Merge branch 'linux-linaro-lsk-v4.4' into linux-linaro-lsk-v4.4-android

* linux-linaro-lsk-v4.4: (783 commits) Linux 4.4.159 iw_cxgb4: only allow 1 flush on user qps HID: sony: Support DS4 dongle HID: sony: Update device ids arm64: Add trace_hardirqs_off annotation in ret_to_user ext4: don't mark mmp buffer head dirty ext4: fix online resizing for bigalloc file systems with a 1k block size ext4: fix online resize's handling of a too-small final block group ext4: recalucate superblock checksum after updating free blocks/inodes ext4: avoid divide by zero fault when deleting corrupted inline directories tty: vt_ioctl: fix potential Spectre v1 drm/nouveau/drm/nouveau: Use pm_runtime_get_noresume() in connector_detect() ocfs2: fix ocfs2 read block panic scsi: target: iscsi: Use hex2bin instead of a re-implementation neighbour: confirm neigh entries when ARP packet is received net: hp100: fix always-true check for link up state net/appletalk: fix minor pointer leak to userspace in SIOCFINDIPDDPRT ipv6: fix possible use-after-free in ip6_xmit() gso_segment: Reset skb->mac_len after modifying network header mm: shmem.c: Correctly annotate new inodes for lockdep ... Conflicts: Makefile fs/squashfs/block.c include/uapi/linux/prctl.h kernel/fork.c kernel/sys.c Trivial merge conflicts in above files. Resolved by rebasing corresponding AOSP changes. arch/arm64/mm/init.c Pick the changes from upstream version of AOSP patch "arm64: check for upper PAGE_SHIFT bits in pfn_valid" instead. Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
2026-03-25 03:50:24 +09:00 · 2018-10-03 13:37:01 +05:30
parent d36d92bca7 c6ee9e74b2
commit c8f435d8fd
685 changed files with 6817 additions and 2591 deletions
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -276,6 +276,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/meltdown
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
+		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -25,7 +25,7 @@ o  GNU C                  3.2                     # gcc --version
 o  GNU make               3.80                    # make --version
 o  binutils               2.12                    # ld -v
 o  util-linux             2.10o                   # fdformat --version
-o  module-init-tools      0.9.10                  # depmod -V
+o  kmod                   13                      # depmod -V
 o  e2fsprogs              1.41.4                  # e2fsck -V
 o  jfsutils               1.1.3                   # fsck.jfs -V
 o  reiserfsprogs          3.6.3                   # reiserfsck -V
@@ -132,12 +132,6 @@ is not build with CONFIG_KALLSYMS and you have no way to rebuild and
 reproduce the Oops with that option, then you can still decode that Oops
 with ksymoops.

-Module-Init-Tools
-----------------
-
-A new module loader is now in the kernel that requires module-init-tools
-to use.  It is backward compatible with the 2.4.x series kernels.
-
 Mkinitrd
 --------

@@ -319,14 +313,15 @@ Util-linux
 ----------
 o  <ftp://ftp.kernel.org/pub/linux/utils/util-linux/>

+Kmod
+----
+o  <https://www.kernel.org/pub/linux/utils/kernel/kmod/>
+o  <https://git.kernel.org/pub/scm/utils/kernel/kmod/kmod.git>
+
 Ksymoops
 --------
 o  <ftp://ftp.kernel.org/pub/linux/utils/kernel/ksymoops/v2.4/>

-Module-Init-Tools
-----------------
-o  <ftp://ftp.kernel.org/pub/linux/kernel/people/rusty/modules/>
-
 Mkinitrd
 --------
 o  <https://code.launchpad.net/initrd-tools/main>
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2520,6 +2520,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			allow data leaks with this option, which is equivalent
 			to spectre_v2=off.

+	nospec_store_bypass_disable
+			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -3687,6 +3690,48 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Not specifying this option is equivalent to
 			spectre_v2=auto.

+	spec_store_bypass_disable=
+			[HW] Control Speculative Store Bypass (SSB) Disable mitigation
+			(Speculative Store Bypass vulnerability)
+
+			Certain CPUs are vulnerable to an exploit against a
+			a common industry wide performance optimization known
+			as "Speculative Store Bypass" in which recent stores
+			to the same memory location may not be observed by
+			later loads during speculative execution. The idea
+			is that such stores are unlikely and that they can
+			be detected prior to instruction retirement at the
+			end of a particular speculation execution window.
+
+			In vulnerable processors, the speculatively forwarded
+			store can be used in a cache side channel attack, for
+			example to read memory to which the attacker does not
+			directly have access (e.g. inside sandboxed code).
+
+			This parameter controls whether the Speculative Store
+			Bypass optimization is used.
+
+			on      - Unconditionally disable Speculative Store Bypass
+			off     - Unconditionally enable Speculative Store Bypass
+			auto    - Kernel detects whether the CPU model contains an
+				  implementation of Speculative Store Bypass and
+				  picks the most appropriate mitigation. If the
+				  CPU is not vulnerable, "off" is selected. If the
+				  CPU is vulnerable the default mitigation is
+				  architecture and Kconfig dependent. See below.
+			prctl   - Control Speculative Store Bypass per thread
+				  via prctl. Speculative Store Bypass is enabled
+				  for a process by default. The state of the control
+				  is inherited on fork.
+			seccomp - Same as "prctl" above, but all seccomp threads
+				  will disable SSB unless they explicitly opt out.
+
+			Not specifying this option is equivalent to
+			spec_store_bypass_disable=auto.
+
+			Default mitigations:
+			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
--- a/Documentation/spec_ctrl.txt
+++ b/Documentation/spec_ctrl.txt
@@ -0,0 +1,94 @@
+===================
+Speculation Control
+===================
+
+Quite some CPUs have speculation-related misfeatures which are in
+fact vulnerabilities causing data leaks in various forms even across
+privilege domains.
+
+The kernel provides mitigation for such vulnerabilities in various
+forms. Some of these mitigations are compile-time configurable and some
+can be supplied on the kernel command line.
+
+There is also a class of mitigations which are very expensive, but they can
+be restricted to a certain set of processes or tasks in controlled
+environments. The mechanism to control these mitigations is via
+:manpage:`prctl(2)`.
+
+There are two prctl options which are related to this:
+
+ * PR_GET_SPECULATION_CTRL
+
+ * PR_SET_SPECULATION_CTRL
+
+PR_GET_SPECULATION_CTRL
+-----------------------
+
+PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
+which is selected with arg2 of prctl(2). The return value uses bits 0-3 with
+the following meaning:
+
+==== ===================== ===================================================
+Bit  Define                Description
+==== ===================== ===================================================
+0    PR_SPEC_PRCTL         Mitigation can be controlled per task by
+                           PR_SET_SPECULATION_CTRL.
+1    PR_SPEC_ENABLE        The speculation feature is enabled, mitigation is
+                           disabled.
+2    PR_SPEC_DISABLE       The speculation feature is disabled, mitigation is
+                           enabled.
+3    PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
+                           subsequent prctl(..., PR_SPEC_ENABLE) will fail.
+==== ===================== ===================================================
+
+If all bits are 0 the CPU is not affected by the speculation misfeature.
+
+If PR_SPEC_PRCTL is set, then the per-task control of the mitigation is
+available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
+misfeature will fail.
+
+PR_SET_SPECULATION_CTRL
+-----------------------
+
+PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
+is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or
+PR_SPEC_FORCE_DISABLE.
+
+Common error codes
+------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+EINVAL  The prctl is not implemented by the architecture or unused
+        prctl(2) arguments are not 0.
+
+ENODEV  arg2 is selecting a not supported speculation misfeature.
+======= =================================================================
+
+PR_SET_SPECULATION_CTRL error codes
+-----------------------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+0       Success
+
+ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
+        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE.
+
+ENXIO   Control of the selected speculation misfeature is not possible.
+        See PR_GET_SPECULATION_CTRL.
+
+EPERM   Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller
+        tried to enable it again.
+======= =================================================================
+
+Speculation misfeature controls
+-------------------------------
+- PR_SPEC_STORE_BYPASS: Speculative Store Bypass
+
+  Invocations:
+   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);
--- a/7
+++ b/7
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 143
+SUBLEVEL = 159
 EXTRAVERSION =
 NAME = Blurry Fish Butt

@@ -419,7 +419,9 @@ export MAKE AWK GENKSYMS INSTALLKERNEL PERL PYTHON UTS_MACHINE
 export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS

 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS
-export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV CFLAGS_KCOV CFLAGS_KASAN
+export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV
+export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE
+export CFLAGS_KCOV
 export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE
 export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE
 export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
@@ -625,6 +627,7 @@ KBUILD_CFLAGS	+= $(call cc-disable-warning,frame-address,)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, format-truncation)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, int-in-bool-context)
+KBUILD_CFLAGS	+= $(call cc-disable-warning, attribute-alias)

 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS	+= $(call cc-option,-Oz,-Os)
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -526,24 +526,19 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path,
 SYSCALL_DEFINE1(osf_utsname, char __user *, name)
 {
 	int error;
+	char tmp[5 * 32];

 	down_read(&uts_sem);
-	error = -EFAULT;
-	if (copy_to_user(name + 0, utsname()->sysname, 32))
-		goto out;
-	if (copy_to_user(name + 32, utsname()->nodename, 32))
-		goto out;
-	if (copy_to_user(name + 64, utsname()->release, 32))
-		goto out;
-	if (copy_to_user(name + 96, utsname()->version, 32))
-		goto out;
-	if (copy_to_user(name + 128, utsname()->machine, 32))
-		goto out;
+	memcpy(tmp + 0 * 32, utsname()->sysname, 32);
+	memcpy(tmp + 1 * 32, utsname()->nodename, 32);
+	memcpy(tmp + 2 * 32, utsname()->release, 32);
+	memcpy(tmp + 3 * 32, utsname()->version, 32);
+	memcpy(tmp + 4 * 32, utsname()->machine, 32);
+	up_read(&uts_sem);

-	error = 0;
- out:
-	up_read(&uts_sem);	
-	return error;
+	if (copy_to_user(name, tmp, sizeof(tmp)))
+		return -EFAULT;
+	return 0;
 }

 SYSCALL_DEFINE0(getpagesize)
@@ -561,24 +556,22 @@ SYSCALL_DEFINE0(getdtablesize)
 */
 SYSCALL_DEFINE2(osf_getdomainname, char __user *, name, int, namelen)
 {
-	unsigned len;
-	int i;
+	int len, err = 0;
+	char *kname;
+	char tmp[32];

-	if (!access_ok(VERIFY_WRITE, name, namelen))
-		return -EFAULT;
-
-	len = namelen;
-	if (len > 32)
-		len = 32;
+	if (namelen < 0 || namelen > 32)
+		namelen = 32;

 	down_read(&uts_sem);
-	for (i = 0; i < len; ++i) {
-		__put_user(utsname()->domainname[i], name + i);
-		if (utsname()->domainname[i] == '\0')
-			break;
-	}
+	kname = utsname()->domainname;
+	len = strnlen(kname, namelen);
+	len = min(len + 1, namelen);
+	memcpy(tmp, kname, len);
 	up_read(&uts_sem);

+	if (copy_to_user(name, tmp, len))
+		return -EFAULT;
 	return 0;
 }

@@ -741,13 +734,14 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count)
 	};
 	unsigned long offset;
 	const char *res;
-	long len, err = -EINVAL;
+	long len;
+	char tmp[__NEW_UTS_LEN + 1];

 	offset = command-1;
 	if (offset >= ARRAY_SIZE(sysinfo_table)) {
 		/* Digital UNIX has a few unpublished interfaces here */
 		printk("sysinfo(%d)", command);
-		goto out;
+		return -EINVAL;
 	}

 	down_read(&uts_sem);
@@ -755,13 +749,11 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count)
 	len = strlen(res)+1;
 	if ((unsigned long)len > (unsigned long)count)
 		len = count;
-	if (copy_to_user(buf, res, len))
-		err = -EFAULT;
-	else
-		err = 0;
+	memcpy(tmp, res, len);
 	up_read(&uts_sem);
- out:
-	return err;
+	if (copy_to_user(buf, tmp, len))
+		return -EFAULT;
+	return 0;
 }

 SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer,
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -14,7 +14,7 @@ endif

 KBUILD_DEFCONFIG := nsim_700_defconfig

-cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
+cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs

@@ -137,16 +137,3 @@ dtbs: scripts

 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
-
-# Hacks to enable final link due to absence of link-time branch relexation
-# and gcc choosing optimal(shorter) branches at -O3
-#
-# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
-# However lib/decompress_inflate.o (.init.text) calls
-# zlib_inflate_workspacesize (.text) causing relocation errors.
-# Thus forcing all exten calls in this file to be long calls
-export CFLAGS_decompress_inflate.o = -mmedium-calls
-export CFLAGS_initramfs.o = -mmedium-calls
-ifdef CONFIG_SMP
-export CFLAGS_core.o = -mmedium-calls
-endif
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -1,6 +1,5 @@
 CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
-# CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -1,6 +1,5 @@
 CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
-# CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -1,6 +1,5 @@
 CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
-# CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -17,8 +17,11 @@
 #ifndef __ASM_ARC_UDELAY_H
 #define __ASM_ARC_UDELAY_H

+#include <asm-generic/types.h>
 #include <asm/param.h>		/* HZ */

+extern unsigned long loops_per_jiffy;
+
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -34,9 +34,7 @@ struct machine_desc {
 	const char		*name;
 	const char		**dt_compat;
 	void			(*init_early)(void);
-#ifdef CONFIG_SMP
 	void			(*init_per_cpu)(unsigned int);
-#endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);

--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -102,7 +102,7 @@ typedef pte_t * pgtable_t;
 #define virt_addr_valid(kaddr)  pfn_valid(__pa(kaddr) >> PAGE_SHIFT)

 /* Default Permissions for stack/heaps pages (Non Executable) */
-#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)

 #define WANT_PAGE_VIRTUAL   1

--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -372,7 +372,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,

 /* Decode a PTE containing swap "identifier "into constituents */
 #define __swp_type(pte_lookalike)	(((pte_lookalike).val) & 0x1f)
-#define __swp_offset(pte_lookalike)	((pte_lookalike).val << 13)
+#define __swp_offset(pte_lookalike)	((pte_lookalike).val >> 13)

 /* NOPs, to keep generic kernel happy */
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -31,10 +31,10 @@ void __init init_IRQ(void)
 	/* a SMP H/w block could do IPI IRQ request here */
 	if (plat_smp_ops.init_per_cpu)
 		plat_smp_ops.init_per_cpu(smp_processor_id());
+#endif

 	if (machine_desc->init_per_cpu)
 		machine_desc->init_per_cpu(smp_processor_id());
-#endif
 }

 /*
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -821,7 +821,7 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
 		      unsigned long pfn)
 {
-	unsigned int paddr = pfn << PAGE_SHIFT;
+	phys_addr_t paddr = pfn << PAGE_SHIFT;

 	u_vaddr &= PAGE_MASK;

@@ -841,8 +841,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page,
 		     unsigned long u_vaddr)
 {
 	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_page(page_address(page), u_vaddr);
-	__flush_dcache_page(page_address(page), page_address(page));
+	__flush_dcache_page((phys_addr_t)page_address(page), u_vaddr);
+	__flush_dcache_page((phys_addr_t)page_address(page),
+			    (phys_addr_t)page_address(page));

 }

--- a/arch/arm/boot/dts/am3517.dtsi
+++ b/arch/arm/boot/dts/am3517.dtsi
@@ -74,6 +74,11 @@
 	};
 };

+/* Table Table 5-79 of the TRM shows 480ab000 is reserved */
+&usb_otg_hs {
+	status = "disabled";
+};
+
 &iva {
 	status = "disabled";
 };
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -508,6 +508,8 @@

 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <272>;
+
+		wakeup-source;
 	};

 	tlv320aic3106: tlv320aic3106@1b {
--- a/arch/arm/boot/dts/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus.dtsi
@@ -110,7 +110,7 @@
 			reg = <0x18008000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 85 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
@@ -138,7 +138,7 @@
 			reg = <0x1800b000 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			interrupts = <GIC_SPI 86 IRQ_TYPE_NONE>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
--- a/arch/arm/boot/dts/da850.dtsi
+++ b/arch/arm/boot/dts/da850.dtsi
@@ -267,11 +267,7 @@
 			compatible = "ti,dm6441-gpio";
 			gpio-controller;
 			reg = <0x226000 0x1000>;
-			interrupts = <42 IRQ_TYPE_EDGE_BOTH
-				43 IRQ_TYPE_EDGE_BOTH 44 IRQ_TYPE_EDGE_BOTH
-				45 IRQ_TYPE_EDGE_BOTH 46 IRQ_TYPE_EDGE_BOTH
-				47 IRQ_TYPE_EDGE_BOTH 48 IRQ_TYPE_EDGE_BOTH
-				49 IRQ_TYPE_EDGE_BOTH 50 IRQ_TYPE_EDGE_BOTH>;
+			interrupts = <42 43 44 45 46 47 48 49 50>;
 			ti,ngpio = <144>;
 			ti,davinci-gpio-unbanked = <0>;
 			status = "disabled";
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -1250,7 +1250,7 @@
 				  /* non-prefetchable memory */
 				  0x82000000 0 0x08000000 0x08000000 0 0x00f00000>;
 			num-lanes = <1>;
-			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clks IMX6SX_CLK_PCIE_REF_125M>,
 				 <&clks IMX6SX_CLK_PCIE_AXI>,
 				 <&clks IMX6SX_CLK_LVDS1_OUT>,
--- a/arch/arm/boot/dts/tegra30-cardhu.dtsi
+++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi
@@ -201,6 +201,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x70>;
+			reset-gpio = <&gpio TEGRA_GPIO(BB, 0) GPIO_ACTIVE_LOW>;
 		};
 	};

--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -145,9 +145,11 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
 CONFIG_NOP_USB_XCEIV=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_ETH=m
+CONFIG_USB_ULPI_BUS=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void)
 	u32 irqstat;

 	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }

--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -251,7 +251,7 @@ extern int __put_user_8(void *, unsigned long long);
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		const typeof(*(p)) __user *__tmp_p = (p);		\
-		register const typeof(*(p)) __r2 asm("r2") = (x);	\
+		register typeof(*(p)) __r2 asm("r2") = (x);	\
 		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -899,19 +899,35 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	pmd = stage2_get_pmd(kvm, cache, addr);
 	VM_BUG_ON(!pmd);

-	/*
-	 * Mapping in huge pages should only happen through a fault.  If a
-	 * page is merged into a transparent huge page, the individual
-	 * subpages of that huge page should be unmapped through MMU
-	 * notifiers before we get here.
-	 *
-	 * Merging of CompoundPages is not supported; they should become
-	 * splitting first, unmapped, merged, and mapped back in on-demand.
-	 */
-	VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
-
 	old_pmd = *pmd;
 	if (pmd_present(old_pmd)) {
+		/*
+		 * Multiple vcpus faulting on the same PMD entry, can
+		 * lead to them sequentially updating the PMD with the
+		 * same value. Following the break-before-make
+		 * (pmd_clear() followed by tlb_flush()) process can
+		 * hinder forward progress due to refaults generated
+		 * on missing translations.
+		 *
+		 * Skip updating the page table if the entry is
+		 * unchanged.
+		 */
+		if (pmd_val(old_pmd) == pmd_val(*new_pmd))
+			return 0;
+
+		/*
+		 * Mapping in huge pages should only happen through a
+		 * fault.  If a page is merged into a transparent huge
+		 * page, the individual subpages of that huge page
+		 * should be unmapped through MMU notifiers before we
+		 * get here.
+		 *
+		 * Merging of CompoundPages is not supported; they
+		 * should become splitting first, unmapped, merged,
+		 * and mapped back in on-demand.
+		 */
+		VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
+
 		pmd_clear(pmd);
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
 	} else {
@@ -968,6 +984,10 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	/* Create 2nd stage page table mapping - Level 3 */
 	old_pte = *pte;
 	if (pte_present(old_pte)) {
+		/* Skip page table update if there is no change */
+		if (pte_val(old_pte) == pte_val(*new_pte))
+			return 0;
+
 		kvm_set_pte(pte, __pte(0));
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
 	} else {
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -260,6 +260,7 @@ static int __init exynos_pmu_irq_init(struct device_node *node,
 					  NULL);
 	if (!domain) {
 		iounmap(pmu_base_addr);
+		pmu_base_addr = NULL;
 		return -ENOMEM;
 	}

--- a/arch/arm/mach-hisi/hotplug.c
+++ b/arch/arm/mach-hisi/hotplug.c
@@ -148,13 +148,20 @@ static int hi3xxx_hotplug_init(void)
 	struct device_node *node;

 	node = of_find_compatible_node(NULL, NULL, "hisilicon,sysctrl");
-	if (node) {
-		ctrl_base = of_iomap(node, 0);
-		id = HI3620_CTRL;
-		return 0;
+	if (!node) {
+		id = ERROR_CTRL;
+		return -ENOENT;
 	}
-	id = ERROR_CTRL;
-	return -ENOENT;
+
+	ctrl_base = of_iomap(node, 0);
+	of_node_put(node);
+	if (!ctrl_base) {
+		id = ERROR_CTRL;
+		return -ENOMEM;
+	}
+
+	id = HI3620_CTRL;
+	return 0;
 }

 void hi3xxx_set_cpu(int cpu, bool enable)
@@ -173,11 +180,15 @@ static bool hix5hd2_hotplug_init(void)
 	struct device_node *np;

 	np = of_find_compatible_node(NULL, NULL, "hisilicon,cpuctrl");
-	if (np) {
-		ctrl_base = of_iomap(np, 0);
-		return true;
-	}
-	return false;
+	if (!np)
+		return false;
+
+	ctrl_base = of_iomap(np, 0);
+	of_node_put(np);
+	if (!ctrl_base)
+		return false;
+
+	return true;
 }

 void hix5hd2_set_cpu(int cpu, bool enable)
@@ -219,10 +230,10 @@ void hip01_set_cpu(int cpu, bool enable)

 	if (!ctrl_base) {
 		np = of_find_compatible_node(NULL, NULL, "hisilicon,hip01-sysctrl");
-		if (np)
-			ctrl_base = of_iomap(np, 0);
-		else
-			BUG();
+		BUG_ON(!np);
+		ctrl_base = of_iomap(np, 0);
+		of_node_put(np);
+		BUG_ON(!ctrl_base);
 	}

 	if (enable) {
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -185,7 +185,7 @@ static int pxa_irq_suspend(void)
 {
 	int i;

-	for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+	for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
 		void __iomem *base = irq_base(i);

 		saved_icmr[i] = __raw_readl(base + ICMR);
@@ -204,7 +204,7 @@ static void pxa_irq_resume(void)
 {
 	int i;

-	for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+	for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
 		void __iomem *base = irq_base(i);

 		__raw_writel(saved_icmr[i], base + ICMR);
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -716,19 +716,28 @@ int __mark_rodata_ro(void *unused)
 	return 0;
 }

+static int kernel_set_to_readonly __read_mostly;
+
 void mark_rodata_ro(void)
 {
+	kernel_set_to_readonly = 1;
 	stop_machine(__mark_rodata_ro, NULL, NULL);
 }

 void set_kernel_text_rw(void)
 {
+	if (!kernel_set_to_readonly)
+		return;
+
 	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
 				current->active_mm);
 }

 void set_kernel_text_ro(void)
 {
+	if (!kernel_set_to_readonly)
+		return;
+
 	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
 				current->active_mm);
 }
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi
@@ -105,7 +105,7 @@
 			led@6 {
 				label = "apq8016-sbc:blue:bt";
 				gpios = <&pm8916_mpps 3 GPIO_ACTIVE_HIGH>;
-				linux,default-trigger = "bt";
+				linux,default-trigger = "bluetooth-power";
 				default-state = "off";
 			};
 		};
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -183,7 +183,7 @@ static void smp_store_cpu_info(unsigned int cpuid)
 * This is the secondary CPU boot entry.  We're using this CPUs
 * idle thread stack, but a set of temporary page tables.
 */
-asmlinkage void secondary_start_kernel(void)
+asmlinkage notrace void secondary_start_kernel(void)
 {
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu;
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -267,11 +267,13 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 }

 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
-#define PFN_MASK ((1UL << (64 - PAGE_SHIFT)) - 1)
-
 int pfn_valid(unsigned long pfn)
 {
-	return (pfn & PFN_MASK) == pfn && memblock_is_map_memory(pfn << PAGE_SHIFT);
+	phys_addr_t addr = pfn << PAGE_SHIFT;
+
+	if ((addr >> PAGE_SHIFT) != pfn)
+		return 0;
+	return memblock_is_memory(addr);
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -882,12 +882,12 @@ int pmd_clear_huge(pmd_t *pmd)
 }

 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return pud_none(*pud);
 }

-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return pmd_none(*pmd);
 }
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -43,6 +43,7 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
 				  unsigned long address)
 {
+	pgtable_page_dtor(page);
 	__free_page(page);
 }

@@ -73,8 +74,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	return page;
 }

-extern inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, struct page *page)
 {
+	pgtable_page_dtor(page);
 	__free_page(page);
 }

--- a/arch/microblaze/boot/Makefile
+++ b/arch/microblaze/boot/Makefile
@@ -21,17 +21,19 @@ $(obj)/linux.bin.gz: $(obj)/linux.bin FORCE
 quiet_cmd_cp = CP      $< $@$2
 	cmd_cp = cat $< >$@$2 || (rm -f $@ && echo false)

-quiet_cmd_strip = STRIP   $@
+quiet_cmd_strip = STRIP   $< $@$2
 	cmd_strip = $(STRIP) -K microblaze_start -K _end -K __log_buf \
-				-K _fdt_start vmlinux -o $@
+				-K _fdt_start $< -o $@$2

 UIMAGE_LOADADDR = $(CONFIG_KERNEL_BASE_ADDR)
+UIMAGE_IN = $@
+UIMAGE_OUT = $@.ub

 $(obj)/simpleImage.%: vmlinux FORCE
 	$(call if_changed,cp,.unstrip)
 	$(call if_changed,objcopy)
 	$(call if_changed,uimage)
-	$(call if_changed,strip)
-	@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
+	$(call if_changed,strip,.strip)
+	@echo 'Kernel: $(UIMAGE_OUT) is ready' ' (#'`cat .version`')'

 clean-files += simpleImage.*.unstrip linux.bin.ub dts/*.dtb
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);

 void ath79_ddr_wb_flush(u32 reg)
 {
-	void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);

 	/* Flush the DDR write buffer. */
 	__raw_writel(0x1, flush_reg);
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -44,6 +44,7 @@ static char ath79_sys_type[ATH79_SYS_TYPE_LEN];

 static void ath79_restart(char *command)
 {
+	local_irq_disable();
 	ath79_device_reset_set(AR71XX_RESET_FULL_CHIP);
 	for (;;)
 		if (cpu_wait)
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -249,12 +249,6 @@ static int __init bcm47xx_cpu_fixes(void)
 		 */
 		if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
 			cpu_wait = NULL;
-
-		/*
-		 * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
-		 * Enable ExternalSync for sync instruction to take effect
-		 */
-		set_c0_config7(MIPS_CONF7_ES);
 		break;
 #endif
 	}
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -349,6 +349,7 @@ static int __init octeon_ehci_device_init(void)
 		return 0;

 	pd = of_find_device_by_node(ehci_node);
+	of_node_put(ehci_node);
 	if (!pd)
 		return 0;

@@ -411,6 +412,7 @@ static int __init octeon_ohci_device_init(void)
 		return 0;

 	pd = of_find_device_by_node(ohci_node);
+	of_node_put(ohci_node);
 	if (!pd)
 		return 0;

--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -141,14 +141,14 @@ static inline void * phys_to_virt(unsigned long address)
 /*
 * ISA I/O bus memory addresses are 1:1 with the physical address.
 */
-static inline unsigned long isa_virt_to_bus(volatile void * address)
+static inline unsigned long isa_virt_to_bus(volatile void *address)
 {
-	return (unsigned long)address - PAGE_OFFSET;
+	return virt_to_phys(address);
 }

-static inline void * isa_bus_to_virt(unsigned long address)
+static inline void *isa_bus_to_virt(unsigned long address)
 {
-	return (void *)(address + PAGE_OFFSET);
+	return phys_to_virt(address);
 }

 #define isa_page_to_bus page_to_phys
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -133,6 +133,7 @@ static inline u32 ath79_pll_rr(unsigned reg)
 static inline void ath79_reset_wr(unsigned reg, u32 val)
 {
 	__raw_writel(val, ath79_reset_base + reg);
+	(void) __raw_readl(ath79_reset_base + reg); /* flush */
 }

 static inline u32 ath79_reset_rr(unsigned reg)
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -606,8 +606,6 @@
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)

 #define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
-/* ExternalSync */
-#define MIPS_CONF7_ES		(_ULCAST_(1) << 8)

 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
@@ -2015,7 +2013,6 @@ __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
 __BUILD_SET_C0(config5)
-__BUILD_SET_C0(config7)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -89,7 +89,7 @@ static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	phys_addr_t size = resource_size(rsrc);

 	*start = fixup_bigphys_addr(rsrc->start, size);
-	*end = rsrc->start + size;
+	*end = rsrc->start + size - 1;
 }

 /*
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -137,7 +137,7 @@ struct mips_fpu_struct {

 #define NUM_DSP_REGS   6

-typedef __u32 dspreg_t;
+typedef unsigned long dspreg_t;

 struct mips_dsp_state {
 	dspreg_t	dspr[NUM_DSP_REGS];
--- a/arch/mips/jz4740/Platform
+++ b/arch/mips/jz4740/Platform
@@ -1,4 +1,4 @@
 platform-$(CONFIG_MACH_INGENIC)	+= jz4740/
 cflags-$(CONFIG_MACH_INGENIC)	+= -I$(srctree)/arch/mips/include/asm/mach-jz4740
 load-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80010000
-zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80600000
+zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff81000000
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -117,7 +117,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
 	unsigned long childksp;
-	p->set_child_tid = p->clear_child_tid = NULL;

 	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;

--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -878,7 +878,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -140,7 +140,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -14,12 +14,14 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/irqchip/mips-gic.h>
+#include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/timekeeper_internal.h>

 #include <asm/abi.h>
+#include <asm/page.h>
 #include <asm/vdso.h>

 /* Kernel-provided data used by the VDSO. */
@@ -128,12 +130,30 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	vvar_size = gic_size + PAGE_SIZE;
 	size = vvar_size + image->size;

+	/*
+	 * Find a region that's large enough for us to perform the
+	 * colour-matching alignment below.
+	 */
+	if (cpu_has_dc_aliases)
+		size += shm_align_mask + 1;
+
 	base = get_unmapped_area(NULL, 0, size, 0, 0);
 	if (IS_ERR_VALUE(base)) {
 		ret = base;
 		goto out;
 	}

+	/*
+	 * If we suffer from dcache aliasing, ensure that the VDSO data page
+	 * mapping is coloured the same as the kernel's mapping of that memory.
+	 * This ensures that when the kernel updates the VDSO data userland
+	 * will observe it without requiring cache invalidations.
+	 */
+	if (cpu_has_dc_aliases) {
+		base = __ALIGN_MASK(base, shm_align_mask);
+		base += ((unsigned long)&vdso_data - gic_size) & shm_align_mask;
+	}
+
 	data_addr = base + gic_size;
 	vdso_addr = data_addr + PAGE_SIZE;

--- a/arch/mips/lib/multi3.c
+++ b/arch/mips/lib/multi3.c
@@ -4,12 +4,12 @@
 #include "libgcc.h"

 /*
- * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
- * specific case only we'll implement it here.
+ * GCC 7 & older can suboptimally generate __multi3 calls for mips64r6, so for
+ * that specific case only we implement that intrinsic here.
 *
 * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
 */
-#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ < 8)

 /* multiply 64-bit values, low 64-bits returned */
 static inline long long notrace dmulu(long long a, long long b)
--- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
@@ -138,7 +138,7 @@ u32 pci_ohci_read_reg(int reg)
 		break;
 	case PCI_OHCI_INT_REG:
 		_rdmsr(DIVIL_MSR_REG(PIC_YSEL_LOW), &hi, &lo);
-		if ((lo & 0x00000f00) == CS5536_USB_INTR)
+		if (((lo >> PIC_YSEL_LOW_USB_SHIFT) & 0xf) == CS5536_USB_INTR)
 			conf_data = 1;
 		break;
 	default:
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -712,7 +712,8 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end)
 static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;

 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -745,7 +746,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;

 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -152,8 +152,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp,

 	top_of_kernel_stack = sp;

-	p->set_child_tid = p->clear_child_tid = NULL;
-
 	/* Locate userspace context on stack... */
 	sp -= STACK_FRAME_OVERHEAD;	/* redzone */
 	sp -= sizeof(struct pt_regs);
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -178,7 +178,7 @@ config PREFETCH

 config MLONGCALLS
 	bool "Enable the -mlong-calls compiler option for big kernels"
-	def_bool y if (!MODULES)
+	default y
 	depends on PA8X00
 	help
 	  If you configure the kernel to include many drivers built-in instead
--- a/arch/parisc/include/asm/barrier.h
+++ b/arch/parisc/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* The synchronize caches instruction executes as a nop on systems in
+   which all memory references are performed in order. */
+#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory")
+
+#if defined(CONFIG_SMP)
+#define mb()		do { synchronize_caches(); } while (0)
+#define rmb()		mb()
+#define wmb()		mb()
+#define dma_rmb()	mb()
+#define dma_wmb()	mb()
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define dma_rmb()	barrier()
+#define dma_wmb()	barrier()
+#endif
+
+#define __smp_mb()	mb()
+#define __smp_rmb()	mb()
+#define __smp_wmb()	mb()
+
+#include <asm-generic/barrier.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -21,7 +21,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 {
 	volatile unsigned int *a;

-	mb();
 	a = __ldcw_align(x);
 	while (__ldcw(a) == 0)
 		while (*a == 0)
@@ -31,16 +30,15 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 				local_irq_disable();
 			} else
 				cpu_relax();
-	mb();
 }

 static inline void arch_spin_unlock(arch_spinlock_t *x)
 {
 	volatile unsigned int *a;
-	mb();
+
 	a = __ldcw_align(x);
-	*a = 1;
 	mb();
+	*a = 1;
 }

 static inline int arch_spin_trylock(arch_spinlock_t *x)
@@ -48,10 +46,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 	int ret;

-	mb();
 	a = __ldcw_align(x);
        ret = __ldcw(a) != 0;
-	mb();

 	return ret;
 }
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -481,6 +481,8 @@
 	/* Release pa_tlb_lock lock without reloading lock address. */
 	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	sync
 	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -354,6 +354,7 @@ ENDPROC(flush_data_cache_local)
 	.macro	tlb_unlock	la,flags,tmp
 #ifdef CONFIG_SMP
 	ldi		1,\tmp
+	sync
 	stw		\tmp,0(\la)
 	mtsm		\flags
 #endif
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -627,11 +627,12 @@ cas_action:
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw,ma	0(%r26), %r28
+1:	ldw	0(%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw,ma	%r24, 0(%r26)
+2:	stw	%r24, 0(%r26)
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -645,6 +646,7 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
@@ -794,30 +796,30 @@ cas2_action:
 	ldo	1(%r0),%r28

 	/* 8bit CAS */
-13:	ldb,ma	0(%r26), %r29
+13:	ldb	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-14:	stb,ma	%r24, 0(%r26)
+14:	stb	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop

 	/* 16bit CAS */
-15:	ldh,ma	0(%r26), %r29
+15:	ldh	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-16:	sth,ma	%r24, 0(%r26)
+16:	sth	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop

 	/* 32bit CAS */
-17:	ldw,ma	0(%r26), %r29
+17:	ldw	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-18:	stw,ma	%r24, 0(%r26)
+18:	stw	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
@@ -825,10 +827,10 @@ cas2_action:

 	/* 64bit CAS */
 #ifdef CONFIG_64BIT
-19:	ldd,ma	0(%r26), %r29
+19:	ldd	0(%r26), %r29
 	sub,*=	%r29, %r25, %r0
 	b,n	cas2_end
-20:	std,ma	%r24, 0(%r26)
+20:	std	%r24, 0(%r26)
 	copy	%r0, %r28
 #else
 	/* Compare first word */
@@ -846,7 +848,8 @@ cas2_action:

 cas2_end:
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
@@ -856,6 +859,7 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -194,9 +194,6 @@ struct fadump_crash_info_header {
 	struct cpumask	cpu_online_mask;
 };

-/* Crash memory ranges */
-#define INIT_CRASHMEM_RANGES	(INIT_MEMBLOCK_REGIONS + 2)
-
 struct fad_crash_memory_ranges {
 	unsigned long long	base;
 	unsigned long long	size;
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -35,6 +35,7 @@
 #include <linux/crash_dump.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
+#include <linux/slab.h>

 #include <asm/page.h>
 #include <asm/prom.h>
@@ -48,8 +49,10 @@ static struct fadump_mem_struct fdm;
 static const struct fadump_mem_struct *fdm_active;

 static DEFINE_MUTEX(fadump_mutex);
-struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES];
+struct fad_crash_memory_ranges *crash_memory_ranges;
+int crash_memory_ranges_size;
 int crash_mem_ranges;
+int max_crash_mem_ranges;

 /* Scan the Firmware Assisted dump configuration details. */
 int __init early_init_dt_scan_fw_dump(unsigned long node,
@@ -726,38 +729,88 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
 	return 0;
 }

-static inline void fadump_add_crash_memory(unsigned long long base,
-					unsigned long long end)
+static void free_crash_memory_ranges(void)
+{
+	kfree(crash_memory_ranges);
+	crash_memory_ranges = NULL;
+	crash_memory_ranges_size = 0;
+	max_crash_mem_ranges = 0;
+}
+
+/*
+ * Allocate or reallocate crash memory ranges array in incremental units
+ * of PAGE_SIZE.
+ */
+static int allocate_crash_memory_ranges(void)
+{
+	struct fad_crash_memory_ranges *new_array;
+	u64 new_size;
+
+	new_size = crash_memory_ranges_size + PAGE_SIZE;
+	pr_debug("Allocating %llu bytes of memory for crash memory ranges\n",
+		 new_size);
+
+	new_array = krealloc(crash_memory_ranges, new_size, GFP_KERNEL);
+	if (new_array == NULL) {
+		pr_err("Insufficient memory for setting up crash memory ranges\n");
+		free_crash_memory_ranges();
+		return -ENOMEM;
+	}
+
+	crash_memory_ranges = new_array;
+	crash_memory_ranges_size = new_size;
+	max_crash_mem_ranges = (new_size /
+				sizeof(struct fad_crash_memory_ranges));
+	return 0;
+}
+
+static inline int fadump_add_crash_memory(unsigned long long base,
+					  unsigned long long end)
 {
 	if (base == end)
-		return;
+		return 0;
+
+	if (crash_mem_ranges == max_crash_mem_ranges) {
+		int ret;
+
+		ret = allocate_crash_memory_ranges();
+		if (ret)
+			return ret;
+	}

 	pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
 		crash_mem_ranges, base, end - 1, (end - base));
 	crash_memory_ranges[crash_mem_ranges].base = base;
 	crash_memory_ranges[crash_mem_ranges].size = end - base;
 	crash_mem_ranges++;
+	return 0;
 }

-static void fadump_exclude_reserved_area(unsigned long long start,
+static int fadump_exclude_reserved_area(unsigned long long start,
 					unsigned long long end)
 {
 	unsigned long long ra_start, ra_end;
+	int ret = 0;

 	ra_start = fw_dump.reserve_dump_area_start;
 	ra_end = ra_start + fw_dump.reserve_dump_area_size;

 	if ((ra_start < end) && (ra_end > start)) {
 		if ((start < ra_start) && (end > ra_end)) {
-			fadump_add_crash_memory(start, ra_start);
-			fadump_add_crash_memory(ra_end, end);
+			ret = fadump_add_crash_memory(start, ra_start);
+			if (ret)
+				return ret;
+
+			ret = fadump_add_crash_memory(ra_end, end);
 		} else if (start < ra_start) {
-			fadump_add_crash_memory(start, ra_start);
+			ret = fadump_add_crash_memory(start, ra_start);
 		} else if (ra_end < end) {
-			fadump_add_crash_memory(ra_end, end);
+			ret = fadump_add_crash_memory(ra_end, end);
 		}
 	} else
-		fadump_add_crash_memory(start, end);
+		ret = fadump_add_crash_memory(start, end);
+
+	return ret;
 }

 static int fadump_init_elfcore_header(char *bufp)
@@ -793,10 +846,11 @@ static int fadump_init_elfcore_header(char *bufp)
 * Traverse through memblock structure and setup crash memory ranges. These
 * ranges will be used create PT_LOAD program headers in elfcore header.
 */
-static void fadump_setup_crash_memory_ranges(void)
+static int fadump_setup_crash_memory_ranges(void)
 {
 	struct memblock_region *reg;
 	unsigned long long start, end;
+	int ret;

 	pr_debug("Setup crash memory ranges.\n");
 	crash_mem_ranges = 0;
@@ -807,7 +861,9 @@ static void fadump_setup_crash_memory_ranges(void)
 	 * specified during fadump registration. We need to create a separate
 	 * program header for this chunk with the correct offset.
 	 */
-	fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
+	ret = fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
+	if (ret)
+		return ret;

 	for_each_memblock(memory, reg) {
 		start = (unsigned long long)reg->base;
@@ -816,8 +872,12 @@ static void fadump_setup_crash_memory_ranges(void)
 			start = fw_dump.boot_memory_size;

 		/* add this range excluding the reserved dump area. */
-		fadump_exclude_reserved_area(start, end);
+		ret = fadump_exclude_reserved_area(start, end);
+		if (ret)
+			return ret;
 	}
+
+	return 0;
 }

 /*
@@ -941,6 +1001,7 @@ static void register_fadump(void)
 {
 	unsigned long addr;
 	void *vaddr;
+	int ret;

 	/*
 	 * If no memory is reserved then we can not register for firmware-
@@ -949,7 +1010,9 @@ static void register_fadump(void)
 	if (!fw_dump.reserve_dump_area_size)
 		return;

-	fadump_setup_crash_memory_ranges();
+	ret = fadump_setup_crash_memory_ranges();
+	if (ret)
+		return ret;

 	addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len);
 	/* Initialize fadump crash info header. */
@@ -1028,6 +1091,7 @@ void fadump_cleanup(void)
 	} else if (fw_dump.dump_registered) {
 		/* Un-register Firmware-assisted dump if it was registered. */
 		fadump_unregister_dump(&fdm);
+		free_crash_memory_ranges();
 	}
 }

--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -720,7 +720,7 @@ start_here:
 	tovirt(r6,r6)
 	lis	r5, abatron_pteptrs@h
 	ori	r5, r5, abatron_pteptrs@l
-	stw	r5, 0xf0(r0)	/* Must match your Abatron config file */
+	stw	r5, 0xf0(0)	/* Must match your Abatron config file */
 	tophys(r5,r5)
 	stw	r6, 0(r5)

--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/errno.h>
 #include <linux/bootmem.h>
+#include <linux/syscalls.h>
 #include <linux/irq.h>
 #include <linux/list.h>
 #include <linux/of.h>
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -69,14 +69,14 @@ static inline void slb_shadow_update(unsigned long ea, int ssize,
 	 * updating it.  No write barriers are needed here, provided
 	 * we only update the current CPU's SLB shadow buffer.
 	 */
-	p->save_area[index].esid = 0;
-	p->save_area[index].vsid = cpu_to_be64(mk_vsid_data(ea, ssize, flags));
-	p->save_area[index].esid = cpu_to_be64(mk_esid_data(ea, ssize, index));
+	WRITE_ONCE(p->save_area[index].esid, 0);
+	WRITE_ONCE(p->save_area[index].vsid, cpu_to_be64(mk_vsid_data(ea, ssize, flags)));
+	WRITE_ONCE(p->save_area[index].esid, cpu_to_be64(mk_esid_data(ea, ssize, index)));
 }

 static inline void slb_shadow_clear(enum slb_index index)
 {
-	get_slb_shadow()->save_area[index].esid = 0;
+	WRITE_ONCE(get_slb_shadow()->save_area[index].esid, 0);
 }

 static inline void create_shadowed_slbe(unsigned long ea, int ssize,
--- a/arch/powerpc/platforms/chrp/time.c
+++ b/arch/powerpc/platforms/chrp/time.c
@@ -27,6 +27,8 @@
 #include <asm/sections.h>
 #include <asm/time.h>

+#include <platforms/chrp/chrp.h>
+
 extern spinlock_t rtc_lock;

 #define NVRAM_AS0  0x74
@@ -62,7 +64,7 @@ long __init chrp_time_init(void)
 	return 0;
 }

-int chrp_cmos_clock_read(int addr)
+static int chrp_cmos_clock_read(int addr)
 {
 	if (nvram_as1 != 0)
 		outb(addr>>8, nvram_as1);
@@ -70,7 +72,7 @@ int chrp_cmos_clock_read(int addr)
 	return (inb(nvram_data));
 }

-void chrp_cmos_clock_write(unsigned long val, int addr)
+static void chrp_cmos_clock_write(unsigned long val, int addr)
 {
 	if (nvram_as1 != 0)
 		outb(addr>>8, nvram_as1);
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -35,6 +35,8 @@
 */
 #define HW_BROADWAY_ICR		0x00
 #define HW_BROADWAY_IMR		0x04
+#define HW_STARLET_ICR		0x08
+#define HW_STARLET_IMR		0x0c


 /*
@@ -74,6 +76,9 @@ static void hlwd_pic_unmask(struct irq_data *d)
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);

 	setbits32(io_base + HW_BROADWAY_IMR, 1 << irq);
+
+	/* Make sure the ARM (aka. Starlet) doesn't handle this interrupt. */
+	clrbits32(io_base + HW_STARLET_IMR, 1 << irq);
 }


--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -467,7 +467,7 @@ void __init bootx_init(unsigned long r3, unsigned long r4)
 	boot_infos_t *bi = (boot_infos_t *) r4;
 	unsigned long hdr;
 	unsigned long space;
-	unsigned long ptr, x;
+	unsigned long ptr;
 	char *model;
 	unsigned long offset = reloc_offset();

@@ -561,6 +561,8 @@ void __init bootx_init(unsigned long r3, unsigned long r4)
 	 * MMU switched OFF, so this should not be useful anymore.
 	 */
 	if (bi->version < 4) {
+		unsigned long x __maybe_unused;
+
 		bootx_printf("Touching pages...\n");

 		/*
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -359,6 +359,7 @@ static int pmac_late_init(void)
 }
 machine_late_initcall(powermac, pmac_late_init);

+void note_bootable_part(dev_t dev, int part, int goodness);
 /*
 * This is __init_refok because we check for "initializing" before
 * touching any of the __init sensitive things and "initializing"
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -371,7 +371,7 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 		/* Closed or other error drop */
 		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
 		    rc != OPAL_BUSY_EVENT) {
-			written = total_len;
+			written += total_len;
 			break;
 		}
 		if (rc == OPAL_SUCCESS) {
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -300,7 +300,7 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 	}

 	savep = __va(regs->gpr[3]);
-	regs->gpr[3] = savep[0];	/* restore original r3 */
+	regs->gpr[3] = be64_to_cpu(savep[0]);	/* restore original r3 */

 	/* If it isn't an extended log we can use the per cpu 64bit buffer */
 	h = (struct rtas_error_log *)&savep[1];
@@ -311,7 +311,7 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs)
 		int len, error_log_length;

 		error_log_length = 8 + rtas_error_extended_log_length(h);
-		len = max_t(int, error_log_length, RTAS_ERROR_LOG_MAX);
+		len = min_t(int, error_log_length, RTAS_ERROR_LOG_MAX);
 		memset(global_mce_data_buf, 0, RTAS_ERROR_LOG_MAX);
 		memcpy(global_mce_data_buf, h, len);
 		errhdr = (struct rtas_error_log *)global_mce_data_buf;
--- a/arch/powerpc/sysdev/mpic_msgr.c
+++ b/arch/powerpc/sysdev/mpic_msgr.c
@@ -196,7 +196,7 @@ static int mpic_msgr_probe(struct platform_device *dev)

 	/* IO map the message register block. */
 	of_address_to_resource(np, 0, &rsrc);
-	msgr_block_addr = ioremap(rsrc.start, rsrc.end - rsrc.start);
+	msgr_block_addr = ioremap(rsrc.start, resource_size(&rsrc));
 	if (!msgr_block_addr) {
 		dev_err(&dev->dev, "Failed to iomap MPIC message registers");
 		return -EFAULT;
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -113,7 +113,7 @@ struct hws_basic_entry {

 struct hws_diag_entry {
 	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
-	unsigned int R:14;	    /* 16-19 and 20-30 reserved		 */
+	unsigned int R:15;	    /* 16-19 and 20-30 reserved		 */
 	unsigned int I:1;	    /* 31 entry valid or invalid	 */
 	u8	     data[];	    /* Machine-dependent sample data	 */
 } __packed;
@@ -129,7 +129,9 @@ struct hws_trailer_entry {
 			unsigned int f:1;	/* 0 - Block Full Indicator   */
 			unsigned int a:1;	/* 1 - Alert request control  */
 			unsigned int t:1;	/* 2 - Timestamp format	      */
-			unsigned long long:61;	/* 3 - 63: Reserved	      */
+			unsigned int :29;	/* 3 - 31: Reserved	      */
+			unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
+			unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
 		};
 		unsigned long long flags;	/* 0 - 63: All indicators     */
 	};
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -261,7 +261,6 @@ struct qdio_outbuf_state {
 	void *user;
 };

-#define QDIO_OUTBUF_STATE_FLAG_NONE	0x00
 #define QDIO_OUTBUF_STATE_FLAG_PENDING	0x01

 #define CHSC_AC1_INITIATE_INPUTQ	0x80
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -26,7 +26,7 @@
 */
 ENTRY(memset)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemset_exit
 	ltgr	%r3,%r3
 	jnz	.Lmemset_fill
 	aghi	%r4,-1
@@ -41,12 +41,13 @@ ENTRY(memset)
 .Lmemset_clear_rest:
 	larl	%r3,.Lmemset_xc
 	ex	%r4,0(%r3)
+.Lmemset_exit:
 	BR_EX	%r14
 .Lmemset_fill:
 	stc	%r3,0(%r2)
 	cghi	%r4,1
 	lgr	%r1,%r2
-	ber	%r14
+	je	.Lmemset_fill_exit
 	aghi	%r4,-2
 	srlg	%r3,%r4,8
 	ltgr	%r3,%r3
@@ -58,6 +59,7 @@ ENTRY(memset)
 .Lmemset_fill_rest:
 	larl	%r3,.Lmemset_mvc
 	ex	%r4,0(%r3)
+.Lmemset_fill_exit:
 	BR_EX	%r14
 .Lmemset_xc:
 	xc	0(1,%r1),0(%r1)
@@ -71,7 +73,7 @@ ENTRY(memset)
 */
 ENTRY(memcpy)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemcpy_exit
 	aghi	%r4,-1
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -80,6 +82,7 @@ ENTRY(memcpy)
 .Lmemcpy_rest:
 	larl	%r5,.Lmemcpy_mvc
 	ex	%r4,0(%r5)
+.Lmemcpy_exit:
 	BR_EX	%r14
 .Lmemcpy_loop:
 	mvc	0(256,%r1),0(%r3)
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -459,6 +459,8 @@ retry:
 	/* No reason to continue if interrupted by SIGKILL. */
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
 		fault = VM_FAULT_SIGNAL;
+		if (flags & FAULT_FLAG_RETRY_NOWAIT)
+			goto out_up;
 		goto out;
 	}
 	if (unlikely(fault & VM_FAULT_ERROR))
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -522,8 +522,6 @@ static void bpf_jit_epilogue(struct bpf_jit *jit)
 			/* br %r1 */
 			_EMIT2(0x07f1);
 		} else {
-			/* larl %r1,.+14 */
-			EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
 			/* ex 0,S390_lowcore.br_r1_tampoline */
 			EMIT4_DISP(0x44000000, REG_0, REG_0,
 				   offsetof(struct _lowcore, br_r1_trampoline));
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -412,6 +412,8 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	hwirq = 0;
 	for_each_pci_msi_entry(msi, pdev) {
 		rc = -EIO;
+		if (hwirq >= msi_vecs)
+			break;
 		irq = irq_alloc_desc(0);	/* Alloc irq on node 0 */
 		if (irq < 0)
 			goto out_msi;
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -201,23 +201,27 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig,

 asmlinkage long sys_getdomainname(char __user *name, int len)
 {
- 	int nlen, err;
- 	
+	int nlen, err;
+	char tmp[__NEW_UTS_LEN + 1];
+
 	if (len < 0)
 		return -EINVAL;

- 	down_read(&uts_sem);
- 	
+	down_read(&uts_sem);
+
 	nlen = strlen(utsname()->domainname) + 1;
 	err = -EINVAL;
 	if (nlen > len)
-		goto out;
+		goto out_unlock;
+	memcpy(tmp, utsname()->domainname, nlen);

-	err = -EFAULT;
-	if (!copy_to_user(name, utsname()->domainname, nlen))
-		err = 0;
+	up_read(&uts_sem);

-out:
+	if (copy_to_user(name, tmp, nlen))
+		return -EFAULT;
+	return 0;
+
+out_unlock:
 	up_read(&uts_sem);
 	return err;
 }
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -524,23 +524,27 @@ extern void check_pending(int signum);

 SYSCALL_DEFINE2(getdomainname, char __user *, name, int, len)
 {
-        int nlen, err;
+	int nlen, err;
+	char tmp[__NEW_UTS_LEN + 1];

 	if (len < 0)
 		return -EINVAL;

- 	down_read(&uts_sem);
- 	
+	down_read(&uts_sem);
+
 	nlen = strlen(utsname()->domainname) + 1;
 	err = -EINVAL;
 	if (nlen > len)
-		goto out;
+		goto out_unlock;
+	memcpy(tmp, utsname()->domainname, nlen);

-	err = -EFAULT;
-	if (!copy_to_user(name, utsname()->domainname, nlen))
-		err = 0;
+	up_read(&uts_sem);

-out:
+	if (copy_to_user(name, tmp, nlen))
+		return -EFAULT;
+	return 0;
+
+out_unlock:
 	up_read(&uts_sem);
 	return err;
 }
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -79,24 +79,33 @@ ENTRY(entry_SYSENTER_compat)
 	ASM_CLAC			/* Clear AC after saving FLAGS */

 	pushq	$__USER32_CS		/* pt_regs->cs */
-	xorq    %r8,%r8
-	pushq	%r8			/* pt_regs->ip = 0 (placeholder) */
+	pushq	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
+	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
-	pushq   %r8                     /* pt_regs->r12 = 0 */
-	pushq   %r8                     /* pt_regs->r13 = 0 */
-	pushq   %r8                     /* pt_regs->r14 = 0 */
-	pushq   %r8                     /* pt_regs->r15 = 0 */
+	xorl	%ebp, %ebp		/* nospec   rbp */
+	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
+	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
+	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
+	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld

 	/*
@@ -185,17 +194,26 @@ ENTRY(entry_SYSCALL_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	xorq    %r8,%r8
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
+	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
-	pushq   %r8                     /* pt_regs->r12 = 0 */
-	pushq   %r8                     /* pt_regs->r13 = 0 */
-	pushq   %r8                     /* pt_regs->r14 = 0 */
-	pushq   %r8                     /* pt_regs->r15 = 0 */
+	xorl	%ebp, %ebp		/* nospec   rbp */
+	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
+	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
+	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
+	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */

 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -292,17 +310,26 @@ ENTRY(entry_INT80_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	xorq    %r8,%r8
-	pushq   %r8                     /* pt_regs->r8  = 0 */
-	pushq   %r8                     /* pt_regs->r9  = 0 */
-	pushq   %r8                     /* pt_regs->r10 = 0 */
-	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
+	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
+	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
+	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   %r12                    /* pt_regs->r12 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld

 	/*
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -6,6 +6,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H

+#include <asm/nospec-branch.h>
+
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -31,6 +33,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -43,6 +46,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 }

 static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -55,6 +59,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -67,6 +72,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 	return error;
 }

--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,

 	asm volatile ("cmp %1,%2; sbb %0,%0;"
 			:"=r" (mask)
-			:"r"(size),"r" (index)
+			:"g"(size),"r" (index)
 			:"cc");
 	return mask;
 }
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -28,6 +28,7 @@ enum cpuid_leafs
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
 	CPUID_8000_0007_EBX,
+	CPUID_7_EDX,
 };

 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -78,8 +79,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))

 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -100,8 +102,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))

 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -12,7 +12,7 @@
 /*
 * Defines x86 CPU feature bits
 */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
+#define NCAPINTS	19	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */

 /*
@@ -193,14 +193,29 @@
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */

-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* Fill RSB on context switches */
+#define X86_FEATURE_RETPOLINE	( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+
+#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_RSB_CTXSW	( 7*32+19) /* "" Fill RSB on context switches */
+
+#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD	( 7*32+17) /* Speculative Store Bypass Disable */

-#define X86_FEATURE_RETPOLINE	( 7*32+29) /* Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+30) /* AMD Retpoline mitigation for Spectre variant 2 */
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */

+#define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/
+#define X86_FEATURE_USE_IBRS_FW	( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD	( 7*32+24) /* "" AMD SSBD implementation */
+
+#define X86_FEATURE_IBRS	( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB	( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP	( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN		( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV	( 7*32+29) /* "" L1TF workaround PTE inversion */
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
@@ -251,6 +266,10 @@

 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+#define X86_FEATURE_AMD_IBPB	(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS	(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD	(13*32+25) /* Virtualized Speculative Store Bypass Disable */

 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
 #define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
@@ -285,6 +304,16 @@
 #define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
 #define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */

+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
+#define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
+
 /*
 * BUG word(s)
 */
@@ -302,5 +331,7 @@
 #define X86_BUG_CPU_MELTDOWN	X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1	X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2	X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF		X86_BUG(18) /* CPU is affected by L1 Terminal Fault */

 #endif /* _ASM_X86_CPUFEATURES_H */
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -59,6 +59,7 @@
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)

 #endif /* _ASM_X86_DISABLED_FEATURES_H */
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,7 @@

 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/nospec-branch.h>

 /*
 * We map the EFI regions needed for runtime services non-contiguously,
@@ -41,8 +42,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 ({									\
 	efi_status_t __s;						\
 	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 	__s = ((efi_##f##_t __attribute__((regparm(0)))*)		\
 		efi.systab->runtime->f)(args);				\
+	firmware_restrict_branch_speculation_end();			\
 	kernel_fpu_end();						\
 	__s;								\
 })
@@ -51,8 +54,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define __efi_call_virt(f, args...) \
 ({									\
 	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 	((efi_##f##_t __attribute__((regparm(0)))*)			\
 		efi.systab->runtime->f)(args);				\
+	firmware_restrict_branch_speculation_end();			\
 	kernel_fpu_end();						\
 })

@@ -73,7 +78,9 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+	firmware_restrict_branch_speculation_end();			\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 	__s;								\
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -12,6 +12,7 @@
 */

 #define INTEL_FAM6_CORE_YONAH		0x0E
+
 #define INTEL_FAM6_CORE2_MEROM		0x0F
 #define INTEL_FAM6_CORE2_MEROM_L	0x16
 #define INTEL_FAM6_CORE2_PENRYN		0x17
@@ -20,6 +21,7 @@
 #define INTEL_FAM6_NEHALEM		0x1E
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
+
 #define INTEL_FAM6_WESTMERE		0x25
 #define INTEL_FAM6_WESTMERE2		0x1F
 #define INTEL_FAM6_WESTMERE_EP		0x2C
@@ -36,9 +38,9 @@
 #define INTEL_FAM6_HASWELL_GT3E		0x46

 #define INTEL_FAM6_BROADWELL_CORE	0x3D
-#define INTEL_FAM6_BROADWELL_XEON_D	0x56
 #define INTEL_FAM6_BROADWELL_GT3E	0x47
 #define INTEL_FAM6_BROADWELL_X		0x4F
+#define INTEL_FAM6_BROADWELL_XEON_D	0x56

 #define INTEL_FAM6_SKYLAKE_MOBILE	0x4E
 #define INTEL_FAM6_SKYLAKE_DESKTOP	0x5E
@@ -56,13 +58,15 @@
 #define INTEL_FAM6_ATOM_SILVERMONT1	0x37 /* BayTrail/BYT / Valleyview */
 #define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
 #define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD1	0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MERRIFIELD2	0x5A /* Annidale */
+#define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
+#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Annidale */
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C
 #define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
+#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A

 /* Xeon Phi */

 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
+#define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */

 #endif /* _ASM_X86_INTEL_FAMILY_H */
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -351,4 +351,10 @@ extern void arch_phys_wc_del(int handle);
 #define arch_phys_wc_add arch_phys_wc_add
 #endif

+#ifdef CONFIG_X86_PAT
+extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size);
+extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size);
+#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc
+#endif
+
 #endif /* _ASM_X86_IO_H */
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -8,7 +8,9 @@
 * Interrupt control:
 */

-static inline unsigned long native_save_fl(void)
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
+extern inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;

@@ -26,7 +28,8 @@ static inline unsigned long native_save_fl(void)
 	return flags;
 }

-static inline void native_restore_fl(unsigned long flags)
+extern inline void native_restore_fl(unsigned long flags);
+extern inline void native_restore_fl(unsigned long flags)
 {
 	asm volatile("push %0 ; popf"
 		     : /* no output */
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,12 +3,18 @@

 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/atomic.h>

 /*
- * The x86 doesn't have a mmu context, but
- * we put the segment information here.
+ * x86 has arch-specific MMU state beyond what lives in mm_struct.
 */
 typedef struct {
+	/*
+	 * ctx_id uniquely identifies this mm_struct.  A ctx_id will never
+	 * be reused, and zero is not a valid ctx_id.
+	 */
+	u64 ctx_id;
+
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 #endif
@@ -24,6 +30,11 @@ typedef struct {
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
 } mm_context_t;

+#define INIT_MM_CONTEXT(mm)						\
+	.context = {							\
+		.ctx_id = 1,						\
+	}
+
 void leave_mm(int cpu);

 #endif /* _ASM_X86_MMU_H */
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -11,6 +11,9 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+
+extern atomic64_t last_mm_ctx_id;
+
 #ifndef CONFIG_PARAVIRT
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
@@ -52,15 +55,15 @@ struct ldt_struct {
 /*
 * Used for LDT copy/destruction.
 */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
+int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context_ldt(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context(struct task_struct *tsk,
-				   struct mm_struct *mm)
+static inline int init_new_context_ldt(struct task_struct *tsk,
+				       struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) {}
 #endif

 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -102,6 +105,17 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 }

+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
+	return init_new_context_ldt(tsk, mm);
+}
+static inline void destroy_context(struct mm_struct *mm)
+{
+	destroy_context_ldt(mm);
+}
+
 extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		      struct task_struct *tsk);

--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -32,6 +32,15 @@
 #define EFER_FFXSR		(1<<_EFER_FFXSR)

 /* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
+#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+#define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
+#define SPEC_CTRL_SSBD			(1 << SPEC_CTRL_SSBD_SHIFT)   /* Speculative Store Bypass Disable */
+
+#define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
+#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+
 #define MSR_IA32_PERFCTR0		0x000000c1
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
@@ -45,6 +54,16 @@
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)

 #define MSR_MTRRcap			0x000000fe
+
+#define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
+#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_SSB_NO			(1 << 4)   /*
+						    * Not susceptible to Speculative Store Bypass
+						    * attack, so no Speculative Store Bypass
+						    * control required.
+						    */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e

@@ -132,6 +151,7 @@

 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_TR			(1UL <<  6)
 #define DEBUGCTLMSR_BTS			(1UL <<  7)
@@ -308,6 +328,8 @@
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */

+#define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
+
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -6,6 +6,7 @@
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
+#include <asm/msr-index.h>

 /*
 * Fill the CPU return stack buffer.
@@ -171,6 +172,14 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };

+/* The Speculative Store Bypass disable variants */
+enum ssb_mitigation {
+	SPEC_STORE_BYPASS_NONE,
+	SPEC_STORE_BYPASS_DISABLE,
+	SPEC_STORE_BYPASS_PRCTL,
+	SPEC_STORE_BYPASS_SECCOMP,
+};
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];

@@ -194,6 +203,51 @@ static inline void vmexit_fill_RSB(void)
 #endif
 }

+static __always_inline
+void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
+{
+	asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
+		: : "c" (msr),
+		    "a" ((u32)val),
+		    "d" ((u32)(val >> 32)),
+		    [feature] "i" (feature)
+		: "memory");
+}
+
+static inline void indirect_branch_prediction_barrier(void)
+{
+	u64 val = PRED_CMD_IBPB;
+
+	alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
+}
+
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
+/*
+ * With retpoline, we must use IBRS to restrict branch prediction
+ * before calling into firmware.
+ *
+ * (Implemented as CPP macros due to header hell.)
+ */
+#define firmware_restrict_branch_speculation_start()			\
+do {									\
+	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
+									\
+	preempt_disable();						\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
+			      X86_FEATURE_USE_IBRS_FW);			\
+} while (0)
+
+#define firmware_restrict_branch_speculation_end()			\
+do {									\
+	u64 val = x86_spec_ctrl_base;					\
+									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
+			      X86_FEATURE_USE_IBRS_FW);			\
+	preempt_enable();						\
+} while (0)
+
 #endif /* __ASSEMBLY__ */

 /*
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -27,8 +27,13 @@
 #define N_EXCEPTION_STACKS 1

 #ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT	44
+/*
+ * This is beyond the 44 bit limit imposed by the 32bit long pfns,
+ * but we need the full mask to make sure inverted PROT_NONE
+ * entries have all the host bits set in a guest.
+ * The real limit is still 44 bits.
+ */
+#define __PHYSICAL_MASK_SHIFT	52
 #define __VIRTUAL_MASK_SHIFT	32

 #else  /* !CONFIG_X86_PAE */
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -77,4 +77,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })

+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+	return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_H */
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_PGTABLE_3LEVEL_H
 #define _ASM_X86_PGTABLE_3LEVEL_H

+#include <asm/atomic64_32.h>
+
 /*
 * Intel Physical Address Extension (PAE) Mode - three-level page
 * tables on PPro+ CPUs.
@@ -142,10 +144,7 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 {
 	pte_t res;

-	/* xchg acts as a barrier before the setting of the high bits */
-	res.pte_low = xchg(&ptep->pte_low, 0);
-	res.pte_high = ptep->pte_high;
-	ptep->pte_high = 0;
+	res.pte = (pteval_t)atomic64_xchg((atomic64_t *)ptep, 0);

 	return res;
 }
@@ -177,11 +176,44 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 #endif

 /* Encode and de-code a swap entry */
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
+
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)			(((x).val) & 0x1f)
 #define __swp_offset(x)			((x).val >> 5)
 #define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
+
+/*
+ * Normally, __swp_entry() converts from arch-independent swp_entry_t to
+ * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
+ * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
+ * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
+ * __swp_entry_to_pte() through the following helper macro based on 64bit
+ * __swp_entry().
+ */
+#define __swp_pteval_entry(type, offset) ((pteval_t) { \
+	(~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
+
+#define __swp_entry_to_pte(x)	((pte_t){ .pte = \
+		__swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
+/*
+ * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
+ * swp_entry_t, but also has to convert it from 64bit to the 32bit
+ * intermediate representation, using the following macros based on 64bit
+ * __swp_type() and __swp_offset().
+ */
+#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
+#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
+
+#define __pte_to_swp_entry(pte)	(__swp_entry(__pteval_swp_type(pte), \
+					     __pteval_swp_offset(pte)))
+
+#include <asm/pgtable-invert.h>

 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */
--- a/arch/x86/include/asm/pgtable-invert.h
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+/*
+ * A clear pte value is special, and doesn't get inverted.
+ *
+ * Note that even users that only pass a pgprot_t (rather
+ * than a full pte) won't trigger the special zero case,
+ * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED
+ * set. So the all zero case really is limited to just the
+ * cleared page table entry case.
+ */
+static inline bool __pte_needs_invert(u64 val)
+{
+	return val && !(val & _PAGE_PRESENT);
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+	return __pte_needs_invert(val) ?  ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	/*
+	 * When a PTE transitions from NONE to !NONE or vice-versa
+	 * invert the PFN part to stop speculation.
+	 * pte_pfn undoes this when needed.
+	 */
+	if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+		val = (val & ~mask) | (~val & mask);
+	return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -148,19 +148,34 @@ static inline int pte_special(pte_t pte)
 	return pte_flags(pte) & _PAGE_SPECIAL;
 }

+/* Entries that were set to PROT_NONE are inverted */
+
+static inline u64 protnone_mask(u64 val);
+
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	phys_addr_t pfn = pte_val(pte);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }

 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
+	phys_addr_t pfn = pmd_val(pmd);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }

 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+	phys_addr_t pfn = pud_val(pud);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+}
+
+static inline unsigned long pgd_pfn(pgd_t pgd)
+{
+	return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }

 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
@@ -305,11 +320,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_RW);
 }

-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline int pte_soft_dirty(pte_t pte)
 {
@@ -359,19 +369,58 @@ static inline pgprotval_t massage_pgprot(pgprot_t pgprot)

 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     massage_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PTE_PFN_MASK;
+	return __pte(pfn | massage_pgprot(pgprot));
 }

 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     massage_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PMD_PAGE_MASK;
+	return __pmd(pfn | massage_pgprot(pgprot));
 }

+static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
+{
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PUD_PAGE_MASK;
+	return __pud(pfn | massage_pgprot(pgprot));
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return pfn_pmd(pmd_pfn(pmd),
+		       __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
+}
+
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return __pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return __pud(v & ~clear);
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_PSE);
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	pteval_t val = pte_val(pte);
+	pteval_t val = pte_val(pte), oldval = val;

 	/*
 	 * Chop off the NX bit (if present), and add the NX portion of
@@ -379,17 +428,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 */
 	val &= _PAGE_CHG_MASK;
 	val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
 	return __pte(val);
 }

 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmdval_t val = pmd_val(pmd);
+	pmdval_t val = pmd_val(pmd), oldval = val;

 	val &= _HPAGE_CHG_MASK;
 	val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
 	return __pmd(val);
 }

@@ -534,8 +583,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
-#define pmd_page(pmd)		\
-	pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT)
+#define pmd_page(pmd)	pfn_to_page(pmd_pfn(pmd))

 /*
 * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
@@ -603,8 +651,7 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
-#define pud_page(pud)		\
-	pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT)
+#define pud_page(pud)	pfn_to_page(pud_pfn(pud))

 /* Find an entry in the second-level page table.. */
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
@@ -644,7 +691,7 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
 * Currently stuck as a macro due to indirect forward reference to
 * linux/mmzone.h's __section_mem_map_addr() definition:
 */
-#define pgd_page(pgd)		pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
+#define pgd_page(pgd)		pfn_to_page(pgd_pfn(pgd))

 /* to find an entry in a page-table-directory. */
 static inline unsigned long pud_index(unsigned long address)
@@ -926,6 +973,14 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 }
 #endif

+#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
+extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return boot_cpu_has_bug(X86_BUG_L1TF);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */

--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -163,18 +163,52 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
 #define pte_unmap(pte) ((void)(pte))/* NOP */

-/* Encode and de-code a swap entry */
-#define SWP_TYPE_BITS 5
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+/*
+ * Encode and de-code a swap entry
+ *
+ * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
+ * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ *
+ * G (8) is aliased and used as a PROT_NONE indicator for
+ * !present ptes.  We need to start storing swap entries above
+ * there.  We also need to avoid using A and D because of an
+ * erratum where they can be incorrectly set by hardware on
+ * non-present PTEs.
+ *
+ * SD (1) in swp entry is used to store soft dirty bit, which helps us
+ * remember soft dirty over page migration
+ *
+ * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
+ * but also L and G.
+ *
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
+ */
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)

 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)

-#define __swp_type(x)			(((x).val >> (_PAGE_BIT_PRESENT + 1)) \
-					 & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)			((x).val >> SWP_OFFSET_SHIFT)
-#define __swp_entry(type, offset)	((swp_entry_t) { \
-					 ((type) << (_PAGE_BIT_PRESENT + 1)) \
-					 | ((offset) << SWP_OFFSET_SHIFT) })
+/* Extract the high bits for type */
+#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
+
+/* Shift up (to get rid of type), then down to get value */
+#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+
+/*
+ * Shift the offset up "too far" by TYPE bits, then down again
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
+ */
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+	(~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
+
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })

@@ -201,6 +235,8 @@ extern void cleanup_highmap(void);
 extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);

+#include <asm/pgtable-invert.h>
+
 #endif /* !__ASSEMBLY__ */

 #endif /* _ASM_X86_PGTABLE_64_H */
--- a/Show More
+++ b/Show More