Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts: drivers/net/xen-netfront.c Minor overlapping changes in xen-netfront.c, mostly to do with some buffer management changes alongside the split of stats into TX and RX. Signed-off-by: David S. Miller <davem@davemloft.net>
author: David S. Miller <davem@davemloft.net> 2015-01-15 00:53:17 -0500
committer: David S. Miller <davem@davemloft.net> 2015-01-15 00:53:17 -0500
commit: 3f3558bb512e0762d5a4573a4aaf038d7a616e92 (patch)
tree: 1e2b43d410093e949209ca33614f5cdfdd16e80e
parent: 9a6b4b392de4569e83ecfd6f382f3369f250b52f (diff)
parent: a6391a924cf5a16761ccd6b45094a7d5b9aeebac (diff)
download: linux-3f3558bb512e0762d5a4573a4aaf038d7a616e92.tar.gz
linux-3f3558bb512e0762d5a4573a4aaf038d7a616e92.tar.xz
268 files changed, 2818 insertions, 1441 deletions
diff --git a/.mailmap b/.mailmap
index ada8ad696b2e..d357e1bd2a43 100644
--- a/.mailmap
+++ b/.mailmap
@@ -51,6 +51,7 @@ Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Henk Vergonet <Henk.Vergonet@gmail.com>
 Henrik Kretzschmar <henne@nachtwindheim.de>
+Henrik Rydberg <rydberg@bitmath.org>
 Herbert Xu <herbert@gondor.apana.org.au>
 Jacob Shin <Jacob.Shin@amd.com>
 James Bottomley <jejb@mulgrave.(none)>
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 9bffdfc648dc..85b022179104 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -66,6 +66,8 @@ fwmark_reflect - BOOLEAN
 route/max_size - INTEGER
 	Maximum number of routes allowed in the kernel.  Increase
 	this when using large numbers of interfaces and/or routes.
+	From linux kernel 3.6 onwards, this is deprecated for ipv4
+	as route cache is no longer used.
 
 neigh/default/gc_thresh1 - INTEGER
 	Minimum number of entries to keep.  Garbage collector will not
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 230ce71f4d75..2b47704f75cb 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -389,9 +389,6 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	.release_cmd			= " + fabric_mod_name + "_release_cmd,\n"
 	buf += "	.shutdown_session		= " + fabric_mod_name + "_shutdown_session,\n"
 	buf += "	.close_session			= " + fabric_mod_name + "_close_session,\n"
-	buf += "	.stop_session			= " + fabric_mod_name + "_stop_session,\n"
-	buf += "	.fall_back_to_erl0		= " + fabric_mod_name + "_reset_nexus,\n"
-	buf += "	.sess_logged_in			= " + fabric_mod_name + "_sess_logged_in,\n"
 	buf += "	.sess_get_index			= " + fabric_mod_name + "_sess_get_index,\n"
 	buf += "	.sess_get_initiator_sid		= NULL,\n"
 	buf += "	.write_pending			= " + fabric_mod_name + "_write_pending,\n"
@@ -402,7 +399,7 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	.queue_data_in			= " + fabric_mod_name + "_queue_data_in,\n"
 	buf += "	.queue_status			= " + fabric_mod_name + "_queue_status,\n"
 	buf += "	.queue_tm_rsp			= " + fabric_mod_name + "_queue_tm_rsp,\n"
-	buf += "	.is_state_remove		= " + fabric_mod_name + "_is_state_remove,\n"
+	buf += "	.aborted_task			= " + fabric_mod_name + "_aborted_task,\n"
 	buf += "	/*\n"
 	buf += "	 * Setup function pointers for generic logic in target_core_fabric_configfs.c\n"
 	buf += "	 */\n"
@@ -428,7 +425,7 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	/*\n"
 	buf += "	 * Register the top level struct config_item_type with TCM core\n"
 	buf += "	 */\n"
-	buf += "	fabric = target_fabric_configfs_init(THIS_MODULE, \"" + fabric_mod_name[4:] + "\");\n"
+	buf += "	fabric = target_fabric_configfs_init(THIS_MODULE, \"" + fabric_mod_name + "\");\n"
 	buf += "	if (IS_ERR(fabric)) {\n"
 	buf += "		printk(KERN_ERR \"target_fabric_configfs_init() failed\\n\");\n"
 	buf += "		return PTR_ERR(fabric);\n"
@@ -595,7 +592,7 @@ def tcm_mod_dump_fabric_ops(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 		if re.search('get_fabric_name', fo):
 			buf += "char *" + fabric_mod_name + "_get_fabric_name(void)\n"
 			buf += "{\n"
-			buf += "	return \"" + fabric_mod_name[4:] + "\";\n"
+			buf += "	return \"" + fabric_mod_name + "\";\n"
 			buf += "}\n\n"
 			bufi += "char *" + fabric_mod_name + "_get_fabric_name(void);\n"
 			continue
@@ -820,27 +817,6 @@ def tcm_mod_dump_fabric_ops(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 			buf += "}\n\n"
 			bufi += "void " + fabric_mod_name + "_close_session(struct se_session *);\n"
 
-		if re.search('stop_session\)\(', fo):
-			buf += "void " + fabric_mod_name + "_stop_session(struct se_session *se_sess, int sess_sleep , int conn_sleep)\n"
-			buf += "{\n"
-			buf += "	return;\n"
-			buf += "}\n\n"
-			bufi += "void " + fabric_mod_name + "_stop_session(struct se_session *, int, int);\n"
-
-		if re.search('fall_back_to_erl0\)\(', fo):
-			buf += "void " + fabric_mod_name + "_reset_nexus(struct se_session *se_sess)\n"
-			buf += "{\n"
-			buf += "	return;\n"
-			buf += "}\n\n"
-			bufi += "void " + fabric_mod_name + "_reset_nexus(struct se_session *);\n"
-
-		if re.search('sess_logged_in\)\(', fo):
-			buf += "int " + fabric_mod_name + "_sess_logged_in(struct se_session *se_sess)\n"
-			buf += "{\n"
-			buf += "	return 0;\n"
-			buf += "}\n\n"
-			bufi += "int " + fabric_mod_name + "_sess_logged_in(struct se_session *);\n"
-
 		if re.search('sess_get_index\)\(', fo):
 			buf += "u32 " + fabric_mod_name + "_sess_get_index(struct se_session *se_sess)\n"
 			buf += "{\n"
@@ -898,19 +874,18 @@ def tcm_mod_dump_fabric_ops(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 			bufi += "int " + fabric_mod_name + "_queue_status(struct se_cmd *);\n"
 
 		if re.search('queue_tm_rsp\)\(', fo):
-			buf += "int " + fabric_mod_name + "_queue_tm_rsp(struct se_cmd *se_cmd)\n"
+			buf += "void " + fabric_mod_name + "_queue_tm_rsp(struct se_cmd *se_cmd)\n"
 			buf += "{\n"
-			buf += "	return 0;\n"
+			buf += "	return;\n"
 			buf += "}\n\n"
-			bufi += "int " + fabric_mod_name + "_queue_tm_rsp(struct se_cmd *);\n"
+			bufi += "void " + fabric_mod_name + "_queue_tm_rsp(struct se_cmd *);\n"
 
-		if re.search('is_state_remove\)\(', fo):
-			buf += "int " + fabric_mod_name + "_is_state_remove(struct se_cmd *se_cmd)\n"
+		if re.search('aborted_task\)\(', fo):
+			buf += "void " + fabric_mod_name + "_aborted_task(struct se_cmd *se_cmd)\n"
 			buf += "{\n"
-			buf += "	return 0;\n"
+			buf += "	return;\n"
 			buf += "}\n\n"
-			bufi += "int " + fabric_mod_name + "_is_state_remove(struct se_cmd *);\n"
-
+			bufi += "void " + fabric_mod_name + "_aborted_task(struct se_cmd *);\n"
 
 	ret = p.write(buf)
 	if ret:
@@ -1018,11 +993,11 @@ def main(modname, proto_ident):
 	tcm_mod_build_kbuild(fabric_mod_dir, fabric_mod_name)
 	tcm_mod_build_kconfig(fabric_mod_dir, fabric_mod_name)
 
-	input = raw_input("Would you like to add " + fabric_mod_name + "to drivers/target/Makefile..? [yes,no]: ")
+	input = raw_input("Would you like to add " + fabric_mod_name + " to drivers/target/Makefile..? [yes,no]: ")
 	if input == "yes" or input == "y":
 		tcm_mod_add_kbuild(tcm_dir, fabric_mod_name)
 
-	input = raw_input("Would you like to add " + fabric_mod_name + "to drivers/target/Kconfig..? [yes,no]: ")
+	input = raw_input("Would you like to add " + fabric_mod_name + " to drivers/target/Kconfig..? [yes,no]: ")
 	if input == "yes" or input == "y":
 		tcm_mod_add_kconfig(tcm_dir, fabric_mod_name)
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 0c2983a62852..9de900572633 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -724,15 +724,15 @@ F:	include/uapi/linux/apm_bios.h
 F:	drivers/char/apm-emulation.c
 
 APPLE BCM5974 MULTITOUCH DRIVER
-M:	Henrik Rydberg <rydberg@euromail.se>
+M:	Henrik Rydberg <rydberg@bitmath.org>
 L:	linux-input@vger.kernel.org
-S:	Maintained
+S:	Odd fixes
 F:	drivers/input/mouse/bcm5974.c
 
 APPLE SMC DRIVER
-M:	Henrik Rydberg <rydberg@euromail.se>
+M:	Henrik Rydberg <rydberg@bitmath.org>
 L:	lm-sensors@lm-sensors.org
-S:	Maintained
+S:	Odd fixes
 F:	drivers/hwmon/applesmc.c
 
 APPLETALK NETWORK LAYER
@@ -2259,6 +2259,7 @@ F:	drivers/gpio/gpio-bt8xx.c
 BTRFS FILE SYSTEM
 M:	Chris Mason <clm@fb.com>
 M:	Josef Bacik <jbacik@fb.com>
+M:	David Sterba <dsterba@suse.cz>
 L:	linux-btrfs@vger.kernel.org
 W:	http://btrfs.wiki.kernel.org/
 Q:	http://patchwork.kernel.org/project/linux-btrfs/list/
@@ -4748,7 +4749,7 @@ S:	Supported
 F:	drivers/scsi/ipr.*
 
 IBM Power Virtual Ethernet Device Driver
-M:	Santiago Leon <santil@linux.vnet.ibm.com>
+M:	Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmveth.*
@@ -4940,10 +4941,10 @@ F:	include/uapi/linux/input.h
 F:	include/linux/input/
 
 INPUT MULTITOUCH (MT) PROTOCOL
-M:	Henrik Rydberg <rydberg@euromail.se>
+M:	Henrik Rydberg <rydberg@bitmath.org>
 L:	linux-input@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rydberg/input-mt.git
-S:	Maintained
+S:	Odd fixes
 F:	Documentation/input/multi-touch-protocol.txt
 F:	drivers/input/input-mt.c
 K:	\b(ABS|SYN)_MT_
@@ -5279,6 +5280,15 @@ W:	www.open-iscsi.org
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/ulp/iser/
 
+ISCSI EXTENSIONS FOR RDMA (ISER) TARGET
+M:	Sagi Grimberg <sagig@mellanox.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master
+L:	linux-rdma@vger.kernel.org
+L:	target-devel@vger.kernel.org
+S:	Supported
+W:	http://www.linux-iscsi.org
+F:	drivers/infiniband/ulp/isert
+
 ISDN SUBSYSTEM
 M:	Karsten Keil <isdn@linux-pingi.de>
 L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
diff --git a/Makefile b/Makefile
index eb4eca56843a..e41a3356abee 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Diseased Newt
 
 # *DOCUMENTATION*
@@ -391,6 +391,7 @@ USERINCLUDE    := \
 # Needed to be compatible with the O= option
 LINUXINCLUDE    := \
 		-I$(srctree)/arch/$(hdr-arch)/include \
+		-Iarch/$(hdr-arch)/include/generated/uapi \
 		-Iarch/$(hdr-arch)/include/generated \
 		$(if $(KBUILD_SRC), -I$(srctree)/include) \
 		-Iinclude \
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index 1e6e5cc1c14c..8c1febd7e3f2 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb.dts
@@ -159,13 +159,28 @@
 	pinctrl-0 = <&pinctrl_enet1>;
 	phy-supply = <&reg_enet_3v3>;
 	phy-mode = "rgmii";
+	phy-handle = <&ethphy1>;
 	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy1: ethernet-phy@0 {
+			reg = <0>;
+		};
+
+		ethphy2: ethernet-phy@1 {
+			reg = <1>;
+		};
+	};
 };
 
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
 	phy-mode = "rgmii";
+	phy-handle = <&ethphy2>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/vf610-twr.dts b/arch/arm/boot/dts/vf610-twr.dts
index a0f762159cb2..f2b64b1b00fa 100644
--- a/arch/arm/boot/dts/vf610-twr.dts
+++ b/arch/arm/boot/dts/vf610-twr.dts
@@ -129,13 +129,28 @@
 
 &fec0 {
 	phy-mode = "rmii";
+	phy-handle = <&ethphy0>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_fec0>;
 	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy0: ethernet-phy@0 {
+			reg = <0>;
+		};
+
+		ethphy1: ethernet-phy@1 {
+			reg = <1>;
+		};
+	};
 };
 
 &fec1 {
 	phy-mode = "rmii";
+	phy-handle = <&ethphy1>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_fec1>;
 	status = "okay";
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 705bb7620673..0c3f5a0dafd3 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -413,6 +413,7 @@
 #define __NR_getrandom			(__NR_SYSCALL_BASE+384)
 #define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 #define __NR_bpf			(__NR_SYSCALL_BASE+386)
+#define __NR_execveat			(__NR_SYSCALL_BASE+387)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index e51833f8cc38..05745eb838c5 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -396,6 +396,7 @@
 		CALL(sys_getrandom)
 /* 385 */	CALL(sys_memfd_create)
 		CALL(sys_bpf)
+		CALL(sys_execveat)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c67cbc..592dda3f21ff 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 59424937e52b..9fe8e241335c 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -220,9 +220,6 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, u
 	static const char units[] = "KMGTPE";
 	u64 prot = val & pg_level[level].mask;
 
-	if (addr < USER_PGTABLES_CEILING)
-		return;
-
 	if (!st->level) {
 		st->level = level;
 		st->current_prot = prot;
@@ -308,15 +305,13 @@ static void walk_pgd(struct seq_file *m)
 	pgd_t *pgd = swapper_pg_dir;
 	struct pg_state st;
 	unsigned long addr;
-	unsigned i, pgdoff = USER_PGTABLES_CEILING / PGDIR_SIZE;
+	unsigned i;
 
 	memset(&st, 0, sizeof(st));
 	st.seq = m;
 	st.marker = address_markers;
 
-	pgd += pgdoff;
-
-	for (i = pgdoff; i < PTRS_PER_PGD; i++, pgd++) {
+	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
 		addr = i * PGDIR_SIZE;
 		if (!pgd_none(*pgd)) {
 			walk_pud(&st, pgd, addr);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 98ad9c79ea0e..2495c8cb47ba 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -658,8 +658,8 @@ static struct section_perm ro_perms[] = {
 		.start  = (unsigned long)_stext,
 		.end    = (unsigned long)__init_begin,
 #ifdef CONFIG_ARM_LPAE
-		.mask   = ~PMD_SECT_RDONLY,
-		.prot   = PMD_SECT_RDONLY,
+		.mask   = ~L_PMD_SECT_RDONLY,
+		.prot   = L_PMD_SECT_RDONLY,
 #else
 		.mask   = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
 		.prot   = PMD_SECT_APX | PMD_SECT_AP_WRITE,
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index cda7c40999b6..4e6ef896c619 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1329,8 +1329,8 @@ static void __init kmap_init(void)
 static void __init map_lowmem(void)
 {
 	struct memblock_region *reg;
-	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	phys_addr_t kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
+	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 
 	/* Map all the lowmem memory banks. */
 	for_each_memblock(memory, reg) {
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index b1fa4e614718..fbe0ca31a99c 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -21,6 +21,7 @@
 
 #include <asm/barrier.h>
 
+#include <linux/bug.h>
 #include <linux/init.h>
 #include <linux/types.h>
 
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index ace70682499b..8e797b2fcc01 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -39,6 +39,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 
+	u32		reg_id_dfr0;
 	u32		reg_id_isar0;
 	u32		reg_id_isar1;
 	u32		reg_id_isar2;
@@ -51,6 +52,10 @@ struct cpuinfo_arm64 {
 	u32		reg_id_mmfr3;
 	u32		reg_id_pfr0;
 	u32		reg_id_pfr1;
+
+	u32		reg_mvfr0;
+	u32		reg_mvfr1;
+	u32		reg_mvfr2;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 8127e45e2637..865a7e28ea2d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -41,6 +41,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+		vcpu->arch.hcr_el2 &= ~HCR_RW;
 }
 
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 286b1bec547c..f9be30ea1cbd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -31,6 +31,7 @@
 
 #include <asm/fpsimd.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
@@ -123,9 +124,6 @@ struct task_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/* Prepare to copy thread state - unlazy all lazy status */
-#define prepare_to_copy(tsk)	do { } while (0)
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 49c9aefd24a5..b780c6c76eec 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		386
+#define __NR_compat_syscalls		387
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 57b641747534..07d435cf2eea 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -147,6 +147,7 @@ static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur)
 	 * If we have AArch32, we care about 32-bit features for compat. These
 	 * registers should be RES0 otherwise.
 	 */
+	diff |= CHECK(id_dfr0, boot, cur, cpu);
 	diff |= CHECK(id_isar0, boot, cur, cpu);
 	diff |= CHECK(id_isar1, boot, cur, cpu);
 	diff |= CHECK(id_isar2, boot, cur, cpu);
@@ -165,6 +166,10 @@ static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur)
 	diff |= CHECK(id_pfr0, boot, cur, cpu);
 	diff |= CHECK(id_pfr1, boot, cur, cpu);
 
+	diff |= CHECK(mvfr0, boot, cur, cpu);
+	diff |= CHECK(mvfr1, boot, cur, cpu);
+	diff |= CHECK(mvfr2, boot, cur, cpu);
+
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
@@ -189,6 +194,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 
+	info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
 	info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
 	info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
 	info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
@@ -202,6 +208,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
 	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
 
+	info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
+	info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
+	info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
+
 	cpuinfo_detect_icache_policy(info);
 
 	check_local_cpu_errata();
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 6fac253bc783..2bb4347d0edf 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -326,6 +326,7 @@ void __init efi_idmap_init(void)
 
 	/* boot time idmap_pg_dir is incomplete, so fill in missing parts */
 	efi_setup_idmap();
+	early_memunmap(memmap.map, memmap.map_end - memmap.map);
 }
 
 static int __init remap_region(efi_memory_desc_t *md, void **new)
@@ -380,7 +381,6 @@ static int __init arm64_enter_virtual_mode(void)
 	}
 
 	mapsize = memmap.map_end - memmap.map;
-	early_memunmap(memmap.map, mapsize);
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index fd027b101de5..9b6f71db2709 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -25,6 +25,7 @@
 #include <linux/mm.h>
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
+#include <asm/alternative.h>
 #include <asm/insn.h>
 #include <asm/sections.h>
 
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad705587..3f62b35fb6f1 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index b80991166754..20fe2932ad0c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -402,6 +402,7 @@ void __init setup_arch(char **cmdline_p)
 	request_standard_resources();
 
 	efi_idmap_init();
+	early_ioremap_reset();
 
 	unflatten_device_tree();
 
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 4f93c67e63de..14944e5b28da 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
 #include <asm/cputype.h>
+#include <asm/io.h>
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index fbe909fb0a1a..c3ca89c27c6b 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -1014,6 +1014,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	 * Instead, we invalidate Stage-2 for this IPA, and the
 	 * whole of Stage-1. Weep...
 	 */
+	lsr	x1, x1, #12
 	tlbi	ipas2e1is, x1
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 70a7816535cd..0b4326578985 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			if (!cpu_has_32bit_el1())
 				return -EINVAL;
 			cpu_reset = &default_regs_reset32;
-			vcpu->arch.hcr_el2 &= ~HCR_RW;
 		} else {
 			cpu_reset = &default_regs_reset;
 		}
diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c
index 6f4bac969bf7..23eada79439c 100644
--- a/arch/blackfin/mach-bf533/boards/stamp.c
+++ b/arch/blackfin/mach-bf533/boards/stamp.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 615ef81def49..e795cb848154 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -893,13 +893,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 	ia64_cpu_to_sapicid[cpu] = -1;
 	set_cpu_present(cpu, false);
@@ -910,8 +910,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 #ifdef CONFIG_ACPI_NUMA
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 32040ace00ea..afbe07907c10 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -231,7 +231,7 @@ failed:
 struct dbfs_d2fc_hdr {
 	u64	len;		/* Length of d2fc buffer without header */
 	u16	version;	/* Version of header */
-	char	tod_ext[16];	/* TOD clock for d2fc */
+	char	tod_ext[STORE_CLOCK_EXT_SIZE]; /* TOD clock for d2fc */
 	u64	count;		/* Number of VM guests in d2fc buffer */
 	char	reserved[30];
 } __attribute__ ((packed));
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index 37b9091ab8c0..16aa0c779e07 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -36,7 +36,7 @@ static inline notrace void __arch_local_irq_ssm(unsigned long flags)
 
 static inline notrace unsigned long arch_local_save_flags(void)
 {
-	return __arch_local_irq_stosm(0x00);
+	return __arch_local_irq_stnsm(0xff);
 }
 
 static inline notrace unsigned long arch_local_irq_save(void)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 8beee1cceba4..98eb2a579223 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -67,20 +67,22 @@ static inline void local_tick_enable(unsigned long long comp)
 	set_clock_comparator(S390_lowcore.clock_comparator);
 }
 
-#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
+#define CLOCK_TICK_RATE		1193180 /* Underlying HZ */
+#define STORE_CLOCK_EXT_SIZE	16	/* stcke writes 16 bytes */
 
 typedef unsigned long long cycles_t;
 
-static inline void get_tod_clock_ext(char clk[16])
+static inline void get_tod_clock_ext(char *clk)
 {
-	typedef struct { char _[sizeof(clk)]; } addrtype;
+	typedef struct { char _[STORE_CLOCK_EXT_SIZE]; } addrtype;
 
 	asm volatile("stcke %0" : "=Q" (*(addrtype *) clk) : : "cc");
 }
 
 static inline unsigned long long get_tod_clock(void)
 {
-	unsigned char clk[16];
+	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+
 	get_tod_clock_ext(clk);
 	return *((unsigned long long *)&clk[1]);
 }
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 2b446cf0cc65..67878af257a0 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -289,7 +289,8 @@
 #define __NR_bpf		351
 #define __NR_s390_pci_mmio_write	352
 #define __NR_s390_pci_mmio_read		353
-#define NR_syscalls 354
+#define __NR_execveat		354
+#define NR_syscalls 355
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index a2987243bc76..939ec474b1dd 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -362,3 +362,4 @@ SYSCALL(sys_memfd_create,sys_memfd_create,compat_sys_memfd_create) /* 350 */
 SYSCALL(sys_bpf,sys_bpf,compat_sys_bpf)
 SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write)
 SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read)
+SYSCALL(sys_execveat,sys_execveat,compat_sys_execveat)
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index f6b3cd056ec2..cc7328080b60 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -48,6 +48,30 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *tsk)
 	return false;
 }
 
+static int check_per_event(unsigned short cause, unsigned long control,
+			   struct pt_regs *regs)
+{
+	if (!(regs->psw.mask & PSW_MASK_PER))
+		return 0;
+	/* user space single step */
+	if (control == 0)
+		return 1;
+	/* over indication for storage alteration */
+	if ((control & 0x20200000) && (cause & 0x2000))
+		return 1;
+	if (cause & 0x8000) {
+		/* all branches */
+		if ((control & 0x80800000) == 0x80000000)
+			return 1;
+		/* branch into selected range */
+		if (((control & 0x80800000) == 0x80800000) &&
+		    regs->psw.addr >= current->thread.per_user.start &&
+		    regs->psw.addr <= current->thread.per_user.end)
+			return 1;
+	}
+	return 0;
+}
+
 int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	int fixup = probe_get_fixup_type(auprobe->insn);
@@ -71,9 +95,13 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		if (regs->psw.addr - utask->xol_vaddr == ilen)
 			regs->psw.addr = utask->vaddr + ilen;
 	}
-	/* If per tracing was active generate trap */
-	if (regs->psw.mask & PSW_MASK_PER)
-		do_per_trap(regs);
+	if (check_per_event(current->thread.per_event.cause,
+			    current->thread.per_user.control, regs)) {
+		/* fix per address */
+		current->thread.per_event.address = utask->vaddr;
+		/* trigger per event */
+		set_pt_regs_flag(regs, PIF_PER_TRAP);
+	}
 	return 0;
 }
 
@@ -106,6 +134,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	clear_thread_flag(TIF_UPROBE_SINGLESTEP);
 	regs->int_code = auprobe->saved_int_code;
 	regs->psw.addr = current->utask->vaddr;
+	current->thread.per_event.address = current->utask->vaddr;
 }
 
 unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
@@ -146,17 +175,20 @@ static void adjust_psw_addr(psw_t *psw, unsigned long len)
 	__rc;						\
 })
 
-#define emu_store_ril(ptr, input)			\
+#define emu_store_ril(regs, ptr, input)			\
 ({							\
 	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(ptr) __ptr = (ptr);			\
 	int __rc = 0;					\
 							\
 	if (!test_facility(34))				\
 		__rc = EMU_ILLEGAL_OP;			\
-	else if ((u64 __force)ptr & mask)		\
+	else if ((u64 __force)__ptr & mask)		\
 		__rc = EMU_SPECIFICATION;		\
-	else if (put_user(*(input), ptr))		\
+	else if (put_user(*(input), __ptr))		\
 		__rc = EMU_ADDRESSING;			\
+	if (__rc == 0)					\
+		sim_stor_event(regs, __ptr, mask + 1);	\
 	__rc;						\
 })
 
@@ -198,6 +230,25 @@ union split_register {
 };
 
 /*
+ * If user per registers are setup to trace storage alterations and an
+ * emulated store took place on a fitting address a user trap is generated.
+ */
+static void sim_stor_event(struct pt_regs *regs, void *addr, int len)
+{
+	if (!(regs->psw.mask & PSW_MASK_PER))
+		return;
+	if (!(current->thread.per_user.control & PER_EVENT_STORE))
+		return;
+	if ((void *)current->thread.per_user.start > (addr + len))
+		return;
+	if ((void *)current->thread.per_user.end < addr)
+		return;
+	current->thread.per_event.address = regs->psw.addr;
+	current->thread.per_event.cause = PER_EVENT_STORE >> 16;
+	set_pt_regs_flag(regs, PIF_PER_TRAP);
+}
+
+/*
  * pc relative instructions are emulated, since parameters may not be
  * accessible from the xol area due to range limitations.
  */
@@ -249,13 +300,13 @@ static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
 			rc = emu_load_ril((u32 __user *)uptr, &rx->u64);
 			break;
 		case 0x07: /* sthrl */
-			rc = emu_store_ril((u16 __user *)uptr, &rx->u16[3]);
+			rc = emu_store_ril(regs, (u16 __user *)uptr, &rx->u16[3]);
 			break;
 		case 0x0b: /* stgrl */
-			rc = emu_store_ril((u64 __user *)uptr, &rx->u64);
+			rc = emu_store_ril(regs, (u64 __user *)uptr, &rx->u64);
 			break;
 		case 0x0f: /* strl */
-			rc = emu_store_ril((u32 __user *)uptr, &rx->u32[1]);
+			rc = emu_store_ril(regs, (u32 __user *)uptr, &rx->u32[1]);
 			break;
 		}
 		break;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 7f0089d9a4aa..e34122e539a1 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -128,8 +128,6 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, system;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index be99357d238c..3cf8cc03fff6 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -322,11 +322,12 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 static unsigned long __gmap_segment_gaddr(unsigned long *entry)
 {
 	struct page *page;
-	unsigned long offset;
+	unsigned long offset, mask;
 
 	offset = (unsigned long) entry / sizeof(unsigned long);
 	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
-	page = pmd_to_page((pmd_t *) entry);
+	mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
+	page = virt_to_page((void *)((unsigned long) entry & mask));
 	return page->index + offset;
 }
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index c52ac77408ca..524496d47ef5 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -431,8 +431,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_DISP(0x88500000, K);
 		break;
 	case BPF_ALU | BPF_NEG: /* A = -A */
-		/* lnr %r5,%r5 */
-		EMIT2(0x1155);
+		/* lcr %r5,%r5 */
+		EMIT2(0x1355);
 		break;
 	case BPF_JMP | BPF_JA: /* ip += K */
 		offset = addrs[i + K] + jit->start - jit->prg;
@@ -502,8 +502,8 @@ branch:		if (filter->jt == filter->jf) {
 xbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
 			jit->seen |= SEEN_XREG;
-			/* cr %r5,%r12 */
-			EMIT2(0x195c);
+			/* clr %r5,%r12 */
+			EMIT2(0x155c);
 		}
 		goto branch;
 	case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 5b016e2498f3..3db07f30636f 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -51,6 +51,7 @@ targets += cpustr.h
 $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 	$(call if_changed,cpustr)
 endif
+clean-files += cpustr.h
 
 # ---------------------------------------------------------------------------
 
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index fd0f848938cc..5a4a089e8b1f 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -26,7 +26,6 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
-obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
@@ -46,6 +45,7 @@ endif
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 2df2a0298f5a..a916c4a61165 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -208,7 +208,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	3*16(p_keys), xkeyA
+			vmovdqa	3*16(p_keys), xkey4
 		.endif
 	.else
 		vmovdqa	3*16(p_keys), xkeyA
@@ -224,7 +224,7 @@ ddq_add_8:
 	add	$(16*by), p_in
 
 	.if (klen == KEY_128)
-		vmovdqa	4*16(p_keys), xkey4
+		vmovdqa	4*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	4*16(p_keys), xkey4
@@ -234,7 +234,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 3 */
+		/* key 3 */
+		.if (klen == KEY_128)
+			vaesenc	xkey4, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -243,13 +248,18 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey4, var_xdata, var_xdata		/* key 4 */
+		/* key 4 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey4, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	6*16(p_keys), xkeyB
+			vmovdqa	6*16(p_keys), xkey8
 		.endif
 	.else
 		vmovdqa	6*16(p_keys), xkeyB
@@ -267,12 +277,17 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyB, var_xdata, var_xdata		/* key 6 */
+		/* key 6 */
+		.if (klen == KEY_128)
+			vaesenc	xkey8, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
-		vmovdqa	8*16(p_keys), xkey8
+		vmovdqa	8*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	8*16(p_keys), xkey8
@@ -288,7 +303,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	9*16(p_keys), xkeyA
+			vmovdqa	9*16(p_keys), xkey12
 		.endif
 	.else
 		vmovdqa	9*16(p_keys), xkeyA
@@ -297,7 +312,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey8, var_xdata, var_xdata		/* key 8 */
+		/* key 8 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey8, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -306,7 +326,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 9 */
+		/* key 9 */
+		.if (klen == KEY_128)
+			vaesenc	xkey12, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -412,7 +437,6 @@ ddq_add_8:
 /* main body of aes ctr load */
 
 .macro do_aes_ctrmain key_len
-
 	cmp	$16, num_bytes
 	jb	.Ldo_return2\key_len
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index e7e9682a33e9..f556c4843aa1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -80,9 +80,11 @@ static inline unsigned int __getcpu(void)
 
 	/*
 	 * Load per CPU data from GDT.  LSL is faster than RDTSCP and
-	 * works on all CPUs.
+	 * works on all CPUs.  This is volatile so that it orders
+	 * correctly wrt barrier() and to keep gcc from cleverly
+	 * hoisting it out of the calling function.
 	 */
-	asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+	asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 
 	return p;
 }
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 4433a4be8171..d1626364a28a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -750,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 #ifdef CONFIG_ACPI_NUMA
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
@@ -768,8 +768,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index e27b49d7c922..80091ae54c2b 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -66,3 +66,4 @@ targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
 	$(call if_changed,mkcapflags)
 endif
+clean-files += capflags.c
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index e2b22df964cd..36d99a337b49 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -28,7 +28,7 @@ function dump_array()
 		# If the /* comment */ starts with a quote string, grab that.
 		VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
 		[ -z "$VALUE" ] && VALUE="\"$NAME\""
-		[ "$VALUE" == '""' ] && continue
+		[ "$VALUE" = '""' ] && continue
 
 		# Name is uppercase, VALUE is all lowercase
 		VALUE="$(echo "$VALUE" | tr A-Z a-z)"
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 18eb78bbdd10..863d9b02563e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	2
+#define UNCORE_EXTRA_PCI_DEV_MAX	3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX		8
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 745b158e9a65..21af6149edf2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -891,6 +891,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2026,6 +2027,17 @@ void hswep_uncore_cpu_init(void)
 {
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+	/* Detect 6-8 core systems with only two SBOXes */
+	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+		u32 capid4;
+
+		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+				      0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			hswep_uncore_sbox.num_boxes = 2;
+	}
+
 	uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2287,6 +2299,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
 						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..781861cc5ee8 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	struct pt_regs *user_regs = task_pt_regs(current);
+
+	/*
+	 * If we're in an NMI that interrupted task_pt_regs setup, then
+	 * we can't sample user regs at all.  This check isn't really
+	 * sufficient, though, as we could be in an NMI inside an interrupt
+	 * that happened during task_pt_regs setup.
+	 */
+	if (regs->sp > (unsigned long)&user_regs->r11 &&
+	    regs->sp <= (unsigned long)(user_regs + 1)) {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
+		return;
+	}
+
+	/*
+	 * RIP, flags, and the argument registers are usually saved.
+	 * orig_ax is probably okay, too.
+	 */
+	regs_user_copy->ip = user_regs->ip;
+	regs_user_copy->cx = user_regs->cx;
+	regs_user_copy->dx = user_regs->dx;
+	regs_user_copy->si = user_regs->si;
+	regs_user_copy->di = user_regs->di;
+	regs_user_copy->r8 = user_regs->r8;
+	regs_user_copy->r9 = user_regs->r9;
+	regs_user_copy->r10 = user_regs->r10;
+	regs_user_copy->r11 = user_regs->r11;
+	regs_user_copy->orig_ax = user_regs->orig_ax;
+	regs_user_copy->flags = user_regs->flags;
+
+	/*
+	 * Don't even try to report the "rest" regs.
+	 */
+	regs_user_copy->bx = -1;
+	regs_user_copy->bp = -1;
+	regs_user_copy->r12 = -1;
+	regs_user_copy->r13 = -1;
+	regs_user_copy->r14 = -1;
+	regs_user_copy->r15 = -1;
+
+	/*
+	 * For this to be at all useful, we need a reasonable guess for
+	 * sp and the ABI.  Be careful: we're in NMI context, and we're
+	 * considering current to be the current task, so we should
+	 * be careful not to look at any other percpu variables that might
+	 * change during context switches.
+	 */
+	if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+	    task_thread_info(current)->status & TS_COMPAT) {
+		/* Easy case: we're in a compat syscall. */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	} else if (user_regs->orig_ax != -1) {
+		/*
+		 * We're probably in a 64-bit syscall.
+		 * Warning: this code is severely racy.  At least it's better
+		 * than just blindly copying user_regs.
+		 */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
+		regs_user_copy->sp = this_cpu_read(old_rsp);
+		regs_user_copy->cs = __USER_CS;
+		regs_user_copy->ss = __USER_DS;
+		regs_user_copy->cx = -1;  /* usually contains garbage */
+	} else {
+		/* We're probably in an interrupt or exception. */
+		regs_user->abi = user_64bit_mode(user_regs) ?
+			PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	}
+
+	regs_user->regs = regs_user_copy;
+}
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 2480978b31cc..1313ae6b478b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -28,7 +28,7 @@
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr)
+	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
 	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a97ee0801475..08a7d313538a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -438,20 +438,20 @@ static unsigned long __init init_range_memory_mapping(
 static unsigned long __init get_new_step_size(unsigned long step_size)
 {
 	/*
-	 * Explain why we shift by 5 and why we don't have to worry about
-	 * 'step_size << 5' overflowing:
-	 *
-	 * initial mapped size is PMD_SIZE (2M).
+	 * Initial mapped size is PMD_SIZE (2M).
 	 * We can not set step_size to be PUD_SIZE (1G) yet.
 	 * In worse case, when we cross the 1G boundary, and
 	 * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
-	 * to map 1G range with PTE. Use 5 as shift for now.
+	 * to map 1G range with PTE. Hence we use one less than the
+	 * difference of page table level shifts.
 	 *
-	 * Don't need to worry about overflow, on 32bit, when step_size
-	 * is 0, round_down() returns 0 for start, and that turns it
-	 * into 0x100000000ULL.
+	 * Don't need to worry about overflow in the top-down case, on 32bit,
+	 * when step_size is 0, round_down() returns 0 for start, and that
+	 * turns it into 0x100000000ULL.
+	 * In the bottom-up case, round_up(x, 0) returns 0 though too, which
+	 * needs to be taken into consideration by the code below.
 	 */
-	return step_size << 5;
+	return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
 }
 
 /**
@@ -471,7 +471,6 @@ static void __init memory_map_top_down(unsigned long map_start,
 	unsigned long step_size;
 	unsigned long addr;
 	unsigned long mapped_ram_size = 0;
-	unsigned long new_mapped_ram_size;
 
 	/* xen has big range in reserved near end of ram, skip it at first.*/
 	addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
@@ -496,14 +495,12 @@ static void __init memory_map_top_down(unsigned long map_start,
 				start = map_start;
 		} else
 			start = map_start;
-		new_mapped_ram_size = init_range_memory_mapping(start,
+		mapped_ram_size += init_range_memory_mapping(start,
 							last_start);
 		last_start = start;
 		min_pfn_mapped = last_start >> PAGE_SHIFT;
-		/* only increase step_size after big range get mapped */
-		if (new_mapped_ram_size > mapped_ram_size)
+		if (mapped_ram_size >= step_size)
 			step_size = get_new_step_size(step_size);
-		mapped_ram_size += new_mapped_ram_size;
 	}
 
 	if (real_end < map_end)
@@ -524,7 +521,7 @@ static void __init memory_map_top_down(unsigned long map_start,
 static void __init memory_map_bottom_up(unsigned long map_start,
 					unsigned long map_end)
 {
-	unsigned long next, new_mapped_ram_size, start;
+	unsigned long next, start;
 	unsigned long mapped_ram_size = 0;
 	/* step_size need to be small so pgt_buf from BRK could cover it */
 	unsigned long step_size = PMD_SIZE;
@@ -539,19 +536,19 @@ static void __init memory_map_bottom_up(unsigned long map_start,
 	 * for page table.
 	 */
 	while (start < map_end) {
-		if (map_end - start > step_size) {
+		if (step_size && map_end - start > step_size) {
 			next = round_up(start + 1, step_size);
 			if (next > map_end)
 				next = map_end;
-		} else
+		} else {
 			next = map_end;
+		}
 
-		new_mapped_ram_size = init_range_memory_mapping(start, next);
+		mapped_ram_size += init_range_memory_mapping(start, next);
 		start = next;
 
-		if (new_mapped_ram_size > mapped_ram_size)
+		if (mapped_ram_size >= step_size)
 			step_size = get_new_step_size(step_size);
-		mapped_ram_size += new_mapped_ram_size;
 	}
 }
 
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 009495b9ab4b..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -41,12 +41,17 @@ void __init init_vdso_image(const struct vdso_image *image)
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits.
-
-   Only used for the 64-bit and x32 vdsos. */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 #ifdef CONFIG_X86_32
@@ -54,22 +59,30 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #else
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 6bf3a13e3e0f..78a881b7fc41 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -40,6 +40,7 @@
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/interface/memory.h>
+#include <xen/interface/nmi.h>
 #include <xen/interface/xen-mca.h>
 #include <xen/features.h>
 #include <xen/page.h>
@@ -66,6 +67,7 @@
 #include <asm/reboot.h>
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
+#include <asm/mach_traps.h>
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/pat.h>
@@ -1351,6 +1353,21 @@ static const struct machine_ops xen_machine_ops __initconst = {
 	.emergency_restart = xen_emergency_restart,
 };
 
+static unsigned char xen_get_nmi_reason(void)
+{
+	unsigned char reason = 0;
+
+	/* Construct a value which looks like it came from port 0x61. */
+	if (test_bit(_XEN_NMIREASON_io_error,
+		     &HYPERVISOR_shared_info->arch.nmi_reason))
+		reason |= NMI_REASON_IOCHK;
+	if (test_bit(_XEN_NMIREASON_pci_serr,
+		     &HYPERVISOR_shared_info->arch.nmi_reason))
+		reason |= NMI_REASON_SERR;
+
+	return reason;
+}
+
 static void __init xen_boot_params_init_edd(void)
 {
 #if IS_ENABLED(CONFIG_EDD)
@@ -1535,9 +1552,12 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
 	pv_apic_ops = xen_apic_ops;
-	if (!xen_pvh_domain())
+	if (!xen_pvh_domain()) {
 		pv_cpu_ops = xen_cpu_ops;
 
+		x86_platform.get_nmi_reason = xen_get_nmi_reason;
+	}
+
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
 	else
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index edbc7a63fd73..70fb5075c901 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -167,10 +167,13 @@ static void * __ref alloc_p2m_page(void)
 	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
 }
 
-/* Only to be called in case of a race for a page just allocated! */
-static void free_p2m_page(void *p)
+static void __ref free_p2m_page(void *p)
 {
-	BUG_ON(!slab_is_available());
+	if (unlikely(!slab_is_available())) {
+		free_bootmem((unsigned long)p, PAGE_SIZE);
+		return;
+	}
+
 	free_page((unsigned long)p);
 }
 
@@ -375,7 +378,7 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m)
 			p2m_missing_pte : p2m_identity_pte;
 		for (i = 0; i < PMDS_PER_MID_PAGE; i++) {
 			pmdp = populate_extra_pmd(
-				(unsigned long)(p2m + pfn + i * PTRS_PER_PTE));
+				(unsigned long)(p2m + pfn) + i * PMD_SIZE);
 			set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE));
 		}
 	}
@@ -436,10 +439,9 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine);
  * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual
  * pmd. In case of PAE/x86-32 there are multiple pmds to allocate!
  */
-static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
+static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
 {
 	pte_t *ptechk;
-	pte_t *pteret = ptep;
 	pte_t *pte_newpg[PMDS_PER_MID_PAGE];
 	pmd_t *pmdp;
 	unsigned int level;
@@ -473,8 +475,6 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
 		if (ptechk == pte_pg) {
 			set_pmd(pmdp,
 				__pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE));
-			if (vaddr == (addr & ~(PMD_SIZE - 1)))
-				pteret = pte_offset_kernel(pmdp, addr);
 			pte_newpg[i] = NULL;
 		}
 
@@ -488,7 +488,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
 		vaddr += PMD_SIZE;
 	}
 
-	return pteret;
+	return lookup_address(addr, &level);
 }
 
 /*
@@ -517,7 +517,7 @@ static bool alloc_p2m(unsigned long pfn)
 
 	if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) {
 		/* PMD level is missing, allocate a new one */
-		ptep = alloc_p2m_pmd(addr, ptep, pte_pg);
+		ptep = alloc_p2m_pmd(addr, pte_pg);
 		if (!ptep)
 			return false;
 	}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index dfd77dec8e2b..865e56cea7a0 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -140,7 +140,7 @@ static void __init xen_del_extra_mem(u64 start, u64 size)
 unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
 {
 	int i;
-	unsigned long addr = PFN_PHYS(pfn);
+	phys_addr_t addr = PFN_PHYS(pfn);
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
 		if (addr >= xen_extra_mem[i].start &&
@@ -160,6 +160,8 @@ void __init xen_inv_extra_mem(void)
 	int i;
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		if (!xen_extra_mem[i].size)
+			continue;
 		pfn_s = PFN_DOWN(xen_extra_mem[i].start);
 		pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size);
 		for (pfn = pfn_s; pfn < pfn_e; pfn++)
@@ -229,15 +231,14 @@ static int __init xen_free_mfn(unsigned long mfn)
  * as a fallback if the remapping fails.
  */
 static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
-	unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity,
-	unsigned long *released)
+	unsigned long end_pfn, unsigned long nr_pages, unsigned long *released)
 {
-	unsigned long len = 0;
 	unsigned long pfn, end;
 	int ret;
 
 	WARN_ON(start_pfn > end_pfn);
 
+	/* Release pages first. */
 	end = min(end_pfn, nr_pages);
 	for (pfn = start_pfn; pfn < end; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
@@ -250,16 +251,14 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
 		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
 
 		if (ret == 1) {
+			(*released)++;
 			if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY))
 				break;
-			len++;
 		} else
 			break;
 	}
 
-	/* Need to release pages first */
-	*released += len;
-	*identity += set_phys_range_identity(start_pfn, end_pfn);
+	set_phys_range_identity(start_pfn, end_pfn);
 }
 
 /*
@@ -287,7 +286,7 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
 	}
 
 	/* Update kernel mapping, but not for highmem. */
-	if ((pfn << PAGE_SHIFT) >= __pa(high_memory))
+	if (pfn >= PFN_UP(__pa(high_memory - 1)))
 		return;
 
 	if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT),
@@ -318,7 +317,6 @@ static void __init xen_do_set_identity_and_remap_chunk(
 	unsigned long ident_pfn_iter, remap_pfn_iter;
 	unsigned long ident_end_pfn = start_pfn + size;
 	unsigned long left = size;
-	unsigned long ident_cnt = 0;
 	unsigned int i, chunk;
 
 	WARN_ON(size == 0);
@@ -347,8 +345,7 @@ static void __init xen_do_set_identity_and_remap_chunk(
 		xen_remap_mfn = mfn;
 
 		/* Set identity map */
-		ident_cnt += set_phys_range_identity(ident_pfn_iter,
-			ident_pfn_iter + chunk);
+		set_phys_range_identity(ident_pfn_iter, ident_pfn_iter + chunk);
 
 		left -= chunk;
 	}
@@ -371,7 +368,7 @@ static void __init xen_do_set_identity_and_remap_chunk(
 static unsigned long __init xen_set_identity_and_remap_chunk(
         const struct e820entry *list, size_t map_size, unsigned long start_pfn,
 	unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn,
-	unsigned long *identity, unsigned long *released)
+	unsigned long *released, unsigned long *remapped)
 {
 	unsigned long pfn;
 	unsigned long i = 0;
@@ -386,8 +383,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		/* Do not remap pages beyond the current allocation */
 		if (cur_pfn >= nr_pages) {
 			/* Identity map remaining pages */
-			*identity += set_phys_range_identity(cur_pfn,
-				cur_pfn + size);
+			set_phys_range_identity(cur_pfn, cur_pfn + size);
 			break;
 		}
 		if (cur_pfn + size > nr_pages)
@@ -398,7 +394,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		if (!remap_range_size) {
 			pr_warning("Unable to find available pfn range, not remapping identity pages\n");
 			xen_set_identity_and_release_chunk(cur_pfn,
-				cur_pfn + left, nr_pages, identity, released);
+				cur_pfn + left, nr_pages, released);
 			break;
 		}
 		/* Adjust size to fit in current e820 RAM region */
@@ -410,7 +406,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		/* Update variables to reflect new mappings. */
 		i += size;
 		remap_pfn += size;
-		*identity += size;
+		*remapped += size;
 	}
 
 	/*
@@ -427,13 +423,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 
 static void __init xen_set_identity_and_remap(
 	const struct e820entry *list, size_t map_size, unsigned long nr_pages,
-	unsigned long *released)
+	unsigned long *released, unsigned long *remapped)
 {
 	phys_addr_t start = 0;
-	unsigned long identity = 0;
 	unsigned long last_pfn = nr_pages;
 	const struct e820entry *entry;
 	unsigned long num_released = 0;
+	unsigned long num_remapped = 0;
 	int i;
 
 	/*
@@ -460,14 +456,14 @@ static void __init xen_set_identity_and_remap(
 				last_pfn = xen_set_identity_and_remap_chunk(
 						list, map_size, start_pfn,
 						end_pfn, nr_pages, last_pfn,
-						&identity, &num_released);
+						&num_released, &num_remapped);
 			start = end;
 		}
 	}
 
 	*released = num_released;
+	*remapped = num_remapped;
 
-	pr_info("Set %ld page(s) to 1-1 mapping\n", identity);
 	pr_info("Released %ld page(s)\n", num_released);
 }
 
@@ -586,6 +582,7 @@ char * __init xen_memory_setup(void)
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
 	unsigned long extra_pages = 0;
+	unsigned long remapped_pages;
 	int i;
 	int op;
 
@@ -635,9 +632,10 @@ char * __init xen_memory_setup(void)
 	 * underlying RAM.
 	 */
 	xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
-				   &xen_released_pages);
+				   &xen_released_pages, &remapped_pages);
 
 	extra_pages += xen_released_pages;
+	extra_pages += remapped_pages;
 
 	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index f473d268d387..69087341d9ae 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -391,7 +391,7 @@ static const struct clock_event_device *xen_clockevent =
 
 struct xen_clock_event_device {
 	struct clock_event_device evt;
-	char *name;
+	char name[16];
 };
 static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.irq = -1 };
 
@@ -420,46 +420,38 @@ void xen_teardown_timer(int cpu)
 	if (evt->irq >= 0) {
 		unbind_from_irqhandler(evt->irq, NULL);
 		evt->irq = -1;
-		kfree(per_cpu(xen_clock_events, cpu).name);
-		per_cpu(xen_clock_events, cpu).name = NULL;
 	}
 }
 
 void xen_setup_timer(int cpu)
 {
-	char *name;
-	struct clock_event_device *evt;
+	struct xen_clock_event_device *xevt = &per_cpu(xen_clock_events, cpu);
+	struct clock_event_device *evt = &xevt->evt;
 	int irq;
 
-	evt = &per_cpu(xen_clock_events, cpu).evt;
 	WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu);
 	if (evt->irq >= 0)
 		xen_teardown_timer(cpu);
 
 	printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu);
 
-	name = kasprintf(GFP_KERNEL, "timer%d", cpu);
-	if (!name)
-		name = "<timer kasprintf failed>";
+	snprintf(xevt->name, sizeof(xevt->name), "timer%d", cpu);
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
 				      IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
 				      IRQF_FORCE_RESUME|IRQF_EARLY_RESUME,
-				      name, NULL);
+				      xevt->name, NULL);
 	(void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX);
 
 	memcpy(evt, xen_clockevent, sizeof(*evt));
 
 	evt->cpumask = cpumask_of(cpu);
 	evt->irq = irq;
-	per_cpu(xen_clock_events, cpu).name = name;
 }
 
 
 void xen_setup_cpu_clockevents(void)
 {
-	BUG_ON(preemptible());
-
 	clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt));
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 30f6153a40c2..3ad405571dcc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -473,6 +473,25 @@ void blk_queue_bypass_end(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
 
+void blk_set_queue_dying(struct request_queue *q)
+{
+	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+
+	if (q->mq_ops)
+		blk_mq_wake_waiters(q);
+	else {
+		struct request_list *rl;
+
+		blk_queue_for_each_rl(rl, q) {
+			if (rl->rq_pool) {
+				wake_up(&rl->wait[BLK_RW_SYNC]);
+				wake_up(&rl->wait[BLK_RW_ASYNC]);
+			}
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(blk_set_queue_dying);
+
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -486,7 +505,7 @@ void blk_cleanup_queue(struct request_queue *q)
 
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
 	mutex_lock(&q->sysfs_lock);
-	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+	blk_set_queue_dying(q);
 	spin_lock_irq(lock);
 
 	/*
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 32e8dbb9ad1c..60c9d4a93fe4 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -68,9 +68,9 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 }
 
 /*
- * Wakeup all potentially sleeping on normal (non-reserved) tags
+ * Wakeup all potentially sleeping on tags
  */
-static void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags)
+void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 {
 	struct blk_mq_bitmap_tags *bt;
 	int i, wake_index;
@@ -85,6 +85,12 @@ static void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags)
 
 		wake_index = bt_index_inc(wake_index);
 	}
+
+	if (include_reserve) {
+		bt = &tags->breserved_tags;
+		if (waitqueue_active(&bt->bs[0].wait))
+			wake_up(&bt->bs[0].wait);
+	}
 }
 
 /*
@@ -100,7 +106,7 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 
 	atomic_dec(&tags->active_queues);
 
-	blk_mq_tag_wakeup_all(tags);
+	blk_mq_tag_wakeup_all(tags, false);
 }
 
 /*
@@ -584,7 +590,7 @@ int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int tdepth)
 	 * static and should never need resizing.
 	 */
 	bt_update_count(&tags->bitmap_tags, tdepth);
-	blk_mq_tag_wakeup_all(tags);
+	blk_mq_tag_wakeup_all(tags, false);
 	return 0;
 }
 
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 6206ed17ef76..a6fa0fc9d41a 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -54,6 +54,7 @@ extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
 extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
+extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 
 enum {
 	BLK_MQ_TAG_CACHE_MIN	= 1,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index da1ab5641227..2f95747c287e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -107,7 +107,7 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref)
 	wake_up_all(&q->mq_freeze_wq);
 }
 
-static void blk_mq_freeze_queue_start(struct request_queue *q)
+void blk_mq_freeze_queue_start(struct request_queue *q)
 {
 	bool freeze;
 
@@ -120,6 +120,7 @@ static void blk_mq_freeze_queue_start(struct request_queue *q)
 		blk_mq_run_queues(q, false);
 	}
 }
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
 
 static void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
@@ -136,7 +137,7 @@ void blk_mq_freeze_queue(struct request_queue *q)
 	blk_mq_freeze_queue_wait(q);
 }
 
-static void blk_mq_unfreeze_queue(struct request_queue *q)
+void blk_mq_unfreeze_queue(struct request_queue *q)
 {
 	bool wake;
 
@@ -149,6 +150,24 @@ static void blk_mq_unfreeze_queue(struct request_queue *q)
 		wake_up_all(&q->mq_freeze_wq);
 	}
 }
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+
+void blk_mq_wake_waiters(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		if (blk_mq_hw_queue_mapped(hctx))
+			blk_mq_tag_wakeup_all(hctx->tags, true);
+
+	/*
+	 * If we are called because the queue has now been marked as
+	 * dying, we need to ensure that processes currently waiting on
+	 * the queue are notified as well.
+	 */
+	wake_up_all(&q->mq_freeze_wq);
+}
 
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 {
@@ -258,8 +277,10 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 		ctx = alloc_data.ctx;
 	}
 	blk_mq_put_ctx(ctx);
-	if (!rq)
+	if (!rq) {
+		blk_mq_queue_exit(q);
 		return ERR_PTR(-EWOULDBLOCK);
+	}
 	return rq;
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
@@ -383,6 +404,12 @@ void blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
+int blk_mq_request_started(struct request *rq)
+{
+	return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+}
+EXPORT_SYMBOL_GPL(blk_mq_request_started);
+
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -500,12 +527,38 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head)
 }
 EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
 
+void blk_mq_cancel_requeue_work(struct request_queue *q)
+{
+	cancel_work_sync(&q->requeue_work);
+}
+EXPORT_SYMBOL_GPL(blk_mq_cancel_requeue_work);
+
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
 	kblockd_schedule_work(&q->requeue_work);
 }
 EXPORT_SYMBOL(blk_mq_kick_requeue_list);
 
+void blk_mq_abort_requeue_list(struct request_queue *q)
+{
+	unsigned long flags;
+	LIST_HEAD(rq_list);
+
+	spin_lock_irqsave(&q->requeue_lock, flags);
+	list_splice_init(&q->requeue_list, &rq_list);
+	spin_unlock_irqrestore(&q->requeue_lock, flags);
+
+	while (!list_empty(&rq_list)) {
+		struct request *rq;
+
+		rq = list_first_entry(&rq_list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		rq->errors = -EIO;
+		blk_mq_end_request(rq, rq->errors);
+	}
+}
+EXPORT_SYMBOL(blk_mq_abort_requeue_list);
+
 static inline bool is_flush_request(struct request *rq,
 		struct blk_flush_queue *fq, unsigned int tag)
 {
@@ -566,13 +619,24 @@ void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		break;
 	}
 }
-		
+
 static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, void *priv, bool reserved)
 {
 	struct blk_mq_timeout_data *data = priv;
 
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
+		/*
+		 * If a request wasn't started before the queue was
+		 * marked dying, kill it here or it'll go unnoticed.
+		 */
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_complete_request(rq);
+		}
+		return;
+	}
+	if (rq->cmd_flags & REQ_NO_TIMEOUT)
 		return;
 
 	if (time_after_eq(jiffies, rq->deadline)) {
@@ -1601,7 +1665,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	hctx->queue = q;
 	hctx->queue_num = hctx_idx;
 	hctx->flags = set->flags;
-	hctx->cmd_size = set->cmd_size;
 
 	blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
 					blk_mq_hctx_notify, hctx);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 206230e64f79..4f4f943c22c3 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -32,6 +32,7 @@ void blk_mq_free_queue(struct request_queue *q);
 void blk_mq_clone_flush_request(struct request *flush_rq,
 		struct request *orig_rq);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
+void blk_mq_wake_waiters(struct request_queue *q);
 
 /*
  * CPU hotplug helpers
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 56c025894cdf..246dfb16c3d9 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -190,6 +190,9 @@ void blk_add_timer(struct request *req)
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
+	if (req->cmd_flags & REQ_NO_TIMEOUT)
+		return;
+
 	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
 	if (!q->mq_ops && !q->rq_timed_out_fn)
 		return;
diff --git a/drivers/Makefile b/drivers/Makefile
index 67d2334dc41e..527a6da8d539 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -50,7 +50,10 @@ obj-$(CONFIG_RESET_CONTROLLER)	+= reset/
 obj-y				+= tty/
 obj-y				+= char/
 
-# gpu/ comes after char for AGP vs DRM startup
+# iommu/ comes before gpu as gpu are using iommu controllers
+obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
+
+# gpu/ comes after char for AGP vs DRM startup and after iommu
 obj-y				+= gpu/
 
 obj-$(CONFIG_CONNECTOR)		+= connector/
@@ -141,7 +144,6 @@ obj-y				+= clk/
 
 obj-$(CONFIG_MAILBOX)		+= mailbox/
 obj-$(CONFIG_HWSPINLOCK)	+= hwspinlock/
-obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
 obj-$(CONFIG_REMOTEPROC)	+= remoteproc/
 obj-$(CONFIG_RPMSG)		+= rpmsg/
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 1fdf5e07a1c7..1020b1b53a17 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -170,7 +170,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	acpi_status status;
 	int ret;
 
-	if (pr->apic_id == -1)
+	if (pr->phys_id == -1)
 		return -ENODEV;
 
 	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
@@ -180,13 +180,13 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	cpu_maps_update_begin();
 	cpu_hotplug_begin();
 
-	ret = acpi_map_lsapic(pr->handle, pr->apic_id, &pr->id);
+	ret = acpi_map_cpu(pr->handle, pr->phys_id, &pr->id);
 	if (ret)
 		goto out;
 
 	ret = arch_register_cpu(pr->id);
 	if (ret) {
-		acpi_unmap_lsapic(pr->id);
+		acpi_unmap_cpu(pr->id);
 		goto out;
 	}
 
@@ -215,7 +215,7 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	union acpi_object object = { 0 };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 	struct acpi_processor *pr = acpi_driver_data(device);
-	int apic_id, cpu_index, device_declaration = 0;
+	int phys_id, cpu_index, device_declaration = 0;
 	acpi_status status = AE_OK;
 	static int cpu0_initialized;
 	unsigned long long value;
@@ -262,15 +262,18 @@ static int acpi_processor_get_info(struct acpi_device *device)
 		pr->acpi_id = value;
 	}
 
-	apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id);
-	if (apic_id < 0)
-		acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n");
-	pr->apic_id = apic_id;
+	phys_id = acpi_get_phys_id(pr->handle, device_declaration, pr->acpi_id);
+	if (phys_id < 0)
+		acpi_handle_debug(pr->handle, "failed to get CPU physical ID.\n");
+	pr->phys_id = phys_id;
 
-	cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id);
+	cpu_index = acpi_map_cpuid(pr->phys_id, pr->acpi_id);
 	if (!cpu0_initialized && !acpi_has_cpu_in_madt()) {
 		cpu0_initialized = 1;
-		/* Handle UP system running SMP kernel, with no LAPIC in MADT */
+		/*
+		 * Handle UP system running SMP kernel, with no CPU
+		 * entry in MADT
+		 */
 		if ((cpu_index == -1) && (num_online_cpus() == 1))
 			cpu_index = 0;
 	}
@@ -458,7 +461,7 @@ static void acpi_processor_remove(struct acpi_device *device)
 
 	/* Remove the CPU. */
 	arch_unregister_cpu(pr->id);
-	acpi_unmap_lsapic(pr->id);
+	acpi_unmap_cpu(pr->id);
 
 	cpu_hotplug_done();
 	cpu_maps_update_done();
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index c2daa85fc9f7..c0d44d394ca3 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -257,7 +257,7 @@ int acpi_bus_init_power(struct acpi_device *device)
 
 	device->power.state = ACPI_STATE_UNKNOWN;
 	if (!acpi_device_is_present(device))
-		return 0;
+		return -ENXIO;
 
 	result = acpi_device_get_power(device, &state);
 	if (result)
diff --git a/drivers/acpi/int340x_thermal.c b/drivers/acpi/int340x_thermal.c
index a27d31d1ba24..9dcf83682e36 100644
--- a/drivers/acpi/int340x_thermal.c
+++ b/drivers/acpi/int340x_thermal.c
@@ -14,10 +14,10 @@
 
 #include "internal.h"
 
-#define DO_ENUMERATION 0x01
+#define INT3401_DEVICE 0X01
 static const struct acpi_device_id int340x_thermal_device_ids[] = {
-	{"INT3400", DO_ENUMERATION },
-	{"INT3401"},
+	{"INT3400"},
+	{"INT3401", INT3401_DEVICE},
 	{"INT3402"},
 	{"INT3403"},
 	{"INT3404"},
@@ -34,7 +34,10 @@ static int int340x_thermal_handler_attach(struct acpi_device *adev,
 					const struct acpi_device_id *id)
 {
 #if defined(CONFIG_INT340X_THERMAL) || defined(CONFIG_INT340X_THERMAL_MODULE)
-	if (id->driver_data == DO_ENUMERATION)
+	acpi_create_platform_device(adev);
+#elif defined(INTEL_SOC_DTS_THERMAL) || defined(INTEL_SOC_DTS_THERMAL_MODULE)
+	/* Intel SoC DTS thermal driver needs INT3401 to set IRQ descriptor */
+	if (id->driver_data == INT3401_DEVICE)
 		acpi_create_platform_device(adev);
 #endif
 	return 1;
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 342942f90a10..02e48394276c 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -69,7 +69,7 @@ static int map_madt_entry(int type, u32 acpi_id)
 	unsigned long madt_end, entry;
 	static struct acpi_table_madt *madt;
 	static int read_madt;
-	int apic_id = -1;
+	int phys_id = -1;	/* CPU hardware ID */
 
 	if (!read_madt) {
 		if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0,
@@ -79,7 +79,7 @@ static int map_madt_entry(int type, u32 acpi_id)
 	}
 
 	if (!madt)
-		return apic_id;
+		return phys_id;
 
 	entry = (unsigned long)madt;
 	madt_end = entry + madt->header.length;
@@ -91,18 +91,18 @@ static int map_madt_entry(int type, u32 acpi_id)
 		struct acpi_subtable_header *header =
 			(struct acpi_subtable_header *)entry;
 		if (header->type == ACPI_MADT_TYPE_LOCAL_APIC) {
-			if (!map_lapic_id(header, acpi_id, &apic_id))
+			if (!map_lapic_id(header, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC) {
-			if (!map_x2apic_id(header, type, acpi_id, &apic_id))
+			if (!map_x2apic_id(header, type, acpi_id, &phys_id))
 				break;
 		} else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC) {
-			if (!map_lsapic_id(header, type, acpi_id, &apic_id))
+			if (!map_lsapic_id(header, type, acpi_id, &phys_id))
 				break;
 		}
 		entry += header->length;
 	}
-	return apic_id;
+	return phys_id;
 }
 
 static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
@@ -110,7 +110,7 @@ static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *obj;
 	struct acpi_subtable_header *header;
-	int apic_id = -1;
+	int phys_id = -1;
 
 	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
 		goto exit;
@@ -126,38 +126,38 @@ static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id)
 
 	header = (struct acpi_subtable_header *)obj->buffer.pointer;
 	if (header->type == ACPI_MADT_TYPE_LOCAL_APIC)
-		map_lapic_id(header, acpi_id, &apic_id);
+		map_lapic_id(header, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC)
-		map_lsapic_id(header, type, acpi_id, &apic_id);
+		map_lsapic_id(header, type, acpi_id, &phys_id);
 	else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC)
-		map_x2apic_id(header, type, acpi_id, &apic_id);
+		map_x2apic_id(header, type, acpi_id, &phys_id);
 
 exit:
 	kfree(buffer.pointer);
-	return apic_id;
+	return phys_id;
 }
 
-int acpi_get_apicid(acpi_handle handle, int type, u32 acpi_id)
+int acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
 {
-	int apic_id;
+	int phys_id;
 
-	apic_id = map_mat_entry(handle, type, acpi_id);
-	if (apic_id == -1)
-		apic_id = map_madt_entry(type, acpi_id);
+	phys_id = map_mat_entry(handle, type, acpi_id);
+	if (phys_id == -1)
+		phys_id = map_madt_entry(type, acpi_id);
 
-	return apic_id;
+	return phys_id;
 }
 
-int acpi_map_cpuid(int apic_id, u32 acpi_id)
+int acpi_map_cpuid(int phys_id, u32 acpi_id)
 {
 #ifdef CONFIG_SMP
 	int i;
 #endif
 
-	if (apic_id == -1) {
+	if (phys_id == -1) {
 		/*
 		 * On UP processor, there is no _MAT or MADT table.
-		 * So above apic_id is always set to -1.
+		 * So above phys_id is always set to -1.
 		 *
 		 * BIOS may define multiple CPU handles even for UP processor.
 		 * For example,
@@ -170,7 +170,7 @@ int acpi_map_cpuid(int apic_id, u32 acpi_id)
 		 *     Processor (CPU3, 0x03, 0x00000410, 0x06) {}
 		 * }
 		 *
-		 * Ignores apic_id and always returns 0 for the processor
+		 * Ignores phys_id and always returns 0 for the processor
 		 * handle with acpi id 0 if nr_cpu_ids is 1.
 		 * This should be the case if SMP tables are not found.
 		 * Return -1 for other CPU's handle.
@@ -178,28 +178,28 @@ int acpi_map_cpuid(int apic_id, u32 acpi_id)
 		if (nr_cpu_ids <= 1 && acpi_id == 0)
 			return acpi_id;
 		else
-			return apic_id;
+			return phys_id;
 	}
 
 #ifdef CONFIG_SMP
 	for_each_possible_cpu(i) {
-		if (cpu_physical_id(i) == apic_id)
+		if (cpu_physical_id(i) == phys_id)
 			return i;
 	}
 #else
 	/* In UP kernel, only processor 0 is valid */
-	if (apic_id == 0)
-		return apic_id;
+	if (phys_id == 0)
+		return phys_id;
 #endif
 	return -1;
 }
 
 int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 {
-	int apic_id;
+	int phys_id;
 
-	apic_id = acpi_get_apicid(handle, type, acpi_id);
+	phys_id = acpi_get_phys_id(handle, type, acpi_id);
 
-	return acpi_map_cpuid(apic_id, acpi_id);
+	return acpi_map_cpuid(phys_id, acpi_id);
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 16914cc30882..dc4d8960684a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1001,7 +1001,7 @@ static void acpi_free_power_resources_lists(struct acpi_device *device)
 	if (device->wakeup.flags.valid)
 		acpi_power_resources_list_free(&device->wakeup.resources);
 
-	if (!device->flags.power_manageable)
+	if (!device->power.flags.power_resources)
 		return;
 
 	for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) {
@@ -1744,10 +1744,8 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 			device->power.flags.power_resources)
 		device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1;
 
-	if (acpi_bus_init_power(device)) {
-		acpi_free_power_resources_lists(device);
+	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
-	}
 }
 
 static void acpi_bus_get_flags(struct acpi_device *device)
@@ -2371,13 +2369,18 @@ static void acpi_bus_attach(struct acpi_device *device)
 	/* Skip devices that are not present. */
 	if (!acpi_device_is_present(device)) {
 		device->flags.visited = false;
+		device->flags.power_manageable = 0;
 		return;
 	}
 	if (device->handler)
 		goto ok;
 
 	if (!device->flags.initialized) {
-		acpi_bus_update_power(device, NULL);
+		device->flags.power_manageable =
+			device->power.states[ACPI_STATE_D0].flags.valid;
+		if (acpi_bus_init_power(device))
+			device->flags.power_manageable = 0;
+
 		device->flags.initialized = true;
 	}
 	device->flags.visited = false;
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index c72e79d2c5ad..032db459370f 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -522,6 +522,16 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "370R4E/370R4V/370R5E/3570RE/370R5V"),
 		},
 	},
+
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1163574 */
+	 .callback = video_disable_native_backlight,
+	 .ident = "Dell XPS15 L521X",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "XPS L521X"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index ae9f615382f6..aa2224aa7caa 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -530,7 +530,7 @@ static int null_add_dev(void)
 			goto out_cleanup_queues;
 
 		nullb->q = blk_mq_init_queue(&nullb->tag_set);
-		if (!nullb->q) {
+		if (IS_ERR(nullb->q)) {
 			rv = -ENOMEM;
 			goto out_cleanup_tags;
 		}
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index b1d5d8797315..cb529e9a82dd 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -215,6 +215,7 @@ static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
 	cmd->fn = handler;
 	cmd->ctx = ctx;
 	cmd->aborted = 0;
+	blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
 }
 
 /* Special values must be less than 0x1000 */
@@ -431,8 +432,13 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	if (unlikely(status)) {
 		if (!(status & NVME_SC_DNR || blk_noretry_request(req))
 		    && (jiffies - req->start_time) < req->timeout) {
+			unsigned long flags;
+
 			blk_mq_requeue_request(req);
-			blk_mq_kick_requeue_list(req->q);
+			spin_lock_irqsave(req->q->queue_lock, flags);
+			if (!blk_queue_stopped(req->q))
+				blk_mq_kick_requeue_list(req->q);
+			spin_unlock_irqrestore(req->q->queue_lock, flags);
 			return;
 		}
 		req->errors = nvme_error_status(status);
@@ -664,8 +670,6 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 		}
 	}
 
-	blk_mq_start_request(req);
-
 	nvme_set_info(cmd, iod, req_completion);
 	spin_lock_irq(&nvmeq->q_lock);
 	if (req->cmd_flags & REQ_DISCARD)
@@ -835,6 +839,7 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	req->cmd_flags |= REQ_NO_TIMEOUT;
 	cmd_info = blk_mq_rq_to_pdu(req);
 	nvme_set_info(cmd_info, req, async_req_completion);
 
@@ -1016,14 +1021,19 @@ static void nvme_abort_req(struct request *req)
 	struct nvme_command cmd;
 
 	if (!nvmeq->qid || cmd_rq->aborted) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&dev_list_lock, flags);
 		if (work_busy(&dev->reset_work))
-			return;
+			goto out;
 		list_del_init(&dev->node);
 		dev_warn(&dev->pci_dev->dev,
 			"I/O %d QID %d timeout, reset controller\n",
 							req->tag, nvmeq->qid);
 		dev->reset_workfn = nvme_reset_failed_dev;
 		queue_work(nvme_workq, &dev->reset_work);
+ out:
+		spin_unlock_irqrestore(&dev_list_lock, flags);
 		return;
 	}
 
@@ -1064,15 +1074,22 @@ static void nvme_cancel_queue_ios(struct blk_mq_hw_ctx *hctx,
 	void *ctx;
 	nvme_completion_fn fn;
 	struct nvme_cmd_info *cmd;
-	static struct nvme_completion cqe = {
-		.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1),
-	};
+	struct nvme_completion cqe;
+
+	if (!blk_mq_request_started(req))
+		return;
 
 	cmd = blk_mq_rq_to_pdu(req);
 
 	if (cmd->ctx == CMD_CTX_CANCELLED)
 		return;
 
+	if (blk_queue_dying(req->q))
+		cqe.status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
+	else
+		cqe.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
+
+
 	dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
 						req->tag, nvmeq->qid);
 	ctx = cancel_cmd_info(cmd, &fn);
@@ -1084,17 +1101,29 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = cmd->nvmeq;
 
-	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
-							nvmeq->qid);
-	if (nvmeq->dev->initialized)
-		nvme_abort_req(req);
-
 	/*
 	 * The aborted req will be completed on receiving the abort req.
 	 * We enable the timer again. If hit twice, it'll cause a device reset,
 	 * as the device then is in a faulty state.
 	 */
-	return BLK_EH_RESET_TIMER;
+	int ret = BLK_EH_RESET_TIMER;
+
+	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
+							nvmeq->qid);
+
+	spin_lock_irq(&nvmeq->q_lock);
+	if (!nvmeq->dev->initialized) {
+		/*
+		 * Force cancelled command frees the request, which requires we
+		 * return BLK_EH_NOT_HANDLED.
+		 */
+		nvme_cancel_queue_ios(nvmeq->hctx, req, nvmeq, reserved);
+		ret = BLK_EH_NOT_HANDLED;
+	} else
+		nvme_abort_req(req);
+	spin_unlock_irq(&nvmeq->q_lock);
+
+	return ret;
 }
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -1131,10 +1160,16 @@ static void nvme_free_queues(struct nvme_dev *dev, int lowest)
  */
 static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 {
-	int vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+	int vector;
 
 	spin_lock_irq(&nvmeq->q_lock);
+	if (nvmeq->cq_vector == -1) {
+		spin_unlock_irq(&nvmeq->q_lock);
+		return 1;
+	}
+	vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
 	nvmeq->dev->online_queues--;
+	nvmeq->cq_vector = -1;
 	spin_unlock_irq(&nvmeq->q_lock);
 
 	irq_set_affinity_hint(vector, NULL);
@@ -1169,11 +1204,13 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 		adapter_delete_sq(dev, qid);
 		adapter_delete_cq(dev, qid);
 	}
+	if (!qid && dev->admin_q)
+		blk_mq_freeze_queue_start(dev->admin_q);
 	nvme_clear_queue(nvmeq);
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
-							int depth, int vector)
+							int depth)
 {
 	struct device *dmadev = &dev->pci_dev->dev;
 	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
@@ -1199,7 +1236,6 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
-	nvmeq->cq_vector = vector;
 	nvmeq->qid = qid;
 	dev->queue_count++;
 	dev->queues[qid] = nvmeq;
@@ -1244,6 +1280,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	struct nvme_dev *dev = nvmeq->dev;
 	int result;
 
+	nvmeq->cq_vector = qid - 1;
 	result = adapter_alloc_cq(dev, qid, nvmeq);
 	if (result < 0)
 		return result;
@@ -1355,6 +1392,14 @@ static struct blk_mq_ops nvme_mq_ops = {
 	.timeout	= nvme_timeout,
 };
 
+static void nvme_dev_remove_admin(struct nvme_dev *dev)
+{
+	if (dev->admin_q && !blk_queue_dying(dev->admin_q)) {
+		blk_cleanup_queue(dev->admin_q);
+		blk_mq_free_tag_set(&dev->admin_tagset);
+	}
+}
+
 static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 {
 	if (!dev->admin_q) {
@@ -1370,21 +1415,20 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 			return -ENOMEM;
 
 		dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
-		if (!dev->admin_q) {
+		if (IS_ERR(dev->admin_q)) {
 			blk_mq_free_tag_set(&dev->admin_tagset);
 			return -ENOMEM;
 		}
-	}
+		if (!blk_get_queue(dev->admin_q)) {
+			nvme_dev_remove_admin(dev);
+			return -ENODEV;
+		}
+	} else
+		blk_mq_unfreeze_queue(dev->admin_q);
 
 	return 0;
 }
 
-static void nvme_free_admin_tags(struct nvme_dev *dev)
-{
-	if (dev->admin_q)
-		blk_mq_free_tag_set(&dev->admin_tagset);
-}
-
 static int nvme_configure_admin_queue(struct nvme_dev *dev)
 {
 	int result;
@@ -1416,7 +1460,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	nvmeq = dev->queues[0];
 	if (!nvmeq) {
-		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH, 0);
+		nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
 		if (!nvmeq)
 			return -ENOMEM;
 	}
@@ -1439,18 +1483,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	if (result)
 		goto free_nvmeq;
 
-	result = nvme_alloc_admin_tags(dev);
-	if (result)
-		goto free_nvmeq;
-
+	nvmeq->cq_vector = 0;
 	result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
 	if (result)
-		goto free_tags;
+		goto free_nvmeq;
 
 	return result;
 
- free_tags:
-	nvme_free_admin_tags(dev);
  free_nvmeq:
 	nvme_free_queues(dev, 0);
 	return result;
@@ -1944,7 +1983,7 @@ static void nvme_create_io_queues(struct nvme_dev *dev)
 	unsigned i;
 
 	for (i = dev->queue_count; i <= dev->max_qid; i++)
-		if (!nvme_alloc_queue(dev, i, dev->q_depth, i - 1))
+		if (!nvme_alloc_queue(dev, i, dev->q_depth))
 			break;
 
 	for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
@@ -2235,13 +2274,18 @@ static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
 			break;
 		if (!schedule_timeout(ADMIN_TIMEOUT) ||
 					fatal_signal_pending(current)) {
+			/*
+			 * Disable the controller first since we can't trust it
+			 * at this point, but leave the admin queue enabled
+			 * until all queue deletion requests are flushed.
+			 * FIXME: This may take a while if there are more h/w
+			 * queues than admin tags.
+			 */
 			set_current_state(TASK_RUNNING);
-
 			nvme_disable_ctrl(dev, readq(&dev->bar->cap));
-			nvme_disable_queue(dev, 0);
-
-			send_sig(SIGKILL, dq->worker->task, 1);
+			nvme_clear_queue(dev->queues[0]);
 			flush_kthread_worker(dq->worker);
+			nvme_disable_queue(dev, 0);
 			return;
 		}
 	}
@@ -2318,7 +2362,6 @@ static void nvme_del_queue_start(struct kthread_work *work)
 {
 	struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
 							cmdinfo.work);
-	allow_signal(SIGKILL);
 	if (nvme_delete_sq(nvmeq))
 		nvme_del_queue_end(nvmeq);
 }
@@ -2376,6 +2419,34 @@ static void nvme_dev_list_remove(struct nvme_dev *dev)
 		kthread_stop(tmp);
 }
 
+static void nvme_freeze_queues(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns;
+
+	list_for_each_entry(ns, &dev->namespaces, list) {
+		blk_mq_freeze_queue_start(ns->queue);
+
+		spin_lock(ns->queue->queue_lock);
+		queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
+		spin_unlock(ns->queue->queue_lock);
+
+		blk_mq_cancel_requeue_work(ns->queue);
+		blk_mq_stop_hw_queues(ns->queue);
+	}
+}
+
+static void nvme_unfreeze_queues(struct nvme_dev *dev)
+{
+	struct nvme_ns *ns;
+
+	list_for_each_entry(ns, &dev->namespaces, list) {
+		queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns->queue);
+		blk_mq_unfreeze_queue(ns->queue);
+		blk_mq_start_stopped_hw_queues(ns->queue, true);
+		blk_mq_kick_requeue_list(ns->queue);
+	}
+}
+
 static void nvme_dev_shutdown(struct nvme_dev *dev)
 {
 	int i;
@@ -2384,8 +2455,10 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	dev->initialized = 0;
 	nvme_dev_list_remove(dev);
 
-	if (dev->bar)
+	if (dev->bar) {
+		nvme_freeze_queues(dev);
 		csts = readl(&dev->bar->csts);
+	}
 	if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
 		for (i = dev->queue_count - 1; i >= 0; i--) {
 			struct nvme_queue *nvmeq = dev->queues[i];
@@ -2400,12 +2473,6 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	nvme_dev_unmap(dev);
 }
 
-static void nvme_dev_remove_admin(struct nvme_dev *dev)
-{
-	if (dev->admin_q && !blk_queue_dying(dev->admin_q))
-		blk_cleanup_queue(dev->admin_q);
-}
-
 static void nvme_dev_remove(struct nvme_dev *dev)
 {
 	struct nvme_ns *ns;
@@ -2413,8 +2480,10 @@ static void nvme_dev_remove(struct nvme_dev *dev)
 	list_for_each_entry(ns, &dev->namespaces, list) {
 		if (ns->disk->flags & GENHD_FL_UP)
 			del_gendisk(ns->disk);
-		if (!blk_queue_dying(ns->queue))
+		if (!blk_queue_dying(ns->queue)) {
+			blk_mq_abort_requeue_list(ns->queue);
 			blk_cleanup_queue(ns->queue);
+		}
 	}
 }
 
@@ -2495,6 +2564,7 @@ static void nvme_free_dev(struct kref *kref)
 	nvme_free_namespaces(dev);
 	nvme_release_instance(dev);
 	blk_mq_free_tag_set(&dev->tagset);
+	blk_put_queue(dev->admin_q);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2591,15 +2661,20 @@ static int nvme_dev_start(struct nvme_dev *dev)
 	}
 
 	nvme_init_queue(dev->queues[0], 0);
+	result = nvme_alloc_admin_tags(dev);
+	if (result)
+		goto disable;
 
 	result = nvme_setup_io_queues(dev);
 	if (result)
-		goto disable;
+		goto free_tags;
 
 	nvme_set_irq_hints(dev);
 
 	return result;
 
+ free_tags:
+	nvme_dev_remove_admin(dev);
  disable:
 	nvme_disable_queue(dev, 0);
 	nvme_dev_list_remove(dev);
@@ -2639,6 +2714,9 @@ static int nvme_dev_resume(struct nvme_dev *dev)
 		dev->reset_workfn = nvme_remove_disks;
 		queue_work(nvme_workq, &dev->reset_work);
 		spin_unlock(&dev_list_lock);
+	} else {
+		nvme_unfreeze_queues(dev);
+		nvme_set_irq_hints(dev);
 	}
 	dev->initialized = 1;
 	return 0;
@@ -2776,11 +2854,10 @@ static void nvme_remove(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->reset_work);
 	misc_deregister(&dev->miscdev);
-	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
+	nvme_dev_remove(dev);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
-	nvme_free_admin_tags(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
 }
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7ef7c098708f..cdfbd21e3597 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -638,7 +638,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_put_disk;
 
 	q = vblk->disk->queue = blk_mq_init_queue(&vblk->tag_set);
-	if (!q) {
+	if (IS_ERR(q)) {
 		err = -ENOMEM;
 		goto out_free_tags;
 	}
diff --git a/drivers/gpio/gpio-dln2.c b/drivers/gpio/gpio-dln2.c
index 978b51eae2ec..ce3c1558cb0a 100644
--- a/drivers/gpio/gpio-dln2.c
+++ b/drivers/gpio/gpio-dln2.c
@@ -47,13 +47,6 @@
 
 #define DLN2_GPIO_MAX_PINS 32
 
-struct dln2_irq_work {
-	struct work_struct work;
-	struct dln2_gpio *dln2;
-	int pin;
-	int type;
-};
-
 struct dln2_gpio {
 	struct platform_device *pdev;
 	struct gpio_chip gpio;
@@ -64,10 +57,12 @@ struct dln2_gpio {
 	 */
 	DECLARE_BITMAP(output_enabled, DLN2_GPIO_MAX_PINS);
 
-	DECLARE_BITMAP(irqs_masked, DLN2_GPIO_MAX_PINS);
-	DECLARE_BITMAP(irqs_enabled, DLN2_GPIO_MAX_PINS);
-	DECLARE_BITMAP(irqs_pending, DLN2_GPIO_MAX_PINS);
-	struct dln2_irq_work *irq_work;
+	/* active IRQs - not synced to hardware */
+	DECLARE_BITMAP(unmasked_irqs, DLN2_GPIO_MAX_PINS);
+	/* active IRQS - synced to hardware */
+	DECLARE_BITMAP(enabled_irqs, DLN2_GPIO_MAX_PINS);
+	int irq_type[DLN2_GPIO_MAX_PINS];
+	struct mutex irq_lock;
 };
 
 struct dln2_gpio_pin {
@@ -141,16 +136,16 @@ static int dln2_gpio_pin_get_out_val(struct dln2_gpio *dln2, unsigned int pin)
 	return !!ret;
 }
 
-static void dln2_gpio_pin_set_out_val(struct dln2_gpio *dln2,
-				      unsigned int pin, int value)
+static int dln2_gpio_pin_set_out_val(struct dln2_gpio *dln2,
+				     unsigned int pin, int value)
 {
 	struct dln2_gpio_pin_val req = {
 		.pin = cpu_to_le16(pin),
 		.value = value,
 	};
 
-	dln2_transfer_tx(dln2->pdev, DLN2_GPIO_PIN_SET_OUT_VAL, &req,
-			 sizeof(req));
+	return dln2_transfer_tx(dln2->pdev, DLN2_GPIO_PIN_SET_OUT_VAL, &req,
+				sizeof(req));
 }
 
 #define DLN2_GPIO_DIRECTION_IN		0
@@ -267,6 +262,13 @@ static int dln2_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 static int dln2_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
 				      int value)
 {
+	struct dln2_gpio *dln2 = container_of(chip, struct dln2_gpio, gpio);
+	int ret;
+
+	ret = dln2_gpio_pin_set_out_val(dln2, offset, value);
+	if (ret < 0)
+		return ret;
+
 	return dln2_gpio_set_direction(chip, offset, DLN2_GPIO_DIRECTION_OUT);
 }
 
@@ -297,36 +299,13 @@ static int dln2_gpio_set_event_cfg(struct dln2_gpio *dln2, unsigned pin,
 				&req, sizeof(req));
 }
 
-static void dln2_irq_work(struct work_struct *w)
-{
-	struct dln2_irq_work *iw = container_of(w, struct dln2_irq_work, work);
-	struct dln2_gpio *dln2 = iw->dln2;
-	u8 type = iw->type & DLN2_GPIO_EVENT_MASK;
-
-	if (test_bit(iw->pin, dln2->irqs_enabled))
-		dln2_gpio_set_event_cfg(dln2, iw->pin, type, 0);
-	else
-		dln2_gpio_set_event_cfg(dln2, iw->pin, DLN2_GPIO_EVENT_NONE, 0);
-}
-
-static void dln2_irq_enable(struct irq_data *irqd)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd);
-	struct dln2_gpio *dln2 = container_of(gc, struct dln2_gpio, gpio);
-	int pin = irqd_to_hwirq(irqd);
-
-	set_bit(pin, dln2->irqs_enabled);
-	schedule_work(&dln2->irq_work[pin].work);
-}
-
-static void dln2_irq_disable(struct irq_data *irqd)
+static void dln2_irq_unmask(struct irq_data *irqd)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd);
 	struct dln2_gpio *dln2 = container_of(gc, struct dln2_gpio, gpio);
 	int pin = irqd_to_hwirq(irqd);
 
-	clear_bit(pin, dln2->irqs_enabled);
-	schedule_work(&dln2->irq_work[pin].work);
+	set_bit(pin, dln2->unmasked_irqs);
 }
 
 static void dln2_irq_mask(struct irq_data *irqd)
@@ -335,27 +314,7 @@ static void dln2_irq_mask(struct irq_data *irqd)
 	struct dln2_gpio *dln2 = container_of(gc, struct dln2_gpio, gpio);
 	int pin = irqd_to_hwirq(irqd);
 
-	set_bit(pin, dln2->irqs_masked);
-}
-
-static void dln2_irq_unmask(struct irq_data *irqd)
-{
-	struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd);
-	struct dln2_gpio *dln2 = container_of(gc, struct dln2_gpio, gpio);
-	struct device *dev = dln2->gpio.dev;
-	int pin = irqd_to_hwirq(irqd);
-
-	if (test_and_clear_bit(pin, dln2->irqs_pending)) {
-		int irq;
-
-		irq = irq_find_mapping(dln2->gpio.irqdomain, pin);
-		if (!irq) {
-			dev_err(dev, "pin %d not mapped to IRQ\n", pin);
-			return;
-		}
-
-		generic_handle_irq(irq);
-	}
+	clear_bit(pin, dln2->unmasked_irqs);
 }
 
 static int dln2_irq_set_type(struct irq_data *irqd, unsigned type)
@@ -366,19 +325,19 @@ static int dln2_irq_set_type(struct irq_data *irqd, unsigned type)
 
 	switch (type) {
 	case IRQ_TYPE_LEVEL_HIGH:
-		dln2->irq_work[pin].type = DLN2_GPIO_EVENT_LVL_HIGH;
+		dln2->irq_type[pin] = DLN2_GPIO_EVENT_LVL_HIGH;
 		break;
 	case IRQ_TYPE_LEVEL_LOW:
-		dln2->irq_work[pin].type = DLN2_GPIO_EVENT_LVL_LOW;
+		dln2->irq_type[pin] = DLN2_GPIO_EVENT_LVL_LOW;
 		break;
 	case IRQ_TYPE_EDGE_BOTH:
-		dln2->irq_work[pin].type = DLN2_GPIO_EVENT_CHANGE;
+		dln2->irq_type[pin] = DLN2_GPIO_EVENT_CHANGE;
 		break;
 	case IRQ_TYPE_EDGE_RISING:
-		dln2->irq_work[pin].type = DLN2_GPIO_EVENT_CHANGE_RISING;
+		dln2->irq_type[pin] = DLN2_GPIO_EVENT_CHANGE_RISING;
 		break;
 	case IRQ_TYPE_EDGE_FALLING:
-		dln2->irq_work[pin].type = DLN2_GPIO_EVENT_CHANGE_FALLING;
+		dln2->irq_type[pin] = DLN2_GPIO_EVENT_CHANGE_FALLING;
 		break;
 	default:
 		return -EINVAL;
@@ -387,13 +346,50 @@ static int dln2_irq_set_type(struct irq_data *irqd, unsigned type)
 	return 0;
 }
 
+static void dln2_irq_bus_lock(struct irq_data *irqd)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd);
+	struct dln2_gpio *dln2 = container_of(gc, struct dln2_gpio, gpio);
+
+	mutex_lock(&dln2->irq_lock);
+}
+
+static void dln2_irq_bus_unlock(struct irq_data *irqd)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd);
+	struct dln2_gpio *dln2 = container_of(gc, struct dln2_gpio, gpio);
+	int pin = irqd_to_hwirq(irqd);
+	int enabled, unmasked;
+	unsigned type;
+	int ret;
+
+	enabled = test_bit(pin, dln2->enabled_irqs);
+	unmasked = test_bit(pin, dln2->unmasked_irqs);
+
+	if (enabled != unmasked) {
+		if (unmasked) {
+			type = dln2->irq_type[pin] & DLN2_GPIO_EVENT_MASK;
+			set_bit(pin, dln2->enabled_irqs);
+		} else {
+			type = DLN2_GPIO_EVENT_NONE;
+			clear_bit(pin, dln2->enabled_irqs);
+		}
+
+		ret = dln2_gpio_set_event_cfg(dln2, pin, type, 0);
+		if (ret)
+			dev_err(dln2->gpio.dev, "failed to set event\n");
+	}
+
+	mutex_unlock(&dln2->irq_lock);
+}
+
 static struct irq_chip dln2_gpio_irqchip = {
 	.name = "dln2-irq",
-	.irq_enable = dln2_irq_enable,
-	.irq_disable = dln2_irq_disable,
 	.irq_mask = dln2_irq_mask,
 	.irq_unmask = dln2_irq_unmask,
 	.irq_set_type = dln2_irq_set_type,
+	.irq_bus_lock = dln2_irq_bus_lock,
+	.irq_bus_sync_unlock = dln2_irq_bus_unlock,
 };
 
 static void dln2_gpio_event(struct platform_device *pdev, u16 echo,
@@ -425,14 +421,7 @@ static void dln2_gpio_event(struct platform_device *pdev, u16 echo,
 		return;
 	}
 
-	if (!test_bit(pin, dln2->irqs_enabled))
-		return;
-	if (test_bit(pin, dln2->irqs_masked)) {
-		set_bit(pin, dln2->irqs_pending);
-		return;
-	}
-
-	switch (dln2->irq_work[pin].type) {
+	switch (dln2->irq_type[pin]) {
 	case DLN2_GPIO_EVENT_CHANGE_RISING:
 		if (event->value)
 			generic_handle_irq(irq);
@@ -451,7 +440,7 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	struct dln2_gpio *dln2;
 	struct device *dev = &pdev->dev;
 	int pins;
-	int i, ret;
+	int ret;
 
 	pins = dln2_gpio_get_pin_count(pdev);
 	if (pins < 0) {
@@ -467,15 +456,7 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	if (!dln2)
 		return -ENOMEM;
 
-	dln2->irq_work = devm_kcalloc(&pdev->dev, pins,
-				      sizeof(struct dln2_irq_work), GFP_KERNEL);
-	if (!dln2->irq_work)
-		return -ENOMEM;
-	for (i = 0; i < pins; i++) {
-		INIT_WORK(&dln2->irq_work[i].work, dln2_irq_work);
-		dln2->irq_work[i].pin = i;
-		dln2->irq_work[i].dln2 = dln2;
-	}
+	mutex_init(&dln2->irq_lock);
 
 	dln2->pdev = pdev;
 
@@ -529,11 +510,8 @@ out:
 static int dln2_gpio_remove(struct platform_device *pdev)
 {
 	struct dln2_gpio *dln2 = platform_get_drvdata(pdev);
-	int i;
 
 	dln2_unregister_event_cb(pdev, DLN2_GPIO_CONDITION_MET_EV);
-	for (i = 0; i < dln2->gpio.ngpio; i++)
-		flush_work(&dln2->irq_work[i].work);
 	gpiochip_remove(&dln2->gpio);
 
 	return 0;
diff --git a/drivers/gpio/gpio-grgpio.c b/drivers/gpio/gpio-grgpio.c
index 09daaf2aeb56..3a5a71050559 100644
--- a/drivers/gpio/gpio-grgpio.c
+++ b/drivers/gpio/gpio-grgpio.c
@@ -441,7 +441,8 @@ static int grgpio_probe(struct platform_device *ofdev)
 	err = gpiochip_add(gc);
 	if (err) {
 		dev_err(&ofdev->dev, "Could not add gpiochip\n");
-		irq_domain_remove(priv->domain);
+		if (priv->domain)
+			irq_domain_remove(priv->domain);
 		return err;
 	}
 
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 66e40398b3d3..e620807418ea 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
 obj-$(CONFIG_DRM_TTM)	+= ttm/
 obj-$(CONFIG_DRM_TDFX)	+= tdfx/
 obj-$(CONFIG_DRM_R128)	+= r128/
+obj-$(CONFIG_HSA_AMD) += amd/amdkfd/
 obj-$(CONFIG_DRM_RADEON)+= radeon/
 obj-$(CONFIG_DRM_MGA)	+= mga/
 obj-$(CONFIG_DRM_I810)	+= i810/
@@ -67,4 +68,3 @@ obj-$(CONFIG_DRM_IMX) += imx/
 obj-y			+= i2c/
 obj-y			+= panel/
 obj-y			+= bridge/
-obj-$(CONFIG_HSA_AMD) += amd/amdkfd/
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 7d4974b83af7..fcfdf23e1913 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -31,7 +31,6 @@
 #include <uapi/linux/kfd_ioctl.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/uaccess.h>
 #include <uapi/asm-generic/mman-common.h>
 #include <asm/processor.h>
 #include "kfd_priv.h"
@@ -127,17 +126,14 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	return 0;
 }
 
-static long kfd_ioctl_get_version(struct file *filep, struct kfd_process *p,
-					void __user *arg)
+static int kfd_ioctl_get_version(struct file *filep, struct kfd_process *p,
+					void *data)
 {
-	struct kfd_ioctl_get_version_args args;
+	struct kfd_ioctl_get_version_args *args = data;
 	int err = 0;
 
-	args.major_version = KFD_IOCTL_MAJOR_VERSION;
-	args.minor_version = KFD_IOCTL_MINOR_VERSION;
-
-	if (copy_to_user(arg, &args, sizeof(args)))
-		err = -EFAULT;
+	args->major_version = KFD_IOCTL_MAJOR_VERSION;
+	args->minor_version = KFD_IOCTL_MINOR_VERSION;
 
 	return err;
 }
@@ -221,10 +217,10 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties,
 	return 0;
 }
 
-static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
-					void __user *arg)
+static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
+					void *data)
 {
-	struct kfd_ioctl_create_queue_args args;
+	struct kfd_ioctl_create_queue_args *args = data;
 	struct kfd_dev *dev;
 	int err = 0;
 	unsigned int queue_id;
@@ -233,16 +229,13 @@ static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 
 	memset(&q_properties, 0, sizeof(struct queue_properties));
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
 	pr_debug("kfd: creating queue ioctl\n");
 
-	err = set_queue_properties_from_user(&q_properties, &args);
+	err = set_queue_properties_from_user(&q_properties, args);
 	if (err)
 		return err;
 
-	dev = kfd_device_by_id(args.gpu_id);
+	dev = kfd_device_by_id(args->gpu_id);
 	if (dev == NULL)
 		return -EINVAL;
 
@@ -250,7 +243,7 @@ static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
-		err = PTR_ERR(pdd);
+		err = -ESRCH;
 		goto err_bind_process;
 	}
 
@@ -263,33 +256,26 @@ static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	if (err != 0)
 		goto err_create_queue;
 
-	args.queue_id = queue_id;
+	args->queue_id = queue_id;
 
 	/* Return gpu_id as doorbell offset for mmap usage */
-	args.doorbell_offset = args.gpu_id << PAGE_SHIFT;
-
-	if (copy_to_user(arg, &args, sizeof(args))) {
-		err = -EFAULT;
-		goto err_copy_args_out;
-	}
+	args->doorbell_offset = args->gpu_id << PAGE_SHIFT;
 
 	mutex_unlock(&p->mutex);
 
-	pr_debug("kfd: queue id %d was created successfully\n", args.queue_id);
+	pr_debug("kfd: queue id %d was created successfully\n", args->queue_id);
 
 	pr_debug("ring buffer address == 0x%016llX\n",
-			args.ring_base_address);
+			args->ring_base_address);
 
 	pr_debug("read ptr address    == 0x%016llX\n",
-			args.read_pointer_address);
+			args->read_pointer_address);
 
 	pr_debug("write ptr address   == 0x%016llX\n",
-			args.write_pointer_address);
+			args->write_pointer_address);
 
 	return 0;
 
-err_copy_args_out:
-	pqm_destroy_queue(&p->pqm, queue_id);
 err_create_queue:
 err_bind_process:
 	mutex_unlock(&p->mutex);
@@ -297,99 +283,90 @@ err_bind_process:
 }
 
 static int kfd_ioctl_destroy_queue(struct file *filp, struct kfd_process *p,
-					void __user *arg)
+					void *data)
 {
 	int retval;
-	struct kfd_ioctl_destroy_queue_args args;
-
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
+	struct kfd_ioctl_destroy_queue_args *args = data;
 
 	pr_debug("kfd: destroying queue id %d for PASID %d\n",
-				args.queue_id,
+				args->queue_id,
 				p->pasid);
 
 	mutex_lock(&p->mutex);
 
-	retval = pqm_destroy_queue(&p->pqm, args.queue_id);
+	retval = pqm_destroy_queue(&p->pqm, args->queue_id);
 
 	mutex_unlock(&p->mutex);
 	return retval;
 }
 
 static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
-					void __user *arg)
+					void *data)
 {
 	int retval;
-	struct kfd_ioctl_update_queue_args args;
+	struct kfd_ioctl_update_queue_args *args = data;
 	struct queue_properties properties;
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	if (args.queue_percentage > KFD_MAX_QUEUE_PERCENTAGE) {
+	if (args->queue_percentage > KFD_MAX_QUEUE_PERCENTAGE) {
 		pr_err("kfd: queue percentage must be between 0 to KFD_MAX_QUEUE_PERCENTAGE\n");
 		return -EINVAL;
 	}
 
-	if (args.queue_priority > KFD_MAX_QUEUE_PRIORITY) {
+	if (args->queue_priority > KFD_MAX_QUEUE_PRIORITY) {
 		pr_err("kfd: queue priority must be between 0 to KFD_MAX_QUEUE_PRIORITY\n");
 		return -EINVAL;
 	}
 
-	if ((args.ring_base_address) &&
+	if ((args->ring_base_address) &&
 		(!access_ok(VERIFY_WRITE,
-			(const void __user *) args.ring_base_address,
+			(const void __user *) args->ring_base_address,
 			sizeof(uint64_t)))) {
 		pr_err("kfd: can't access ring base address\n");
 		return -EFAULT;
 	}
 
-	if (!is_power_of_2(args.ring_size) && (args.ring_size != 0)) {
+	if (!is_power_of_2(args->ring_size) && (args->ring_size != 0)) {
 		pr_err("kfd: ring size must be a power of 2 or 0\n");
 		return -EINVAL;
 	}
 
-	properties.queue_address = args.ring_base_address;
-	properties.queue_size = args.ring_size;
-	properties.queue_percent = args.queue_percentage;
-	properties.priority = args.queue_priority;
+	properties.queue_address = args->ring_base_address;
+	properties.queue_size = args->ring_size;
+	properties.queue_percent = args->queue_percentage;
+	properties.priority = args->queue_priority;
 
 	pr_debug("kfd: updating queue id %d for PASID %d\n",
-			args.queue_id, p->pasid);
+			args->queue_id, p->pasid);
 
 	mutex_lock(&p->mutex);
 
-	retval = pqm_update_queue(&p->pqm, args.queue_id, &properties);
+	retval = pqm_update_queue(&p->pqm, args->queue_id, &properties);
 
 	mutex_unlock(&p->mutex);
 
 	return retval;
 }
 
-static long kfd_ioctl_set_memory_policy(struct file *filep,
-				struct kfd_process *p, void __user *arg)
+static int kfd_ioctl_set_memory_policy(struct file *filep,
+					struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_set_memory_policy_args args;
+	struct kfd_ioctl_set_memory_policy_args *args = data;
 	struct kfd_dev *dev;
 	int err = 0;
 	struct kfd_process_device *pdd;
 	enum cache_policy default_policy, alternate_policy;
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	if (args.default_policy != KFD_IOC_CACHE_POLICY_COHERENT
-	    && args.default_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
+	if (args->default_policy != KFD_IOC_CACHE_POLICY_COHERENT
+	    && args->default_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
 		return -EINVAL;
 	}
 
-	if (args.alternate_policy != KFD_IOC_CACHE_POLICY_COHERENT
-	    && args.alternate_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
+	if (args->alternate_policy != KFD_IOC_CACHE_POLICY_COHERENT
+	    && args->alternate_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
 		return -EINVAL;
 	}
 
-	dev = kfd_device_by_id(args.gpu_id);
+	dev = kfd_device_by_id(args->gpu_id);
 	if (dev == NULL)
 		return -EINVAL;
 
@@ -397,23 +374,23 @@ static long kfd_ioctl_set_memory_policy(struct file *filep,
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
-		err = PTR_ERR(pdd);
+		err = -ESRCH;
 		goto out;
 	}
 
-	default_policy = (args.default_policy == KFD_IOC_CACHE_POLICY_COHERENT)
+	default_policy = (args->default_policy == KFD_IOC_CACHE_POLICY_COHERENT)
 			 ? cache_policy_coherent : cache_policy_noncoherent;
 
 	alternate_policy =
-		(args.alternate_policy == KFD_IOC_CACHE_POLICY_COHERENT)
+		(args->alternate_policy == KFD_IOC_CACHE_POLICY_COHERENT)
 		   ? cache_policy_coherent : cache_policy_noncoherent;
 
 	if (!dev->dqm->set_cache_memory_policy(dev->dqm,
 				&pdd->qpd,
 				default_policy,
 				alternate_policy,
-				(void __user *)args.alternate_aperture_base,
-				args.alternate_aperture_size))
+				(void __user *)args->alternate_aperture_base,
+				args->alternate_aperture_size))
 		err = -EINVAL;
 
 out:
@@ -422,53 +399,44 @@ out:
 	return err;
 }
 
-static long kfd_ioctl_get_clock_counters(struct file *filep,
-				struct kfd_process *p, void __user *arg)
+static int kfd_ioctl_get_clock_counters(struct file *filep,
+				struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_get_clock_counters_args args;
+	struct kfd_ioctl_get_clock_counters_args *args = data;
 	struct kfd_dev *dev;
 	struct timespec time;
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	dev = kfd_device_by_id(args.gpu_id);
+	dev = kfd_device_by_id(args->gpu_id);
 	if (dev == NULL)
 		return -EINVAL;
 
 	/* Reading GPU clock counter from KGD */
-	args.gpu_clock_counter = kfd2kgd->get_gpu_clock_counter(dev->kgd);
+	args->gpu_clock_counter = kfd2kgd->get_gpu_clock_counter(dev->kgd);
 
 	/* No access to rdtsc. Using raw monotonic time */
 	getrawmonotonic(&time);
-	args.cpu_clock_counter = (uint64_t)timespec_to_ns(&time);
+	args->cpu_clock_counter = (uint64_t)timespec_to_ns(&time);
 
 	get_monotonic_boottime(&time);
-	args.system_clock_counter = (uint64_t)timespec_to_ns(&time);
+	args->system_clock_counter = (uint64_t)timespec_to_ns(&time);
 
 	/* Since the counter is in nano-seconds we use 1GHz frequency */
-	args.system_clock_freq = 1000000000;
-
-	if (copy_to_user(arg, &args, sizeof(args)))
-		return -EFAULT;
+	args->system_clock_freq = 1000000000;
 
 	return 0;
 }
 
 
 static int kfd_ioctl_get_process_apertures(struct file *filp,
-				struct kfd_process *p, void __user *arg)
+				struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_get_process_apertures_args args;
+	struct kfd_ioctl_get_process_apertures_args *args = data;
 	struct kfd_process_device_apertures *pAperture;
 	struct kfd_process_device *pdd;
 
 	dev_dbg(kfd_device, "get apertures for PASID %d", p->pasid);
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	args.num_of_nodes = 0;
+	args->num_of_nodes = 0;
 
 	mutex_lock(&p->mutex);
 
@@ -477,7 +445,8 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 		/* Run over all pdd of the process */
 		pdd = kfd_get_first_process_device_data(p);
 		do {
-			pAperture = &args.process_apertures[args.num_of_nodes];
+			pAperture =
+				&args->process_apertures[args->num_of_nodes];
 			pAperture->gpu_id = pdd->dev->id;
 			pAperture->lds_base = pdd->lds_base;
 			pAperture->lds_limit = pdd->lds_limit;
@@ -487,7 +456,7 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 			pAperture->scratch_limit = pdd->scratch_limit;
 
 			dev_dbg(kfd_device,
-				"node id %u\n", args.num_of_nodes);
+				"node id %u\n", args->num_of_nodes);
 			dev_dbg(kfd_device,
 				"gpu id %u\n", pdd->dev->id);
 			dev_dbg(kfd_device,
@@ -503,80 +472,131 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 			dev_dbg(kfd_device,
 				"scratch_limit %llX\n", pdd->scratch_limit);
 
-			args.num_of_nodes++;
+			args->num_of_nodes++;
 		} while ((pdd = kfd_get_next_process_device_data(p, pdd)) != NULL &&
-				(args.num_of_nodes < NUM_OF_SUPPORTED_GPUS));
+				(args->num_of_nodes < NUM_OF_SUPPORTED_GPUS));
 	}
 
 	mutex_unlock(&p->mutex);
 
-	if (copy_to_user(arg, &args, sizeof(args)))
-		return -EFAULT;
-
 	return 0;
 }
 
+#define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
+	[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
+
+/** Ioctl table */
+static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_VERSION,
+			kfd_ioctl_get_version, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_CREATE_QUEUE,
+			kfd_ioctl_create_queue, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DESTROY_QUEUE,
+			kfd_ioctl_destroy_queue, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_MEMORY_POLICY,
+			kfd_ioctl_set_memory_policy, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_CLOCK_COUNTERS,
+			kfd_ioctl_get_clock_counters, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_PROCESS_APERTURES,
+			kfd_ioctl_get_process_apertures, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UPDATE_QUEUE,
+			kfd_ioctl_update_queue, 0),
+};
+
+#define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
+
 static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
 	struct kfd_process *process;
-	long err = -EINVAL;
+	amdkfd_ioctl_t *func;
+	const struct amdkfd_ioctl_desc *ioctl = NULL;
+	unsigned int nr = _IOC_NR(cmd);
+	char stack_kdata[128];
+	char *kdata = NULL;
+	unsigned int usize, asize;
+	int retcode = -EINVAL;
 
-	dev_dbg(kfd_device,
-		"ioctl cmd 0x%x (#%d), arg 0x%lx\n",
-		cmd, _IOC_NR(cmd), arg);
+	if (nr >= AMDKFD_CORE_IOCTL_COUNT)
+		goto err_i1;
+
+	if ((nr >= AMDKFD_COMMAND_START) && (nr < AMDKFD_COMMAND_END)) {
+		u32 amdkfd_size;
+
+		ioctl = &amdkfd_ioctls[nr];
+
+		amdkfd_size = _IOC_SIZE(ioctl->cmd);
+		usize = asize = _IOC_SIZE(cmd);
+		if (amdkfd_size > asize)
+			asize = amdkfd_size;
+
+		cmd = ioctl->cmd;
+	} else
+		goto err_i1;
+
+	dev_dbg(kfd_device, "ioctl cmd 0x%x (#%d), arg 0x%lx\n", cmd, nr, arg);
 
 	process = kfd_get_process(current);
-	if (IS_ERR(process))
-		return PTR_ERR(process);
+	if (IS_ERR(process)) {
+		dev_dbg(kfd_device, "no process\n");
+		goto err_i1;
+	}
 
-	switch (cmd) {
-	case KFD_IOC_GET_VERSION:
-		err = kfd_ioctl_get_version(filep, process, (void __user *)arg);
-		break;
-	case KFD_IOC_CREATE_QUEUE:
-		err = kfd_ioctl_create_queue(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_DESTROY_QUEUE:
-		err = kfd_ioctl_destroy_queue(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_SET_MEMORY_POLICY:
-		err = kfd_ioctl_set_memory_policy(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_GET_CLOCK_COUNTERS:
-		err = kfd_ioctl_get_clock_counters(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_GET_PROCESS_APERTURES:
-		err = kfd_ioctl_get_process_apertures(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_UPDATE_QUEUE:
-		err = kfd_ioctl_update_queue(filep, process,
-						(void __user *)arg);
-		break;
-
-	default:
-		dev_err(kfd_device,
-			"unknown ioctl cmd 0x%x, arg 0x%lx)\n",
-			cmd, arg);
-		err = -EINVAL;
-		break;
+	/* Do not trust userspace, use our own definition */
+	func = ioctl->func;
+
+	if (unlikely(!func)) {
+		dev_dbg(kfd_device, "no function\n");
+		retcode = -EINVAL;
+		goto err_i1;
 	}
 
-	if (err < 0)
-		dev_err(kfd_device,
-			"ioctl error %ld for ioctl cmd 0x%x (#%d)\n",
-			err, cmd, _IOC_NR(cmd));
+	if (cmd & (IOC_IN | IOC_OUT)) {
+		if (asize <= sizeof(stack_kdata)) {
+			kdata = stack_kdata;
+		} else {
+			kdata = kmalloc(asize, GFP_KERNEL);
+			if (!kdata) {
+				retcode = -ENOMEM;
+				goto err_i1;
+			}
+		}
+		if (asize > usize)
+			memset(kdata + usize, 0, asize - usize);
+	}
 
-	return err;
+	if (cmd & IOC_IN) {
+		if (copy_from_user(kdata, (void __user *)arg, usize) != 0) {
+			retcode = -EFAULT;
+			goto err_i1;
+		}
+	} else if (cmd & IOC_OUT) {
+		memset(kdata, 0, usize);
+	}
+
+	retcode = func(filep, process, kdata);
+
+	if (cmd & IOC_OUT)
+		if (copy_to_user((void __user *)arg, kdata, usize) != 0)
+			retcode = -EFAULT;
+
+err_i1:
+	if (!ioctl)
+		dev_dbg(kfd_device, "invalid ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
+			  task_pid_nr(current), cmd, nr);
+
+	if (kdata != stack_kdata)
+		kfree(kdata);
+
+	if (retcode)
+		dev_dbg(kfd_device, "ret = %d\n", retcode);
+
+	return retcode;
 }
 
 static int kfd_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 924e90c072e5..9c8961d22360 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -161,6 +161,9 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 {
 	int bit = qpd->vmid - KFD_VMID_START_OFFSET;
 
+	/* Release the vmid mapping */
+	set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
+
 	set_bit(bit, (unsigned long *)&dqm->vmid_bitmap);
 	qpd->vmid = 0;
 	q->properties.vmid = 0;
@@ -272,6 +275,18 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 		return retval;
 	}
 
+	pr_debug("kfd: loading mqd to hqd on pipe (%d) queue (%d)\n",
+			q->pipe,
+			q->queue);
+
+	retval = mqd->load_mqd(mqd, q->mqd, q->pipe,
+			q->queue, q->properties.write_ptr);
+	if (retval != 0) {
+		deallocate_hqd(dqm, q);
+		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		return retval;
+	}
+
 	return 0;
 }
 
@@ -320,6 +335,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 {
 	int retval;
 	struct mqd_manager *mqd;
+	bool prev_active = false;
 
 	BUG_ON(!dqm || !q || !q->mqd);
 
@@ -330,10 +346,18 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		return -ENOMEM;
 	}
 
-	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
 	if (q->properties.is_active == true)
+		prev_active = true;
+
+	/*
+	 *
+	 * check active state vs. the previous state
+	 * and modify counter accordingly
+	 */
+	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
+	if ((q->properties.is_active == true) && (prev_active == false))
 		dqm->queue_count++;
-	else
+	else if ((q->properties.is_active == false) && (prev_active == true))
 		dqm->queue_count--;
 
 	if (sched_policy != KFD_SCHED_POLICY_NO_HWS)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index adc31474e786..4c3828cf45bf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -184,7 +184,7 @@ static bool is_occupied(struct mqd_manager *mm, void *mqd,
 			uint32_t queue_id)
 {
 
-	return kfd2kgd->hqd_is_occupies(mm->dev->kgd, queue_address,
+	return kfd2kgd->hqd_is_occupied(mm->dev->kgd, queue_address,
 					pipe_id, queue_id);
 
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 71699ad97d74..4c25ef504f79 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -32,7 +32,7 @@ int kfd_pasid_init(void)
 {
 	pasid_limit = max_num_of_processes;
 
-	pasid_bitmap = kzalloc(BITS_TO_LONGS(pasid_limit), GFP_KERNEL);
+	pasid_bitmap = kcalloc(BITS_TO_LONGS(pasid_limit), sizeof(long), GFP_KERNEL);
 	if (!pasid_bitmap)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f9fb81e3bb09..a5edb29507e3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -463,6 +463,24 @@ struct kfd_process {
 	bool is_32bit_user_mode;
 };
 
+/**
+ * Ioctl function type.
+ *
+ * \param filep pointer to file structure.
+ * \param p amdkfd process pointer.
+ * \param data pointer to arg that was copied from user.
+ */
+typedef int amdkfd_ioctl_t(struct file *filep, struct kfd_process *p,
+				void *data);
+
+struct amdkfd_ioctl_desc {
+	unsigned int cmd;
+	int flags;
+	amdkfd_ioctl_t *func;
+	unsigned int cmd_drv;
+	const char *name;
+};
+
 void kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 struct kfd_process *kfd_create_process(const struct task_struct *);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index b11792d7e70e..cca1708fd811 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -921,7 +921,7 @@ static int kfd_build_sysfs_node_tree(void)
 	uint32_t i = 0;
 
 	list_for_each_entry(dev, &topology_device_list, list) {
-		ret = kfd_build_sysfs_node_entry(dev, 0);
+		ret = kfd_build_sysfs_node_entry(dev, i);
 		if (ret < 0)
 			return ret;
 		i++;
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 47b551970a14..96a512208fad 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -183,7 +183,7 @@ struct kfd2kgd_calls {
 	int (*hqd_load)(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr);
 
-	bool (*hqd_is_occupies)(struct kgd_dev *kgd, uint64_t queue_address,
+	bool (*hqd_is_occupied)(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id);
 
 	int (*hqd_destroy)(struct kgd_dev *kgd, uint32_t reset_type,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 70d0f0f06f1a..e9f891c432f8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1756,8 +1756,6 @@ struct drm_i915_private {
 	 */
 	struct workqueue_struct *dp_wq;
 
-	uint32_t bios_vgacntr;
-
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
 	struct {
 		int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 52adcb680be3..c11603b4cf1d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1048,6 +1048,7 @@ int
 i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_pwrite *args = data;
 	struct drm_i915_gem_object *obj;
 	int ret;
@@ -1067,9 +1068,11 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 			return -EFAULT;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
-		return ret;
+		goto put_rpm;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
 	if (&obj->base == NULL) {
@@ -1121,6 +1124,9 @@ out:
 	drm_gem_object_unreference(&obj->base);
 unlock:
 	mutex_unlock(&dev->struct_mutex);
+put_rpm:
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 996c2931c499..d0d3dfbe6d2a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3725,8 +3725,6 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -3736,6 +3734,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if (I915_READ16(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
@@ -3907,8 +3906,6 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -3918,6 +3915,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if (I915_READ(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fb3e3d429191..e2af1383b179 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13057,11 +13057,7 @@ static void i915_disable_vga(struct drm_device *dev)
 	vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
 	udelay(300);
 
-	/*
-	 * Fujitsu-Siemens Lifebook S6010 (830) has problems resuming
-	 * from S3 without preserving (some of?) the other bits.
-	 */
-	I915_WRITE(vga_reg, dev_priv->bios_vgacntr | VGA_DISP_DISABLE);
+	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
 	POSTING_READ(vga_reg);
 }
 
@@ -13146,8 +13142,6 @@ void intel_modeset_init(struct drm_device *dev)
 
 	intel_shared_dpll_init(dev);
 
-	/* save the BIOS value before clobbering it */
-	dev_priv->bios_vgacntr = I915_READ(i915_vgacntrl_reg(dev));
 	/* Just disable it once at startup */
 	i915_disable_vga(dev);
 	intel_setup_outputs(dev);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index f5a78d53e297..ac6da7102fbb 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -615,29 +615,6 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 		vlv_power_sequencer_reset(dev_priv);
 }
 
-static void check_power_well_state(struct drm_i915_private *dev_priv,
-				   struct i915_power_well *power_well)
-{
-	bool enabled = power_well->ops->is_enabled(dev_priv, power_well);
-
-	if (power_well->always_on || !i915.disable_power_well) {
-		if (!enabled)
-			goto mismatch;
-
-		return;
-	}
-
-	if (enabled != (power_well->count > 0))
-		goto mismatch;
-
-	return;
-
-mismatch:
-	WARN(1, "state mismatch for '%s' (always_on %d hw state %d use-count %d disable_power_well %d\n",
-		  power_well->name, power_well->always_on, enabled,
-		  power_well->count, i915.disable_power_well);
-}
-
 /**
  * intel_display_power_get - grab a power domain reference
  * @dev_priv: i915 device instance
@@ -669,8 +646,6 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
 			power_well->ops->enable(dev_priv, power_well);
 			power_well->hw_enabled = true;
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	power_domains->domain_use_count[domain]++;
@@ -709,8 +684,6 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 			power_well->hw_enabled = false;
 			power_well->ops->disable(dev_priv, power_well);
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	mutex_unlock(&power_domains->lock);
diff --git a/drivers/gpu/drm/nouveau/core/core/event.c b/drivers/gpu/drm/nouveau/core/core/event.c
index ff2b434b3db4..760947e380c9 100644
--- a/drivers/gpu/drm/nouveau/core/core/event.c
+++ b/drivers/gpu/drm/nouveau/core/core/event.c
@@ -26,7 +26,7 @@
 void
 nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (--event->refs[index * event->types_nr + type] == 0) {
@@ -39,7 +39,7 @@ nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 void
 nvkm_event_get(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (++event->refs[index * event->types_nr + type] == 1) {
diff --git a/drivers/gpu/drm/nouveau/core/core/notify.c b/drivers/gpu/drm/nouveau/core/core/notify.c
index d1bcde55e9d7..839a32577680 100644
--- a/drivers/gpu/drm/nouveau/core/core/notify.c
+++ b/drivers/gpu/drm/nouveau/core/core/notify.c
@@ -98,7 +98,7 @@ nvkm_notify_send(struct nvkm_notify *notify, void *data, u32 size)
 	struct nvkm_event *event = notify->event;
 	unsigned long flags;
 
-	BUG_ON(!spin_is_locked(&event->list_lock));
+	assert_spin_locked(&event->list_lock);
 	BUG_ON(size != notify->size);
 
 	spin_lock_irqsave(&event->refs_lock, flags);
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
index 674da1f095b2..732922690653 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
@@ -249,6 +249,39 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
 		device->oclass[NVDEV_ENGINE_PERFMON] = &nvf0_perfmon_oclass;
 		break;
+	case 0x106:
+		device->cname = "GK208B";
+		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
+		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
+		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
+		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
+		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nvc0_devinit_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  gk20a_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_BUS    ] =  nvc0_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
+		device->oclass[NVDEV_SUBDEV_FB     ] =  nve0_fb_oclass;
+		device->oclass[NVDEV_SUBDEV_LTC    ] =  gk104_ltc_oclass;
+		device->oclass[NVDEV_SUBDEV_IBUS   ] = &nve0_ibus_oclass;
+		device->oclass[NVDEV_SUBDEV_INSTMEM] =  nv50_instmem_oclass;
+		device->oclass[NVDEV_SUBDEV_VM     ] = &nvc0_vmmgr_oclass;
+		device->oclass[NVDEV_SUBDEV_BAR    ] = &nvc0_bar_oclass;
+		device->oclass[NVDEV_SUBDEV_PWR    ] =  nv108_pwr_oclass;
+		device->oclass[NVDEV_SUBDEV_VOLT   ] = &nv40_volt_oclass;
+		device->oclass[NVDEV_ENGINE_DMAOBJ ] =  nvd0_dmaeng_oclass;
+		device->oclass[NVDEV_ENGINE_FIFO   ] =  nv108_fifo_oclass;
+		device->oclass[NVDEV_ENGINE_SW     ] =  nvc0_software_oclass;
+		device->oclass[NVDEV_ENGINE_GR     ] =  nv108_graph_oclass;
+		device->oclass[NVDEV_ENGINE_DISP   ] =  nvf0_disp_oclass;
+		device->oclass[NVDEV_ENGINE_COPY0  ] = &nve0_copy0_oclass;
+		device->oclass[NVDEV_ENGINE_COPY1  ] = &nve0_copy1_oclass;
+		device->oclass[NVDEV_ENGINE_COPY2  ] = &nve0_copy2_oclass;
+		device->oclass[NVDEV_ENGINE_BSP    ] = &nve0_bsp_oclass;
+		device->oclass[NVDEV_ENGINE_VP     ] = &nve0_vp_oclass;
+		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
+		break;
 	case 0x108:
 		device->cname = "GK208";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c b/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c
index 5e58bba0dd5c..a7a890fad1e5 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c
@@ -44,8 +44,10 @@ static void
 pramin_fini(void *data)
 {
 	struct priv *priv = data;
-	nv_wr32(priv->bios, 0x001700, priv->bar0);
-	kfree(priv);
+	if (priv) {
+		nv_wr32(priv->bios, 0x001700, priv->bar0);
+		kfree(priv);
+	}
 }
 
 static void *
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c
index 00f2ca7e44a5..033a8e999497 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c
@@ -24,34 +24,71 @@
 
 #include "nv50.h"
 
+struct nvaa_ram_priv {
+	struct nouveau_ram base;
+	u64 poller_base;
+};
+
 static int
 nvaa_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	      struct nouveau_oclass *oclass, void *data, u32 datasize,
 	      struct nouveau_object **pobject)
 {
-	const u32 rsvd_head = ( 256 * 1024) >> 12; /* vga memory */
-	const u32 rsvd_tail = (1024 * 1024) >> 12; /* vbios etc */
+	u32 rsvd_head = ( 256 * 1024); /* vga memory */
+	u32 rsvd_tail = (1024 * 1024); /* vbios etc */
 	struct nouveau_fb *pfb = nouveau_fb(parent);
-	struct nouveau_ram *ram;
+	struct nvaa_ram_priv *priv;
 	int ret;
 
-	ret = nouveau_ram_create(parent, engine, oclass, &ram);
-	*pobject = nv_object(ram);
+	ret = nouveau_ram_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	ram->size = nv_rd32(pfb, 0x10020c);
-	ram->size = (ram->size & 0xffffff00) | ((ram->size & 0x000000ff) << 32);
+	priv->base.type   = NV_MEM_TYPE_STOLEN;
+	priv->base.stolen = (u64)nv_rd32(pfb, 0x100e10) << 12;
+	priv->base.size   = (u64)nv_rd32(pfb, 0x100e14) << 12;
 
-	ret = nouveau_mm_init(&pfb->vram, rsvd_head, (ram->size >> 12) -
-			      (rsvd_head + rsvd_tail), 1);
+	rsvd_tail += 0x1000;
+	priv->poller_base = priv->base.size - rsvd_tail;
+
+	ret = nouveau_mm_init(&pfb->vram, rsvd_head >> 12,
+			      (priv->base.size  - (rsvd_head + rsvd_tail)) >> 12,
+			      1);
 	if (ret)
 		return ret;
 
-	ram->type   = NV_MEM_TYPE_STOLEN;
-	ram->stolen = (u64)nv_rd32(pfb, 0x100e10) << 12;
-	ram->get = nv50_ram_get;
-	ram->put = nv50_ram_put;
+	priv->base.get = nv50_ram_get;
+	priv->base.put = nv50_ram_put;
+	return 0;
+}
+
+static int
+nvaa_ram_init(struct nouveau_object *object)
+{
+	struct nouveau_fb *pfb = nouveau_fb(object);
+	struct nvaa_ram_priv *priv = (void *)object;
+	int ret;
+	u64 dniso, hostnb, flush;
+
+	ret = nouveau_ram_init(&priv->base);
+	if (ret)
+		return ret;
+
+	dniso  = ((priv->base.size - (priv->poller_base + 0x00)) >> 5) - 1;
+	hostnb = ((priv->base.size - (priv->poller_base + 0x20)) >> 5) - 1;
+	flush  = ((priv->base.size - (priv->poller_base + 0x40)) >> 5) - 1;
+
+	/* Enable NISO poller for various clients and set their associated
+	 * read address, only for MCP77/78 and MCP79/7A. (fd#25701)
+	 */
+	nv_wr32(pfb, 0x100c18, dniso);
+	nv_mask(pfb, 0x100c14, 0x00000000, 0x00000001);
+	nv_wr32(pfb, 0x100c1c, hostnb);
+	nv_mask(pfb, 0x100c14, 0x00000000, 0x00000002);
+	nv_wr32(pfb, 0x100c24, flush);
+	nv_mask(pfb, 0x100c14, 0x00000000, 0x00010000);
+
 	return 0;
 }
 
@@ -60,7 +97,7 @@ nvaa_ram_oclass = {
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nvaa_ram_ctor,
 		.dtor = _nouveau_ram_dtor,
-		.init = _nouveau_ram_init,
+		.init = nvaa_ram_init,
 		.fini = _nouveau_ram_fini,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
index a75c35ccf25c..165401c4045c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
@@ -24,13 +24,6 @@
 
 #include "nv04.h"
 
-static void
-nv4c_mc_msi_rearm(struct nouveau_mc *pmc)
-{
-	struct nv04_mc_priv *priv = (void *)pmc;
-	nv_wr08(priv, 0x088050, 0xff);
-}
-
 struct nouveau_oclass *
 nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 	.base.handle = NV_SUBDEV(MC, 0x4c),
@@ -41,5 +34,4 @@ nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 		.fini = _nouveau_mc_fini,
 	},
 	.intr = nv04_mc_intr,
-	.msi_rearm = nv4c_mc_msi_rearm,
 }.base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 21ec561edc99..bba2960d3dfb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1572,8 +1572,10 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	 * so use the DMA API for them.
 	 */
 	if (!nv_device_is_cpu_coherent(device) &&
-	    ttm->caching_state == tt_uncached)
+	    ttm->caching_state == tt_uncached) {
 		ttm_dma_unpopulate(ttm_dma, dev->dev);
+		return;
+	}
 
 #if __OS_HAS_AGP
 	if (drm->agp.stat == ENABLED) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 42c34babc2e5..bf0f9e21d714 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -36,7 +36,14 @@ void
 nouveau_gem_object_del(struct drm_gem_object *gem)
 {
 	struct nouveau_bo *nvbo = nouveau_gem_object(gem);
+	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct ttm_buffer_object *bo = &nvbo->bo;
+	struct device *dev = drm->dev->dev;
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (WARN_ON(ret < 0 && ret != -EACCES))
+		return;
 
 	if (gem->import_attach)
 		drm_prime_gem_destroy(gem, nvbo->bo.sg);
@@ -46,6 +53,9 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 	/* reset filp so nouveau_bo_del_ttm() can test for it */
 	gem->filp = NULL;
 	ttm_bo_unref(&bo);
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
 }
 
 int
@@ -53,7 +63,9 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_bo *nvbo = nouveau_gem_object(gem);
+	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct nouveau_vma *vma;
+	struct device *dev = drm->dev->dev;
 	int ret;
 
 	if (!cli->vm)
@@ -71,11 +83,16 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv)
 			goto out;
 		}
 
+		ret = pm_runtime_get_sync(dev);
+		if (ret < 0 && ret != -EACCES)
+			goto out;
+
 		ret = nouveau_bo_vma_add(nvbo, cli->vm, vma);
-		if (ret) {
+		if (ret)
 			kfree(vma);
-			goto out;
-		}
+
+		pm_runtime_mark_last_busy(dev);
+		pm_runtime_put_autosuspend(dev);
 	} else {
 		vma->refcount++;
 	}
@@ -129,6 +146,8 @@ nouveau_gem_object_close(struct drm_gem_object *gem, struct drm_file *file_priv)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_bo *nvbo = nouveau_gem_object(gem);
+	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
+	struct device *dev = drm->dev->dev;
 	struct nouveau_vma *vma;
 	int ret;
 
@@ -141,8 +160,14 @@ nouveau_gem_object_close(struct drm_gem_object *gem, struct drm_file *file_priv)
 
 	vma = nouveau_bo_vma_find(nvbo, cli->vm);
 	if (vma) {
-		if (--vma->refcount == 0)
-			nouveau_gem_object_unmap(nvbo, vma);
+		if (--vma->refcount == 0) {
+			ret = pm_runtime_get_sync(dev);
+			if (!WARN_ON(ret < 0 && ret != -EACCES)) {
+				nouveau_gem_object_unmap(nvbo, vma);
+				pm_runtime_mark_last_busy(dev);
+				pm_runtime_put_autosuspend(dev);
+			}
+		}
 	}
 	ttm_bo_unreserve(&nvbo->bo);
 }
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index d59ec491dbb9..ed644a4f6f57 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1851,10 +1851,9 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				return pll;
 		}
 		/* otherwise, pick one of the plls */
-		if ((rdev->family == CHIP_KAVERI) ||
-		    (rdev->family == CHIP_KABINI) ||
+		if ((rdev->family == CHIP_KABINI) ||
 		    (rdev->family == CHIP_MULLINS)) {
-			/* KB/KV/ML has PPLL1 and PPLL2 */
+			/* KB/ML has PPLL1 and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -1863,7 +1862,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 			DRM_ERROR("unable to allocate a PPLL\n");
 			return ATOM_PPLL_INVALID;
 		} else {
-			/* CI has PPLL0, PPLL1, and PPLL2 */
+			/* CI/KV has PPLL0, PPLL1, and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -2155,6 +2154,7 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	case ATOM_PPLL0:
 		/* disable the ppll */
 		if ((rdev->family == CHIP_ARUBA) ||
+		    (rdev->family == CHIP_KAVERI) ||
 		    (rdev->family == CHIP_BONAIRE) ||
 		    (rdev->family == CHIP_HAWAII))
 			atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 11ba9d21b89b..db42a670f995 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -492,6 +492,10 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 	struct radeon_connector_atom_dig *dig_connector;
 	int dp_clock;
 
+	if ((mode->clock > 340000) &&
+	    (!radeon_connector_is_dp12_capable(connector)))
+		return MODE_CLOCK_HIGH;
+
 	if (!radeon_connector->con_priv)
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index ba85986febea..03003f8a6de6 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -2156,4 +2156,6 @@
 #define ATC_VM_APERTURE1_HIGH_ADDR				0x330Cu
 #define ATC_VM_APERTURE1_LOW_ADDR				0x3304u
 
+#define IH_VMID_0_LUT						0x3D40u
+
 #endif
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
index 2fe8cfc966d9..bafdf92a5732 100644
--- a/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -103,7 +103,7 @@ static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 		return;
 	}
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 9b42001295ba..e3e9c10cfba9 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2745,13 +2745,11 @@ int kv_dpm_init(struct radeon_device *rdev)
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
 	if (radeon_bapm == -1) {
-		/* There are stability issues reported on with
-		 * bapm enabled on an asrock system.
-		 */
-		if (rdev->pdev->subsystem_vendor == 0x1849)
-			pi->bapm_enable = false;
-		else
+		/* only enable bapm on KB, ML by default */
+		if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 			pi->bapm_enable = true;
+		else
+			pi->bapm_enable = false;
 	} else if (radeon_bapm == 0) {
 		pi->bapm_enable = false;
 	} else {
diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c
index 242fd8b1b221..8bf87f1203cc 100644
--- a/drivers/gpu/drm/radeon/radeon_kfd.c
+++ b/drivers/gpu/drm/radeon/radeon_kfd.c
@@ -72,7 +72,7 @@ static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr);
 
-static bool kgd_hqd_is_occupies(struct kgd_dev *kgd, uint64_t queue_address,
+static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id);
 
 static int kgd_hqd_destroy(struct kgd_dev *kgd, uint32_t reset_type,
@@ -92,7 +92,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.init_memory = kgd_init_memory,
 	.init_pipeline = kgd_init_pipeline,
 	.hqd_load = kgd_hqd_load,
-	.hqd_is_occupies = kgd_hqd_is_occupies,
+	.hqd_is_occupied = kgd_hqd_is_occupied,
 	.hqd_destroy = kgd_hqd_destroy,
 	.get_fw_version = get_fw_version
 };
@@ -101,6 +101,7 @@ static const struct kgd2kfd_calls *kgd2kfd;
 
 bool radeon_kfd_init(void)
 {
+#if defined(CONFIG_HSA_AMD_MODULE)
 	bool (*kgd2kfd_init_p)(unsigned, const struct kfd2kgd_calls*,
 				const struct kgd2kfd_calls**);
 
@@ -117,6 +118,17 @@ bool radeon_kfd_init(void)
 	}
 
 	return true;
+#elif defined(CONFIG_HSA_AMD)
+	if (!kgd2kfd_init(KFD_INTERFACE_VERSION, &kfd2kgd, &kgd2kfd)) {
+		kgd2kfd = NULL;
+
+		return false;
+	}
+
+	return true;
+#else
+	return false;
+#endif
 }
 
 void radeon_kfd_fini(void)
@@ -378,6 +390,10 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 		cpu_relax();
 	write_register(kgd, ATC_VMID_PASID_MAPPING_UPDATE_STATUS, 1U << vmid);
 
+	/* Mapping vmid to pasid also for IH block */
+	write_register(kgd, IH_VMID_0_LUT + vmid * sizeof(uint32_t),
+			pasid_mapping);
+
 	return 0;
 }
 
@@ -517,7 +533,7 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
-static bool kgd_hqd_is_occupies(struct kgd_dev *kgd, uint64_t queue_address,
+static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id)
 {
 	uint32_t act;
@@ -556,6 +572,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, uint32_t reset_type,
 		if (timeout == 0) {
 			pr_err("kfd: cp queue preemption time out (%dms)\n",
 				temp);
+			release_queue(kgd);
 			return -ETIME;
 		}
 		msleep(20);
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 535403e0c8a2..15aee723db77 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -1703,7 +1703,7 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 	u32 format;
 	u32 *buffer;
 	const u8 __user *data;
-	int size, dwords, tex_width, blit_width, spitch;
+	unsigned int size, dwords, tex_width, blit_width, spitch;
 	u32 height;
 	int i;
 	u32 texpitch, microtile;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 230b6f887cd8..dfdc26970022 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -27,7 +27,8 @@ if HID
 
 config HID_BATTERY_STRENGTH
 	bool "Battery level reporting for HID devices"
-	depends on HID && POWER_SUPPLY && HID = POWER_SUPPLY
+	depends on HID
+	select POWER_SUPPLY
 	default n
 	---help---
 	This option adds support of reporting battery strength (for HID devices
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index c3d0ac1a0988..8b638792cb43 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1805,6 +1805,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 7460f3402298..9243359c1821 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -526,6 +526,7 @@
 #define USB_DEVICE_ID_KYE_GPEN_560	0x5003
 #define USB_DEVICE_ID_KYE_EASYPEN_I405X	0x5010
 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X	0x5011
+#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2	0x501a
 #define USB_DEVICE_ID_KYE_EASYPEN_M610X	0x5013
 
 #define USB_VENDOR_ID_LABTEC		0x1020
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index e0a0f06ac5ef..9505605b6e22 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -312,6 +312,9 @@ static const struct hid_device_id hid_battery_quirks[] = {
 			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{}
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index b92bf01a1ae8..158fcf577fae 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -323,6 +323,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		}
 		break;
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 		if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) {
 			rdesc = mousepen_i608x_rdesc_fixed;
 			*rsize = sizeof(mousepen_i608x_rdesc_fixed);
@@ -415,6 +416,7 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	switch (id->product) {
 	case USB_DEVICE_ID_KYE_EASYPEN_I405X:
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 	case USB_DEVICE_ID_KYE_EASYPEN_M610X:
 		ret = kye_tablet_enable(hdev);
 		if (ret) {
@@ -446,6 +448,8 @@ static const struct hid_device_id kye_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+				USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) },
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index c917ab61aafa..5bc6d80d5be7 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -962,10 +962,24 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 
 	switch (data[0]) {
 	case REPORT_ID_DJ_SHORT:
+		if (size != DJREPORT_SHORT_LENGTH) {
+			dev_err(&hdev->dev, "DJ report of bad size (%d)", size);
+			return false;
+		}
 		return logi_dj_dj_event(hdev, report, data, size);
 	case REPORT_ID_HIDPP_SHORT:
-		/* intentional fallthrough */
+		if (size != HIDPP_REPORT_SHORT_LENGTH) {
+			dev_err(&hdev->dev,
+				"Short HID++ report of bad size (%d)", size);
+			return false;
+		}
+		return logi_dj_hidpp_event(hdev, report, data, size);
 	case REPORT_ID_HIDPP_LONG:
+		if (size != HIDPP_REPORT_LONG_LENGTH) {
+			dev_err(&hdev->dev,
+				"Long HID++ report of bad size (%d)", size);
+			return false;
+		}
 		return logi_dj_hidpp_event(hdev, report, data, size);
 	}
 
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 2f420c0b6609..a93cefe0e522 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -282,6 +282,33 @@ static inline bool hidpp_report_is_connect_event(struct hidpp_report *report)
 		(report->rap.sub_id == 0x41);
 }
 
+/**
+ * hidpp_prefix_name() prefixes the current given name with "Logitech ".
+ */
+static void hidpp_prefix_name(char **name, int name_length)
+{
+#define PREFIX_LENGTH 9 /* "Logitech " */
+
+	int new_length;
+	char *new_name;
+
+	if (name_length > PREFIX_LENGTH &&
+	    strncmp(*name, "Logitech ", PREFIX_LENGTH) == 0)
+		/* The prefix has is already in the name */
+		return;
+
+	new_length = PREFIX_LENGTH + name_length;
+	new_name = kzalloc(new_length, GFP_KERNEL);
+	if (!new_name)
+		return;
+
+	snprintf(new_name, new_length, "Logitech %s", *name);
+
+	kfree(*name);
+
+	*name = new_name;
+}
+
 /* -------------------------------------------------------------------------- */
 /* HIDP++ 1.0 commands                                                        */
 /* -------------------------------------------------------------------------- */
@@ -321,6 +348,10 @@ static char *hidpp_get_unifying_name(struct hidpp_device *hidpp_dev)
 		return NULL;
 
 	memcpy(name, &response.rap.params[2], len);
+
+	/* include the terminating '\0' */
+	hidpp_prefix_name(&name, len + 1);
+
 	return name;
 }
 
@@ -498,6 +529,9 @@ static char *hidpp_get_device_name(struct hidpp_device *hidpp)
 		index += ret;
 	}
 
+	/* include the terminating '\0' */
+	hidpp_prefix_name(&name, __name_length + 1);
+
 	return name;
 }
 
@@ -794,18 +828,25 @@ static int wtp_raw_event(struct hid_device *hdev, u8 *data, int size)
 
 	switch (data[0]) {
 	case 0x02:
+		if (size < 2) {
+			hid_err(hdev, "Received HID report of bad size (%d)",
+				size);
+			return 1;
+		}
 		if (hidpp->quirks & HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS) {
 			input_event(wd->input, EV_KEY, BTN_LEFT,
 					!!(data[1] & 0x01));
 			input_event(wd->input, EV_KEY, BTN_RIGHT,
 					!!(data[1] & 0x02));
 			input_sync(wd->input);
+			return 0;
 		} else {
 			if (size < 21)
 				return 1;
 			return wtp_mouse_raw_xy_event(hidpp, &data[7]);
 		}
 	case REPORT_ID_HIDPP_LONG:
+		/* size is already checked in hidpp_raw_event. */
 		if ((report->fap.feature_index != wd->mt_feature_index) ||
 		    (report->fap.funcindex_clientid != EVENT_TOUCHPAD_RAW_XY))
 			return 1;
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index 1a07e07d99a0..47d7e74231e5 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -35,6 +35,8 @@ static struct class *pyra_class;
 static void profile_activated(struct pyra_device *pyra,
 		unsigned int new_profile)
 {
+	if (new_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return;
 	pyra->actual_profile = new_profile;
 	pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi;
 }
@@ -257,9 +259,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp,
 	if (off != 0 || count != PYRA_SIZE_SETTINGS)
 		return -EINVAL;
 
-	mutex_lock(&pyra->pyra_lock);
-
 	settings = (struct pyra_settings const *)buf;
+	if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return -EINVAL;
+
+	mutex_lock(&pyra->pyra_lock);
 
 	retval = pyra_set_settings(usb_dev, settings);
 	if (retval) {
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index d32037cbf9db..d43e967e7533 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -706,12 +706,7 @@ static int i2c_hid_start(struct hid_device *hid)
 
 static void i2c_hid_stop(struct hid_device *hid)
 {
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-
 	hid->claimed = 0;
-
-	i2c_hid_free_buffers(ihid);
 }
 
 static int i2c_hid_open(struct hid_device *hid)
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index dc89be90b35e..b27b3d33ebab 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -124,6 +124,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1232336b960e..40dfbc0444c0 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4029,14 +4029,6 @@ static int device_notifier(struct notifier_block *nb,
 	if (action != BUS_NOTIFY_REMOVED_DEVICE)
 		return 0;
 
-	/*
-	 * If the device is still attached to a device driver we can't
-	 * tear down the domain yet as DMA mappings may still be in use.
-	 * Wait for the BUS_NOTIFY_UNBOUND_DRIVER event to do that.
-	 */
-	if (action == BUS_NOTIFY_DEL_DEVICE && dev->driver != NULL)
-		return 0;
-
 	domain = find_domain(dev);
 	if (!domain)
 		return 0;
@@ -4428,6 +4420,10 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 				domain_remove_one_dev_info(old_domain, dev);
 			else
 				domain_remove_dev_info(old_domain);
+
+			if (!domain_type_is_vm_or_si(old_domain) &&
+			     list_empty(&old_domain->devices))
+				domain_exit(old_domain);
 		}
 	}
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 68dfb0fd5ee9..748693192c20 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -558,7 +558,7 @@ static pmd_t *ipmmu_alloc_pmd(struct ipmmu_vmsa_device *mmu, pgd_t *pgd,
 
 static u64 ipmmu_page_prot(unsigned int prot, u64 type)
 {
-	u64 pgprot = ARM_VMSA_PTE_XN | ARM_VMSA_PTE_nG | ARM_VMSA_PTE_AF
+	u64 pgprot = ARM_VMSA_PTE_nG | ARM_VMSA_PTE_AF
 		   | ARM_VMSA_PTE_SH_IS | ARM_VMSA_PTE_AP_UNPRIV
 		   | ARM_VMSA_PTE_NS | type;
 
@@ -568,8 +568,8 @@ static u64 ipmmu_page_prot(unsigned int prot, u64 type)
 	if (prot & IOMMU_CACHE)
 		pgprot |= IMMAIR_ATTR_IDX_WBRWA << ARM_VMSA_PTE_ATTRINDX_SHIFT;
 
-	if (prot & IOMMU_EXEC)
-		pgprot &= ~ARM_VMSA_PTE_XN;
+	if (prot & IOMMU_NOEXEC)
+		pgprot |= ARM_VMSA_PTE_XN;
 	else if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
 		/* If no access create a faulting entry to avoid TLB fills. */
 		pgprot &= ~ARM_VMSA_PTE_PAGE;
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index b2023af384b9..6a8b1ec4a48a 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -1009,7 +1009,6 @@ static struct platform_driver rk_iommu_driver = {
 	.remove = rk_iommu_remove,
 	.driver = {
 		   .name = "rk_iommu",
-		   .owner = THIS_MODULE,
 		   .of_match_table = of_match_ptr(rk_iommu_dt_ids),
 	},
 };
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index a82e542ffc21..0b380603a578 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -4880,7 +4880,7 @@ static void sig_ind(PLCI *plci)
 	byte SS_Ind[] = "\x05\x02\x00\x02\x00\x00"; /* Hold_Ind struct*/
 	byte CF_Ind[] = "\x09\x02\x00\x06\x00\x00\x00\x00\x00\x00";
 	byte Interr_Err_Ind[] = "\x0a\x02\x00\x07\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00";
-	byte CONF_Ind[] = "\x09\x16\x00\x06\x00\x00\0x00\0x00\0x00\0x00";
+	byte CONF_Ind[] = "\x09\x16\x00\x06\x00\x00\x00\x00\x00\x00";
 	byte force_mt_info = false;
 	byte dir;
 	dword d;
diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c
index 26515c27ea8c..25e419752a7b 100644
--- a/drivers/leds/leds-netxbig.c
+++ b/drivers/leds/leds-netxbig.c
@@ -330,18 +330,18 @@ create_netxbig_led(struct platform_device *pdev,
 	led_dat->sata = 0;
 	led_dat->cdev.brightness = LED_OFF;
 	led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
-	/*
-	 * If available, expose the SATA activity blink capability through
-	 * a "sata" sysfs attribute.
-	 */
-	if (led_dat->mode_val[NETXBIG_LED_SATA] != NETXBIG_LED_INVALID_MODE)
-		led_dat->cdev.groups = netxbig_led_groups;
 	led_dat->mode_addr = template->mode_addr;
 	led_dat->mode_val = template->mode_val;
 	led_dat->bright_addr = template->bright_addr;
 	led_dat->bright_max = (1 << pdata->gpio_ext->num_data) - 1;
 	led_dat->timer = pdata->timer;
 	led_dat->num_timer = pdata->num_timer;
+	/*
+	 * If available, expose the SATA activity blink capability through
+	 * a "sata" sysfs attribute.
+	 */
+	if (led_dat->mode_val[NETXBIG_LED_SATA] != NETXBIG_LED_INVALID_MODE)
+		led_dat->cdev.groups = netxbig_led_groups;
 
 	return led_classdev_register(&pdev->dev, &led_dat->cdev);
 }
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index e3e56d35f0ee..970314e0aac8 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -247,6 +247,7 @@ static const struct sdhci_acpi_uid_slot sdhci_acpi_uids[] = {
 	{ "INT33BB"  , "3" , &sdhci_acpi_slot_int_sd },
 	{ "INT33C6"  , NULL, &sdhci_acpi_slot_int_sdio },
 	{ "INT3436"  , NULL, &sdhci_acpi_slot_int_sdio },
+	{ "INT344D"  , NULL, &sdhci_acpi_slot_int_sdio },
 	{ "PNP0D40"  },
 	{ },
 };
@@ -257,6 +258,7 @@ static const struct acpi_device_id sdhci_acpi_ids[] = {
 	{ "INT33BB"  },
 	{ "INT33C6"  },
 	{ "INT3436"  },
+	{ "INT344D"  },
 	{ "PNP0D40"  },
 	{ },
 };
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 03427755b902..4f38554ce679 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -993,6 +993,31 @@ static const struct pci_device_id pci_ids[] = {
 		.subdevice	= PCI_ANY_ID,
 		.driver_data	= (kernel_ulong_t)&sdhci_intel_mrfl_mmc,
 	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_SPT_EMMC,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_SPT_SDIO,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sdio,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_SPT_SD,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sd,
+	},
+
 	{
 		.vendor		= PCI_VENDOR_ID_O2,
 		.device		= PCI_DEVICE_ID_O2_8120,
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index d57c3d169914..1ec684d06d54 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -21,6 +21,9 @@
 #define PCI_DEVICE_ID_INTEL_CLV_EMMC0	0x08e5
 #define PCI_DEVICE_ID_INTEL_CLV_EMMC1	0x08e6
 #define PCI_DEVICE_ID_INTEL_QRK_SD	0x08A7
+#define PCI_DEVICE_ID_INTEL_SPT_EMMC	0x9d2b
+#define PCI_DEVICE_ID_INTEL_SPT_SDIO	0x9d2c
+#define PCI_DEVICE_ID_INTEL_SPT_SD	0x9d2d
 
 /*
  * PCI registers
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 45238871192d..ca3424e7ef71 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -300,13 +300,6 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
-	if (of_device_is_compatible(np, "marvell,armada-380-sdhci")) {
-		ret = mv_conf_mbus_windows(pdev, mv_mbus_dram_info());
-		if (ret < 0)
-			goto err_mbus_win;
-	}
-
-
 	pltfm_host = sdhci_priv(host);
 	pltfm_host->priv = pxa;
 
@@ -325,6 +318,12 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	if (!IS_ERR(pxa->clk_core))
 		clk_prepare_enable(pxa->clk_core);
 
+	if (of_device_is_compatible(np, "marvell,armada-380-sdhci")) {
+		ret = mv_conf_mbus_windows(pdev, mv_mbus_dram_info());
+		if (ret < 0)
+			goto err_mbus_win;
+	}
+
 	/* enable 1/8V DDR capable */
 	host->mmc->caps |= MMC_CAP_1_8V_DDR;
 
@@ -396,11 +395,11 @@ err_add_host:
 	pm_runtime_disable(&pdev->dev);
 err_of_parse:
 err_cd_req:
+err_mbus_win:
 	clk_disable_unprepare(pxa->clk_io);
 	if (!IS_ERR(pxa->clk_core))
 		clk_disable_unprepare(pxa->clk_core);
 err_clk_get:
-err_mbus_win:
 	sdhci_pltfm_free(pdev);
 	return ret;
 }
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index cbb245b58538..1453cd127921 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -259,8 +259,6 @@ static void sdhci_reinit(struct sdhci_host *host)
 
 		del_timer_sync(&host->tuning_timer);
 		host->flags &= ~SDHCI_NEEDS_RETUNING;
-		host->mmc->max_blk_count =
-			(host->quirks & SDHCI_QUIRK_NO_MULTIBLOCK) ? 1 : 65535;
 	}
 	sdhci_enable_card_detection(host);
 }
@@ -1353,6 +1351,8 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	sdhci_runtime_pm_get(host);
 
+	present = mmc_gpio_get_cd(host->mmc);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	WARN_ON(host->mrq != NULL);
@@ -1381,7 +1381,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	 *     zero: cd-gpio is used, and card is removed
 	 *     one: cd-gpio is used, and card is present
 	 */
-	present = mmc_gpio_get_cd(host->mmc);
 	if (present < 0) {
 		/* If polling, assume that the card is always present. */
 		if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
@@ -1880,6 +1879,18 @@ static int sdhci_card_busy(struct mmc_host *mmc)
 	return !(present_state & SDHCI_DATA_LVL_MASK);
 }
 
+static int sdhci_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+	host->flags |= SDHCI_HS400_TUNING;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	return 0;
+}
+
 static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
@@ -1887,10 +1898,18 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	int tuning_loop_counter = MAX_TUNING_LOOP;
 	int err = 0;
 	unsigned long flags;
+	unsigned int tuning_count = 0;
+	bool hs400_tuning;
 
 	sdhci_runtime_pm_get(host);
 	spin_lock_irqsave(&host->lock, flags);
 
+	hs400_tuning = host->flags & SDHCI_HS400_TUNING;
+	host->flags &= ~SDHCI_HS400_TUNING;
+
+	if (host->tuning_mode == SDHCI_TUNING_MODE_1)
+		tuning_count = host->tuning_count;
+
 	/*
 	 * The Host Controller needs tuning only in case of SDR104 mode
 	 * and for SDR50 mode when Use Tuning for SDR50 is set in the
@@ -1899,8 +1918,20 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	 * tuning function has to be executed.
 	 */
 	switch (host->timing) {
+	/* HS400 tuning is done in HS200 mode */
 	case MMC_TIMING_MMC_HS400:
+		err = -EINVAL;
+		goto out_unlock;
+
 	case MMC_TIMING_MMC_HS200:
+		/*
+		 * Periodic re-tuning for HS400 is not expected to be needed, so
+		 * disable it here.
+		 */
+		if (hs400_tuning)
+			tuning_count = 0;
+		break;
+
 	case MMC_TIMING_UHS_SDR104:
 		break;
 
@@ -1911,9 +1942,7 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		/* FALLTHROUGH */
 
 	default:
-		spin_unlock_irqrestore(&host->lock, flags);
-		sdhci_runtime_pm_put(host);
-		return 0;
+		goto out_unlock;
 	}
 
 	if (host->ops->platform_execute_tuning) {
@@ -2037,24 +2066,11 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	}
 
 out:
-	/*
-	 * If this is the very first time we are here, we start the retuning
-	 * timer. Since only during the first time, SDHCI_NEEDS_RETUNING
-	 * flag won't be set, we check this condition before actually starting
-	 * the timer.
-	 */
-	if (!(host->flags & SDHCI_NEEDS_RETUNING) && host->tuning_count &&
-	    (host->tuning_mode == SDHCI_TUNING_MODE_1)) {
+	host->flags &= ~SDHCI_NEEDS_RETUNING;
+
+	if (tuning_count) {
 		host->flags |= SDHCI_USING_RETUNING_TIMER;
-		mod_timer(&host->tuning_timer, jiffies +
-			host->tuning_count * HZ);
-		/* Tuning mode 1 limits the maximum data length to 4MB */
-		mmc->max_blk_count = (4 * 1024 * 1024) / mmc->max_blk_size;
-	} else if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-		/* Reload the new initial value for timer */
-		mod_timer(&host->tuning_timer, jiffies +
-			  host->tuning_count * HZ);
+		mod_timer(&host->tuning_timer, jiffies + tuning_count * HZ);
 	}
 
 	/*
@@ -2070,6 +2086,7 @@ out:
 
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+out_unlock:
 	spin_unlock_irqrestore(&host->lock, flags);
 	sdhci_runtime_pm_put(host);
 
@@ -2110,15 +2127,18 @@ static void sdhci_card_event(struct mmc_host *mmc)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	unsigned long flags;
+	int present;
 
 	/* First check if client has provided their own card event */
 	if (host->ops->card_event)
 		host->ops->card_event(host);
 
+	present = sdhci_do_get_cd(host);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	/* Check host->mrq first in case we are runtime suspended */
-	if (host->mrq && !sdhci_do_get_cd(host)) {
+	if (host->mrq && !present) {
 		pr_err("%s: Card removed during transfer!\n",
 			mmc_hostname(host->mmc));
 		pr_err("%s: Resetting controller.\n",
@@ -2142,6 +2162,7 @@ static const struct mmc_host_ops sdhci_ops = {
 	.hw_reset	= sdhci_hw_reset,
 	.enable_sdio_irq = sdhci_enable_sdio_irq,
 	.start_signal_voltage_switch	= sdhci_start_signal_voltage_switch,
+	.prepare_hs400_tuning		= sdhci_prepare_hs400_tuning,
 	.execute_tuning			= sdhci_execute_tuning,
 	.card_event			= sdhci_card_event,
 	.card_busy	= sdhci_card_busy,
@@ -3260,8 +3281,9 @@ int sdhci_add_host(struct sdhci_host *host)
 		mmc->max_segs = SDHCI_MAX_SEGS;
 
 	/*
-	 * Maximum number of sectors in one transfer. Limited by DMA boundary
-	 * size (512KiB).
+	 * Maximum number of sectors in one transfer. Limited by SDMA boundary
+	 * size (512KiB). Note some tuning modes impose a 4MiB limit, but this
+	 * is less anyway.
 	 */
 	mmc->max_req_size = 524288;
 
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e398eda07298..c8af3ce3ea38 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -184,15 +184,16 @@ static void alx_schedule_reset(struct alx_priv *alx)
 	schedule_work(&alx->reset_wk);
 }
 
-static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
+static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
 	struct alx_rrd *rrd;
 	struct alx_buffer *rxb;
 	struct sk_buff *skb;
 	u16 length, rfd_cleaned = 0;
+	int work = 0;
 
-	while (budget > 0) {
+	while (work < budget) {
 		rrd = &rxq->rrd[rxq->rrd_read_idx];
 		if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT)))
 			break;
@@ -203,7 +204,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
 		    ALX_GET_FIELD(le32_to_cpu(rrd->word0),
 				  RRD_NOR) != 1) {
 			alx_schedule_reset(alx);
-			return 0;
+			return work;
 		}
 
 		rxb = &rxq->bufs[rxq->read_idx];
@@ -243,7 +244,7 @@ static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
 		}
 
 		napi_gro_receive(&alx->napi, skb);
-		budget--;
+		work++;
 
 next_pkt:
 		if (++rxq->read_idx == alx->rx_ringsz)
@@ -258,21 +259,22 @@ next_pkt:
 	if (rfd_cleaned)
 		alx_refill_rx_ring(alx, GFP_ATOMIC);
 
-	return budget > 0;
+	return work;
 }
 
 static int alx_poll(struct napi_struct *napi, int budget)
 {
 	struct alx_priv *alx = container_of(napi, struct alx_priv, napi);
 	struct alx_hw *hw = &alx->hw;
-	bool complete = true;
 	unsigned long flags;
+	bool tx_complete;
+	int work;
 
-	complete = alx_clean_tx_irq(alx) &&
-		   alx_clean_rx_irq(alx, budget);
+	tx_complete = alx_clean_tx_irq(alx);
+	work = alx_clean_rx_irq(alx, budget);
 
-	if (!complete)
-		return 1;
+	if (!tx_complete || work == budget)
+		return budget;
 
 	napi_complete(&alx->napi);
 
@@ -284,7 +286,7 @@ static int alx_poll(struct napi_struct *napi, int budget)
 
 	alx_post_write(hw);
 
-	return 0;
+	return work;
 }
 
 static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 4cf43bfbc955..615a6dbde047 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7413,6 +7413,8 @@ static inline void tg3_netif_start(struct tg3 *tp)
 }
 
 static void tg3_irq_quiesce(struct tg3 *tp)
+	__releases(tp->lock)
+	__acquires(tp->lock)
 {
 	int i;
 
@@ -7421,8 +7423,12 @@ static void tg3_irq_quiesce(struct tg3 *tp)
 	tp->irq_sync = 1;
 	smp_mb();
 
+	spin_unlock_bh(&tp->lock);
+
 	for (i = 0; i < tp->irq_cnt; i++)
 		synchronize_irq(tp->napi[i].irq_vec);
+
+	spin_lock_bh(&tp->lock);
 }
 
 /* Fully shutdown all tg3 driver activity elsewhere in the system.
@@ -9018,6 +9024,8 @@ static void tg3_restore_clk(struct tg3 *tp)
 
 /* tp->lock is held. */
 static int tg3_chip_reset(struct tg3 *tp)
+	__releases(tp->lock)
+	__acquires(tp->lock)
 {
 	u32 val;
 	void (*write_op)(struct tg3 *, u32, u32);
@@ -9073,9 +9081,13 @@ static int tg3_chip_reset(struct tg3 *tp)
 	}
 	smp_mb();
 
+	tg3_full_unlock(tp);
+
 	for (i = 0; i < tp->irq_cnt; i++)
 		synchronize_irq(tp->napi[i].irq_vec);
 
+	tg3_full_lock(tp, 0);
+
 	if (tg3_asic_rev(tp) == ASIC_REV_57780) {
 		val = tr32(TG3_PCIE_LNKCTL) & ~TG3_PCIE_LNKCTL_L1_PLL_PD_EN;
 		tw32(TG3_PCIE_LNKCTL, val | TG3_PCIE_LNKCTL_L1_PLL_PD_DIS);
@@ -10903,11 +10915,13 @@ static void tg3_timer(unsigned long __opaque)
 {
 	struct tg3 *tp = (struct tg3 *) __opaque;
 
-	if (tp->irq_sync || tg3_flag(tp, RESET_TASK_PENDING))
-		goto restart_timer;
-
 	spin_lock(&tp->lock);
 
+	if (tp->irq_sync || tg3_flag(tp, RESET_TASK_PENDING)) {
+		spin_unlock(&tp->lock);
+		goto restart_timer;
+	}
+
 	if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
 	    tg3_flag(tp, 57765_CLASS))
 		tg3_chk_missed_msi(tp);
@@ -11101,11 +11115,13 @@ static void tg3_reset_task(struct work_struct *work)
 	struct tg3 *tp = container_of(work, struct tg3, reset_task);
 	int err;
 
+	rtnl_lock();
 	tg3_full_lock(tp, 0);
 
 	if (!netif_running(tp->dev)) {
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
 		tg3_full_unlock(tp);
+		rtnl_unlock();
 		return;
 	}
 
@@ -11138,6 +11154,7 @@ out:
 		tg3_phy_start(tp);
 
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
+	rtnl_unlock();
 }
 
 static int tg3_request_irq(struct tg3 *tp, int irq_num)
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index 55eb7f2af2b4..7ef55f5fa664 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -340,7 +340,7 @@ static int __init at91ether_probe(struct platform_device *pdev)
 		res = PTR_ERR(lp->pclk);
 		goto err_free_dev;
 	}
-	clk_enable(lp->pclk);
+	clk_prepare_enable(lp->pclk);
 
 	lp->hclk = ERR_PTR(-ENOENT);
 	lp->tx_clk = ERR_PTR(-ENOENT);
@@ -406,7 +406,7 @@ static int __init at91ether_probe(struct platform_device *pdev)
 err_out_unregister_netdev:
 	unregister_netdev(dev);
 err_disable_clock:
-	clk_disable(lp->pclk);
+	clk_disable_unprepare(lp->pclk);
 err_free_dev:
 	free_netdev(dev);
 	return res;
@@ -424,7 +424,7 @@ static int at91ether_remove(struct platform_device *pdev)
 	kfree(lp->mii_bus->irq);
 	mdiobus_free(lp->mii_bus);
 	unregister_netdev(dev);
-	clk_disable(lp->pclk);
+	clk_disable_unprepare(lp->pclk);
 	free_netdev(dev);
 
 	return 0;
@@ -440,7 +440,7 @@ static int at91ether_suspend(struct platform_device *pdev, pm_message_t mesg)
 		netif_stop_queue(net_dev);
 		netif_device_detach(net_dev);
 
-		clk_disable(lp->pclk);
+		clk_disable_unprepare(lp->pclk);
 	}
 	return 0;
 }
@@ -451,7 +451,7 @@ static int at91ether_resume(struct platform_device *pdev)
 	struct macb *lp = netdev_priv(net_dev);
 
 	if (netif_running(net_dev)) {
-		clk_enable(lp->pclk);
+		clk_prepare_enable(lp->pclk);
 
 		netif_device_attach(net_dev);
 		netif_start_queue(net_dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 710e5e2bac9f..122e2964e63b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2426,7 +2426,7 @@ static void cfg_queues(struct adapter *adapter)
 	 */
 	n10g = 0;
 	for_each_port(adapter, pidx)
-		n10g += is_10g_port(&adap2pinfo(adapter, pidx)->link_cfg);
+		n10g += is_x_10g_port(&adap2pinfo(adapter, pidx)->link_cfg);
 
 	/*
 	 * We default to 1 queue per non-10G port and up to # of cores queues
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index fcc610813856..1b5506df35b1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -324,6 +324,8 @@ int t4vf_port_init(struct adapter *adapter, int pidx)
 		return v;
 
 	v = be32_to_cpu(port_rpl.u.info.lstatus_to_modtype);
+	pi->mdio_addr = (v & FW_PORT_CMD_MDIOCAP_F) ?
+			FW_PORT_CMD_MDIOADDR_G(v) : -1;
 	pi->port_type = FW_PORT_CMD_PTYPE_G(v);
 	pi->mod_type = FW_PORT_MOD_TYPE_NA;
 
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index a379c3e4b57f..13d00a38a5bd 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -398,13 +398,8 @@ static int dnet_poll(struct napi_struct *napi, int budget)
 		 * break out of while loop if there are no more
 		 * packets waiting
 		 */
-		if (!(dnet_readl(bp, RX_FIFO_WCNT) >> 16)) {
-			napi_complete(napi);
-			int_enable = dnet_readl(bp, INTR_ENB);
-			int_enable |= DNET_INTR_SRC_RX_CMDFIFOAF;
-			dnet_writel(bp, int_enable, INTR_ENB);
-			return 0;
-		}
+		if (!(dnet_readl(bp, RX_FIFO_WCNT) >> 16))
+			break;
 
 		cmd_word = dnet_readl(bp, RX_LEN_FIFO);
 		pkt_len = cmd_word & 0xFFFF;
@@ -433,20 +428,17 @@ static int dnet_poll(struct napi_struct *napi, int budget)
 			       "size %u.\n", dev->name, pkt_len);
 	}
 
-	budget -= npackets;
-
 	if (npackets < budget) {
 		/* We processed all packets available.  Tell NAPI it can
-		 * stop polling then re-enable rx interrupts */
+		 * stop polling then re-enable rx interrupts.
+		 */
 		napi_complete(napi);
 		int_enable = dnet_readl(bp, INTR_ENB);
 		int_enable |= DNET_INTR_SRC_RX_CMDFIFOAF;
 		dnet_writel(bp, int_enable, INTR_ENB);
-		return 0;
 	}
 
-	/* There are still packets waiting */
-	return 1;
+	return npackets;
 }
 
 static irqreturn_t dnet_interrupt(int irq, void *dev_id)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index d77a96fdf1dd..a86af8a7485d 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -426,6 +426,8 @@ struct bufdesc_ex {
  * (40ns * 6).
  */
 #define FEC_QUIRK_BUG_CAPTURE		(1 << 10)
+/* Controller has only one MDIO bus */
+#define FEC_QUIRK_SINGLE_MDIO		(1 << 11)
 
 struct fec_enet_priv_tx_q {
 	int index;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 49cd358c30fa..1c7a7e43dd9c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -91,7 +91,8 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = 0,
 	}, {
 		.name = "imx28-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME,
+		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
+				FEC_QUIRK_SINGLE_MDIO,
 	}, {
 		.name = "imx6q-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
@@ -1956,7 +1957,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	int err = -ENXIO, i;
 
 	/*
-	 * The dual fec interfaces are not equivalent with enet-mac.
+	 * The i.MX28 dual fec interfaces are not equal.
 	 * Here are the differences:
 	 *
 	 *  - fec0 supports MII & RMII modes while fec1 only supports RMII
@@ -1971,7 +1972,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	 * mdio interface in board design, and need to be configured by
 	 * fec0 mii_bus.
 	 */
-	if ((fep->quirks & FEC_QUIRK_ENET_MAC) && fep->dev_id > 0) {
+	if ((fep->quirks & FEC_QUIRK_SINGLE_MDIO) && fep->dev_id > 0) {
 		/* fec1 uses fec0 mii_bus */
 		if (mii_cnt && fec0_mii_bus) {
 			fep->mii_bus = fec0_mii_bus;
@@ -2034,7 +2035,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	mii_cnt++;
 
 	/* save fec0 mii_bus */
-	if (fep->quirks & FEC_QUIRK_ENET_MAC)
+	if (fep->quirks & FEC_QUIRK_SINGLE_MDIO)
 		fec0_mii_bus = fep->mii_bus;
 
 	return 0;
@@ -3191,6 +3192,7 @@ fec_probe(struct platform_device *pdev)
 		pdev->id_entry = of_id->data;
 	fep->quirks = pdev->id_entry->driver_data;
 
+	fep->netdev = ndev;
 	fep->num_rx_queues = num_rx_qs;
 	fep->num_tx_queues = num_tx_qs;
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 5b8300a32bf5..4d61ef50b465 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -281,6 +281,17 @@ config I40E_DCB
 
 	  If unsure, say N.
 
+config I40E_FCOE
+	bool "Fibre Channel over Ethernet (FCoE)"
+	default n
+	depends on I40E && DCB && FCOE
+	---help---
+	  Say Y here if you want to use Fibre Channel over Ethernet (FCoE)
+	  in the driver. This will create new netdev for exclusive FCoE
+	  use with XL710 FCoE offloads enabled.
+
+	  If unsure, say N.
+
 config I40EVF
 	tristate "Intel(R) XL710 X710 Virtual Function Ethernet support"
 	depends on PCI_MSI
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 4b94ddb29c24..c40581999121 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -44,4 +44,4 @@ i40e-objs := i40e_main.o \
 	i40e_virtchnl_pf.o
 
 i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o
-i40e-$(CONFIG_FCOE:m=y) += i40e_fcoe.o
+i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index 045b5c4b98b3..ad802dd0f67a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -78,7 +78,7 @@ do {                                                            \
 } while (0)
 
 typedef enum i40e_status_code i40e_status;
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#ifdef CONFIG_I40E_FCOE
 #define I40E_FCOE
-#endif /* CONFIG_FCOE or CONFIG_FCOE_MODULE */
+#endif
 #endif /* _I40E_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 9f536dd8e1ec..bb86390a0967 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -658,6 +658,8 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
 	return le32_to_cpu(*(volatile __le32 *)head);
 }
 
+#define WB_STRIDE 0x3
+
 /**
  * i40e_clean_tx_irq - Reclaim resources after transmit completes
  * @tx_ring:  tx ring to clean
@@ -759,6 +761,18 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	tx_ring->q_vector->tx.total_bytes += total_bytes;
 	tx_ring->q_vector->tx.total_packets += total_packets;
 
+	/* check to see if there are any non-cache aligned descriptors
+	 * waiting to be written back, and kick the hardware to force
+	 * them to be written back in case of napi polling
+	 */
+	if (budget &&
+	    !((i & WB_STRIDE) == WB_STRIDE) &&
+	    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+	    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+		tx_ring->arm_wb = true;
+	else
+		tx_ring->arm_wb = false;
+
 	if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
 		/* schedule immediate reset if we believe we hung */
 		dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
@@ -777,13 +791,16 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
 		dev_info(tx_ring->dev,
-			 "tx hang detected on queue %d, resetting adapter\n",
+			 "tx hang detected on queue %d, reset requested\n",
 			 tx_ring->queue_index);
 
-		tx_ring->netdev->netdev_ops->ndo_tx_timeout(tx_ring->netdev);
+		/* do not fire the reset immediately, wait for the stack to
+		 * decide we are truly stuck, also prevents every queue from
+		 * simultaneously requesting a reset
+		 */
 
-		/* the adapter is about to reset, no point in enabling stuff */
-		return true;
+		/* the adapter is about to reset, no point in enabling polling */
+		budget = 1;
 	}
 
 	netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
@@ -806,7 +823,25 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 		}
 	}
 
-	return budget > 0;
+	return !!budget;
+}
+
+/**
+ * i40e_force_wb - Arm hardware to do a wb on noncache aligned descriptors
+ * @vsi: the VSI we care about
+ * @q_vector: the vector  on which to force writeback
+ *
+ **/
+static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector)
+{
+	u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
+		  I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+		  I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK
+		  /* allow 00 to be written to the index */;
+
+	wr32(&vsi->back->hw,
+	     I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1),
+	     val);
 }
 
 /**
@@ -1290,9 +1325,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	 * so the total length of IPv4 header is IHL*4 bytes
 	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
 	 */
-	if (ipv4_tunnel &&
-	    (decoded.inner_prot != I40E_RX_PTYPE_INNER_PROT_UDP) &&
-	    !(rx_status & (1 << I40E_RX_DESC_STATUS_UDP_0_SHIFT))) {
+	if (ipv4_tunnel) {
 		skb->transport_header = skb->mac_header +
 					sizeof(struct ethhdr) +
 					(ip_hdr(skb)->ihl * 4);
@@ -1302,15 +1335,19 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 					  skb->protocol == htons(ETH_P_8021AD))
 					  ? VLAN_HLEN : 0;
 
-		rx_udp_csum = udp_csum(skb);
-		iph = ip_hdr(skb);
-		csum = csum_tcpudp_magic(
-				iph->saddr, iph->daddr,
-				(skb->len - skb_transport_offset(skb)),
-				IPPROTO_UDP, rx_udp_csum);
+		if ((ip_hdr(skb)->protocol == IPPROTO_UDP) &&
+		    (udp_hdr(skb)->check != 0)) {
+			rx_udp_csum = udp_csum(skb);
+			iph = ip_hdr(skb);
+			csum = csum_tcpudp_magic(
+					iph->saddr, iph->daddr,
+					(skb->len - skb_transport_offset(skb)),
+					IPPROTO_UDP, rx_udp_csum);
 
-		if (udp_hdr(skb)->check != csum)
-			goto checksum_fail;
+			if (udp_hdr(skb)->check != csum)
+				goto checksum_fail;
+
+		} /* else its GRE and so no outer UDP header */
 	}
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1581,6 +1618,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	struct i40e_vsi *vsi = q_vector->vsi;
 	struct i40e_ring *ring;
 	bool clean_complete = true;
+	bool arm_wb = false;
 	int budget_per_ring;
 
 	if (test_bit(__I40E_DOWN, &vsi->state)) {
@@ -1591,8 +1629,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
-	i40e_for_each_ring(ring, q_vector->tx)
+	i40e_for_each_ring(ring, q_vector->tx) {
 		clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+		arm_wb |= ring->arm_wb;
+	}
 
 	/* We attempt to distribute budget to each Rx queue fairly, but don't
 	 * allow the budget to go below 1 because that would exit polling early.
@@ -1603,8 +1643,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 		clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring);
 
 	/* If work not completed, return budget and polling will return */
-	if (!clean_complete)
+	if (!clean_complete) {
+		if (arm_wb)
+			i40e_force_wb(vsi, q_vector);
 		return budget;
+	}
 
 	/* Work is done so exit the polling mode and re-enable the interrupt */
 	napi_complete(napi);
@@ -1840,17 +1883,16 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (protocol == htons(ETH_P_IP)) {
-		iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+	ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+
+	if (iph->version == 4) {
 		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
 		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
 						 0, IPPROTO_TCP, 0);
-	} else if (skb_is_gso_v6(skb)) {
-
-		ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb)
-					   : ipv6_hdr(skb);
+	} else if (ipv6h->version == 6) {
 		tcph = skb->encapsulation ? inner_tcp_hdr(skb) : tcp_hdr(skb);
 		ipv6h->payload_len = 0;
 		tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
@@ -1946,13 +1988,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
 		} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
-			if (tx_flags & I40E_TX_FLAGS_TSO) {
-				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
+			if (tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
-			} else {
-				*cd_tunneling |=
-					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
-			}
 		}
 
 		/* Now set the ctx descriptor fields */
@@ -1962,7 +2000,10 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 				   ((skb_inner_network_offset(skb) -
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
-
+		if (this_ip_hdr->version == 6) {
+			tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			tx_flags |= I40E_TX_FLAGS_IPV6;
+		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
 		this_ip_hdr = ip_hdr(skb);
@@ -2198,7 +2239,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* Place RS bit on last descriptor of any packet that spans across the
 	 * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
 	 */
-#define WB_STRIDE 0x3
 	if (((i & WB_STRIDE) != WB_STRIDE) &&
 	    (first <= &tx_ring->tx_bi[i]) &&
 	    (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index e60d3accb2e2..18b00231d2f1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -241,6 +241,7 @@ struct i40e_ring {
 	unsigned long last_rx_timestamp;
 
 	bool ring_active;		/* is ring online or not */
+	bool arm_wb;		/* do something to arm write back */
 
 	/* stats structs */
 	struct i40e_queue_stats	stats;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index c29ba80ae02b..37583a9d8853 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -473,6 +473,7 @@ static struct sh_eth_cpu_data r8a777x_data = {
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
 			  EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
 			  EESR_ECI,
+	.fdr_value	= 0x00000f0f,
 
 	.apr		= 1,
 	.mpr		= 1,
@@ -495,6 +496,7 @@ static struct sh_eth_cpu_data r8a779x_data = {
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
 			  EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
 			  EESR_ECI,
+	.fdr_value	= 0x00000f0f,
 
 	.apr		= 1,
 	.mpr		= 1,
@@ -536,6 +538,8 @@ static struct sh_eth_cpu_data sh7724_data = {
 			  EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
 			  EESR_ECI,
 
+	.trscer_err_mask = DESC_I_RINT8,
+
 	.apr		= 1,
 	.mpr		= 1,
 	.tpauser	= 1,
@@ -856,6 +860,9 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd)
 
 	if (!cd->eesr_err_check)
 		cd->eesr_err_check = DEFAULT_EESR_ERR_CHECK;
+
+	if (!cd->trscer_err_mask)
+		cd->trscer_err_mask = DEFAULT_TRSCER_ERR_MASK;
 }
 
 static int sh_eth_check_reset(struct net_device *ndev)
@@ -1294,7 +1301,7 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start)
 	/* Frame recv control (enable multiple-packets per rx irq) */
 	sh_eth_write(ndev, RMCR_RNC, RMCR);
 
-	sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER);
+	sh_eth_write(ndev, mdp->cd->trscer_err_mask, TRSCER);
 
 	if (mdp->cd->bculr)
 		sh_eth_write(ndev, 0x800, BCULR);	/* Burst sycle set */
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 22301bf9c21d..71f5de1171bd 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -369,6 +369,8 @@ enum DESC_I_BIT {
 	DESC_I_RINT1 = 0x0001,
 };
 
+#define DEFAULT_TRSCER_ERR_MASK (DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2)
+
 /* RPADIR */
 enum RPADIR_BIT {
 	RPADIR_PADS1 = 0x20000, RPADIR_PADS0 = 0x10000,
@@ -470,6 +472,9 @@ struct sh_eth_cpu_data {
 	unsigned long tx_check;
 	unsigned long eesr_err_check;
 
+	/* Error mask */
+	unsigned long trscer_err_mask;
+
 	/* hardware features */
 	unsigned long irq_flags; /* IRQ configuration flags */
 	unsigned no_psr:1;	/* EtherC DO NOT have PSR */
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index e61ee8351272..64d1cef4cda1 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -610,7 +610,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 
 			/* Clear all mcast from ALE */
 			cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS <<
-						 priv->host_port);
+						 priv->host_port, -1);
 
 			/* Flood All Unicast Packets to Host port */
 			cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1);
@@ -634,6 +634,12 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
+	int vid;
+
+	if (priv->data.dual_emac)
+		vid = priv->slaves[priv->emac_port].port_vlan;
+	else
+		vid = priv->data.default_vlan;
 
 	if (ndev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
@@ -649,7 +655,8 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	cpsw_ale_set_allmulti(priv->ale, priv->ndev->flags & IFF_ALLMULTI);
 
 	/* Clear all mcast from ALE */
-	cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port);
+	cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port,
+				 vid);
 
 	if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 097ebe7077ac..5246b3a18ff8 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -234,7 +234,7 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry,
 		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 }
 
-int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS];
 	int ret, idx;
@@ -245,6 +245,14 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
 		if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR)
 			continue;
 
+		/* if vid passed is -1 then remove all multicast entry from
+		 * the table irrespective of vlan id, if a valid vlan id is
+		 * passed then remove only multicast added to that vlan id.
+		 * if vlan id doesn't match then move on to next entry.
+		 */
+		if (vid != -1 && cpsw_ale_get_vlan_id(ale_entry) != vid)
+			continue;
+
 		if (cpsw_ale_get_mcast(ale_entry)) {
 			u8 addr[6];
 
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index c0d4127aa549..af1e7ecd87c6 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -92,7 +92,7 @@ void cpsw_ale_stop(struct cpsw_ale *ale);
 
 int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout);
 int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask);
-int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask);
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid);
 int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port,
 		       int flags, u16 vid);
 int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port,
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 43bcfff71d95..4b2bfc52c52f 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -622,6 +622,7 @@ static int team_change_mode(struct team *team, const char *kind)
 static void team_notify_peers_work(struct work_struct *work)
 {
 	struct team *team;
+	int val;
 
 	team = container_of(work, struct team, notify_peers.dw.work);
 
@@ -629,9 +630,14 @@ static void team_notify_peers_work(struct work_struct *work)
 		schedule_delayed_work(&team->notify_peers.dw, 0);
 		return;
 	}
+	val = atomic_dec_if_positive(&team->notify_peers.count_pending);
+	if (val < 0) {
+		rtnl_unlock();
+		return;
+	}
 	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev);
 	rtnl_unlock();
-	if (!atomic_dec_and_test(&team->notify_peers.count_pending))
+	if (val)
 		schedule_delayed_work(&team->notify_peers.dw,
 				      msecs_to_jiffies(team->notify_peers.interval));
 }
@@ -662,6 +668,7 @@ static void team_notify_peers_fini(struct team *team)
 static void team_mcast_rejoin_work(struct work_struct *work)
 {
 	struct team *team;
+	int val;
 
 	team = container_of(work, struct team, mcast_rejoin.dw.work);
 
@@ -669,9 +676,14 @@ static void team_mcast_rejoin_work(struct work_struct *work)
 		schedule_delayed_work(&team->mcast_rejoin.dw, 0);
 		return;
 	}
+	val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending);
+	if (val < 0) {
+		rtnl_unlock();
+		return;
+	}
 	call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev);
 	rtnl_unlock();
-	if (!atomic_dec_and_test(&team->mcast_rejoin.count_pending))
+	if (val)
 		schedule_delayed_work(&team->mcast_rejoin.dw,
 				      msecs_to_jiffies(team->mcast_rejoin.interval));
 }
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index dcb6d33141e0..1e9cdca37014 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -1276,7 +1276,7 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int* actual_length)
         awd.done = 0;
 
         urb->context = &awd;
-        status = usb_submit_urb(urb, GFP_NOIO);
+        status = usb_submit_urb(urb, GFP_ATOMIC);
         if (status) {
                 // something went wrong
                 usb_free_urb(urb);
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index e5be2d21868f..a5f9198d5747 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -69,8 +69,8 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL7260_UCODE_API_MAX	10
-#define IWL3160_UCODE_API_MAX	10
+#define IWL7260_UCODE_API_MAX	12
+#define IWL3160_UCODE_API_MAX	12
 
 /* Oldest version we won't warn about */
 #define IWL7260_UCODE_API_OK	10
@@ -105,7 +105,7 @@
 #define IWL7265_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode"
 
 #define IWL7265D_FW_PRE "iwlwifi-7265D-"
-#define IWL7265D_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode"
+#define IWL7265D_MODULE_FIRMWARE(api) IWL7265D_FW_PRE __stringify(api) ".ucode"
 
 #define NVM_HW_SECTION_NUM_FAMILY_7000		0
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-8000.c b/drivers/net/wireless/iwlwifi/iwl-8000.c
index bf0a95cb7153..3668fc57e770 100644
--- a/drivers/net/wireless/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-8000.c
@@ -69,7 +69,7 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL8000_UCODE_API_MAX	10
+#define IWL8000_UCODE_API_MAX	12
 
 /* Oldest version we won't warn about */
 #define IWL8000_UCODE_API_OK	10
diff --git a/drivers/net/wireless/iwlwifi/iwl-fw-file.h b/drivers/net/wireless/iwlwifi/iwl-fw-file.h
index f2a047f6bb3e..1bbe4fc47b97 100644
--- a/drivers/net/wireless/iwlwifi/iwl-fw-file.h
+++ b/drivers/net/wireless/iwlwifi/iwl-fw-file.h
@@ -243,6 +243,9 @@ enum iwl_ucode_tlv_flag {
  * @IWL_UCODE_TLV_API_SF_NO_DUMMY_NOTIF: ucode supports disabling dummy notif.
  * @IWL_UCODE_TLV_API_FRAGMENTED_SCAN: This ucode supports active dwell time
  *	longer than the passive one, which is essential for fragmented scan.
+ * @IWL_UCODE_TLV_API_BASIC_DWELL: use only basic dwell time in scan command,
+ *	regardless of the band or the number of the probes. FW will calculate
+ *	the actual dwell time.
  */
 enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_WOWLAN_CONFIG_TID	= BIT(0),
@@ -253,6 +256,7 @@ enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_LMAC_SCAN		= BIT(6),
 	IWL_UCODE_TLV_API_SF_NO_DUMMY_NOTIF	= BIT(7),
 	IWL_UCODE_TLV_API_FRAGMENTED_SCAN	= BIT(8),
+	IWL_UCODE_TLV_API_BASIC_DWELL		= BIT(13),
 };
 
 /**
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 1f2acf47bfb2..201846de94e7 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -672,6 +672,7 @@ struct iwl_scan_channel_opt {
  * @IWL_MVM_LMAC_SCAN_FLAG_FRAGMENTED: all passive scans will be fragmented
  * @IWL_MVM_LMAC_SCAN_FLAGS_RRM_ENABLED: insert WFA vendor-specific TPC report
  *	and DS parameter set IEs into probe requests.
+ * @IWL_MVM_LMAC_SCAN_FLAG_MATCH: Send match found notification on matches
  */
 enum iwl_mvm_lmac_scan_flags {
 	IWL_MVM_LMAC_SCAN_FLAG_PASS_ALL		= BIT(0),
@@ -681,6 +682,7 @@ enum iwl_mvm_lmac_scan_flags {
 	IWL_MVM_LMAC_SCAN_FLAG_MULTIPLE_SSIDS	= BIT(4),
 	IWL_MVM_LMAC_SCAN_FLAG_FRAGMENTED	= BIT(5),
 	IWL_MVM_LMAC_SCAN_FLAGS_RRM_ENABLED	= BIT(6),
+	IWL_MVM_LMAC_SCAN_FLAG_MATCH		= BIT(9),
 };
 
 enum iwl_scan_priority {
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index e5294d01181e..ec9a8e7bae1d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -171,15 +171,21 @@ static void iwl_mvm_scan_fill_ssids(struct iwl_ssid_ie *cmd_ssid,
  * already included in the probe template, so we need to set only
  * req->n_ssids - 1 bits in addition to the first bit.
  */
-static u16 iwl_mvm_get_active_dwell(enum ieee80211_band band, int n_ssids)
+static u16 iwl_mvm_get_active_dwell(struct iwl_mvm *mvm,
+				    enum ieee80211_band band, int n_ssids)
 {
+	if (mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_BASIC_DWELL)
+		return 10;
 	if (band == IEEE80211_BAND_2GHZ)
 		return 20  + 3 * (n_ssids + 1);
 	return 10  + 2 * (n_ssids + 1);
 }
 
-static u16 iwl_mvm_get_passive_dwell(enum ieee80211_band band)
+static u16 iwl_mvm_get_passive_dwell(struct iwl_mvm *mvm,
+				     enum ieee80211_band band)
 {
+	if (mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_BASIC_DWELL)
+			return 110;
 	return band == IEEE80211_BAND_2GHZ ? 100 + 20 : 100 + 10;
 }
 
@@ -331,7 +337,8 @@ static void iwl_mvm_scan_calc_params(struct iwl_mvm *mvm,
 		 */
 		if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
 			u32 passive_dwell =
-				iwl_mvm_get_passive_dwell(IEEE80211_BAND_2GHZ);
+				iwl_mvm_get_passive_dwell(mvm,
+							  IEEE80211_BAND_2GHZ);
 			params->max_out_time = passive_dwell;
 		} else {
 			params->passive_fragmented = true;
@@ -348,8 +355,8 @@ not_bound:
 			params->dwell[band].passive = frag_passive_dwell;
 		else
 			params->dwell[band].passive =
-				iwl_mvm_get_passive_dwell(band);
-		params->dwell[band].active = iwl_mvm_get_active_dwell(band,
+				iwl_mvm_get_passive_dwell(mvm, band);
+		params->dwell[band].active = iwl_mvm_get_active_dwell(mvm, band,
 								      n_ssids);
 	}
 }
@@ -1448,6 +1455,8 @@ int iwl_mvm_unified_sched_scan_lmac(struct iwl_mvm *mvm,
 
 	if (iwl_mvm_scan_pass_all(mvm, req))
 		flags |= IWL_MVM_LMAC_SCAN_FLAG_PASS_ALL;
+	else
+		flags |= IWL_MVM_LMAC_SCAN_FLAG_MATCH;
 
 	if (req->n_ssids == 1 && req->ssids[0].ssid_len != 0)
 		flags |= IWL_MVM_LMAC_SCAN_FLAG_PRE_CONNECTION;
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 4f15d9decc81..4333306ccdee 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -108,8 +108,12 @@ void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
 			tx_flags &= ~TX_CMD_FLG_SEQ_CTL;
 	}
 
-	/* tid_tspec will default to 0 = BE when QOS isn't enabled */
-	ac = tid_to_mac80211_ac[tx_cmd->tid_tspec];
+	/* Default to 0 (BE) when tid_spec is set to IWL_TID_NON_QOS */
+	if (tx_cmd->tid_tspec < IWL_MAX_TID_COUNT)
+		ac = tid_to_mac80211_ac[tx_cmd->tid_tspec];
+	else
+		ac = tid_to_mac80211_ac[0];
+
 	tx_flags |= iwl_mvm_bt_coex_tx_prio(mvm, hdr, info, ac) <<
 			TX_CMD_FLG_BT_PRIO_POS;
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index e56e77ef5d2e..917431e30f74 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -665,7 +665,7 @@ bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm)
 	if (num_of_ant(mvm->fw->valid_rx_ant) == 1)
 		return false;
 
-	if (!mvm->cfg->rx_with_siso_diversity)
+	if (mvm->cfg->rx_with_siso_diversity)
 		return false;
 
 	ieee80211_iterate_active_interfaces_atomic(
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 2f0c4b170344..d5aadb00dd9e 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -527,8 +527,10 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else if (cfg == &iwl7265_n_cfg)
 		cfg_7265d = &iwl7265d_n_cfg;
 	if (cfg_7265d &&
-	    (iwl_trans->hw_rev & CSR_HW_REV_TYPE_MSK) == CSR_HW_REV_TYPE_7265D)
+	    (iwl_trans->hw_rev & CSR_HW_REV_TYPE_MSK) == CSR_HW_REV_TYPE_7265D) {
 		cfg = cfg_7265d;
+		iwl_trans->cfg = cfg_7265d;
+	}
 #endif
 
 	pci_set_drvdata(pdev, iwl_trans);
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index 846a2e6e34d8..c70efb9a6e78 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -666,7 +666,8 @@ tx_status_ok:
 }
 
 static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
-				    u8 *entry, int rxring_idx, int desc_idx)
+				    struct sk_buff *new_skb, u8 *entry,
+				    int rxring_idx, int desc_idx)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
@@ -674,11 +675,15 @@ static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
 	u8 tmp_one = 1;
 	struct sk_buff *skb;
 
+	if (likely(new_skb)) {
+		skb = new_skb;
+		goto remap;
+	}
 	skb = dev_alloc_skb(rtlpci->rxbuffersize);
 	if (!skb)
 		return 0;
-	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 
+remap:
 	/* just set skb->cb to mapping addr for pci_unmap_single use */
 	*((dma_addr_t *)skb->cb) =
 		pci_map_single(rtlpci->pdev, skb_tail_pointer(skb),
@@ -686,6 +691,7 @@ static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
 	bufferaddress = *((dma_addr_t *)skb->cb);
 	if (pci_dma_mapping_error(rtlpci->pdev, bufferaddress))
 		return 0;
+	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 	if (rtlpriv->use_new_trx_flow) {
 		rtlpriv->cfg->ops->set_desc(hw, (u8 *)entry, false,
 					    HW_DESC_RX_PREPARE,
@@ -781,6 +787,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		/*rx pkt */
 		struct sk_buff *skb = rtlpci->rx_ring[rxring_idx].rx_buf[
 				      rtlpci->rx_ring[rxring_idx].idx];
+		struct sk_buff *new_skb;
 
 		if (rtlpriv->use_new_trx_flow) {
 			rx_remained_cnt =
@@ -807,6 +814,13 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		pci_unmap_single(rtlpci->pdev, *((dma_addr_t *)skb->cb),
 				 rtlpci->rxbuffersize, PCI_DMA_FROMDEVICE);
 
+		/* get a new skb - if fail, old one will be reused */
+		new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
+		if (unlikely(!new_skb)) {
+			pr_err("Allocation of new skb failed in %s\n",
+			       __func__);
+			goto no_new;
+		}
 		if (rtlpriv->use_new_trx_flow) {
 			buffer_desc =
 			  &rtlpci->rx_ring[rxring_idx].buffer_desc
@@ -911,14 +925,16 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 			schedule_work(&rtlpriv->works.lps_change_work);
 		}
 end:
+		skb = new_skb;
+no_new:
 		if (rtlpriv->use_new_trx_flow) {
-			_rtl_pci_init_one_rxdesc(hw, (u8 *)buffer_desc,
+			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)buffer_desc,
 						 rxring_idx,
-					       rtlpci->rx_ring[rxring_idx].idx);
+						 rtlpci->rx_ring[rxring_idx].idx);
 		} else {
-			_rtl_pci_init_one_rxdesc(hw, (u8 *)pdesc, rxring_idx,
+			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)pdesc,
+						 rxring_idx,
 						 rtlpci->rx_ring[rxring_idx].idx);
-
 			if (rtlpci->rx_ring[rxring_idx].idx ==
 			    rtlpci->rxringcount - 1)
 				rtlpriv->cfg->ops->set_desc(hw, (u8 *)pdesc,
@@ -1307,7 +1323,7 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw, int rxring_idx)
 		rtlpci->rx_ring[rxring_idx].idx = 0;
 		for (i = 0; i < rtlpci->rxringcount; i++) {
 			entry = &rtlpci->rx_ring[rxring_idx].buffer_desc[i];
-			if (!_rtl_pci_init_one_rxdesc(hw, (u8 *)entry,
+			if (!_rtl_pci_init_one_rxdesc(hw, NULL, (u8 *)entry,
 						      rxring_idx, i))
 				return -ENOMEM;
 		}
@@ -1332,7 +1348,7 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw, int rxring_idx)
 
 		for (i = 0; i < rtlpci->rxringcount; i++) {
 			entry = &rtlpci->rx_ring[rxring_idx].desc[i];
-			if (!_rtl_pci_init_one_rxdesc(hw, (u8 *)entry,
+			if (!_rtl_pci_init_one_rxdesc(hw, NULL, (u8 *)entry,
 						      rxring_idx, i))
 				return -ENOMEM;
 		}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 01a4350eb313..7cfa6c027c0c 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -88,10 +88,8 @@ struct netfront_cb {
 #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
 
 struct netfront_stats {
-	u64			rx_packets;
-	u64			tx_packets;
-	u64			rx_bytes;
-	u64			tx_bytes;
+	u64			packets;
+	u64			bytes;
 	struct u64_stats_sync	syncp;
 };
 
@@ -156,7 +154,8 @@ struct netfront_info {
 	struct netfront_queue *queues;
 
 	/* Statistics */
-	struct netfront_stats __percpu *stats;
+	struct netfront_stats __percpu *rx_stats;
+	struct netfront_stats __percpu *tx_stats;
 
 	atomic_t rx_gso_checksum_fixup;
 };
@@ -519,7 +518,7 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
 static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
-	struct netfront_stats *stats = this_cpu_ptr(np->stats);
+	struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
 	struct xen_netif_tx_request *tx, *first_tx;
 	unsigned int i;
 	int notify;
@@ -622,10 +621,10 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (notify)
 		notify_remote_via_irq(queue->tx_irq);
 
-	u64_stats_update_begin(&stats->syncp);
-	stats->tx_bytes += skb->len;
-	stats->tx_packets++;
-	u64_stats_update_end(&stats->syncp);
+	u64_stats_update_begin(&tx_stats->syncp);
+	tx_stats->bytes += skb->len;
+	tx_stats->packets++;
+	u64_stats_update_end(&tx_stats->syncp);
 
 	/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
 	xennet_tx_buf_gc(queue);
@@ -881,7 +880,7 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 static int handle_incoming_queue(struct netfront_queue *queue,
 				 struct sk_buff_head *rxq)
 {
-	struct netfront_stats *stats = this_cpu_ptr(queue->info->stats);
+	struct netfront_stats *rx_stats = this_cpu_ptr(queue->info->rx_stats);
 	int packets_dropped = 0;
 	struct sk_buff *skb;
 
@@ -902,10 +901,10 @@ static int handle_incoming_queue(struct netfront_queue *queue,
 			continue;
 		}
 
-		u64_stats_update_begin(&stats->syncp);
-		stats->rx_packets++;
-		stats->rx_bytes += skb->len;
-		u64_stats_update_end(&stats->syncp);
+		u64_stats_update_begin(&rx_stats->syncp);
+		rx_stats->packets++;
+		rx_stats->bytes += skb->len;
+		u64_stats_update_end(&rx_stats->syncp);
 
 		/* Pass it up. */
 		napi_gro_receive(&queue->napi, skb);
@@ -1029,18 +1028,22 @@ static struct rtnl_link_stats64 *xennet_get_stats64(struct net_device *dev,
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		struct netfront_stats *stats = per_cpu_ptr(np->stats, cpu);
+		struct netfront_stats *rx_stats = per_cpu_ptr(np->rx_stats, cpu);
+		struct netfront_stats *tx_stats = per_cpu_ptr(np->tx_stats, cpu);
 		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+			tx_packets = tx_stats->packets;
+			tx_bytes = tx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
 
-			rx_packets = stats->rx_packets;
-			tx_packets = stats->tx_packets;
-			rx_bytes = stats->rx_bytes;
-			tx_bytes = stats->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+		do {
+			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+			rx_packets = rx_stats->packets;
+			rx_bytes = rx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
 
 		tot->rx_packets += rx_packets;
 		tot->tx_packets += tx_packets;
@@ -1225,6 +1228,15 @@ static const struct net_device_ops xennet_netdev_ops = {
 #endif
 };
 
+static void xennet_free_netdev(struct net_device *netdev)
+{
+	struct netfront_info *np = netdev_priv(netdev);
+
+	free_percpu(np->rx_stats);
+	free_percpu(np->tx_stats);
+	free_netdev(netdev);
+}
+
 static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 {
 	int err;
@@ -1245,8 +1257,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	np->queues = NULL;
 
 	err = -ENOMEM;
-	np->stats = netdev_alloc_pcpu_stats(struct netfront_stats);
-	if (np->stats == NULL)
+	np->rx_stats = netdev_alloc_pcpu_stats(struct netfront_stats);
+	if (np->rx_stats == NULL)
+		goto exit;
+	np->tx_stats = netdev_alloc_pcpu_stats(struct netfront_stats);
+	if (np->tx_stats == NULL)
 		goto exit;
 
 	netdev->netdev_ops	= &xennet_netdev_ops;
@@ -1277,7 +1292,7 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	return netdev;
 
  exit:
-	free_netdev(netdev);
+	xennet_free_netdev(netdev);
 	return ERR_PTR(err);
 }
 
@@ -1319,7 +1334,7 @@ static int netfront_probe(struct xenbus_device *dev,
 	return 0;
 
  fail:
-	free_netdev(netdev);
+	xennet_free_netdev(netdev);
 	dev_set_drvdata(&dev->dev, NULL);
 	return err;
 }
@@ -2139,9 +2154,7 @@ static int xennet_remove(struct xenbus_device *dev)
 		info->queues = NULL;
 	}
 
-	free_percpu(info->stats);
-
-	free_netdev(info->netdev);
+	xennet_free_netdev(info->netdev);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index ba74f0aa60c7..3c22dbebc80f 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -89,6 +89,7 @@ struct rockchip_iomux {
  * @reg_pull: optional separate register for additional pull settings
  * @clk: clock of the gpio bank
  * @irq: interrupt of the gpio bank
+ * @saved_enables: Saved content of GPIO_INTEN at suspend time.
  * @pin_base: first pin number
  * @nr_pins: number of pins in this bank
  * @name: name of the bank
@@ -107,6 +108,7 @@ struct rockchip_pin_bank {
 	struct regmap			*regmap_pull;
 	struct clk			*clk;
 	int				irq;
+	u32				saved_enables;
 	u32				pin_base;
 	u8				nr_pins;
 	char				*name;
@@ -1543,6 +1545,51 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type)
 	return 0;
 }
 
+static void rockchip_irq_suspend(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct rockchip_pin_bank *bank = gc->private;
+
+	bank->saved_enables = irq_reg_readl(gc, GPIO_INTEN);
+	irq_reg_writel(gc, gc->wake_active, GPIO_INTEN);
+}
+
+static void rockchip_irq_resume(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct rockchip_pin_bank *bank = gc->private;
+
+	irq_reg_writel(gc, bank->saved_enables, GPIO_INTEN);
+}
+
+static void rockchip_irq_disable(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 val;
+
+	irq_gc_lock(gc);
+
+	val = irq_reg_readl(gc, GPIO_INTEN);
+	val &= ~d->mask;
+	irq_reg_writel(gc, val, GPIO_INTEN);
+
+	irq_gc_unlock(gc);
+}
+
+static void rockchip_irq_enable(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 val;
+
+	irq_gc_lock(gc);
+
+	val = irq_reg_readl(gc, GPIO_INTEN);
+	val |= d->mask;
+	irq_reg_writel(gc, val, GPIO_INTEN);
+
+	irq_gc_unlock(gc);
+}
+
 static int rockchip_interrupts_register(struct platform_device *pdev,
 						struct rockchip_pinctrl *info)
 {
@@ -1581,12 +1628,16 @@ static int rockchip_interrupts_register(struct platform_device *pdev,
 		gc = irq_get_domain_generic_chip(bank->domain, 0);
 		gc->reg_base = bank->reg_base;
 		gc->private = bank;
-		gc->chip_types[0].regs.mask = GPIO_INTEN;
+		gc->chip_types[0].regs.mask = GPIO_INTMASK;
 		gc->chip_types[0].regs.ack = GPIO_PORTS_EOI;
 		gc->chip_types[0].chip.irq_ack = irq_gc_ack_set_bit;
-		gc->chip_types[0].chip.irq_mask = irq_gc_mask_clr_bit;
-		gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit;
+		gc->chip_types[0].chip.irq_mask = irq_gc_mask_set_bit;
+		gc->chip_types[0].chip.irq_unmask = irq_gc_mask_clr_bit;
+		gc->chip_types[0].chip.irq_enable = rockchip_irq_enable;
+		gc->chip_types[0].chip.irq_disable = rockchip_irq_disable;
 		gc->chip_types[0].chip.irq_set_wake = irq_gc_set_wake;
+		gc->chip_types[0].chip.irq_suspend = rockchip_irq_suspend;
+		gc->chip_types[0].chip.irq_resume = rockchip_irq_resume;
 		gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type;
 		gc->wake_enabled = IRQ_MSK(bank->nr_pins);
 
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 7c9d51382248..9e5ec00084bb 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1012,8 +1012,10 @@ static void st_pinconf_dbg_show(struct pinctrl_dev *pctldev,
 				   struct seq_file *s, unsigned pin_id)
 {
 	unsigned long config;
-	st_pinconf_get(pctldev, pin_id, &config);
 
+	mutex_unlock(&pctldev->mutex);
+	st_pinconf_get(pctldev, pin_id, &config);
+	mutex_lock(&pctldev->mutex);
 	seq_printf(s, "[OE:%ld,PU:%ld,OD:%ld]\n"
 		"\t\t[retime:%ld,invclk:%ld,clknotdat:%ld,"
 		"de:%ld,rt-clk:%ld,rt-delay:%ld]",
@@ -1443,6 +1445,7 @@ static struct gpio_chip st_gpio_template = {
 
 static struct irq_chip st_gpio_irqchip = {
 	.name		= "GPIO",
+	.irq_disable	= st_gpio_irq_mask,
 	.irq_mask	= st_gpio_irq_mask,
 	.irq_unmask	= st_gpio_irq_unmask,
 	.irq_set_type	= st_gpio_irq_set_type,
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 91e97ec01418..4d41bf75c233 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -1163,9 +1163,13 @@ static inline int ap_test_config_card_id(unsigned int id)
  */
 static inline int ap_test_config_domain(unsigned int domain)
 {
-	if (!ap_configuration)
-		return 1;
-	return ap_test_config(ap_configuration->aqm, domain);
+	if (!ap_configuration)	  /* QCI not supported */
+		if (domain < 16)
+			return 1; /* then domains 0...15 are configured */
+		else
+			return 0;
+	else
+		return ap_test_config(ap_configuration->aqm, domain);
 }
 
 /**
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 12ca291c1380..cce1cbc1a927 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -734,7 +734,9 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	 * Return target busy if we've received a non-zero retry_delay_timer
 	 * in a FCP_RSP.
 	 */
-	if (time_after(jiffies, fcport->retry_delay_timestamp))
+	if (fcport->retry_delay_timestamp == 0) {
+		/* retry delay not set */
+	} else if (time_after(jiffies, fcport->retry_delay_timestamp))
 		fcport->retry_delay_timestamp = 0;
 	else
 		goto qc24_target_busy;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 55f6774f706f..aebde3289c50 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -2027,10 +2027,10 @@ iscsit_process_text_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 		goto reject;
 	}
 	if (!strncmp("=All", text_ptr, 4)) {
-		cmd->cmd_flags |= IFC_SENDTARGETS_ALL;
+		cmd->cmd_flags |= ICF_SENDTARGETS_ALL;
 	} else if (!strncmp("=iqn.", text_ptr, 5) ||
 		   !strncmp("=eui.", text_ptr, 5)) {
-		cmd->cmd_flags |= IFC_SENDTARGETS_SINGLE;
+		cmd->cmd_flags |= ICF_SENDTARGETS_SINGLE;
 	} else {
 		pr_err("Unable to locate valid SendTargets=%s value\n", text_ptr);
 		goto reject;
@@ -3415,10 +3415,10 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
 		return -ENOMEM;
 	}
 	/*
-	 * Locate pointer to iqn./eui. string for IFC_SENDTARGETS_SINGLE
+	 * Locate pointer to iqn./eui. string for ICF_SENDTARGETS_SINGLE
 	 * explicit case..
 	 */
-	if (cmd->cmd_flags & IFC_SENDTARGETS_SINGLE) {
+	if (cmd->cmd_flags & ICF_SENDTARGETS_SINGLE) {
 		text_ptr = strchr(text_in, '=');
 		if (!text_ptr) {
 			pr_err("Unable to locate '=' string in text_in:"
@@ -3434,7 +3434,7 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
 
 	spin_lock(&tiqn_lock);
 	list_for_each_entry(tiqn, &g_tiqn_list, tiqn_list) {
-		if ((cmd->cmd_flags & IFC_SENDTARGETS_SINGLE) &&
+		if ((cmd->cmd_flags & ICF_SENDTARGETS_SINGLE) &&
 		     strcmp(tiqn->tiqn, text_ptr)) {
 			continue;
 		}
@@ -3512,7 +3512,7 @@ eob:
 		if (end_of_buf)
 			break;
 
-		if (cmd->cmd_flags & IFC_SENDTARGETS_SINGLE)
+		if (cmd->cmd_flags & ICF_SENDTARGETS_SINGLE)
 			break;
 	}
 	spin_unlock(&tiqn_lock);
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 09a522bae222..cbcff38ac9b7 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -135,8 +135,8 @@ enum cmd_flags_table {
 	ICF_CONTIG_MEMORY			= 0x00000020,
 	ICF_ATTACHED_TO_RQUEUE			= 0x00000040,
 	ICF_OOO_CMDSN				= 0x00000080,
-	IFC_SENDTARGETS_ALL			= 0x00000100,
-	IFC_SENDTARGETS_SINGLE			= 0x00000200,
+	ICF_SENDTARGETS_ALL			= 0x00000100,
+	ICF_SENDTARGETS_SINGLE			= 0x00000200,
 };
 
 /* struct iscsi_cmd->i_state */
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 7653cfb027a2..58f49ff69b14 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1103,51 +1103,6 @@ int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth)
 }
 EXPORT_SYMBOL(se_dev_set_queue_depth);
 
-int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
-{
-	int block_size = dev->dev_attrib.block_size;
-
-	if (dev->export_count) {
-		pr_err("dev[%p]: Unable to change SE Device"
-			" fabric_max_sectors while export_count is %d\n",
-			dev, dev->export_count);
-		return -EINVAL;
-	}
-	if (!fabric_max_sectors) {
-		pr_err("dev[%p]: Illegal ZERO value for"
-			" fabric_max_sectors\n", dev);
-		return -EINVAL;
-	}
-	if (fabric_max_sectors < DA_STATUS_MAX_SECTORS_MIN) {
-		pr_err("dev[%p]: Passed fabric_max_sectors: %u less than"
-			" DA_STATUS_MAX_SECTORS_MIN: %u\n", dev, fabric_max_sectors,
-				DA_STATUS_MAX_SECTORS_MIN);
-		return -EINVAL;
-	}
-	if (fabric_max_sectors > DA_STATUS_MAX_SECTORS_MAX) {
-		pr_err("dev[%p]: Passed fabric_max_sectors: %u"
-			" greater than DA_STATUS_MAX_SECTORS_MAX:"
-			" %u\n", dev, fabric_max_sectors,
-			DA_STATUS_MAX_SECTORS_MAX);
-		return -EINVAL;
-	}
-	/*
-	 * Align max_sectors down to PAGE_SIZE to follow transport_allocate_data_tasks()
-	 */
-	if (!block_size) {
-		block_size = 512;
-		pr_warn("Defaulting to 512 for zero block_size\n");
-	}
-	fabric_max_sectors = se_dev_align_max_sectors(fabric_max_sectors,
-						      block_size);
-
-	dev->dev_attrib.fabric_max_sectors = fabric_max_sectors;
-	pr_debug("dev[%p]: SE Device max_sectors changed to %u\n",
-			dev, fabric_max_sectors);
-	return 0;
-}
-EXPORT_SYMBOL(se_dev_set_fabric_max_sectors);
-
 int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 {
 	if (dev->export_count) {
@@ -1156,10 +1111,10 @@ int se_dev_set_optimal_sectors(struct se_device *dev, u32 optimal_sectors)
 			dev, dev->export_count);
 		return -EINVAL;
 	}
-	if (optimal_sectors > dev->dev_attrib.fabric_max_sectors) {
+	if (optimal_sectors > dev->dev_attrib.hw_max_sectors) {
 		pr_err("dev[%p]: Passed optimal_sectors %u cannot be"
-			" greater than fabric_max_sectors: %u\n", dev,
-			optimal_sectors, dev->dev_attrib.fabric_max_sectors);
+			" greater than hw_max_sectors: %u\n", dev,
+			optimal_sectors, dev->dev_attrib.hw_max_sectors);
 		return -EINVAL;
 	}
 
@@ -1553,8 +1508,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.unmap_granularity_alignment =
 				DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT;
 	dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN;
-	dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
-	dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
 
 	xcopy_lun = &dev->xcopy_lun;
 	xcopy_lun->lun_se_dev = dev;
@@ -1595,6 +1548,7 @@ int target_configure_device(struct se_device *dev)
 	dev->dev_attrib.hw_max_sectors =
 		se_dev_align_max_sectors(dev->dev_attrib.hw_max_sectors,
 					 dev->dev_attrib.hw_block_size);
+	dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors;
 
 	dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
 	dev->creation_time = get_jiffies_64();
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index c2aea099ea4a..d836de200a03 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -621,7 +621,16 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	struct fd_prot fd_prot;
 	sense_reason_t rc;
 	int ret = 0;
-
+	/*
+	 * We are currently limited by the number of iovecs (2048) per
+	 * single vfs_[writev,readv] call.
+	 */
+	if (cmd->data_length > FD_MAX_BYTES) {
+		pr_err("FILEIO: Not able to process I/O of %u bytes due to"
+		       "FD_MAX_BYTES: %u iovec count limitiation\n",
+			cmd->data_length, FD_MAX_BYTES);
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+	}
 	/*
 	 * Call vectorized fileio functions to map struct scatterlist
 	 * physical memory addresses to struct iovec virtual memory.
@@ -959,7 +968,6 @@ static struct configfs_attribute *fileio_backend_dev_attrs[] = {
 	&fileio_dev_attrib_hw_block_size.attr,
 	&fileio_dev_attrib_block_size.attr,
 	&fileio_dev_attrib_hw_max_sectors.attr,
-	&fileio_dev_attrib_fabric_max_sectors.attr,
 	&fileio_dev_attrib_optimal_sectors.attr,
 	&fileio_dev_attrib_hw_queue_depth.attr,
 	&fileio_dev_attrib_queue_depth.attr,
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 3efff94fbd97..78346b850968 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -124,7 +124,7 @@ static int iblock_configure_device(struct se_device *dev)
 	q = bdev_get_queue(bd);
 
 	dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd);
-	dev->dev_attrib.hw_max_sectors = UINT_MAX;
+	dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
 	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
 	/*
@@ -883,7 +883,6 @@ static struct configfs_attribute *iblock_backend_dev_attrs[] = {
 	&iblock_dev_attrib_hw_block_size.attr,
 	&iblock_dev_attrib_block_size.attr,
 	&iblock_dev_attrib_hw_max_sectors.attr,
-	&iblock_dev_attrib_fabric_max_sectors.attr,
 	&iblock_dev_attrib_optimal_sectors.attr,
 	&iblock_dev_attrib_hw_queue_depth.attr,
 	&iblock_dev_attrib_queue_depth.attr,
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index d56f2aaba9af..283cf786ef98 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -528,6 +528,18 @@ static int core_scsi3_pr_seq_non_holder(
 
 			return 0;
 		}
+       } else if (we && registered_nexus) {
+               /*
+                * Reads are allowed for Write Exclusive locks
+                * from all registrants.
+                */
+               if (cmd->data_direction == DMA_FROM_DEVICE) {
+                       pr_debug("Allowing READ CDB: 0x%02x for %s"
+                               " reservation\n", cdb[0],
+                               core_scsi3_pr_dump_type(pr_reg_type));
+
+                       return 0;
+               }
 	}
 	pr_debug("%s Conflict for %sregistered nexus %s CDB: 0x%2x"
 		" for %s reservation\n", transport_dump_cmd_direction(cmd),
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 60ebd170a561..98e83ac5661b 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -657,7 +657,6 @@ static struct configfs_attribute *rd_mcp_backend_dev_attrs[] = {
 	&rd_mcp_dev_attrib_hw_block_size.attr,
 	&rd_mcp_dev_attrib_block_size.attr,
 	&rd_mcp_dev_attrib_hw_max_sectors.attr,
-	&rd_mcp_dev_attrib_fabric_max_sectors.attr,
 	&rd_mcp_dev_attrib_optimal_sectors.attr,
 	&rd_mcp_dev_attrib_hw_queue_depth.attr,
 	&rd_mcp_dev_attrib_queue_depth.attr,
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 11bea1952435..cd4bed7b2757 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -953,21 +953,6 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 
 	if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
 		unsigned long long end_lba;
-
-		if (sectors > dev->dev_attrib.fabric_max_sectors) {
-			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
-				" big sectors %u exceeds fabric_max_sectors:"
-				" %u\n", cdb[0], sectors,
-				dev->dev_attrib.fabric_max_sectors);
-			return TCM_INVALID_CDB_FIELD;
-		}
-		if (sectors > dev->dev_attrib.hw_max_sectors) {
-			printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
-				" big sectors %u exceeds backend hw_max_sectors:"
-				" %u\n", cdb[0], sectors,
-				dev->dev_attrib.hw_max_sectors);
-			return TCM_INVALID_CDB_FIELD;
-		}
 check_lba:
 		end_lba = dev->transport->get_blocks(dev) + 1;
 		if (cmd->t_task_lba + sectors > end_lba) {
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 1307600fe726..4c71657da56a 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -505,7 +505,6 @@ static sense_reason_t
 spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
-	u32 max_sectors;
 	int have_tp = 0;
 	int opt, min;
 
@@ -539,9 +538,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	/*
 	 * Set MAXIMUM TRANSFER LENGTH
 	 */
-	max_sectors = min(dev->dev_attrib.fabric_max_sectors,
-			  dev->dev_attrib.hw_max_sectors);
-	put_unaligned_be32(max_sectors, &buf[8]);
+	put_unaligned_be32(dev->dev_attrib.hw_max_sectors, &buf[8]);
 
 	/*
 	 * Set OPTIMAL TRANSFER LENGTH
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 8bfa61c9693d..1157b559683b 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1118,7 +1118,6 @@ static struct configfs_attribute *tcmu_backend_dev_attrs[] = {
 	&tcmu_dev_attrib_hw_block_size.attr,
 	&tcmu_dev_attrib_block_size.attr,
 	&tcmu_dev_attrib_hw_max_sectors.attr,
-	&tcmu_dev_attrib_fabric_max_sectors.attr,
 	&tcmu_dev_attrib_optimal_sectors.attr,
 	&tcmu_dev_attrib_hw_queue_depth.attr,
 	&tcmu_dev_attrib_queue_depth.attr,
diff --git a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c
index 231cabc16e16..2c2ec7666eb1 100644
--- a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c
+++ b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c
@@ -119,15 +119,11 @@ int acpi_parse_trt(acpi_handle handle, int *trt_count, struct trt **trtp,
 			continue;
 
 		result = acpi_bus_get_device(trt->source, &adev);
-		if (!result)
-			acpi_create_platform_device(adev);
-		else
+		if (result)
 			pr_warn("Failed to get source ACPI device\n");
 
 		result = acpi_bus_get_device(trt->target, &adev);
-		if (!result)
-			acpi_create_platform_device(adev);
-		else
+		if (result)
 			pr_warn("Failed to get target ACPI device\n");
 	}
 
@@ -206,16 +202,12 @@ int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp,
 
 		if (art->source) {
 			result = acpi_bus_get_device(art->source, &adev);
-			if (!result)
-				acpi_create_platform_device(adev);
-			else
+			if (result)
 				pr_warn("Failed to get source ACPI device\n");
 		}
 		if (art->target) {
 			result = acpi_bus_get_device(art->target, &adev);
-			if (!result)
-				acpi_create_platform_device(adev);
-			else
+			if (result)
 				pr_warn("Failed to get source ACPI device\n");
 		}
 	}
diff --git a/drivers/thermal/int340x_thermal/processor_thermal_device.c b/drivers/thermal/int340x_thermal/processor_thermal_device.c
index 31bb553aac26..0fe5dbbea968 100644
--- a/drivers/thermal/int340x_thermal/processor_thermal_device.c
+++ b/drivers/thermal/int340x_thermal/processor_thermal_device.c
@@ -130,6 +130,8 @@ static int proc_thermal_add(struct device *dev,
 	int ret;
 
 	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
 
 	status = acpi_evaluate_object(adev->handle, "PPCC", NULL, &buf);
 	if (ACPI_FAILURE(status))
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 255201f22126..7cc0122a18ce 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -840,13 +840,11 @@ static const struct vfio_device_ops vfio_pci_ops = {
 
 static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	u8 type;
 	struct vfio_pci_device *vdev;
 	struct iommu_group *group;
 	int ret;
 
-	pci_read_config_byte(pdev, PCI_HEADER_TYPE, &type);
-	if ((type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL)
+	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
 	group = iommu_group_get(&pdev->dev);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index bcaf4cabb858..6906f76332f4 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -538,7 +538,7 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 		++headcount;
 		seg += in;
 	}
-	heads[headcount - 1].len = cpu_to_vhost32(vq, len - datalen);
+	heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen);
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 01c01cb3933f..d695b1673ae5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -911,6 +911,23 @@ vhost_scsi_map_iov_to_prot(struct tcm_vhost_cmd *cmd,
 	return 0;
 }
 
+static int vhost_scsi_to_tcm_attr(int attr)
+{
+	switch (attr) {
+	case VIRTIO_SCSI_S_SIMPLE:
+		return TCM_SIMPLE_TAG;
+	case VIRTIO_SCSI_S_ORDERED:
+		return TCM_ORDERED_TAG;
+	case VIRTIO_SCSI_S_HEAD:
+		return TCM_HEAD_TAG;
+	case VIRTIO_SCSI_S_ACA:
+		return TCM_ACA_TAG;
+	default:
+		break;
+	}
+	return TCM_SIMPLE_TAG;
+}
+
 static void tcm_vhost_submission_work(struct work_struct *work)
 {
 	struct tcm_vhost_cmd *cmd =
@@ -936,9 +953,10 @@ static void tcm_vhost_submission_work(struct work_struct *work)
 	rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
 			cmd->tvc_cdb, &cmd->tvc_sense_buf[0],
 			cmd->tvc_lun, cmd->tvc_exp_data_len,
-			cmd->tvc_task_attr, cmd->tvc_data_direction,
-			TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count,
-			NULL, 0, sg_prot_ptr, cmd->tvc_prot_sgl_count);
+			vhost_scsi_to_tcm_attr(cmd->tvc_task_attr),
+			cmd->tvc_data_direction, TARGET_SCF_ACK_KREF,
+			sg_ptr, cmd->tvc_sgl_count, NULL, 0, sg_prot_ptr,
+			cmd->tvc_prot_sgl_count);
 	if (rc < 0) {
 		transport_send_check_condition_and_sense(se_cmd,
 				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 2ef9529809d8..9756f21b809e 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -282,6 +282,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 
 	vp_free_vectors(vdev);
 	kfree(vp_dev->vqs);
+	vp_dev->vqs = NULL;
 }
 
 static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
@@ -421,15 +422,6 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 	return 0;
 }
 
-void virtio_pci_release_dev(struct device *_d)
-{
-	/*
-	 * No need for a release method as we allocate/free
-	 * all devices together with the pci devices.
-	 * Provide an empty one to avoid getting a warning from core.
-	 */
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int virtio_pci_freeze(struct device *dev)
 {
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index adddb647b21d..5a497289b7e9 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -126,7 +126,6 @@ const char *vp_bus_name(struct virtio_device *vdev);
  * - ignore the affinity request if we're using INTX
  */
 int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
-void virtio_pci_release_dev(struct device *);
 
 int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
 			    const struct pci_device_id *id);
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 6c76f0f5658c..a5486e65e04b 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -211,6 +211,17 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.set_vq_affinity = vp_set_vq_affinity,
 };
 
+static void virtio_pci_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev = dev_to_virtio(_d);
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* As struct device is a kobject, it's not safe to
+	 * free the memory (including the reference counter itself)
+	 * until it's release callback. */
+	kfree(vp_dev);
+}
+
 /* the PCI probing function */
 int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
 			    const struct pci_device_id *id)
@@ -302,5 +313,4 @@ void virtio_pci_legacy_remove(struct pci_dev *pci_dev)
 	pci_iounmap(pci_dev, vp_dev->ioaddr);
 	pci_release_regions(pci_dev);
 	pci_disable_device(pci_dev);
-	kfree(vp_dev);
 }
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 2d3e32ebfd15..8729cf68d2fe 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1552,7 +1552,6 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 {
 	int ret;
 	int type;
-	struct btrfs_tree_block_info *info;
 	struct btrfs_extent_inline_ref *eiref;
 
 	if (*ptr == (unsigned long)-1)
@@ -1573,9 +1572,17 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 	}
 
 	/* we can treat both ref types equally here */
-	info = (struct btrfs_tree_block_info *)(ei + 1);
 	*out_root = btrfs_extent_inline_ref_offset(eb, eiref);
-	*out_level = btrfs_tree_block_level(eb, info);
+
+	if (key->type == BTRFS_EXTENT_ITEM_KEY) {
+		struct btrfs_tree_block_info *info;
+
+		info = (struct btrfs_tree_block_info *)(ei + 1);
+		*out_level = btrfs_tree_block_level(eb, info);
+	} else {
+		ASSERT(key->type == BTRFS_METADATA_ITEM_KEY);
+		*out_level = (u8)key->offset;
+	}
 
 	if (ret == 1)
 		*ptr = (unsigned long)-1;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 054577bddaf2..de4e70fb3cbb 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1857,6 +1857,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 
+	/*
+	 * we don't do delayed inode updates during log recovery because it
+	 * leads to enospc problems.  This means we also can't do
+	 * delayed inode refs
+	 */
+	if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+		return -EAGAIN;
+
 	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a80b97100d90..15116585e714 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3139,9 +3139,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 
 	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
-	if (ret < 0)
+	if (ret) {
+		if (ret > 0)
+			ret = -ENOENT;
 		goto fail;
-	BUG_ON(ret); /* Corruption */
+	}
 
 	leaf = path->nodes[0];
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
@@ -3149,11 +3151,9 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 fail:
-	if (ret) {
+	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
-		return ret;
-	}
-	return 0;
+	return ret;
 
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e687bb0dc73a..8bf326affb94 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6255,8 +6255,10 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 out_fail:
 	btrfs_end_transaction(trans, root);
-	if (drop_on_err)
+	if (drop_on_err) {
+		inode_dec_link_count(inode);
 		iput(inode);
+	}
 	btrfs_balance_delayed_items(root);
 	btrfs_btree_balance_dirty(root);
 	return err;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f2bb13a23f86..9e1569ffbf6e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2607,9 +2607,9 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
 		ret = scrub_pages_for_parity(sparity, logical, l, physical, dev,
 					     flags, gen, mirror_num,
 					     have_csum ? csum : NULL);
-skip:
 		if (ret)
 			return ret;
+skip:
 		len -= l;
 		logical += l;
 		physical += l;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index f5013d92a7e6..c81c0e004588 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1416,7 +1416,7 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 		}
 	}
 
-	dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+	dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
 	     inode, ceph_vinop(inode), len, locked_page);
 
 	if (len > 0) {
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 99d440a4a6ba..ee85cd4e136a 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,14 +740,15 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
 		O_RDONLY	| O_WRONLY	| O_RDWR	|
 		O_CREAT		| O_EXCL	| O_NOCTTY	|
 		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
 		__O_SYNC	| O_DSYNC	| FASYNC	|
 		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
 		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH	| __O_TMPFILE
+		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
+		__FMODE_NONOTIFY
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/locks.c b/fs/locks.c
index 735b8d3fa78c..59e2f905e4ff 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1702,7 +1702,7 @@ static int generic_delete_lease(struct file *filp)
 			break;
 	}
 	trace_generic_delete_lease(inode, fl);
-	if (fl)
+	if (fl && IS_LEASE(fl))
 		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
 	spin_unlock(&inode->i_lock);
 	locks_dispose_list(&dispose);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3550a9c87616..c06a1ba80d73 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3897,11 +3897,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		status = nfs4_setlease(dp);
 		goto out;
 	}
-	atomic_inc(&fp->fi_delegees);
 	if (fp->fi_had_conflict) {
 		status = -EAGAIN;
 		goto out_unlock;
 	}
+	atomic_inc(&fp->fi_delegees);
 	hash_delegation_locked(dp, fp);
 	status = 0;
 out_unlock:
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index c991616acca9..bff8567aa42d 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -259,16 +259,15 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 	struct fsnotify_event *kevent;
 	char __user *start;
 	int ret;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	start = buf;
 	group = file->private_data;
 
 	pr_debug("%s: group=%p\n", __func__, group);
 
+	add_wait_queue(&group->notification_waitq, &wait);
 	while (1) {
-		prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
 		mutex_lock(&group->notification_mutex);
 		kevent = get_one_event(group, count);
 		mutex_unlock(&group->notification_mutex);
@@ -289,7 +288,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 
 			if (start != buf)
 				break;
-			schedule();
+
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 			continue;
 		}
 
@@ -318,8 +318,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 		buf += ret;
 		count -= ret;
 	}
+	remove_wait_queue(&group->notification_waitq, &wait);
 
-	finish_wait(&group->notification_waitq, &wait);
 	if (start != buf && ret != -EFAULT)
 		ret = buf - start;
 	return ret;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 79b5af5e6a7b..cecd875653e4 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2023,11 +2023,8 @@ leave:
 	dlm_lockres_drop_inflight_ref(dlm, res);
 	spin_unlock(&res->spinlock);
 
-	if (ret < 0) {
+	if (ret < 0)
 		mlog_errno(ret);
-		if (newlock)
-			dlm_lock_put(newlock);
-	}
 
 	return ret;
 }
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b931e04e3388..914c121ec890 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     struct inode *inode,
 				     const char *symname);
 
+static int ocfs2_double_lock(struct ocfs2_super *osb,
+			     struct buffer_head **bh1,
+			     struct inode *inode1,
+			     struct buffer_head **bh2,
+			     struct inode *inode2,
+			     int rename);
+
+static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
 
@@ -678,8 +686,10 @@ static int ocfs2_link(struct dentry *old_dentry,
 {
 	handle_t *handle;
 	struct inode *inode = old_dentry->d_inode;
+	struct inode *old_dir = old_dentry->d_parent->d_inode;
 	int err;
 	struct buffer_head *fe_bh = NULL;
+	struct buffer_head *old_dir_bh = NULL;
 	struct buffer_head *parent_fe_bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
@@ -696,19 +706,33 @@ static int ocfs2_link(struct dentry *old_dentry,
 
 	dquot_initialize(dir);
 
-	err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT);
+	err = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
+			&parent_fe_bh, dir, 0);
 	if (err < 0) {
 		if (err != -ENOENT)
 			mlog_errno(err);
 		return err;
 	}
 
+	/* make sure both dirs have bhs
+	 * get an extra ref on old_dir_bh if old==new */
+	if (!parent_fe_bh) {
+		if (old_dir_bh) {
+			parent_fe_bh = old_dir_bh;
+			get_bh(parent_fe_bh);
+		} else {
+			mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str);
+			err = -EIO;
+			goto out;
+		}
+	}
+
 	if (!dir->i_nlink) {
 		err = -ENOENT;
 		goto out;
 	}
 
-	err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+	err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name,
 			old_dentry->d_name.len, &old_de_ino);
 	if (err) {
 		err = -ENOENT;
@@ -801,10 +825,11 @@ out_unlock_inode:
 	ocfs2_inode_unlock(inode, 1);
 
 out:
-	ocfs2_inode_unlock(dir, 1);
+	ocfs2_double_unlock(old_dir, dir);
 
 	brelse(fe_bh);
 	brelse(parent_fe_bh);
+	brelse(old_dir_bh);
 
 	ocfs2_free_dir_lookup_result(&lookup);
 
@@ -1072,14 +1097,15 @@ static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
 }
 
 /*
- * The only place this should be used is rename!
+ * The only place this should be used is rename and link!
  * if they have the same id, then the 1st one is the only one locked.
  */
 static int ocfs2_double_lock(struct ocfs2_super *osb,
 			     struct buffer_head **bh1,
 			     struct inode *inode1,
 			     struct buffer_head **bh2,
-			     struct inode *inode2)
+			     struct inode *inode2,
+			     int rename)
 {
 	int status;
 	int inode1_is_ancestor, inode2_is_ancestor;
@@ -1127,7 +1153,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 		}
 		/* lock id2 */
 		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
-						 OI_LS_RENAME1);
+				rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
@@ -1136,7 +1162,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	/* lock id1 */
-	status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2);
+	status = ocfs2_inode_lock_nested(inode1, bh1, 1,
+			rename == 1 ?  OI_LS_RENAME2 : OI_LS_PARENT);
 	if (status < 0) {
 		/*
 		 * An error return must mean that no cluster locks
@@ -1252,7 +1279,7 @@ static int ocfs2_rename(struct inode *old_dir,
 
 	/* if old and new are the same, this'll just do one lock. */
 	status = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
-				   &new_dir_bh, new_dir);
+				   &new_dir_bh, new_dir, 1);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 3ca9b751f122..b95dc32a6e6b 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -196,8 +196,8 @@ struct acpi_processor_flags {
 struct acpi_processor {
 	acpi_handle handle;
 	u32 acpi_id;
-	u32 apic_id;
-	u32 id;
+	u32 phys_id;	/* CPU hardware ID such as APIC ID for x86 */
+	u32 id;		/* CPU logical ID allocated by OS */
 	u32 pblk;
 	int performance_platform_limit;
 	int throttling_platform_limit;
@@ -310,8 +310,8 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 #endif				/* CONFIG_CPU_FREQ */
 
 /* in processor_core.c */
-int acpi_get_apicid(acpi_handle, int type, u32 acpi_id);
-int acpi_map_cpuid(int apic_id, u32 acpi_id);
+int acpi_get_phys_id(acpi_handle, int type, u32 acpi_id);
+int acpi_map_cpuid(int phys_id, u32 acpi_id);
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
 
 /* in processor_pdc.c */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 08848050922e..db284bff29dc 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -136,8 +136,12 @@ static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 
 static inline void __tlb_reset_range(struct mmu_gather *tlb)
 {
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
+	if (tlb->fullmm) {
+		tlb->start = tlb->end = ~0;
+	} else {
+		tlb->start = TASK_SIZE;
+		tlb->end = 0;
+	}
 }
 
 /*
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 856d381b1d5b..d459cd17b477 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -147,8 +147,8 @@ void acpi_numa_arch_fixup(void);
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
-int acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu);
-int acpi_unmap_lsapic(int cpu);
+int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu);
+int acpi_unmap_cpu(int cpu);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8aded9ab2e4e..5735e7130d63 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -34,7 +34,6 @@ struct blk_mq_hw_ctx {
 	unsigned long		flags;		/* BLK_MQ_F_* flags */
 
 	struct request_queue	*queue;
-	unsigned int		queue_num;
 	struct blk_flush_queue	*fq;
 
 	void			*driver_data;
@@ -54,7 +53,7 @@ struct blk_mq_hw_ctx {
 	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
 
 	unsigned int		numa_node;
-	unsigned int		cmd_size;	/* per-request extra data */
+	unsigned int		queue_num;
 
 	atomic_t		nr_active;
 
@@ -195,13 +194,16 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
+int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, int error);
 void __blk_mq_end_request(struct request *rq, int error);
 
 void blk_mq_requeue_request(struct request *rq);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head);
+void blk_mq_cancel_requeue_work(struct request_queue *q);
 void blk_mq_kick_requeue_list(struct request_queue *q);
+void blk_mq_abort_requeue_list(struct request_queue *q);
 void blk_mq_complete_request(struct request *rq);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
@@ -212,6 +214,8 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_unfreeze_queue(struct request_queue *q);
+void blk_mq_freeze_queue_start(struct request_queue *q);
 
 /*
  * Driver command data is immediately after the request. So subtract request
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 445d59231bc4..c294e3e25e37 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -190,6 +190,7 @@ enum rq_flag_bits {
 	__REQ_PM,		/* runtime pm request */
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
+	__REQ_NO_TIMEOUT,	/* requests may never expire */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -243,5 +244,6 @@ enum rq_flag_bits {
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
+#define REQ_NO_TIMEOUT		(1ULL << __REQ_NO_TIMEOUT)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 5d86416d35f2..61b19c46bdb3 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -87,8 +87,8 @@ struct ceph_osd_req_op {
 			struct ceph_osd_data osd_data;
 		} extent;
 		struct {
-			__le32 name_len;
-			__le32 value_len;
+			u32 name_len;
+			u32 value_len;
 			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
 			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
 			struct ceph_osd_data osd_data;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index a1c81f80978e..33063f872ee3 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -215,7 +215,7 @@ static __always_inline void __read_once_size(volatile void *p, void *res, int si
 	}
 }
 
-static __always_inline void __assign_once_size(volatile void *p, void *res, int size)
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
 {
 	switch (size) {
 	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
@@ -235,15 +235,15 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int
 /*
  * Prevent the compiler from merging or refetching reads or writes. The
  * compiler is also forbidden from reordering successive instances of
- * READ_ONCE, ASSIGN_ONCE and ACCESS_ONCE (see below), but only when the
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
  * compiler is aware of some particular ordering.  One way to make the
  * compiler aware of ordering is to put the two invocations of READ_ONCE,
- * ASSIGN_ONCE or ACCESS_ONCE() in different C statements.
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
  *
  * In contrast to ACCESS_ONCE these two macros will also work on aggregate
  * data types like structs or unions. If the size of the accessed data
  * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and ASSIGN_ONCE()  will fall back to memcpy and print a
+ * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
  * compile-time warning.
  *
  * Their two major use cases are: (1) Mediating communication between
@@ -257,8 +257,8 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int
 #define READ_ONCE(x) \
 	({ typeof(x) __val; __read_once_size(&x, &__val, sizeof(__val)); __val; })
 
-#define ASSIGN_ONCE(val, x) \
-	({ typeof(x) __val; __val = val; __assign_once_size(&x, &__val, sizeof(__val)); __val; })
+#define WRITE_ONCE(x, val) \
+	({ typeof(x) __val; __val = val; __write_once_size(&x, &__val, sizeof(__val)); __val; })
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f90c0282c114..42efe13077b6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,7 +135,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
+#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 290db1269c4c..75ae2e2631fc 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -13,11 +13,54 @@
  * Copyright (C) 2009 Jason Wessel <jason.wessel@windriver.com>
  */
 
+/* Shifted versions of the command enable bits are be used if the command
+ * has no arguments (see kdb_check_flags). This allows commands, such as
+ * go, to have different permissions depending upon whether it is called
+ * with an argument.
+ */
+#define KDB_ENABLE_NO_ARGS_SHIFT 10
+
 typedef enum {
-	KDB_REPEAT_NONE = 0,	/* Do not repeat this command */
-	KDB_REPEAT_NO_ARGS,	/* Repeat the command without arguments */
-	KDB_REPEAT_WITH_ARGS,	/* Repeat the command including its arguments */
-} kdb_repeat_t;
+	KDB_ENABLE_ALL = (1 << 0), /* Enable everything */
+	KDB_ENABLE_MEM_READ = (1 << 1),
+	KDB_ENABLE_MEM_WRITE = (1 << 2),
+	KDB_ENABLE_REG_READ = (1 << 3),
+	KDB_ENABLE_REG_WRITE = (1 << 4),
+	KDB_ENABLE_INSPECT = (1 << 5),
+	KDB_ENABLE_FLOW_CTRL = (1 << 6),
+	KDB_ENABLE_SIGNAL = (1 << 7),
+	KDB_ENABLE_REBOOT = (1 << 8),
+	/* User exposed values stop here, all remaining flags are
+	 * exclusively used to describe a commands behaviour.
+	 */
+
+	KDB_ENABLE_ALWAYS_SAFE = (1 << 9),
+	KDB_ENABLE_MASK = (1 << KDB_ENABLE_NO_ARGS_SHIFT) - 1,
+
+	KDB_ENABLE_ALL_NO_ARGS = KDB_ENABLE_ALL << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_MEM_READ_NO_ARGS = KDB_ENABLE_MEM_READ
+				      << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_MEM_WRITE_NO_ARGS = KDB_ENABLE_MEM_WRITE
+				       << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_REG_READ_NO_ARGS = KDB_ENABLE_REG_READ
+				      << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_REG_WRITE_NO_ARGS = KDB_ENABLE_REG_WRITE
+				       << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_INSPECT_NO_ARGS = KDB_ENABLE_INSPECT
+				     << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_FLOW_CTRL_NO_ARGS = KDB_ENABLE_FLOW_CTRL
+				       << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_SIGNAL_NO_ARGS = KDB_ENABLE_SIGNAL
+				    << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_REBOOT_NO_ARGS = KDB_ENABLE_REBOOT
+				    << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_ALWAYS_SAFE_NO_ARGS = KDB_ENABLE_ALWAYS_SAFE
+					 << KDB_ENABLE_NO_ARGS_SHIFT,
+	KDB_ENABLE_MASK_NO_ARGS = KDB_ENABLE_MASK << KDB_ENABLE_NO_ARGS_SHIFT,
+
+	KDB_REPEAT_NO_ARGS = 0x40000000, /* Repeat the command w/o arguments */
+	KDB_REPEAT_WITH_ARGS = 0x80000000, /* Repeat the command with args */
+} kdb_cmdflags_t;
 
 typedef int (*kdb_func_t)(int, const char **);
 
@@ -62,6 +105,7 @@ extern atomic_t kdb_event;
 #define KDB_BADLENGTH	(-19)
 #define KDB_NOBP	(-20)
 #define KDB_BADADDR	(-21)
+#define KDB_NOPERM	(-22)
 
 /*
  * kdb_diemsg
@@ -146,17 +190,17 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos)
 
 /* Dynamic kdb shell command registration */
 extern int kdb_register(char *, kdb_func_t, char *, char *, short);
-extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
-			       short, kdb_repeat_t);
+extern int kdb_register_flags(char *, kdb_func_t, char *, char *,
+			      short, kdb_cmdflags_t);
 extern int kdb_unregister(char *);
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
 static inline void kdb_init(int level) {}
 static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
 			       char *help, short minlen) { return 0; }
-static inline int kdb_register_repeat(char *cmd, kdb_func_t func, char *usage,
-				      char *help, short minlen,
-				      kdb_repeat_t repeat) { return 0; }
+static inline int kdb_register_flags(char *cmd, kdb_func_t func, char *usage,
+				     char *help, short minlen,
+				     kdb_cmdflags_t flags) { return 0; }
 static inline int kdb_unregister(char *cmd) { return 0; }
 #endif	/* CONFIG_KGDB_KDB */
 enum {
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 375af80bde7d..f767a0de611f 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -137,6 +137,7 @@ struct sdhci_host {
 #define SDHCI_SDR104_NEEDS_TUNING (1<<10)	/* SDR104/HS200 needs tuning */
 #define SDHCI_USING_RETUNING_TIMER (1<<11)	/* Host is using a retuning timer for the card */
 #define SDHCI_USE_64_BIT_DMA	(1<<12)	/* Use 64-bit DMA */
+#define SDHCI_HS400_TUNING	(1<<13)	/* Tuning for HS400 */
 
 	unsigned int version;	/* SDHCI spec. version */
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 47921c291dd6..642d426a668f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -852,11 +852,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	3. Update dev->stats asynchronously and atomically, and define
  *	   neither operation.
  *
- * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid);
+ * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);
  *	If device support VLAN filtering this function is called when a
  *	VLAN id is registered.
  *
- * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
+ * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);
  *	If device support VLAN filtering this function is called when a
  *	VLAN id is unregistered.
  *
@@ -2096,7 +2096,7 @@ extern rwlock_t				dev_base_lock;		/* Device list lock */
 	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_in_bond_rcu(bond, slave)	\
 		for_each_netdev_rcu(&init_net, slave)	\
-			if (netdev_master_upper_dev_get_rcu(slave) == bond)
+			if (netdev_master_upper_dev_get_rcu(slave) == (bond))
 #define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
 
 static inline struct net_device *next_net_device(struct net_device *dev)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84ccb1f9..4f7a61ca4b39 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,11 +79,6 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs {
-	__u64		abi;
-	struct pt_regs	*regs;
-};
-
 struct task_struct;
 
 /*
@@ -610,7 +605,14 @@ struct perf_sample_data {
 		u32	reserved;
 	}				cpu_entry;
 	struct perf_callchain_entry	*callchain;
+
+	/*
+	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
+	 * on arch details.
+	 */
 	struct perf_regs		regs_user;
+	struct pt_regs			regs_user_copy;
+
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 } ____cacheline_aligned;
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 3c73d5fe18be..a5f98d53d732 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,11 +1,19 @@
 #ifndef _LINUX_PERF_REGS_H
 #define _LINUX_PERF_REGS_H
 
+struct perf_regs {
+	__u64		abi;
+	struct pt_regs	*regs;
+};
+
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy);
 #else
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
@@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_NONE;
 }
+
+static inline void perf_get_regs_user(struct perf_regs *regs_user,
+				      struct pt_regs *regs,
+				      struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_HAVE_PERF_REGS */
 #endif /* _LINUX_PERF_REGS_H */
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c0c2bce6b0b7..d9d7e7e56352 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -37,6 +37,16 @@ struct anon_vma {
 	atomic_t refcount;
 
 	/*
+	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 *
+	 * This counter is used for making decision about reusing anon_vma
+	 * instead of forking new one. See comments in function anon_vma_clone.
+	 */
+	unsigned degree;
+
+	struct anon_vma *parent;	/* Parent of this anon_vma */
+
+	/*
 	 * NOTE: the LSB of the rb_root.rb_node is set by
 	 * mm_take_all_locks() _after_ taking the above lock. So the
 	 * rb_root must only be read/written after taking the above lock
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index a219be961c0a..00048339c23e 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -177,7 +177,6 @@ int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
-void set_page_dirty_balance(struct page *page);
 void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 430cfaf92285..db81c65b8f48 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -135,7 +135,6 @@ int	se_dev_set_is_nonrot(struct se_device *, int);
 int	se_dev_set_emulate_rest_reord(struct se_device *dev, int);
 int	se_dev_set_queue_depth(struct se_device *, u32);
 int	se_dev_set_max_sectors(struct se_device *, u32);
-int	se_dev_set_fabric_max_sectors(struct se_device *, u32);
 int	se_dev_set_optimal_sectors(struct se_device *, u32);
 int	se_dev_set_block_size(struct se_device *, u32);
 
diff --git a/include/target/target_core_backend_configfs.h b/include/target/target_core_backend_configfs.h
index 3247d7530107..186f7a923570 100644
--- a/include/target/target_core_backend_configfs.h
+++ b/include/target/target_core_backend_configfs.h
@@ -98,8 +98,6 @@ static struct target_backend_dev_attrib_attribute _backend##_dev_attrib_##_name
 	TB_DEV_ATTR(_backend, block_size, S_IRUGO | S_IWUSR);		\
 	DEF_TB_DEV_ATTRIB_RO(_backend, hw_max_sectors);			\
 	TB_DEV_ATTR_RO(_backend, hw_max_sectors);			\
-	DEF_TB_DEV_ATTRIB(_backend, fabric_max_sectors);		\
-	TB_DEV_ATTR(_backend, fabric_max_sectors, S_IRUGO | S_IWUSR);	\
 	DEF_TB_DEV_ATTRIB(_backend, optimal_sectors);			\
 	TB_DEV_ATTR(_backend, optimal_sectors, S_IRUGO | S_IWUSR);	\
 	DEF_TB_DEV_ATTRIB_RO(_backend, hw_queue_depth);			\
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 397fb635766a..4a8795a87b9e 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -77,8 +77,6 @@
 #define DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT	0
 /* Default max_write_same_len, disabled by default */
 #define DA_MAX_WRITE_SAME_LEN			0
-/* Default max transfer length */
-#define DA_FABRIC_MAX_SECTORS			8192
 /* Use a model alias based on the configfs backend device name */
 #define DA_EMULATE_MODEL_ALIAS			0
 /* Emulation for Direct Page Out */
@@ -694,7 +692,6 @@ struct se_dev_attrib {
 	u32		hw_block_size;
 	u32		block_size;
 	u32		hw_max_sectors;
-	u32		fabric_max_sectors;
 	u32		optimal_sectors;
 	u32		hw_queue_depth;
 	u32		queue_depth;
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 7543b3e51331..e063effe0cc1 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -5,7 +5,7 @@
 
 /*
  * FMODE_EXEC is 0x20
- * FMODE_NONOTIFY is 0x1000000
+ * FMODE_NONOTIFY is 0x4000000
  * These cannot be used by userspace O_* until internal and external open
  * flags are split.
  * -Eric Paris
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 7acef41fc209..af94f31e33ac 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -128,27 +128,34 @@ struct kfd_ioctl_get_process_apertures_args {
 	uint32_t pad;
 };
 
-#define KFD_IOC_MAGIC 'K'
+#define AMDKFD_IOCTL_BASE 'K'
+#define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
+#define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
+#define AMDKFD_IOW(nr, type)		_IOW(AMDKFD_IOCTL_BASE, nr, type)
+#define AMDKFD_IOWR(nr, type)		_IOWR(AMDKFD_IOCTL_BASE, nr, type)
 
-#define KFD_IOC_GET_VERSION \
-		_IOR(KFD_IOC_MAGIC, 1, struct kfd_ioctl_get_version_args)
+#define AMDKFD_IOC_GET_VERSION			\
+		AMDKFD_IOR(0x01, struct kfd_ioctl_get_version_args)
 
-#define KFD_IOC_CREATE_QUEUE \
-		_IOWR(KFD_IOC_MAGIC, 2, struct kfd_ioctl_create_queue_args)
+#define AMDKFD_IOC_CREATE_QUEUE			\
+		AMDKFD_IOWR(0x02, struct kfd_ioctl_create_queue_args)
 
-#define KFD_IOC_DESTROY_QUEUE \
-	_IOWR(KFD_IOC_MAGIC, 3, struct kfd_ioctl_destroy_queue_args)
+#define AMDKFD_IOC_DESTROY_QUEUE		\
+		AMDKFD_IOWR(0x03, struct kfd_ioctl_destroy_queue_args)
 
-#define KFD_IOC_SET_MEMORY_POLICY \
-	_IOW(KFD_IOC_MAGIC, 4, struct kfd_ioctl_set_memory_policy_args)
+#define AMDKFD_IOC_SET_MEMORY_POLICY		\
+		AMDKFD_IOW(0x04, struct kfd_ioctl_set_memory_policy_args)
 
-#define KFD_IOC_GET_CLOCK_COUNTERS \
-	_IOWR(KFD_IOC_MAGIC, 5, struct kfd_ioctl_get_clock_counters_args)
+#define AMDKFD_IOC_GET_CLOCK_COUNTERS		\
+		AMDKFD_IOWR(0x05, struct kfd_ioctl_get_clock_counters_args)
 
-#define KFD_IOC_GET_PROCESS_APERTURES \
-	_IOR(KFD_IOC_MAGIC, 6, struct kfd_ioctl_get_process_apertures_args)
+#define AMDKFD_IOC_GET_PROCESS_APERTURES	\
+		AMDKFD_IOR(0x06, struct kfd_ioctl_get_process_apertures_args)
 
-#define KFD_IOC_UPDATE_QUEUE \
-	_IOW(KFD_IOC_MAGIC, 7, struct kfd_ioctl_update_queue_args)
+#define AMDKFD_IOC_UPDATE_QUEUE			\
+		AMDKFD_IOW(0x07, struct kfd_ioctl_update_queue_args)
+
+#define AMDKFD_COMMAND_START		0x01
+#define AMDKFD_COMMAND_END		0x08
 
 #endif
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 3a6dcaa359b7..f714e8633352 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -174,6 +174,10 @@ enum ovs_packet_attr {
 	OVS_PACKET_ATTR_USERDATA,    /* OVS_ACTION_ATTR_USERSPACE arg. */
 	OVS_PACKET_ATTR_EGRESS_TUN_KEY,  /* Nested OVS_TUNNEL_KEY_ATTR_*
 					    attributes. */
+	OVS_PACKET_ATTR_UNUSED1,
+	OVS_PACKET_ATTR_UNUSED2,
+	OVS_PACKET_ATTR_PROBE,      /* Packet operation is a feature probe,
+				       error logging should be suppressed. */
 	__OVS_PACKET_ATTR_MAX
 };
 
diff --git a/include/xen/interface/nmi.h b/include/xen/interface/nmi.h
new file mode 100644
index 000000000000..b47d9d06fade
--- /dev/null
+++ b/include/xen/interface/nmi.h
@@ -0,0 +1,51 @@
+/******************************************************************************
+ * nmi.h
+ *
+ * NMI callback registration and reason codes.
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_NMI_H__
+#define __XEN_PUBLIC_NMI_H__
+
+#include <xen/interface/xen.h>
+
+/*
+ * NMI reason codes:
+ * Currently these are x86-specific, stored in arch_shared_info.nmi_reason.
+ */
+ /* I/O-check error reported via ISA port 0x61, bit 6. */
+#define _XEN_NMIREASON_io_error     0
+#define XEN_NMIREASON_io_error      (1UL << _XEN_NMIREASON_io_error)
+ /* PCI SERR reported via ISA port 0x61, bit 7. */
+#define _XEN_NMIREASON_pci_serr     1
+#define XEN_NMIREASON_pci_serr      (1UL << _XEN_NMIREASON_pci_serr)
+ /* Unknown hardware-generated NMI. */
+#define _XEN_NMIREASON_unknown      2
+#define XEN_NMIREASON_unknown       (1UL << _XEN_NMIREASON_unknown)
+
+/*
+ * long nmi_op(unsigned int cmd, void *arg)
+ * NB. All ops return zero on success, else a negative error code.
+ */
+
+/*
+ * Register NMI callback for this (calling) VCPU. Currently this only makes
+ * sense for domain 0, vcpu 0. All other callers will be returned EINVAL.
+ * arg == pointer to xennmi_callback structure.
+ */
+#define XENNMI_register_callback   0
+struct xennmi_callback {
+    unsigned long handler_address;
+    unsigned long pad;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xennmi_callback);
+
+/*
+ * Deregister NMI callback for this (calling) VCPU.
+ * arg == NULL.
+ */
+#define XENNMI_unregister_callback 1
+
+#endif /* __XEN_PUBLIC_NMI_H__ */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 1adf62b39b96..07ce18ca71e0 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -27,6 +27,9 @@
  * version 2. This program is licensed "as is" without any warranty of any
  * kind, whether express or implied.
  */
+
+#define pr_fmt(fmt) "KGDB: " fmt
+
 #include <linux/pid_namespace.h>
 #include <linux/clocksource.h>
 #include <linux/serial_core.h>
@@ -196,8 +199,8 @@ int __weak kgdb_validate_break_address(unsigned long addr)
 		return err;
 	err = kgdb_arch_remove_breakpoint(&tmp);
 	if (err)
-		printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
-		   "memory destroyed at: %lx", addr);
+		pr_err("Critical breakpoint error, kernel memory destroyed at: %lx\n",
+		       addr);
 	return err;
 }
 
@@ -256,8 +259,8 @@ int dbg_activate_sw_breakpoints(void)
 		error = kgdb_arch_set_breakpoint(&kgdb_break[i]);
 		if (error) {
 			ret = error;
-			printk(KERN_INFO "KGDB: BP install failed: %lx",
-			       kgdb_break[i].bpt_addr);
+			pr_info("BP install failed: %lx\n",
+				kgdb_break[i].bpt_addr);
 			continue;
 		}
 
@@ -319,8 +322,8 @@ int dbg_deactivate_sw_breakpoints(void)
 			continue;
 		error = kgdb_arch_remove_breakpoint(&kgdb_break[i]);
 		if (error) {
-			printk(KERN_INFO "KGDB: BP remove failed: %lx\n",
-			       kgdb_break[i].bpt_addr);
+			pr_info("BP remove failed: %lx\n",
+				kgdb_break[i].bpt_addr);
 			ret = error;
 		}
 
@@ -367,7 +370,7 @@ int dbg_remove_all_break(void)
 			goto setundefined;
 		error = kgdb_arch_remove_breakpoint(&kgdb_break[i]);
 		if (error)
-			printk(KERN_ERR "KGDB: breakpoint remove failed: %lx\n",
+			pr_err("breakpoint remove failed: %lx\n",
 			       kgdb_break[i].bpt_addr);
 setundefined:
 		kgdb_break[i].state = BP_UNDEFINED;
@@ -400,9 +403,9 @@ static int kgdb_io_ready(int print_wait)
 	if (print_wait) {
 #ifdef CONFIG_KGDB_KDB
 		if (!dbg_kdb_mode)
-			printk(KERN_CRIT "KGDB: waiting... or $3#33 for KDB\n");
+			pr_crit("waiting... or $3#33 for KDB\n");
 #else
-		printk(KERN_CRIT "KGDB: Waiting for remote debugger\n");
+		pr_crit("Waiting for remote debugger\n");
 #endif
 	}
 	return 1;
@@ -430,8 +433,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 		exception_level = 0;
 		kgdb_skipexception(ks->ex_vector, ks->linux_regs);
 		dbg_activate_sw_breakpoints();
-		printk(KERN_CRIT "KGDB: re-enter error: breakpoint removed %lx\n",
-			addr);
+		pr_crit("re-enter error: breakpoint removed %lx\n", addr);
 		WARN_ON_ONCE(1);
 
 		return 1;
@@ -444,7 +446,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 		panic("Recursive entry to debugger");
 	}
 
-	printk(KERN_CRIT "KGDB: re-enter exception: ALL breakpoints killed\n");
+	pr_crit("re-enter exception: ALL breakpoints killed\n");
 #ifdef CONFIG_KGDB_KDB
 	/* Allow kdb to debug itself one level */
 	return 0;
@@ -471,6 +473,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 	int cpu;
 	int trace_on = 0;
 	int online_cpus = num_online_cpus();
+	u64 time_left;
 
 	kgdb_info[ks->cpu].enter_kgdb++;
 	kgdb_info[ks->cpu].exception_state |= exception_state;
@@ -595,9 +598,13 @@ return_normal:
 	/*
 	 * Wait for the other CPUs to be notified and be waiting for us:
 	 */
-	while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
-				atomic_read(&slaves_in_kgdb)) != online_cpus)
+	time_left = loops_per_jiffy * HZ;
+	while (kgdb_do_roundup && --time_left &&
+	       (atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) !=
+		   online_cpus)
 		cpu_relax();
+	if (!time_left)
+		pr_crit("KGDB: Timed out waiting for secondary CPUs.\n");
 
 	/*
 	 * At this point the primary processor is completely
@@ -795,15 +802,15 @@ static struct console kgdbcons = {
 static void sysrq_handle_dbg(int key)
 {
 	if (!dbg_io_ops) {
-		printk(KERN_CRIT "ERROR: No KGDB I/O module available\n");
+		pr_crit("ERROR: No KGDB I/O module available\n");
 		return;
 	}
 	if (!kgdb_connected) {
 #ifdef CONFIG_KGDB_KDB
 		if (!dbg_kdb_mode)
-			printk(KERN_CRIT "KGDB or $3#33 for KDB\n");
+			pr_crit("KGDB or $3#33 for KDB\n");
 #else
-		printk(KERN_CRIT "Entering KGDB\n");
+		pr_crit("Entering KGDB\n");
 #endif
 	}
 
@@ -945,7 +952,7 @@ static void kgdb_initial_breakpoint(void)
 {
 	kgdb_break_asap = 0;
 
-	printk(KERN_CRIT "kgdb: Waiting for connection from remote gdb...\n");
+	pr_crit("Waiting for connection from remote gdb...\n");
 	kgdb_breakpoint();
 }
 
@@ -964,8 +971,7 @@ int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
 	if (dbg_io_ops) {
 		spin_unlock(&kgdb_registration_lock);
 
-		printk(KERN_ERR "kgdb: Another I/O driver is already "
-				"registered with KGDB.\n");
+		pr_err("Another I/O driver is already registered with KGDB\n");
 		return -EBUSY;
 	}
 
@@ -981,8 +987,7 @@ int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
 
 	spin_unlock(&kgdb_registration_lock);
 
-	printk(KERN_INFO "kgdb: Registered I/O driver %s.\n",
-	       new_dbg_io_ops->name);
+	pr_info("Registered I/O driver %s\n", new_dbg_io_ops->name);
 
 	/* Arm KGDB now. */
 	kgdb_register_callbacks();
@@ -1017,8 +1022,7 @@ void kgdb_unregister_io_module(struct kgdb_io *old_dbg_io_ops)
 
 	spin_unlock(&kgdb_registration_lock);
 
-	printk(KERN_INFO
-		"kgdb: Unregistered I/O driver %s, debugger disabled.\n",
+	pr_info("Unregistered I/O driver %s, debugger disabled\n",
 		old_dbg_io_ops->name);
 }
 EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index b20d544f20c2..e1dbf4a2c69e 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -531,22 +531,29 @@ void __init kdb_initbptab(void)
 	for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++)
 		bp->bp_free = 1;
 
-	kdb_register_repeat("bp", kdb_bp, "[<vaddr>]",
-		"Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("bl", kdb_bp, "[<vaddr>]",
-		"Display breakpoints", 0, KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("bp", kdb_bp, "[<vaddr>]",
+		"Set/Display breakpoints", 0,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("bl", kdb_bp, "[<vaddr>]",
+		"Display breakpoints", 0,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
 	if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT)
-		kdb_register_repeat("bph", kdb_bp, "[<vaddr>]",
-		"[datar [length]|dataw [length]]   Set hw brk", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("bc", kdb_bc, "<bpnum>",
-		"Clear Breakpoint", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("be", kdb_bc, "<bpnum>",
-		"Enable Breakpoint", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("bd", kdb_bc, "<bpnum>",
-		"Disable Breakpoint", 0, KDB_REPEAT_NONE);
-
-	kdb_register_repeat("ss", kdb_ss, "",
-		"Single Step", 1, KDB_REPEAT_NO_ARGS);
+		kdb_register_flags("bph", kdb_bp, "[<vaddr>]",
+		"[datar [length]|dataw [length]]   Set hw brk", 0,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("bc", kdb_bc, "<bpnum>",
+		"Clear Breakpoint", 0,
+		KDB_ENABLE_FLOW_CTRL);
+	kdb_register_flags("be", kdb_bc, "<bpnum>",
+		"Enable Breakpoint", 0,
+		KDB_ENABLE_FLOW_CTRL);
+	kdb_register_flags("bd", kdb_bc, "<bpnum>",
+		"Disable Breakpoint", 0,
+		KDB_ENABLE_FLOW_CTRL);
+
+	kdb_register_flags("ss", kdb_ss, "",
+		"Single Step", 1,
+		KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS);
 	/*
 	 * Architecture dependent initialization.
 	 */
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index 8859ca34dcfe..15e1a7af5dd0 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -129,6 +129,10 @@ int kdb_stub(struct kgdb_state *ks)
 		ks->pass_exception = 1;
 		KDB_FLAG_SET(CATASTROPHIC);
 	}
+	/* set CATASTROPHIC if the system contains unresponsive processors */
+	for_each_online_cpu(i)
+		if (!kgdb_info[i].enter_kgdb)
+			KDB_FLAG_SET(CATASTROPHIC);
 	if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
 		KDB_STATE_CLEAR(SSBPT);
 		KDB_STATE_CLEAR(DOING_SS);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 379650b984f8..f191bddf64b8 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/ctype.h>
+#include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/kmsg_dump.h>
@@ -23,6 +24,7 @@
 #include <linux/vmalloc.h>
 #include <linux/atomic.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
@@ -42,6 +44,12 @@
 #include <linux/slab.h>
 #include "kdb_private.h"
 
+#undef	MODULE_PARAM_PREFIX
+#define	MODULE_PARAM_PREFIX "kdb."
+
+static int kdb_cmd_enabled = CONFIG_KDB_DEFAULT_ENABLE;
+module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600);
+
 #define GREP_LEN 256
 char kdb_grep_string[GREP_LEN];
 int kdb_grepping_flag;
@@ -121,6 +129,7 @@ static kdbmsg_t kdbmsgs[] = {
 	KDBMSG(BADLENGTH, "Invalid length field"),
 	KDBMSG(NOBP, "No Breakpoint exists"),
 	KDBMSG(BADADDR, "Invalid address"),
+	KDBMSG(NOPERM, "Permission denied"),
 };
 #undef KDBMSG
 
@@ -188,6 +197,26 @@ struct task_struct *kdb_curr_task(int cpu)
 }
 
 /*
+ * Check whether the flags of the current command and the permissions
+ * of the kdb console has allow a command to be run.
+ */
+static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions,
+				   bool no_args)
+{
+	/* permissions comes from userspace so needs massaging slightly */
+	permissions &= KDB_ENABLE_MASK;
+	permissions |= KDB_ENABLE_ALWAYS_SAFE;
+
+	/* some commands change group when launched with no arguments */
+	if (no_args)
+		permissions |= permissions << KDB_ENABLE_NO_ARGS_SHIFT;
+
+	flags |= KDB_ENABLE_ALL;
+
+	return permissions & flags;
+}
+
+/*
  * kdbgetenv - This function will return the character string value of
  *	an environment variable.
  * Parameters:
@@ -476,6 +505,15 @@ int kdbgetaddrarg(int argc, const char **argv, int *nextarg,
 	kdb_symtab_t symtab;
 
 	/*
+	 * If the enable flags prohibit both arbitrary memory access
+	 * and flow control then there are no reasonable grounds to
+	 * provide symbol lookup.
+	 */
+	if (!kdb_check_flags(KDB_ENABLE_MEM_READ | KDB_ENABLE_FLOW_CTRL,
+			     kdb_cmd_enabled, false))
+		return KDB_NOPERM;
+
+	/*
 	 * Process arguments which follow the following syntax:
 	 *
 	 *  symbol | numeric-address [+/- numeric-offset]
@@ -641,8 +679,13 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
 		if (!s->count)
 			s->usable = 0;
 		if (s->usable)
-			kdb_register(s->name, kdb_exec_defcmd,
-				     s->usage, s->help, 0);
+			/* macros are always safe because when executed each
+			 * internal command re-enters kdb_parse() and is
+			 * safety checked individually.
+			 */
+			kdb_register_flags(s->name, kdb_exec_defcmd, s->usage,
+					   s->help, 0,
+					   KDB_ENABLE_ALWAYS_SAFE);
 		return 0;
 	}
 	if (!s->usable)
@@ -1003,25 +1046,22 @@ int kdb_parse(const char *cmdstr)
 
 	if (i < kdb_max_commands) {
 		int result;
+
+		if (!kdb_check_flags(tp->cmd_flags, kdb_cmd_enabled, argc <= 1))
+			return KDB_NOPERM;
+
 		KDB_STATE_SET(CMD);
 		result = (*tp->cmd_func)(argc-1, (const char **)argv);
 		if (result && ignore_errors && result > KDB_CMD_GO)
 			result = 0;
 		KDB_STATE_CLEAR(CMD);
-		switch (tp->cmd_repeat) {
-		case KDB_REPEAT_NONE:
-			argc = 0;
-			if (argv[0])
-				*(argv[0]) = '\0';
-			break;
-		case KDB_REPEAT_NO_ARGS:
-			argc = 1;
-			if (argv[1])
-				*(argv[1]) = '\0';
-			break;
-		case KDB_REPEAT_WITH_ARGS:
-			break;
-		}
+
+		if (tp->cmd_flags & KDB_REPEAT_WITH_ARGS)
+			return result;
+
+		argc = tp->cmd_flags & KDB_REPEAT_NO_ARGS ? 1 : 0;
+		if (argv[argc])
+			*(argv[argc]) = '\0';
 		return result;
 	}
 
@@ -1921,10 +1961,14 @@ static int kdb_rm(int argc, const char **argv)
  */
 static int kdb_sr(int argc, const char **argv)
 {
+	bool check_mask =
+	    !kdb_check_flags(KDB_ENABLE_ALL, kdb_cmd_enabled, false);
+
 	if (argc != 1)
 		return KDB_ARGCOUNT;
+
 	kdb_trap_printk++;
-	__handle_sysrq(*argv[1], false);
+	__handle_sysrq(*argv[1], check_mask);
 	kdb_trap_printk--;
 
 	return 0;
@@ -2157,6 +2201,8 @@ static void kdb_cpu_status(void)
 	for (start_cpu = -1, i = 0; i < NR_CPUS; i++) {
 		if (!cpu_online(i)) {
 			state = 'F';	/* cpu is offline */
+		} else if (!kgdb_info[i].enter_kgdb) {
+			state = 'D';	/* cpu is online but unresponsive */
 		} else {
 			state = ' ';	/* cpu is responding to kdb */
 			if (kdb_task_state_char(KDB_TSK(i)) == 'I')
@@ -2210,7 +2256,7 @@ static int kdb_cpu(int argc, const char **argv)
 	/*
 	 * Validate cpunum
 	 */
-	if ((cpunum > NR_CPUS) || !cpu_online(cpunum))
+	if ((cpunum > NR_CPUS) || !kgdb_info[cpunum].enter_kgdb)
 		return KDB_BADCPUNUM;
 
 	dbg_switch_cpu = cpunum;
@@ -2375,6 +2421,8 @@ static int kdb_help(int argc, const char **argv)
 			return 0;
 		if (!kt->cmd_name)
 			continue;
+		if (!kdb_check_flags(kt->cmd_flags, kdb_cmd_enabled, true))
+			continue;
 		if (strlen(kt->cmd_usage) > 20)
 			space = "\n                                    ";
 		kdb_printf("%-15.15s %-20s%s%s\n", kt->cmd_name,
@@ -2629,7 +2677,7 @@ static int kdb_grep_help(int argc, const char **argv)
 }
 
 /*
- * kdb_register_repeat - This function is used to register a kernel
+ * kdb_register_flags - This function is used to register a kernel
  * 	debugger command.
  * Inputs:
  *	cmd	Command name
@@ -2641,12 +2689,12 @@ static int kdb_grep_help(int argc, const char **argv)
  *	zero for success, one if a duplicate command.
  */
 #define kdb_command_extend 50	/* arbitrary */
-int kdb_register_repeat(char *cmd,
-			kdb_func_t func,
-			char *usage,
-			char *help,
-			short minlen,
-			kdb_repeat_t repeat)
+int kdb_register_flags(char *cmd,
+		       kdb_func_t func,
+		       char *usage,
+		       char *help,
+		       short minlen,
+		       kdb_cmdflags_t flags)
 {
 	int i;
 	kdbtab_t *kp;
@@ -2694,19 +2742,18 @@ int kdb_register_repeat(char *cmd,
 	kp->cmd_func   = func;
 	kp->cmd_usage  = usage;
 	kp->cmd_help   = help;
-	kp->cmd_flags  = 0;
 	kp->cmd_minlen = minlen;
-	kp->cmd_repeat = repeat;
+	kp->cmd_flags  = flags;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kdb_register_repeat);
+EXPORT_SYMBOL_GPL(kdb_register_flags);
 
 
 /*
  * kdb_register - Compatibility register function for commands that do
  *	not need to specify a repeat state.  Equivalent to
- *	kdb_register_repeat with KDB_REPEAT_NONE.
+ *	kdb_register_flags with flags set to 0.
  * Inputs:
  *	cmd	Command name
  *	func	Function to execute the command
@@ -2721,8 +2768,7 @@ int kdb_register(char *cmd,
 	     char *help,
 	     short minlen)
 {
-	return kdb_register_repeat(cmd, func, usage, help, minlen,
-				   KDB_REPEAT_NONE);
+	return kdb_register_flags(cmd, func, usage, help, minlen, 0);
 }
 EXPORT_SYMBOL_GPL(kdb_register);
 
@@ -2764,80 +2810,109 @@ static void __init kdb_inittab(void)
 	for_each_kdbcmd(kp, i)
 		kp->cmd_name = NULL;
 
-	kdb_register_repeat("md", kdb_md, "<vaddr>",
+	kdb_register_flags("md", kdb_md, "<vaddr>",
 	  "Display Memory Contents, also mdWcN, e.g. md8c1", 1,
-			    KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mdr", kdb_md, "<vaddr> <bytes>",
-	  "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mdp", kdb_md, "<paddr> <bytes>",
-	  "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mds", kdb_md, "<vaddr>",
-	  "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("mm", kdb_mm, "<vaddr> <contents>",
-	  "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS);
-	kdb_register_repeat("go", kdb_go, "[<vaddr>]",
-	  "Continue Execution", 1, KDB_REPEAT_NONE);
-	kdb_register_repeat("rd", kdb_rd, "",
-	  "Display Registers", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("rm", kdb_rm, "<reg> <contents>",
-	  "Modify Registers", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("ef", kdb_ef, "<vaddr>",
-	  "Display exception frame", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("bt", kdb_bt, "[<vaddr>]",
-	  "Stack traceback", 1, KDB_REPEAT_NONE);
-	kdb_register_repeat("btp", kdb_bt, "<pid>",
-	  "Display stack for process <pid>", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
-	  "Backtrace all processes matching state flag", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("btc", kdb_bt, "",
-	  "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("btt", kdb_bt, "<vaddr>",
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("mdr", kdb_md, "<vaddr> <bytes>",
+	  "Display Raw Memory", 0,
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("mdp", kdb_md, "<paddr> <bytes>",
+	  "Display Physical Memory", 0,
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("mds", kdb_md, "<vaddr>",
+	  "Display Memory Symbolically", 0,
+	  KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("mm", kdb_mm, "<vaddr> <contents>",
+	  "Modify Memory Contents", 0,
+	  KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS);
+	kdb_register_flags("go", kdb_go, "[<vaddr>]",
+	  "Continue Execution", 1,
+	  KDB_ENABLE_REG_WRITE | KDB_ENABLE_ALWAYS_SAFE_NO_ARGS);
+	kdb_register_flags("rd", kdb_rd, "",
+	  "Display Registers", 0,
+	  KDB_ENABLE_REG_READ);
+	kdb_register_flags("rm", kdb_rm, "<reg> <contents>",
+	  "Modify Registers", 0,
+	  KDB_ENABLE_REG_WRITE);
+	kdb_register_flags("ef", kdb_ef, "<vaddr>",
+	  "Display exception frame", 0,
+	  KDB_ENABLE_MEM_READ);
+	kdb_register_flags("bt", kdb_bt, "[<vaddr>]",
+	  "Stack traceback", 1,
+	  KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS);
+	kdb_register_flags("btp", kdb_bt, "<pid>",
+	  "Display stack for process <pid>", 0,
+	  KDB_ENABLE_INSPECT);
+	kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]",
+	  "Backtrace all processes matching state flag", 0,
+	  KDB_ENABLE_INSPECT);
+	kdb_register_flags("btc", kdb_bt, "",
+	  "Backtrace current process on each cpu", 0,
+	  KDB_ENABLE_INSPECT);
+	kdb_register_flags("btt", kdb_bt, "<vaddr>",
 	  "Backtrace process given its struct task address", 0,
-			    KDB_REPEAT_NONE);
-	kdb_register_repeat("env", kdb_env, "",
-	  "Show environment variables", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("set", kdb_set, "",
-	  "Set environment variables", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("help", kdb_help, "",
-	  "Display Help Message", 1, KDB_REPEAT_NONE);
-	kdb_register_repeat("?", kdb_help, "",
-	  "Display Help Message", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("cpu", kdb_cpu, "<cpunum>",
-	  "Switch to new cpu", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("kgdb", kdb_kgdb, "",
-	  "Enter kgdb mode", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("ps", kdb_ps, "[<flags>|A]",
-	  "Display active task list", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("pid", kdb_pid, "<pidnum>",
-	  "Switch to another task", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("reboot", kdb_reboot, "",
-	  "Reboot the machine immediately", 0, KDB_REPEAT_NONE);
+	  KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS);
+	kdb_register_flags("env", kdb_env, "",
+	  "Show environment variables", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
+	kdb_register_flags("set", kdb_set, "",
+	  "Set environment variables", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
+	kdb_register_flags("help", kdb_help, "",
+	  "Display Help Message", 1,
+	  KDB_ENABLE_ALWAYS_SAFE);
+	kdb_register_flags("?", kdb_help, "",
+	  "Display Help Message", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
+	kdb_register_flags("cpu", kdb_cpu, "<cpunum>",
+	  "Switch to new cpu", 0,
+	  KDB_ENABLE_ALWAYS_SAFE_NO_ARGS);
+	kdb_register_flags("kgdb", kdb_kgdb, "",
+	  "Enter kgdb mode", 0, 0);
+	kdb_register_flags("ps", kdb_ps, "[<flags>|A]",
+	  "Display active task list", 0,
+	  KDB_ENABLE_INSPECT);
+	kdb_register_flags("pid", kdb_pid, "<pidnum>",
+	  "Switch to another task", 0,
+	  KDB_ENABLE_INSPECT);
+	kdb_register_flags("reboot", kdb_reboot, "",
+	  "Reboot the machine immediately", 0,
+	  KDB_ENABLE_REBOOT);
 #if defined(CONFIG_MODULES)
-	kdb_register_repeat("lsmod", kdb_lsmod, "",
-	  "List loaded kernel modules", 0, KDB_REPEAT_NONE);
+	kdb_register_flags("lsmod", kdb_lsmod, "",
+	  "List loaded kernel modules", 0,
+	  KDB_ENABLE_INSPECT);
 #endif
 #if defined(CONFIG_MAGIC_SYSRQ)
-	kdb_register_repeat("sr", kdb_sr, "<key>",
-	  "Magic SysRq key", 0, KDB_REPEAT_NONE);
+	kdb_register_flags("sr", kdb_sr, "<key>",
+	  "Magic SysRq key", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 #endif
 #if defined(CONFIG_PRINTK)
-	kdb_register_repeat("dmesg", kdb_dmesg, "[lines]",
-	  "Display syslog buffer", 0, KDB_REPEAT_NONE);
+	kdb_register_flags("dmesg", kdb_dmesg, "[lines]",
+	  "Display syslog buffer", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 #endif
 	if (arch_kgdb_ops.enable_nmi) {
-		kdb_register_repeat("disable_nmi", kdb_disable_nmi, "",
-		  "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE);
-	}
-	kdb_register_repeat("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
-	  "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("kill", kdb_kill, "<-signal> <pid>",
-	  "Send a signal to a process", 0, KDB_REPEAT_NONE);
-	kdb_register_repeat("summary", kdb_summary, "",
-	  "Summarize the system", 4, KDB_REPEAT_NONE);
-	kdb_register_repeat("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
-	  "Display per_cpu variables", 3, KDB_REPEAT_NONE);
-	kdb_register_repeat("grephelp", kdb_grep_help, "",
-	  "Display help on | grep", 0, KDB_REPEAT_NONE);
+		kdb_register_flags("disable_nmi", kdb_disable_nmi, "",
+		  "Disable NMI entry to KDB", 0,
+		  KDB_ENABLE_ALWAYS_SAFE);
+	}
+	kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"",
+	  "Define a set of commands, down to endefcmd", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
+	kdb_register_flags("kill", kdb_kill, "<-signal> <pid>",
+	  "Send a signal to a process", 0,
+	  KDB_ENABLE_SIGNAL);
+	kdb_register_flags("summary", kdb_summary, "",
+	  "Summarize the system", 4,
+	  KDB_ENABLE_ALWAYS_SAFE);
+	kdb_register_flags("per_cpu", kdb_per_cpu, "<sym> [<bytes>] [<cpu>]",
+	  "Display per_cpu variables", 3,
+	  KDB_ENABLE_MEM_READ);
+	kdb_register_flags("grephelp", kdb_grep_help, "",
+	  "Display help on | grep", 0,
+	  KDB_ENABLE_ALWAYS_SAFE);
 }
 
 /* Execute any commands defined in kdb_cmds.  */
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 7afd3c8c41d5..eaacd1693954 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -172,10 +172,9 @@ typedef struct _kdbtab {
 	kdb_func_t cmd_func;		/* Function to execute command */
 	char    *cmd_usage;		/* Usage String for this command */
 	char    *cmd_help;		/* Help message for this command */
-	short    cmd_flags;		/* Parsing flags */
 	short    cmd_minlen;		/* Minimum legal # command
 					 * chars required */
-	kdb_repeat_t cmd_repeat;	/* Does command auto repeat on enter? */
+	kdb_cmdflags_t cmd_flags;	/* Command behaviour flags */
 } kdbtab_t;
 
 extern int kdb_bt(int, const char **);	/* KDB display back trace */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2bebc..882f835a0d85 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs)
+				  struct pt_regs *regs,
+				  struct pt_regs *regs_user_copy)
 {
-	if (!user_mode(regs)) {
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		regs_user->abi  = perf_reg_abi(current);
+	if (user_mode(regs)) {
+		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
+	} else if (current->mm) {
+		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs);
+		perf_sample_regs_user(&data->regs_user, regs,
+				      &data->regs_user_copy);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
diff --git a/kernel/exit.c b/kernel/exit.c
index 1ea4369890a3..6806c55475ee 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1287,9 +1287,15 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 static int wait_consider_task(struct wait_opts *wo, int ptrace,
 				struct task_struct *p)
 {
+	/*
+	 * We can race with wait_task_zombie() from another thread.
+	 * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
+	 * can't confuse the checks below.
+	 */
+	int exit_state = ACCESS_ONCE(p->exit_state);
 	int ret;
 
-	if (unlikely(p->exit_state == EXIT_DEAD))
+	if (unlikely(exit_state == EXIT_DEAD))
 		return 0;
 
 	ret = eligible_child(wo, p);
@@ -1310,7 +1316,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		return 0;
 	}
 
-	if (unlikely(p->exit_state == EXIT_TRACE)) {
+	if (unlikely(exit_state == EXIT_TRACE)) {
 		/*
 		 * ptrace == 0 means we are the natural parent. In this case
 		 * we should clear notask_error, debugger will notify us.
@@ -1337,7 +1343,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	}
 
 	/* slay zombie? */
-	if (p->exit_state == EXIT_ZOMBIE) {
+	if (exit_state == EXIT_ZOMBIE) {
 		/* we don't reap group leaders with subthreads */
 		if (!delay_group_leader(p)) {
 			/*
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 5cf6731b98e9..3ef3736002d8 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -80,13 +80,13 @@ void debug_mutex_unlock(struct mutex *lock)
 			DEBUG_LOCKS_WARN_ON(lock->owner != current);
 
 		DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
-		mutex_clear_owner(lock);
 	}
 
 	/*
 	 * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
 	 * mutexes so that we can do it here after we've verified state.
 	 */
+	mutex_clear_owner(lock);
 	atomic_set(&lock->count, 1);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b5797b78add6..c0accc00566e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7113,9 +7113,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	alloc_size += num_possible_cpus() * cpumask_size();
-#endif
 	if (alloc_size) {
 		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
@@ -7135,13 +7132,13 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
+	}
 #ifdef CONFIG_CPUMASK_OFFSTACK
-		for_each_possible_cpu(i) {
-			per_cpu(load_balance_mask, i) = (void *)ptr;
-			ptr += cpumask_size();
-		}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
+	for_each_possible_cpu(i) {
+		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
+			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e5db8c6feebd..b52092f2636d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -570,24 +570,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 static
 int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-	int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
-	int rorun = dl_se->runtime <= 0;
-
-	if (!rorun && !dmiss)
-		return 0;
-
-	/*
-	 * If we are beyond our current deadline and we are still
-	 * executing, then we have already used some of the runtime of
-	 * the next instance. Thus, if we do not account that, we are
-	 * stealing bandwidth from the system at each deadline miss!
-	 */
-	if (dmiss) {
-		dl_se->runtime = rorun ? dl_se->runtime : 0;
-		dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
-	}
-
-	return 1;
+	return (dl_se->runtime <= 0);
 }
 
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -826,10 +809,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
-		replenish_dl_entity(dl_se, pi_se);
-	else
+	if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
 		update_dl_entity(dl_se, pi_se);
+	else if (flags & ENQUEUE_REPLENISH)
+		replenish_dl_entity(dl_se, pi_se);
 
 	__enqueue_dl_entity(dl_se);
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df2cdf77f899..40667cbf371b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4005,6 +4005,10 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
+	/* init_cfs_bandwidth() was not called */
+	if (!cfs_b->throttled_cfs_rq.next)
+		return;
+
 	hrtimer_cancel(&cfs_b->period_timer);
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
@@ -4424,7 +4428,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		 * wl = S * s'_i; see (2)
 		 */
 		if (W > 0 && w < W)
-			wl = (w * tg->shares) / W;
+			wl = (w * (long)tg->shares) / W;
 		else
 			wl = tg->shares;
 
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index b0b1c44e923a..3ccf5c2c1320 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -132,8 +132,8 @@ static int kdb_ftdump(int argc, const char **argv)
 
 static __init int kdb_ftrace_register(void)
 {
-	kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
-			    "Dump ftrace log", 0, KDB_REPEAT_NONE);
+	kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
+			    "Dump ftrace log", 0, KDB_ENABLE_ALWAYS_SAFE);
 	return 0;
 }
 
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 358eb81fa28d..c635a107a7de 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -73,6 +73,31 @@ config KGDB_KDB
 	help
 	  KDB frontend for kernel
 
+config KDB_DEFAULT_ENABLE
+	hex "KDB: Select kdb command functions to be enabled by default"
+	depends on KGDB_KDB
+	default 0x1
+	help
+	  Specifiers which kdb commands are enabled by default. This may
+	  be set to 1 or 0 to enable all commands or disable almost all
+	  commands.
+
+	  Alternatively the following bitmask applies:
+
+	    0x0002 - allow arbitrary reads from memory and symbol lookup
+	    0x0004 - allow arbitrary writes to memory
+	    0x0008 - allow current register state to be inspected
+	    0x0010 - allow current register state to be modified
+	    0x0020 - allow passive inspection (backtrace, process list, lsmod)
+	    0x0040 - allow flow control management (breakpoint, single step)
+	    0x0080 - enable signalling of processes
+	    0x0100 - allow machine to be rebooted
+
+	  The config option merely sets the default at boot time. Both
+	  issuing 'echo X > /sys/module/kdb/parameters/cmd_enable' or
+          setting with kdb.cmd_enable=X kernel command line option will
+	  override the default settings.
+
 config KDB_KEYBOARD
 	bool "KGDB_KDB: keyboard as input device"
 	depends on VT && KGDB_KDB
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 2404d03e251a..03dd576e6773 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -11,6 +11,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 //#define DEBUG
+#include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/assoc_array_priv.h>
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 56badfc4810a..957d3da53ddd 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -14,7 +14,6 @@ config DEBUG_PAGEALLOC
 	depends on !KMEMCHECK
 	select PAGE_EXTENSION
 	select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	select PAGE_GUARD if ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	---help---
 	  Unmap pages from the kernel linear mapping after free_pages().
 	  This results in a large slowdown, but helps to find certain types
@@ -27,13 +26,5 @@ config DEBUG_PAGEALLOC
 	  that would result in incorrect warnings of memory corruption after
 	  a resume because free pages are not saved to the suspend image.
 
-config WANT_PAGE_DEBUG_FLAGS
-	bool
-
 config PAGE_POISONING
 	bool
-	select WANT_PAGE_DEBUG_FLAGS
-
-config PAGE_GUARD
-	bool
-	select WANT_PAGE_DEBUG_FLAGS
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ef91e856c7e4..851924fa5170 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3043,18 +3043,6 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
 		mem_cgroup_swap_statistics(from, false);
 		mem_cgroup_swap_statistics(to, true);
-		/*
-		 * This function is only called from task migration context now.
-		 * It postpones page_counter and refcount handling till the end
-		 * of task migration(mem_cgroup_clear_mc()) for performance
-		 * improvement. But we cannot postpone css_get(to)  because if
-		 * the process that has been moved to @to does swap-in, the
-		 * refcount of @to might be decreased to 0.
-		 *
-		 * We are in attach() phase, so the cgroup is guaranteed to be
-		 * alive, so we can just call css_get().
-		 */
-		css_get(&to->css);
 		return 0;
 	}
 	return -EINVAL;
@@ -4679,6 +4667,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (parent_css == NULL) {
 		root_mem_cgroup = memcg;
 		page_counter_init(&memcg->memory, NULL);
+		memcg->soft_limit = PAGE_COUNTER_MAX;
 		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
 	}
@@ -4724,6 +4713,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 
 	if (parent->use_hierarchy) {
 		page_counter_init(&memcg->memory, &parent->memory);
+		memcg->soft_limit = PAGE_COUNTER_MAX;
 		page_counter_init(&memcg->memsw, &parent->memsw);
 		page_counter_init(&memcg->kmem, &parent->kmem);
 
@@ -4733,6 +4723,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		 */
 	} else {
 		page_counter_init(&memcg->memory, NULL);
+		memcg->soft_limit = PAGE_COUNTER_MAX;
 		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
 		/*
@@ -4807,7 +4798,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX);
 	mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX);
 	memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX);
-	memcg->soft_limit = 0;
+	memcg->soft_limit = PAGE_COUNTER_MAX;
 }
 
 #ifdef CONFIG_MMU
diff --git a/mm/memory.c b/mm/memory.c
index d7e497e98f46..54f3a9b00956 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -235,6 +235,9 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 
 static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
+	if (!tlb->end)
+		return;
+
 	tlb_flush(tlb);
 	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
@@ -247,7 +250,7 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;
 
-	for (batch = &tlb->local; batch; batch = batch->next) {
+	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
 		free_pages_and_swap_cache(batch->pages, batch->nr);
 		batch->nr = 0;
 	}
@@ -256,9 +259,6 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 
 void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
-		return;
-
 	tlb_flush_mmu_tlbonly(tlb);
 	tlb_flush_mmu_free(tlb);
 }
@@ -2137,17 +2137,24 @@ reuse:
 		if (!dirty_page)
 			return ret;
 
-		/*
-		 * Yes, Virginia, this is actually required to prevent a race
-		 * with clear_page_dirty_for_io() from clearing the page dirty
-		 * bit after it clear all dirty ptes, but before a racing
-		 * do_wp_page installs a dirty pte.
-		 *
-		 * do_shared_fault is protected similarly.
-		 */
 		if (!page_mkwrite) {
-			wait_on_page_locked(dirty_page);
-			set_page_dirty_balance(dirty_page);
+			struct address_space *mapping;
+			int dirtied;
+
+			lock_page(dirty_page);
+			dirtied = set_page_dirty(dirty_page);
+			VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page);
+			mapping = dirty_page->mapping;
+			unlock_page(dirty_page);
+
+			if (dirtied && mapping) {
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+
 			/* file_update_time outside page_lock */
 			if (vma->vm_file)
 				file_update_time(vma->vm_file);
diff --git a/mm/mmap.c b/mm/mmap.c
index 7b36aa7cc89a..7f684d5a8087 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -778,10 +778,12 @@ again:			remove_next = 1 + (end > next->vm_end);
 		if (exporter && exporter->anon_vma && !importer->anon_vma) {
 			int error;
 
+			importer->anon_vma = exporter->anon_vma;
 			error = anon_vma_clone(importer, exporter);
-			if (error)
+			if (error) {
+				importer->anon_vma = NULL;
 				return error;
-			importer->anon_vma = exporter->anon_vma;
+			}
 		}
 	}
 
@@ -2099,14 +2101,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start;
+	unsigned long new_start, actual_size;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	actual_size = size;
+	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
+		actual_size -= PAGE_SIZE;
+	if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d5d81f5384d1..6f4335238e33 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1541,16 +1541,6 @@ pause:
 		bdi_start_background_writeback(bdi);
 }
 
-void set_page_dirty_balance(struct page *page)
-{
-	if (set_page_dirty(page)) {
-		struct address_space *mapping = page_mapping(page);
-
-		if (mapping)
-			balance_dirty_pages_ratelimited(mapping);
-	}
-}
-
 static DEFINE_PER_CPU(int, bdp_ratelimits);
 
 /*
@@ -2123,32 +2113,25 @@ EXPORT_SYMBOL(account_page_dirtied);
  * page dirty in that case, but not all the buffers.  This is a "bottom-up"
  * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
  *
- * Most callers have locked the page, which pins the address_space in memory.
- * But zap_pte_range() does not lock the page, however in that case the
- * mapping is pinned by the vma's ->vm_file reference.
- *
- * We take care to handle the case where the page was truncated from the
- * mapping by re-checking page_mapping() inside tree_lock.
+ * The caller must ensure this doesn't race with truncation.  Most will simply
+ * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
+ * the pte lock held, which also locks out truncation.
  */
 int __set_page_dirty_nobuffers(struct page *page)
 {
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
-		struct address_space *mapping2;
 		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
-		mapping2 = page_mapping(page);
-		if (mapping2) { /* Race with truncate? */
-			BUG_ON(mapping2 != mapping);
-			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
-			account_page_dirtied(page, mapping);
-			radix_tree_tag_set(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-		}
+		BUG_ON(page_mapping(page) != mapping);
+		WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
+		account_page_dirtied(page, mapping);
+		radix_tree_tag_set(&mapping->page_tree, page_index(page),
+				   PAGECACHE_TAG_DIRTY);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
@@ -2305,12 +2288,10 @@ int clear_page_dirty_for_io(struct page *page)
 		/*
 		 * We carefully synchronise fault handlers against
 		 * installing a dirty pte and marking the page dirty
-		 * at this point. We do this by having them hold the
-		 * page lock at some point after installing their
-		 * pte, but before marking the page dirty.
-		 * Pages are always locked coming in here, so we get
-		 * the desired exclusion. See mm/memory.c:do_wp_page()
-		 * for more comments.
+		 * at this point.  We do this by having them hold the
+		 * page lock while dirtying the page, and pages are
+		 * always locked coming in here, so we get the desired
+		 * exclusion.
 		 */
 		if (TestClearPageDirty(page)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
diff --git a/mm/rmap.c b/mm/rmap.c
index c5bc241127b2..71cd5bd0c17d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -72,6 +72,8 @@ static inline struct anon_vma *anon_vma_alloc(void)
 	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
 	if (anon_vma) {
 		atomic_set(&anon_vma->refcount, 1);
+		anon_vma->degree = 1;	/* Reference for first vma */
+		anon_vma->parent = anon_vma;
 		/*
 		 * Initialise the anon_vma root to point to itself. If called
 		 * from fork, the root will be reset to the parents anon_vma.
@@ -188,6 +190,8 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 		if (likely(!vma->anon_vma)) {
 			vma->anon_vma = anon_vma;
 			anon_vma_chain_link(vma, avc, anon_vma);
+			/* vma reference or self-parent link for new root */
+			anon_vma->degree++;
 			allocated = NULL;
 			avc = NULL;
 		}
@@ -236,6 +240,14 @@ static inline void unlock_anon_vma_root(struct anon_vma *root)
 /*
  * Attach the anon_vmas from src to dst.
  * Returns 0 on success, -ENOMEM on failure.
+ *
+ * If dst->anon_vma is NULL this function tries to find and reuse existing
+ * anon_vma which has no vmas and only one child anon_vma. This prevents
+ * degradation of anon_vma hierarchy to endless linear chain in case of
+ * constantly forking task. On the other hand, an anon_vma with more than one
+ * child isn't reused even if there was no alive vma, thus rmap walker has a
+ * good chance of avoiding scanning the whole hierarchy when it searches where
+ * page is mapped.
  */
 int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
@@ -256,7 +268,21 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		anon_vma = pavc->anon_vma;
 		root = lock_anon_vma_root(root, anon_vma);
 		anon_vma_chain_link(dst, avc, anon_vma);
+
+		/*
+		 * Reuse existing anon_vma if its degree lower than two,
+		 * that means it has no vma and only one anon_vma child.
+		 *
+		 * Do not chose parent anon_vma, otherwise first child
+		 * will always reuse it. Root anon_vma is never reused:
+		 * it has self-parent reference and at least one child.
+		 */
+		if (!dst->anon_vma && anon_vma != src->anon_vma &&
+				anon_vma->degree < 2)
+			dst->anon_vma = anon_vma;
 	}
+	if (dst->anon_vma)
+		dst->anon_vma->degree++;
 	unlock_anon_vma_root(root);
 	return 0;
 
@@ -280,6 +306,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	if (!pvma->anon_vma)
 		return 0;
 
+	/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
+	vma->anon_vma = NULL;
+
 	/*
 	 * First, attach the new VMA to the parent VMA's anon_vmas,
 	 * so rmap can find non-COWed pages in child processes.
@@ -288,6 +317,10 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	if (error)
 		return error;
 
+	/* An existing anon_vma has been reused, all done then. */
+	if (vma->anon_vma)
+		return 0;
+
 	/* Then add our own anon_vma. */
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
@@ -301,6 +334,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	 * lock any of the anon_vmas in this anon_vma tree.
 	 */
 	anon_vma->root = pvma->anon_vma->root;
+	anon_vma->parent = pvma->anon_vma;
 	/*
 	 * With refcounts, an anon_vma can stay around longer than the
 	 * process it belongs to. The root anon_vma needs to be pinned until
@@ -311,6 +345,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	vma->anon_vma = anon_vma;
 	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
+	anon_vma->parent->degree++;
 	anon_vma_unlock_write(anon_vma);
 
 	return 0;
@@ -341,12 +376,16 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		 * Leave empty anon_vmas on the list - we'll need
 		 * to free them outside the lock.
 		 */
-		if (RB_EMPTY_ROOT(&anon_vma->rb_root))
+		if (RB_EMPTY_ROOT(&anon_vma->rb_root)) {
+			anon_vma->parent->degree--;
 			continue;
+		}
 
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
+	if (vma->anon_vma)
+		vma->anon_vma->degree--;
 	unlock_anon_vma_root(root);
 
 	/*
@@ -357,6 +396,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
 
+		BUG_ON(anon_vma->degree);
 		put_anon_vma(anon_vma);
 
 		list_del(&avc->same_vma);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd9a72bc4a1b..ab2505c3ef54 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2921,18 +2921,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 		return false;
 
 	/*
-	 * There is a potential race between when kswapd checks its watermarks
-	 * and a process gets throttled. There is also a potential race if
-	 * processes get throttled, kswapd wakes, a large process exits therby
-	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
-	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
-	 * so wake them now if necessary. If necessary, processes will wake
-	 * kswapd and get throttled again
+	 * The throttled processes are normally woken up in balance_pgdat() as
+	 * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+	 * race between when kswapd checks the watermarks and a process gets
+	 * throttled. There is also a potential race if processes get
+	 * throttled, kswapd wakes, a large process exits thereby balancing the
+	 * zones, which causes kswapd to exit balance_pgdat() before reaching
+	 * the wake up checks. If kswapd is going to sleep, no process should
+	 * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
+	 * the wake up is premature, processes will wake kswapd and get
+	 * throttled again. The difference from wake ups in balance_pgdat() is
+	 * that here we are under prepare_to_wait().
 	 */
-	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
-		wake_up(&pgdat->pfmemalloc_wait);
-		return false;
-	}
+	if (waitqueue_active(&pgdat->pfmemalloc_wait))
+		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	return pgdat_balanced(pgdat, order, classzone_idx);
 }
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 1f1de715197c..e2aa7be3a847 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -154,7 +154,8 @@ int br_handle_frame_finish(struct sk_buff *skb)
 	dst = NULL;
 
 	if (is_broadcast_ether_addr(dest)) {
-		if (p->flags & BR_PROXYARP &&
+		if (IS_ENABLED(CONFIG_INET) &&
+		    p->flags & BR_PROXYARP &&
 		    skb->protocol == htons(ETH_P_ARP))
 			br_do_proxy_arp(skb, br, vid);
 
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 15845814a0f2..ba6eb17226da 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -676,7 +676,7 @@ static int calcu_signature(struct ceph_x_authorizer *au,
 	int ret;
 	char tmp_enc[40];
 	__le32 tmp[5] = {
-		16u, msg->hdr.crc, msg->footer.front_crc,
+		cpu_to_le32(16), msg->hdr.crc, msg->footer.front_crc,
 		msg->footer.middle_crc, msg->footer.data_crc,
 	};
 	ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index a83062ceeec9..f2148e22b148 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -717,7 +717,7 @@ static int get_poolop_reply_buf(const char *src, size_t src_len,
 	if (src_len != sizeof(u32) + dst_len)
 		return -EINVAL;
 
-	buf_len = le32_to_cpu(*(u32 *)src);
+	buf_len = le32_to_cpu(*(__le32 *)src);
 	if (buf_len != dst_len)
 		return -EINVAL;
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8e38f17288d3..8d614c93f86a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2043,6 +2043,12 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 			case NDTPA_BASE_REACHABLE_TIME:
 				NEIGH_VAR_SET(p, BASE_REACHABLE_TIME,
 					      nla_get_msecs(tbp[i]));
+				/* update reachable_time as well, otherwise, the change will
+				 * only be effective after the next time neigh_periodic_work
+				 * decides to recompute it (can be multiple minutes)
+				 */
+				p->reachable_time =
+					neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 				break;
 			case NDTPA_GC_STALETIME:
 				NEIGH_VAR_SET(p, GC_STALETIME,
@@ -2921,6 +2927,31 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write,
+					  void __user *buffer,
+					  size_t *lenp, loff_t *ppos)
+{
+	struct neigh_parms *p = ctl->extra2;
+	int ret;
+
+	if (strcmp(ctl->procname, "base_reachable_time") == 0)
+		ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
+	else if (strcmp(ctl->procname, "base_reachable_time_ms") == 0)
+		ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos);
+	else
+		ret = -1;
+
+	if (write && ret == 0) {
+		/* update reachable_time as well, otherwise, the change will
+		 * only be effective after the next time neigh_periodic_work
+		 * decides to recompute it
+		 */
+		p->reachable_time =
+			neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
+	}
+	return ret;
+}
+
 #define NEIGH_PARMS_DATA_OFFSET(index)	\
 	(&((struct neigh_parms *) 0)->data[index])
 
@@ -3047,6 +3078,19 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 		t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler;
 		/* ReachableTime (in milliseconds) */
 		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler;
+	} else {
+		/* Those handlers will update p->reachable_time after
+		 * base_reachable_time(_ms) is set to ensure the new timer starts being
+		 * applied after the next neighbour update instead of waiting for
+		 * neigh_periodic_work to update its value (can be multiple minutes)
+		 * So any handler that replaces them should do this as well
+		 */
+		/* ReachableTime */
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler =
+			neigh_proc_base_reachable_time;
+		/* ReachableTime (in milliseconds) */
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler =
+			neigh_proc_base_reachable_time;
 	}
 
 	/* Don't export sysctls to unprivileged users */
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index ff2d23d8c87a..6ecfce63201a 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -27,10 +27,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
 
 	memset(&mr, 0, sizeof(mr));
 	if (priv->sreg_proto_min) {
-		mr.range[0].min.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		mr.range[0].max.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		mr.range[0].min.all =
+			*(__be16 *)&data[priv->sreg_proto_min].data[0];
+		mr.range[0].max.all =
+			*(__be16 *)&data[priv->sreg_proto_max].data[0];
 		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index 2433a6bfb191..11820b6b3613 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -27,10 +27,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
 
 	memset(&range, 0, sizeof(range));
 	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		range.min_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_min].data[0];
+		range.max_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_max].data[0];
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 1d5341f3761d..5d3daae98bf0 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct nf_conn *ct;
 	struct net *net;
 
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
@@ -322,6 +322,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct ip_vs_conn *n_cp;
 	struct net *net;
 
+	/* no diff required for incoming packets */
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -330,9 +333,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	/* no diff required for incoming packets */
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index a11674806707..46d1b26a468e 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -611,16 +611,15 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
-	/* We have to check the DYING flag inside the lock to prevent
-	   a race against nf_ct_get_next_corpse() possibly called from
-	   user context, else we insert an already 'dead' hash, blocking
-	   further use of that particular connection -JM */
+	/* We have to check the DYING flag after unlink to prevent
+	 * a race against nf_ct_get_next_corpse() possibly called from
+	 * user context, else we insert an already 'dead' hash, blocking
+	 * further use of that particular connection -JM.
+	 */
+	nf_ct_del_from_dying_or_unconfirmed_list(ct);
 
-	if (unlikely(nf_ct_is_dying(ct))) {
-		nf_conntrack_double_unlock(hash, reply_hash);
-		local_bh_enable();
-		return NF_ACCEPT;
-	}
+	if (unlikely(nf_ct_is_dying(ct)))
+		goto out;
 
 	/* See if there's one in the list already, including reverse:
 	   NAT could have grabbed it without realizing, since we're
@@ -636,8 +635,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
 
-	nf_ct_del_from_dying_or_unconfirmed_list(ct);
-
 	/* Timer relative to confirmation time, not original
 	   setting time, otherwise we'd get timer wrap in
 	   weird delay cases. */
@@ -673,6 +670,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	return NF_ACCEPT;
 
 out:
+	nf_ct_add_to_dying_list(ct);
 	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 129a8daa4abf..3b3ddb4fb9ee 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -713,16 +713,12 @@ static int nft_flush_table(struct nft_ctx *ctx)
 	struct nft_chain *chain, *nc;
 	struct nft_set *set, *ns;
 
-	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+	list_for_each_entry(chain, &ctx->table->chains, list) {
 		ctx->chain = chain;
 
 		err = nft_delrule_by_chain(ctx);
 		if (err < 0)
 			goto out;
-
-		err = nft_delchain(ctx);
-		if (err < 0)
-			goto out;
 	}
 
 	list_for_each_entry_safe(set, ns, &ctx->table->sets, list) {
@@ -735,6 +731,14 @@ static int nft_flush_table(struct nft_ctx *ctx)
 			goto out;
 	}
 
+	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+		ctx->chain = chain;
+
+		err = nft_delchain(ctx);
+		if (err < 0)
+			goto out;
+	}
+
 	err = nft_deltable(ctx);
 out:
 	return err;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index cde4a6702fa3..c421d94c4652 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -321,7 +321,8 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlh->nlmsg_len < NLMSG_HDRLEN) {
+		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
+		    skb->len < nlh->nlmsg_len) {
 			err = -EINVAL;
 			goto ack;
 		}
@@ -469,7 +470,7 @@ static int nfnetlink_bind(struct net *net, int group)
 	int type;
 
 	if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX)
-		return -EINVAL;
+		return 0;
 
 	type = nfnl_group2type[group];
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index afe2b0b45ec4..aff54fb1c8a0 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr,
 	}
 
 	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		range.min_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_min].data[0];
+		range.max_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_max].data[0];
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 54854e3ecd83..8bda3cc12344 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -524,7 +524,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct vport *input_vport;
 	int len;
 	int err;
-	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool log = !a[OVS_PACKET_ATTR_PROBE];
 
 	err = -EINVAL;
 	if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
@@ -610,6 +610,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 	[OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN },
 	[OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
 	[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
+	[OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG },
 };
 
 static const struct genl_ops dp_packet_genl_ops[] = {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d37075b0d6d5..9c28cec1a083 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2517,7 +2517,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -EINVAL;
 	if (sock->type == SOCK_DGRAM) {
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
-		if (unlikely(offset) < 0)
+		if (unlikely(offset < 0))
 			goto out_free;
 	} else {
 		if (ll_header_truncated(dev, len))
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1cb61242e55e..4439ac4c1b53 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -606,7 +606,7 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	struct kvec *head = buf->head;
 	struct kvec *tail = buf->tail;
 	int fraglen;
-	int new, old;
+	int new;
 
 	if (len > buf->len) {
 		WARN_ON_ONCE(1);
@@ -629,8 +629,8 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 	buf->len -= fraglen;
 
 	new = buf->page_base + buf->page_len;
-	old = new + fraglen;
-	xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT);
+
+	xdr->page_ptr = buf->pages + (new >> PAGE_SHIFT);
 
 	if (buf->page_len) {
 		xdr->p = page_address(*xdr->page_ptr);
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index 1bca180db8ad..627f8cbbedb8 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -42,19 +42,19 @@ __clean-files	:= $(extra-y) $(extra-m) $(extra-)       \
 
 __clean-files   := $(filter-out $(no-clean-files), $(__clean-files))
 
-# as clean-files is given relative to the current directory, this adds
-# a $(obj) prefix, except for absolute paths
+# clean-files is given relative to the current directory, unless it
+# starts with $(objtree)/ (which means "./", so do not add "./" unless
+# you want to delete a file from the toplevel object directory).
 
 __clean-files   := $(wildcard                                               \
-                   $(addprefix $(obj)/, $(filter-out /%, $(__clean-files))) \
-		   $(filter /%, $(__clean-files)))
+		   $(addprefix $(obj)/, $(filter-out $(objtree)/%, $(__clean-files))) \
+		   $(filter $(objtree)/%, $(__clean-files)))
 
-# as clean-dirs is given relative to the current directory, this adds
-# a $(obj) prefix, except for absolute paths
+# same as clean-files
 
 __clean-dirs    := $(wildcard                                               \
-                   $(addprefix $(obj)/, $(filter-out /%, $(clean-dirs)))    \
-		   $(filter /%, $(clean-dirs)))
+		   $(addprefix $(obj)/, $(filter-out $(objtree)/%, $(clean-dirs)))    \
+		   $(filter $(objtree)/%, $(clean-dirs)))
 
 # ==========================================================================
 
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 9609a7f0faea..c7952375ac53 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -148,12 +148,12 @@ static noinline void key_gc_unused_keys(struct list_head *keys)
 		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
 			atomic_dec(&key->user->nikeys);
 
-		key_user_put(key->user);
-
 		/* now throw away the key memory */
 		if (key->type->destroy)
 			key->type->destroy(key);
 
+		key_user_put(key->user);
+
 		kfree(key->description);
 
 #ifdef KEY_DEBUGGING
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index 255dabc6fc33..2a85e4209f0b 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -124,7 +124,7 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 	spin_lock_irq(&efw->lock);
 
 	t = (struct snd_efw_transaction *)data;
-	length = min_t(size_t, t->length * sizeof(t->length), length);
+	length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
 
 	if (efw->push_ptr < efw->pull_ptr)
 		capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 5f13d2d18079..b422e406a9cb 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3353,6 +3353,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x10de0067, .name = "MCP67 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x10de0070, .name = "GPU 70 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0071, .name = "GPU 71 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de0072, .name = "GPU 72 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x11069f80, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
 { .id = 0x11069f81, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
@@ -3413,6 +3414,7 @@ MODULE_ALIAS("snd-hda-codec-id:10de0060");
 MODULE_ALIAS("snd-hda-codec-id:10de0067");
 MODULE_ALIAS("snd-hda-codec-id:10de0070");
 MODULE_ALIAS("snd-hda-codec-id:10de0071");
+MODULE_ALIAS("snd-hda-codec-id:10de0072");
 MODULE_ALIAS("snd-hda-codec-id:10de8001");
 MODULE_ALIAS("snd-hda-codec-id:11069f80");
 MODULE_ALIAS("snd-hda-codec-id:11069f81");
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 4f6413e01c13..605d14003d25 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -568,9 +568,9 @@ static void stac_store_hints(struct hda_codec *codec)
 			spec->gpio_mask;
 	}
 	if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir))
-		spec->gpio_mask &= spec->gpio_mask;
-	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
 		spec->gpio_dir &= spec->gpio_mask;
+	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
+		spec->gpio_data &= spec->gpio_mask;
 	if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask))
 		spec->eapd_mask &= spec->gpio_mask;
 	if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute))
diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index 272844746135..327f8642ca80 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -816,7 +816,7 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *cdev)
 		return -EINVAL;
 	}
 
-	if (cdev->n_streams < 2) {
+	if (cdev->n_streams < 1) {
 		dev_err(dev, "bogus number of streams: %d\n", cdev->n_streams);
 		return -EINVAL;
 	}
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 6f803609e498..0b0112c80f22 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -317,7 +317,7 @@ int pthread_mutex_destroy(pthread_mutex_t *mutex)
 	 *
 	 * TODO: Hook into free() and add that check there as well.
 	 */
-	debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex));
+	debug_check_no_locks_freed(mutex, sizeof(*mutex));
 	__del_lock(__get_lock(mutex));
 	return ll_pthread_mutex_destroy(mutex);
 }
@@ -341,7 +341,7 @@ int pthread_rwlock_destroy(pthread_rwlock_t *rwlock)
 {
 	try_init_preload();
 
-	debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock));
+	debug_check_no_locks_freed(rwlock, sizeof(*rwlock));
 	__del_lock(__get_lock(rwlock));
 	return ll_pthread_rwlock_destroy(rwlock);
 }
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e7417fe97a97..747f86103599 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		if (nr_samples > 0) {
 			total_nr_samples += nr_samples;
 			hists__collapse_resort(hists, NULL);
-			hists__output_resort(hists);
+			hists__output_resort(hists, NULL);
 
 			if (symbol_conf.event_group &&
 			    !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1ce425d101a9..1fd96c13f199 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -545,6 +545,42 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
 	return __hist_entry__cmp_compute(p_left, p_right, c);
 }
 
+static int64_t
+hist_entry__cmp_nop(struct hist_entry *left __maybe_unused,
+		    struct hist_entry *right __maybe_unused)
+{
+	return 0;
+}
+
+static int64_t
+hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right)
+{
+	if (sort_compute)
+		return 0;
+
+	if (left->stat.period == right->stat.period)
+		return 0;
+	return left->stat.period > right->stat.period ? 1 : -1;
+}
+
+static int64_t
+hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute(right, left, COMPUTE_DELTA);
+}
+
+static int64_t
+hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute(right, left, COMPUTE_RATIO);
+}
+
+static int64_t
+hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void insert_hist_entry_by_compute(struct rb_root *root,
 					 struct hist_entry *he,
 					 int c)
@@ -605,7 +641,7 @@ static void hists__process(struct hists *hists)
 		hists__precompute(hists);
 		hists__compute_resort(hists);
 	} else {
-		hists__output_resort(hists);
+		hists__output_resort(hists, NULL);
 	}
 
 	hists__fprintf(hists, true, 0, 0, 0, stdout);
@@ -1038,27 +1074,35 @@ static void data__hpp_register(struct data__file *d, int idx)
 	fmt->header = hpp__header;
 	fmt->width  = hpp__width;
 	fmt->entry  = hpp__entry_global;
+	fmt->cmp    = hist_entry__cmp_nop;
+	fmt->collapse = hist_entry__cmp_nop;
 
 	/* TODO more colors */
 	switch (idx) {
 	case PERF_HPP_DIFF__BASELINE:
 		fmt->color = hpp__color_baseline;
+		fmt->sort  = hist_entry__cmp_baseline;
 		break;
 	case PERF_HPP_DIFF__DELTA:
 		fmt->color = hpp__color_delta;
+		fmt->sort  = hist_entry__cmp_delta;
 		break;
 	case PERF_HPP_DIFF__RATIO:
 		fmt->color = hpp__color_ratio;
+		fmt->sort  = hist_entry__cmp_ratio;
 		break;
 	case PERF_HPP_DIFF__WEIGHTED_DIFF:
 		fmt->color = hpp__color_wdiff;
+		fmt->sort  = hist_entry__cmp_wdiff;
 		break;
 	default:
+		fmt->sort  = hist_entry__cmp_nop;
 		break;
 	}
 
 	init_header(d, dfmt);
 	perf_hpp__column_register(fmt);
+	perf_hpp__register_sort_field(fmt);
 }
 
 static void ui_init(void)
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 011195e38f21..198f3c3aff95 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -19,7 +19,9 @@
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int i;
-	const struct option list_options[] = {
+	bool raw_dump = false;
+	struct option list_options[] = {
+		OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
 		OPT_END()
 	};
 	const char * const list_usage[] = {
@@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
+	set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN);
+
 	argc = parse_options(argc, argv, list_options, list_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	setup_pager();
 
+	if (raw_dump) {
+		print_events(NULL, true);
+		return 0;
+	}
+
 	if (argc == 0) {
 		print_events(NULL, false);
 		return 0;
@@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_hwcache_events(NULL, false);
 		else if (strcmp(argv[i], "pmu") == 0)
 			print_pmu_events(NULL, false);
-		else if (strcmp(argv[i], "--raw-dump") == 0)
-			print_events(NULL, true);
 		else {
 			char *sep = strchr(argv[i], ':'), *s;
 			int sep_idx;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 39367609c707..072ae8ad67fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -457,6 +457,19 @@ static void report__collapse_hists(struct report *rep)
 	ui_progress__finish();
 }
 
+static void report__output_resort(struct report *rep)
+{
+	struct ui_progress prog;
+	struct perf_evsel *pos;
+
+	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
+
+	evlist__for_each(rep->session->evlist, pos)
+		hists__output_resort(evsel__hists(pos), &prog);
+
+	ui_progress__finish();
+}
+
 static int __cmd_report(struct report *rep)
 {
 	int ret;
@@ -505,13 +518,20 @@ static int __cmd_report(struct report *rep)
 	if (session_done())
 		return 0;
 
+	/*
+	 * recalculate number of entries after collapsing since it
+	 * might be changed during the collapse phase.
+	 */
+	rep->nr_entries = 0;
+	evlist__for_each(session->evlist, pos)
+		rep->nr_entries += evsel__hists(pos)->nr_entries;
+
 	if (rep->nr_entries == 0) {
 		ui__error("The %s file has no samples!\n", file->path);
 		return 0;
 	}
 
-	evlist__for_each(session->evlist, pos)
-		hists__output_resort(evsel__hists(pos));
+	report__output_resort(rep);
 
 	return report__browse_hists(rep);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0aa7747ff139..961cea183a83 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -285,7 +285,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
@@ -554,7 +554,7 @@ static void perf_top__sort_new_samples(void *arg)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 }
 
 static void *display_thread_tui(void *arg)
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 614d5c4978ab..8d110dec393e 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -187,7 +187,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 	 * function since TEST_ASSERT_VAL() returns in case of failure.
 	 */
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("use callchain: %d, cumulate callchain: %d\n",
@@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 	 *   30.00%    10.00%     perf  perf           [.] cmd_record
 	 *   20.00%     0.00%     bash  libc           [.] malloc
 	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
-	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
-	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
 	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
-	 *   10.00%    10.00%     perf  libc           [.] free
 	 *   10.00%    10.00%     perf  libc           [.] malloc
-	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
 	 */
 	struct result expected[] = {
 		{ 7000, 2000, "perf", "perf",     "main" },
@@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		{ 3000, 1000, "perf", "perf",     "cmd_record" },
 		{ 2000,    0, "bash", "libc",     "malloc" },
 		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
-		{ 1000, 1000, "perf", "[kernel]", "schedule" },
-		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
 		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
 		{ 1000, 1000, "perf", "libc",     "free" },
 		{ 1000, 1000, "perf", "libc",     "malloc" },
-		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
 	};
 
 	symbol_conf.use_callchain = false;
@@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	 *                  malloc
 	 *                  main
 	 *
-	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
 	 *              |
-	 *              --- schedule
-	 *                  run_command
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
 	 *                  main
 	 *
 	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
@@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	 *                  run_command
 	 *                  main
 	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
 	 *   10.00%    10.00%     perf  libc           [.] free
 	 *              |
 	 *              --- free
@@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 	 *                  run_command
 	 *                  main
 	 *
-	 *   10.00%    10.00%     bash  bash           [.] xmalloc
-	 *              |
-	 *              --- xmalloc
-	 *                  malloc
-	 *                  xmalloc     <--- NOTE: there's a cycle
-	 *                  malloc
-	 *                  xmalloc
-	 *                  main
-	 *
 	 */
 	struct result expected[] = {
 		{ 7000, 2000, "perf", "perf",     "main" },
@@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		{ 3000, 1000, "perf", "perf",     "cmd_record" },
 		{ 2000,    0, "bash", "libc",     "malloc" },
 		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
-		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
 		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
 		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
 		{ 1000, 1000, "perf", "libc",     "free" },
 		{ 1000, 1000, "perf", "libc",     "malloc" },
-		{ 1000, 1000, "bash", "bash",     "xmalloc" },
 	};
 	struct callchain_result expected_callchain[] = {
 		{
@@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 				{ "bash",     "main" }, },
 		},
 		{
-			3, {	{ "[kernel]", "schedule" },
-				{ "perf",     "run_command" },
-				{ "perf",     "main" }, },
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
 		},
 		{
 			3, {	{ "[kernel]", "sys_perf_event_open" },
@@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 				{ "perf",     "main" }, },
 		},
 		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
 			4, {	{ "libc",     "free" },
 				{ "perf",     "cmd_record" },
 				{ "perf",     "run_command" },
@@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 				{ "perf",     "run_command" },
 				{ "perf",     "main" }, },
 		},
-		{
-			6, {	{ "bash",     "xmalloc" },
-				{ "libc",     "malloc" },
-				{ "bash",     "xmalloc" },
-				{ "libc",     "malloc" },
-				{ "bash",     "xmalloc" },
-				{ "bash",     "main" }, },
-		},
 	};
 
 	symbol_conf.use_callchain = true;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 74f257a81265..59e53db7914c 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -138,7 +138,7 @@ int test__hists_filter(void)
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
-		hists__output_resort(hists);
+		hists__output_resort(hists, NULL);
 
 		if (verbose > 2) {
 			pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a748f2be1222..f5547610da02 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists);
+	hists__output_resort(hists, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e6bb04b5b09b..788506eef567 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -550,7 +550,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = !!rb_next(node);
+	need_percent = node && rb_next(node);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index dc0d095f318c..482adae3cc44 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 		if (ret)
 			return ret;
 
+		if (a->thread != b->thread || !symbol_conf.use_callchain)
+			return 0;
+
 		ret = b->callchain->max_depth - a->callchain->max_depth;
 	}
 	return ret;
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 2f612562978c..3c38f25b1695 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,5 +1,8 @@
 #include <signal.h>
 #include <stdbool.h>
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
@@ -88,6 +91,25 @@ int ui__getch(int delay_secs)
 	return SLkp_getkey();
 }
 
+#ifdef HAVE_BACKTRACE_SUPPORT
+static void ui__signal_backtrace(int sig)
+{
+	void *stackdump[32];
+	size_t size;
+
+	ui__exit(false);
+	psignal(sig, "perf");
+
+	printf("-------- backtrace --------\n");
+	size = backtrace(stackdump, ARRAY_SIZE(stackdump));
+	backtrace_symbols_fd(stackdump, size, STDOUT_FILENO);
+
+	exit(0);
+}
+#else
+# define ui__signal_backtrace  ui__signal
+#endif
+
 static void ui__signal(int sig)
 {
 	ui__exit(false);
@@ -122,8 +144,8 @@ int ui__init(void)
 	ui_browser__init();
 	tui_progress__init();
 
-	signal(SIGSEGV, ui__signal);
-	signal(SIGFPE, ui__signal);
+	signal(SIGSEGV, ui__signal_backtrace);
+	signal(SIGFPE, ui__signal_backtrace);
 	signal(SIGINT, ui__signal);
 	signal(SIGQUIT, ui__signal);
 	signal(SIGTERM, ui__signal);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 64b377e591e4..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 
 	return bf;
 }
+
+static void free_callchain_node(struct callchain_node *node)
+{
+	struct callchain_list *list, *tmp;
+	struct callchain_node *child;
+	struct rb_node *n;
+
+	list_for_each_entry_safe(list, tmp, &node->val, list) {
+		list_del(&list->list);
+		free(list);
+	}
+
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = container_of(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+		rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+		free_callchain_node(child);
+		free(child);
+	}
+}
+
+void free_callchain(struct callchain_root *root)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index dbc08cf5f970..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
 
+void free_callchain(struct callchain_root *root);
+
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6e88b9e395df..182395546ddc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
+#include "ui/progress.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -303,7 +304,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 	size_t callchain_size = 0;
 	struct hist_entry *he;
 
-	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+	if (symbol_conf.use_callchain)
 		callchain_size = sizeof(struct callchain_root);
 
 	he = zalloc(sizeof(*he) + callchain_size);
@@ -736,7 +737,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	callchain_append(he->callchain, &callchain_cursor, sample->period);
+	hist_entry__append_callchain(he, sample);
 
 	/*
 	 * We need to re-initialize the cursor since callchain_append()
@@ -809,7 +810,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	callchain_append(he->callchain, &cursor, sample->period);
+	if (symbol_conf.use_callchain)
+		callchain_append(he->callchain, &cursor, sample->period);
 	return 0;
 }
 
@@ -945,6 +947,7 @@ void hist_entry__free(struct hist_entry *he)
 	zfree(&he->mem_info);
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
+	free_callchain(he->callchain);
 	free(he);
 }
 
@@ -987,6 +990,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		else
 			p = &(*p)->rb_right;
 	}
+	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
@@ -1024,7 +1028,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	if (!sort__need_collapse)
 		return;
 
+	hists->nr_entries = 0;
+
 	root = hists__get_rotate_entries_in(hists);
+
 	next = rb_first(root);
 
 	while (next) {
@@ -1119,7 +1126,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	rb_insert_color(&he->rb_node, entries);
 }
 
-void hists__output_resort(struct hists *hists)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
@@ -1148,6 +1155,9 @@ void hists__output_resort(struct hists *hists)
 
 		if (!n->filtered)
 			hists__calc_col_len(hists, n);
+
+		if (prog)
+			ui_progress__update(prog, 1);
 	}
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d0ef9a19a744..46bd50344f85 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -121,7 +121,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
-void hists__output_resort(struct hists *hists);
+void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28eb1417cb2a..7f9b8632e433 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
-		pr_warning("Probe point '%s' not found.\n",
+		pr_warning("Probe point '%s' not found in debuginfo.\n",
 			   synthesize_perf_probe_point(&pev->point));
-		return -ENOENT;
+		if (need_dwarf)
+			return -ENOENT;
+		return 0;
 	}
 	/* Error path : ntevs < 0 */
 	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c7918f83b300..b5247d777f0e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	int ret = 0;
 
 #if _ELFUTILS_PREREQ(0, 142)
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+
 	/* Get the call frame information from this dwarf */
-	pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
+	elf = dwarf_getelf(dbg->dbg);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		return -EINVAL;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+	    shdr.sh_type == SHT_PROGBITS) {
+		pf->cfi = dwarf_getcfi_elf(elf);
+	} else {
+		pf->cfi = dwarf_getcfi(dbg->dbg);
+	}
 #endif
 
 	off = 0;
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index d273624c93a6..e238c9559caf 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -62,7 +62,7 @@ static int _check_execveat_fail(int fd, const char *path, int flags,
 }
 
 static int check_execveat_invoked_rc(int fd, const char *path, int flags,
-				     int expected_rc)
+				     int expected_rc, int expected_rc2)
 {
 	int status;
 	int rc;
@@ -98,9 +98,10 @@ static int check_execveat_invoked_rc(int fd, const char *path, int flags,
 			child, status);
 		return 1;
 	}
-	if (WEXITSTATUS(status) != expected_rc) {
-		printf("[FAIL] (child %d exited with %d not %d)\n",
-			child, WEXITSTATUS(status), expected_rc);
+	if ((WEXITSTATUS(status) != expected_rc) &&
+	    (WEXITSTATUS(status) != expected_rc2)) {
+		printf("[FAIL] (child %d exited with %d not %d nor %d)\n",
+			child, WEXITSTATUS(status), expected_rc, expected_rc2);
 		return 1;
 	}
 	printf("[OK]\n");
@@ -109,7 +110,7 @@ static int check_execveat_invoked_rc(int fd, const char *path, int flags,
 
 static int check_execveat(int fd, const char *path, int flags)
 {
-	return check_execveat_invoked_rc(fd, path, flags, 99);
+	return check_execveat_invoked_rc(fd, path, flags, 99, 99);
 }
 
 static char *concat(const char *left, const char *right)
@@ -192,9 +193,15 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
 	 * Execute as a long pathname relative to ".".  If this is a script,
 	 * the interpreter will launch but fail to open the script because its
 	 * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX.
+	 *
+	 * The failure code is usually 127 (POSIX: "If a command is not found,
+	 * the exit status shall be 127."), but some systems give 126 (POSIX:
+	 * "If the command name is found, but it is not an executable utility,
+	 * the exit status shall be 126."), so allow either.
 	 */
 	if (is_script)
-		fail += check_execveat_invoked_rc(dot_dfd, longpath, 0, 127);
+		fail += check_execveat_invoked_rc(dot_dfd, longpath, 0,
+						  127, 126);
 	else
 		fail += check_execveat(dot_dfd, longpath, 0);
 
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index 94dae65eea41..8519e9ee97e3 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -536,10 +536,9 @@ int main(int argc, char *argv[])
 {
 	struct mq_attr attr;
 	char *option, *next_option;
-	int i, cpu;
+	int i, cpu, rc;
 	struct sigaction sa;
 	poptContext popt_context;
-	char rc;
 	void *retval;
 
 	main_thread = pthread_self();
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4c4b1f631ecf..077828c889f1 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -7,7 +7,7 @@ BINARIES += transhuge-stress
 
 all: $(BINARIES)
 %: %.c
-	$(CC) $(CFLAGS) -o $@ $^
+	$(CC) $(CFLAGS) -o $@ $^ -lrt
 
 run_tests: all
 	@/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1)
author	David S. Miller <davem@davemloft.net>	2015-01-15 00:53:17 -0500
committer	David S. Miller <davem@davemloft.net>	2015-01-15 00:53:17 -0500
commit	3f3558bb512e0762d5a4573a4aaf038d7a616e92 (patch)
tree	1e2b43d410093e949209ca33614f5cdfdd16e80e
parent	9a6b4b392de4569e83ecfd6f382f3369f250b52f (diff)
parent	a6391a924cf5a16761ccd6b45094a7d5b9aeebac (diff)
download	linux-3f3558bb512e0762d5a4573a4aaf038d7a616e92.tar.gz linux-3f3558bb512e0762d5a4573a4aaf038d7a616e92.tar.xz