Merge tag 'v3.13-rc5' into next

Linux 3.13-rc5

* tag 'v3.13-rc5': (231 commits)
  Linux 3.13-rc5
  aio: clean up and fix aio_setup_ring page mapping
  aio/migratepages: make aio migrate pages sane
  aio: fix kioctx leak introduced by "aio: Fix a trinity splat"
  Don't set the INITRD_COMPRESS environment variable automatically
  mm: fix build of split ptlock code
  pstore: Don't allow high traffic options on fragile devices
  mm: do not allocate page->ptl dynamically, if spinlock_t fits to long
  mm: page_alloc: revert NUMA aspect of fair allocation policy
  Revert "mm: page_alloc: exclude unreclaimable allocations from zone fairness policy"
  mm: Fix NULL pointer dereference in madvise(MADV_WILLNEED) support
  qla2xxx: Fix scsi_host leak on qlt_lport_register callback failure
  target: Remove extra percpu_ref_init
  arm64: ptrace: avoid using HW_BREAKPOINT_EMPTY for disabled events
  ARC: Allow conditional multiple inclusion of uapi/asm/unistd.h
  target/file: Update hw_max_sectors based on current block_size
  iser-target: Move INIT_WORK setup into isert_create_device_ib_res
  iscsi-target: Fix incorrect np->np_thread NULL assignment
  mm/hugetlb: check for pte NULL pointer in __page_check_address()
  fix build with make 3.80
  ...

Conflicts:
	drivers/usb/phy/Kconfig

Documentation/module-signing.txt

@@ -0,0 +1,240 @@
+			==============================
+			KERNEL MODULE SIGNING FACILITY
+			==============================
+
+CONTENTS
+
+ - Overview.
+ - Configuring module signing.
+ - Generating signing keys.
+ - Public keys in the kernel.
+ - Manually signing modules.
+ - Signed modules and stripping.
+ - Loading signed modules.
+ - Non-valid signatures and unsigned modules.
+ - Administering/protecting the private key.
+
+
+========
+OVERVIEW
+========
+
+The kernel module signing facility cryptographically signs modules during
+installation and then checks the signature upon loading the module.  This
+allows increased kernel security by disallowing the loading of unsigned modules
+or modules signed with an invalid key.  Module signing increases security by
+making it harder to load a malicious module into the kernel.  The module
+signature checking is done by the kernel so that it is not necessary to have
+trusted userspace bits.
+
+This facility uses X.509 ITU-T standard certificates to encode the public keys
+involved.  The signatures are not themselves encoded in any industrial standard
+type.  The facility currently only supports the RSA public key encryption
+standard (though it is pluggable and permits others to be used).  The possible
+hash algorithms that can be used are SHA-1, SHA-224, SHA-256, SHA-384, and
+SHA-512 (the algorithm is selected by data in the signature).
+
+
+==========================
+CONFIGURING MODULE SIGNING
+==========================
+
+The module signing facility is enabled by going to the "Enable Loadable Module
+Support" section of the kernel configuration and turning on
+
+	CONFIG_MODULE_SIG	"Module signature verification"
+
+This has a number of options available:
+
+ (1) "Require modules to be validly signed" (CONFIG_MODULE_SIG_FORCE)
+
+     This specifies how the kernel should deal with a module that has a
+     signature for which the key is not known or a module that is unsigned.
+
+     If this is off (ie. "permissive"), then modules for which the key is not
+     available and modules that are unsigned are permitted, but the kernel will
+     be marked as being tainted.
+
+     If this is on (ie. "restrictive"), only modules that have a valid
+     signature that can be verified by a public key in the kernel's possession
+     will be loaded.  All other modules will generate an error.
+
+     Irrespective of the setting here, if the module has a signature block that
+     cannot be parsed, it will be rejected out of hand.
+
+
+ (2) "Automatically sign all modules" (CONFIG_MODULE_SIG_ALL)
+
+     If this is on then modules will be automatically signed during the
+     modules_install phase of a build.  If this is off, then the modules must
+     be signed manually using:
+
+	scripts/sign-file
+
+
+ (3) "Which hash algorithm should modules be signed with?"
+
+     This presents a choice of which hash algorithm the installation phase will
+     sign the modules with:
+
+	CONFIG_SIG_SHA1		"Sign modules with SHA-1"
+	CONFIG_SIG_SHA224	"Sign modules with SHA-224"
+	CONFIG_SIG_SHA256	"Sign modules with SHA-256"
+	CONFIG_SIG_SHA384	"Sign modules with SHA-384"
+	CONFIG_SIG_SHA512	"Sign modules with SHA-512"
+
+     The algorithm selected here will also be built into the kernel (rather
+     than being a module) so that modules signed with that algorithm can have
+     their signatures checked without causing a dependency loop.
+
+
+=======================
+GENERATING SIGNING KEYS
+=======================
+
+Cryptographic keypairs are required to generate and check signatures.  A
+private key is used to generate a signature and the corresponding public key is
+used to check it.  The private key is only needed during the build, after which
+it can be deleted or stored securely.  The public key gets built into the
+kernel so that it can be used to check the signatures as the modules are
+loaded.
+
+Under normal conditions, the kernel build will automatically generate a new
+keypair using openssl if one does not exist in the files:
+
+	signing_key.priv
+	signing_key.x509
+
+during the building of vmlinux (the public part of the key needs to be built
+into vmlinux) using parameters in the:
+
+	x509.genkey
+
+file (which is also generated if it does not already exist).
+
+It is strongly recommended that you provide your own x509.genkey file.
+
+Most notably, in the x509.genkey file, the req_distinguished_name section
+should be altered from the default:
+
+	[ req_distinguished_name ]
+	O = Magrathea
+	CN = Glacier signing key
+	emailAddress = slartibartfast@magrathea.h2g2
+
+The generated RSA key size can also be set with:
+
+	[ req ]
+	default_bits = 4096
+
+
+It is also possible to manually generate the key private/public files using the
+x509.genkey key generation configuration file in the root node of the Linux
+kernel sources tree and the openssl command.  The following is an example to
+generate the public/private key files:
+
+	openssl req -new -nodes -utf8 -sha256 -days 36500 -batch -x509 \
+	   -config x509.genkey -outform DER -out signing_key.x509 \
+	   -keyout signing_key.priv
+
+
+=========================
+PUBLIC KEYS IN THE KERNEL
+=========================
+
+The kernel contains a ring of public keys that can be viewed by root.  They're
+in a keyring called ".system_keyring" that can be seen by:
+
+	[root@deneb ~]# cat /proc/keys
+	...
+	223c7853 I------     1 perm 1f030000     0     0 keyring   .system_keyring: 1
+	302d2d52 I------     1 perm 1f010000     0     0 asymmetri Fedora kernel signing key: d69a84e6bce3d216b979e9505b3e3ef9a7118079: X509.RSA a7118079 []
+	...
+
+Beyond the public key generated specifically for module signing, any file
+placed in the kernel source root directory or the kernel build root directory
+whose name is suffixed with ".x509" will be assumed to be an X.509 public key
+and will be added to the keyring.
+
+Further, the architecture code may take public keys from a hardware store and
+add those in also (e.g. from the UEFI key database).
+
+Finally, it is possible to add additional public keys by doing:
+
+	keyctl padd asymmetric "" [.system_keyring-ID] <[key-file]
+
+e.g.:
+
+	keyctl padd asymmetric "" 0x223c7853 <my_public_key.x509
+
+Note, however, that the kernel will only permit keys to be added to
+.system_keyring _if_ the new key's X.509 wrapper is validly signed by a key
+that is already resident in the .system_keyring at the time the key was added.
+
+
+=========================
+MANUALLY SIGNING MODULES
+=========================
+
+To manually sign a module, use the scripts/sign-file tool available in
+the Linux kernel source tree.  The script requires 4 arguments:
+
+	1.  The hash algorithm (e.g., sha256)
+	2.  The private key filename
+	3.  The public key filename
+	4.  The kernel module to be signed
+
+The following is an example to sign a kernel module:
+
+	scripts/sign-file sha512 kernel-signkey.priv \
+		kernel-signkey.x509 module.ko
+
+The hash algorithm used does not have to match the one configured, but if it
+doesn't, you should make sure that hash algorithm is either built into the
+kernel or can be loaded without requiring itself.
+
+
+============================
+SIGNED MODULES AND STRIPPING
+============================
+
+A signed module has a digital signature simply appended at the end.  The string
+"~Module signature appended~." at the end of the module's file confirms that a
+signature is present but it does not confirm that the signature is valid!
+
+Signed modules are BRITTLE as the signature is outside of the defined ELF
+container.  Thus they MAY NOT be stripped once the signature is computed and
+attached.  Note the entire module is the signed payload, including any and all
+debug information present at the time of signing.
+
+
+======================
+LOADING SIGNED MODULES
+======================
+
+Modules are loaded with insmod, modprobe, init_module() or finit_module(),
+exactly as for unsigned modules as no processing is done in userspace.  The
+signature checking is all done within the kernel.
+
+
+=========================================
+NON-VALID SIGNATURES AND UNSIGNED MODULES
+=========================================
+
+If CONFIG_MODULE_SIG_FORCE is enabled or enforcemodulesig=1 is supplied on
+the kernel command line, the kernel will only load validly signed modules
+for which it has a public key.   Otherwise, it will also load modules that are
+unsigned.   Any module for which the kernel has a key, but which proves to have
+a signature mismatch will not be permitted to load.
+
+Any module that has an unparseable signature will be rejected.
+
+
+=========================================
+ADMINISTERING/PROTECTING THE PRIVATE KEY
+=========================================
+
+Since the private key is used to sign modules, viruses and malware could use
+the private key to sign modules and compromise the operating system.  The
+private key must be either destroyed or moved to a secure location and not kept
+in the root node of the kernel source tree.

Documentation/networking/ip-sysctl.txt

@@ -16,8 +16,12 @@ ip_default_ttl - INTEGER
 	Default: 64 (as recommended by RFC1700)
 
 ip_no_pmtu_disc - BOOLEAN
-	Disable Path MTU Discovery.
-	default FALSE
+	Disable Path MTU Discovery. If enabled and a
+	fragmentation-required ICMP is received, the PMTU to this
+	destination will be set to min_pmtu (see below). You will need
+	to raise min_pmtu to the smallest interface MTU on your system
+	manually if you want to avoid locally generated fragments.
+	Default: FALSE
 
 min_pmtu - INTEGER
 	default 552 - minimum discovered Path MTU

MAINTAINERS

@@ -1008,6 +1008,8 @@ M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-keystone/
+F:	drivers/clk/keystone/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
 
 ARM/LOGICPD PXA270 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
@@ -3761,9 +3763,11 @@ F:	include/uapi/linux/gigaset_dev.h
 
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
-S:	Maintained
+M:	Alexandre Courbot <gnurou@gmail.com>
 L:	linux-gpio@vger.kernel.org
-F:	Documentation/gpio.txt
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
+S:	Maintained
+F:	Documentation/gpio/
 F:	drivers/gpio/
 F:	include/linux/gpio*
 F:	include/asm-generic/gpio.h
@@ -3831,6 +3835,12 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/gspca/
 
+GUID PARTITION TABLE (GPT)
+M:	Davidlohr Bueso <davidlohr@hp.com>
+L:	linux-efi@vger.kernel.org
+S:	Maintained
+F:	block/partitions/efi.*
+
 STK1160 USB VIDEO CAPTURE DRIVER
 M:	Ezequiel Garcia <elezegarcia@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -5911,12 +5921,21 @@ M:	Steffen Klassert <steffen.klassert@secunet.com>
 M:	Herbert Xu <herbert@gondor.apana.org.au>
 M:	"David S. Miller" <davem@davemloft.net>
 L:	netdev@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git
 S:	Maintained
 F:	net/xfrm/
 F:	net/key/
 F:	net/ipv4/xfrm*
+F:	net/ipv4/esp4.c
+F:	net/ipv4/ah4.c
+F:	net/ipv4/ipcomp.c
+F:	net/ipv4/ip_vti.c
 F:	net/ipv6/xfrm*
+F:	net/ipv6/esp6.c
+F:	net/ipv6/ah6.c
+F:	net/ipv6/ipcomp6.c
+F:	net/ipv6/ip6_vti.c
 F:	include/uapi/linux/xfrm.h
 F:	include/net/xfrm.h
 
@@ -9571,7 +9590,7 @@ F:	drivers/xen/*swiotlb*
 
 XFS FILESYSTEM
 P:	Silicon Graphics Inc
-M:	Dave Chinner <dchinner@fromorbit.com>
+M:	Dave Chinner <david@fromorbit.com>
 M:	Ben Myers <bpm@sgi.com>
 M:	xfs@oss.sgi.com
 L:	xfs@oss.sgi.com

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = One Giant Leap for Frogkind
 
 # *DOCUMENTATION*
@@ -732,19 +732,15 @@ export mod_strip_cmd
 # Select initial ramdisk compression format, default is gzip(1).
 # This shall be used by the dracut(8) tool while creating an initramfs image.
 #
-INITRD_COMPRESS=gzip
-ifeq ($(CONFIG_RD_BZIP2), y)
-        INITRD_COMPRESS=bzip2
-else ifeq ($(CONFIG_RD_LZMA), y)
-        INITRD_COMPRESS=lzma
-else ifeq ($(CONFIG_RD_XZ), y)
-        INITRD_COMPRESS=xz
-else ifeq ($(CONFIG_RD_LZO), y)
-        INITRD_COMPRESS=lzo
-else ifeq ($(CONFIG_RD_LZ4), y)
-        INITRD_COMPRESS=lz4
-endif
-export INITRD_COMPRESS
+INITRD_COMPRESS-y                  := gzip
+INITRD_COMPRESS-$(CONFIG_RD_BZIP2) := bzip2
+INITRD_COMPRESS-$(CONFIG_RD_LZMA)  := lzma
+INITRD_COMPRESS-$(CONFIG_RD_XZ)    := xz
+INITRD_COMPRESS-$(CONFIG_RD_LZO)   := lzo
+INITRD_COMPRESS-$(CONFIG_RD_LZ4)   := lz4
+# do not export INITRD_COMPRESS, since we didn't actually
+# choose a sane default compression above.
+# export INITRD_COMPRESS := $(INITRD_COMPRESS-y)
 
 ifdef CONFIG_MODULE_SIG_ALL
 MODSECKEY = ./signing_key.priv

arch/arc/include/uapi/asm/unistd.h

@@ -8,7 +8,11 @@
 
 /******** no-legacy-syscalls-ABI *******/
 
-#ifndef _UAPI_ASM_ARC_UNISTD_H
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
 #define _UAPI_ASM_ARC_UNISTD_H
 
 #define __ARCH_WANT_SYS_EXECVE
@@ -36,4 +40,6 @@ __SYSCALL(__NR_arc_gettls, sys_arc_gettls)
 #define __NR_sysfs		(__NR_arch_specific_syscall + 3)
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
+#undef __SYSCALL
+
 #endif

arch/arm/boot/dts/r8a7790.dtsi

@@ -87,9 +87,9 @@
 		interrupts = <1 9 0xf04>;
 	};
 
-	gpio0: gpio@ffc40000 {
+	gpio0: gpio@e6050000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc40000 0 0x2c>;
+		reg = <0 0xe6050000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 4 0x4>;
 		#gpio-cells = <2>;
@@ -99,9 +99,9 @@
 		interrupt-controller;
 	};
 
-	gpio1: gpio@ffc41000 {
+	gpio1: gpio@e6051000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc41000 0 0x2c>;
+		reg = <0 0xe6051000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 5 0x4>;
 		#gpio-cells = <2>;
@@ -111,9 +111,9 @@
 		interrupt-controller;
 	};
 
-	gpio2: gpio@ffc42000 {
+	gpio2: gpio@e6052000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc42000 0 0x2c>;
+		reg = <0 0xe6052000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 6 0x4>;
 		#gpio-cells = <2>;
@@ -123,9 +123,9 @@
 		interrupt-controller;
 	};
 
-	gpio3: gpio@ffc43000 {
+	gpio3: gpio@e6053000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc43000 0 0x2c>;
+		reg = <0 0xe6053000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 7 0x4>;
 		#gpio-cells = <2>;
@@ -135,9 +135,9 @@
 		interrupt-controller;
 	};
 
-	gpio4: gpio@ffc44000 {
+	gpio4: gpio@e6054000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc44000 0 0x2c>;
+		reg = <0 0xe6054000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 8 0x4>;
 		#gpio-cells = <2>;
@@ -147,9 +147,9 @@
 		interrupt-controller;
 	};
 
-	gpio5: gpio@ffc45000 {
+	gpio5: gpio@e6055000 {
 		compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
-		reg = <0 0xffc45000 0 0x2c>;
+		reg = <0 0xe6055000 0 0x50>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 9 0x4>;
 		#gpio-cells = <2>;

arch/arm/mach-omap2/display.c

@@ -101,13 +101,51 @@ static const struct omap_dss_hwmod_data omap4_dss_hwmod_data[] __initconst = {
 	{ "dss_hdmi", "omapdss_hdmi", -1 },
 };
 
+static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
+{
+	u32 enable_mask, enable_shift;
+	u32 pipd_mask, pipd_shift;
+	u32 reg;
+
+	if (dsi_id == 0) {
+		enable_mask = OMAP4_DSI1_LANEENABLE_MASK;
+		enable_shift = OMAP4_DSI1_LANEENABLE_SHIFT;
+		pipd_mask = OMAP4_DSI1_PIPD_MASK;
+		pipd_shift = OMAP4_DSI1_PIPD_SHIFT;
+	} else if (dsi_id == 1) {
+		enable_mask = OMAP4_DSI2_LANEENABLE_MASK;
+		enable_shift = OMAP4_DSI2_LANEENABLE_SHIFT;
+		pipd_mask = OMAP4_DSI2_PIPD_MASK;
+		pipd_shift = OMAP4_DSI2_PIPD_SHIFT;
+	} else {
+		return -ENODEV;
+	}
+
+	reg = omap4_ctrl_pad_readl(OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY);
+
+	reg &= ~enable_mask;
+	reg &= ~pipd_mask;
+
+	reg |= (lanes << enable_shift) & enable_mask;
+	reg |= (lanes << pipd_shift) & pipd_mask;
+
+	omap4_ctrl_pad_writel(reg, OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY);
+
+	return 0;
+}
+
 static int omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
 {
+	if (cpu_is_omap44xx())
+		return omap4_dsi_mux_pads(dsi_id, lane_mask);
+
 	return 0;
 }
 
 static void omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
 {
+	if (cpu_is_omap44xx())
+		omap4_dsi_mux_pads(dsi_id, 0);
 }
 
 static int omap_dss_set_min_bus_tput(struct device *dev, unsigned long tput)

arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c

@@ -8,8 +8,6 @@
  * published by the Free Software Foundation.
 */
 
-#include <linux/clk-provider.h>
-#include <linux/irqchip.h>
 #include <linux/of_platform.h>
 
 #include <asm/mach/arch.h>
@@ -48,15 +46,9 @@ static void __init s3c64xx_dt_map_io(void)
 		panic("SoC is not S3C64xx!");
 }
 
-static void __init s3c64xx_dt_init_irq(void)
-{
-	of_clk_init(NULL);
-	samsung_wdt_reset_of_init();
-	irqchip_init();
-};
-
 static void __init s3c64xx_dt_init_machine(void)
 {
+	samsung_wdt_reset_of_init();
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
@@ -79,7 +71,6 @@ DT_MACHINE_START(S3C6400_DT, "Samsung S3C64xx (Flattened Device Tree)")
 	/* Maintainer: Tomasz Figa <tomasz.figa@gmail.com> */
 	.dt_compat	= s3c64xx_dt_compat,
 	.map_io		= s3c64xx_dt_map_io,
-	.init_irq	= s3c64xx_dt_init_irq,
 	.init_machine	= s3c64xx_dt_init_machine,
 	.restart        = s3c64xx_dt_restart,
 MACHINE_END

arch/arm/mach-shmobile/board-lager.c

@@ -245,7 +245,9 @@ static void __init lager_init(void)
 {
 	lager_add_standard_devices();
 
-	phy_register_fixup_for_id("r8a7790-ether-ff:01", lager_ksz8041_fixup);
+	if (IS_ENABLED(CONFIG_PHYLIB))
+		phy_register_fixup_for_id("r8a7790-ether-ff:01",
+					  lager_ksz8041_fixup);
 }
 
 static const char * const lager_boards_compat_dt[] __initconst = {

arch/arm/xen/enlighten.c

@@ -96,7 +96,7 @@ static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
 	struct remap_data *info = data;
 	struct page *page = info->pages[info->index++];
 	unsigned long pfn = page_to_pfn(page);
-	pte_t pte = pfn_pte(pfn, info->prot);
+	pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
 
 	if (map_foreign_page(pfn, info->fgmfn, info->domid))
 		return -EFAULT;
@@ -224,10 +224,10 @@ static int __init xen_guest_init(void)
 	}
 	if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
 		return 0;
-	xen_hvm_resume_frames = res.start >> PAGE_SHIFT;
+	xen_hvm_resume_frames = res.start;
 	xen_events_irq = irq_of_parse_and_map(node, 0);
 	pr_info("Xen %s support found, events_irq=%d gnttab_frame_pfn=%lx\n",
-			version, xen_events_irq, xen_hvm_resume_frames);
+			version, xen_events_irq, (xen_hvm_resume_frames >> PAGE_SHIFT));
 	xen_domain_type = XEN_HVM_DOMAIN;
 
 	xen_setup_features();

arch/arm64/include/asm/xen/page-coherent.h

@@ -23,25 +23,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     struct dma_attrs *attrs)
 {
-	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 }
 
 static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
 		struct dma_attrs *attrs)
 {
-	__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
 }
 
 static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
 }
 
 static inline void xen_dma_sync_single_for_device(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
 }
 #endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */

arch/arm64/kernel/ptrace.c

@@ -214,31 +214,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 {
 	int err, len, type, disabled = !ctrl.enabled;
 
-	if (disabled) {
-		len = 0;
-		type = HW_BREAKPOINT_EMPTY;
-	} else {
-		err = arch_bp_generic_fields(ctrl, &len, &type);
-		if (err)
-			return err;
-
-		switch (note_type) {
-		case NT_ARM_HW_BREAK:
-			if ((type & HW_BREAKPOINT_X) != type)
-				return -EINVAL;
-			break;
-		case NT_ARM_HW_WATCH:
-			if ((type & HW_BREAKPOINT_RW) != type)
-				return -EINVAL;
-			break;
-		default:
+	attr->disabled = disabled;
+	if (disabled)
+		return 0;
+
+	err = arch_bp_generic_fields(ctrl, &len, &type);
+	if (err)
+		return err;
+
+	switch (note_type) {
+	case NT_ARM_HW_BREAK:
+		if ((type & HW_BREAKPOINT_X) != type)
 			return -EINVAL;
-		}
+		break;
+	case NT_ARM_HW_WATCH:
+		if ((type & HW_BREAKPOINT_RW) != type)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->disabled	= disabled;
 
 	return 0;
 }

arch/powerpc/include/asm/kvm_book3s.h

@@ -192,6 +192,10 @@ extern void kvmppc_load_up_vsx(void);
 extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
 extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
 extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
+extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+				 struct kvm_vcpu *vcpu);
+extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+				   struct kvmppc_book3s_shadow_vcpu *svcpu);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {

arch/powerpc/include/asm/kvm_book3s_asm.h

@@ -79,6 +79,7 @@ struct kvmppc_host_state {
 	ulong vmhandler;
 	ulong scratch0;
 	ulong scratch1;
+	ulong scratch2;
 	u8 in_guest;
 	u8 restore_hid5;
 	u8 napping;
@@ -106,6 +107,7 @@ struct kvmppc_host_state {
 };
 
 struct kvmppc_book3s_shadow_vcpu {
+	bool in_use;
 	ulong gpr[14];
 	u32 cr;
 	u32 xer;

arch/powerpc/include/asm/opal.h

@@ -720,13 +720,13 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val);
+int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
 int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		       uint32_t addr, uint32_t data, uint32_t sz);
 int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
-		      uint32_t addr, uint32_t *data, uint32_t sz);
+		      uint32_t addr, __be32 *data, uint32_t sz);
 int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
 int64_t opal_manage_flash(uint8_t op);
 int64_t opal_update_flash(uint64_t blk_list);

arch/powerpc/include/asm/switch_to.h

@@ -35,7 +35,7 @@ extern void giveup_vsx(struct task_struct *);
 extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
-extern void switch_booke_debug_regs(struct thread_struct *new_thread);
+extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
 #ifndef CONFIG_SMP
 extern void discard_lazy_cpu_state(void);

arch/powerpc/kernel/asm-offsets.c

@@ -576,6 +576,7 @@ int main(void)
 	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
 	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
 	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+	HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
 	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
 	HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
 	HSTATE_FIELD(HSTATE_NAPPING, napping);

arch/powerpc/kernel/crash_dump.c

@@ -124,15 +124,15 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 {
 	unsigned long addr;
-	const u32 *basep, *sizep;
+	const __be32 *basep, *sizep;
 	unsigned int rtas_start = 0, rtas_end = 0;
 
 	basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
 	sizep = of_get_property(rtas.dev, "rtas-size", NULL);
 
 	if (basep && sizep) {
-		rtas_start = *basep;
-		rtas_end = *basep + *sizep;
+		rtas_start = be32_to_cpup(basep);
+		rtas_end = rtas_start + be32_to_cpup(sizep);
 	}
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {

arch/powerpc/kernel/process.c

@@ -339,7 +339,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread)
 #endif
 }
 
-static void prime_debug_regs(struct thread_struct *thread)
+static void prime_debug_regs(struct debug_reg *debug)
 {
 	/*
 	 * We could have inherited MSR_DE from userspace, since
@@ -348,22 +348,22 @@ static void prime_debug_regs(struct thread_struct *thread)
 	 */
 	mtmsr(mfmsr() & ~MSR_DE);
 
-	mtspr(SPRN_IAC1, thread->debug.iac1);
-	mtspr(SPRN_IAC2, thread->debug.iac2);
+	mtspr(SPRN_IAC1, debug->iac1);
+	mtspr(SPRN_IAC2, debug->iac2);
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
-	mtspr(SPRN_IAC3, thread->debug.iac3);
-	mtspr(SPRN_IAC4, thread->debug.iac4);
+	mtspr(SPRN_IAC3, debug->iac3);
+	mtspr(SPRN_IAC4, debug->iac4);
 #endif
-	mtspr(SPRN_DAC1, thread->debug.dac1);
-	mtspr(SPRN_DAC2, thread->debug.dac2);
+	mtspr(SPRN_DAC1, debug->dac1);
+	mtspr(SPRN_DAC2, debug->dac2);
 #if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-	mtspr(SPRN_DVC1, thread->debug.dvc1);
-	mtspr(SPRN_DVC2, thread->debug.dvc2);
+	mtspr(SPRN_DVC1, debug->dvc1);
+	mtspr(SPRN_DVC2, debug->dvc2);
 #endif
-	mtspr(SPRN_DBCR0, thread->debug.dbcr0);
-	mtspr(SPRN_DBCR1, thread->debug.dbcr1);
+	mtspr(SPRN_DBCR0, debug->dbcr0);
+	mtspr(SPRN_DBCR1, debug->dbcr1);
 #ifdef CONFIG_BOOKE
-	mtspr(SPRN_DBCR2, thread->debug.dbcr2);
+	mtspr(SPRN_DBCR2, debug->dbcr2);
 #endif
 }
 /*
@@ -371,11 +371,11 @@ static void prime_debug_regs(struct thread_struct *thread)
  * debug registers, set the debug registers from the values
  * stored in the new thread.
  */
-void switch_booke_debug_regs(struct thread_struct *new_thread)
+void switch_booke_debug_regs(struct debug_reg *new_debug)
 {
 	if ((current->thread.debug.dbcr0 & DBCR0_IDM)
-		|| (new_thread->debug.dbcr0 & DBCR0_IDM))
-			prime_debug_regs(new_thread);
+		|| (new_debug->dbcr0 & DBCR0_IDM))
+			prime_debug_regs(new_debug);
 }
 EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
 #else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
@@ -683,7 +683,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	switch_booke_debug_regs(&new->thread);
+	switch_booke_debug_regs(&new->thread.debug);
 #else
 /*
  * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would

arch/powerpc/kernel/ptrace.c

@@ -1555,7 +1555,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			flush_fp_to_thread(child);
 			if (fpidx < (PT_FPSCR - PT_FPR0))
-				memcpy(&tmp, &child->thread.fp_state.fpr,
+				memcpy(&tmp, &child->thread.TS_FPR(fpidx),
 				       sizeof(long));
 			else
 				tmp = child->thread.fp_state.fpscr;
@@ -1588,7 +1588,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			flush_fp_to_thread(child);
 			if (fpidx < (PT_FPSCR - PT_FPR0))
-				memcpy(&child->thread.fp_state.fpr, &data,
+				memcpy(&child->thread.TS_FPR(fpidx), &data,
 				       sizeof(long));
 			else
 				child->thread.fp_state.fpscr = data;

arch/powerpc/kernel/setup-common.c

@@ -479,7 +479,7 @@ void __init smp_setup_cpu_maps(void)
 	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) &&
 	    (dn = of_find_node_by_path("/rtas"))) {
 		int num_addr_cell, num_size_cell, maxcpus;
-		const unsigned int *ireg;
+		const __be32 *ireg;
 
 		num_addr_cell = of_n_addr_cells(dn);
 		num_size_cell = of_n_size_cells(dn);
@@ -489,7 +489,7 @@ void __init smp_setup_cpu_maps(void)
 		if (!ireg)
 			goto out;
 
-		maxcpus = ireg[num_addr_cell + num_size_cell];
+		maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell);
 
 		/* Double maxcpus for processors which have SMT capability */
 		if (cpu_has_feature(CPU_FTR_SMT))

arch/powerpc/kernel/smp.c

@@ -580,7 +580,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 int cpu_to_core_id(int cpu)
 {
 	struct device_node *np;
-	const int *reg;
+	const __be32 *reg;
 	int id = -1;
 
 	np = of_get_cpu_node(cpu, NULL);
@@ -591,7 +591,7 @@ int cpu_to_core_id(int cpu)
 	if (!reg)
 		goto out;
 
-	id = *reg;
+	id = be32_to_cpup(reg);
 out:
 	of_node_put(np);
 	return id;

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -469,11 +469,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		slb_v = vcpu->kvm->arch.vrma_slb_v;
 	}
 
+	preempt_disable();
 	/* Find the HPTE in the hash table */
 	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
 					 HPTE_V_VALID | HPTE_V_ABSENT);
-	if (index < 0)
+	if (index < 0) {
+		preempt_enable();
 		return -ENOENT;
+	}
 	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
 	v = hptep[0] & ~HPTE_V_HVLOCK;
 	gr = kvm->arch.revmap[index].guest_rpte;
@@ -481,6 +484,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Unlock the HPTE */
 	asm volatile("lwsync" : : : "memory");
 	hptep[0] = v;
+	preempt_enable();
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
@@ -665,6 +669,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			return -EFAULT;
 	} else {
 		page = pages[0];
+		pfn = page_to_pfn(page);
 		if (PageHuge(page)) {
 			page = compound_head(page);
 			pte_size <<= compound_order(page);
@@ -689,7 +694,6 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			}
 			rcu_read_unlock_sched();
 		}
-		pfn = page_to_pfn(page);
 	}
 
 	ret = -EFAULT;
@@ -707,8 +711,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
 	}
 
-	/* Set the HPTE to point to pfn */
-	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+	/*
+	 * Set the HPTE to point to pfn.
+	 * Since the pfn is at PAGE_SIZE granularity, make sure we
+	 * don't mask out lower-order bits if psize < PAGE_SIZE.
+	 */
+	if (psize < PAGE_SIZE)
+		psize = PAGE_SIZE;
+	r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
 	if (hpte_is_writable(r) && !write_ok)
 		r = hpte_make_readonly(r);
 	ret = RESUME_GUEST;

arch/powerpc/kvm/book3s_hv.c

@@ -131,8 +131,9 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
 	    vc->preempt_tb != TB_NIL) {
 		vc->stolen_tb += mftb() - vc->preempt_tb;
@@ -143,19 +144,20 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
 		vcpu->arch.busy_preempt = TB_NIL;
 	}
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
 static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
 		vc->preempt_tb = mftb();
 	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
 		vcpu->arch.busy_preempt = mftb();
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
 static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
@@ -486,11 +488,11 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
 	 */
 	if (vc->vcore_state != VCORE_INACTIVE &&
 	    vc->runner->arch.run_task != current) {
-		spin_lock(&vc->runner->arch.tbacct_lock);
+		spin_lock_irq(&vc->runner->arch.tbacct_lock);
 		p = vc->stolen_tb;
 		if (vc->preempt_tb != TB_NIL)
 			p += now - vc->preempt_tb;
-		spin_unlock(&vc->runner->arch.tbacct_lock);
+		spin_unlock_irq(&vc->runner->arch.tbacct_lock);
 	} else {
 		p = vc->stolen_tb;
 	}
@@ -512,10 +514,10 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	core_stolen = vcore_stolen_time(vc, now);
 	stolen = core_stolen - vcpu->arch.stolen_logged;
 	vcpu->arch.stolen_logged = core_stolen;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	stolen += vcpu->arch.busy_stolen;
 	vcpu->arch.busy_stolen = 0;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	if (!dt || !vpa)
 		return;
 	memset(dt, 0, sizeof(struct dtl_entry));
@@ -589,7 +591,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
 			return RESUME_HOST;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		rc = kvmppc_rtas_hcall(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 		if (rc == -ENOENT)
 			return RESUME_HOST;
@@ -1115,13 +1119,13 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	now = mftb();
 	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
 		vcpu->arch.stolen_logged;
 	vcpu->arch.busy_preempt = now;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
 	list_del(&vcpu->arch.run_list);
 }

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -225,6 +225,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		is_io = pa & (HPTE_R_I | HPTE_R_W);
 		pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
 		pa &= PAGE_MASK;
+		pa |= gpa & ~PAGE_MASK;
 	} else {
 		/* Translate to host virtual address */
 		hva = __gfn_to_hva_memslot(memslot, gfn);
@@ -238,13 +239,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 				ptel = hpte_make_readonly(ptel);
 			is_io = hpte_cache_bits(pte_val(pte));
 			pa = pte_pfn(pte) << PAGE_SHIFT;
+			pa |= hva & (pte_size - 1);
+			pa |= gpa & ~PAGE_MASK;
 		}
 	}
 
 	if (pte_size < psize)
 		return H_PARAMETER;
-	if (pa && pte_size > psize)
-		pa |= gpa & (pte_size - 1);
 
 	ptel &= ~(HPTE_R_PP0 - psize);
 	ptel |= pa;
@@ -749,6 +750,10 @@ static int slb_base_page_shift[4] = {
 	20,	/* 1M, unsupported */
 };
 
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
 long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			      unsigned long valid)
 {

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -153,7 +153,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 13:	b	machine_check_fwnmi
 
-
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
  * Relocation is off and most register values are lost.
@@ -224,6 +223,11 @@ kvm_start_guest:
 	/* Clear our vcpu pointer so we don't come back in early */
 	li	r0, 0
 	std	r0, HSTATE_KVM_VCPU(r13)
+	/*
+	 * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+	 * the nap_count, because once the increment to nap_count is
+	 * visible we could be given another vcpu.
+	 */
 	lwsync
 	/* Clear any pending IPI - we're an offline thread */
 	ld	r5, HSTATE_XICS_PHYS(r13)
@@ -241,7 +245,6 @@ kvm_start_guest:
 	/* increment the nap count and then go to nap mode */
 	ld	r4, HSTATE_KVM_VCORE(r13)
 	addi	r4, r4, VCORE_NAP_COUNT
-	lwsync				/* make previous updates visible */
 51:	lwarx	r3, 0, r4
 	addi	r3, r3, 1
 	stwcx.	r3, 0, r4
@@ -751,15 +754,14 @@ kvmppc_interrupt_hv:
 	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
-	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
-	std	r9, HSTATE_HOST_R2(r13)
+	std	r9, HSTATE_SCRATCH2(r13)
 
 	lbz	r9, HSTATE_IN_GUEST(r13)
 	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
 	beq	kvmppc_bad_host_intr
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	cmpwi	r9, KVM_GUEST_MODE_GUEST
-	ld	r9, HSTATE_HOST_R2(r13)
+	ld	r9, HSTATE_SCRATCH2(r13)
 	beq	kvmppc_interrupt_pr
 #endif
 	/* We're now back in the host but in guest MMU context */
@@ -779,7 +781,7 @@ kvmppc_interrupt_hv:
 	std	r6, VCPU_GPR(R6)(r9)
 	std	r7, VCPU_GPR(R7)(r9)
 	std	r8, VCPU_GPR(R8)(r9)
-	ld	r0, HSTATE_HOST_R2(r13)
+	ld	r0, HSTATE_SCRATCH2(r13)
 	std	r0, VCPU_GPR(R9)(r9)
 	std	r10, VCPU_GPR(R10)(r9)
 	std	r11, VCPU_GPR(R11)(r9)
@@ -990,14 +992,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 */
 	/* Increment the threads-exiting-guest count in the 0xff00
 	   bits of vcore->entry_exit_count */
-	lwsync
 	ld	r5,HSTATE_KVM_VCORE(r13)
 	addi	r6,r5,VCORE_ENTRY_EXIT
 41:	lwarx	r3,0,r6
 	addi	r0,r3,0x100
 	stwcx.	r0,0,r6
 	bne	41b
-	lwsync
+	isync		/* order stwcx. vs. reading napping_threads */
 
 	/*
 	 * At this point we have an interrupt that we have to pass
@@ -1030,6 +1031,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	sld	r0,r0,r4
 	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
 	beq	43f
+	/* Order entry/exit update vs. IPIs */
+	sync
 	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
 	subf	r6,r4,r13
 42:	andi.	r0,r3,1
@@ -1638,10 +1641,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	bge	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
+	/* order napping_threads update vs testing entry_exit_count */
+	isync
 	li	r0,1
 	stb	r0,HSTATE_NAPPING(r13)
-	/* order napping_threads update vs testing entry_exit_count */
-	lwsync
 	mr	r4,r3
 	lwz	r7,VCORE_ENTRY_EXIT(r5)
 	cmpwi	r7,0x100

arch/powerpc/kvm/book3s_interrupts.S

@@ -129,29 +129,32 @@ kvm_start_lightweight:
 	 * R12      = exit handler id
 	 * R13      = PACA
 	 * SVCPU.*  = guest *
+	 * MSR.EE   = 1
 	 *
 	 */
 
+	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
+	/*
+	 * kvmppc_copy_from_svcpu can clobber volatile registers, save
+	 * the exit handler id to the vcpu and restore it from there later.
+	 */
+	stw	r12, VCPU_TRAP(r3)
+
 	/* Transfer reg values from shadow vcpu back to vcpu struct */
 	/* On 64-bit, interrupts are still off at this point */
-	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
 	GET_SHADOW_VCPU(r4)
 	bl	FUNC(kvmppc_copy_from_svcpu)
 	nop
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* Re-enable interrupts */
-	ld	r3, HSTATE_HOST_MSR(r13)
-	ori	r3, r3, MSR_EE
-	MTMSR_EERI(r3)
-
 	/*
 	 * Reload kernel SPRG3 value.
 	 * No need to save guest value as usermode can't modify SPRG3.
 	 */
 	ld	r3, PACA_SPRG3(r13)
 	mtspr	SPRN_SPRG3, r3
-
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	/* R7 = vcpu */
@@ -177,7 +180,7 @@ kvm_start_lightweight:
 	PPC_STL	r31, VCPU_GPR(R31)(r7)
 
 	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
-	mr	r5, r12
+	lwz	r5, VCPU_TRAP(r7)
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)

arch/powerpc/kvm/book3s_pr.c

@@ -66,6 +66,7 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu->in_use = 0;
 	svcpu_put(svcpu);
 #endif
 	vcpu->cpu = smp_processor_id();
@@ -78,6 +79,9 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	if (svcpu->in_use) {
+		kvmppc_copy_from_svcpu(vcpu, svcpu);
+	}
 	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
 	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
 	svcpu_put(svcpu);
@@ -110,12 +114,26 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
 	svcpu->ctr = vcpu->arch.ctr;
 	svcpu->lr  = vcpu->arch.lr;
 	svcpu->pc  = vcpu->arch.pc;
+	svcpu->in_use = true;
 }
 
 /* Copy data touched by real-mode code from shadow vcpu back to vcpu */
 void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 			    struct kvmppc_book3s_shadow_vcpu *svcpu)
 {
+	/*
+	 * vcpu_put would just call us again because in_use hasn't
+	 * been updated yet.
+	 */
+	preempt_disable();
+
+	/*
+	 * Maybe we were already preempted and synced the svcpu from
+	 * our preempt notifiers. Don't bother touching this svcpu then.
+	 */
+	if (!svcpu->in_use)
+		goto out;
+
 	vcpu->arch.gpr[0] = svcpu->gpr[0];
 	vcpu->arch.gpr[1] = svcpu->gpr[1];
 	vcpu->arch.gpr[2] = svcpu->gpr[2];
@@ -139,6 +157,10 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 	vcpu->arch.fault_dar   = svcpu->fault_dar;
 	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
 	vcpu->arch.last_inst   = svcpu->last_inst;
+	svcpu->in_use = false;
+
+out:
+	preempt_enable();
 }
 
 static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)

arch/powerpc/kvm/book3s_rmhandlers.S

@@ -153,15 +153,11 @@ _GLOBAL(kvmppc_entry_trampoline)
 
 	li	r6, MSR_IR | MSR_DR
 	andc	r6, r5, r6	/* Clear DR and IR in MSR value */
-#ifdef CONFIG_PPC_BOOK3S_32
 	/*
 	 * Set EE in HOST_MSR so that it's enabled when we get into our
-	 * C exit handler function.  On 64-bit we delay enabling
-	 * interrupts until we have finished transferring stuff
-	 * to or from the PACA.
+	 * C exit handler function.
 	 */
 	ori	r5, r5, MSR_EE
-#endif
 	mtsrr0	r7
 	mtsrr1	r6
 	RFI

arch/powerpc/kvm/booke.c

@@ -681,7 +681,7 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret, s;
-	struct thread_struct thread;
+	struct debug_reg debug;
 #ifdef CONFIG_PPC_FPU
 	struct thread_fp_state fp;
 	int fpexc_mode;
@@ -723,9 +723,9 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 
 	/* Switch to guest debug context */
-	thread.debug = vcpu->arch.shadow_dbg_reg;
-	switch_booke_debug_regs(&thread);
-	thread.debug = current->thread.debug;
+	debug = vcpu->arch.shadow_dbg_reg;
+	switch_booke_debug_regs(&debug);
+	debug = current->thread.debug;
 	current->thread.debug = vcpu->arch.shadow_dbg_reg;
 
 	kvmppc_fix_ee_before_entry();
@@ -736,8 +736,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	   We also get here with interrupts enabled. */
 
 	/* Switch back to user space debug context */
-	switch_booke_debug_regs(&thread);
-	current->thread.debug = thread.debug;
+	switch_booke_debug_regs(&debug);
+	current->thread.debug = debug;
 
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);

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

@@ -24,25 +24,25 @@ static int opal_lpc_chip_id = -1;
 static u8 opal_lpc_inb(unsigned long port)
 {
 	int64_t rc;
-	uint32_t data;
+	__be32 data;
 
 	if (opal_lpc_chip_id < 0 || port > 0xffff)
 		return 0xff;
 	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1);
-	return rc ? 0xff : data;
+	return rc ? 0xff : be32_to_cpu(data);
 }
 
 static __le16 __opal_lpc_inw(unsigned long port)
 {
 	int64_t rc;
-	uint32_t data;
+	__be32 data;
 
 	if (opal_lpc_chip_id < 0 || port > 0xfffe)
 		return 0xffff;
 	if (port & 1)
 		return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1);
 	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2);
-	return rc ? 0xffff : data;
+	return rc ? 0xffff : be32_to_cpu(data);
 }
 static u16 opal_lpc_inw(unsigned long port)
 {
@@ -52,7 +52,7 @@ static u16 opal_lpc_inw(unsigned long port)
 static __le32 __opal_lpc_inl(unsigned long port)
 {
 	int64_t rc;
-	uint32_t data;
+	__be32 data;
 
 	if (opal_lpc_chip_id < 0 || port > 0xfffc)
 		return 0xffffffff;
@@ -62,7 +62,7 @@ static __le32 __opal_lpc_inl(unsigned long port)
 		       (__le32)opal_lpc_inb(port + 2) <<  8 |
 			       opal_lpc_inb(port + 3);
 	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4);
-	return rc ? 0xffffffff : data;
+	return rc ? 0xffffffff : be32_to_cpu(data);
 }
 
 static u32 opal_lpc_inl(unsigned long port)

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

@@ -96,9 +96,11 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
 {
 	struct opal_scom_map *m = map;
 	int64_t rc;
+	__be64 v;
 
 	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value));
+	rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+	*value = be64_to_cpu(v);
 	return opal_xscom_err_xlate(rc);
 }
 

arch/powerpc/platforms/pseries/lparcfg.c

@@ -157,7 +157,7 @@ static void parse_ppp_data(struct seq_file *m)
 {
 	struct hvcall_ppp_data ppp_data;
 	struct device_node *root;
-	const int *perf_level;
+	const __be32 *perf_level;
 	int rc;
 
 	rc = h_get_ppp(&ppp_data);
@@ -201,7 +201,7 @@ static void parse_ppp_data(struct seq_file *m)
 		perf_level = of_get_property(root,
 				"ibm,partition-performance-parameters-level",
 					     NULL);
-		if (perf_level && (*perf_level >= 1)) {
+		if (perf_level && (be32_to_cpup(perf_level) >= 1)) {
 			seq_printf(m,
 			    "physical_procs_allocated_to_virtualization=%d\n",
 				   ppp_data.phys_platform_procs);
@@ -435,7 +435,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	int partition_potential_processors;
 	int partition_active_processors;
 	struct device_node *rtas_node;
-	const int *lrdrp = NULL;
+	const __be32 *lrdrp = NULL;
 
 	rtas_node = of_find_node_by_path("/rtas");
 	if (rtas_node)
@@ -444,7 +444,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	if (lrdrp == NULL) {
 		partition_potential_processors = vdso_data->processorCount;
 	} else {
-		partition_potential_processors = *(lrdrp + 4);
+		partition_potential_processors = be32_to_cpup(lrdrp + 4);
 	}
 	of_node_put(rtas_node);
 
@@ -654,7 +654,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
 	const char *model = "";
 	const char *system_id = "";
 	const char *tmp;
-	const unsigned int *lp_index_ptr;
+	const __be32 *lp_index_ptr;
 	unsigned int lp_index = 0;
 
 	seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
@@ -670,7 +670,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
 		lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
 					NULL);
 		if (lp_index_ptr)
-			lp_index = *lp_index_ptr;
+			lp_index = be32_to_cpup(lp_index_ptr);
 		of_node_put(rootdn);
 	}
 	seq_printf(m, "serial_number=%s\n", system_id);

arch/powerpc/platforms/pseries/msi.c

@@ -130,7 +130,8 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 {
 	struct device_node *dn;
 	struct pci_dn *pdn;
-	const u32 *req_msi;
+	const __be32 *p;
+	u32 req_msi;
 
 	pdn = pci_get_pdn(pdev);
 	if (!pdn)
@@ -138,19 +139,20 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 
 	dn = pdn->node;
 
-	req_msi = of_get_property(dn, prop_name, NULL);
-	if (!req_msi) {
+	p = of_get_property(dn, prop_name, NULL);
+	if (!p) {
 		pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name);
 		return -ENOENT;
 	}
 
-	if (*req_msi < nvec) {
+	req_msi = be32_to_cpup(p);
+	if (req_msi < nvec) {
 		pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec);
 
-		if (*req_msi == 0) /* Be paranoid */
+		if (req_msi == 0) /* Be paranoid */
 			return -ENOSPC;
 
-		return *req_msi;
+		return req_msi;
 	}
 
 	return 0;
@@ -171,7 +173,7 @@ static int check_req_msix(struct pci_dev *pdev, int nvec)
 static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 {
 	struct device_node *dn;
-	const u32 *p;
+	const __be32 *p;
 
 	dn = of_node_get(pci_device_to_OF_node(dev));
 	while (dn) {
@@ -179,7 +181,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 		if (p) {
 			pr_debug("rtas_msi: found prop on dn %s\n",
 				dn->full_name);
-			*total = *p;
+			*total = be32_to_cpup(p);
 			return dn;
 		}
 
@@ -232,13 +234,13 @@ struct msi_counts {
 static void *count_non_bridge_devices(struct device_node *dn, void *data)
 {
 	struct msi_counts *counts = data;
-	const u32 *p;
+	const __be32 *p;
 	u32 class;
 
 	pr_debug("rtas_msi: counting %s\n", dn->full_name);
 
 	p = of_get_property(dn, "class-code", NULL);
-	class = p ? *p : 0;
+	class = p ? be32_to_cpup(p) : 0;
 
 	if ((class >> 8) != PCI_CLASS_BRIDGE_PCI)
 		counts->num_devices++;
@@ -249,7 +251,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data)
 static void *count_spare_msis(struct device_node *dn, void *data)
 {
 	struct msi_counts *counts = data;
-	const u32 *p;
+	const __be32 *p;
 	int req;
 
 	if (dn == counts->requestor)
@@ -260,11 +262,11 @@ static void *count_spare_msis(struct device_node *dn, void *data)
 		req = 0;
 		p = of_get_property(dn, "ibm,req#msi", NULL);
 		if (p)
-			req = *p;
+			req = be32_to_cpup(p);
 
 		p = of_get_property(dn, "ibm,req#msi-x", NULL);
 		if (p)
-			req = max(req, (int)*p);
+			req = max(req, (int)be32_to_cpup(p));
 	}
 
 	if (req < counts->quota)

arch/powerpc/platforms/pseries/nvram.c

@@ -43,8 +43,8 @@ static char nvram_buf[NVRW_CNT];	/* assume this is in the first 4GB */
 static DEFINE_SPINLOCK(nvram_lock);
 
 struct err_log_info {
-	int error_type;
-	unsigned int seq_num;
+	__be32 error_type;
+	__be32 seq_num;
 };
 
 struct nvram_os_partition {
@@ -79,9 +79,9 @@ static const char *pseries_nvram_os_partitions[] = {
 };
 
 struct oops_log_info {
-	u16 version;
-	u16 report_length;
-	u64 timestamp;
+	__be16 version;
+	__be16 report_length;
+	__be64 timestamp;
 } __attribute__((packed));
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
@@ -291,8 +291,8 @@ int nvram_write_os_partition(struct nvram_os_partition *part, char * buff,
 		length = part->size;
 	}
 
-	info.error_type = err_type;
-	info.seq_num = error_log_cnt;
+	info.error_type = cpu_to_be32(err_type);
+	info.seq_num = cpu_to_be32(error_log_cnt);
 
 	tmp_index = part->index;
 
@@ -364,8 +364,8 @@ int nvram_read_partition(struct nvram_os_partition *part, char *buff,
 	}
 
 	if (part->os_partition) {
-		*error_log_cnt = info.seq_num;
-		*err_type = info.error_type;
+		*error_log_cnt = be32_to_cpu(info.seq_num);
+		*err_type = be32_to_cpu(info.error_type);
 	}
 
 	return 0;
@@ -529,9 +529,9 @@ static int zip_oops(size_t text_len)
 		pr_err("nvram: logging uncompressed oops/panic report\n");
 		return -1;
 	}
-	oops_hdr->version = OOPS_HDR_VERSION;
-	oops_hdr->report_length = (u16) zipped_len;
-	oops_hdr->timestamp = get_seconds();
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(zipped_len);
+	oops_hdr->timestamp = cpu_to_be64(get_seconds());
 	return 0;
 }
 
@@ -574,9 +574,9 @@ static int nvram_pstore_write(enum pstore_type_id type,
 				clobbering_unread_rtas_event())
 		return -1;
 
-	oops_hdr->version = OOPS_HDR_VERSION;
-	oops_hdr->report_length = (u16) size;
-	oops_hdr->timestamp = get_seconds();
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(size);
+	oops_hdr->timestamp = cpu_to_be64(get_seconds());
 
 	if (compressed)
 		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
@@ -670,16 +670,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		size_t length, hdr_size;
 
 		oops_hdr = (struct oops_log_info *)buff;
-		if (oops_hdr->version < OOPS_HDR_VERSION) {
+		if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
 			/* Old format oops header had 2-byte record size */
 			hdr_size = sizeof(u16);
-			length = oops_hdr->version;
+			length = be16_to_cpu(oops_hdr->version);
 			time->tv_sec = 0;
 			time->tv_nsec = 0;
 		} else {
 			hdr_size = sizeof(*oops_hdr);
-			length = oops_hdr->report_length;
-			time->tv_sec = oops_hdr->timestamp;
+			length = be16_to_cpu(oops_hdr->report_length);
+			time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
 			time->tv_nsec = 0;
 		}
 		*buf = kmalloc(length, GFP_KERNEL);
@@ -889,13 +889,13 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 		kmsg_dump_get_buffer(dumper, false,
 				     oops_data, oops_data_sz, &text_len);
 		err_type = ERR_TYPE_KERNEL_PANIC;
-		oops_hdr->version = OOPS_HDR_VERSION;
-		oops_hdr->report_length = (u16) text_len;
-		oops_hdr->timestamp = get_seconds();
+		oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+		oops_hdr->report_length = cpu_to_be16(text_len);
+		oops_hdr->timestamp = cpu_to_be64(get_seconds());
 	}
 
 	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+		(int) (sizeof(*oops_hdr) + text_len), err_type,
 		++oops_count);
 
 	spin_unlock_irqrestore(&lock, flags);

arch/powerpc/platforms/pseries/pci.c

@@ -113,7 +113,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
 	struct device_node *dn, *pdn;
 	struct pci_bus *bus;
-	const uint32_t *pcie_link_speed_stats;
+	const __be32 *pcie_link_speed_stats;
 
 	bus = bridge->bus;
 
@@ -122,7 +122,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		return 0;
 
 	for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
-		pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn,
+		pcie_link_speed_stats = of_get_property(pdn,
 			"ibm,pcie-link-speed-stats", NULL);
 		if (pcie_link_speed_stats)
 			break;
@@ -135,7 +135,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		return 0;
 	}
 
-	switch (pcie_link_speed_stats[0]) {
+	switch (be32_to_cpup(pcie_link_speed_stats)) {
 	case 0x01:
 		bus->max_bus_speed = PCIE_SPEED_2_5GT;
 		break;
@@ -147,7 +147,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		break;
 	}
 
-	switch (pcie_link_speed_stats[1]) {
+	switch (be32_to_cpup(pcie_link_speed_stats)) {
 	case 0x01:
 		bus->cur_bus_speed = PCIE_SPEED_2_5GT;
 		break;

arch/sh/lib/Makefile

@@ -6,7 +6,7 @@ lib-y  = delay.o memmove.o memchr.o \
 	 checksum.o strlen.o div64.o div64-generic.o
 
 # Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
 	 ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
 	 udiv_qrnnd.o
 

arch/sparc/include/asm/pgtable_64.h

@@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte)
 }
 
 #define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 {
 	return pte_val(a) & _PAGE_VALID;
 }
@@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
-	if (likely(mm != &init_mm) && pte_accessible(orig))
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
 		tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 

arch/x86/Kconfig

@@ -26,6 +26,7 @@ config X86
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE

arch/x86/include/asm/pgtable.h

@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)

arch/x86/include/asm/preempt.h

@@ -7,6 +7,12 @@
 
 DECLARE_PER_CPU(int, __preempt_count);
 
+/*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
+#define PREEMPT_ENABLED	(0 + PREEMPT_NEED_RESCHED)
+
 /*
  * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
  * that think a non-zero value indicates we cannot preempt.
@@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val)
 	__this_cpu_add_4(__preempt_count, -val);
 }
 
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
 	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");

arch/x86/kernel/cpu/perf_event.h

@@ -262,11 +262,20 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
-#define EVENT_CONSTRAINT_END		\
-	EVENT_CONSTRAINT(0, 0, 0)
+/*
+ * We define the end marker as having a weight of -1
+ * to enable blacklisting of events using a counter bitmask
+ * of zero and thus a weight of zero.
+ * The end marker has a weight that cannot possibly be
+ * obtained from counting the bits in the bitmask.
+ */
+#define EVENT_CONSTRAINT_END { .weight = -1 }
 
+/*
+ * Check for end marker with weight == -1
+ */
 #define for_each_event_constraint(e, c)	\
-	for ((e) = (c); (e)->weight; (e)++)
+	for ((e) = (c); (e)->weight != -1; (e)++)
 
 /*
  * Extra registers for specific events.

arch/x86/mm/gup.c

@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {

drivers/acpi/apei/erst.c

@@ -942,6 +942,7 @@ static int erst_clearer(enum pstore_type_id type, u64 id, int count,
 static struct pstore_info erst_info = {
 	.owner		= THIS_MODULE,
 	.name		= "erst",
+	.flags		= PSTORE_FLAGS_FRAGILE,
 	.open		= erst_open_pstore,
 	.close		= erst_close_pstore,
 	.read		= erst_reader,

drivers/clk/clk-s2mps11.c

@@ -60,7 +60,7 @@ static int s2mps11_clk_prepare(struct clk_hw *hw)
 	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
 	int ret;
 
-	ret = regmap_update_bits(s2mps11->iodev->regmap,
+	ret = regmap_update_bits(s2mps11->iodev->regmap_pmic,
 				S2MPS11_REG_RTC_CTRL,
 				 s2mps11->mask, s2mps11->mask);
 	if (!ret)
@@ -74,7 +74,7 @@ static void s2mps11_clk_unprepare(struct clk_hw *hw)
 	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
 	int ret;
 
-	ret = regmap_update_bits(s2mps11->iodev->regmap, S2MPS11_REG_RTC_CTRL,
+	ret = regmap_update_bits(s2mps11->iodev->regmap_pmic, S2MPS11_REG_RTC_CTRL,
 			   s2mps11->mask, ~s2mps11->mask);
 
 	if (!ret)
@@ -174,7 +174,7 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 		s2mps11_clk->hw.init = &s2mps11_clks_init[i];
 		s2mps11_clk->mask = 1 << i;
 
-		ret = regmap_read(s2mps11_clk->iodev->regmap,
+		ret = regmap_read(s2mps11_clk->iodev->regmap_pmic,
 				  S2MPS11_REG_RTC_CTRL, &val);
 		if (ret < 0)
 			goto err_reg;

drivers/clocksource/Kconfig

@@ -75,6 +75,7 @@ config CLKSRC_DBX500_PRCMU_SCHED_CLOCK
 config CLKSRC_EFM32
 	bool "Clocksource for Energy Micro's EFM32 SoCs" if !ARCH_EFM32
 	depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST)
+	select CLKSRC_MMIO
 	default ARCH_EFM32
 	help
 	  Support to use the timers of EFM32 SoCs as clock source and clock

drivers/clocksource/clksrc-of.c

@@ -35,6 +35,5 @@ void __init clocksource_of_init(void)
 
 		init_func = match->data;
 		init_func(np);
-		of_node_put(np);
 	}
 }

drivers/clocksource/dw_apb_timer_of.c

@@ -108,12 +108,11 @@ static void __init add_clocksource(struct device_node *source_timer)
 
 static u64 read_sched_clock(void)
 {
-	return __raw_readl(sched_io_base);
+	return ~__raw_readl(sched_io_base);
 }
 
 static const struct of_device_id sptimer_ids[] __initconst = {
 	{ .compatible = "picochip,pc3x2-rtc" },
-	{ .compatible = "snps,dw-apb-timer-sp" },
 	{ /* Sentinel */ },
 };
 
@@ -151,4 +150,6 @@ static void __init dw_apb_timer_init(struct device_node *timer)
 	num_called++;
 }
 CLOCKSOURCE_OF_DECLARE(pc3x2_timer, "picochip,pc3x2-timer", dw_apb_timer_init);
-CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer-osc", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer_osc, "snps,dw-apb-timer-osc", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer_sp, "snps,dw-apb-timer-sp", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer", dw_apb_timer_init);

drivers/clocksource/sun4i_timer.c

@@ -179,6 +179,9 @@ static void __init sun4i_timer_init(struct device_node *node)
 	writel(TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
 	       timer_base + TIMER_CTL_REG(0));
 
+	/* Make sure timer is stopped before playing with interrupts */
+	sun4i_clkevt_time_stop(0);
+
 	ret = setup_irq(irq, &sun4i_timer_irq);
 	if (ret)
 		pr_warn("failed to setup irq %d\n", irq);

drivers/clocksource/time-armada-370-xp.c

@@ -255,11 +255,6 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np)
 
 	ticks_per_jiffy = (timer_clk + HZ / 2) / HZ;
 
-	/*
-	 * Set scale and timer for sched_clock.
-	 */
-	sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk);
-
 	/*
 	 * Setup free-running clocksource timer (interrupts
 	 * disabled).
@@ -270,6 +265,11 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np)
 	timer_ctrl_clrset(0, TIMER0_EN | TIMER0_RELOAD_EN |
 			     TIMER0_DIV(TIMER_DIVIDER_SHIFT));
 
+	/*
+	 * Set scale and timer for sched_clock.
+	 */
+	sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk);
+
 	clocksource_mmio_init(timer_base + TIMER0_VAL_OFF,
 			      "armada_370_xp_clocksource",
 			      timer_clk, 300, 32, clocksource_mmio_readl_down);

drivers/dma/Kconfig

@@ -62,6 +62,7 @@ config INTEL_IOATDMA
 	tristate "Intel I/OAT DMA support"
 	depends on PCI && X86
 	select DMA_ENGINE
+	select DMA_ENGINE_RAID
 	select DCA
 	help
 	  Enable support for the Intel(R) I/OAT DMA engine present
@@ -112,6 +113,7 @@ config MV_XOR
 	bool "Marvell XOR engine support"
 	depends on PLAT_ORION
 	select DMA_ENGINE
+	select DMA_ENGINE_RAID
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	---help---
 	  Enable support for the Marvell XOR engine.
@@ -187,6 +189,7 @@ config AMCC_PPC440SPE_ADMA
 	tristate "AMCC PPC440SPe ADMA support"
 	depends on 440SPe || 440SP
 	select DMA_ENGINE
+	select DMA_ENGINE_RAID
 	select ARCH_HAS_ASYNC_TX_FIND_CHANNEL
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	help
@@ -352,6 +355,7 @@ config NET_DMA
 	bool "Network: TCP receive copy offload"
 	depends on DMA_ENGINE && NET
 	default (INTEL_IOATDMA || FSL_DMA)
+	depends on BROKEN
 	help
 	  This enables the use of DMA engines in the network stack to
 	  offload receive copy-to-user operations, freeing CPU cycles.
@@ -377,4 +381,7 @@ config DMATEST
 	  Simple DMA test client. Say N unless you're debugging a
 	  DMA Device driver.
 
+config DMA_ENGINE_RAID
+	bool
+
 endif

drivers/dma/at_hdmac_regs.h

@@ -347,10 +347,6 @@ static struct device *chan2dev(struct dma_chan *chan)
 {
 	return &chan->dev->device;
 }
-static struct device *chan2parent(struct dma_chan *chan)
-{
-	return chan->dev->device.parent;
-}
 
 #if defined(VERBOSE_DEBUG)
 static void vdbg_dump_regs(struct at_dma_chan *atchan)

drivers/dma/dmaengine.c

@@ -912,7 +912,7 @@ struct dmaengine_unmap_pool {
 #define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
 static struct dmaengine_unmap_pool unmap_pool[] = {
 	__UNMAP_POOL(2),
-	#if IS_ENABLED(CONFIG_ASYNC_TX_DMA)
+	#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID)
 	__UNMAP_POOL(16),
 	__UNMAP_POOL(128),
 	__UNMAP_POOL(256),
@@ -1054,7 +1054,7 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 	dma_cookie_t cookie;
 	unsigned long flags;
 
-	unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOIO);
+	unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOWAIT);
 	if (!unmap)
 		return -ENOMEM;
 

drivers/dma/dmatest.c

@@ -539,9 +539,9 @@ static int dmatest_func(void *data)
 
 		um->len = params->buf_size;
 		for (i = 0; i < src_cnt; i++) {
-			unsigned long buf = (unsigned long) thread->srcs[i];
+			void *buf = thread->srcs[i];
 			struct page *pg = virt_to_page(buf);
-			unsigned pg_off = buf & ~PAGE_MASK;
+			unsigned pg_off = (unsigned long) buf & ~PAGE_MASK;
 
 			um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
 						   um->len, DMA_TO_DEVICE);
@@ -559,9 +559,9 @@ static int dmatest_func(void *data)
 		/* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
 		dsts = &um->addr[src_cnt];
 		for (i = 0; i < dst_cnt; i++) {
-			unsigned long buf = (unsigned long) thread->dsts[i];
+			void *buf = thread->dsts[i];
 			struct page *pg = virt_to_page(buf);
-			unsigned pg_off = buf & ~PAGE_MASK;
+			unsigned pg_off = (unsigned long) buf & ~PAGE_MASK;
 
 			dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len,
 					       DMA_BIDIRECTIONAL);

drivers/dma/fsldma.c

@@ -86,11 +86,6 @@ static void set_desc_cnt(struct fsldma_chan *chan,
 	hw->count = CPU_TO_DMA(chan, count, 32);
 }
 
-static u32 get_desc_cnt(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
-{
-	return DMA_TO_CPU(chan, desc->hw.count, 32);
-}
-
 static void set_desc_src(struct fsldma_chan *chan,
 			 struct fsl_dma_ld_hw *hw, dma_addr_t src)
 {
@@ -101,16 +96,6 @@ static void set_desc_src(struct fsldma_chan *chan,
 	hw->src_addr = CPU_TO_DMA(chan, snoop_bits | src, 64);
 }
 
-static dma_addr_t get_desc_src(struct fsldma_chan *chan,
-			       struct fsl_desc_sw *desc)
-{
-	u64 snoop_bits;
-
-	snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX)
-		? ((u64)FSL_DMA_SATR_SREADTYPE_SNOOP_READ << 32) : 0;
-	return DMA_TO_CPU(chan, desc->hw.src_addr, 64) & ~snoop_bits;
-}
-
 static void set_desc_dst(struct fsldma_chan *chan,
 			 struct fsl_dma_ld_hw *hw, dma_addr_t dst)
 {
@@ -121,16 +106,6 @@ static void set_desc_dst(struct fsldma_chan *chan,
 	hw->dst_addr = CPU_TO_DMA(chan, snoop_bits | dst, 64);
 }
 
-static dma_addr_t get_desc_dst(struct fsldma_chan *chan,
-			       struct fsl_desc_sw *desc)
-{
-	u64 snoop_bits;
-
-	snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX)
-		? ((u64)FSL_DMA_DATR_DWRITETYPE_SNOOP_WRITE << 32) : 0;
-	return DMA_TO_CPU(chan, desc->hw.dst_addr, 64) & ~snoop_bits;
-}
-
 static void set_desc_next(struct fsldma_chan *chan,
 			  struct fsl_dma_ld_hw *hw, dma_addr_t next)
 {
@@ -408,7 +383,7 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct fsl_desc_sw *desc = tx_to_fsl_desc(tx);
 	struct fsl_desc_sw *child;
 	unsigned long flags;
-	dma_cookie_t cookie;
+	dma_cookie_t cookie = -EINVAL;
 
 	spin_lock_irqsave(&chan->desc_lock, flags);
 
@@ -854,10 +829,6 @@ static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
 				      struct fsl_desc_sw *desc)
 {
 	struct dma_async_tx_descriptor *txd = &desc->async_tx;
-	struct device *dev = chan->common.device->dev;
-	dma_addr_t src = get_desc_src(chan, desc);
-	dma_addr_t dst = get_desc_dst(chan, desc);
-	u32 len = get_desc_cnt(chan, desc);
 
 	/* Run the link descriptor callback function */
 	if (txd->callback) {

drivers/dma/mv_xor.c

@@ -54,12 +54,6 @@ static void mv_desc_init(struct mv_xor_desc_slot *desc, unsigned long flags)
 	hw_desc->desc_command = (1 << 31);
 }
 
-static u32 mv_desc_get_dest_addr(struct mv_xor_desc_slot *desc)
-{
-	struct mv_xor_desc *hw_desc = desc->hw_desc;
-	return hw_desc->phy_dest_addr;
-}
-
 static void mv_desc_set_byte_count(struct mv_xor_desc_slot *desc,
 				   u32 byte_count)
 {
@@ -787,7 +781,6 @@ static void mv_xor_issue_pending(struct dma_chan *chan)
 /*
  * Perform a transaction to verify the HW works.
  */
-#define MV_XOR_TEST_SIZE 2000
 
 static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
 {
@@ -797,20 +790,21 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
 	struct dma_chan *dma_chan;
 	dma_cookie_t cookie;
 	struct dma_async_tx_descriptor *tx;
+	struct dmaengine_unmap_data *unmap;
 	int err = 0;
 
-	src = kmalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL);
+	src = kmalloc(sizeof(u8) * PAGE_SIZE, GFP_KERNEL);
 	if (!src)
 		return -ENOMEM;
 
-	dest = kzalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL);
+	dest = kzalloc(sizeof(u8) * PAGE_SIZE, GFP_KERNEL);
 	if (!dest) {
 		kfree(src);
 		return -ENOMEM;
 	}
 
 	/* Fill in src buffer */
-	for (i = 0; i < MV_XOR_TEST_SIZE; i++)
+	for (i = 0; i < PAGE_SIZE; i++)
 		((u8 *) src)[i] = (u8)i;
 
 	dma_chan = &mv_chan->dmachan;
@@ -819,14 +813,26 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
 		goto out;
 	}
 
-	dest_dma = dma_map_single(dma_chan->device->dev, dest,
-				  MV_XOR_TEST_SIZE, DMA_FROM_DEVICE);
+	unmap = dmaengine_get_unmap_data(dma_chan->device->dev, 2, GFP_KERNEL);
+	if (!unmap) {
+		err = -ENOMEM;
+		goto free_resources;
+	}
+
+	src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0,
+				 PAGE_SIZE, DMA_TO_DEVICE);
+	unmap->to_cnt = 1;
+	unmap->addr[0] = src_dma;
 
-	src_dma = dma_map_single(dma_chan->device->dev, src,
-				 MV_XOR_TEST_SIZE, DMA_TO_DEVICE);
+	dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0,
+				  PAGE_SIZE, DMA_FROM_DEVICE);
+	unmap->from_cnt = 1;
+	unmap->addr[1] = dest_dma;
+
+	unmap->len = PAGE_SIZE;
 
 	tx = mv_xor_prep_dma_memcpy(dma_chan, dest_dma, src_dma,
-				    MV_XOR_TEST_SIZE, 0);
+				    PAGE_SIZE, 0);
 	cookie = mv_xor_tx_submit(tx);
 	mv_xor_issue_pending(dma_chan);
 	async_tx_ack(tx);
@@ -841,8 +847,8 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
 	}
 
 	dma_sync_single_for_cpu(dma_chan->device->dev, dest_dma,
-				MV_XOR_TEST_SIZE, DMA_FROM_DEVICE);
-	if (memcmp(src, dest, MV_XOR_TEST_SIZE)) {
+				PAGE_SIZE, DMA_FROM_DEVICE);
+	if (memcmp(src, dest, PAGE_SIZE)) {
 		dev_err(dma_chan->device->dev,
 			"Self-test copy failed compare, disabling\n");
 		err = -ENODEV;
@@ -850,6 +856,7 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
 	}
 
 free_resources:
+	dmaengine_unmap_put(unmap);
 	mv_xor_free_chan_resources(dma_chan);
 out:
 	kfree(src);
@@ -867,13 +874,15 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
 	dma_addr_t dma_srcs[MV_XOR_NUM_SRC_TEST];
 	dma_addr_t dest_dma;
 	struct dma_async_tx_descriptor *tx;
+	struct dmaengine_unmap_data *unmap;
 	struct dma_chan *dma_chan;
 	dma_cookie_t cookie;
 	u8 cmp_byte = 0;
 	u32 cmp_word;
 	int err = 0;
+	int src_count = MV_XOR_NUM_SRC_TEST;
 
-	for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) {
+	for (src_idx = 0; src_idx < src_count; src_idx++) {
 		xor_srcs[src_idx] = alloc_page(GFP_KERNEL);
 		if (!xor_srcs[src_idx]) {
 			while (src_idx--)
@@ -890,13 +899,13 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
 	}
 
 	/* Fill in src buffers */
-	for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) {
+	for (src_idx = 0; src_idx < src_count; src_idx++) {
 		u8 *ptr = page_address(xor_srcs[src_idx]);
 		for (i = 0; i < PAGE_SIZE; i++)
 			ptr[i] = (1 << src_idx);
 	}
 
-	for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++)
+	for (src_idx = 0; src_idx < src_count; src_idx++)
 		cmp_byte ^= (u8) (1 << src_idx);
 
 	cmp_word = (cmp_byte << 24) | (cmp_byte << 16) |
@@ -910,16 +919,29 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
 		goto out;
 	}
 
+	unmap = dmaengine_get_unmap_data(dma_chan->device->dev, src_count + 1,
+					 GFP_KERNEL);
+	if (!unmap) {
+		err = -ENOMEM;
+		goto free_resources;
+	}
+
 	/* test xor */
-	dest_dma = dma_map_page(dma_chan->device->dev, dest, 0, PAGE_SIZE,
-				DMA_FROM_DEVICE);
+	for (i = 0; i < src_count; i++) {
+		unmap->addr[i] = dma_map_page(dma_chan->device->dev, xor_srcs[i],
+					      0, PAGE_SIZE, DMA_TO_DEVICE);
+		dma_srcs[i] = unmap->addr[i];
+		unmap->to_cnt++;
+	}
 
-	for (i = 0; i < MV_XOR_NUM_SRC_TEST; i++)
-		dma_srcs[i] = dma_map_page(dma_chan->device->dev, xor_srcs[i],
-					   0, PAGE_SIZE, DMA_TO_DEVICE);
+	unmap->addr[src_count] = dma_map_page(dma_chan->device->dev, dest, 0, PAGE_SIZE,
+				      DMA_FROM_DEVICE);
+	dest_dma = unmap->addr[src_count];
+	unmap->from_cnt = 1;
+	unmap->len = PAGE_SIZE;
 
 	tx = mv_xor_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
-				 MV_XOR_NUM_SRC_TEST, PAGE_SIZE, 0);
+				 src_count, PAGE_SIZE, 0);
 
 	cookie = mv_xor_tx_submit(tx);
 	mv_xor_issue_pending(dma_chan);
@@ -948,9 +970,10 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
 	}
 
 free_resources:
+	dmaengine_unmap_put(unmap);
 	mv_xor_free_chan_resources(dma_chan);
 out:
-	src_idx = MV_XOR_NUM_SRC_TEST;
+	src_idx = src_count;
 	while (src_idx--)
 		__free_page(xor_srcs[src_idx]);
 	__free_page(dest);
@@ -1176,6 +1199,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 		int i = 0;
 
 		for_each_child_of_node(pdev->dev.of_node, np) {
+			struct mv_xor_chan *chan;
 			dma_cap_mask_t cap_mask;
 			int irq;
 
@@ -1193,21 +1217,21 @@ static int mv_xor_probe(struct platform_device *pdev)
 				goto err_channel_add;
 			}
 
-			xordev->channels[i] =
-				mv_xor_channel_add(xordev, pdev, i,
-						   cap_mask, irq);
-			if (IS_ERR(xordev->channels[i])) {
-				ret = PTR_ERR(xordev->channels[i]);
-				xordev->channels[i] = NULL;
+			chan = mv_xor_channel_add(xordev, pdev, i,
+						  cap_mask, irq);
+			if (IS_ERR(chan)) {
+				ret = PTR_ERR(chan);
 				irq_dispose_mapping(irq);
 				goto err_channel_add;
 			}
 
+			xordev->channels[i] = chan;
 			i++;
 		}
 	} else if (pdata && pdata->channels) {
 		for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
 			struct mv_xor_channel_data *cd;
+			struct mv_xor_chan *chan;
 			int irq;
 
 			cd = &pdata->channels[i];
@@ -1222,13 +1246,14 @@ static int mv_xor_probe(struct platform_device *pdev)
 				goto err_channel_add;
 			}
 
-			xordev->channels[i] =
-				mv_xor_channel_add(xordev, pdev, i,
-						   cd->cap_mask, irq);
-			if (IS_ERR(xordev->channels[i])) {
-				ret = PTR_ERR(xordev->channels[i]);
+			chan = mv_xor_channel_add(xordev, pdev, i,
+						  cd->cap_mask, irq);
+			if (IS_ERR(chan)) {
+				ret = PTR_ERR(chan);
 				goto err_channel_add;
 			}
+
+			xordev->channels[i] = chan;
 		}
 	}
 

drivers/dma/pl330.c

@@ -2492,12 +2492,9 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx)
 
 static inline void _init_desc(struct dma_pl330_desc *desc)
 {
-	desc->pchan = NULL;
 	desc->req.x = &desc->px;
 	desc->req.token = desc;
 	desc->rqcfg.swap = SWAP_NO;
-	desc->rqcfg.privileged = 0;
-	desc->rqcfg.insnaccess = 0;
 	desc->rqcfg.scctl = SCCTRL0;
 	desc->rqcfg.dcctl = DCCTRL0;
 	desc->req.cfg = &desc->rqcfg;
@@ -2517,7 +2514,7 @@ static int add_desc(struct dma_pl330_dmac *pdmac, gfp_t flg, int count)
 	if (!pdmac)
 		return 0;
 
-	desc = kmalloc(count * sizeof(*desc), flg);
+	desc = kcalloc(count, sizeof(*desc), flg);
 	if (!desc)
 		return 0;
 

drivers/dma/ppc4xx/adma.c

@@ -532,29 +532,6 @@ static void ppc440spe_desc_init_memcpy(struct ppc440spe_adma_desc_slot *desc,
 	hw_desc->opc = DMA_CDB_OPC_MV_SG1_SG2;
 }
 
-/**
- * ppc440spe_desc_init_memset - initialize the descriptor for MEMSET operation
- */
-static void ppc440spe_desc_init_memset(struct ppc440spe_adma_desc_slot *desc,
-					int value, unsigned long flags)
-{
-	struct dma_cdb *hw_desc = desc->hw_desc;
-
-	memset(desc->hw_desc, 0, sizeof(struct dma_cdb));
-	desc->hw_next = NULL;
-	desc->src_cnt = 1;
-	desc->dst_cnt = 1;
-
-	if (flags & DMA_PREP_INTERRUPT)
-		set_bit(PPC440SPE_DESC_INT, &desc->flags);
-	else
-		clear_bit(PPC440SPE_DESC_INT, &desc->flags);
-
-	hw_desc->sg1u = hw_desc->sg1l = cpu_to_le32((u32)value);
-	hw_desc->sg3u = hw_desc->sg3l = cpu_to_le32((u32)value);
-	hw_desc->opc = DMA_CDB_OPC_DFILL128;
-}
-
 /**
  * ppc440spe_desc_set_src_addr - set source address into the descriptor
  */
@@ -1504,8 +1481,6 @@ static dma_cookie_t ppc440spe_adma_run_tx_complete_actions(
 		struct ppc440spe_adma_chan *chan,
 		dma_cookie_t cookie)
 {
-	int i;
-
 	BUG_ON(desc->async_tx.cookie < 0);
 	if (desc->async_tx.cookie > 0) {
 		cookie = desc->async_tx.cookie;
@@ -3898,7 +3873,7 @@ static void ppc440spe_adma_init_capabilities(struct ppc440spe_adma_device *adev)
 			ppc440spe_adma_prep_dma_interrupt;
 	}
 	pr_info("%s: AMCC(R) PPC440SP(E) ADMA Engine: "
-	  "( %s%s%s%s%s%s%s)\n",
+	  "( %s%s%s%s%s%s)\n",
 	  dev_name(adev->dev),
 	  dma_has_cap(DMA_PQ, adev->common.cap_mask) ? "pq " : "",
 	  dma_has_cap(DMA_PQ_VAL, adev->common.cap_mask) ? "pq_val " : "",

drivers/dma/txx9dmac.c

@@ -406,7 +406,6 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
 	dma_async_tx_callback callback;
 	void *param;
 	struct dma_async_tx_descriptor *txd = &desc->txd;
-	struct txx9dmac_slave *ds = dc->chan.private;
 
 	dev_vdbg(chan2dev(&dc->chan), "descriptor %u %p complete\n",
 		 txd->cookie, desc);

drivers/firewire/sbp2.c

@@ -1623,7 +1623,6 @@ static struct scsi_host_template scsi_driver_template = {
 	.cmd_per_lun		= 1,
 	.can_queue		= 1,
 	.sdev_attrs		= sbp2_scsi_sysfs_attrs,
-	.no_write_same		= 1,
 };
 
 MODULE_AUTHOR("Kristian Hoegsberg <krh@bitplanet.net>");

drivers/firmware/efi/efi-pstore.c

@@ -356,6 +356,7 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 static struct pstore_info efi_pstore_info = {
 	.owner		= THIS_MODULE,
 	.name		= "efi",
+	.flags		= PSTORE_FLAGS_FRAGILE,
 	.open		= efi_pstore_open,
 	.close		= efi_pstore_close,
 	.read		= efi_pstore_read,

drivers/gpio/gpio-msm-v2.c

@@ -252,7 +252,7 @@ static void msm_gpio_irq_mask(struct irq_data *d)
 
 	spin_lock_irqsave(&tlmm_lock, irq_flags);
 	writel(TARGET_PROC_NONE, GPIO_INTR_CFG_SU(gpio));
-	clear_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+	clear_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
 	__clear_bit(gpio, msm_gpio.enabled_irqs);
 	spin_unlock_irqrestore(&tlmm_lock, irq_flags);
 }
@@ -264,7 +264,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d)
 
 	spin_lock_irqsave(&tlmm_lock, irq_flags);
 	__set_bit(gpio, msm_gpio.enabled_irqs);
-	set_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+	set_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
 	writel(TARGET_PROC_SCORPION, GPIO_INTR_CFG_SU(gpio));
 	spin_unlock_irqrestore(&tlmm_lock, irq_flags);
 }

drivers/gpio/gpio-rcar.c

@@ -169,7 +169,8 @@ static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id)
 	u32 pending;
 	unsigned int offset, irqs_handled = 0;
 
-	while ((pending = gpio_rcar_read(p, INTDT))) {
+	while ((pending = gpio_rcar_read(p, INTDT) &
+			  gpio_rcar_read(p, INTMSK))) {
 		offset = __ffs(pending);
 		gpio_rcar_write(p, INTCLR, BIT(offset));
 		generic_handle_irq(irq_find_mapping(p->irq_domain, offset));

drivers/gpio/gpio-twl4030.c

@@ -300,7 +300,7 @@ static int twl_direction_in(struct gpio_chip *chip, unsigned offset)
 	if (offset < TWL4030_GPIO_MAX)
 		ret = twl4030_set_gpio_direction(offset, 1);
 	else
-		ret = -EINVAL;
+		ret = -EINVAL;	/* LED outputs can't be set as input */
 
 	if (!ret)
 		priv->direction &= ~BIT(offset);
@@ -354,11 +354,20 @@ static void twl_set(struct gpio_chip *chip, unsigned offset, int value)
 static int twl_direction_out(struct gpio_chip *chip, unsigned offset, int value)
 {
 	struct gpio_twl4030_priv *priv = to_gpio_twl4030(chip);
-	int ret = -EINVAL;
+	int ret = 0;
 
 	mutex_lock(&priv->mutex);
-	if (offset < TWL4030_GPIO_MAX)
+	if (offset < TWL4030_GPIO_MAX) {
 		ret = twl4030_set_gpio_direction(offset, 0);
+		if (ret) {
+			mutex_unlock(&priv->mutex);
+			return ret;
+		}
+	}
+
+	/*
+	 *  LED gpios i.e. offset >= TWL4030_GPIO_MAX are always output
+	 */
 
 	priv->direction |= BIT(offset);
 	mutex_unlock(&priv->mutex);

drivers/gpu/drm/armada/armada_drm.h

@@ -103,6 +103,7 @@ void armada_drm_queue_unref_work(struct drm_device *,
 extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs;
 
 int armada_fbdev_init(struct drm_device *);
+void armada_fbdev_lastclose(struct drm_device *);
 void armada_fbdev_fini(struct drm_device *);
 
 int armada_overlay_plane_create(struct drm_device *, unsigned long);

drivers/gpu/drm/armada/armada_drv.c

@@ -321,6 +321,11 @@ static struct drm_ioctl_desc armada_ioctls[] = {
 		DRM_UNLOCKED),
 };
 
+static void armada_drm_lastclose(struct drm_device *dev)
+{
+	armada_fbdev_lastclose(dev);
+}
+
 static const struct file_operations armada_drm_fops = {
 	.owner			= THIS_MODULE,
 	.llseek			= no_llseek,
@@ -337,7 +342,7 @@ static struct drm_driver armada_drm_driver = {
 	.open			= NULL,
 	.preclose		= NULL,
 	.postclose		= NULL,
-	.lastclose		= NULL,
+	.lastclose		= armada_drm_lastclose,
 	.unload			= armada_drm_unload,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= armada_drm_enable_vblank,

drivers/gpu/drm/armada/armada_fbdev.c

@@ -105,9 +105,9 @@ static int armada_fb_create(struct drm_fb_helper *fbh,
 	drm_fb_helper_fill_fix(info, dfb->fb.pitches[0], dfb->fb.depth);
 	drm_fb_helper_fill_var(info, fbh, sizes->fb_width, sizes->fb_height);
 
-	DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08x\n",
-		dfb->fb.width, dfb->fb.height,
-		dfb->fb.bits_per_pixel, obj->phys_addr);
+	DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08llx\n",
+		dfb->fb.width, dfb->fb.height, dfb->fb.bits_per_pixel,
+		(unsigned long long)obj->phys_addr);
 
 	return 0;
 
@@ -177,6 +177,16 @@ int armada_fbdev_init(struct drm_device *dev)
 	return ret;
 }
 
+void armada_fbdev_lastclose(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+
+	drm_modeset_lock_all(dev);
+	if (priv->fbdev)
+		drm_fb_helper_restore_fbdev_mode(priv->fbdev);
+	drm_modeset_unlock_all(dev);
+}
+
 void armada_fbdev_fini(struct drm_device *dev)
 {
 	struct armada_private *priv = dev->dev_private;
@@ -192,11 +202,11 @@ void armada_fbdev_fini(struct drm_device *dev)
 			framebuffer_release(info);
 		}
 
+		drm_fb_helper_fini(fbh);
+
 		if (fbh->fb)
 			fbh->fb->funcs->destroy(fbh->fb);
 
-		drm_fb_helper_fini(fbh);
-
 		priv->fbdev = NULL;
 	}
 }

drivers/gpu/drm/armada/armada_gem.c

@@ -172,8 +172,9 @@ armada_gem_linear_back(struct drm_device *dev, struct armada_gem_object *obj)
 		obj->dev_addr = obj->linear->start;
 	}
 
-	DRM_DEBUG_DRIVER("obj %p phys %#x dev %#x\n",
-			 obj, obj->phys_addr, obj->dev_addr);
+	DRM_DEBUG_DRIVER("obj %p phys %#llx dev %#llx\n", obj,
+			 (unsigned long long)obj->phys_addr,
+			 (unsigned long long)obj->dev_addr);
 
 	return 0;
 }
@@ -557,7 +558,6 @@ armada_gem_prime_import(struct drm_device *dev, struct dma_buf *buf)
 			 * refcount on the gem object itself.
 			 */
 			drm_gem_object_reference(obj);
-			dma_buf_put(buf);
 			return obj;
 		}
 	}
@@ -573,6 +573,7 @@ armada_gem_prime_import(struct drm_device *dev, struct dma_buf *buf)
 	}
 
 	dobj->obj.import_attach = attach;
+	get_dma_buf(buf);
 
 	/*
 	 * Don't call dma_buf_map_attachment() here - it maps the

drivers/gpu/drm/drm_edid.c

@@ -68,6 +68,8 @@
 #define EDID_QUIRK_DETAILED_SYNC_PP		(1 << 6)
 /* Force reduced-blanking timings for detailed modes */
 #define EDID_QUIRK_FORCE_REDUCED_BLANKING	(1 << 7)
+/* Force 8bpc */
+#define EDID_QUIRK_FORCE_8BPC			(1 << 8)
 
 struct detailed_mode_closure {
 	struct drm_connector *connector;
@@ -128,6 +130,9 @@ static struct edid_quirk {
 
 	/* Medion MD 30217 PG */
 	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
+
+	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
+	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
 };
 
 /*
@@ -3435,6 +3440,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid)
 
 	drm_add_display_info(edid, &connector->display_info);
 
+	if (quirks & EDID_QUIRK_FORCE_8BPC)
+		connector->display_info.bpc = 8;
+
 	return num_modes;
 }
 EXPORT_SYMBOL(drm_add_edid_modes);

drivers/gpu/drm/drm_stub.c

@@ -566,11 +566,11 @@ err_unload:
 	if (dev->driver->unload)
 		dev->driver->unload(dev);
 err_primary_node:
-	drm_put_minor(dev->primary);
+	drm_unplug_minor(dev->primary);
 err_render_node:
-	drm_put_minor(dev->render);
+	drm_unplug_minor(dev->render);
 err_control_node:
-	drm_put_minor(dev->control);
+	drm_unplug_minor(dev->control);
 err_agp:
 	if (dev->driver->bus->agp_destroy)
 		dev->driver->bus->agp_destroy(dev);

drivers/gpu/drm/i915/i915_dma.c

@@ -83,6 +83,14 @@ void i915_update_dri1_breadcrumb(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv;
 
+	/*
+	 * The dri breadcrumb update races against the drm master disappearing.
+	 * Instead of trying to fix this (this is by far not the only ums issue)
+	 * just don't do the update in kms mode.
+	 */
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
 	if (dev->primary->master) {
 		master_priv = dev->primary->master->driver_priv;
 		if (master_priv->sarea_priv)
@@ -1490,16 +1498,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	spin_lock_init(&dev_priv->uncore.lock);
 	spin_lock_init(&dev_priv->mm.object_stat_lock);
 	mutex_init(&dev_priv->dpio_lock);
-	mutex_init(&dev_priv->rps.hw_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
-	mutex_init(&dev_priv->pc8.lock);
-	dev_priv->pc8.requirements_met = false;
-	dev_priv->pc8.gpu_idle = false;
-	dev_priv->pc8.irqs_disabled = false;
-	dev_priv->pc8.enabled = false;
-	dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
-	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
+	intel_pm_setup(dev);
 
 	intel_display_crc_init(dev);
 
@@ -1603,7 +1604,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	}
 
 	intel_irq_init(dev);
-	intel_pm_init(dev);
 	intel_uncore_sanitize(dev);
 
 	/* Try to make sure MCHBAR is enabled before poking at it */
@@ -1848,8 +1848,10 @@ void i915_driver_lastclose(struct drm_device * dev)
 
 void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
 {
+	mutex_lock(&dev->struct_mutex);
 	i915_gem_context_close(dev, file_priv);
 	i915_gem_release(dev, file_priv);
+	mutex_unlock(&dev->struct_mutex);
 }
 
 void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)

drivers/gpu/drm/i915/i915_drv.c

@@ -651,6 +651,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		intel_modeset_init_hw(dev);
 
 		drm_modeset_lock_all(dev);
+		drm_mode_config_reset(dev);
 		intel_modeset_setup_hw_state(dev, true);
 		drm_modeset_unlock_all(dev);
 

drivers/gpu/drm/i915/i915_drv.h

@@ -1755,8 +1755,13 @@ struct drm_i915_file_private {
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
 				 ((dev)->pdev->device & 0xFF00) == 0x0C00)
-#define IS_ULT(dev)		(IS_HASWELL(dev) && \
+#define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
+				 (((dev)->pdev->device & 0xf) == 0x2  || \
+				 ((dev)->pdev->device & 0xf) == 0x6 || \
+				 ((dev)->pdev->device & 0xf) == 0xe))
+#define IS_HSW_ULT(dev)		(IS_HASWELL(dev) && \
 				 ((dev)->pdev->device & 0xFF00) == 0x0A00)
+#define IS_ULT(dev)		(IS_HSW_ULT(dev) || IS_BDW_ULT(dev))
 #define IS_HSW_GT3(dev)		(IS_HASWELL(dev) && \
 				 ((dev)->pdev->device & 0x00F0) == 0x0020)
 #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
@@ -1901,9 +1906,7 @@ void i915_queue_hangcheck(struct drm_device *dev);
 void i915_handle_error(struct drm_device *dev, bool wedged);
 
 extern void intel_irq_init(struct drm_device *dev);
-extern void intel_pm_init(struct drm_device *dev);
 extern void intel_hpd_init(struct drm_device *dev);
-extern void intel_pm_init(struct drm_device *dev);
 
 extern void intel_uncore_sanitize(struct drm_device *dev);
 extern void intel_uncore_early_sanitize(struct drm_device *dev);

drivers/gpu/drm/i915/i915_gem_context.c

@@ -347,10 +347,8 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
-	mutex_lock(&dev->struct_mutex);
 	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
 	idr_destroy(&file_priv->context_idr);
-	mutex_unlock(&dev->struct_mutex);
 }
 
 static struct i915_hw_context *
@@ -423,11 +421,21 @@ static int do_switch(struct i915_hw_context *to)
 	if (ret)
 		return ret;
 
-	/* Clear this page out of any CPU caches for coherent swap-in/out. Note
+	/*
+	 * Pin can switch back to the default context if we end up calling into
+	 * evict_everything - as a last ditch gtt defrag effort that also
+	 * switches to the default context. Hence we need to reload from here.
+	 */
+	from = ring->last_context;
+
+	/*
+	 * Clear this page out of any CPU caches for coherent swap-in/out. Note
 	 * that thanks to write = false in this call and us not setting any gpu
 	 * write domains when putting a context object onto the active list
 	 * (when switching away from it), this won't block.
-	 * XXX: We need a real interface to do this instead of trickery. */
+	 *
+	 * XXX: We need a real interface to do this instead of trickery.
+	 */
 	ret = i915_gem_object_set_to_gtt_domain(to->obj, false);
 	if (ret) {
 		i915_gem_object_unpin(to->obj);

drivers/gpu/drm/i915/i915_gem_evict.c

@@ -88,6 +88,7 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
 	} else
 		drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level);
 
+search_again:
 	/* First see if there is a large enough contiguous idle region... */
 	list_for_each_entry(vma, &vm->inactive_list, mm_list) {
 		if (mark_free(vma, &unwind_list))
@@ -115,10 +116,17 @@ none:
 		list_del_init(&vma->exec_list);
 	}
 
-	/* We expect the caller to unpin, evict all and try again, or give up.
-	 * So calling i915_gem_evict_vm() is unnecessary.
+	/* Can we unpin some objects such as idle hw contents,
+	 * or pending flips?
 	 */
-	return -ENOSPC;
+	ret = nonblocking ? -ENOSPC : i915_gpu_idle(dev);
+	if (ret)
+		return ret;
+
+	/* Only idle the GPU and repeat the search once */
+	i915_gem_retire_requests(dev);
+	nonblocking = true;
+	goto search_again;
 
 found:
 	/* drm_mm doesn't allow any other other operations while

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -337,8 +337,8 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 		kfree(ppgtt->gen8_pt_dma_addr[i]);
 	}
 
-	__free_pages(ppgtt->gen8_pt_pages, ppgtt->num_pt_pages << PAGE_SHIFT);
-	__free_pages(ppgtt->pd_pages, ppgtt->num_pd_pages << PAGE_SHIFT);
+	__free_pages(ppgtt->gen8_pt_pages, get_order(ppgtt->num_pt_pages << PAGE_SHIFT));
+	__free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT));
 }
 
 /**
@@ -1241,6 +1241,11 @@ static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
 	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
 	if (bdw_gmch_ctl)
 		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+	if (bdw_gmch_ctl > 4) {
+		WARN_ON(!i915_preliminary_hw_support);
+		return 4<<20;
+	}
+
 	return bdw_gmch_ctl << 20;
 }
 

drivers/gpu/drm/i915/intel_display.c

@@ -9135,7 +9135,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 	if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5)
 		PIPE_CONF_CHECK_I(pipe_bpp);
 
-	if (!IS_HASWELL(dev)) {
+	if (!HAS_DDI(dev)) {
 		PIPE_CONF_CHECK_CLOCK_FUZZY(adjusted_mode.crtc_clock);
 		PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock);
 	}
@@ -11036,8 +11036,6 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 	}
 
 	intel_modeset_check_state(dev);
-
-	drm_mode_config_reset(dev);
 }
 
 void intel_modeset_gem_init(struct drm_device *dev)
@@ -11046,7 +11044,10 @@ void intel_modeset_gem_init(struct drm_device *dev)
 
 	intel_setup_overlay(dev);
 
+	drm_modeset_lock_all(dev);
+	drm_mode_config_reset(dev);
 	intel_modeset_setup_hw_state(dev, false);
+	drm_modeset_unlock_all(dev);
 }
 
 void intel_modeset_cleanup(struct drm_device *dev)

drivers/gpu/drm/i915/intel_drv.h

@@ -821,6 +821,7 @@ void intel_update_sprite_watermarks(struct drm_plane *plane,
 				    uint32_t sprite_width, int pixel_size,
 				    bool enabled, bool scaled);
 void intel_init_pm(struct drm_device *dev);
+void intel_pm_setup(struct drm_device *dev);
 bool intel_fbc_enabled(struct drm_device *dev);
 void intel_update_fbc(struct drm_device *dev);
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv);

drivers/gpu/drm/i915/intel_panel.c

@@ -451,7 +451,9 @@ static u32 intel_panel_get_backlight(struct drm_device *dev,
 
 	spin_lock_irqsave(&dev_priv->backlight.lock, flags);
 
-	if (HAS_PCH_SPLIT(dev)) {
+	if (IS_BROADWELL(dev)) {
+		val = I915_READ(BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK;
+	} else if (HAS_PCH_SPLIT(dev)) {
 		val = I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
 	} else {
 		if (IS_VALLEYVIEW(dev))
@@ -479,6 +481,13 @@ static u32 intel_panel_get_backlight(struct drm_device *dev,
 	return val;
 }
 
+static void intel_bdw_panel_set_backlight(struct drm_device *dev, u32 level)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val = I915_READ(BLC_PWM_PCH_CTL2) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+	I915_WRITE(BLC_PWM_PCH_CTL2, val | level);
+}
+
 static void intel_pch_panel_set_backlight(struct drm_device *dev, u32 level)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -496,7 +505,9 @@ static void intel_panel_actually_set_backlight(struct drm_device *dev,
 	DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level);
 	level = intel_panel_compute_brightness(dev, pipe, level);
 
-	if (HAS_PCH_SPLIT(dev))
+	if (IS_BROADWELL(dev))
+		return intel_bdw_panel_set_backlight(dev, level);
+	else if (HAS_PCH_SPLIT(dev))
 		return intel_pch_panel_set_backlight(dev, level);
 
 	if (is_backlight_combination_mode(dev)) {
@@ -666,7 +677,16 @@ void intel_panel_enable_backlight(struct intel_connector *connector)
 		POSTING_READ(reg);
 		I915_WRITE(reg, tmp | BLM_PWM_ENABLE);
 
-		if (HAS_PCH_SPLIT(dev) &&
+		if (IS_BROADWELL(dev)) {
+			/*
+			 * Broadwell requires PCH override to drive the PCH
+			 * backlight pin. The above will configure the CPU
+			 * backlight pin, which we don't plan to use.
+			 */
+			tmp = I915_READ(BLC_PWM_PCH_CTL1);
+			tmp |= BLM_PCH_OVERRIDE_ENABLE | BLM_PCH_PWM_ENABLE;
+			I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
+		} else if (HAS_PCH_SPLIT(dev) &&
 		    !(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) {
 			tmp = I915_READ(BLC_PWM_PCH_CTL1);
 			tmp |= BLM_PCH_PWM_ENABLE;

drivers/gpu/drm/i915/intel_pm.c

@@ -5685,6 +5685,7 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool is_enabled, enable_requested;
+	unsigned long irqflags;
 	uint32_t tmp;
 
 	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
@@ -5702,9 +5703,24 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 				      HSW_PWR_WELL_STATE_ENABLED), 20))
 				DRM_ERROR("Timeout enabling power well\n");
 		}
+
+		if (IS_BROADWELL(dev)) {
+			spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+			I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_B),
+				   dev_priv->de_irq_mask[PIPE_B]);
+			I915_WRITE(GEN8_DE_PIPE_IER(PIPE_B),
+				   ~dev_priv->de_irq_mask[PIPE_B] |
+				   GEN8_PIPE_VBLANK);
+			I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_C),
+				   dev_priv->de_irq_mask[PIPE_C]);
+			I915_WRITE(GEN8_DE_PIPE_IER(PIPE_C),
+				   ~dev_priv->de_irq_mask[PIPE_C] |
+				   GEN8_PIPE_VBLANK);
+			POSTING_READ(GEN8_DE_PIPE_IER(PIPE_C));
+			spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+		}
 	} else {
 		if (enable_requested) {
-			unsigned long irqflags;
 			enum pipe p;
 
 			I915_WRITE(HSW_PWR_WELL_DRIVER, 0);
@@ -6130,10 +6146,19 @@ int vlv_freq_opcode(int ddr_freq, int val)
 	return val;
 }
 
-void intel_pm_init(struct drm_device *dev)
+void intel_pm_setup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	mutex_init(&dev_priv->rps.hw_lock);
+
+	mutex_init(&dev_priv->pc8.lock);
+	dev_priv->pc8.requirements_met = false;
+	dev_priv->pc8.gpu_idle = false;
+	dev_priv->pc8.irqs_disabled = false;
+	dev_priv->pc8.enabled = false;
+	dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
+	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
 	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
 			  intel_gen6_powersave_work);
 }

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -965,6 +965,7 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 	} else if (IS_GEN6(ring->dev)) {
 		mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
 	} else {
+		/* XXX: gen8 returns to sanity */
 		mmio = RING_HWS_PGA(ring->mmio_base);
 	}
 

drivers/gpu/drm/i915/intel_uncore.c

@@ -784,6 +784,7 @@ static int gen6_do_reset(struct drm_device *dev)
 int intel_gpu_reset(struct drm_device *dev)
 {
 	switch (INTEL_INFO(dev)->gen) {
+	case 8:
 	case 7:
 	case 6: return gen6_do_reset(dev);
 	case 5: return ironlake_do_reset(dev);

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -858,6 +858,12 @@ static int nouveau_pmops_runtime_suspend(struct device *dev)
 	if (nouveau_runtime_pm == 0)
 		return -EINVAL;
 
+	/* are we optimus enabled? */
+	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
+		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+		return -EINVAL;
+	}
+
 	nv_debug_level(SILENT);
 	drm_kms_helper_poll_disable(drm_dev);
 	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);

drivers/gpu/drm/radeon/atombios_crtc.c

@@ -1196,7 +1196,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	} else if ((rdev->family == CHIP_TAHITI) ||
 		   (rdev->family == CHIP_PITCAIRN))
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16);
-	else if (rdev->family == CHIP_VERDE)
+	else if ((rdev->family == CHIP_VERDE) ||
+		 (rdev->family == CHIP_OLAND) ||
+		 (rdev->family == CHIP_HAINAN)) /* for completeness.  HAINAN has no display hw */
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16);
 
 	switch (radeon_crtc->crtc_id) {

drivers/gpu/drm/radeon/cik_sdma.c

@@ -458,7 +458,7 @@ int cik_copy_dma(struct radeon_device *rdev,
 		radeon_ring_write(ring, 0); /* src/dst endian swap */
 		radeon_ring_write(ring, src_offset & 0xffffffff);
 		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff);
-		radeon_ring_write(ring, dst_offset & 0xfffffffc);
+		radeon_ring_write(ring, dst_offset & 0xffffffff);
 		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff);
 		src_offset += cur_size_in_bytes;
 		dst_offset += cur_size_in_bytes;

drivers/gpu/drm/radeon/radeon_asic.c

@@ -2021,7 +2021,7 @@ static struct radeon_asic ci_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = NULL,
+		.blit = &cik_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &cik_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2122,7 +2122,7 @@ static struct radeon_asic kv_asic = {
 		.hdmi_setmode = &evergreen_hdmi_setmode,
 	},
 	.copy = {
-		.blit = NULL,
+		.blit = &cik_copy_cpdma,
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &cik_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,

drivers/gpu/drm/radeon/radeon_drv.c

@@ -508,15 +508,6 @@ static const struct file_operations radeon_driver_kms_fops = {
 #endif
 };
 
-
-static void
-radeon_pci_shutdown(struct pci_dev *pdev)
-{
-	struct drm_device *dev = pci_get_drvdata(pdev);
-
-	radeon_driver_unload_kms(dev);
-}
-
 static struct drm_driver kms_driver = {
 	.driver_features =
 	    DRIVER_USE_AGP |
@@ -586,7 +577,6 @@ static struct pci_driver radeon_kms_pci_driver = {
 	.probe = radeon_pci_probe,
 	.remove = radeon_pci_remove,
 	.driver.pm = &radeon_pm_ops,
-	.shutdown = radeon_pci_shutdown,
 };
 
 static int __init radeon_init(void)

drivers/gpu/drm/radeon/rs690.c

@@ -162,6 +162,16 @@ static void rs690_mc_init(struct radeon_device *rdev)
 	base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
 	base = G_000100_MC_FB_START(base) << 16;
 	rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
+	/* Some boards seem to be configured for 128MB of sideport memory,
+	 * but really only have 64MB.  Just skip the sideport and use
+	 * UMA memory.
+	 */
+	if (rdev->mc.igp_sideport_enabled &&
+	    (rdev->mc.real_vram_size == (384 * 1024 * 1024))) {
+		base += 128 * 1024 * 1024;
+		rdev->mc.real_vram_size -= 128 * 1024 * 1024;
+		rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
+	}
 
 	/* Use K8 direct mapping for fast fb access. */ 
 	rdev->fastfb_working = false;

drivers/gpu/drm/ttm/ttm_bo_vm.c

@@ -169,9 +169,9 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) +
-	    drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
-	page_last = vma_pages(vma) +
-	    drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
+		vma->vm_pgoff - drm_vma_node_start(&bo->vma_node);
+	page_last = vma_pages(vma) + vma->vm_pgoff -
+		drm_vma_node_start(&bo->vma_node);
 
 	if (unlikely(page_offset >= bo->num_pages)) {
 		retval = VM_FAULT_SIGBUS;

drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c

@@ -68,6 +68,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 				  SVGA_FIFO_3D_HWVERSION));
 		break;
 	}
+	case DRM_VMW_PARAM_MAX_SURF_MEMORY:
+		param->value = dev_priv->memory_size;
+		break;
 	default:
 		DRM_ERROR("Illegal vmwgfx get param request: %d\n",
 			  param->param);

drivers/iio/adc/ad7887.c

@@ -200,7 +200,13 @@ static const struct ad7887_chip_info ad7887_chip_info_tbl[] = {
 			.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 			.address = 1,
 			.scan_index = 1,
-			.scan_type = IIO_ST('u', 12, 16, 0),
+			.scan_type = {
+				.sign = 'u',
+				.realbits = 12,
+				.storagebits = 16,
+				.shift = 0,
+				.endianness = IIO_BE,
+			},
 		},
 		.channel[1] = {
 			.type = IIO_VOLTAGE,
@@ -210,7 +216,13 @@ static const struct ad7887_chip_info ad7887_chip_info_tbl[] = {
 			.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 			.address = 0,
 			.scan_index = 0,
-			.scan_type = IIO_ST('u', 12, 16, 0),
+			.scan_type = {
+				.sign = 'u',
+				.realbits = 12,
+				.storagebits = 16,
+				.shift = 0,
+				.endianness = IIO_BE,
+			},
 		},
 		.channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2),
 		.int_vref_mv = 2500,

drivers/iio/imu/adis16400_core.c

@@ -651,7 +651,12 @@ static const struct iio_chan_spec adis16448_channels[] = {
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = ADIS16448_BARO_OUT,
 		.scan_index = ADIS16400_SCAN_BARO,
-		.scan_type = IIO_ST('s', 16, 16, 0),
+		.scan_type = {
+			.sign = 's',
+			.realbits = 16,
+			.storagebits = 16,
+			.endianness = IIO_BE,
+		},
 	},
 	ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12),
 	IIO_CHAN_SOFT_TIMESTAMP(11)

drivers/iio/light/cm36651.c

@@ -387,7 +387,7 @@ static int cm36651_read_int_time(struct cm36651_data *cm36651,
 		return -EINVAL;
 	}
 
-	return IIO_VAL_INT_PLUS_MICRO;
+	return IIO_VAL_INT;
 }
 
 static int cm36651_write_int_time(struct cm36651_data *cm36651,

drivers/infiniband/ulp/isert/ib_isert.c

@@ -207,7 +207,9 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn)
 	isert_conn->conn_rx_descs = NULL;
 }
 
+static void isert_cq_tx_work(struct work_struct *);
 static void isert_cq_tx_callback(struct ib_cq *, void *);
+static void isert_cq_rx_work(struct work_struct *);
 static void isert_cq_rx_callback(struct ib_cq *, void *);
 
 static int
@@ -259,26 +261,36 @@ isert_create_device_ib_res(struct isert_device *device)
 		cq_desc[i].device = device;
 		cq_desc[i].cq_index = i;
 
+		INIT_WORK(&cq_desc[i].cq_rx_work, isert_cq_rx_work);
 		device->dev_rx_cq[i] = ib_create_cq(device->ib_device,
 						isert_cq_rx_callback,
 						isert_cq_event_callback,
 						(void *)&cq_desc[i],
 						ISER_MAX_RX_CQ_LEN, i);
-		if (IS_ERR(device->dev_rx_cq[i]))
+		if (IS_ERR(device->dev_rx_cq[i])) {
+			ret = PTR_ERR(device->dev_rx_cq[i]);
+			device->dev_rx_cq[i] = NULL;
 			goto out_cq;
+		}
 
+		INIT_WORK(&cq_desc[i].cq_tx_work, isert_cq_tx_work);
 		device->dev_tx_cq[i] = ib_create_cq(device->ib_device,
 						isert_cq_tx_callback,
 						isert_cq_event_callback,
 						(void *)&cq_desc[i],
 						ISER_MAX_TX_CQ_LEN, i);
-		if (IS_ERR(device->dev_tx_cq[i]))
+		if (IS_ERR(device->dev_tx_cq[i])) {
+			ret = PTR_ERR(device->dev_tx_cq[i]);
+			device->dev_tx_cq[i] = NULL;
 			goto out_cq;
+		}
 
-		if (ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP))
+		ret = ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP);
+		if (ret)
 			goto out_cq;
 
-		if (ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP))
+		ret = ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP);
+		if (ret)
 			goto out_cq;
 	}
 
@@ -1724,7 +1736,6 @@ isert_cq_tx_callback(struct ib_cq *cq, void *context)
 {
 	struct isert_cq_desc *cq_desc = (struct isert_cq_desc *)context;
 
-	INIT_WORK(&cq_desc->cq_tx_work, isert_cq_tx_work);
 	queue_work(isert_comp_wq, &cq_desc->cq_tx_work);
 }
 
@@ -1768,7 +1779,6 @@ isert_cq_rx_callback(struct ib_cq *cq, void *context)
 {
 	struct isert_cq_desc *cq_desc = (struct isert_cq_desc *)context;
 
-	INIT_WORK(&cq_desc->cq_rx_work, isert_cq_rx_work);
 	queue_work(isert_rx_wq, &cq_desc->cq_rx_work);
 }
 

drivers/irqchip/irq-renesas-intc-irqpin.c

@@ -149,8 +149,9 @@ static void intc_irqpin_read_modify_write(struct intc_irqpin_priv *p,
 static void intc_irqpin_mask_unmask_prio(struct intc_irqpin_priv *p,
 					 int irq, int do_mask)
 {
-	int bitfield_width = 4; /* PRIO assumed to have fixed bitfield width */
-	int shift = (7 - irq) * bitfield_width; /* PRIO assumed to be 32-bit */
+	/* The PRIO register is assumed to be 32-bit with fixed 4-bit fields. */
+	int bitfield_width = 4;
+	int shift = 32 - (irq + 1) * bitfield_width;
 
 	intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_PRIO,
 				      shift, bitfield_width,
@@ -159,8 +160,9 @@ static void intc_irqpin_mask_unmask_prio(struct intc_irqpin_priv *p,
 
 static int intc_irqpin_set_sense(struct intc_irqpin_priv *p, int irq, int value)
 {
+	/* The SENSE register is assumed to be 32-bit. */
 	int bitfield_width = p->config.sense_bitfield_width;
-	int shift = (7 - irq) * bitfield_width; /* SENSE assumed to be 32-bit */
+	int shift = 32 - (irq + 1) * bitfield_width;
 
 	dev_dbg(&p->pdev->dev, "sense irq = %d, mode = %d\n", irq, value);
 

drivers/net/can/usb/ems_usb.c

@@ -625,6 +625,7 @@ static int ems_usb_start(struct ems_usb *dev)
 			usb_unanchor_urb(urb);
 			usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf,
 					  urb->transfer_dma);
+			usb_free_urb(urb);
 			break;
 		}
 
@@ -798,8 +799,8 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 	 * allowed (MAX_TX_URBS).
 	 */
 	if (!context) {
-		usb_unanchor_urb(urb);
 		usb_free_coherent(dev->udev, size, buf, urb->transfer_dma);
+		usb_free_urb(urb);
 
 		netdev_warn(netdev, "couldn't find free context\n");
 

drivers/net/can/usb/peak_usb/pcan_usb_pro.c

@@ -927,6 +927,9 @@ static int pcan_usb_pro_init(struct peak_usb_device *dev)
 	/* set LED in default state (end of init phase) */
 	pcan_usb_pro_set_led(dev, 0, 1);
 
+	kfree(bi);
+	kfree(fi);
+
 	return 0;
 
  err_out:

drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c

@@ -447,8 +447,9 @@ irqreturn_t qlcnic_83xx_intr(int irq, void *data)
 
 	qlcnic_83xx_poll_process_aen(adapter);
 
-	if (ahw->diag_test == QLCNIC_INTERRUPT_TEST) {
-		ahw->diag_cnt++;
+	if (ahw->diag_test) {
+		if (ahw->diag_test == QLCNIC_INTERRUPT_TEST)
+			ahw->diag_cnt++;
 		qlcnic_83xx_enable_legacy_msix_mbx_intr(adapter);
 		return IRQ_HANDLED;
 	}
@@ -1345,11 +1346,6 @@ static int qlcnic_83xx_diag_alloc_res(struct net_device *netdev, int test,
 	}
 
 	if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) {
-		/* disable and free mailbox interrupt */
-		if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
-			qlcnic_83xx_enable_mbx_poll(adapter);
-			qlcnic_83xx_free_mbx_intr(adapter);
-		}
 		adapter->ahw->loopback_state = 0;
 		adapter->ahw->hw_ops->setup_link_event(adapter, 1);
 	}
@@ -1363,33 +1359,20 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev,
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_host_sds_ring *sds_ring;
-	int ring, err;
+	int ring;
 
 	clear_bit(__QLCNIC_DEV_UP, &adapter->state);
 	if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST) {
 		for (ring = 0; ring < adapter->drv_sds_rings; ring++) {
 			sds_ring = &adapter->recv_ctx->sds_rings[ring];
-			qlcnic_83xx_disable_intr(adapter, sds_ring);
-			if (!(adapter->flags & QLCNIC_MSIX_ENABLED))
-				qlcnic_83xx_enable_mbx_poll(adapter);
+			if (adapter->flags & QLCNIC_MSIX_ENABLED)
+				qlcnic_83xx_disable_intr(adapter, sds_ring);
 		}
 	}
 
 	qlcnic_fw_destroy_ctx(adapter);
 	qlcnic_detach(adapter);
 
-	if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) {
-		if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
-			err = qlcnic_83xx_setup_mbx_intr(adapter);
-			qlcnic_83xx_disable_mbx_poll(adapter);
-			if (err) {
-				dev_err(&adapter->pdev->dev,
-					"%s: failed to setup mbx interrupt\n",
-					__func__);
-				goto out;
-			}
-		}
-	}
 	adapter->ahw->diag_test = 0;
 	adapter->drv_sds_rings = drv_sds_rings;
 
@@ -1399,9 +1382,6 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev,
 	if (netif_running(netdev))
 		__qlcnic_up(adapter, netdev);
 
-	if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST &&
-	    !(adapter->flags & QLCNIC_MSIX_ENABLED))
-		qlcnic_83xx_disable_mbx_poll(adapter);
 out:
 	netif_device_attach(netdev);
 }
@@ -3754,6 +3734,19 @@ static void qlcnic_83xx_decode_mbx_rsp(struct qlcnic_adapter *adapter,
 	return;
 }
 
+static inline void qlcnic_dump_mailbox_registers(struct qlcnic_adapter *adapter)
+{
+	struct qlcnic_hardware_context *ahw = adapter->ahw;
+	u32 offset;
+
+	offset = QLCRDX(ahw, QLCNIC_DEF_INT_MASK);
+	dev_info(&adapter->pdev->dev, "Mbx interrupt mask=0x%x, Mbx interrupt enable=0x%x, Host mbx control=0x%x, Fw mbx control=0x%x",
+		 readl(ahw->pci_base0 + offset),
+		 QLCRDX(ahw, QLCNIC_MBX_INTR_ENBL),
+		 QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL),
+		 QLCRDX(ahw, QLCNIC_FW_MBX_CTRL));
+}
+
 static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 {
 	struct qlcnic_mailbox *mbx = container_of(work, struct qlcnic_mailbox,
@@ -3798,6 +3791,8 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 				__func__, cmd->cmd_op, cmd->type, ahw->pci_func,
 				ahw->op_mode);
 			clear_bit(QLC_83XX_MBX_READY, &mbx->status);
+			qlcnic_dump_mailbox_registers(adapter);
+			qlcnic_83xx_get_mbx_data(adapter, cmd);
 			qlcnic_dump_mbx(adapter, cmd);
 			qlcnic_83xx_idc_request_reset(adapter,
 						      QLCNIC_FORCE_FW_DUMP_KEY);

drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h

@@ -662,4 +662,5 @@ pci_ers_result_t qlcnic_83xx_io_error_detected(struct pci_dev *,
 					       pci_channel_state_t);
 pci_ers_result_t qlcnic_83xx_io_slot_reset(struct pci_dev *);
 void qlcnic_83xx_io_resume(struct pci_dev *);
+void qlcnic_83xx_stop_hw(struct qlcnic_adapter *);
 #endif

drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c

@@ -740,6 +740,7 @@ static int qlcnic_83xx_idc_unknown_state(struct qlcnic_adapter *adapter)
 	adapter->ahw->idc.err_code = -EIO;
 	dev_err(&adapter->pdev->dev,
 		"%s: Device in unknown state\n", __func__);
+	clear_bit(__QLCNIC_RESETTING, &adapter->state);
 	return 0;
 }
 
@@ -818,7 +819,6 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter)
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	struct qlcnic_mailbox *mbx = ahw->mailbox;
 	int ret = 0;
-	u32 owner;
 	u32 val;
 
 	/* Perform NIC configuration based ready state entry actions */
@@ -848,9 +848,9 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter)
 			set_bit(__QLCNIC_RESETTING, &adapter->state);
 			qlcnic_83xx_idc_enter_need_reset_state(adapter, 1);
 		}  else {
-			owner = qlcnic_83xx_idc_find_reset_owner_id(adapter);
-			if (ahw->pci_func == owner)
-				qlcnic_dump_fw(adapter);
+			netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n",
+				    __func__);
+			qlcnic_83xx_idc_enter_failed_state(adapter, 1);
 		}
 		return -EIO;
 	}
@@ -948,13 +948,26 @@ static int qlcnic_83xx_idc_need_quiesce_state(struct qlcnic_adapter *adapter)
 	return 0;
 }
 
-static int qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter)
+static void qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter)
 {
-	dev_err(&adapter->pdev->dev, "%s: please restart!!\n", __func__);
+	struct qlcnic_hardware_context *ahw = adapter->ahw;
+	u32 val, owner;
+
+	val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL);
+	if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) {
+		owner = qlcnic_83xx_idc_find_reset_owner_id(adapter);
+		if (ahw->pci_func == owner) {
+			qlcnic_83xx_stop_hw(adapter);
+			qlcnic_dump_fw(adapter);
+		}
+	}
+
+	netdev_warn(adapter->netdev, "%s: Reboot will be required to recover the adapter!!\n",
+		    __func__);
 	clear_bit(__QLCNIC_RESETTING, &adapter->state);
-	adapter->ahw->idc.err_code = -EIO;
+	ahw->idc.err_code = -EIO;
 
-	return 0;
+	return;
 }
 
 static int qlcnic_83xx_idc_quiesce_state(struct qlcnic_adapter *adapter)
@@ -1063,12 +1076,6 @@ void qlcnic_83xx_idc_poll_dev_state(struct work_struct *work)
 	adapter->ahw->idc.prev_state = adapter->ahw->idc.curr_state;
 	qlcnic_83xx_periodic_tasks(adapter);
 
-	/* Do not reschedule if firmaware is in hanged state and auto
-	 * recovery is disabled
-	 */
-	if ((adapter->flags & QLCNIC_FW_HANG) && !qlcnic_auto_fw_reset)
-		return;
-
 	/* Re-schedule the function */
 	if (test_bit(QLC_83XX_MODULE_LOADED, &adapter->ahw->idc.status))
 		qlcnic_schedule_work(adapter, qlcnic_83xx_idc_poll_dev_state,
@@ -1219,10 +1226,10 @@ void qlcnic_83xx_idc_request_reset(struct qlcnic_adapter *adapter, u32 key)
 	}
 
 	val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL);
-	if ((val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) ||
-	    !qlcnic_auto_fw_reset) {
-		dev_err(&adapter->pdev->dev,
-			"%s:failed, device in non reset mode\n", __func__);
+	if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) {
+		netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n",
+			    __func__);
+		qlcnic_83xx_idc_enter_failed_state(adapter, 0);
 		qlcnic_83xx_unlock_driver(adapter);
 		return;
 	}
@@ -1254,24 +1261,24 @@ static int qlcnic_83xx_copy_bootloader(struct qlcnic_adapter *adapter)
 	if (size & 0xF)
 		size = (size + 16) & ~0xF;
 
-	p_cache = kzalloc(size, GFP_KERNEL);
+	p_cache = vzalloc(size);
 	if (p_cache == NULL)
 		return -ENOMEM;
 
 	ret = qlcnic_83xx_lockless_flash_read32(adapter, src, p_cache,
 						size / sizeof(u32));
 	if (ret) {
-		kfree(p_cache);
+		vfree(p_cache);
 		return ret;
 	}
 	/* 16 byte write to MS memory */
 	ret = qlcnic_83xx_ms_mem_write128(adapter, dest, (u32 *)p_cache,
 					  size / 16);
 	if (ret) {
-		kfree(p_cache);
+		vfree(p_cache);
 		return ret;
 	}
-	kfree(p_cache);
+	vfree(p_cache);
 
 	return ret;
 }
@@ -1939,7 +1946,7 @@ static void qlcnic_83xx_exec_template_cmd(struct qlcnic_adapter *p_dev,
 	p_dev->ahw->reset.seq_index = index;
 }
 
-static void qlcnic_83xx_stop_hw(struct qlcnic_adapter *p_dev)
+void qlcnic_83xx_stop_hw(struct qlcnic_adapter *p_dev)
 {
 	p_dev->ahw->reset.seq_index = 0;
 
@@ -1994,6 +2001,14 @@ static int qlcnic_83xx_restart_hw(struct qlcnic_adapter *adapter)
 	val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL);
 	if (!(val & QLC_83XX_IDC_GRACEFULL_RESET))
 		qlcnic_dump_fw(adapter);
+
+	if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) {
+		netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n",
+			    __func__);
+		qlcnic_83xx_idc_enter_failed_state(adapter, 1);
+		return err;
+	}
+
 	qlcnic_83xx_init_hw(adapter);
 
 	if (qlcnic_83xx_copy_bootloader(adapter))
@@ -2073,8 +2088,8 @@ int qlcnic_83xx_configure_opmode(struct qlcnic_adapter *adapter)
 		ahw->nic_mode = QLCNIC_DEFAULT_MODE;
 		adapter->nic_ops->init_driver = qlcnic_83xx_init_default_driver;
 		ahw->idc.state_entry = qlcnic_83xx_idc_ready_state_entry;
-		adapter->max_sds_rings = ahw->max_rx_ques;
-		adapter->max_tx_rings = ahw->max_tx_ques;
+		adapter->max_sds_rings = QLCNIC_MAX_SDS_RINGS;
+		adapter->max_tx_rings = QLCNIC_MAX_TX_RINGS;
 	} else {
 		return -EIO;
 	}