Merge branch 'linus' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

.mailmap

@@ -107,6 +107,7 @@ Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
 Mark Brown <broonie@sirena.org.uk>
+Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
 Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
 Matthieu CASTET <castet.matthieu@free.fr>

Documentation/admin-guide/kernel-parameters.rst

@@ -109,6 +109,7 @@ parameter is applicable::
 	IPV6	IPv6 support is enabled.
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
+	ISOL	CPU Isolation is enabled.
 	JOY	Appropriate joystick support is enabled.
 	KGDB	Kernel debugger support is enabled.
 	KVM	Kernel Virtual Machine support is enabled.

Documentation/admin-guide/kernel-parameters.txt

@@ -328,11 +328,15 @@
 			not play well with APC CPU idle - disable it if you have
 			APC and your system crashes randomly.
 
-	apic=		[APIC,X86-32] Advanced Programmable Interrupt Controller
+	apic=		[APIC,X86] Advanced Programmable Interrupt Controller
 			Change the output verbosity whilst booting
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
+			For X86-32, this can also be used to specify an APIC
+			driver name.
+			Format: apic=driver_name
+			Examples: apic=bigsmp
 
 	apic_extnmi=	[APIC,X86] External NMI delivery setting
 			Format: { bsp (default) | all | none }
@@ -1737,7 +1741,7 @@
 	isapnp=		[ISAPNP]
 			Format: <RDP>,<reset>,<pci_scan>,<verbosity>
 
-	isolcpus=	[KNL,SMP] Isolate a given set of CPUs from disturbance.
+	isolcpus=	[KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
 			[Deprecated - use cpusets instead]
 			Format: [flag-list,]<cpu-list>
 
@@ -2662,7 +2666,7 @@
 			Valid arguments: on, off
 			Default: on
 
-	nohz_full=	[KNL,BOOT]
+	nohz_full=	[KNL,BOOT,SMP,ISOL]
 			The argument is a cpu list, as described above.
 			In kernels built with CONFIG_NO_HZ_FULL=y, set
 			the specified list of CPUs whose tick will be stopped
@@ -2708,6 +2712,8 @@
 			steal time is computed, but won't influence scheduler
 			behaviour
 
+	nopti		[X86-64] Disable kernel page table isolation
+
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
@@ -3282,6 +3288,12 @@
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
+	pti=		[X86_64]
+			Control user/kernel address space isolation:
+			on - enable
+			off - disable
+			auto - default setting
+
 	pty.legacy_count=
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.

Documentation/admin-guide/thunderbolt.rst

@@ -230,7 +230,7 @@ If supported by your machine this will be exposed by the WMI bus with
 a sysfs attribute called "force_power".
 
 For example the intel-wmi-thunderbolt driver exposes this attribute in:
-  /sys/devices/platform/PNP0C14:00/wmi_bus/wmi_bus-PNP0C14:00/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
+  /sys/bus/wmi/devices/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
 
   To force the power to on, write 1 to this attribute file.
   To disable force power, write 0 to this attribute file.

Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt

@@ -13,7 +13,6 @@ Required properties:
                  at25df321a
                  at25df641
                  at26df081a
-                 en25s64
                  mr25h128
                  mr25h256
                  mr25h10
@@ -33,7 +32,6 @@ Required properties:
                  s25fl008k
                  s25fl064k
                  sst25vf040b
-                 sst25wf040b
                  m25p40
                  m25p80
                  m25p16

Documentation/devicetree/bindings/sound/da7218.txt

@@ -73,7 +73,7 @@ Example:
 		compatible = "dlg,da7218";
 		reg = <0x1a>;
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		wakeup-source;
 
 		VDD-supply = <&reg_audio>;

Documentation/devicetree/bindings/sound/da7219.txt

@@ -77,7 +77,7 @@ Example:
 		reg = <0x1a>;
 
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 
 		VDD-supply = <&reg_audio>;
 		VDDMIC-supply = <&reg_audio>;

Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt

@@ -12,24 +12,30 @@ Required properties:
   - "fsl,imx53-ecspi" for SPI compatible with the one integrated on i.MX53 and later Soc
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain CSPI/eCSPI interrupt
-- cs-gpios : Specifies the gpio pins to be used for chipselects.
 - clocks : Clock specifiers for both ipg and per clocks.
 - clock-names : Clock names should include both "ipg" and "per"
 See the clock consumer binding,
 	Documentation/devicetree/bindings/clock/clock-bindings.txt
-- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
-		Documentation/devicetree/bindings/dma/dma.txt
-- dma-names: DMA request names should include "tx" and "rx" if present.
 
-Obsolete properties:
-- fsl,spi-num-chipselects : Contains the number of the chipselect
+Recommended properties:
+- cs-gpios : GPIOs to use as chip selects, see spi-bus.txt.  While the native chip
+select lines can be used, they appear to always generate a pulse between each
+word of a transfer.  Most use cases will require GPIO based chip selects to
+generate a valid transaction.
 
 Optional properties:
+- num-cs :  Number of total chip selects, see spi-bus.txt.
+- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
+Documentation/devicetree/bindings/dma/dma.txt.
+- dma-names: DMA request names, if present, should include "tx" and "rx".
 - fsl,spi-rdy-drctl: Integer, representing the value of DRCTL, the register
 controlling the SPI_READY handling. Note that to enable the DRCTL consideration,
 the SPI_READY mode-flag needs to be set too.
 Valid values are: 0 (disabled), 1 (edge-triggered burst) and 2 (level-triggered burst).
 
+Obsolete properties:
+- fsl,spi-num-chipselects : Contains the number of the chipselect
+
 Example:
 
 ecspi@70010000 {

Documentation/gpu/i915.rst

@@ -341,10 +341,7 @@ GuC
 GuC-specific firmware loader
 ----------------------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_loader.c
-   :doc: GuC-specific firmware loader
-
-.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_loader.c
+.. kernel-doc:: drivers/gpu/drm/i915/intel_guc_fw.c
    :internal:
 
 GuC-based command submission

Documentation/x86/x86_64/mm.txt

@@ -1,6 +1,4 @@
 
-<previous description obsolete, deleted>
-
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
@@ -14,13 +12,17 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+				    vaddr_end for KASLR
+fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
+fffffe8000000000 - fffffeffffffffff (=39 bits) LDT remap for PTI
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space (variable)
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Virtual memory map with 5 level page tables:
@@ -29,26 +31,31 @@ Virtual memory map with 5 level page tables:
 hole caused by [56:63] sign extension
 ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
 ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
-ff90000000000000 - ff91ffffffffffff (=49 bits) hole
-ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI
+ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB)
 ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
 ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
+... unused hole ...
+				    vaddr_end for KASLR
+fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
 ... unused hole ...
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Architecture defines a 64-bit virtual address. Implementations can support
 less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
-through to the most-significant implemented bit are set to either all ones
-or all zero. This causes hole between user space and kernel addresses.
+through to the most-significant implemented bit are sign extended.
+This causes hole between user space and kernel addresses if you interpret them
+as unsigned.
 
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
@@ -58,19 +65,15 @@ vmalloc space is lazily synchronized into the different PML4/PML5 pages of
 the processes using the page fault handler, with init_top_pgt as
 reference.
 
-Current X86-64 implementations support up to 46 bits of address space (64 TB),
-which is our current limit. This expands into MBZ space in the page tables.
-
 We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
 memory window (this size is arbitrary, it can be raised later if needed).
 The mappings are not part of any other kernel PGD and are only available
 during EFI runtime calls.
 
-The module mapping space size changes based on the CONFIG requirements for the
-following fixmap section.
-
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
 
--Andi Kleen, Jul 2004
+Be very careful vs. KASLR when changing anything here. The KASLR address
+range must not overlap with anything except the KASAN shadow area, which is
+correct as KASAN disables KASLR.

MAINTAINERS

@@ -2621,24 +2621,22 @@ F:	fs/bfs/
 F:	include/uapi/linux/bfs_fs.h
 
 BLACKFIN ARCHITECTURE
-M:	Steven Miao <realmz6@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 T:	git git://git.code.sf.net/p/adi-linux/code
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	arch/blackfin/
 
 BLACKFIN EMAC DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/net/ethernet/adi/
 
 BLACKFIN MEDIA DRIVER
-M:	Scott Jiang <scott.jiang.linux@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org/
-S:	Supported
+S:	Orphan
 F:	drivers/media/platform/blackfin/
 F:	drivers/media/i2c/adv7183*
 F:	drivers/media/i2c/vs6624*
@@ -2646,25 +2644,25 @@ F:	drivers/media/i2c/vs6624*
 BLACKFIN RTC DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/rtc/rtc-bfin.c
 
 BLACKFIN SDH DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/mmc/host/bfin_sdh.c
 
 BLACKFIN SERIAL DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/tty/serial/bfin_uart.c
 
 BLACKFIN WATCHDOG DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/watchdog/bfin_wdt.c
 
 BLINKM RGB LED DRIVER
@@ -5151,15 +5149,15 @@ F:	sound/usb/misc/ua101.c
 EFI TEST DRIVER
 L:	linux-efi@vger.kernel.org
 M:	Ivan Hu <ivan.hu@canonical.com>
-M:	Matt Fleming <matt@codeblueprint.co.uk>
+M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
 S:	Maintained
 F:	drivers/firmware/efi/test/
 
 EFI VARIABLE FILESYSTEM
 M:	Matthew Garrett <matthew.garrett@nebula.com>
 M:	Jeremy Kerr <jk@ozlabs.org>
-M:	Matt Fleming <matt@codeblueprint.co.uk>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
+M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 L:	linux-efi@vger.kernel.org
 S:	Maintained
 F:	fs/efivarfs/
@@ -5320,7 +5318,6 @@ S:	Supported
 F:	security/integrity/evm/
 
 EXTENSIBLE FIRMWARE INTERFACE (EFI)
-M:	Matt Fleming <matt@codeblueprint.co.uk>
 M:	Ard Biesheuvel <ard.biesheuvel@linaro.org>
 L:	linux-efi@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
@@ -13493,6 +13490,7 @@ M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
 S:	Maintained
+F:	Documentation/admin-guide/thunderbolt.rst
 F:	drivers/thunderbolt/
 F:	include/linux/thunderbolt.h
 

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -789,6 +789,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
+
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 

arch/arm/boot/dts/aspeed-g4.dtsi

@@ -219,7 +219,7 @@
 				compatible = "aspeed,ast2400-vuart";
 				reg = <0x1e787000 0x40>;
 				reg-shift = <2>;
-				interrupts = <10>;
+				interrupts = <8>;
 				clocks = <&clk_uart>;
 				no-loopback-test;
 				status = "disabled";

arch/arm/boot/dts/at91-tse850-3.dts

@@ -221,6 +221,7 @@
 	jc42@18 {
 		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
 		reg = <0x18>;
+		smbus-timeout-disable;
 	};
 
 	dpot: mcp4651-104@28 {

arch/arm/boot/dts/da850-lego-ev3.dts

@@ -178,7 +178,7 @@
 	 */
 	battery {
 		pinctrl-names = "default";
-		pintctrl-0 = <&battery_pins>;
+		pinctrl-0 = <&battery_pins>;
 		compatible = "lego,ev3-battery";
 		io-channels = <&adc 4>, <&adc 3>;
 		io-channel-names = "voltage", "current";
@@ -392,7 +392,7 @@
 	batt_volt_en {
 		gpio-hog;
 		gpios = <6 GPIO_ACTIVE_HIGH>;
-		output-low;
+		output-high;
 	};
 };
 

arch/arm/boot/dts/exynos5800-peach-pi.dts

@@ -664,6 +664,10 @@
 	status = "okay";
 };
 
+&mixer {
+	status = "okay";
+};
+
 /* eMMC flash */
 &mmc_0 {
 	status = "okay";

arch/arm/boot/dts/ls1021a-qds.dts

@@ -215,7 +215,7 @@
 				reg = <0x2a>;
 				VDDA-supply = <&reg_3p3v>;
 				VDDIO-supply = <&reg_3p3v>;
-				clocks = <&sys_mclk 1>;
+				clocks = <&sys_mclk>;
 			};
 		};
 	};

arch/arm/boot/dts/ls1021a-twr.dts

@@ -187,7 +187,7 @@
 		reg = <0x0a>;
 		VDDA-supply = <&reg_3p3v>;
 		VDDIO-supply = <&reg_3p3v>;
-		clocks = <&sys_mclk 1>;
+		clocks = <&sys_mclk>;
 	};
 };
 

arch/arm/boot/dts/rk3066a-marsboard.dts

@@ -83,6 +83,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&vdd_arm>;
+};
+
 &i2c1 {
 	status = "okay";
 	clock-frequency = <400000>;

arch/arm/boot/dts/rk3288.dtsi

@@ -956,7 +956,7 @@
 	iep_mmu: iommu@ff900800 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff900800 0x0 0x40>;
-		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "iep_mmu";
 		#iommu-cells = <0>;
 		status = "disabled";

arch/arm/boot/dts/sun4i-a10.dtsi

@@ -502,8 +502,8 @@
 			reg = <0x01c16000 0x1000>;
 			interrupts = <58>;
 			clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
-				 <&ccu 9>,
-				 <&ccu 18>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "pll-0", "pll-1";
 			dmas = <&dma SUN4I_DMA_NORMAL 16>,
 			       <&dma SUN4I_DMA_NORMAL 16>,

arch/arm/boot/dts/sun5i-a10s.dtsi

@@ -82,8 +82,8 @@
 			reg = <0x01c16000 0x1000>;
 			interrupts = <58>;
 			clocks = <&ccu CLK_AHB_HDMI>, <&ccu CLK_HDMI>,
-				 <&ccu 9>,
-				 <&ccu 16>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "pll-0", "pll-1";
 			dmas = <&dma SUN4I_DMA_NORMAL 16>,
 			       <&dma SUN4I_DMA_NORMAL 16>,

arch/arm/boot/dts/sun6i-a31.dtsi

@@ -429,8 +429,8 @@
 			interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB1_HDMI>, <&ccu CLK_HDMI>,
 				 <&ccu CLK_HDMI_DDC>,
-				 <&ccu 7>,
-				 <&ccu 13>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "ddc", "pll-0", "pll-1";
 			resets = <&ccu RST_AHB1_HDMI>;
 			reset-names = "ahb";

arch/arm/boot/dts/sun7i-a20.dtsi

@@ -581,8 +581,8 @@
 			reg = <0x01c16000 0x1000>;
 			interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
-				 <&ccu 9>,
-				 <&ccu 18>;
+				 <&ccu CLK_PLL_VIDEO0_2X>,
+				 <&ccu CLK_PLL_VIDEO1_2X>;
 			clock-names = "ahb", "mod", "pll-0", "pll-1";
 			dmas = <&dma SUN4I_DMA_NORMAL 16>,
 			       <&dma SUN4I_DMA_NORMAL 16>,

arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts

@@ -146,6 +146,7 @@
 	status = "okay";
 
 	axp81x: pmic@3a3 {
+		compatible = "x-powers,axp813";
 		reg = <0x3a3>;
 		interrupt-parent = <&r_intc>;
 		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;

arch/arm/boot/dts/tango4-common.dtsi

@@ -156,7 +156,6 @@
 			reg = <0x6e000 0x400>;
 			ranges = <0 0x6e000 0x400>;
 			interrupt-parent = <&gic>;
-			interrupt-controller;
 			#address-cells = <1>;
 			#size-cells = <1>;
 

arch/arm/kernel/traps.c

@@ -793,7 +793,6 @@ void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
-EXPORT_SYMBOL(abort);
 
 void __init trap_init(void)
 {

arch/arm/lib/csumpartialcopyuser.S

@@ -85,7 +85,11 @@
 		.pushsection .text.fixup,"ax"
 		.align	4
 9001:		mov	r4, #-EFAULT
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		ldr	r5, [sp, #9*4]		@ *err_ptr
+#else
 		ldr	r5, [sp, #8*4]		@ *err_ptr
+#endif
 		str	r4, [r5]
 		ldmia	sp, {r1, r2}		@ retrieve dst, len
 		add	r2, r2, r1

arch/arm/mach-davinci/dm365.c

@@ -868,10 +868,10 @@ static const struct dma_slave_map dm365_edma_map[] = {
 	{ "spi_davinci.0", "rx", EDMA_FILTER_PARAM(0, 17) },
 	{ "spi_davinci.3", "tx", EDMA_FILTER_PARAM(0, 18) },
 	{ "spi_davinci.3", "rx", EDMA_FILTER_PARAM(0, 19) },
-	{ "dm6441-mmc.0", "rx", EDMA_FILTER_PARAM(0, 26) },
-	{ "dm6441-mmc.0", "tx", EDMA_FILTER_PARAM(0, 27) },
-	{ "dm6441-mmc.1", "rx", EDMA_FILTER_PARAM(0, 30) },
-	{ "dm6441-mmc.1", "tx", EDMA_FILTER_PARAM(0, 31) },
+	{ "da830-mmc.0", "rx", EDMA_FILTER_PARAM(0, 26) },
+	{ "da830-mmc.0", "tx", EDMA_FILTER_PARAM(0, 27) },
+	{ "da830-mmc.1", "rx", EDMA_FILTER_PARAM(0, 30) },
+	{ "da830-mmc.1", "tx", EDMA_FILTER_PARAM(0, 31) },
 };
 
 static struct edma_soc_info dm365_edma_pdata = {
@@ -925,12 +925,14 @@ static struct resource edma_resources[] = {
 	/* not using TC*_ERR */
 };
 
-static struct platform_device dm365_edma_device = {
-	.name			= "edma",
-	.id			= 0,
-	.dev.platform_data	= &dm365_edma_pdata,
-	.num_resources		= ARRAY_SIZE(edma_resources),
-	.resource		= edma_resources,
+static const struct platform_device_info dm365_edma_device __initconst = {
+	.name		= "edma",
+	.id		= 0,
+	.dma_mask	= DMA_BIT_MASK(32),
+	.res		= edma_resources,
+	.num_res	= ARRAY_SIZE(edma_resources),
+	.data		= &dm365_edma_pdata,
+	.size_data	= sizeof(dm365_edma_pdata),
 };
 
 static struct resource dm365_asp_resources[] = {
@@ -1428,13 +1430,18 @@ int __init dm365_init_video(struct vpfe_config *vpfe_cfg,
 
 static int __init dm365_init_devices(void)
 {
+	struct platform_device *edma_pdev;
 	int ret = 0;
 
 	if (!cpu_is_davinci_dm365())
 		return 0;
 
 	davinci_cfg_reg(DM365_INT_EDMA_CC);
-	platform_device_register(&dm365_edma_device);
+	edma_pdev = platform_device_register_full(&dm365_edma_device);
+	if (IS_ERR(edma_pdev)) {
+		pr_warn("%s: Failed to register eDMA\n", __func__);
+		return PTR_ERR(edma_pdev);
+	}
 
 	platform_device_register(&dm365_mdio_device);
 	platform_device_register(&dm365_emac_device);

arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts

@@ -75,6 +75,7 @@
 	pinctrl-0 = <&rgmii_pins>;
 	phy-mode = "rgmii";
 	phy-handle = <&ext_rgmii_phy>;
+	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 };
 

arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts

@@ -77,6 +77,7 @@
 	pinctrl-0 = <&rmii_pins>;
 	phy-mode = "rmii";
 	phy-handle = <&ext_rmii_phy1>;
+	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 
 };

arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts

@@ -82,6 +82,7 @@
 	pinctrl-0 = <&rgmii_pins>;
 	phy-mode = "rgmii";
 	phy-handle = <&ext_rgmii_phy>;
+	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 };
 
@@ -95,7 +96,7 @@
 &mmc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	vqmmc-supply = <&reg_vcc1v8>;
 	bus-width = <8>;
 	non-removable;

arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi

@@ -45,19 +45,10 @@
 
 #include "sun50i-a64.dtsi"
 
-/ {
-	reg_vcc3v3: vcc3v3 {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
-};
-
 &mmc0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc0_pins>;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&reg_dcdc1>;
 	non-removable;
 	disable-wp;
 	bus-width = <4>;

arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus2.dts

@@ -71,7 +71,7 @@
 	pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
-	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 

arch/arm64/boot/dts/renesas/salvator-common.dtsi

@@ -255,7 +255,6 @@
 &avb {
 	pinctrl-0 = <&avb_pins>;
 	pinctrl-names = "default";
-	renesas,no-ether-link;
 	phy-handle = <&phy0>;
 	status = "okay";
 

arch/arm64/boot/dts/renesas/ulcb.dtsi

@@ -145,7 +145,6 @@
 &avb {
 	pinctrl-0 = <&avb_pins>;
 	pinctrl-names = "default";
-	renesas,no-ether-link;
 	phy-handle = <&phy0>;
 	status = "okay";
 

arch/arm64/boot/dts/rockchip/rk3328-rock64.dts

@@ -132,6 +132,8 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>;
 	clock_in_out = "input";
+	/* shows instability at 1GBit right now */
+	max-speed = <100>;
 	phy-supply = <&vcc_io>;
 	phy-mode = "rgmii";
 	pinctrl-names = "default";

arch/arm64/boot/dts/rockchip/rk3328.dtsi

@@ -514,7 +514,7 @@
 	tsadc: tsadc@ff250000 {
 		compatible = "rockchip,rk3328-tsadc";
 		reg = <0x0 0xff250000 0x0 0x100>;
-		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>;
 		assigned-clocks = <&cru SCLK_TSADC>;
 		assigned-clock-rates = <50000>;
 		clocks = <&cru SCLK_TSADC>, <&cru PCLK_TSADC>;

arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi

@@ -155,17 +155,6 @@
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
 	};
-
-	vdd_log: vdd-log {
-		compatible = "pwm-regulator";
-		pwms = <&pwm2 0 25000 0>;
-		regulator-name = "vdd_log";
-		regulator-min-microvolt = <800000>;
-		regulator-max-microvolt = <1400000>;
-		regulator-always-on;
-		regulator-boot-on;
-		status = "okay";
-	};
 };
 
 &cpu_b0 {

arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi

@@ -198,8 +198,8 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-ranges = <&pinctrl 0 0 0>,
-				      <&pinctrl 96 0 0>,
-				      <&pinctrl 160 0 0>;
+				      <&pinctrl 104 0 0>,
+				      <&pinctrl 168 0 0>;
 			gpio-ranges-group-names = "gpio_range0",
 						  "gpio_range1",
 						  "gpio_range2";

arch/arm64/kvm/hyp/debug-sr.c

@@ -74,6 +74,9 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 {
 	u64 reg;
 
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
 	/* SPE present on this CPU? */
 	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
 						  ID_AA64DFR0_PMSVER_SHIFT))

arch/m32r/kernel/traps.c

@@ -122,7 +122,6 @@ void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
-EXPORT_SYMBOL(abort);
 
 void __init trap_init(void)
 {

arch/parisc/boot/compressed/misc.c

@@ -123,8 +123,8 @@ int puts(const char *s)
 	while ((nuline = strchr(s, '\n')) != NULL) {
 		if (nuline != s)
 			pdc_iodc_print(s, nuline - s);
-			pdc_iodc_print("\r\n", 2);
-			s = nuline + 1;
+		pdc_iodc_print("\r\n", 2);
+		s = nuline + 1;
 	}
 	if (*s != '\0')
 		pdc_iodc_print(s, strlen(s));

arch/parisc/include/asm/thread_info.h

@@ -35,7 +35,12 @@ struct thread_info {
 
 /* thread information allocation */
 
+#ifdef CONFIG_IRQSTACKS
+#define THREAD_SIZE_ORDER	2 /* PA-RISC requires at least 16k stack */
+#else
 #define THREAD_SIZE_ORDER	3 /* PA-RISC requires at least 32k stack */
+#endif
+
 /* Be sure to hunt all references to this down when you change the size of
  * the kernel stack */
 #define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)

arch/parisc/kernel/entry.S

@@ -878,9 +878,6 @@ ENTRY_CFI(syscall_exit_rfi)
 	STREG   %r19,PT_SR7(%r16)
 
 intr_return:
-	/* NOTE: Need to enable interrupts incase we schedule. */
-	ssm     PSW_SM_I, %r0
-
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
@@ -907,6 +904,11 @@ intr_check_sig:
 	LDREG	PT_IASQ1(%r16), %r20
 	cmpib,COND(=),n 0,%r20,intr_restore /* backward */
 
+	/* NOTE: We need to enable interrupts if we have to deliver
+	 * signals. We used to do this earlier but it caused kernel
+	 * stack overflows. */
+	ssm     PSW_SM_I, %r0
+
 	copy	%r0, %r25			/* long in_syscall = 0 */
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
@@ -958,6 +960,10 @@ intr_do_resched:
 	cmpib,COND(=)	0, %r20, intr_do_preempt
 	nop
 
+	/* NOTE: We need to enable interrupts if we schedule.  We used
+	 * to do this earlier but it caused kernel stack overflows. */
+	ssm     PSW_SM_I, %r0
+
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29		/* Reference param save area */
 #endif

arch/parisc/kernel/hpmc.S

@@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc)
 
 
 	__INITRODATA
+	.align 4
 	.export os_hpmc_size
 os_hpmc_size:
 	.word .os_hpmc_end-.os_hpmc

arch/parisc/kernel/unwind.c

@@ -15,7 +15,6 @@
 #include <linux/slab.h>
 #include <linux/kallsyms.h>
 #include <linux/sort.h>
-#include <linux/sched.h>
 
 #include <linux/uaccess.h>
 #include <asm/assembly.h>

arch/parisc/lib/delay.c

@@ -16,9 +16,7 @@
 #include <linux/preempt.h>
 #include <linux/init.h>
 
-#include <asm/processor.h>
 #include <asm/delay.h>
-
 #include <asm/special_insns.h>    /* for mfctl() */
 #include <asm/processor.h> /* for boot_cpu_data */
 

arch/powerpc/include/asm/mmu_context.h

@@ -160,9 +160,10 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 #endif
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 #ifndef CONFIG_PPC_BOOK3S_64

arch/powerpc/kernel/process.c

@@ -1403,7 +1403,7 @@ void show_regs(struct pt_regs * regs)
 
 	printk("NIP:  "REG" LR: "REG" CTR: "REG"\n",
 	       regs->nip, regs->link, regs->ctr);
-	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
+	printk("REGS: %px TRAP: %04lx   %s  (%s)\n",
 	       regs, regs->trap, print_tainted(), init_utsname()->release);
 	printk("MSR:  "REG" ", regs->msr);
 	print_msr_bits(regs->msr);

arch/powerpc/kvm/book3s_xive.c

@@ -725,7 +725,8 @@ u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
 
 	/* Return the per-cpu state for state saving/migration */
 	return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
-	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT |
+	       (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT;
 }
 
 int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
@@ -1558,7 +1559,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 
 	/*
 	 * Restore P and Q. If the interrupt was pending, we
-	 * force both P and Q, which will trigger a resend.
+	 * force Q and !P, which will trigger a resend.
 	 *
 	 * That means that a guest that had both an interrupt
 	 * pending (queued) and Q set will restore with only
@@ -1566,7 +1567,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	 * is perfectly fine as coalescing interrupts that haven't
 	 * been presented yet is always allowed.
 	 */
-	if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+	if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING))
 		state->old_p = true;
 	if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
 		state->old_q = true;

arch/powerpc/net/bpf_jit_comp64.c

@@ -763,7 +763,8 @@ emit_clear:
 			func = (u8 *) __bpf_call_base + imm;
 
 			/* Save skb pointer if we need to re-cache skb data */
-			if (bpf_helper_changes_pkt_data(func))
+			if ((ctx->seen & SEEN_SKB) &&
+			    bpf_helper_changes_pkt_data(func))
 				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
 
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -772,7 +773,8 @@ emit_clear:
 			PPC_MR(b2p[BPF_REG_0], 3);
 
 			/* refresh skb cache */
-			if (bpf_helper_changes_pkt_data(func)) {
+			if ((ctx->seen & SEEN_SKB) &&
+			    bpf_helper_changes_pkt_data(func)) {
 				/* reload skb pointer to r3 */
 				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
 				bpf_jit_emit_skb_loads(image, ctx);

arch/powerpc/perf/core-book3s.c

@@ -410,8 +410,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	int ret;
 	__u64 target;
 
-	if (is_kernel_addr(addr))
-		return branch_target((unsigned int *)addr);
+	if (is_kernel_addr(addr)) {
+		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+			return 0;
+
+		return branch_target(&instr);
+	}
 
 	/* Userspace: need copy instruction here then translate it */
 	pagefault_disable();

arch/powerpc/perf/imc-pmu.c

@@ -309,6 +309,19 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
 	if (!cpumask_test_and_clear_cpu(cpu, &nest_imc_cpumask))
 		return 0;
 
+	/*
+	 * Check whether nest_imc is registered. We could end up here if the
+	 * cpuhotplug callback registration fails. i.e, callback invokes the
+	 * offline path for all successfully registered nodes. At this stage,
+	 * nest_imc pmu will not be registered and we should return here.
+	 *
+	 * We return with a zero since this is not an offline failure. And
+	 * cpuhp_setup_state() returns the actual failure reason to the caller,
+	 * which in turn will call the cleanup routine.
+	 */
+	if (!nest_pmus)
+		return 0;
+
 	/*
 	 * Now that this cpu is one of the designated,
 	 * find a next cpu a) which is online and b) in same chip.
@@ -1171,6 +1184,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		if (nest_pmus == 1) {
 			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
 			kfree(nest_imc_refc);
+			kfree(per_nest_pmu_arr);
 		}
 
 		if (nest_pmus > 0)
@@ -1195,7 +1209,6 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
 	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
 	kfree(pmu_ptr);
-	kfree(per_nest_pmu_arr);
 	return;
 }
 
@@ -1309,6 +1322,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			ret = nest_pmu_cpumask_init();
 			if (ret) {
 				mutex_unlock(&nest_init_lock);
+				kfree(nest_imc_refc);
+				kfree(per_nest_pmu_arr);
 				goto err_free;
 			}
 		}

arch/powerpc/sysdev/fsl_msi.c

@@ -354,6 +354,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
 }
 
 static struct lock_class_key fsl_msi_irq_class;
+static struct lock_class_key fsl_msi_irq_request_class;
 
 static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 			       int offset, int irq_index)
@@ -373,7 +374,8 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 		dev_err(&dev->dev, "No memory for MSI cascade data\n");
 		return -ENOMEM;
 	}
-	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class);
+	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class,
+			      &fsl_msi_irq_request_class);
 	cascade_data->index = offset;
 	cascade_data->msi_data = msi;
 	cascade_data->virq = virt_msir;

arch/s390/lib/uaccess.c

@@ -89,11 +89,11 @@ EXPORT_SYMBOL(enable_sacf_uaccess);
 
 void disable_sacf_uaccess(mm_segment_t old_fs)
 {
+	current->thread.mm_segment = old_fs;
 	if (old_fs == USER_DS && test_facility(27)) {
 		__ctl_load(S390_lowcore.user_asce, 1, 1);
 		clear_cpu_flag(CIF_ASCE_PRIMARY);
 	}
-	current->thread.mm_segment = old_fs;
 }
 EXPORT_SYMBOL(disable_sacf_uaccess);
 

arch/s390/net/bpf_jit_comp.c

@@ -55,8 +55,7 @@ struct bpf_jit {
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
 #define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_SKB_CHANGE	64	/* code changes skb data */
-#define SEEN_REG_AX	128	/* code uses constant blinding */
+#define SEEN_REG_AX	64	/* code uses constant blinding */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -448,12 +447,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB)
+	if (jit->seen & SEEN_SKB) {
 		emit_load_skb_data_hlen(jit);
-	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
+	}
 }
 
 /*
@@ -983,8 +982,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if (bpf_helper_changes_pkt_data((void *)func)) {
-			jit->seen |= SEEN_SKB_CHANGE;
+		if ((jit->seen & SEEN_SKB) &&
+		    bpf_helper_changes_pkt_data((void *)func)) {
 			/* lg %b1,ST_OFF_SKBP(%r15) */
 			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
 				      REG_15, STK_OFF_SKBP);

arch/s390/pci/pci_dma.c

@@ -181,6 +181,9 @@ out_unlock:
 static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 			   size_t size, int flags)
 {
+	unsigned long irqflags;
+	int ret;
+
 	/*
 	 * With zdev->tlb_refresh == 0, rpcit is not required to establish new
 	 * translations when previously invalid translation-table entries are
@@ -196,8 +199,22 @@ static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 			return 0;
 	}
 
-	return zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
-				  PAGE_ALIGN(size));
+	ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
+				 PAGE_ALIGN(size));
+	if (ret == -ENOMEM && !s390_iommu_strict) {
+		/* enable the hypervisor to free some resources */
+		if (zpci_refresh_global(zdev))
+			goto out;
+
+		spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags);
+		bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap,
+			      zdev->lazy_bitmap, zdev->iommu_pages);
+		bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages);
+		spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags);
+		ret = 0;
+	}
+out:
+	return ret;
 }
 
 static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,

arch/s390/pci/pci_insn.c

@@ -89,6 +89,9 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 	if (cc)
 		zpci_err_insn(cc, status, addr, range);
 
+	if (cc == 1 && (status == 4 || status == 16))
+		return -ENOMEM;
+
 	return (cc) ? -EIO : 0;
 }
 

arch/sparc/lib/hweight.S

@@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32)
 	.previous
 
 ENTRY(__arch_hweight64)
-	sethi	%hi(__sw_hweight16), %g1
-	jmpl	%g1 + %lo(__sw_hweight16), %g0
+	sethi	%hi(__sw_hweight64), %g1
+	jmpl	%g1 + %lo(__sw_hweight64), %g0
 	 nop
 ENDPROC(__arch_hweight64)
 EXPORT_SYMBOL(__arch_hweight64)

arch/sparc/mm/fault_32.c

@@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
 	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 	       tsk->comm, task_pid_nr(tsk), address,
 	       (void *)regs->pc, (void *)regs->u_regs[UREG_I7],

arch/sparc/mm/fault_64.c

@@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
 	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 	       tsk->comm, task_pid_nr(tsk), address,
 	       (void *)regs->tpc, (void *)regs->u_regs[UREG_I7],

arch/sparc/net/bpf_jit_comp_64.c

@@ -1245,14 +1245,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		u8 *func = ((u8 *)__bpf_call_base) + imm;
 
 		ctx->saw_call = true;
+		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+			emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
 
 		emit_call((u32 *)func, ctx);
 		emit_nop(ctx);
 
 		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
 
-		if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind)
-			load_skb_regs(ctx, bpf2sparc[BPF_REG_6]);
+		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+			load_skb_regs(ctx, L7);
 		break;
 	}
 

arch/um/include/asm/mmu_context.h

@@ -15,9 +15,10 @@ extern void uml_setup_stubs(struct mm_struct *mm);
 /*
  * Needed since we do not use the asm-generic/mm_hooks.h:
  */
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	uml_setup_stubs(mm);
+	return 0;
 }
 extern void arch_exit_mmap(struct mm_struct *mm);
 static inline void arch_unmap(struct mm_struct *mm,

arch/um/kernel/trap.c

@@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs)
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
 		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 		tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
 		(void *)UPT_IP(regs), (void *)UPT_SP(regs),

arch/unicore32/include/asm/mmu_context.h

@@ -81,9 +81,10 @@ do { \
 	} \
 } while (0)
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 static inline void arch_unmap(struct mm_struct *mm,

arch/unicore32/kernel/traps.c

@@ -298,7 +298,6 @@ void abort(void)
 	/* if that doesn't kill us, halt */
 	panic("Oops failed to kill thread");
 }
-EXPORT_SYMBOL(abort);
 
 void __init trap_init(void)
 {

arch/x86/Kconfig

@@ -926,7 +926,8 @@ config MAXSMP
 config NR_CPUS
 	int "Maximum number of CPUs" if SMP && !MAXSMP
 	range 2 8 if SMP && X86_32 && !X86_BIGSMP
-	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+	range 2 64 if SMP && X86_32 && X86_BIGSMP
+	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
 	range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
 	default "1" if !SMP
 	default "8192" if MAXSMP

arch/x86/boot/compressed/pagetable.c

@@ -23,6 +23,9 @@
  */
 #undef CONFIG_AMD_MEM_ENCRYPT
 
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
 #include "misc.h"
 
 /* These actually do the work of building the kernel identity maps. */

arch/x86/boot/genimage.sh

@@ -80,39 +80,43 @@ genfdimage288() {
 	mcopy $FBZIMAGE w:linux
 }
 
-genisoimage() {
+geniso() {
 	tmp_dir=`dirname $FIMAGE`/isoimage
 	rm -rf $tmp_dir
 	mkdir $tmp_dir
-	for i in lib lib64 share end ; do
+	for i in lib lib64 share ; do
 		for j in syslinux ISOLINUX ; do
 			if [ -f /usr/$i/$j/isolinux.bin ] ; then
 				isolinux=/usr/$i/$j/isolinux.bin
-				cp $isolinux $tmp_dir
 			fi
 		done
 		for j in syslinux syslinux/modules/bios ; do
 			if [ -f /usr/$i/$j/ldlinux.c32 ]; then
 				ldlinux=/usr/$i/$j/ldlinux.c32
-				cp $ldlinux $tmp_dir
 			fi
 		done
 		if [ -n "$isolinux" -a -n "$ldlinux" ] ; then
 			break
 		fi
-		if [ $i = end -a -z "$isolinux" ] ; then
-			echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
-			exit 1
-		fi
 	done
+	if [ -z "$isolinux" ] ; then
+		echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
+		exit 1
+	fi
+	if [ -z "$ldlinux" ] ; then
+		echo 'Need an ldlinux.c32 file, please install syslinux/isolinux.'
+		exit 1
+	fi
+	cp $isolinux $tmp_dir
+	cp $ldlinux $tmp_dir
 	cp $FBZIMAGE $tmp_dir/linux
 	echo "$KCMDLINE" > $tmp_dir/isolinux.cfg
 	if [ -f "$FDINITRD" ] ; then
 		cp "$FDINITRD" $tmp_dir/initrd.img
 	fi
-	mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \
-		-c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \
-		$tmp_dir
+	genisoimage -J -r -input-charset=utf-8 -quiet -o $FIMAGE \
+		-b isolinux.bin -c boot.cat -no-emul-boot -boot-load-size 4 \
+		-boot-info-table $tmp_dir
 	isohybrid $FIMAGE 2>/dev/null || true
 	rm -rf $tmp_dir
 }
@@ -121,6 +125,6 @@ case $1 in
 	bzdisk)     genbzdisk;;
 	fdimage144) genfdimage144;;
 	fdimage288) genfdimage288;;
-	isoimage)   genisoimage;;
+	isoimage)   geniso;;
 	*)          echo 'Unknown image format'; exit 1;
 esac

arch/x86/entry/calling.h

@@ -1,6 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/jump_label.h>
 #include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
 
 /*
 
@@ -187,6 +192,146 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_SWITCH_PGTABLES_MASK	(1<<PAGE_SHIFT)
+#define PTI_SWITCH_MASK		(PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT))
+
+.macro SET_NOFLUSH_BIT	reg:req
+	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+	ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+	/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+	andq    $(~PTI_SWITCH_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	mov	%cr3, \scratch_reg
+	ADJUST_KERNEL_CR3 \scratch_reg
+	mov	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask   \
+	PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	mov	%cr3, \scratch_reg
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+	/*
+	 * Test if the ASID needs a flush.
+	 */
+	movq	\scratch_reg, \scratch_reg2
+	andq	$(0x7FF), \scratch_reg		/* mask ASID */
+	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jnc	.Lnoflush_\@
+
+	/* Flush needed, clear the bit */
+	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	movq	\scratch_reg2, \scratch_reg
+	jmp	.Lwrcr3_\@
+
+.Lnoflush_\@:
+	movq	\scratch_reg2, \scratch_reg
+	SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_\@:
+	/* Flip the PGD and ASID to the user version */
+	orq     $(PTI_SWITCH_MASK), \scratch_reg
+	mov	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK	scratch_reg:req
+	pushq	%rax
+	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+	popq	%rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+	ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+	movq	%cr3, \scratch_reg
+	movq	\scratch_reg, \save_reg
+	/*
+	 * Is the "switch mask" all zero?  That means that both of
+	 * these are zero:
+	 *
+	 *	1. The user/kernel PCID bit, and
+	 *	2. The user/kernel "bit" that points CR3 to the
+	 *	   bottom half of the 8k PGD
+	 *
+	 * That indicates a kernel CR3 value, not a user CR3.
+	 */
+	testq	$(PTI_SWITCH_MASK), \scratch_reg
+	jz	.Ldone_\@
+
+	ADJUST_KERNEL_CR3 \scratch_reg
+	movq	\scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+	/*
+	 * KERNEL pages can always resume with NOFLUSH as we do
+	 * explicit flushes.
+	 */
+	bt	$X86_CR3_PTI_SWITCH_BIT, \save_reg
+	jnc	.Lnoflush_\@
+
+	/*
+	 * Check if there's a pending flush for the user ASID we're
+	 * about to set.
+	 */
+	movq	\save_reg, \scratch_reg
+	andq	$(0x7FF), \scratch_reg
+	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jnc	.Lnoflush_\@
+
+	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jmp	.Lwrcr3_\@
+
+.Lnoflush_\@:
+	SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+	/*
+	 * The CR3 write could be avoided when not changing its value,
+	 * but would require a CR3 read *and* a scratch register.
+	 */
+	movq	\save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
 #endif /* CONFIG_X86_64 */
 
 /*

arch/x86/entry/entry_32.S

@@ -941,9 +941,10 @@ ENTRY(debug)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
 
 	TRACE_IRQS_OFF
@@ -984,9 +985,10 @@ ENTRY(nmi)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack
 
 	/* Not on SYSENTER stack. */

arch/x86/entry/entry_64.S

@@ -23,7 +23,6 @@
 #include <asm/segment.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
-#include "calling.h"
 #include <asm/asm-offsets.h>
 #include <asm/msr.h>
 #include <asm/unistd.h>
@@ -40,6 +39,8 @@
 #include <asm/frame.h>
 #include <linux/err.h>
 
+#include "calling.h"
+
 .code64
 .section .entry.text, "ax"
 
@@ -140,6 +141,67 @@ END(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
+	.pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline.  This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address).  So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline.  We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+	_entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH	CPU_ENTRY_AREA_entry_stack + \
+			SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+	UNWIND_HINT_EMPTY
+	swapgs
+
+	/* Stash the user RSP. */
+	movq	%rsp, RSP_SCRATCH
+
+	/* Note: using %rsp as a scratch reg. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+	/* Load the top of the task stack into RSP */
+	movq	CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+	/* Start building the simulated IRET frame. */
+	pushq	$__USER_DS			/* pt_regs->ss */
+	pushq	RSP_SCRATCH			/* pt_regs->sp */
+	pushq	%r11				/* pt_regs->flags */
+	pushq	$__USER_CS			/* pt_regs->cs */
+	pushq	%rcx				/* pt_regs->ip */
+
+	/*
+	 * x86 lacks a near absolute jump, and we can't jump to the real
+	 * entry text with a relative jump.  We could push the target
+	 * address and then use retq, but this destroys the pipeline on
+	 * many CPUs (wasting over 20 cycles on Sandy Bridge).  Instead,
+	 * spill RDI and restore it in a second-stage trampoline.
+	 */
+	pushq	%rdi
+	movq	$entry_SYSCALL_64_stage2, %rdi
+	jmp	*%rdi
+END(entry_SYSCALL_64_trampoline)
+
+	.popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+	UNWIND_HINT_EMPTY
+	popq	%rdi
+	jmp	entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
 ENTRY(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
 	/*
@@ -149,6 +211,10 @@ ENTRY(entry_SYSCALL_64)
 	 */
 
 	swapgs
+	/*
+	 * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+	 * is not required to switch CR3.
+	 */
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
@@ -330,8 +396,25 @@ syscall_return_via_sysret:
 	popq	%rsi	/* skip rcx */
 	popq	%rdx
 	popq	%rsi
+
+	/*
+	 * Now all regs are restored except RSP and RDI.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	pushq	RSP-RDI(%rdi)	/* RSP */
+	pushq	(%rdi)		/* RDI */
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
 	popq	%rdi
-	movq	RSP-ORIG_RAX(%rsp), %rsp
+	popq	%rsp
 	USERGS_SYSRET64
 END(entry_SYSCALL_64)
 
@@ -466,12 +549,13 @@ END(irq_entries_start)
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
-	pushfq
-	testl $X86_EFLAGS_IF, (%rsp)
+	pushq %rax
+	SAVE_FLAGS(CLBR_RAX)
+	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
 .Lokay_\@:
-	addq $8, %rsp
+	popq %rax
 #endif
 .endm
 
@@ -563,6 +647,13 @@ END(irq_entries_start)
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
 	cld
+
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jz	1f
+	SWAPGS
+	call	switch_to_thread_stack
+1:
+
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
@@ -572,12 +663,8 @@ END(irq_entries_start)
 	jz	1f
 
 	/*
-	 * IRQ from user mode.  Switch to kernel gsbase and inform context
-	 * tracking that we're in kernel mode.
-	 */
-	SWAPGS
-
-	/*
+	 * IRQ from user mode.
+	 *
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
 	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
@@ -630,10 +717,43 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	ud2
 1:
 #endif
-	SWAPGS
 	POP_EXTRA_REGS
-	POP_C_REGS
-	addq	$8, %rsp	/* skip regs->orig_ax */
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+
+	/*
+	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	/* Copy the IRET frame to the trampoline stack. */
+	pushq	6*8(%rdi)	/* SS */
+	pushq	5*8(%rdi)	/* RSP */
+	pushq	4*8(%rdi)	/* EFLAGS */
+	pushq	3*8(%rdi)	/* CS */
+	pushq	2*8(%rdi)	/* RIP */
+
+	/* Push user RDI on the trampoline stack. */
+	pushq	(%rdi)
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
+	/* Restore RDI. */
+	popq	%rdi
+	SWAPGS
 	INTERRUPT_RETURN
 
 
@@ -713,7 +833,9 @@ native_irq_return_ldt:
 	 */
 
 	pushq	%rdi				/* Stash user RDI */
-	SWAPGS
+	SWAPGS					/* to kernel GS */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
+
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
 	movq	%rax, (0*8)(%rdi)		/* user RAX */
 	movq	(1*8)(%rsp), %rax		/* user RIP */
@@ -729,7 +851,6 @@ native_irq_return_ldt:
 	/* Now RAX == RSP. */
 
 	andl	$0xffff0000, %eax		/* RAX = (RSP & 0xffff0000) */
-	popq	%rdi				/* Restore user RDI */
 
 	/*
 	 * espfix_stack[31:16] == 0.  The page tables are set up such that
@@ -740,7 +861,11 @@ native_irq_return_ldt:
 	 * still points to an RO alias of the ESPFIX stack.
 	 */
 	orq	PER_CPU_VAR(espfix_stack), %rax
-	SWAPGS
+
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+	SWAPGS					/* to user GS */
+	popq	%rdi				/* Restore user RDI */
+
 	movq	%rax, %rsp
 	UNWIND_HINT_IRET_REGS offset=8
 
@@ -829,7 +954,35 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+/*
+ * Switch to the thread stack.  This is called with the IRET frame and
+ * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+ENTRY(switch_to_thread_stack)
+	UNWIND_HINT_FUNC
+
+	pushq	%rdi
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
+	ret
+END(switch_to_thread_stack)
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
@@ -848,11 +1001,12 @@ ENTRY(\sym)
 
 	ALLOC_PT_GPREGS_ON_STACK
 
-	.if \paranoid
-	.if \paranoid == 1
+	.if \paranoid < 2
 	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
-	jnz	1f
+	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
+
+	.if \paranoid
 	call	paranoid_entry
 	.else
 	call	error_entry
@@ -894,20 +1048,15 @@ ENTRY(\sym)
 	jmp	error_exit
 	.endif
 
-	.if \paranoid == 1
+	.if \paranoid < 2
 	/*
-	 * Paranoid entry from userspace.  Switch stacks and treat it
+	 * Entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers
 	 * run in real process context if user_mode(regs).
 	 */
-1:
+.Lfrom_usermode_switch_stack_\@:
 	call	error_entry
 
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-	call	sync_regs
-	movq	%rax, %rsp			/* switch stack */
-
 	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
@@ -1119,7 +1268,11 @@ ENTRY(paranoid_entry)
 	js	1f				/* negative -> in kernel */
 	SWAPGS
 	xorl	%ebx, %ebx
-1:	ret
+
+1:
+	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+	ret
 END(paranoid_entry)
 
 /*
@@ -1141,6 +1294,7 @@ ENTRY(paranoid_exit)
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	.Lparanoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
+	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
 	jmp	.Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
@@ -1168,8 +1322,18 @@ ENTRY(error_entry)
 	 * from user mode due to an IRET fault.
 	 */
 	SWAPGS
+	/* We have user CR3.  Change to kernel CR3. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 .Lerror_entry_from_usermode_after_swapgs:
+	/* Put us onto the real thread stack. */
+	popq	%r12				/* save return addr in %12 */
+	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
+	call	sync_regs
+	movq	%rax, %rsp			/* switch stack */
+	ENCODE_FRAME_POINTER
+	pushq	%r12
+
 	/*
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
@@ -1206,6 +1370,7 @@ ENTRY(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	jmp .Lerror_entry_done
 
 .Lbstep_iret:
@@ -1215,10 +1380,11 @@ ENTRY(error_entry)
 
 .Lerror_bad_iret:
 	/*
-	 * We came from an IRET to user mode, so we have user gsbase.
-	 * Switch to kernel gsbase:
+	 * We came from an IRET to user mode, so we have user
+	 * gsbase and CR3.  Switch to kernel gsbase and CR3:
 	 */
 	SWAPGS
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
@@ -1250,6 +1416,10 @@ END(error_exit)
 /*
  * Runs on exception stack.  Xen PV does not go through this path at all,
  * so we can use real assembly here.
+ *
+ * Registers:
+ *	%r14: Used to save/restore the CR3 of the interrupted context
+ *	      when PAGE_TABLE_ISOLATION is in use.  Do not clobber.
  */
 ENTRY(nmi)
 	UNWIND_HINT_IRET_REGS
@@ -1313,6 +1483,7 @@ ENTRY(nmi)
 
 	swapgs
 	cld
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1565,6 +1736,8 @@ end_repeat_nmi:
 	movq	$-1, %rsi
 	call	do_nmi
 
+	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	nmi_restore
 nmi_swapgs:

arch/x86/entry/entry_64_compat.S

@@ -48,7 +48,11 @@
  */
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
-	SWAPGS_UNSAFE_STACK
+	SWAPGS
+
+	/* We are about to clobber %rsp anyway, clobbering here is OK */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/*
@@ -186,8 +190,13 @@ ENTRY(entry_SYSCALL_compat)
 	/* Interrupts are off on entry. */
 	swapgs
 
-	/* Stash user ESP and switch to the kernel stack. */
+	/* Stash user ESP */
 	movl	%esp, %r8d
+
+	/* Use %rsp as scratch reg. User ESP is stashed in r8 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+	/* Switch to the kernel stack */
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
@@ -256,10 +265,22 @@ sysret32_from_system_call:
 	 * when the system call started, which is already known to user
 	 * code.  We zero R8-R10 to avoid info leaks.
          */
+	movq	RSP-ORIG_RAX(%rsp), %rsp
+
+	/*
+	 * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+	 * on the process stack which is not mapped to userspace and
+	 * not readable after we SWITCH_TO_USER_CR3.  Delay the CR3
+	 * switch until after after the last reference to the process
+	 * stack.
+	 *
+	 * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+	 */
+	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
 	xorq	%r8, %r8
 	xorq	%r9, %r9
 	xorq	%r10, %r10
-	movq	RSP-ORIG_RAX(%rsp), %rsp
 	swapgs
 	sysretl
 END(entry_SYSCALL_compat)
@@ -306,8 +327,11 @@ ENTRY(entry_INT80_compat)
 	 */
 	movl	%eax, %eax
 
-	/* Construct struct pt_regs on stack (iret frame is already on stack) */
 	pushq	%rax			/* pt_regs->orig_ax */
+
+	/* switch to thread stack expects orig_ax to be pushed */
+	call	switch_to_thread_stack
+
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -37,6 +37,7 @@
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/traps.h>
+#include <asm/paravirt.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
@@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
+	/* This should be unreachable in NATIVE mode. */
+	if (WARN_ON(vsyscall_mode == NATIVE))
+		return false;
+
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -329,16 +334,47 @@ int in_gate_area_no_mm(unsigned long addr)
 	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present.  If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+	p4d->p4d |= _PAGE_USER;
+#endif
+	pud = pud_offset(p4d, VSYSCALL_ADDR);
+	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+	pmd = pmd_offset(pud, VSYSCALL_ADDR);
+	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
 void __init map_vsyscall(void)
 {
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	if (vsyscall_mode != NONE)
+	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 			     vsyscall_mode == NATIVE
 			     ? PAGE_KERNEL_VSYSCALL
 			     : PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+	}
 
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);

arch/x86/events/intel/core.c

@@ -3847,6 +3847,8 @@ static struct attribute *intel_pmu_attrs[] = {
 
 __init int intel_pmu_init(void)
 {
+	struct attribute **extra_attr = NULL;
+	struct attribute **to_free = NULL;
 	union cpuid10_edx edx;
 	union cpuid10_eax eax;
 	union cpuid10_ebx ebx;
@@ -3854,7 +3856,6 @@ __init int intel_pmu_init(void)
 	unsigned int unused;
 	struct extra_reg *er;
 	int version, i;
-	struct attribute **extra_attr = NULL;
 	char *name;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
@@ -4294,6 +4295,7 @@ __init int intel_pmu_init(void)
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
 		extra_attr = merge_attr(extra_attr, skl_format_attr);
+		to_free = extra_attr;
 		x86_pmu.cpu_events = get_hsw_events_attrs();
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
@@ -4401,6 +4403,7 @@ __init int intel_pmu_init(void)
 		pr_cont("full-width counters, ");
 	}
 
+	kfree(to_free);
 	return 0;
 }
 

arch/x86/events/intel/ds.c

@@ -3,16 +3,19 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/perf_event.h>
+#include <asm/tlbflush.h>
 #include <asm/insn.h>
 
 #include "../perf_event.h"
 
+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
 
-#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -279,17 +282,67 @@ void fini_debug_store_on_cpu(int cpu)
 
 static DEFINE_PER_CPU(void *, insn_buffer);
 
-static int alloc_pebs_buffer(int cpu)
+static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	unsigned long start = (unsigned long)cea;
+	phys_addr_t pa;
+	size_t msz = 0;
+
+	pa = virt_to_phys(addr);
+
+	preempt_disable();
+	for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
+		cea_set_pte(cea, pa, prot);
+
+	/*
+	 * This is a cross-CPU update of the cpu_entry_area, we must shoot down
+	 * all TLB entries for it.
+	 */
+	flush_tlb_kernel_range(start, start + size);
+	preempt_enable();
+}
+
+static void ds_clear_cea(void *cea, size_t size)
+{
+	unsigned long start = (unsigned long)cea;
+	size_t msz = 0;
+
+	preempt_disable();
+	for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
+		cea_set_pte(cea, 0, PAGE_NONE);
+
+	flush_tlb_kernel_range(start, start + size);
+	preempt_enable();
+}
+
+static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
+{
+	unsigned int order = get_order(size);
 	int node = cpu_to_node(cpu);
-	int max;
-	void *buffer, *ibuffer;
+	struct page *page;
+
+	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+	return page ? page_address(page) : NULL;
+}
+
+static void dsfree_pages(const void *buffer, size_t size)
+{
+	if (buffer)
+		free_pages((unsigned long)buffer, get_order(size));
+}
+
+static int alloc_pebs_buffer(int cpu)
+{
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	size_t bsiz = x86_pmu.pebs_buffer_size;
+	int max, node = cpu_to_node(cpu);
+	void *buffer, *ibuffer, *cea;
 
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -300,25 +353,27 @@ static int alloc_pebs_buffer(int cpu)
 	if (x86_pmu.intel_cap.pebs_format < 2) {
 		ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
 		if (!ibuffer) {
-			kfree(buffer);
+			dsfree_pages(buffer, bsiz);
 			return -ENOMEM;
 		}
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
-
-	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
-
-	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+	hwev->ds_pebs_vaddr = buffer;
+	/* Update the cpu entry area mapping */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+	ds->pebs_buffer_base = (unsigned long) cea;
+	ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
 	ds->pebs_index = ds->pebs_buffer_base;
-	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
-		max * x86_pmu.pebs_record_size;
-
+	max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
+	ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
 	return 0;
 }
 
 static void release_pebs_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *cea;
 
 	if (!ds || !x86_pmu.pebs)
 		return;
@@ -326,73 +381,70 @@ static void release_pebs_buffer(int cpu)
 	kfree(per_cpu(insn_buffer, cpu));
 	per_cpu(insn_buffer, cpu) = NULL;
 
-	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	/* Clear the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+	ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
 	ds->pebs_buffer_base = 0;
+	dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
+	hwev->ds_pebs_vaddr = NULL;
 }
 
 static int alloc_bts_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	int node = cpu_to_node(cpu);
-	int max, thresh;
-	void *buffer;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *buffer, *cea;
+	int max;
 
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
 	if (unlikely(!buffer)) {
 		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
 	}
-
-	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
-	thresh = max / 16;
-
-	ds->bts_buffer_base = (u64)(unsigned long)buffer;
+	hwev->ds_bts_vaddr = buffer;
+	/* Update the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+	ds->bts_buffer_base = (unsigned long) cea;
+	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	ds->bts_absolute_maximum = ds->bts_buffer_base +
-		max * BTS_RECORD_SIZE;
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
-		thresh * BTS_RECORD_SIZE;
-
+	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
 	return 0;
 }
 
 static void release_bts_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *cea;
 
 	if (!ds || !x86_pmu.bts)
 		return;
 
-	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	/* Clear the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+	ds_clear_cea(cea, BTS_BUFFER_SIZE);
 	ds->bts_buffer_base = 0;
+	dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
+	hwev->ds_bts_vaddr = NULL;
 }
 
 static int alloc_ds_buffer(int cpu)
 {
-	int node = cpu_to_node(cpu);
-	struct debug_store *ds;
-
-	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
-	if (unlikely(!ds))
-		return -ENOMEM;
+	struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;
 
+	memset(ds, 0, sizeof(*ds));
 	per_cpu(cpu_hw_events, cpu).ds = ds;
-
 	return 0;
 }
 
 static void release_ds_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-	if (!ds)
-		return;
-
 	per_cpu(cpu_hw_events, cpu).ds = NULL;
-	kfree(ds);
 }
 
 void release_ds_buffers(void)

arch/x86/events/perf_event.h

@@ -14,6 +14,8 @@
 
 #include <linux/perf_event.h>
 
+#include <asm/intel_ds.h>
+
 /* To enable MSR tracing please use the generic trace points. */
 
 /*
@@ -77,8 +79,6 @@ struct amd_nb {
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS		8
 #define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
 
 /*
@@ -95,23 +95,6 @@ struct amd_nb {
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
 
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
-	u64	bts_buffer_base;
-	u64	bts_index;
-	u64	bts_absolute_maximum;
-	u64	bts_interrupt_threshold;
-	u64	pebs_buffer_base;
-	u64	pebs_index;
-	u64	pebs_absolute_maximum;
-	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
-};
-
 #define PEBS_REGS \
 	(PERF_REG_X86_AX | \
 	 PERF_REG_X86_BX | \
@@ -216,6 +199,8 @@ struct cpu_hw_events {
 	 * Intel DebugStore bits
 	 */
 	struct debug_store	*ds;
+	void			*ds_pebs_vaddr;
+	void			*ds_bts_vaddr;
 	u64			pebs_enabled;
 	int			n_pebs;
 	int			n_large_pebs;

arch/x86/include/asm/alternative.h

@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
-	".popsection"
+	".popsection\n"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
 	OLDINSTR_2(oldinstr, 1, 2)					\
@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
-	".popsection"
+	".popsection\n"
 
 /*
  * Alternative instructions for different CPU types or capabilities.

arch/x86/include/asm/cpu_entry_area.h

@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+#include <asm/intel_ds.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code.  Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below entry_stack and thus serves (on x86_64) as
+	 * a a read-only guard page.
+	 */
+	struct entry_stack_page entry_stack_page;
+
+	/*
+	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
+	 * we need task switches to work, and task switches write to the TSS.
+	 */
+	struct tss_struct tss;
+
+	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+	/*
+	 * Per CPU debug store for Intel performance monitoring. Wastes a
+	 * full page at the moment.
+	 */
+	struct debug_store cpu_debug_store;
+	/*
+	 * The actual PEBS/BTS buffers must be mapped to user space
+	 * 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)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#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)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif

arch/x86/include/asm/cpufeature.h

@@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().

arch/x86/include/asm/cpufeatures.h

@@ -197,11 +197,12 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
@@ -340,5 +341,6 @@
 #define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/desc.h

@@ -7,6 +7,7 @@
 #include <asm/mmu.h>
 #include <asm/fixmap.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
@@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	desc->type		= (info->read_exec_only ^ 1) << 1;
 	desc->type	       |= info->contents << 2;
+	/* Set the ACCESS bit so it can be mapped RO */
+	desc->type	       |= 1;
 
 	desc->s			= 1;
 	desc->dpl		= 0x3;
@@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
 	return this_cpu_ptr(&gdt_page)->gdt;
 }
 
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
-	return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
 /* Provide the fixmap address of the remapped GDT */
 static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
 {
-	unsigned int idx = get_cpu_gdt_ro_index(cpu);
-	return (struct desc_struct *)__fix_to_virt(idx);
+	return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
 }
 
 /* Provide the current read-only GDT */
@@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
 #endif
 }
 
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
 {
 	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;

arch/x86/include/asm/disabled-features.h

@@ -50,6 +50,12 @@
 # define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI		0
+#else
+# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -60,7 +66,7 @@
 #define DISABLED_MASK4	(DISABLE_PCID)
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
-#define DISABLED_MASK7	0
+#define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_MPX)
 #define DISABLED_MASK10	0

arch/x86/include/asm/espfix.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ESPFIX_H
 #define _ASM_X86_ESPFIX_H
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
 
 #include <asm/percpu.h>
 
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
 extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
 
 #endif /* _ASM_X86_ESPFIX_H */

arch/x86/include/asm/fixmap.h

@@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP;
 			 PAGE_SIZE)
 #endif
 
-
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
@@ -84,7 +83,6 @@ enum fixed_addresses {
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 #endif
-	FIX_RO_IDT,	/* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,6 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
-	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_GDT_REMAP_BEGIN,
-	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
 
 #ifdef CONFIG_ACPI_APEI_GHES
 	/* Used for GHES mapping from assorted contexts */
@@ -143,7 +138,7 @@ enum fixed_addresses {
 extern void reserve_top_address(unsigned long reserve);
 
 #define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
 
 extern int fixmaps_set;
 

arch/x86/include/asm/hypervisor.h

@@ -20,16 +20,7 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
-#ifdef CONFIG_HYPERVISOR_GUEST
-
-#include <asm/kvm_para.h>
-#include <asm/x86_init.h>
-#include <asm/xen/hypervisor.h>
-
-/*
- * x86 hypervisor information
- */
-
+/* x86 hypervisor types  */
 enum x86_hypervisor_type {
 	X86_HYPER_NATIVE = 0,
 	X86_HYPER_VMWARE,
@@ -39,6 +30,12 @@ enum x86_hypervisor_type {
 	X86_HYPER_KVM,
 };
 
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/x86_init.h>
+#include <asm/xen/hypervisor.h>
+
 struct hypervisor_x86 {
 	/* Hypervisor name */
 	const char	*name;
@@ -58,7 +55,15 @@ struct hypervisor_x86 {
 
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return x86_hyper_type == type;
+}
 #else
 static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return type == X86_HYPER_NATIVE;
+}
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */

arch/x86/include/asm/intel_ds.h

@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS		8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+	char	bts_buffer[BTS_BUFFER_SIZE];
+	char	pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif

arch/x86/include/asm/invpcid.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */

arch/x86/include/asm/irqdomain.h

@@ -44,7 +44,7 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs);
 extern int mp_irqdomain_activate(struct irq_domain *domain,
-				 struct irq_data *irq_data, bool early);
+				 struct irq_data *irq_data, bool reserve);
 extern void mp_irqdomain_deactivate(struct irq_domain *domain,
 				    struct irq_data *irq_data);
 extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);

arch/x86/include/asm/irqflags.h

@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
 	swapgs;					\
 	sysretl
 
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x)		pushfq; popq %rax
+#endif
 #else
 #define INTERRUPT_RETURN		iret
 #define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit

arch/x86/include/asm/kdebug.h

@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 

arch/x86/include/asm/mmu.h

@@ -3,6 +3,7 @@
 #define _ASM_X86_MMU_H
 
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 
@@ -27,7 +28,8 @@ typedef struct {
 	atomic64_t tlb_gen;
 
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
-	struct ldt_struct *ldt;
+	struct rw_semaphore	ldt_usr_sem;
+	struct ldt_struct	*ldt;
 #endif
 
 #ifdef CONFIG_X86_64

arch/x86/include/asm/mmu_context.h

@@ -50,22 +50,53 @@ struct ldt_struct {
 	 * call gates.  On native, we could merge the ldt_struct and LDT
 	 * allocations, but it's not worth trying to optimize.
 	 */
-	struct desc_struct *entries;
-	unsigned int nr_entries;
+	struct desc_struct	*entries;
+	unsigned int		nr_entries;
+
+	/*
+	 * If PTI is in use, then the entries array is not mapped while we're
+	 * in user mode.  The whole array will be aliased at the addressed
+	 * given by ldt_slot_va(slot).  We use two slots so that we can allocate
+	 * and map, and enable a new LDT without invalidating the mapping
+	 * of an older, still-in-use LDT.
+	 *
+	 * slot will be -1 if this LDT doesn't have an alias mapping.
+	 */
+	int			slot;
 };
 
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+	BUG();
+#endif
+}
+
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+	mm->context.ldt = NULL;
+	init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
 void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
-				       struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
 #endif
 
 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -90,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 	 * that we can see.
 	 */
 
-	if (unlikely(ldt))
-		set_ldt(ldt->entries, ldt->nr_entries);
-	else
+	if (unlikely(ldt)) {
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+				/*
+				 * Whoops -- either the new LDT isn't mapped
+				 * (if slot == -1) or is mapped into a bogus
+				 * slot (if slot > 1).
+				 */
+				clear_LDT();
+				return;
+			}
+
+			/*
+			 * If page table isolation is enabled, ldt->entries
+			 * will not be mapped in the userspace pagetables.
+			 * Tell the CPU to access the LDT through the alias
+			 * at ldt_slot_va(ldt->slot).
+			 */
+			set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+		} else {
+			set_ldt(ldt->entries, ldt->nr_entries);
+		}
+	} else {
 		clear_LDT();
+	}
 #else
 	clear_LDT();
 #endif
@@ -132,18 +184,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mutex_init(&mm->context.lock);
+
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
 
-	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
 	}
-	#endif
-	return init_new_context_ldt(tsk, mm);
+#endif
+	init_new_context_ldt(mm);
+	return 0;
 }
 static inline void destroy_context(struct mm_struct *mm)
 {
@@ -176,15 +231,16 @@ do {						\
 } while (0)
 #endif
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	paravirt_arch_dup_mmap(oldmm, mm);
+	return ldt_dup_context(oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 	paravirt_arch_exit_mmap(mm);
+	ldt_arch_exit_mmap(mm);
 }
 
 #ifdef CONFIG_X86_64
@@ -281,33 +337,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	return __pkru_allows_pkey(vma_pkey(vma), write);
 }
 
-/*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits.  This serves two purposes.  It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero.  It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
-	if (static_cpu_has(X86_FEATURE_PCID)) {
-		VM_WARN_ON_ONCE(asid > 4094);
-		return __sme_pa(mm->pgd) | (asid + 1);
-	} else {
-		VM_WARN_ON_ONCE(asid != 0);
-		return __sme_pa(mm->pgd);
-	}
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
-	VM_WARN_ON_ONCE(asid > 4094);
-	return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
 /*
  * This can be used from process context to figure out what the value of
  * CR3 is without needing to do a (slow) __read_cr3().
@@ -317,7 +346,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
  */
 static inline unsigned long __get_current_cr3_fast(void)
 {
-	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
 		this_cpu_read(cpu_tlbstate.loaded_mm_asid));
 
 	/* For now, be very restrictive about when this can be called. */

arch/x86/include/asm/paravirt.h

@@ -927,6 +927,15 @@ extern void default_banner(void);
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
 		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers)                                        \
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
 #endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */

arch/x86/include/asm/pgalloc.h

@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
  */
 extern gfp_t __userpte_alloc_gfp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
+ * both 8k in size and 8k-aligned.  That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
 /*
  * Allocate and free page tables.
  */

arch/x86/include/asm/pgtable.h

@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
@@ -841,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 
 static inline int p4d_bad(p4d_t p4d)
 {
-	return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+	unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (p4d_flags(p4d) & ~ignore_flags) != 0;
 }
 #endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
@@ -875,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	unsigned long ignore_flags = _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
@@ -904,7 +915,11 @@ static inline int pgd_none(pgd_t pgd)
  * pgd_offset() returns a (pgd_t *)
  * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
  */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
 /*
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
@@ -1106,7 +1121,14 @@ static inline int pud_write(pud_t pud)
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+	/* Clone the user space pgd as well */
+	memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+	       count * sizeof(pgd_t));
+#endif
 }
 
 #define PTE_SHIFT ilog2(PTRS_PER_PTE)

arch/x86/include/asm/pgtable_32_types.h

@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
+/*
+ * 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_BASE				\
+	((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START

arch/x86/include/asm/pgtable_64.h

@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif
+
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+	p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
 	*p4dp = p4d;
+#endif
 }
 
 static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	*pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
 	*pgdp = pgd;
+#endif
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)

arch/x86/include/asm/pgtable_64_types.h

@@ -75,33 +75,52 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+/*
+ * See Documentation/x86/x86_64/mm.txt for a description of the memory map.
+ *
+ * Be very careful vs. KASLR when changing anything here. The KASLR address
+ * range must not overlap with anything except the KASAN shadow area, which
+ * is correct as KASAN disables KASLR.
+ */
+#define MAXMEM			_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
 #ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(12800, UL)
+# define __VMALLOC_BASE		_AC(0xffa0000000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-112, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #else
-#define VMALLOC_SIZE_TB	_AC(32, UL)
-#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(32, UL)
+# define __VMALLOC_BASE		_AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-3, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START	vmalloc_base
-#define VMEMMAP_START	vmemmap_base
+# define VMALLOC_START		vmalloc_base
+# define VMEMMAP_START		vmemmap_base
 #else
-#define VMALLOC_START	__VMALLOC_BASE
-#define VMEMMAP_START	__VMEMMAP_BASE
+# define VMALLOC_START		__VMALLOC_BASE
+# define VMEMMAP_START		__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END		(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
-#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
+#define MODULES_END		_AC(0xffffffffff000000, UL)
+#define MODULES_LEN		(MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY	_AC(-2, UL)
+#define ESPFIX_BASE_ADDR	(ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD	_AC(-4, UL)
+#define CPU_ENTRY_AREA_BASE	(CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START		( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END		(-68 * (_AC(1, UL) << 30))
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64