Linux 5.4.8

commit 15f0ec941f upstream.

LTP memfd_create04 started failing for some huge page sizes
after v5.4-10135-gc3bfc5dd73c6.

The problem is the check introduced to for_each_hstate() loop that
should skip default_hstate_idx.  Since it doesn't update 'i' counter,
all subsequent huge page sizes are skipped as well.

Fixes: 8fc312b32b ("mm/hugetlbfs: fix error handling when setting up mounts")
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/admin-guide/hw-vuln/mds.rst

@@ -265,8 +265,11 @@ time with the option "mds=". The valid arguments for this option are:
 
   ============  =============================================================
 
-Not specifying this option is equivalent to "mds=full".
-
+Not specifying this option is equivalent to "mds=full". For processors
+that are affected by both TAA (TSX Asynchronous Abort) and MDS,
+specifying just "mds=off" without an accompanying "tsx_async_abort=off"
+will have no effect as the same mitigation is used for both
+vulnerabilities.
 
 Mitigation selection guide
 --------------------------

Documentation/admin-guide/hw-vuln/tsx_async_abort.rst

@@ -174,7 +174,10 @@ the option "tsx_async_abort=". The valid arguments for this option are:
                 CPU is not vulnerable to cross-thread TAA attacks.
   ============  =============================================================
 
-Not specifying this option is equivalent to "tsx_async_abort=full".
+Not specifying this option is equivalent to "tsx_async_abort=full". For
+processors that are affected by both TAA and MDS, specifying just
+"tsx_async_abort=off" without an accompanying "mds=off" will have no
+effect as the same mitigation is used for both vulnerabilities.
 
 The kernel command line also allows to control the TSX feature using the
 parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used

Documentation/admin-guide/kernel-parameters.txt

@@ -2473,6 +2473,12 @@
 				     SMT on vulnerable CPUs
 			off        - Unconditionally disable MDS mitigation
 
+			On TAA-affected machines, mds=off can be prevented by
+			an active TAA mitigation as both vulnerabilities are
+			mitigated with the same mechanism so in order to disable
+			this mitigation, you need to specify tsx_async_abort=off
+			too.
+
 			Not specifying this option is equivalent to
 			mds=full.
 
@@ -4931,6 +4937,11 @@
 				     vulnerable to cross-thread TAA attacks.
 			off        - Unconditionally disable TAA mitigation
 
+			On MDS-affected machines, tsx_async_abort=off can be
+			prevented by an active MDS mitigation as both vulnerabilities
+			are mitigated with the same mechanism so in order to disable
+			this mitigation, you need to specify mds=off too.
+
 			Not specifying this option is equivalent to
 			tsx_async_abort=full.  On CPUs which are MDS affected
 			and deploy MDS mitigation, TAA mitigation is not
@@ -5090,13 +5101,13 @@
 			Flags is a set of characters, each corresponding
 			to a common usb-storage quirk flag as follows:
 				a = SANE_SENSE (collect more than 18 bytes
-					of sense data);
+					of sense data, not on uas);
 				b = BAD_SENSE (don't collect more than 18
-					bytes of sense data);
+					bytes of sense data, not on uas);
 				c = FIX_CAPACITY (decrease the reported
 					device capacity by one sector);
 				d = NO_READ_DISC_INFO (don't use
-					READ_DISC_INFO command);
+					READ_DISC_INFO command, not on uas);
 				e = NO_READ_CAPACITY_16 (don't use
 					READ_CAPACITY_16 command);
 				f = NO_REPORT_OPCODES (don't use report opcodes
@@ -5111,17 +5122,18 @@
 				j = NO_REPORT_LUNS (don't use report luns
 					command, uas only);
 				l = NOT_LOCKABLE (don't try to lock and
-					unlock ejectable media);
+					unlock ejectable media, not on uas);
 				m = MAX_SECTORS_64 (don't transfer more
-					than 64 sectors = 32 KB at a time);
+					than 64 sectors = 32 KB at a time,
+					not on uas);
 				n = INITIAL_READ10 (force a retry of the
-					initial READ(10) command);
+					initial READ(10) command, not on uas);
 				o = CAPACITY_OK (accept the capacity
-					reported by the device);
+					reported by the device, not on uas);
 				p = WRITE_CACHE (the device cache is ON
-					by default);
+					by default, not on uas);
 				r = IGNORE_RESIDUE (the device reports
-					bogus residue values);
+					bogus residue values, not on uas);
 				s = SINGLE_LUN (the device has only one
 					Logical Unit);
 				t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
@@ -5130,7 +5142,8 @@
 				w = NO_WP_DETECT (don't test whether the
 					medium is write-protected).
 				y = ALWAYS_SYNC (issue a SYNCHRONIZE_CACHE
-					even if the device claims no cache)
+					even if the device claims no cache,
+					not on uas)
 			Example: quirks=0419:aaf5:rl,0421:0433:rc
 
 	user_debug=	[KNL,ARM]

Documentation/devicetree/bindings/Makefile

@@ -12,7 +12,6 @@ $(obj)/%.example.dts: $(src)/%.yaml FORCE
 	$(call if_changed,chk_binding)
 
 DT_TMP_SCHEMA := processed-schema.yaml
-extra-y += $(DT_TMP_SCHEMA)
 
 quiet_cmd_mk_schema = SCHEMA  $@
       cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(real-prereqs)
@@ -26,8 +25,12 @@ DT_DOCS = $(shell \
 
 DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS))
 
+ifeq ($(CHECK_DTBS),)
 extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES))
 extra-y += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES))
+endif
 
 $(obj)/$(DT_TMP_SCHEMA): $(DT_SCHEMA_FILES) FORCE
 	$(call if_changed,mk_schema)
+
+extra-y += $(DT_TMP_SCHEMA)

Documentation/devicetree/bindings/net/wireless/qcom,ath10k.txt

@@ -81,6 +81,12 @@ Optional properties:
 	Definition: Name of external front end module used. Some valid FEM names
 		    for example: "microsemi-lx5586", "sky85703-11"
 		    and "sky85803" etc.
+- qcom,snoc-host-cap-8bit-quirk:
+	Usage: Optional
+	Value type: <empty>
+	Definition: Quirk specifying that the firmware expects the 8bit version
+		    of the host capability QMI request
+
 
 Example (to supply PCI based wifi block details):
 

Documentation/devicetree/writing-schema.rst

@@ -130,11 +130,13 @@ binding schema. All of the DT binding documents can be validated using the
 
     make dt_binding_check
 
-In order to perform validation of DT source files, use the `dtbs_check` target::
+In order to perform validation of DT source files, use the ``dtbs_check`` target::
 
     make dtbs_check
 
-This will first run the `dt_binding_check` which generates the processed schema.
+Note that ``dtbs_check`` will skip any binding schema files with errors. It is
+necessary to use ``dt_binding_check`` to get all the validation errors in the
+binding schema files.
 
 It is also possible to run checks with a single schema file by setting the
 ``DT_SCHEMA_FILES`` variable to a specific schema file.

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 0
+SUBLEVEL = 8
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 

arch/arm/boot/compressed/libfdt_env.h

@@ -2,11 +2,13 @@
 #ifndef _ARM_LIBFDT_ENV_H
 #define _ARM_LIBFDT_ENV_H
 
+#include <linux/limits.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <asm/byteorder.h>
 
-#define INT_MAX			((int)(~0U>>1))
+#define INT32_MAX	S32_MAX
+#define UINT32_MAX	U32_MAX
 
 typedef __be16 fdt16_t;
 typedef __be32 fdt32_t;

arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi

@@ -160,12 +160,12 @@
 		regulator-enable-ramp-delay = <1000>;
 	};
 
-	/* Used by DSS */
+	/* Used by DSS and is the "zerov_regulator" trigger for SoC off mode */
 	vcsi: VCSI {
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 		regulator-enable-ramp-delay = <1000>;
-		regulator-boot-on;
+		regulator-always-on;
 	};
 
 	vdac: VDAC {

arch/arm/boot/dts/omap3-pandora-common.dtsi

@@ -226,6 +226,17 @@
 		gpio = <&gpio6 4 GPIO_ACTIVE_HIGH>;	/* GPIO_164 */
 	};
 
+	/* wl1251 wifi+bt module */
+	wlan_en: fixed-regulator-wg7210_en {
+		compatible = "regulator-fixed";
+		regulator-name = "vwlan";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		startup-delay-us = <50000>;
+		enable-active-high;
+		gpio = <&gpio1 23 GPIO_ACTIVE_HIGH>;
+	};
+
 	/* wg7210 (wifi+bt module) 32k clock buffer */
 	wg7210_32k: fixed-regulator-wg7210_32k {
 		compatible = "regulator-fixed";
@@ -522,9 +533,30 @@
 	/*wp-gpios = <&gpio4 31 GPIO_ACTIVE_HIGH>;*/	/* GPIO_127 */
 };
 
-/* mmc3 is probed using pdata-quirks to pass wl1251 card data */
 &mmc3 {
-	status = "disabled";
+	vmmc-supply = <&wlan_en>;
+
+	bus-width = <4>;
+	non-removable;
+	ti,non-removable;
+	cap-power-off-card;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc3_pins>;
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	wlan: wifi@1 {
+		compatible = "ti,wl1251";
+
+		reg = <1>;
+
+		interrupt-parent = <&gpio1>;
+		interrupts = <21 IRQ_TYPE_LEVEL_HIGH>;	/* GPIO_21 */
+
+		ti,wl1251-has-eeprom;
+	};
 };
 
 /* bluetooth*/

arch/arm/boot/dts/omap3-tao3530.dtsi

@@ -222,7 +222,7 @@
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vmmc1>;
 	vqmmc-supply = <&vsim>;
-	cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>;
 	bus-width = <8>;
 };
 

arch/arm/boot/dts/s3c6410-mini6410.dts

@@ -165,6 +165,10 @@
 	};
 };
 
+&clocks {
+	clocks = <&fin_pll>;
+};
+
 &sdhci0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd0_clk>, <&sd0_cmd>, <&sd0_cd>, <&sd0_bus4>;

arch/arm/boot/dts/s3c6410-smdk6410.dts

@@ -69,6 +69,10 @@
 	};
 };
 
+&clocks {
+	clocks = <&fin_pll>;
+};
+
 &sdhci0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd0_clk>, <&sd0_cmd>, <&sd0_cd>, <&sd0_bus4>;

arch/arm/mach-omap2/pdata-quirks.c

@@ -7,7 +7,6 @@
 #include <linux/clk.h>
 #include <linux/davinci_emac.h>
 #include <linux/gpio.h>
-#include <linux/gpio/machine.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/of_platform.h>
@@ -311,118 +310,15 @@ static void __init omap3_logicpd_torpedo_init(void)
 }
 
 /* omap3pandora legacy devices */
-#define PANDORA_WIFI_IRQ_GPIO		21
-#define PANDORA_WIFI_NRESET_GPIO	23
 
 static struct platform_device pandora_backlight = {
 	.name	= "pandora-backlight",
 	.id	= -1,
 };
 
-static struct regulator_consumer_supply pandora_vmmc3_supply[] = {
-	REGULATOR_SUPPLY("vmmc", "omap_hsmmc.2"),
-};
-
-static struct regulator_init_data pandora_vmmc3 = {
-	.constraints = {
-		.valid_ops_mask		= REGULATOR_CHANGE_STATUS,
-	},
-	.num_consumer_supplies	= ARRAY_SIZE(pandora_vmmc3_supply),
-	.consumer_supplies	= pandora_vmmc3_supply,
-};
-
-static struct fixed_voltage_config pandora_vwlan = {
-	.supply_name		= "vwlan",
-	.microvolts		= 1800000, /* 1.8V */
-	.startup_delay		= 50000, /* 50ms */
-	.init_data		= &pandora_vmmc3,
-};
-
-static struct platform_device pandora_vwlan_device = {
-	.name		= "reg-fixed-voltage",
-	.id		= 1,
-	.dev = {
-		.platform_data = &pandora_vwlan,
-	},
-};
-
-static struct gpiod_lookup_table pandora_vwlan_gpiod_table = {
-	.dev_id = "reg-fixed-voltage.1",
-	.table = {
-		/*
-		 * As this is a low GPIO number it should be at the first
-		 * GPIO bank.
-		 */
-		GPIO_LOOKUP("gpio-0-31", PANDORA_WIFI_NRESET_GPIO,
-			    NULL, GPIO_ACTIVE_HIGH),
-		{ },
-	},
-};
-
-static void pandora_wl1251_init_card(struct mmc_card *card)
-{
-	/*
-	 * We have TI wl1251 attached to MMC3. Pass this information to
-	 * SDIO core because it can't be probed by normal methods.
-	 */
-	if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) {
-		card->quirks |= MMC_QUIRK_NONSTD_SDIO;
-		card->cccr.wide_bus = 1;
-		card->cis.vendor = 0x104c;
-		card->cis.device = 0x9066;
-		card->cis.blksize = 512;
-		card->cis.max_dtr = 24000000;
-		card->ocr = 0x80;
-	}
-}
-
-static struct omap2_hsmmc_info pandora_mmc3[] = {
-	{
-		.mmc		= 3,
-		.caps		= MMC_CAP_4_BIT_DATA | MMC_CAP_POWER_OFF_CARD,
-		.init_card	= pandora_wl1251_init_card,
-	},
-	{}	/* Terminator */
-};
-
-static void __init pandora_wl1251_init(void)
-{
-	struct wl1251_platform_data pandora_wl1251_pdata;
-	int ret;
-
-	memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata));
-
-	pandora_wl1251_pdata.power_gpio = -1;
-
-	ret = gpio_request_one(PANDORA_WIFI_IRQ_GPIO, GPIOF_IN, "wl1251 irq");
-	if (ret < 0)
-		goto fail;
-
-	pandora_wl1251_pdata.irq = gpio_to_irq(PANDORA_WIFI_IRQ_GPIO);
-	if (pandora_wl1251_pdata.irq < 0)
-		goto fail_irq;
-
-	pandora_wl1251_pdata.use_eeprom = true;
-	ret = wl1251_set_platform_data(&pandora_wl1251_pdata);
-	if (ret < 0)
-		goto fail_irq;
-
-	return;
-
-fail_irq:
-	gpio_free(PANDORA_WIFI_IRQ_GPIO);
-fail:
-	pr_err("wl1251 board initialisation failed\n");
-}
-
 static void __init omap3_pandora_legacy_init(void)
 {
 	platform_device_register(&pandora_backlight);
-	gpiod_add_lookup_table(&pandora_vwlan_gpiod_table);
-	platform_device_register(&pandora_vwlan_device);
-	omap_hsmmc_init(pandora_mmc3);
-	omap_hsmmc_late_init(pandora_mmc3);
-	pandora_wl1251_init();
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 

arch/arm/mach-tegra/reset-handler.S

@@ -44,16 +44,16 @@ ENTRY(tegra_resume)
 	cmp	r6, #TEGRA20
 	beq	1f				@ Yes
 	/* Clear the flow controller flags for this CPU. */
-	cpu_to_csr_reg r1, r0
+	cpu_to_csr_reg r3, r0
 	mov32	r2, TEGRA_FLOW_CTRL_BASE
-	ldr	r1, [r2, r1]
+	ldr	r1, [r2, r3]
 	/* Clear event & intr flag */
 	orr	r1, r1, \
 		#FLOW_CTRL_CSR_INTR_FLAG | FLOW_CTRL_CSR_EVENT_FLAG
 	movw	r0, #0x3FFD	@ enable, cluster_switch, immed, bitmaps
 				@ & ext flags for CPU power mgnt
 	bic	r1, r1, r0
-	str	r1, [r2]
+	str	r1, [r2, r3]
 1:
 
 	mov32	r9, 0xc09

arch/arm/mm/dma-mapping-nommu.c

@@ -35,7 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
 				 unsigned long attrs)
 
 {
-	void *ret = dma_alloc_from_global_coherent(size, dma_handle);
+	void *ret = dma_alloc_from_global_coherent(dev, size, dma_handle);
 
 	/*
 	 * dma_alloc_from_global_coherent() may fail because:

arch/arm/mm/proc-v7-bugs.c

@@ -65,6 +65,9 @@ static void cpu_v7_spectre_init(void)
 		break;
 
 #ifdef CONFIG_ARM_PSCI
+	case ARM_CPU_PART_BRAHMA_B53:
+		/* Requires no workaround */
+		break;
 	default:
 		/* Other ARM CPUs require no workaround */
 		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM)

arch/arm64/boot/dts/exynos/exynos5433.dtsi

@@ -18,8 +18,8 @@
 
 / {
 	compatible = "samsung,exynos5433";
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	interrupt-parent = <&gic>;
 
@@ -311,7 +311,7 @@
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		ranges;
+		ranges = <0x0 0x0 0x0 0x18000000>;
 
 		chipid@10000000 {
 			compatible = "samsung,exynos4210-chipid";

arch/arm64/boot/dts/exynos/exynos7.dtsi

@@ -12,8 +12,8 @@
 / {
 	compatible = "samsung,exynos7";
 	interrupt-parent = <&gic>;
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	aliases {
 		pinctrl0 = &pinctrl_alive;
@@ -98,7 +98,7 @@
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		ranges;
+		ranges = <0 0 0 0x18000000>;
 
 		chipid@10000000 {
 			compatible = "samsung,exynos4210-chipid";

arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi

@@ -309,9 +309,8 @@
 			regulator-name = "VDD_12V";
 			regulator-min-microvolt = <1200000>;
 			regulator-max-microvolt = <1200000>;
-			gpio = <&gpio TEGRA194_MAIN_GPIO(A, 1) GPIO_ACTIVE_LOW>;
+			gpio = <&gpio TEGRA194_MAIN_GPIO(A, 1) GPIO_ACTIVE_HIGH>;
 			regulator-boot-on;
-			enable-active-low;
 		};
 	};
 };

arch/arm64/boot/dts/nvidia/tegra210-p2597.dtsi

@@ -1612,7 +1612,7 @@
 			regulator-name = "VDD_HDMI_5V0";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
-			gpio = <&exp1 12 GPIO_ACTIVE_LOW>;
+			gpio = <&exp1 12 GPIO_ACTIVE_HIGH>;
 			enable-active-high;
 			vin-supply = <&vdd_5v0_sys>;
 		};

arch/arm64/include/asm/uaccess.h

@@ -62,8 +62,13 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
+	/*
+	 * Asynchronous I/O running in a kernel thread does not have the
+	 * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag
+	 * the user address before checking.
+	 */
 	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) &&
-	    test_thread_flag(TIF_TAGGED_ADDR))
+	    (current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR)))
 		addr = untagged_addr(addr);
 
 	__chk_user_ptr(addr);

arch/arm64/kernel/psci.c

@@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 
 static int cpu_psci_cpu_kill(unsigned int cpu)
 {
-	int err, i;
+	int err;
+	unsigned long start, end;
 
 	if (!psci_ops.affinity_info)
 		return 0;
@@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	 * while it is dying. So, try again a few times.
 	 */
 
-	for (i = 0; i < 10; i++) {
+	start = jiffies;
+	end = start + msecs_to_jiffies(100);
+	do {
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
-			pr_info("CPU%d killed.\n", cpu);
+			pr_info("CPU%d killed (polled %d ms)\n", cpu,
+				jiffies_to_msecs(jiffies - start));
 			return 0;
 		}
 
-		msleep(10);
-		pr_info("Retrying again to check for CPU kill\n");
-	}
+		usleep_range(100, 1000);
+	} while (time_before(jiffies, end));
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);

arch/arm64/kvm/sys_regs.c

@@ -2360,8 +2360,11 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG)
 		return NULL;
 
+	if (!index_to_params(id, &params))
+		return NULL;
+
 	table = get_target_table(vcpu->arch.target, true, &num);
-	r = find_reg_by_id(id, &params, table, num);
+	r = find_reg(&params, table, num);
 	if (!r)
 		r = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
 

arch/mips/include/asm/pgtable-64.h

@@ -18,10 +18,12 @@
 #include <asm/fixmap.h>
 
 #define __ARCH_USE_5LEVEL_HACK
-#if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48)
+#if CONFIG_PGTABLE_LEVELS == 2
 #include <asm-generic/pgtable-nopmd.h>
-#elif !(defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_MIPS_VA_BITS_48))
+#elif CONFIG_PGTABLE_LEVELS == 3
 #include <asm-generic/pgtable-nopud.h>
+#else
+#include <asm-generic/5level-fixup.h>
 #endif
 
 /*
@@ -216,6 +218,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 	return pgd_val(pgd);
 }
 
+#define pgd_phys(pgd)		virt_to_phys((void *)pgd_val(pgd))
+#define pgd_page(pgd)		(pfn_to_page(pgd_phys(pgd) >> PAGE_SHIFT))
+
 static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
 {
 	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);

arch/mips/ralink/Kconfig

@@ -51,6 +51,7 @@ choice
 		select MIPS_GIC
 		select COMMON_CLK
 		select CLKSRC_MIPS_GIC
+		select HAVE_PCI if PCI_MT7621
 endchoice
 
 choice

arch/powerpc/Makefile

@@ -91,11 +91,13 @@ MULTIPLEWORD	:= -mmultiple
 endif
 
 ifdef CONFIG_PPC64
+ifndef CONFIG_CC_IS_CLANG
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mcall-aixdesc)
 aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
 aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mabi=elfv2
 endif
+endif
 
 ifndef CONFIG_CC_IS_CLANG
   cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
@@ -141,6 +143,7 @@ endif
 endif
 
 CFLAGS-$(CONFIG_PPC64)	:= $(call cc-option,-mtraceback=no)
+ifndef CONFIG_CC_IS_CLANG
 ifdef CONFIG_CPU_LITTLE_ENDIAN
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
@@ -149,6 +152,7 @@ CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 endif
+endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 

arch/powerpc/boot/libfdt_env.h

@@ -6,6 +6,8 @@
 #include <string.h>
 
 #define INT_MAX			((int)(~0U>>1))
+#define UINT32_MAX		((u32)~0U)
+#define INT32_MAX		((s32)(UINT32_MAX >> 1))
 
 #include "of.h"
 

arch/powerpc/include/asm/asm-prototypes.h

@@ -152,9 +152,12 @@ void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
 /* Patch sites */
 extern s32 patch__call_flush_count_cache;
 extern s32 patch__flush_count_cache_return;
+extern s32 patch__flush_link_stack_return;
+extern s32 patch__call_kvm_flush_link_stack;
 extern s32 patch__memset_nocache, patch__memcpy_nocache;
 
 extern long flush_count_cache;
+extern long kvm_flush_link_stack;
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv);

arch/powerpc/include/asm/fixmap.h

@@ -77,7 +77,12 @@ enum fixed_addresses {
 static inline void __set_fixmap(enum fixed_addresses idx,
 				phys_addr_t phys, pgprot_t flags)
 {
-	map_kernel_page(fix_to_virt(idx), phys, flags);
+	if (__builtin_constant_p(idx))
+		BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
+	else if (WARN_ON(idx >= __end_of_fixed_addresses))
+		return;
+
+	map_kernel_page(__fix_to_virt(idx), phys, flags);
 }
 
 #endif /* !__ASSEMBLY__ */

arch/powerpc/include/asm/sections.h

@@ -5,8 +5,22 @@
 
 #include <linux/elf.h>
 #include <linux/uaccess.h>
+
+#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed
+
 #include <asm-generic/sections.h>
 
+extern bool init_mem_is_free;
+
+static inline int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+	if (!init_mem_is_free)
+		return 0;
+
+	return addr >= (unsigned long)__init_begin &&
+		addr < (unsigned long)__init_end;
+}
+
 extern char __head_end[];
 
 #ifdef __powerpc64__

arch/powerpc/include/asm/security_features.h

@@ -81,6 +81,9 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // Software required to flush count cache on context switch
 #define SEC_FTR_FLUSH_COUNT_CACHE	0x0000000000000400ull
 
+// Software required to flush link stack on context switch
+#define SEC_FTR_FLUSH_LINK_STACK	0x0000000000001000ull
+
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \

arch/powerpc/include/asm/uaccess.h

@@ -401,7 +401,7 @@ copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
 	return n;
 }
 
-extern unsigned long __clear_user(void __user *addr, unsigned long size);
+unsigned long __arch_clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
 {
@@ -409,12 +409,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 	might_fault();
 	if (likely(access_ok(addr, size))) {
 		allow_write_to_user(addr, size);
-		ret = __clear_user(addr, size);
+		ret = __arch_clear_user(addr, size);
 		prevent_write_to_user(addr, size);
 	}
 	return ret;
 }
 
+static inline unsigned long __clear_user(void __user *addr, unsigned long size)
+{
+	return clear_user(addr, size);
+}
+
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strnlen_user(const char __user *str, long n);
 

arch/powerpc/include/asm/vdso_datapage.h

@@ -82,6 +82,7 @@ struct vdso_data {
 	__s32 wtom_clock_nsec;			/* Wall to monotonic clock nsec */
 	__s64 wtom_clock_sec;			/* Wall to monotonic clock sec */
 	struct timespec stamp_xtime;		/* xtime as at tb_orig_stamp */
+	__u32 hrtimer_res;			/* hrtimer resolution */
    	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
@@ -103,6 +104,7 @@ struct vdso_data {
 	__s32 wtom_clock_nsec;
 	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
 	__u32 stamp_sec_fraction;	/* fractional seconds of stamp_xtime */
+	__u32 hrtimer_res;		/* hrtimer resolution */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 	__u32 dcache_block_size;	/* L1 d-cache block size     */
 	__u32 icache_block_size;	/* L1 i-cache block size     */

arch/powerpc/kernel/Makefile

@@ -5,8 +5,8 @@
 
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
-# Disable clang warning for using setjmp without setjmp.h header
-CFLAGS_crash.o		+= $(call cc-disable-warning, builtin-requires-header)
+# Avoid clang warnings around longjmp/setjmp declarations
+CFLAGS_crash.o += -ffreestanding
 
 ifdef CONFIG_PPC64
 CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)

arch/powerpc/kernel/asm-offsets.c

@@ -387,6 +387,7 @@ int main(void)
 	OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec);
 	OFFSET(STAMP_XTIME, vdso_data, stamp_xtime);
 	OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
+	OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
 	OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
 	OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
@@ -417,7 +418,6 @@ int main(void)
 	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
 	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
-	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 
 #ifdef CONFIG_BUG
 	DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));

arch/powerpc/kernel/eeh_driver.c

@@ -897,12 +897,12 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 
 	/* Log the event */
 	if (pe->type & EEH_PE_PHB) {
-		pr_err("EEH: PHB#%x failure detected, location: %s\n",
+		pr_err("EEH: Recovering PHB#%x, location: %s\n",
 			pe->phb->global_number, eeh_pe_loc_get(pe));
 	} else {
 		struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb);
 
-		pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+		pr_err("EEH: Recovering PHB#%x-PE#%x\n",
 		       pe->phb->global_number, pe->addr);
 		pr_err("EEH: PE location: %s, PHB location: %s\n",
 		       eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));

arch/powerpc/kernel/entry_64.S

@@ -537,6 +537,7 @@ flush_count_cache:
 	/* Save LR into r9 */
 	mflr	r9
 
+	// Flush the link stack
 	.rept 64
 	bl	.+4
 	.endr
@@ -546,6 +547,11 @@ flush_count_cache:
 	.balign 32
 	/* Restore LR */
 1:	mtlr	r9
+
+	// If we're just flushing the link stack, return here
+3:	nop
+	patch_site 3b patch__flush_link_stack_return
+
 	li	r9,0x7fff
 	mtctr	r9
 

arch/powerpc/kernel/irq.c

@@ -619,8 +619,6 @@ void __do_irq(struct pt_regs *regs)
 
 	trace_irq_entry(regs);
 
-	check_stack_overflow();
-
 	/*
 	 * Query the platform PIC for the interrupt & ack it.
 	 *
@@ -652,6 +650,8 @@ void do_IRQ(struct pt_regs *regs)
 	irqsp = hardirq_ctx[raw_smp_processor_id()];
 	sirqsp = softirq_ctx[raw_smp_processor_id()];
 
+	check_stack_overflow();
+
 	/* Already there ? */
 	if (unlikely(cursp == irqsp || cursp == sirqsp)) {
 		__do_irq(regs);

arch/powerpc/kernel/misc_64.S

@@ -82,7 +82,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
 	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of cache block size */
-	srw.	r8,r8,r9		/* compute line count */
+	srd.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	mtctr	r8
 1:	dcbst	0,r6
@@ -98,7 +98,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5
 	lwz	r9,ICACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of Icache block size */
-	srw.	r8,r8,r9		/* compute line count */
+	srd.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	mtctr	r8
 2:	icbi	0,r6

arch/powerpc/kernel/security.c

@@ -24,6 +24,7 @@ enum count_cache_flush_type {
 	COUNT_CACHE_FLUSH_HW	= 0x4,
 };
 static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+static bool link_stack_flush_enabled;
 
 bool barrier_nospec_enabled;
 static bool no_nospec;
@@ -141,32 +142,33 @@ ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, cha
 
 	thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV);
 
-	if (rfi_flush || thread_priv) {
+	if (rfi_flush) {
 		struct seq_buf s;
 		seq_buf_init(&s, buf, PAGE_SIZE - 1);
 
-		seq_buf_printf(&s, "Mitigation: ");
-
-		if (rfi_flush)
-			seq_buf_printf(&s, "RFI Flush");
-
-		if (rfi_flush && thread_priv)
-			seq_buf_printf(&s, ", ");
-
+		seq_buf_printf(&s, "Mitigation: RFI Flush");
 		if (thread_priv)
-			seq_buf_printf(&s, "L1D private per thread");
+			seq_buf_printf(&s, ", L1D private per thread");
 
 		seq_buf_printf(&s, "\n");
 
 		return s.len;
 	}
 
+	if (thread_priv)
+		return sprintf(buf, "Vulnerable: L1D private per thread\n");
+
 	if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) &&
 	    !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR))
 		return sprintf(buf, "Not affected\n");
 
 	return sprintf(buf, "Vulnerable\n");
 }
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_meltdown(dev, attr, buf);
+}
 #endif
 
 ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
@@ -212,11 +214,19 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 
 		if (ccd)
 			seq_buf_printf(&s, "Indirect branch cache disabled");
+
+		if (link_stack_flush_enabled)
+			seq_buf_printf(&s, ", Software link stack flush");
+
 	} else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
 		seq_buf_printf(&s, "Mitigation: Software count cache flush");
 
 		if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
 			seq_buf_printf(&s, " (hardware accelerated)");
+
+		if (link_stack_flush_enabled)
+			seq_buf_printf(&s, ", Software link stack flush");
+
 	} else if (btb_flush_enabled) {
 		seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
 	} else {
@@ -377,18 +387,49 @@ static __init int stf_barrier_debugfs_init(void)
 device_initcall(stf_barrier_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
 
+static void no_count_cache_flush(void)
+{
+	count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+	pr_info("count-cache-flush: software flush disabled.\n");
+}
+
 static void toggle_count_cache_flush(bool enable)
 {
-	if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+	if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) &&
+	    !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK))
+		enable = false;
+
+	if (!enable) {
 		patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP);
-		count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
-		pr_info("count-cache-flush: software flush disabled.\n");
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP);
+#endif
+		pr_info("link-stack-flush: software flush disabled.\n");
+		link_stack_flush_enabled = false;
+		no_count_cache_flush();
 		return;
 	}
 
+	// This enables the branch from _switch to flush_count_cache
 	patch_branch_site(&patch__call_flush_count_cache,
 			  (u64)&flush_count_cache, BRANCH_SET_LINK);
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	// This enables the branch from guest_exit_cont to kvm_flush_link_stack
+	patch_branch_site(&patch__call_kvm_flush_link_stack,
+			  (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+#endif
+
+	pr_info("link-stack-flush: software flush enabled.\n");
+	link_stack_flush_enabled = true;
+
+	// If we just need to flush the link stack, patch an early return
+	if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+		patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR);
+		no_count_cache_flush();
+		return;
+	}
+
 	if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
 		count_cache_flush_type = COUNT_CACHE_FLUSH_SW;
 		pr_info("count-cache-flush: full software flush sequence enabled.\n");
@@ -407,11 +448,20 @@ void setup_count_cache_flush(void)
 	if (no_spectrev2 || cpu_mitigations_off()) {
 		if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) ||
 		    security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED))
-			pr_warn("Spectre v2 mitigations not under software control, can't disable\n");
+			pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n");
 
 		enable = false;
 	}
 
+	/*
+	 * There's no firmware feature flag/hypervisor bit to tell us we need to
+	 * flush the link stack on context switch. So we set it here if we see
+	 * either of the Spectre v2 mitigations that aim to protect userspace.
+	 */
+	if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) ||
+	    security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE))
+		security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
+
 	toggle_count_cache_flush(enable);
 }
 

arch/powerpc/kernel/time.c

@@ -232,7 +232,7 @@ static u64 scan_dispatch_log(u64 stop_tb)
  * Accumulate stolen time by scanning the dispatch trace log.
  * Called on entry from user mode.
  */
-void accumulate_stolen_time(void)
+void notrace accumulate_stolen_time(void)
 {
 	u64 sst, ust;
 	unsigned long save_irq_soft_mask = irq_soft_mask_return();
@@ -959,6 +959,7 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
 	vdso_data->stamp_xtime = xt;
 	vdso_data->stamp_sec_fraction = frac_sec;
+	vdso_data->hrtimer_res = hrtimer_resolution;
 	smp_wmb();
 	++(vdso_data->tb_update_count);
 }

arch/powerpc/kernel/traps.c

@@ -250,15 +250,22 @@ static void oops_end(unsigned long flags, struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(oops_end);
 
+static char *get_mmu_str(void)
+{
+	if (early_radix_enabled())
+		return " MMU=Radix";
+	if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return " MMU=Hash";
+	return "";
+}
+
 static int __die(const char *str, struct pt_regs *regs, long err)
 {
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
-	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n",
+	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
 	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
-	       PAGE_SIZE / 1024,
-	       early_radix_enabled() ? " MMU=Radix" : "",
-	       early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "",
+	       PAGE_SIZE / 1024, get_mmu_str(),
 	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
 	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
 	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",

arch/powerpc/kernel/vdso32/gettimeofday.S

@@ -156,12 +156,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
 	bne	cr0,99f
 
+	mflr	r12
+  .cfi_register lr,r12
+	bl	__get_datapage@local	/* get data page */
+	lwz	r5, CLOCK_HRTIMER_RES(r3)
+	mtlr	r12
 	li	r3,0
 	cmpli	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
-	lis	r5,CLOCK_REALTIME_RES@h
-	ori	r5,r5,CLOCK_REALTIME_RES@l
 	stw	r3,TSPC32_TV_SEC(r4)
 	stw	r5,TSPC32_TV_NSEC(r4)
 	blr

arch/powerpc/kernel/vdso64/cacheflush.S

@@ -35,7 +35,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
 	lwz	r9,CFG_DCACHE_LOGBLOCKSZ(r10)
-	srw.	r8,r8,r9		/* compute line count */
+	srd.	r8,r8,r9		/* compute line count */
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
 	mtctr	r8
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5
 	lwz	r9,CFG_ICACHE_LOGBLOCKSZ(r10)
-	srw.	r8,r8,r9		/* compute line count */
+	srd.	r8,r8,r9		/* compute line count */
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
 	mtctr	r8

arch/powerpc/kernel/vdso64/gettimeofday.S

@@ -186,12 +186,15 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
 	bne	cr0,99f
 
+	mflr	r12
+  .cfi_register lr,r12
+	bl	V_LOCAL_FUNC(__get_datapage)
+	lwz	r5, CLOCK_HRTIMER_RES(r3)
+	mtlr	r12
 	li	r3,0
 	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
-	lis	r5,CLOCK_REALTIME_RES@h
-	ori	r5,r5,CLOCK_REALTIME_RES@l
 	std	r3,TSPC64_TV_SEC(r4)
 	std	r5,TSPC64_TV_NSEC(r4)
 	blr

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -11,6 +11,7 @@
  */
 
 #include <asm/ppc_asm.h>
+#include <asm/code-patching-asm.h>
 #include <asm/kvm_asm.h>
 #include <asm/reg.h>
 #include <asm/mmu.h>
@@ -1116,7 +1117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r7, VCPU_GPR(R7)(r4)
 	bne	ret_to_ultra
 
-	lwz	r0, VCPU_CR(r4)
+	ld	r0, VCPU_CR(r4)
 	mtcr	r0
 
 	ld	r0, VCPU_GPR(R0)(r4)
@@ -1136,7 +1137,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
  *   R3 = UV_RETURN
  */
 ret_to_ultra:
-	lwz	r0, VCPU_CR(r4)
+	ld	r0, VCPU_CR(r4)
 	mtcr	r0
 
 	ld	r0, VCPU_GPR(R3)(r4)
@@ -1487,6 +1488,13 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 1:
 #endif /* CONFIG_KVM_XICS */
 
+	/*
+	 * Possibly flush the link stack here, before we do a blr in
+	 * guest_exit_short_path.
+	 */
+1:	nop
+	patch_site 1b patch__call_kvm_flush_link_stack
+
 	/* If we came in through the P9 short path, go back out to C now */
 	lwz	r0, STACK_SLOT_SHORT_PATH(r1)
 	cmpwi	r0, 0
@@ -1963,6 +1971,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	mtlr	r0
 	blr
 
+.balign 32
+.global kvm_flush_link_stack
+kvm_flush_link_stack:
+	/* Save LR into r0 */
+	mflr	r0
+
+	/* Flush the link stack. On Power8 it's up to 32 entries in size. */
+	.rept 32
+	bl	.+4
+	.endr
+
+	/* And on Power9 it's up to 64. */
+BEGIN_FTR_SECTION
+	.rept 32
+	bl	.+4
+	.endr
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+	/* Restore LR */
+	mtlr	r0
+	blr
+
 kvmppc_guest_external:
 	/* External interrupt, first check for host_ipi. If this is
 	 * set, we know the host wants us out so let's do it now

arch/powerpc/kvm/book3s_xive.c

@@ -2005,6 +2005,10 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 
 	pr_devel("Creating xive for partition\n");
 
+	/* Already there ? */
+	if (kvm->arch.xive)
+		return -EEXIST;
+
 	xive = kvmppc_xive_get_device(kvm, type);
 	if (!xive)
 		return -ENOMEM;
@@ -2014,12 +2018,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	xive->kvm = kvm;
 	mutex_init(&xive->lock);
 
-	/* Already there ? */
-	if (kvm->arch.xive)
-		ret = -EEXIST;
-	else
-		kvm->arch.xive = xive;
-
 	/* We use the default queue size set by the host */
 	xive->q_order = xive_native_default_eq_shift();
 	if (xive->q_order < PAGE_SHIFT)
@@ -2039,6 +2037,7 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	if (ret)
 		return ret;
 
+	kvm->arch.xive = xive;
 	return 0;
 }
 

arch/powerpc/kvm/book3s_xive_native.c

@@ -50,6 +50,24 @@ static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
 	}
 }
 
+static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q,
+					      u8 prio, __be32 *qpage,
+					      u32 order, bool can_escalate)
+{
+	int rc;
+	__be32 *qpage_prev = q->qpage;
+
+	rc = xive_native_configure_queue(vp_id, q, prio, qpage, order,
+					 can_escalate);
+	if (rc)
+		return rc;
+
+	if (qpage_prev)
+		put_page(virt_to_page(qpage_prev));
+
+	return rc;
+}
+
 void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
@@ -582,19 +600,14 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 		q->guest_qaddr  = 0;
 		q->guest_qshift = 0;
 
-		rc = xive_native_configure_queue(xc->vp_id, q, priority,
-						 NULL, 0, true);
+		rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
+							NULL, 0, true);
 		if (rc) {
 			pr_err("Failed to reset queue %d for VCPU %d: %d\n",
 			       priority, xc->server_num, rc);
 			return rc;
 		}
 
-		if (q->qpage) {
-			put_page(virt_to_page(q->qpage));
-			q->qpage = NULL;
-		}
-
 		return 0;
 	}
 
@@ -624,12 +637,6 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
-	page = gfn_to_page(kvm, gfn);
-	if (is_error_page(page)) {
-		srcu_read_unlock(&kvm->srcu, srcu_idx);
-		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
-		return -EINVAL;
-	}
 
 	page_size = kvm_host_page_size(kvm, gfn);
 	if (1ull << kvm_eq.qshift > page_size) {
@@ -638,6 +645,13 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 		return -EINVAL;
 	}
 
+	page = gfn_to_page(kvm, gfn);
+	if (is_error_page(page)) {
+		srcu_read_unlock(&kvm->srcu, srcu_idx);
+		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
+		return -EINVAL;
+	}
+
 	qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK);
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 
@@ -653,8 +667,8 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	  * OPAL level because the use of END ESBs is not supported by
 	  * Linux.
 	  */
-	rc = xive_native_configure_queue(xc->vp_id, q, priority,
-					 (__be32 *) qaddr, kvm_eq.qshift, true);
+	rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
+					(__be32 *) qaddr, kvm_eq.qshift, true);
 	if (rc) {
 		pr_err("Failed to configure queue %d for VCPU %d: %d\n",
 		       priority, xc->server_num, rc);
@@ -1081,7 +1095,6 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	dev->private = xive;
 	xive->dev = dev;
 	xive->kvm = kvm;
-	kvm->arch.xive = xive;
 	mutex_init(&xive->mapping_lock);
 	mutex_init(&xive->lock);
 
@@ -1102,6 +1115,7 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	if (ret)
 		return ret;
 
+	kvm->arch.xive = xive;
 	return 0;
 }
 

arch/powerpc/lib/string_32.S

@@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
-_GLOBAL(__clear_user)
+_GLOBAL(__arch_clear_user)
 /*
  * Use dcbz on the complete cache lines in the destination
  * to set them to zero.  This requires that the destination
@@ -87,4 +87,4 @@ _GLOBAL(__clear_user)
 	EX_TABLE(8b, 91b)
 	EX_TABLE(9b, 91b)
 
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)

arch/powerpc/lib/string_64.S

@@ -17,7 +17,7 @@ PPC64_CACHES:
 	.section	".text"
 
 /**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
@@ -58,7 +58,7 @@ err3;	stb	r0,0(r3)
 	mr	r3,r4
 	blr
 
-_GLOBAL_TOC(__clear_user)
+_GLOBAL_TOC(__arch_clear_user)
 	cmpdi	r4,32
 	neg	r6,r3
 	li	r0,0
@@ -181,4 +181,4 @@ err1;	dcbz	0,r3
 	cmpdi	r4,32
 	blt	.Lshort_clear
 	b	.Lmedium_clear
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)

arch/powerpc/mm/book3s64/hash_utils.c

@@ -294,10 +294,18 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
 					       HPTE_V_BOLTED, psize, psize,
 					       ssize);
-
+		if (ret == -1) {
+			/* Try to remove a non bolted entry */
+			ret = mmu_hash_ops.hpte_remove(hpteg);
+			if (ret != -1)
+				ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
+							       HPTE_V_BOLTED, psize, psize,
+							       ssize);
+		}
 		if (ret < 0)
 			break;
 
+		cond_resched();
 #ifdef CONFIG_DEBUG_PAGEALLOC
 		if (debug_pagealloc_enabled() &&
 			(paddr >> PAGE_SHIFT) < linear_map_hash_count)

arch/powerpc/platforms/powernv/opal-imc.c

@@ -285,7 +285,14 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 			domain = IMC_DOMAIN_THREAD;
 			break;
 		case IMC_TYPE_TRACE:
-			domain = IMC_DOMAIN_TRACE;
+			/*
+			 * FIXME. Using trace_imc events to monitor application
+			 * or KVM thread performance can cause a checkstop
+			 * (system crash).
+			 * Disable it for now.
+			 */
+			pr_info_once("IMC: disabling trace_imc PMU\n");
+			domain = -1;
 			break;
 		default:
 			pr_warn("IMC Unknown Device type \n");

arch/powerpc/platforms/pseries/cmm.c

@@ -411,6 +411,10 @@ static struct bus_type cmm_subsys = {
 	.dev_name = "cmm",
 };
 
+static void cmm_release_device(struct device *dev)
+{
+}
+
 /**
  * cmm_sysfs_register - Register with sysfs
  *
@@ -426,6 +430,7 @@ static int cmm_sysfs_register(struct device *dev)
 
 	dev->id = 0;
 	dev->bus = &cmm_subsys;
+	dev->release = cmm_release_device;
 
 	if ((rc = device_register(dev)))
 		goto subsys_unregister;

arch/powerpc/platforms/pseries/papr_scm.c

@@ -152,7 +152,7 @@ static int papr_scm_meta_get(struct papr_scm_priv *p,
 	int len, read;
 	int64_t ret;
 
-	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
 		return -EINVAL;
 
 	for (len = hdr->in_length; len; len -= read) {
@@ -206,7 +206,7 @@ static int papr_scm_meta_set(struct papr_scm_priv *p,
 	__be64 data_be;
 	int64_t ret;
 
-	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
 		return -EINVAL;
 
 	for (len = hdr->in_length; len; len -= wrote) {

arch/powerpc/sysdev/xive/common.c

@@ -1035,6 +1035,15 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
 	xd->target = XIVE_INVALID_TARGET;
 	irq_set_handler_data(virq, xd);
 
+	/*
+	 * Turn OFF by default the interrupt being mapped. A side
+	 * effect of this check is the mapping the ESB page of the
+	 * interrupt in the Linux address space. This prevents page
+	 * fault issues in the crash handler which masks all
+	 * interrupts.
+	 */
+	xive_esb_read(xd, XIVE_ESB_SET_PQ_01);
+
 	return 0;
 }
 

arch/powerpc/sysdev/xive/spapr.c

@@ -392,20 +392,28 @@ static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
 	data->esb_shift = esb_shift;
 	data->trig_page = trig_page;
 
+	data->hw_irq = hw_irq;
+
 	/*
 	 * No chip-id for the sPAPR backend. This has an impact how we
 	 * pick a target. See xive_pick_irq_target().
 	 */
 	data->src_chip = XIVE_INVALID_CHIP_ID;
 
+	/*
+	 * When the H_INT_ESB flag is set, the H_INT_ESB hcall should
+	 * be used for interrupt management. Skip the remapping of the
+	 * ESB pages which are not available.
+	 */
+	if (data->flags & XIVE_IRQ_FLAG_H_INT_ESB)
+		return 0;
+
 	data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift);
 	if (!data->eoi_mmio) {
 		pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq);
 		return -ENOMEM;
 	}
 
-	data->hw_irq = hw_irq;
-
 	/* Full function page supports trigger */
 	if (flags & XIVE_SRC_TRIGGER) {
 		data->trig_mmio = data->eoi_mmio;

arch/powerpc/tools/relocs_check.sh

@@ -20,7 +20,7 @@ objdump="$1"
 vmlinux="$2"
 
 bad_relocs=$(
-"$objdump" -R "$vmlinux" |
+$objdump -R "$vmlinux" |
 	# Only look at relocation lines.
 	grep -E '\<R_' |
 	# These relocations are okay

arch/powerpc/tools/unrel_branch_check.sh

@@ -18,14 +18,14 @@ vmlinux="$2"
 #__end_interrupts should be located within the first 64K
 
 end_intr=0x$(
-"$objdump" -R "$vmlinux" -d --start-address=0xc000000000000000		\
+$objdump -R "$vmlinux" -d --start-address=0xc000000000000000           \
 		 --stop-address=0xc000000000010000 |
 grep '\<__end_interrupts>:' |
 awk '{print $1}'
 )
 
 BRANCHES=$(
-"$objdump" -R "$vmlinux" -D --start-address=0xc000000000000000		\
+$objdump -R "$vmlinux" -D --start-address=0xc000000000000000           \
 		--stop-address=${end_intr} |
 grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" |
 grep -v '\<__start_initialization_multiplatform>' |

arch/powerpc/xmon/Makefile

@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for xmon
 
-# Disable clang warning for using setjmp without setjmp.h header
-subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header)
+# Avoid clang warnings around longjmp/setjmp declarations
+subdir-ccflags-y := -ffreestanding
 
 GCOV_PROFILE := n
 KCOV_INSTRUMENT := n

arch/s390/boot/startup.c

@@ -170,6 +170,11 @@ void startup_kernel(void)
 		handle_relocs(__kaslr_offset);
 
 	if (__kaslr_offset) {
+		/*
+		 * Save KASLR offset for early dumps, before vmcore_info is set.
+		 * Mark as uneven to distinguish from real vmcore_info pointer.
+		 */
+		S390_lowcore.vmcore_info = __kaslr_offset | 0x1UL;
 		/* Clear non-relocated kernel */
 		if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED))
 			memset(img, 0, vmlinux.image_size);

arch/s390/crypto/sha_common.c

@@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	struct s390_sha_ctx *ctx = shash_desc_ctx(desc);
 	unsigned int bsize = crypto_shash_blocksize(desc->tfm);
 	u64 bits;
-	unsigned int n, mbl_offset;
+	unsigned int n;
+	int mbl_offset;
 
 	n = ctx->count % bsize;
 	bits = ctx->count * 8;
-	mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32);
+	mbl_offset = s390_crypto_shash_parmsize(ctx->func);
 	if (mbl_offset < 0)
 		return -EINVAL;
 
+	mbl_offset = mbl_offset / sizeof(u32);
+
 	/* set total msg bit length (mbl) in CPACF parmblock */
 	switch (ctx->func) {
 	case CPACF_KLMD_SHA_1:

arch/s390/include/asm/pgalloc.h

@@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION2_ENTRY_EMPTY);
 	return (p4d_t *) table;
 }
-#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d)
+
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		crst_table_free(mm, (unsigned long *) p4d);
+}
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
@@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 		crst_table_init(table, _REGION3_ENTRY_EMPTY);
 	return (pud_t *) table;
 }
-#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (!mm_pud_folded(mm))
+		crst_table_free(mm, (unsigned long *) pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
@@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	crst_table_free(mm, (unsigned long *) pmd);
 }

arch/s390/include/asm/pgtable.h

@@ -1173,8 +1173,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t entry)
 {
-	if (!MACHINE_HAS_NX)
-		pte_val(entry) &= ~_PAGE_NOEXEC;
 	if (pte_present(entry))
 		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm))
@@ -1191,6 +1189,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pte_t __pte;
 	pte_val(__pte) = physpage + pgprot_val(pgprot);
+	if (!MACHINE_HAS_NX)
+		pte_val(__pte) &= ~_PAGE_NOEXEC;
 	return pte_mkyoung(__pte);
 }
 

arch/s390/include/asm/timex.h

@@ -10,8 +10,9 @@
 #ifndef _ASM_S390_TIMEX_H
 #define _ASM_S390_TIMEX_H
 
-#include <asm/lowcore.h>
+#include <linux/preempt.h>
 #include <linux/time64.h>
+#include <asm/lowcore.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -186,15 +187,18 @@ extern unsigned char tod_clock_base[16] __aligned(8);
 /**
  * get_clock_monotonic - returns current time in clock rate units
  *
- * The caller must ensure that preemption is disabled.
  * The clock and tod_clock_base get changed via stop_machine.
- * Therefore preemption must be disabled when calling this
- * function, otherwise the returned value is not guaranteed to
- * be monotonic.
+ * Therefore preemption must be disabled, otherwise the returned
+ * value is not guaranteed to be monotonic.
  */
 static inline unsigned long long get_tod_clock_monotonic(void)
 {
-	return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	unsigned long long tod;
+
+	preempt_disable_notrace();
+	tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1];
+	preempt_enable_notrace();
+	return tod;
 }
 
 /**

arch/s390/kernel/dis.c

@@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
 				ptr += sprintf(ptr, "%%v%i", value);
-			else if (operand->flags & OPERAND_PCREL)
-				ptr += sprintf(ptr, "%lx", (signed int) value
-								      + addr);
-			else if (operand->flags & OPERAND_SIGNED)
+			else if (operand->flags & OPERAND_PCREL) {
+				void *pcrel = (void *)((int)value + addr);
+
+				ptr += sprintf(ptr, "%px", pcrel);
+			} else if (operand->flags & OPERAND_SIGNED)
 				ptr += sprintf(ptr, "%i", value);
 			else
 				ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs)
 		else
 			*ptr++ = ' ';
 		addr = regs->psw.addr + start - 32;
-		ptr += sprintf(ptr, "%016lx: ", addr);
+		ptr += sprintf(ptr, "%px: ", (void *)addr);
 		if (start + opsize >= end)
 			break;
 		for (i = 0; i < opsize; i++)
@@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len)
 		opsize = insn_length(*code);
 		if (opsize > len)
 			break;
-		ptr += sprintf(ptr, "%p: ", code);
+		ptr += sprintf(ptr, "%px: ", code);
 		for (i = 0; i < opsize; i++)
 			ptr += sprintf(ptr, "%02x", code[i]);
 		*ptr++ = '\t';

arch/s390/kernel/machine_kexec.c

@@ -164,7 +164,9 @@ static bool kdump_csum_valid(struct kimage *image)
 #ifdef CONFIG_CRASH_DUMP
 	int rc;
 
+	preempt_disable();
 	rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image);
+	preempt_enable();
 	return rc == 0;
 #else
 	return false;
@@ -254,10 +256,10 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 	vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
 	vmcoreinfo_append_str("EDMA=%lx\n", __edma);
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)

arch/s390/kernel/perf_cpum_cf.c

@@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = {
 	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
 };
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	int err = 0;
 	u64 ev;
 
-	switch (attr->type) {
+	switch (type) {
 	case PERF_TYPE_RAW:
 		/* Raw events are used to access counters directly,
 		 * hence do not permit excludes */
@@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static int cpumf_pmu_event_init(struct perf_event *event)
 {
+	unsigned int type = event->attr.type;
 	int err;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-	case PERF_TYPE_RAW:
-		err = __hw_perf_event_init(event);
-		break;
-	default:
+	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+		err = __hw_perf_event_init(event, type);
+	else if (event->pmu->type == type)
+		/* Registered as unknown PMU */
+		err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+	else
 		return -ENOENT;
-	}
 
 	if (unlikely(err) && event->destroy)
 		event->destroy(event);
@@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void)
 		return -ENODEV;
 
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
-	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
 	if (rc)
 		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
 	return rc;

arch/s390/kernel/perf_cpum_cf_diag.c

@@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event)
 	int err = -ENOENT;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d config %#llx "
+			    "%s event %p cpu %d config %#llx type:%u "
 			    "sample_type %#llx cf_diag_events %d\n", __func__,
-			    event, event->cpu, attr->config, attr->sample_type,
-			    atomic_read(&cf_diag_events));
+			    event, event->cpu, attr->config, event->pmu->type,
+			    attr->sample_type, atomic_read(&cf_diag_events));
 
 	if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
-	    event->attr.type != PERF_TYPE_RAW)
+	    event->attr.type != event->pmu->type)
 		goto out;
 
 	/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@ static int __init cf_diag_init(void)
 	}
 	debug_register_view(cf_diag_dbg, &debug_sprintf_view);
 
-	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+	rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
 	if (rc) {
 		debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
 		debug_unregister(cf_diag_dbg);

arch/s390/kernel/perf_cpum_sf.c

@@ -193,7 +193,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 				   unsigned long num_sdb, gfp_t gfp_flags)
 {
 	int i, rc;
-	unsigned long *new, *tail;
+	unsigned long *new, *tail, *tail_prev = NULL;
 
 	if (!sfb->sdbt || !sfb->tail)
 		return -EINVAL;
@@ -232,6 +232,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 			sfb->num_sdbt++;
 			/* Link current page to tail of chain */
 			*tail = (unsigned long)(void *) new + 1;
+			tail_prev = tail;
 			tail = new;
 		}
 
@@ -241,10 +242,22 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb,
 		 * issue, a new realloc call (if required) might succeed.
 		 */
 		rc = alloc_sample_data_block(tail, gfp_flags);
-		if (rc)
+		if (rc) {
+			/* Undo last SDBT. An SDBT with no SDB at its first
+			 * entry but with an SDBT entry instead can not be
+			 * handled by the interrupt handler code.
+			 * Avoid this situation.
+			 */
+			if (tail_prev) {
+				sfb->num_sdbt--;
+				free_page((unsigned long) new);
+				tail = tail_prev;
+			}
 			break;
+		}
 		sfb->num_sdb++;
 		tail++;
+		tail_prev = new = NULL;	/* Allocated at least one SBD */
 	}
 
 	/* Link sampling buffer to its origin */

arch/s390/kernel/perf_event.c

@@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
 	struct unwind_state state;
+	unsigned long addr;
 
-	unwind_for_each_frame(&state, current, regs, 0)
-		perf_callchain_store(entry, state.ip);
+	unwind_for_each_frame(&state, current, regs, 0) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
 }
 
 /* Perf definitions for PMU event attributes in sysfs */

arch/s390/kernel/smp.c

@@ -262,10 +262,13 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	lc->spinlock_index = 0;
 	lc->percpu_offset = __per_cpu_offset[cpu];
 	lc->kernel_asce = S390_lowcore.kernel_asce;
+	lc->user_asce = S390_lowcore.kernel_asce;
 	lc->machine_flags = S390_lowcore.machine_flags;
 	lc->user_timer = lc->system_timer =
 		lc->steal_timer = lc->avg_steal_timer = 0;
 	__ctl_store(lc->cregs_save_area, 0, 15);
+	lc->cregs_save_area[1] = lc->kernel_asce;
+	lc->cregs_save_area[7] = lc->vdso_asce;
 	save_access_regs((unsigned int *) lc->access_regs_save_area);
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
 	       sizeof(lc->stfle_fac_list));
@@ -816,6 +819,8 @@ static void smp_init_secondary(void)
 
 	S390_lowcore.last_update_clock = get_tod_clock();
 	restore_access_regs(S390_lowcore.access_regs_save_area);
+	set_cpu_flag(CIF_ASCE_PRIMARY);
+	set_cpu_flag(CIF_ASCE_SECONDARY);
 	cpu_init();
 	preempt_disable();
 	init_cpu_timer();

arch/s390/kernel/unwind_bc.c

@@ -60,6 +60,11 @@ bool unwind_next_frame(struct unwind_state *state)
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
 		regs = NULL;
+		if (!__kernel_text_address(ip)) {
+			/* skip bogus %r14 */
+			state->regs = NULL;
+			return unwind_next_frame(state);
+		}
 	} else {
 		sf = (struct stack_frame *) state->sp;
 		sp = READ_ONCE_NOCHECK(sf->back_chain);

arch/s390/mm/maccess.c

@@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size)
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 }
 
-static int __memcpy_real(void *dest, void *src, size_t count)
+static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
@@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count)
 	return rc;
 }
 
-static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
-				  unsigned long count)
+static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest,
+							unsigned long src,
+							unsigned long count)
 {
 	int irqs_disabled, rc;
 	unsigned long flags;
 
 	if (!count)
 		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
+	flags = arch_local_irq_save();
 	irqs_disabled = arch_irqs_disabled_flags(flags);
 	if (!irqs_disabled)
 		trace_hardirqs_off();
+	__arch_local_irq_stnsm(0xf8); // disable DAT
 	rc = __memcpy_real((void *) dest, (void *) src, (size_t) count);
+	if (flags & PSW_MASK_DAT)
+		__arch_local_irq_stosm(0x04); // enable DAT
 	if (!irqs_disabled)
 		trace_hardirqs_on();
 	__arch_local_irq_ssm(flags);
@@ -115,9 +119,15 @@ static unsigned long _memcpy_real(unsigned long dest, unsigned long src,
  */
 int memcpy_real(void *dest, void *src, size_t count)
 {
-	if (S390_lowcore.nodat_stack != 0)
-		return CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack,
-				     3, dest, src, count);
+	int rc;
+
+	if (S390_lowcore.nodat_stack != 0) {
+		preempt_disable();
+		rc = CALL_ON_STACK(_memcpy_real, S390_lowcore.nodat_stack, 3,
+				   dest, src, count);
+		preempt_enable();
+		return rc;
+	}
 	/*
 	 * This is a really early memcpy_real call, the stacks are
 	 * not set up yet. Just call _memcpy_real on the early boot

arch/s390/net/bpf_jit_comp.c

@@ -23,6 +23,7 @@
 #include <linux/filter.h>
 #include <linux/init.h>
 #include <linux/bpf.h>
+#include <linux/mm.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
 #include <asm/facility.h>
@@ -1369,7 +1370,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	memset(&jit, 0, sizeof(jit));
-	jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
+	jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
 	if (jit.addrs == NULL) {
 		fp = orig_fp;
 		goto out;
@@ -1422,7 +1423,7 @@ skip_init_ctx:
 	if (!fp->is_func || extra_pass) {
 		bpf_prog_fill_jited_linfo(fp, jit.addrs + 1);
 free_addrs:
-		kfree(jit.addrs);
+		kvfree(jit.addrs);
 		kfree(jit_data);
 		fp->aux->jit_data = NULL;
 	}

arch/sh/include/cpu-sh4/cpu/sh7734.h

@@ -134,7 +134,7 @@ enum {
 	GPIO_FN_EX_WAIT1, GPIO_FN_SD1_DAT0_A, GPIO_FN_DREQ2, GPIO_FN_CAN1_TX_C,
 		GPIO_FN_ET0_LINK_C, GPIO_FN_ET0_ETXD5_A,
 	GPIO_FN_EX_WAIT0, GPIO_FN_TCLK1_B,
-	GPIO_FN_RD_WR, GPIO_FN_TCLK0,
+	GPIO_FN_RD_WR, GPIO_FN_TCLK0, GPIO_FN_CAN_CLK_B, GPIO_FN_ET0_ETXD4,
 	GPIO_FN_EX_CS5, GPIO_FN_SD1_CMD_A, GPIO_FN_ATADIR, GPIO_FN_QSSL_B,
 		GPIO_FN_ET0_ETXD3_A,
 	GPIO_FN_EX_CS4, GPIO_FN_SD1_WP_A, GPIO_FN_ATAWR, GPIO_FN_QMI_QIO1_B,

arch/sparc/include/asm/io_64.h

@@ -407,6 +407,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 }
 
 #define ioremap_nocache(X,Y)		ioremap((X),(Y))
+#define ioremap_uc(X,Y)			ioremap((X),(Y))
 #define ioremap_wc(X,Y)			ioremap((X),(Y))
 #define ioremap_wt(X,Y)			ioremap((X),(Y))
 

arch/um/drivers/virtio_uml.c

@@ -83,7 +83,7 @@ static int full_sendmsg_fds(int fd, const void *buf, unsigned int len,
 	return 0;
 }
 
-static int full_read(int fd, void *buf, int len)
+static int full_read(int fd, void *buf, int len, bool abortable)
 {
 	int rc;
 
@@ -93,7 +93,7 @@ static int full_read(int fd, void *buf, int len)
 			buf += rc;
 			len -= rc;
 		}
-	} while (len && (rc > 0 || rc == -EINTR));
+	} while (len && (rc > 0 || rc == -EINTR || (!abortable && rc == -EAGAIN)));
 
 	if (rc < 0)
 		return rc;
@@ -104,7 +104,7 @@ static int full_read(int fd, void *buf, int len)
 
 static int vhost_user_recv_header(int fd, struct vhost_user_msg *msg)
 {
-	return full_read(fd, msg, sizeof(msg->header));
+	return full_read(fd, msg, sizeof(msg->header), true);
 }
 
 static int vhost_user_recv(int fd, struct vhost_user_msg *msg,
@@ -118,7 +118,7 @@ static int vhost_user_recv(int fd, struct vhost_user_msg *msg,
 	size = msg->header.size;
 	if (size > max_payload_size)
 		return -EPROTO;
-	return full_read(fd, &msg->payload, size);
+	return full_read(fd, &msg->payload, size, false);
 }
 
 static int vhost_user_recv_resp(struct virtio_uml_device *vu_dev,

arch/x86/entry/entry_32.S

@@ -172,7 +172,7 @@
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
 	.if \no_user_check == 0
 	/* coming from usermode? */
-	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
+	testl	$USER_SEGMENT_RPL_MASK, PT_CS(%esp)
 	jz	.Lend_\@
 	.endif
 	/* On user-cr3? */
@@ -205,64 +205,76 @@
 #define CS_FROM_ENTRY_STACK	(1 << 31)
 #define CS_FROM_USER_CR3	(1 << 30)
 #define CS_FROM_KERNEL		(1 << 29)
+#define CS_FROM_ESPFIX		(1 << 28)
 
 .macro FIXUP_FRAME
 	/*
 	 * The high bits of the CS dword (__csh) are used for CS_FROM_*.
 	 * Clear them in case hardware didn't do this for us.
 	 */
-	andl	$0x0000ffff, 3*4(%esp)
+	andl	$0x0000ffff, 4*4(%esp)
 
 #ifdef CONFIG_VM86
-	testl	$X86_EFLAGS_VM, 4*4(%esp)
+	testl	$X86_EFLAGS_VM, 5*4(%esp)
 	jnz	.Lfrom_usermode_no_fixup_\@
 #endif
-	testl	$SEGMENT_RPL_MASK, 3*4(%esp)
+	testl	$USER_SEGMENT_RPL_MASK, 4*4(%esp)
 	jnz	.Lfrom_usermode_no_fixup_\@
 
-	orl	$CS_FROM_KERNEL, 3*4(%esp)
+	orl	$CS_FROM_KERNEL, 4*4(%esp)
 
 	/*
 	 * When we're here from kernel mode; the (exception) stack looks like:
 	 *
-	 *  5*4(%esp) - <previous context>
-	 *  4*4(%esp) - flags
-	 *  3*4(%esp) - cs
-	 *  2*4(%esp) - ip
-	 *  1*4(%esp) - orig_eax
-	 *  0*4(%esp) - gs / function
+	 *  6*4(%esp) - <previous context>
+	 *  5*4(%esp) - flags
+	 *  4*4(%esp) - cs
+	 *  3*4(%esp) - ip
+	 *  2*4(%esp) - orig_eax
+	 *  1*4(%esp) - gs / function
+	 *  0*4(%esp) - fs
 	 *
 	 * Lets build a 5 entry IRET frame after that, such that struct pt_regs
 	 * is complete and in particular regs->sp is correct. This gives us
-	 * the original 5 enties as gap:
+	 * the original 6 enties as gap:
 	 *
-	 * 12*4(%esp) - <previous context>
-	 * 11*4(%esp) - gap / flags
-	 * 10*4(%esp) - gap / cs
-	 *  9*4(%esp) - gap / ip
-	 *  8*4(%esp) - gap / orig_eax
-	 *  7*4(%esp) - gap / gs / function
-	 *  6*4(%esp) - ss
-	 *  5*4(%esp) - sp
-	 *  4*4(%esp) - flags
-	 *  3*4(%esp) - cs
-	 *  2*4(%esp) - ip
-	 *  1*4(%esp) - orig_eax
-	 *  0*4(%esp) - gs / function
+	 * 14*4(%esp) - <previous context>
+	 * 13*4(%esp) - gap / flags
+	 * 12*4(%esp) - gap / cs
+	 * 11*4(%esp) - gap / ip
+	 * 10*4(%esp) - gap / orig_eax
+	 *  9*4(%esp) - gap / gs / function
+	 *  8*4(%esp) - gap / fs
+	 *  7*4(%esp) - ss
+	 *  6*4(%esp) - sp
+	 *  5*4(%esp) - flags
+	 *  4*4(%esp) - cs
+	 *  3*4(%esp) - ip
+	 *  2*4(%esp) - orig_eax
+	 *  1*4(%esp) - gs / function
+	 *  0*4(%esp) - fs
 	 */
 
 	pushl	%ss		# ss
 	pushl	%esp		# sp (points at ss)
-	addl	$6*4, (%esp)	# point sp back at the previous context
-	pushl	6*4(%esp)	# flags
-	pushl	6*4(%esp)	# cs
-	pushl	6*4(%esp)	# ip
-	pushl	6*4(%esp)	# orig_eax
-	pushl	6*4(%esp)	# gs / function
+	addl	$7*4, (%esp)	# point sp back at the previous context
+	pushl	7*4(%esp)	# flags
+	pushl	7*4(%esp)	# cs
+	pushl	7*4(%esp)	# ip
+	pushl	7*4(%esp)	# orig_eax
+	pushl	7*4(%esp)	# gs / function
+	pushl	7*4(%esp)	# fs
 .Lfrom_usermode_no_fixup_\@:
 .endm
 
 .macro IRET_FRAME
+	/*
+	 * We're called with %ds, %es, %fs, and %gs from the interrupted
+	 * frame, so we shouldn't use them.  Also, we may be in ESPFIX
+	 * mode and therefore have a nonzero SS base and an offset ESP,
+	 * so any attempt to access the stack needs to use SS.  (except for
+	 * accesses through %esp, which automatically use SS.)
+	 */
 	testl $CS_FROM_KERNEL, 1*4(%esp)
 	jz .Lfinished_frame_\@
 
@@ -276,31 +288,40 @@
 	movl	5*4(%esp), %eax		# (modified) regs->sp
 
 	movl	4*4(%esp), %ecx		# flags
-	movl	%ecx, -4(%eax)
+	movl	%ecx, %ss:-1*4(%eax)
 
 	movl	3*4(%esp), %ecx		# cs
 	andl	$0x0000ffff, %ecx
-	movl	%ecx, -8(%eax)
+	movl	%ecx, %ss:-2*4(%eax)
 
 	movl	2*4(%esp), %ecx		# ip
-	movl	%ecx, -12(%eax)
+	movl	%ecx, %ss:-3*4(%eax)
 
 	movl	1*4(%esp), %ecx		# eax
-	movl	%ecx, -16(%eax)
+	movl	%ecx, %ss:-4*4(%eax)
 
 	popl	%ecx
-	lea	-16(%eax), %esp
+	lea	-4*4(%eax), %esp
 	popl	%eax
 .Lfinished_frame_\@:
 .endm
 
-.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0
 	cld
 .if \skip_gs == 0
 	PUSH_GS
 .endif
-	FIXUP_FRAME
 	pushl	%fs
+
+	pushl	%eax
+	movl	$(__KERNEL_PERCPU), %eax
+	movl	%eax, %fs
+.if \unwind_espfix > 0
+	UNWIND_ESPFIX_STACK
+.endif
+	popl	%eax
+
+	FIXUP_FRAME
 	pushl	%es
 	pushl	%ds
 	pushl	\pt_regs_ax
@@ -313,8 +334,6 @@
 	movl	$(__USER_DS), %edx
 	movl	%edx, %ds
 	movl	%edx, %es
-	movl	$(__KERNEL_PERCPU), %edx
-	movl	%edx, %fs
 .if \skip_gs == 0
 	SET_KERNEL_GS %edx
 .endif
@@ -324,8 +343,8 @@
 .endif
 .endm
 
-.macro SAVE_ALL_NMI cr3_reg:req
-	SAVE_ALL
+.macro SAVE_ALL_NMI cr3_reg:req unwind_espfix=0
+	SAVE_ALL unwind_espfix=\unwind_espfix
 
 	BUG_IF_WRONG_CR3
 
@@ -357,6 +376,7 @@
 2:	popl	%es
 3:	popl	%fs
 	POP_GS \pop
+	IRET_FRAME
 .pushsection .fixup, "ax"
 4:	movl	$0, (%esp)
 	jmp	1b
@@ -395,7 +415,8 @@
 
 .macro CHECK_AND_APPLY_ESPFIX
 #ifdef CONFIG_X86_ESPFIX32
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
 
 	ALTERNATIVE	"jmp .Lend_\@", "", X86_BUG_ESPFIX
 
@@ -1075,7 +1096,6 @@ restore_all:
 	/* Restore user state */
 	RESTORE_REGS pop=4			# skip orig_eax/error_code
 .Lirq_return:
-	IRET_FRAME
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
 	 * when returning from IPI handler and when returning from
@@ -1128,30 +1148,43 @@ ENDPROC(entry_INT80_32)
  * We can't call C functions using the ESPFIX stack. This code reads
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
+ *
+ * We might be on user CR3 here, so percpu data is not mapped and we can't
+ * access the GDT through the percpu segment.  Instead, use SGDT to find
+ * the cpu_entry_area alias of the GDT.
  */
 #ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
-	mov	GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
-	mov	GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+	pushl	%ecx
+	subl	$2*4, %esp
+	sgdt	(%esp)
+	movl	2(%esp), %ecx				/* GDT address */
+	/*
+	 * Careful: ECX is a linear pointer, so we need to force base
+	 * zero.  %cs is the only known-linear segment we have right now.
+	 */
+	mov	%cs:GDT_ESPFIX_OFFSET + 4(%ecx), %al	/* bits 16..23 */
+	mov	%cs:GDT_ESPFIX_OFFSET + 7(%ecx), %ah	/* bits 24..31 */
 	shl	$16, %eax
+	addl	$2*4, %esp
+	popl	%ecx
 	addl	%esp, %eax			/* the adjusted stack pointer */
 	pushl	$__KERNEL_DS
 	pushl	%eax
 	lss	(%esp), %esp			/* switch to the normal stack segment */
 #endif
 .endm
+
 .macro UNWIND_ESPFIX_STACK
+	/* It's safe to clobber %eax, all other regs need to be preserved */
 #ifdef CONFIG_X86_ESPFIX32
 	movl	%ss, %eax
 	/* see if on espfix stack */
 	cmpw	$__ESPFIX_SS, %ax
-	jne	27f
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %es
+	jne	.Lno_fixup_\@
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
-27:
+.Lno_fixup_\@:
 #endif
 .endm
 
@@ -1341,11 +1374,6 @@ END(spurious_interrupt_bug)
 
 #ifdef CONFIG_XEN_PV
 ENTRY(xen_hypervisor_callback)
-	pushl	$-1				/* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-	TRACE_IRQS_OFF
-
 	/*
 	 * Check to see if we got the event in the critical
 	 * region in xen_iret_direct, after we've reenabled
@@ -1353,16 +1381,17 @@ ENTRY(xen_hypervisor_callback)
 	 * iret instruction's behaviour where it delivers a
 	 * pending interrupt when enabling interrupts:
 	 */
-	movl	PT_EIP(%esp), %eax
-	cmpl	$xen_iret_start_crit, %eax
+	cmpl	$xen_iret_start_crit, (%esp)
 	jb	1f
-	cmpl	$xen_iret_end_crit, %eax
+	cmpl	$xen_iret_end_crit, (%esp)
 	jae	1f
-
-	jmp	xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1:	mov	%esp, %eax
+	call	xen_iret_crit_fixup
+1:
+	pushl	$-1				/* orig_ax = -1 => not a system call */
+	SAVE_ALL
+	ENCODE_FRAME_POINTER
+	TRACE_IRQS_OFF
+	mov	%esp, %eax
 	call	xen_evtchn_do_upcall
 #ifndef CONFIG_PREEMPTION
 	call	xen_maybe_preempt_hcall
@@ -1449,10 +1478,9 @@ END(page_fault)
 
 common_exception_read_cr2:
 	/* the function address is in %gs's slot on the stack */
-	SAVE_ALL switch_stacks=1 skip_gs=1
+	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
 
 	ENCODE_FRAME_POINTER
-	UNWIND_ESPFIX_STACK
 
 	/* fixup %gs */
 	GS_TO_REG %ecx
@@ -1474,9 +1502,8 @@ END(common_exception_read_cr2)
 
 common_exception:
 	/* the function address is in %gs's slot on the stack */
-	SAVE_ALL switch_stacks=1 skip_gs=1
+	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
 	ENCODE_FRAME_POINTER
-	UNWIND_ESPFIX_STACK
 
 	/* fixup %gs */
 	GS_TO_REG %ecx
@@ -1515,6 +1542,10 @@ ENTRY(nmi)
 	ASM_CLAC
 
 #ifdef CONFIG_X86_ESPFIX32
+	/*
+	 * ESPFIX_SS is only ever set on the return to user path
+	 * after we've switched to the entry stack.
+	 */
 	pushl	%eax
 	movl	%ss, %eax
 	cmpw	$__ESPFIX_SS, %ax
@@ -1550,6 +1581,11 @@ ENTRY(nmi)
 	movl	%ebx, %esp
 
 .Lnmi_return:
+#ifdef CONFIG_X86_ESPFIX32
+	testl	$CS_FROM_ESPFIX, PT_CS(%esp)
+	jnz	.Lnmi_from_espfix
+#endif
+
 	CHECK_AND_APPLY_ESPFIX
 	RESTORE_ALL_NMI cr3_reg=%edi pop=4
 	jmp	.Lirq_return
@@ -1557,23 +1593,42 @@ ENTRY(nmi)
 #ifdef CONFIG_X86_ESPFIX32
 .Lnmi_espfix_stack:
 	/*
-	 * create the pointer to lss back
+	 * Create the pointer to LSS back
 	 */
 	pushl	%ss
 	pushl	%esp
 	addl	$4, (%esp)
-	/* copy the iret frame of 12 bytes */
-	.rept 3
-	pushl	16(%esp)
-	.endr
-	pushl	%eax
-	SAVE_ALL_NMI cr3_reg=%edi
+
+	/* Copy the (short) IRET frame */
+	pushl	4*4(%esp)	# flags
+	pushl	4*4(%esp)	# cs
+	pushl	4*4(%esp)	# ip
+
+	pushl	%eax		# orig_ax
+
+	SAVE_ALL_NMI cr3_reg=%edi unwind_espfix=1
 	ENCODE_FRAME_POINTER
-	FIXUP_ESPFIX_STACK			# %eax == %esp
+
+	/* clear CS_FROM_KERNEL, set CS_FROM_ESPFIX */
+	xorl	$(CS_FROM_ESPFIX | CS_FROM_KERNEL), PT_CS(%esp)
+
 	xorl	%edx, %edx			# zero error code
-	call	do_nmi
+	movl	%esp, %eax			# pt_regs pointer
+	jmp	.Lnmi_from_sysenter_stack
+
+.Lnmi_from_espfix:
 	RESTORE_ALL_NMI cr3_reg=%edi
-	lss	12+4(%esp), %esp		# back to espfix stack
+	/*
+	 * Because we cleared CS_FROM_KERNEL, IRET_FRAME 'forgot' to
+	 * fix up the gap and long frame:
+	 *
+	 *  3 - original frame	(exception)
+	 *  2 - ESPFIX block	(above)
+	 *  6 - gap		(FIXUP_FRAME)
+	 *  5 - long frame	(FIXUP_FRAME)
+	 *  1 - orig_ax
+	 */
+	lss	(1+5+6)*4(%esp), %esp			# back to espfix stack
 	jmp	.Lirq_return
 #endif
 END(nmi)

arch/x86/include/asm/cpu_entry_area.h

@@ -78,8 +78,12 @@ struct cpu_entry_area {
 
 	/*
 	 * The GDT is just below entry_stack and thus serves (on x86_64) as
-	 * a a read-only guard page.
+	 * a read-only guard page. On 32-bit the GDT must be writeable, so
+	 * it needs an extra guard page.
 	 */
+#ifdef CONFIG_X86_32
+	char guard_entry_stack[PAGE_SIZE];
+#endif
 	struct entry_stack_page entry_stack_page;
 
 	/*
@@ -94,7 +98,6 @@ struct cpu_entry_area {
 	 */
 	struct cea_exception_stacks estacks;
 #endif
-#ifdef CONFIG_CPU_SUP_INTEL
 	/*
 	 * Per CPU debug store for Intel performance monitoring. Wastes a
 	 * full page at the moment.
@@ -105,11 +108,13 @@ struct cpu_entry_area {
 	 * Reserve enough fixmap PTEs.
 	 */
 	struct debug_store_buffers cpu_debug_buffers;
-#endif
 };
 
-#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+#define CPU_ENTRY_AREA_SIZE		(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_ARRAY_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+/* Total size includes the readonly IDT mapping page as well: */
+#define CPU_ENTRY_AREA_TOTAL_SIZE	(CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
@@ -117,13 +122,14 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
+/* Single page reserved for the readonly IDT mapping: */
 #define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
 #define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
 
 #define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
 
 #define CPU_ENTRY_AREA_MAP_SIZE			\
-	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 

arch/x86/include/asm/crash.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_CRASH_H
 #define _ASM_X86_CRASH_H
 
+struct kimage;
+
 int crash_load_segments(struct kimage *image);
 int crash_copy_backup_region(struct kimage *image);
 int crash_setup_memmap_entries(struct kimage *image,

arch/x86/include/asm/fixmap.h

@@ -156,7 +156,7 @@ extern pte_t *kmap_pte;
 extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
-void native_set_fixmap(enum fixed_addresses idx,
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
 		       phys_addr_t phys, pgprot_t flags);
 
 #ifndef CONFIG_PARAVIRT_XXL

arch/x86/include/asm/fpu/internal.h

@@ -509,7 +509,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
 
 static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
 {
-	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+	return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
 }
 
 /*

arch/x86/include/asm/pgtable_32_types.h

@@ -44,11 +44,11 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
  * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
  * to avoid include recursion hell
  */
-#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 39)
 
-#define CPU_ENTRY_AREA_BASE						\
-	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
-	 & PMD_MASK)
+/* The +1 is for the readonly IDT page: */
+#define CPU_ENTRY_AREA_BASE	\
+	((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK)
 
 #define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)

arch/x86/include/asm/segment.h

@@ -31,6 +31,18 @@
  */
 #define SEGMENT_RPL_MASK	0x3
 
+/*
+ * When running on Xen PV, the actual privilege level of the kernel is 1,
+ * not 0. Testing the Requested Privilege Level in a segment selector to
+ * determine whether the context is user mode or kernel mode with
+ * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level
+ * matches the 0x3 mask.
+ *
+ * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV
+ * kernels because privilege level 2 is never used.
+ */
+#define USER_SEGMENT_RPL_MASK	0x2
+
 /* User mode is privilege level 3: */
 #define USER_RPL		0x3
 

arch/x86/include/asm/syscall_wrapper.h

@@ -48,12 +48,13 @@
  * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias
  * named __ia32_sys_*()
  */
-#define SYSCALL_DEFINE0(sname)					\
-	SYSCALL_METADATA(_##sname, 0);				\
-	asmlinkage long __x64_sys_##sname(void);		\
-	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);	\
-	SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname);	\
-	asmlinkage long __x64_sys_##sname(void)
+
+#define SYSCALL_DEFINE0(sname)						\
+	SYSCALL_METADATA(_##sname, 0);					\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\
+	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);		\
+	SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname);		\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
 
 #define COND_SYSCALL(name)						\
 	cond_syscall(__x64_sys_##name);					\
@@ -181,11 +182,11 @@
  * macros to work correctly.
  */
 #ifndef SYSCALL_DEFINE0
-#define SYSCALL_DEFINE0(sname)					\
-	SYSCALL_METADATA(_##sname, 0);				\
-	asmlinkage long __x64_sys_##sname(void);		\
-	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);	\
-	asmlinkage long __x64_sys_##sname(void)
+#define SYSCALL_DEFINE0(sname)						\
+	SYSCALL_METADATA(_##sname, 0);					\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\
+	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);		\
+	asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
 #endif
 
 #ifndef COND_SYSCALL

arch/x86/kernel/apic/io_apic.c

@@ -1727,9 +1727,10 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
 
 static inline bool ioapic_irqd_mask(struct irq_data *data)
 {
-	/* If we are moving the irq we need to mask it */
+	/* If we are moving the IRQ we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		mask_ioapic_irq(data);
+		if (!irqd_irq_masked(data))
+			mask_ioapic_irq(data);
 		return true;
 	}
 	return false;
@@ -1766,7 +1767,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 		 */
 		if (!io_apic_level_ack_pending(data->chip_data))
 			irq_move_masked_irq(data);
-		unmask_ioapic_irq(data);
+		/* If the IRQ is masked in the core, leave it: */
+		if (!irqd_irq_masked(data))
+			unmask_ioapic_irq(data);
 	}
 }
 #else

arch/x86/kernel/cpu/bugs.c

@@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
+static void __init mds_print_mitigation(void);
 static void __init taa_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
@@ -108,6 +109,12 @@ void __init check_bugs(void)
 	mds_select_mitigation();
 	taa_select_mitigation();
 
+	/*
+	 * As MDS and TAA mitigations are inter-related, print MDS
+	 * mitigation until after TAA mitigation selection is done.
+	 */
+	mds_print_mitigation();
+
 	arch_smt_update();
 
 #ifdef CONFIG_X86_32
@@ -245,6 +252,12 @@ static void __init mds_select_mitigation(void)
 		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
 			cpu_smt_disable(false);
 	}
+}
+
+static void __init mds_print_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
+		return;
 
 	pr_info("%s\n", mds_strings[mds_mitigation]);
 }
@@ -304,8 +317,12 @@ static void __init taa_select_mitigation(void)
 		return;
 	}
 
-	/* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */
-	if (taa_mitigation == TAA_MITIGATION_OFF)
+	/*
+	 * TAA mitigation via VERW is turned off if both
+	 * tsx_async_abort=off and mds=off are specified.
+	 */
+	if (taa_mitigation == TAA_MITIGATION_OFF &&
+	    mds_mitigation == MDS_MITIGATION_OFF)
 		goto out;
 
 	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
@@ -339,6 +356,15 @@ static void __init taa_select_mitigation(void)
 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
 
+	/*
+	 * Update MDS mitigation, if necessary, as the mds_user_clear is
+	 * now enabled for TAA mitigation.
+	 */
+	if (mds_mitigation == MDS_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_MDS)) {
+		mds_mitigation = MDS_MITIGATION_FULL;
+		mds_select_mitigation();
+	}
 out:
 	pr_info("%s\n", taa_strings[taa_mitigation]);
 }

arch/x86/kernel/cpu/mce/amd.c

@@ -266,10 +266,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 	smca_set_misc_banks_map(bank, cpu);
 
 	/* Return early if this bank was already initialized. */
-	if (smca_banks[bank].hwid)
+	if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0)
 		return;
 
-	if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) {
+	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) {
 		pr_warn("Failed to read MCA_IPID for bank %d\n", bank);
 		return;
 	}

arch/x86/kernel/cpu/mce/core.c

@@ -814,8 +814,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 		if (quirk_no_way_out)
 			quirk_no_way_out(i, m, regs);
 
+		m->bank = i;
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
-			m->bank = i;
 			mce_read_aux(m, i);
 			*msg = tmp;
 			return 1;

arch/x86/kernel/cpu/mce/therm_throt.c

@@ -188,7 +188,7 @@ static void therm_throt_process(bool new_event, int event, int level)
 	/* if we just entered the thermal event */
 	if (new_event) {
 		if (event == THERMAL_THROTTLING_EVENT)
-			pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
+			pr_warn("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
 				this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package",
 				state->count);

arch/x86/kernel/doublefault.c

@@ -65,6 +65,9 @@ struct x86_hw_tss doublefault_tss __cacheline_aligned = {
 	.ss		= __KERNEL_DS,
 	.ds		= __USER_DS,
 	.fs		= __KERNEL_PERCPU,
+#ifndef CONFIG_X86_32_LAZY_GS
+	.gs		= __KERNEL_STACK_CANARY,
+#endif
 
 	.__cr3		= __pa_nodebug(swapper_pg_dir),
 };

arch/x86/kernel/early-quirks.c

@@ -710,6 +710,8 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+	{ PCI_VENDOR_ID_INTEL, 0x3e20,
+		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,

arch/x86/kernel/head_32.S

@@ -571,6 +571,16 @@ ENTRY(initial_page_table)
 #  error "Kernel PMDs should be 1, 2 or 3"
 # endif
 	.align PAGE_SIZE		/* needs to be page-sized too */
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * PTI needs another page so sync_initial_pagetable() works correctly
+	 * and does not scribble over the data which is placed behind the
+	 * actual initial_page_table. See clone_pgd_range().
+	 */
+	.fill 1024, 4, 0
+#endif
+
 #endif
 
 .data

arch/x86/kvm/cpuid.c

@@ -402,7 +402,8 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 			entry->edx |= F(SPEC_CTRL);
 		if (boot_cpu_has(X86_FEATURE_STIBP))
 			entry->edx |= F(INTEL_STIBP);
-		if (boot_cpu_has(X86_FEATURE_SSBD))
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    boot_cpu_has(X86_FEATURE_AMD_SSBD))
 			entry->edx |= F(SPEC_CTRL_SSBD);
 		/*
 		 * We emulate ARCH_CAPABILITIES in software even
@@ -504,7 +505,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	r = -E2BIG;
 
-	if (*nent >= maxnent)
+	if (WARN_ON(*nent >= maxnent))
 		goto out;
 
 	do_host_cpuid(entry, function, 0);
@@ -759,7 +760,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 			entry->ebx |= F(AMD_IBRS);
 		if (boot_cpu_has(X86_FEATURE_STIBP))
 			entry->ebx |= F(AMD_STIBP);
-		if (boot_cpu_has(X86_FEATURE_SSBD))
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    boot_cpu_has(X86_FEATURE_AMD_SSBD))
 			entry->ebx |= F(AMD_SSBD);
 		if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
 			entry->ebx |= F(AMD_SSB_NO);
@@ -810,6 +812,9 @@ out:
 static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
 			 int *nent, int maxnent, unsigned int type)
 {
+	if (*nent >= maxnent)
+		return -E2BIG;
+
 	if (type == KVM_GET_EMULATED_CPUID)
 		return __do_cpuid_func_emulated(entry, func, nent, maxnent);
 

arch/x86/kvm/vmx/nested.c

@@ -2418,6 +2418,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				entry_failure_code))
 		return -EINVAL;
 
+	/*
+	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
+	 * on nested VM-Exit, which can occur without actually running L2 and
+	 * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
+	 * transition to HLT instead of running L2.
+	 */
+	if (enable_ept)
+		vmcs_writel(GUEST_CR3, vmcs12->guest_cr3);
+
 	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
 	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
 	    is_pae_paging(vcpu)) {

arch/x86/kvm/vmx/vmx.c

@@ -2995,6 +2995,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	struct kvm *kvm = vcpu->kvm;
+	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
 	u64 eptp;
 
@@ -3011,15 +3012,18 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 		}
 
-		if (enable_unrestricted_guest || is_paging(vcpu) ||
-		    is_guest_mode(vcpu))
+		/* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */
+		if (is_guest_mode(vcpu))
+			update_guest_cr3 = false;
+		else if (enable_unrestricted_guest || is_paging(vcpu))
 			guest_cr3 = kvm_read_cr3(vcpu);
 		else
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
 		ept_load_pdptrs(vcpu);
 	}
 
-	vmcs_writel(GUEST_CR3, guest_cr3);
+	if (update_guest_cr3)
+		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
 int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)

arch/x86/kvm/x86.c

@@ -300,13 +300,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -1327,10 +1328,15 @@ static u64 kvm_get_arch_capabilities(void)
 	 * If TSX is disabled on the system, guests are also mitigated against
 	 * TAA and clear CPU buffer mitigation is not required for guests.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
-	    (data & ARCH_CAP_TSX_CTRL_MSR))
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~ARCH_CAP_TAA_NO;
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
+	else if (data & ARCH_CAP_TSX_CTRL_MSR)
 		data &= ~ARCH_CAP_MDS_NO;
 
+	/* KVM does not emulate MSR_IA32_TSX_CTRL.  */
+	data &= ~ARCH_CAP_TSX_CTRL_MSR;
 	return data;
 }
 
@@ -4421,6 +4427,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4444,7 +4451,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {

arch/x86/lib/x86-opcode-map.txt

@@ -333,7 +333,7 @@ AVXcode: 1
 06: CLTS
 07: SYSRET (o64)
 08: INVD
-09: WBINVD
+09: WBINVD | WBNOINVD (F3)
 0a:
 0b: UD2 (1B)
 0c:
@@ -364,7 +364,7 @@ AVXcode: 1
 # a ModR/M byte.
 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
-1c:
+1c: Grp20 (1A),(1C)
 1d:
 1e:
 1f: NOP Ev
@@ -792,6 +792,8 @@ f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
 f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
+f9: MOVDIRI My,Gy
 EndTable
 
 Table: 3-byte opcode 2 (0x0f 0x3a)
@@ -943,9 +945,9 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
 5: rdpkru (110),(11B) | wrpkru (111),(11B)
@@ -1020,7 +1022,7 @@ GrpTable: Grp15
 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
 4: XSAVE | ptwrite Ey (F3),(11B)
 5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B)
 7: clflush | clflushopt (66) | sfence (11B)
 EndTable
 
@@ -1051,6 +1053,10 @@ GrpTable: Grp19
 6: vscatterpf1qps/d Wx (66),(ev)
 EndTable
 
+GrpTable: Grp20
+0: cldemote Mb
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH

arch/x86/math-emu/fpu_system.h

@@ -107,6 +107,8 @@ static inline bool seg_writable(struct desc_struct *d)
 #define FPU_access_ok(y,z)	if ( !access_ok(y,z) ) \
 				math_abort(FPU_info,SIGSEGV)
 #define FPU_abort		math_abort(FPU_info, SIGSEGV)
+#define FPU_copy_from_user(to, from, n)	\
+		do { if (copy_from_user(to, from, n)) FPU_abort; } while (0)
 
 #undef FPU_IGNORE_CODE_SEGV
 #ifdef FPU_IGNORE_CODE_SEGV
@@ -122,7 +124,7 @@ static inline bool seg_writable(struct desc_struct *d)
 #define	FPU_code_access_ok(z) FPU_access_ok((void __user *)FPU_EIP,z)
 #endif
 
-#define FPU_get_user(x,y)       get_user((x),(y))
-#define FPU_put_user(x,y)       put_user((x),(y))
+#define FPU_get_user(x,y) do { if (get_user((x),(y))) FPU_abort; } while (0)
+#define FPU_put_user(x,y) do { if (put_user((x),(y))) FPU_abort; } while (0)
 
 #endif