspend handlers build warning
	mtd: sh_flctl: pass FIFO as physical address
	mtd: cfi: enforce valid geometry configuration
	fbdev: s6e8ax0: avoid unused function warnings
	modsign: hide openssl output in silent builds
	Drivers: hv: vmbus: fix build warning
	fbdev: sm712fb: avoid unused function warnings
	hwrng: exynos - use __maybe_unused to hide pm functions
	USB: cdc_subset: only build when one driver is enabled
	rtlwifi: fix gcc-6 indentation warning
	staging: wilc1000: fix kbuild test robot error
	x86/platform/olpc: Fix resume handler build warning
	netfilter: ipvs: avoid unused variable warnings
	ipv4: ipconfig: avoid unused ic_proto_used symbol
	tc1100-wmi: fix build warning when CONFIG_PM not enabled
	tlan: avoid unused label with PCI=n
	drm/vmwgfx: use *_32_bits() macros
	tty: cyclades: cyz_interrupt is only used for PCI
	genirq/msi: Add stubs for get_cached_msi_msg/pci_write_msi_msg
	ASoC: mediatek: add i2c dependency
	iio: adc: axp288: remove redundant duplicate const on axp288_adc_channels
	infiniband: cxgb4: use %pR format string for printing resources
	b2c2: flexcop: avoid unused function warnings
	i2c: remove __init from i2c_register_board_info()
	staging: unisys: visorinput depends on INPUT
	tc358743: fix register i2c_rd/wr functions
	drm/nouveau: hide gcc-4.9 -Wmaybe-uninitialized
	Input: tca8418_keypad - hide gcc-4.9 -Wmaybe-uninitialized warning
	KVM: add X86_LOCAL_APIC dependency
	go7007: add MEDIA_CAMERA_SUPPORT dependency
	em28xx: only use mt9v011 if camera support is enabled
	ISDN: eicon: reduce stack size of sig_ind function
	ASoC: rockchip: use __maybe_unused to hide st_irq_syscfg_resume
	serial: 8250_mid: fix broken DMA dependency
	drm/gma500: Sanity-check pipe index
	hdpvr: hide unused variable
	v4l: remove MEDIA_TUNER dependency for VIDEO_TUNER
	cw1200: fix bogus maybe-uninitialized warning
	wireless: cw1200: use __maybe_unused to hide pm functions_
	perf/x86: Shut up false-positive -Wmaybe-uninitialized warning
	dmaengine: zx: fix build warning
	net: hp100: remove unnecessary #ifdefs
	gpio: xgene: mark PM functions as __maybe_unused
	ncpfs: fix unused variable warning
	Revert "power: bq27xxx_battery: Remove unneeded dependency in Kconfig"
	power: bq27xxx_battery: mark some symbols __maybe_unused
	isdn: sc: work around type mismatch warning
	binfmt_elf: compat: avoid unused function warning
	idle: i7300: add PCI dependency
	usb: phy: msm add regulator dependency
	ncr5380: shut up gcc indentation warning
	ARM: tegra: select USB_ULPI from EHCI rather than platform
	ASoC: Intel: Kconfig: fix build when ACPI is not enabled
	netlink: fix nla_put_{u8,u16,u32} for KASAN
	dell-wmi, dell-laptop: depends DMI
	genksyms: Fix segfault with invalid declarations
	x86/microcode/AMD: Change load_microcode_amd()'s param to bool to fix preemptibility bug
	drm/gma500: remove helper function
	kasan: rework Kconfig settings
	KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously
	x86/retpoline: Remove the esp/rsp thunk
	KVM: x86: Make indirect calls in emulator speculation safe
	KVM: VMX: Make indirect call speculation safe
	module/retpoline: Warn about missing retpoline in module
	x86/nospec: Fix header guards names
	x86/bugs: Drop one "mitigation" from dmesg
	x86/cpu/bugs: Make retpoline module warning conditional
	x86/spectre: Check CONFIG_RETPOLINE in command line parser
	Documentation: Document array_index_nospec
	array_index_nospec: Sanitize speculative array de-references
	x86: Implement array_index_mask_nospec
	x86: Introduce barrier_nospec
	x86/get_user: Use pointer masking to limit speculation
	x86/syscall: Sanitize syscall table de-references under speculation
	vfs, fdtable: Prevent bounds-check bypass via speculative execution
	nl80211: Sanitize array index in parse_txq_params
	x86/spectre: Report get_user mitigation for spectre_v1
	x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable"
	x86/paravirt: Remove 'noreplace-paravirt' cmdline option
	x86/kvm: Update spectre-v1 mitigation
	x86/retpoline: Avoid retpolines for built-in __init functions
	x86/spectre: Simplify spectre_v2 command line parsing
	x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL
	KVM: nVMX: kmap() can't fail
	KVM: nVMX: vmx_complete_nested_posted_interrupt() can't fail
	kvm: nVMX: Fix kernel panics induced by illegal INVEPT/INVVPID types
	KVM: VMX: clean up declaration of VPID/EPT invalidation types
	KVM: nVMX: invvpid handling improvements
	crypto: s5p-sss - Fix kernel Oops in AES-ECB mode
	net: dst_cache_per_cpu_dst_set() can be static
	Linux 4.4.118

Change-Id: I01c76e1c15a611e13a1e98092bc5c01cdb5b6adb
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

42 files changed, 381 insertions, 273 deletions

diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index de8791a4d131..3ef1d5a26389 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -807,7 +807,8 @@
 			reg = <0x48038000 0x2000>,
 			      <0x46000000 0x400000>;
 			reg-names = "mpu", "dat";
-			interrupts = <80>, <81>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 8>,
@@ -821,7 +822,8 @@
 			reg = <0x4803C000 0x2000>,
 			      <0x46400000 0x400000>;
 			reg-names = "mpu", "dat";
-			interrupts = <82>, <83>;
+			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 10>,
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 5a206c100ce2..8a5628c4b135 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -844,14 +844,12 @@
 			usbhsohci: ohci@4a064800 {
 				compatible = "ti,ohci-omap3";
 				reg = <0x4a064800 0x400>;
-				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
 			usbhsehci: ehci@4a064c00 {
 				compatible = "ti,ehci-omap";
 				reg = <0x4a064c00 0x400>;
-				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index 5ac122e88f67..9ff92050053c 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -73,6 +73,25 @@ phys_addr_t omap_secure_ram_mempool_base(void)
 	return omap_secure_memblock_base;
 }
 
+u32 omap3_save_secure_ram(void __iomem *addr, int size)
+{
+	u32 ret;
+	u32 param[5];
+
+	if (size != OMAP3_SAVE_SECURE_RAM_SZ)
+		return OMAP3_SAVE_SECURE_RAM_SZ;
+
+	param[0] = 4;		/* Number of arguments */
+	param[1] = __pa(addr);	/* Physical address for saving */
+	param[2] = 0;
+	param[3] = 1;
+	param[4] = 1;
+
+	ret = save_secure_ram_context(__pa(param));
+
+	return ret;
+}
+
 /**
  * rx51_secure_dispatcher: Routine to dispatch secure PPA API calls
  * @idx: The PPA API index
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index af2851fbcdf0..ab6ce2597a88 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -31,6 +31,8 @@
 /* Maximum Secure memory storage size */
 #define OMAP_SECURE_RAM_STORAGE	(88 * SZ_1K)
 
+#define OMAP3_SAVE_SECURE_RAM_SZ	0x803F
+
 /* Secure low power HAL API index */
 #define OMAP4_HAL_SAVESECURERAM_INDEX	0x1a
 #define OMAP4_HAL_SAVEHW_INDEX		0x1b
@@ -64,6 +66,8 @@ extern u32 omap_smc2(u32 id, u32 falg, u32 pargs);
 extern u32 omap_smc3(u32 id, u32 process, u32 flag, u32 pargs);
 extern phys_addr_t omap_secure_ram_mempool_base(void);
 extern int omap_secure_ram_reserve_memblock(void);
+extern u32 save_secure_ram_context(u32 args_pa);
+extern u32 omap3_save_secure_ram(void __iomem *save_regs, int size);
 
 extern u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs,
 				  u32 arg1, u32 arg2, u32 arg3, u32 arg4);
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index b668719b9b25..8e30772cfe32 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -81,10 +81,6 @@ extern unsigned int omap3_do_wfi_sz;
 /* ... and its pointer from SRAM after copy */
 extern void (*omap3_do_wfi_sram)(void);
 
-/* save_secure_ram_context function pointer and size, for copy to SRAM */
-extern int save_secure_ram_context(u32 *addr);
-extern unsigned int save_secure_ram_context_sz;
-
 extern void omap3_save_scratchpad_contents(void);
 
 #define PM_RTA_ERRATUM_i608		(1 << 0)
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 2dbd3785ee6f..181da202f981 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -48,6 +48,7 @@
 #include "prm3xxx.h"
 #include "pm.h"
 #include "sdrc.h"
+#include "omap-secure.h"
 #include "sram.h"
 #include "control.h"
 #include "vc.h"
@@ -66,7 +67,6 @@ struct power_state {
 
 static LIST_HEAD(pwrst_list);
 
-static int (*_omap_save_secure_sram)(u32 *addr);
 void (*omap3_do_wfi_sram)(void);
 
 static struct powerdomain *mpu_pwrdm, *neon_pwrdm;
@@ -121,8 +121,8 @@ static void omap3_save_secure_ram_context(void)
 		 * will hang the system.
 		 */
 		pwrdm_set_next_pwrst(mpu_pwrdm, PWRDM_POWER_ON);
-		ret = _omap_save_secure_sram((u32 *)(unsigned long)
-				__pa(omap3_secure_ram_storage));
+		ret = omap3_save_secure_ram(omap3_secure_ram_storage,
+					    OMAP3_SAVE_SECURE_RAM_SZ);
 		pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state);
 		/* Following is for error tracking, it should not happen */
 		if (ret) {
@@ -431,15 +431,10 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *unused)
  *
  * The minimum set of functions is pushed to SRAM for execution:
  * - omap3_do_wfi for erratum i581 WA,
- * - save_secure_ram_context for security extensions.
  */
 void omap_push_sram_idle(void)
 {
 	omap3_do_wfi_sram = omap_sram_push(omap3_do_wfi, omap3_do_wfi_sz);
-
-	if (omap_type() != OMAP2_DEVICE_TYPE_GP)
-		_omap_save_secure_sram = omap_sram_push(save_secure_ram_context,
-				save_secure_ram_context_sz);
 }
 
 static void __init pm_errata_configure(void)
@@ -551,7 +546,7 @@ int __init omap3_pm_init(void)
 	clkdm_add_wkdep(neon_clkdm, mpu_clkdm);
 	if (omap_type() != OMAP2_DEVICE_TYPE_GP) {
 		omap3_secure_ram_storage =
-			kmalloc(0x803F, GFP_KERNEL);
+			kmalloc(OMAP3_SAVE_SECURE_RAM_SZ, GFP_KERNEL);
 		if (!omap3_secure_ram_storage)
 			pr_err("Memory allocation failed when allocating for secure sram context\n");
 
diff --git a/arch/arm/mach-omap2/prm33xx.c b/arch/arm/mach-omap2/prm33xx.c
index dcb5001d77da..973bcd754e1c 100644
--- a/arch/arm/mach-omap2/prm33xx.c
+++ b/arch/arm/mach-omap2/prm33xx.c
@@ -176,17 +176,6 @@ static int am33xx_pwrdm_read_pwrst(struct powerdomain *pwrdm)
 	return v;
 }
 
-static int am33xx_pwrdm_read_prev_pwrst(struct powerdomain *pwrdm)
-{
-	u32 v;
-
-	v = am33xx_prm_read_reg(pwrdm->prcm_offs, pwrdm->pwrstst_offs);
-	v &= AM33XX_LASTPOWERSTATEENTERED_MASK;
-	v >>= AM33XX_LASTPOWERSTATEENTERED_SHIFT;
-
-	return v;
-}
-
 static int am33xx_pwrdm_set_lowpwrstchange(struct powerdomain *pwrdm)
 {
 	am33xx_prm_rmw_reg_bits(AM33XX_LOWPOWERSTATECHANGE_MASK,
@@ -357,7 +346,6 @@ struct pwrdm_ops am33xx_pwrdm_operations = {
 	.pwrdm_set_next_pwrst		= am33xx_pwrdm_set_next_pwrst,
 	.pwrdm_read_next_pwrst		= am33xx_pwrdm_read_next_pwrst,
 	.pwrdm_read_pwrst		= am33xx_pwrdm_read_pwrst,
-	.pwrdm_read_prev_pwrst		= am33xx_pwrdm_read_prev_pwrst,
 	.pwrdm_set_logic_retst		= am33xx_pwrdm_set_logic_retst,
 	.pwrdm_read_logic_pwrst		= am33xx_pwrdm_read_logic_pwrst,
 	.pwrdm_read_logic_retst		= am33xx_pwrdm_read_logic_retst,
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index 1b9f0520dea9..3e0d802c59da 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -93,20 +93,13 @@ ENTRY(enable_omap3630_toggle_l2_on_restore)
 ENDPROC(enable_omap3630_toggle_l2_on_restore)
 
 /*
- * Function to call rom code to save secure ram context. This gets
- * relocated to SRAM, so it can be all in .data section. Otherwise
- * we need to initialize api_params separately.
+ * Function to call rom code to save secure ram context.
+ *
+ * r0 = physical address of the parameters
  */
-	.data
-	.align	3
 ENTRY(save_secure_ram_context)
 	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
-	adr	r3, api_params		@ r3 points to parameters
-	str	r0, [r3,#0x4]		@ r0 has sdram address
-	ldr	r12, high_mask
-	and	r3, r3, r12
-	ldr	r12, sram_phy_addr_mask
-	orr	r3, r3, r12
+	mov	r3, r0			@ physical address of parameters
 	mov	r0, #25			@ set service ID for PPA
 	mov	r12, r0			@ copy secure service ID in r12
 	mov	r1, #0			@ set task id for ROM code in r1
@@ -120,18 +113,7 @@ ENTRY(save_secure_ram_context)
 	nop
 	nop
 	ldmfd	sp!, {r4 - r11, pc}
-	.align
-sram_phy_addr_mask:
-	.word	SRAM_BASE_P
-high_mask:
-	.word	0xffff
-api_params:
-	.word	0x4, 0x0, 0x0, 0x1, 0x1
 ENDPROC(save_secure_ram_context)
-ENTRY(save_secure_ram_context_sz)
-	.word	. - save_secure_ram_context
-
-	.text
 
 /*
  * ======================
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 0fa4c5f8b1be..2d43357d4a0a 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -12,8 +12,6 @@ menuconfig ARCH_TEGRA
 	select ARCH_HAS_RESET_CONTROLLER
 	select RESET_CONTROLLER
 	select SOC_BUS
-	select USB_ULPI if USB_PHY
-	select USB_ULPI_VIEWPORT if USB_PHY
 	help
 	  This enables support for NVIDIA Tegra based systems.
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 768151fcb2cb..beca509bc257 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -981,7 +981,7 @@ source "fs/Kconfig.binfmt"
 config COMPAT
 	bool "Kernel support for 32-bit EL0"
 	depends on ARM64_4K_PAGES || EXPERT
-	select COMPAT_BINFMT_ELF
+	select COMPAT_BINFMT_ELF if BINFMT_ELF
 	select HAVE_UID16
 	select OLD_SIGSUSPEND3
 	select COMPAT_OLD_SIGACTION
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 4043c35962cc..5edb50772c11 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -90,8 +90,6 @@ config ARCH_TEGRA_132_SOC
 	bool "NVIDIA Tegra132 SoC"
 	depends on ARCH_TEGRA
 	select PINCTRL_TEGRA124
-	select USB_ULPI if USB_PHY
-	select USB_ULPI_VIEWPORT if USB_PHY
 	help
 	  Enable support for NVIDIA Tegra132 SoC, based on the Denver
 	  ARMv8 CPU.  The Tegra132 SoC is similar to the Tegra124 SoC,
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 4dd5f93d0303..7f42b646d528 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -54,6 +54,7 @@
 			reg = <0x000>;
 			enable-method = "psci";
 			cpu-idle-states = <&CPU_SLEEP_0>;
+			#cooling-cells = <2>;
 		};
 
 		cpu1: cpu@1 {
@@ -70,6 +71,7 @@
 			reg = <0x100>;
 			enable-method = "psci";
 			cpu-idle-states = <&CPU_SLEEP_0>;
+			#cooling-cells = <2>;
 		};
 
 		cpu3: cpu@101 {
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
index 561190d15881..0bfe1df12b19 100644
--- a/arch/arm64/include/asm/bug.h
+++ b/arch/arm64/include/asm/bug.h
@@ -20,9 +20,6 @@
 
 #include <asm/brk-imm.h>
 
-#ifdef CONFIG_GENERIC_BUG
-#define HAVE_ARCH_BUG
-
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 #define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
 #define __BUGVERBOSE_LOCATION(file, line)				\
@@ -36,28 +33,36 @@
 #define _BUGVERBOSE_LOCATION(file, line)
 #endif
 
-#define _BUG_FLAGS(flags) __BUG_FLAGS(flags)
+#ifdef CONFIG_GENERIC_BUG
 
-#define __BUG_FLAGS(flags) asm volatile (		\
+#define __BUG_ENTRY(flags) 				\
 		".pushsection __bug_table,\"a\"\n\t"	\
 		".align 2\n\t"				\
 	"0:	.long 1f - 0b\n\t"			\
 _BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
 		".short " #flags "\n\t"			\
 		".popsection\n"				\
-							\
-	"1:	brk %[imm]"				\
-		:: [imm] "i" (BUG_BRK_IMM)		\
-)
+	"1:	"
+#else
+#define __BUG_ENTRY(flags) ""
+#endif
+
+#define __BUG_FLAGS(flags)				\
+	asm volatile (					\
+		__BUG_ENTRY(flags)			\
+		"brk %[imm]" :: [imm] "i" (BUG_BRK_IMM)	\
+	);
 
-#define BUG() do {				\
-	_BUG_FLAGS(0);				\
-	unreachable();				\
+
+#define BUG() do {					\
+	__BUG_FLAGS(0);					\
+	unreachable();					\
 } while (0)
 
-#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint))
+#define __WARN_TAINT(taint) 				\
+	__BUG_FLAGS(BUGFLAG_TAINT(taint))
 
-#endif /* ! CONFIG_GENERIC_BUG */
+#define HAVE_ARCH_BUG
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b2ab164a8094..4eba7c00ea1f 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1381,7 +1381,7 @@ static int collect_events(struct perf_event *group, int max_count,
 	int n = 0;
 	struct perf_event *event;
 
-	if (!is_software_event(group)) {
+	if (group->pmu->task_ctx_nr == perf_hw_context) {
 		if (n >= max_count)
 			return -1;
 		ctrs[n] = group;
@@ -1389,7 +1389,7 @@ static int collect_events(struct perf_event *group, int max_count,
 		events[n++] = group->hw.config;
 	}
 	list_for_each_entry(event, &group->sibling_list, group_entry) {
-		if (!is_software_event(event) &&
+		if (event->pmu->task_ctx_nr == perf_hw_context &&
 		    event->state != PERF_EVENT_STATE_OFF) {
 			if (n >= max_count)
 				return -1;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 93a1b2af3ec3..ad1f3bfafe75 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1027,7 +1027,7 @@ config X86_MCE_THRESHOLD
 	def_bool y
 
 config X86_MCE_INJECT
-	depends on X86_MCE
+	depends on X86_MCE && X86_LOCAL_APIC
 	tristate "Machine check injector support"
 	---help---
 	  Provide support for injecting machine checks for testing purposes.
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 1f6c306a9a00..e5031f46c443 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -379,6 +379,7 @@ config X86_DEBUG_FPU
 
 config PUNIT_ATOM_DEBUG
 	tristate "ATOM Punit debug driver"
+	depends on PCI
 	select DEBUG_FS
 	select IOSF_MBI
 	---help---
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 707adf8b6a9f..6171d9153a33 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -71,12 +71,13 @@ GCOV_PROFILE := n
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
+silent_redirect_image = >/dev/null
 cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
-			       $(obj)/zoffset.h $@
+			       $(obj)/zoffset.h $@ $($(quiet)redirect_image)
 
 $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
 	$(call if_changed,image)
-	@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
+	@$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')'
 
 OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S
 $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index 1c3b7ceb36d2..e7273a606a07 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -55,29 +55,31 @@
 #define RAB1bl %bl
 #define RAB2bl %cl
 
+#define CD0 0x0(%rsp)
+#define CD1 0x8(%rsp)
+#define CD2 0x10(%rsp)
+
+# used only before/after all rounds
 #define RCD0 %r8
 #define RCD1 %r9
 #define RCD2 %r10
 
-#define RCD0d %r8d
-#define RCD1d %r9d
-#define RCD2d %r10d
-
-#define RX0 %rbp
-#define RX1 %r11
-#define RX2 %r12
+# used only during rounds
+#define RX0 %r8
+#define RX1 %r9
+#define RX2 %r10
 
-#define RX0d %ebp
-#define RX1d %r11d
-#define RX2d %r12d
+#define RX0d %r8d
+#define RX1d %r9d
+#define RX2d %r10d
 
-#define RY0 %r13
-#define RY1 %r14
-#define RY2 %r15
+#define RY0 %r11
+#define RY1 %r12
+#define RY2 %r13
 
-#define RY0d %r13d
-#define RY1d %r14d
-#define RY2d %r15d
+#define RY0d %r11d
+#define RY1d %r12d
+#define RY2d %r13d
 
 #define RT0 %rdx
 #define RT1 %rsi
@@ -85,6 +87,8 @@
 #define RT0d %edx
 #define RT1d %esi
 
+#define RT1bl %sil
+
 #define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \
 	movzbl ab ## bl,		tmp2 ## d; \
 	movzbl ab ## bh,		tmp1 ## d; \
@@ -92,6 +96,11 @@
 	op1##l T0(CTX, tmp2, 4),	dst ## d; \
 	op2##l T1(CTX, tmp1, 4),	dst ## d;
 
+#define swap_ab_with_cd(ab, cd, tmp)	\
+	movq cd, tmp;			\
+	movq ab, cd;			\
+	movq tmp, ab;
+
 /*
  * Combined G1 & G2 function. Reordered with help of rotates to have moves
  * at begining.
@@ -110,15 +119,15 @@
 	/* G1,2 && G2,2 */ \
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \
-	xchgq cd ## 0, ab ## 0; \
+	swap_ab_with_cd(ab ## 0, cd ## 0, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \
-	xchgq cd ## 1, ab ## 1; \
+	swap_ab_with_cd(ab ## 1, cd ## 1, RT0); \
 	\
 	do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \
 	do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \
-	xchgq cd ## 2, ab ## 2;
+	swap_ab_with_cd(ab ## 2, cd ## 2, RT0);
 
 #define enc_round_end(ab, x, y, n) \
 	addl y ## d,			x ## d; \
@@ -168,6 +177,16 @@
 	decrypt_round3(ba, dc, (n*2)+1); \
 	decrypt_round3(ba, dc, (n*2));
 
+#define push_cd()	\
+	pushq RCD2;	\
+	pushq RCD1;	\
+	pushq RCD0;
+
+#define pop_cd()	\
+	popq RCD0;	\
+	popq RCD1;	\
+	popq RCD2;
+
 #define inpack3(in, n, xy, m) \
 	movq 4*(n)(in),			xy ## 0; \
 	xorq w+4*m(CTX),		xy ## 0; \
@@ -223,11 +242,8 @@ ENTRY(__twofish_enc_blk_3way)
 	 *	%rdx: src, RIO
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rcx; /* bool xor */
@@ -235,40 +251,36 @@ ENTRY(__twofish_enc_blk_3way)
 
 	inpack_enc3();
 
-	encrypt_cycle3(RAB, RCD, 0);
-	encrypt_cycle3(RAB, RCD, 1);
-	encrypt_cycle3(RAB, RCD, 2);
-	encrypt_cycle3(RAB, RCD, 3);
-	encrypt_cycle3(RAB, RCD, 4);
-	encrypt_cycle3(RAB, RCD, 5);
-	encrypt_cycle3(RAB, RCD, 6);
-	encrypt_cycle3(RAB, RCD, 7);
+	push_cd();
+	encrypt_cycle3(RAB, CD, 0);
+	encrypt_cycle3(RAB, CD, 1);
+	encrypt_cycle3(RAB, CD, 2);
+	encrypt_cycle3(RAB, CD, 3);
+	encrypt_cycle3(RAB, CD, 4);
+	encrypt_cycle3(RAB, CD, 5);
+	encrypt_cycle3(RAB, CD, 6);
+	encrypt_cycle3(RAB, CD, 7);
+	pop_cd();
 
 	popq RIO; /* dst */
-	popq %rbp; /* bool xor */
+	popq RT1; /* bool xor */
 
-	testb %bpl, %bpl;
+	testb RT1bl, RT1bl;
 	jnz .L__enc_xor3;
 
 	outunpack_enc3(mov);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 
 .L__enc_xor3:
 	outunpack_enc3(xor);
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(__twofish_enc_blk_3way)
 
@@ -278,35 +290,31 @@ ENTRY(twofish_dec_blk_3way)
 	 *	%rsi: dst
 	 *	%rdx: src, RIO
 	 */
-	pushq %r15;
-	pushq %r14;
 	pushq %r13;
 	pushq %r12;
-	pushq %rbp;
 	pushq %rbx;
 
 	pushq %rsi; /* dst */
 
 	inpack_dec3();
 
-	decrypt_cycle3(RAB, RCD, 7);
-	decrypt_cycle3(RAB, RCD, 6);
-	decrypt_cycle3(RAB, RCD, 5);
-	decrypt_cycle3(RAB, RCD, 4);
-	decrypt_cycle3(RAB, RCD, 3);
-	decrypt_cycle3(RAB, RCD, 2);
-	decrypt_cycle3(RAB, RCD, 1);
-	decrypt_cycle3(RAB, RCD, 0);
+	push_cd();
+	decrypt_cycle3(RAB, CD, 7);
+	decrypt_cycle3(RAB, CD, 6);
+	decrypt_cycle3(RAB, CD, 5);
+	decrypt_cycle3(RAB, CD, 4);
+	decrypt_cycle3(RAB, CD, 3);
+	decrypt_cycle3(RAB, CD, 2);
+	decrypt_cycle3(RAB, CD, 1);
+	decrypt_cycle3(RAB, CD, 0);
+	pop_cd();
 
 	popq RIO; /* dst */
 
 	outunpack_dec3();
 
 	popq %rbx;
-	popq %rbp;
 	popq %r12;
 	popq %r13;
-	popq %r14;
-	popq %r15;
 	ret;
 ENDPROC(twofish_dec_blk_3way)
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 1a4477cedc49..b5eb1cca70a0 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -20,6 +20,7 @@
 #include <linux/export.h>
 #include <linux/context_tracking.h>
 #include <linux/user-return-notifier.h>
+#include <linux/nospec.h>
 #include <linux/uprobes.h>
 
 #include <asm/desc.h>
@@ -381,6 +382,7 @@ __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 	}
 
 	if (likely(nr < IA32_NR_syscalls)) {
+		nr = array_index_nospec(nr, IA32_NR_syscalls);
 		/*
 		 * It's possible that a 32-bit syscall implementation
 		 * takes a 64-bit parameter but nonetheless assumes that
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index b15aa4083dfd..5a25ada75aeb 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -37,5 +37,4 @@ INDIRECT_THUNK(dx)
 INDIRECT_THUNK(si)
 INDIRECT_THUNK(di)
 INDIRECT_THUNK(bp)
-INDIRECT_THUNK(sp)
 #endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 0681d2532527..814ef83c6720 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -24,6 +24,34 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
+/**
+ * array_index_mask_nospec() - generate a mask that is ~0UL when the
+ * 	bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * Returns:
+ *     0 - (index < size)
+ */
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+		unsigned long size)
+{
+	unsigned long mask;
+
+	asm ("cmp %1,%2; sbb %0,%0;"
+			:"=r" (mask)
+			:"r"(size),"r" (index)
+			:"cc");
+	return mask;
+}
+
+/* Override the default implementation from linux/nospec.h. */
+#define array_index_mask_nospec array_index_mask_nospec
+
+/* Prevent speculative execution past this barrier. */
+#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
+					   "lfence", X86_FEATURE_LFENCE_RDTSC)
+
 #ifdef CONFIG_X86_PPRO_FENCE
 #define dma_rmb()	rmb()
 #else
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index adfc847a395e..fb163f02ebb1 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,6 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
 
 #define PATCH_MAX_SIZE PAGE_SIZE
 extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 77d8b284e4a7..5a10ac8c131e 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -147,8 +147,7 @@ static __always_inline unsigned long long rdtsc_ordered(void)
 	 * that some other imaginary CPU is updating continuously with a
 	 * time stamp.
 	 */
-	alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
-			  "lfence", X86_FEATURE_LFENCE_RDTSC);
+	barrier_nospec();
 	return rdtsc();
 }
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 492370b9b35b..66094a0473a8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-#ifndef __NOSPEC_BRANCH_H__
-#define __NOSPEC_BRANCH_H__
+#ifndef _ASM_X86_NOSPEC_BRANCH_H_
+#define _ASM_X86_NOSPEC_BRANCH_H_
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
@@ -178,7 +178,7 @@ extern char __indirect_thunk_end[];
  * On VMEXIT we must ensure that no RSB predictions learned in the guest
  * can be followed in the host, by overwriting the RSB completely. Both
  * retpoline and IBRS mitigations for Spectre v2 need this; only on future
- * CPUs with IBRS_ATT *might* it be avoided.
+ * CPUs with IBRS_ALL *might* it be avoided.
  */
 static inline void vmexit_fill_RSB(void)
 {
@@ -195,4 +195,4 @@ static inline void vmexit_fill_RSB(void)
 }
 
 #endif /* __ASSEMBLY__ */
-#endif /* __NOSPEC_BRANCH_H__ */
+#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 14c63c7e8337..6b6e16d813b9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -400,10 +400,11 @@ enum vmcs_field {
 #define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 2)
 
 #define VMX_NR_VPIDS				(1 << 16)
+#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
 #define VMX_VPID_EXTENT_ALL_CONTEXT		2
+#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL	3
 
-#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_EPT_EXTENT_CONTEXT			1
 #define VMX_EPT_EXTENT_GLOBAL			2
 #define VMX_EPT_EXTENT_SHIFT			24
@@ -420,8 +421,10 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
 
 #define VMX_VPID_INVVPID_BIT                    (1ull << 0) /* (32 - 32) */
+#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT     (1ull << 8) /* (40 - 32) */
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9) /* (41 - 32) */
 #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
+#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT   (1ull << 11) /* (43 - 32) */
 
 #define VMX_EPT_DEFAULT_GAW			3
 #define VMX_EPT_MAX_GAW				0x4
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index d6f375f1b928..89829c3d5a74 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -45,17 +45,6 @@ static int __init setup_noreplace_smp(char *str)
 }
 __setup("noreplace-smp", setup_noreplace_smp);
 
-#ifdef CONFIG_PARAVIRT
-static int __initdata_or_module noreplace_paravirt = 0;
-
-static int __init setup_noreplace_paravirt(char *str)
-{
-	noreplace_paravirt = 1;
-	return 1;
-}
-__setup("noreplace-paravirt", setup_noreplace_paravirt);
-#endif
-
 #define DPRINTK(fmt, args...)						\
 do {									\
 	if (debug_alternative)						\
@@ -587,9 +576,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
 	struct paravirt_patch_site *p;
 	char insnbuf[MAX_PATCH_LEN];
 
-	if (noreplace_paravirt)
-		return;
-
 	for (p = start; p < end; p++) {
 		unsigned int used;
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 8cacf62ec458..ecaf7c9baf75 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/utsname.h>
 #include <linux/cpu.h>
+#include <linux/module.h>
 
 #include <asm/nospec-branch.h>
 #include <asm/cmdline.h>
@@ -89,20 +90,42 @@ static const char *spectre_v2_strings[] = {
 };
 
 #undef pr_fmt
-#define pr_fmt(fmt)     "Spectre V2 mitigation: " fmt
+#define pr_fmt(fmt)     "Spectre V2 : " fmt
 
 static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
 
+
+#ifdef RETPOLINE
+static bool spectre_v2_bad_module;
+
+bool retpoline_module_ok(bool has_retpoline)
+{
+	if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline)
+		return true;
+
+	pr_err("System may be vulnerable to spectre v2\n");
+	spectre_v2_bad_module = true;
+	return false;
+}
+
+static inline const char *spectre_v2_module_string(void)
+{
+	return spectre_v2_bad_module ? " - vulnerable module loaded" : "";
+}
+#else
+static inline const char *spectre_v2_module_string(void) { return ""; }
+#endif
+
 static void __init spec2_print_if_insecure(const char *reason)
 {
 	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		pr_info("%s\n", reason);
+		pr_info("%s selected on command line.\n", reason);
 }
 
 static void __init spec2_print_if_secure(const char *reason)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
-		pr_info("%s\n", reason);
+		pr_info("%s selected on command line.\n", reason);
 }
 
 static inline bool retp_compiler(void)
@@ -117,42 +140,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt)
 	return len == arglen && !strncmp(arg, opt, len);
 }
 
+static const struct {
+	const char *option;
+	enum spectre_v2_mitigation_cmd cmd;
+	bool secure;
+} mitigation_options[] = {
+	{ "off",               SPECTRE_V2_CMD_NONE,              false },
+	{ "on",                SPECTRE_V2_CMD_FORCE,             true },
+	{ "retpoline",         SPECTRE_V2_CMD_RETPOLINE,         false },
+	{ "retpoline,amd",     SPECTRE_V2_CMD_RETPOLINE_AMD,     false },
+	{ "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
+	{ "auto",              SPECTRE_V2_CMD_AUTO,              false },
+};
+
 static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 {
 	char arg[20];
-	int ret;
-
-	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
-				  sizeof(arg));
-	if (ret > 0)  {
-		if (match_option(arg, ret, "off")) {
-			goto disable;
-		} else if (match_option(arg, ret, "on")) {
-			spec2_print_if_secure("force enabled on command line.");
-			return SPECTRE_V2_CMD_FORCE;
-		} else if (match_option(arg, ret, "retpoline")) {
-			spec2_print_if_insecure("retpoline selected on command line.");
-			return SPECTRE_V2_CMD_RETPOLINE;
-		} else if (match_option(arg, ret, "retpoline,amd")) {
-			if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
-				pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
-				return SPECTRE_V2_CMD_AUTO;
-			}
-			spec2_print_if_insecure("AMD retpoline selected on command line.");
-			return SPECTRE_V2_CMD_RETPOLINE_AMD;
-		} else if (match_option(arg, ret, "retpoline,generic")) {
-			spec2_print_if_insecure("generic retpoline selected on command line.");
-			return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
-		} else if (match_option(arg, ret, "auto")) {
+	int ret, i;
+	enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO;
+
+	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+		return SPECTRE_V2_CMD_NONE;
+	else {
+		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+					  sizeof(arg));
+		if (ret < 0)
+			return SPECTRE_V2_CMD_AUTO;
+
+		for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) {
+			if (!match_option(arg, ret, mitigation_options[i].option))
+				continue;
+			cmd = mitigation_options[i].cmd;
+			break;
+		}
+
+		if (i >= ARRAY_SIZE(mitigation_options)) {
+			pr_err("unknown option (%s). Switching to AUTO select\n",
+			       mitigation_options[i].option);
 			return SPECTRE_V2_CMD_AUTO;
 		}
 	}
 
-	if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+	if ((cmd == SPECTRE_V2_CMD_RETPOLINE ||
+	     cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
+	     cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
+	    !IS_ENABLED(CONFIG_RETPOLINE)) {
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
+		       mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
-disable:
-	spec2_print_if_insecure("disabled on command line.");
-	return SPECTRE_V2_CMD_NONE;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+		pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (mitigation_options[i].secure)
+		spec2_print_if_secure(mitigation_options[i].option);
+	else
+		spec2_print_if_insecure(mitigation_options[i].option);
+
+	return cmd;
 }
 
 /* Check for Skylake-like CPUs (for RSB handling) */
@@ -190,10 +239,10 @@ static void __init spectre_v2_select_mitigation(void)
 		return;
 
 	case SPECTRE_V2_CMD_FORCE:
-		/* FALLTRHU */
 	case SPECTRE_V2_CMD_AUTO:
-		goto retpoline_auto;
-
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_auto;
+		break;
 	case SPECTRE_V2_CMD_RETPOLINE_AMD:
 		if (IS_ENABLED(CONFIG_RETPOLINE))
 			goto retpoline_amd;
@@ -268,7 +317,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev,
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Vulnerable\n");
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev,
@@ -277,6 +326,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]);
+	return sprintf(buf, "%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+		       spectre_v2_module_string());
 }
 #endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 4cfba4371a71..101bfae369e1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -152,7 +152,6 @@ static void raise_mce(struct mce *m)
 	if (context == MCJ_CTX_RANDOM)
 		return;
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
 		unsigned long start;
 		int cpu;
@@ -193,9 +192,7 @@ static void raise_mce(struct mce *m)
 		raise_local();
 		put_cpu();
 		put_online_cpus();
-	} else
-#endif
-	{
+	} else {
 		preempt_disable();
 		raise_local();
 		preempt_enable();
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 2a0f44d225fe..6da6f9cd6d2d 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -131,6 +131,9 @@ static size_t compute_container_size(u8 *data, u32 total_size)
 	return size;
 }
 
+static enum ucode_state
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
+
 /*
  * Early load occurs before we can vmalloc(). So we look for the microcode
  * patch container file in initrd, traverse equivalent cpu table, look for a
@@ -438,7 +441,7 @@ int __init save_microcode_in_initrd_amd(void)
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
-	ret = load_microcode_amd(smp_processor_id(), eax, container, container_size);
+	ret = load_microcode_amd(true, eax, container, container_size);
 	if (ret != UCODE_OK)
 		retval = -EINVAL;
 
@@ -854,7 +857,8 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 	return UCODE_OK;
 }
 
-enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+static enum ucode_state
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
@@ -868,8 +872,8 @@ enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t s
 
 #ifdef CONFIG_X86_32
 	/* save BSP's matching patch for early load */
-	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(cpu);
+	if (save) {
+		struct ucode_patch *p = find_patch(0);
 		if (p) {
 			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
 			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -901,11 +905,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	enum ucode_state ret = UCODE_NFOUND;
 	const struct firmware *fw;
 
 	/* reload ucode container only on the boot cpu */
-	if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+	if (!refresh_fw || !bsp)
 		return UCODE_OK;
 
 	if (c->x86 >= 0x15)
@@ -922,7 +927,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5b2f2306fbcc..b52a8d08ab36 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -188,8 +188,8 @@ static void release_pmc_hardware(void) {}
 
 static bool check_hw_exists(void)
 {
-	u64 val, val_fail, val_new= ~0;
-	int i, reg, reg_fail, ret = 0;
+	u64 val, val_fail = -1, val_new= ~0;
+	int i, reg, reg_fail = -1, ret = 0;
 	int bios_fail = 0;
 	int reg_safe = -1;
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 8f1a3f443f7d..70284d38fdc2 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -669,14 +669,17 @@ __PAGE_ALIGNED_BSS
 initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
-ENTRY(initial_page_table)
+.globl initial_page_table
+initial_page_table:
 	.fill 1024,4,0
 #endif
 initial_pg_fixmap:
 	.fill 1024,4,0
-ENTRY(empty_zero_page)
+.globl empty_zero_page
+empty_zero_page:
 	.fill 4096,1,0
-ENTRY(swapper_pg_dir)
+.globl swapper_pg_dir
+swapper_pg_dir:
 	.fill 1024,4,0
 
 /*
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 639a6e34500c..53b7f53f6207 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -22,7 +22,8 @@ config KVM
 	depends on HAVE_KVM
 	depends on HIGH_RES_TIMERS
 	# for TASKSTATS/TASK_DELAY_ACCT:
-	depends on NET
+	depends on NET && MULTIUSER
+	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e4eb1d2bf849..8864fec63a20 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -26,6 +26,7 @@
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
 #include <asm/debugreg.h>
+#include <asm/nospec-branch.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -1000,8 +1001,8 @@ static u8 test_cc(unsigned int condition, unsigned long flags)
 	void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
-	asm("push %[flags]; popf; call *%[fastop]"
-	    : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
+	asm("push %[flags]; popf; " CALL_NOSPEC
+	    : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
 	return rc;
 }
 
@@ -5297,9 +5298,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
 	ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
 	if (!(ctxt->d & ByteOp))
 		fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
-	asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
+	asm("push %[flags]; popf; " CALL_NOSPEC "; pushf; pop %[flags]\n"
 	    : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
-	      [fastop]"+S"(fop)
+	      [thunk_target]"+S"(fop)
 	    : "c"(ctxt->src2.val));
 	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
 	if (!fop) /* exception is returned in fop variable */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2a1a8737015b..849517805eef 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -32,6 +32,7 @@
 #include <linux/slab.h>
 #include <linux/tboot.h>
 #include <linux/hrtimer.h>
+#include <linux/nospec.h>
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
@@ -125,6 +126,12 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
 
 #define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
 
+#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
+	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
+
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
@@ -827,21 +834,18 @@ static const unsigned short vmcs_field_to_offset_table[] = {
 
 static inline short vmcs_field_to_offset(unsigned long field)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
+	const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table);
+	unsigned short offset;
 
-	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table))
+	BUILD_BUG_ON(size > SHRT_MAX);
+	if (field >= size)
 		return -ENOENT;
 
-	/*
-	 * FIXME: Mitigation for CVE-2017-5753.  To be replaced with a
-	 * generic mechanism.
-	 */
-	asm("lfence");
-
-	if (vmcs_field_to_offset_table[field] == 0)
+	field = array_index_nospec(field, size);
+	offset = vmcs_field_to_offset_table[field];
+	if (offset == 0)
 		return -ENOENT;
-
-	return vmcs_field_to_offset_table[field];
+	return offset;
 }
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
@@ -2659,8 +2663,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 */
 	if (enable_vpid)
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
-				VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
-				VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
+			VMX_VPID_EXTENT_SUPPORTED_MASK;
 	else
 		vmx->nested.nested_vmx_vpid_caps = 0;
 
@@ -4514,7 +4517,7 @@ static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
 	return enable_apicv && lapic_in_kernel(vcpu);
 }
 
-static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
+static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
@@ -4525,19 +4528,15 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	    vmx->nested.pi_pending) {
 		vmx->nested.pi_pending = false;
 		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return 0;
+			return;
 
 		max_irr = find_last_bit(
 			(unsigned long *)vmx->nested.pi_desc->pir, 256);
 
 		if (max_irr == 256)
-			return 0;
+			return;
 
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
-		if (!vapic_page) {
-			WARN_ON(1);
-			return -ENOMEM;
-		}
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
 
@@ -4548,7 +4547,6 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
-	return 0;
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
@@ -7368,7 +7366,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 
 	types = (vmx->nested.nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -7425,9 +7423,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
 
-	types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
+	types = (vmx->nested.nested_vmx_vpid_caps &
+			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -7447,21 +7446,27 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	}
 
 	switch (type) {
+	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
 	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
-		/*
-		 * Old versions of KVM use the single-context version so we
-		 * have to support it; just treat it the same as all-context.
-		 */
+	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
+		if (!vpid) {
+			nested_vmx_failValid(vcpu,
+				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+			skip_emulated_instruction(vcpu);
+			return 1;
+		}
+		break;
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
-		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
-		nested_vmx_succeed(vcpu);
 		break;
 	default:
-		/* Trap individual address invalidation invvpid calls */
-		BUG_ON(1);
-		break;
+		WARN_ON_ONCE(1);
+		skip_emulated_instruction(vcpu);
+		return 1;
 	}
 
+	__vmx_flush_tlb(vcpu, vmx->nested.vpid02);
+	nested_vmx_succeed(vcpu);
+
 	skip_emulated_instruction(vcpu);
 	return 1;
 }
@@ -8377,13 +8382,13 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			"pushf\n\t"
 			"orl $0x200, (%%" _ASM_SP ")\n\t"
 			__ASM_SIZE(push) " $%c[cs]\n\t"
-			"call *%[entry]\n\t"
+			CALL_NOSPEC
 			:
 #ifdef CONFIG_X86_64
 			[sp]"=&r"(tmp)
 #endif
 			:
-			[entry]"r"(entry),
+			THUNK_TARGET(entry),
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
@@ -9240,11 +9245,6 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
 		return false;
 	}
 	msr_bitmap = (unsigned long *)kmap(page);
-	if (!msr_bitmap) {
-		nested_release_page_clean(page);
-		WARN_ON(1);
-		return false;
-	}
 
 	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
 		if (nested_cpu_has_apic_reg_virt(vmcs12))
@@ -10166,7 +10166,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		return 0;
 	}
 
-	return vmx_complete_nested_posted_interrupt(vcpu);
+	vmx_complete_nested_posted_interrupt(vcpu);
+	return 0;
 }
 
 static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3900d34980de..f37f0c72b22a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2755,6 +2755,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
+	/*
+	 * If userspace has set any breakpoints or watchpoints, dr6 is restored
+	 * on every vmexit, but if not, we might have a stale dr6 from the
+	 * guest. do_debug expects dr6 to be cleared after it runs, do the same.
+	 */
+	set_debugreg(0, 6);
 }
 
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -8204,6 +8210,13 @@ static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
 				      sizeof(val));
 }
 
+static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val)
+{
+
+	return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val,
+				      sizeof(u32));
+}
+
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work)
 {
@@ -8230,6 +8243,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 				 struct kvm_async_pf *work)
 {
 	struct x86_exception fault;
+	u32 val;
 
 	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
@@ -8237,14 +8251,24 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
 	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 
-	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
-	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
-		fault.vector = PF_VECTOR;
-		fault.error_code_valid = true;
-		fault.error_code = 0;
-		fault.nested_page_fault = false;
-		fault.address = work->arch.token;
-		kvm_inject_page_fault(vcpu, &fault);
+	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
+	    !apf_get_user(vcpu, &val)) {
+		if (val == KVM_PV_REASON_PAGE_NOT_PRESENT &&
+		    vcpu->arch.exception.pending &&
+		    vcpu->arch.exception.nr == PF_VECTOR &&
+		    !apf_put_user(vcpu, 0)) {
+			vcpu->arch.exception.pending = false;
+			vcpu->arch.exception.nr = 0;
+			vcpu->arch.exception.has_error_code = false;
+			vcpu->arch.exception.error_code = 0;
+		} else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
+			fault.vector = PF_VECTOR;
+			fault.error_code_valid = true;
+			fault.error_code = 0;
+			fault.nested_page_fault = false;
+			fault.address = work->arch.token;
+			kvm_inject_page_fault(vcpu, &fault);
+		}
 	}
 	vcpu->arch.apf.halted = false;
 	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 46668cda4ffd..490b2ee4e4bb 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -38,6 +38,8 @@ ENTRY(__get_user_1)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 1:	movzbl (%_ASM_AX),%edx
 	xor %eax,%eax
@@ -51,6 +53,8 @@ ENTRY(__get_user_2)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 2:	movzwl -1(%_ASM_AX),%edx
 	xor %eax,%eax
@@ -64,6 +68,8 @@ ENTRY(__get_user_4)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 3:	movl -3(%_ASM_AX),%edx
 	xor %eax,%eax
@@ -78,6 +84,8 @@ ENTRY(__get_user_8)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 4:	movq -7(%_ASM_AX),%rdx
 	xor %eax,%eax
@@ -89,6 +97,8 @@ ENTRY(__get_user_8)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user_8
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 4:	movl -7(%_ASM_AX),%edx
 5:	movl -3(%_ASM_AX),%ecx
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index e611a124c442..3d06b482ebc7 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -36,7 +36,6 @@ GENERATE_THUNK(_ASM_DX)
 GENERATE_THUNK(_ASM_SI)
 GENERATE_THUNK(_ASM_DI)
 GENERATE_THUNK(_ASM_BP)
-GENERATE_THUNK(_ASM_SP)
 #ifdef CONFIG_64BIT
 GENERATE_THUNK(r8)
 GENERATE_THUNK(r9)
diff --git a/arch/x86/math-emu/Makefile b/arch/x86/math-emu/Makefile
index 9b0c63b60302..1b2dac174321 100644
--- a/arch/x86/math-emu/Makefile
+++ b/arch/x86/math-emu/Makefile
@@ -5,8 +5,8 @@
 #DEBUG	= -DDEBUGGING
 DEBUG	=
 PARANOID = -DPARANOID
-EXTRA_CFLAGS	:= $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION)
-EXTRA_AFLAGS	:= $(PARANOID)
+ccflags-y += $(PARANOID) $(DEBUG) -fno-builtin $(MATH_EMULATION)
+asflags-y += $(PARANOID)
 
 # From 'C' language sources:
 C_OBJS =fpu_entry.o errors.o \
diff --git a/arch/x86/math-emu/reg_compare.c b/arch/x86/math-emu/reg_compare.c
index b77360fdbf4a..19b33b50adfa 100644
--- a/arch/x86/math-emu/reg_compare.c
+++ b/arch/x86/math-emu/reg_compare.c
@@ -168,7 +168,7 @@ static int compare(FPU_REG const *b, int tagb)
 /* This function requires that st(0) is not empty */
 int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag)
 {
-	int f = 0, c;
+	int f, c;
 
 	c = compare(loaded_data, loaded_tag);
 
@@ -189,12 +189,12 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag)
 		case COMP_No_Comp:
 			f = SW_C3 | SW_C2 | SW_C0;
 			break;
-#ifdef PARANOID
 		default:
+#ifdef PARANOID
 			EXCEPTION(EX_INTERNAL | 0x121);
+#endif /* PARANOID */
 			f = SW_C3 | SW_C2 | SW_C0;
 			break;
-#endif /* PARANOID */
 		}
 	setcc(f);
 	if (c & COMP_Denormal) {
@@ -205,7 +205,7 @@ int FPU_compare_st_data(FPU_REG const *loaded_data, u_char loaded_tag)
 
 static int compare_st_st(int nr)
 {
-	int f = 0, c;
+	int f, c;
 	FPU_REG *st_ptr;
 
 	if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) {
@@ -235,12 +235,12 @@ static int compare_st_st(int nr)
 		case COMP_No_Comp:
 			f = SW_C3 | SW_C2 | SW_C0;
 			break;
-#ifdef PARANOID
 		default:
+#ifdef PARANOID
 			EXCEPTION(EX_INTERNAL | 0x122);
+#endif /* PARANOID */
 			f = SW_C3 | SW_C2 | SW_C0;
 			break;
-#endif /* PARANOID */
 		}
 	setcc(f);
 	if (c & COMP_Denormal) {
@@ -283,12 +283,12 @@ static int compare_i_st_st(int nr)
 	case COMP_No_Comp:
 		f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF;
 		break;
-#ifdef PARANOID
 	default:
+#ifdef PARANOID
 		EXCEPTION(EX_INTERNAL | 0x122);
+#endif /* PARANOID */
 		f = 0;
 		break;
-#endif /* PARANOID */
 	}
 	FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f;
 	if (c & COMP_Denormal) {
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index b9c78f3bcd67..53ab3f367472 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -348,11 +348,11 @@ void iounmap(volatile void __iomem *addr)
 	    (void __force *)addr < phys_to_virt(ISA_END_ADDRESS))
 		return;
 
+	mmiotrace_iounmap(addr);
+
 	addr = (volatile void __iomem *)
 		(PAGE_MASK & (unsigned long __force)addr);
 
-	mmiotrace_iounmap(addr);
-
 	/* Use the vm area unlocked, assuming the caller
 	   ensures there isn't another iounmap for the same address
 	   in parallel. Reuse of the virtual address is prevented by
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index ddb2244b06a1..76604c8a2a48 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -434,17 +434,18 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	unsigned long flags;
 	int ret = 0;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	unsigned int l;
 	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	if (get_kmmio_probe(p->addr)) {
+	if (get_kmmio_probe(addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte) {
 		ret = -EINVAL;
 		goto out;
@@ -453,7 +454,7 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
-		if (add_kmmio_fault_page(p->addr + size))
+		if (add_kmmio_fault_page(addr + size))
 			pr_err("Unable to set page fault.\n");
 		size += page_level_size(l);
 	}
@@ -527,19 +528,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 {
 	unsigned long flags;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
 	unsigned int l;
 	pte_t *pte;
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte)
 		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
-		release_kmmio_fault_page(p->addr + size, &release_list);
+		release_kmmio_fault_page(addr + size, &release_list);
 		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c
index 55130846ac87..c0533fbc39e3 100644
--- a/arch/x86/platform/olpc/olpc-xo15-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo15-sci.c
@@ -196,6 +196,7 @@ static int xo15_sci_remove(struct acpi_device *device)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int xo15_sci_resume(struct device *dev)
 {
 	/* Enable all EC events */
@@ -207,6 +208,7 @@ static int xo15_sci_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(xo15_sci_pm, NULL, xo15_sci_resume);