Merge tag 'char-misc-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver updates from Greg KH:
 "Here is the big char/misc driver update for 4.8-rc1.

  Not a lot of stuff, but it's all over the place, full details are in
  the shortlog.  All of these have been in linux-next with no reported
  issues for a while"

* tag 'char-misc-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (49 commits)
  lkdtm: silence warnings about function declarations
  lkdtm: hide unused functions
  intel_th: pci: Add Kaby Lake PCH-H support
  intel_th: Fix a deadlock in modprobing
  dsp56k: prevent a harmless underflow
  chardev: add missing line break in pr_warn
  lkdtm: use struct arrays instead of enums
  lkdtm: move jprobe entry points to start of source
  lkdtm: reorganize module paramaters
  lkdtm: rename globals for clarity
  lkdtm: rename "count" to "crash_count"
  lkdtm: remove intentional off-by-one array access
  lkdtm: split remaining logic bug tests to separate file
  lkdtm: split heap corruption tests to separate file
  lkdtm: split memory permissions tests to separate file
  lkdtm: split usercopy tests to separate file
  lkdtm: drop "alloc_size" parameter
  lkdtm: add usercopy test for blocking kernel text
  extcon: adc-jack: add suspend/resume support
  extcon: add missing of_node_put after calling of_parse_phandle
  ...
diff --git a/.mailmap b/.mailmap
index 779a9ca..52489f5 100644
--- a/.mailmap
+++ b/.mailmap
@@ -21,6 +21,7 @@
 Andrew Morton <akpm@linux-foundation.org>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andy Adamson <andros@citi.umich.edu>
+Antoine Tenart <antoine.tenart@free-electrons.com>
 Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
 Archit Taneja <archit@ti.com>
 Arnaud Patard <arnaud.patard@rtp-net.org>
@@ -30,6 +31,9 @@
 Ben Gardner <bgardner@wabtec.com>
 Ben M Cahill <ben.m.cahill@intel.com>
 Björn Steinbrink <B.Steinbrink@gmx.de>
+Boris Brezillon <boris.brezillon@free-electrons.com>
+Boris Brezillon <boris.brezillon@free-electrons.com> <b.brezillon.dev@gmail.com>
+Boris Brezillon <boris.brezillon@free-electrons.com> <b.brezillon@overkiz.com>
 Brian Avery <b.avery@hp.com>
 Brian King <brking@us.ibm.com>
 Christoph Hellwig <hch@lst.de>
diff --git a/Documentation/gdb-kernel-debugging.txt b/Documentation/gdb-kernel-debugging.txt
index 4ab7d43..7050ce8 100644
--- a/Documentation/gdb-kernel-debugging.txt
+++ b/Documentation/gdb-kernel-debugging.txt
@@ -139,27 +139,6 @@
       start_comm = "swapper/2\000\000\000\000\000\000"
     }
 
- o Dig into a radix tree data structure, such as the IRQ descriptors:
-    (gdb) print (struct irq_desc)$lx_radix_tree_lookup(irq_desc_tree, 18)
-    $6 = {
-      irq_common_data = {
-        state_use_accessors = 67584,
-        handler_data = 0x0 <__vectors_start>,
-        msi_desc = 0x0 <__vectors_start>,
-        affinity = {{
-            bits = {65535}
-          }}
-      },
-      irq_data = {
-        mask = 0,
-        irq = 18,
-        hwirq = 27,
-        common = 0xee803d80,
-        chip = 0xc0eb0854 <gic_data>,
-        domain = 0xee808000,
-        parent_data = 0x0 <__vectors_start>,
-        chip_data = 0xc0eb0854 <gic_data>
-      } <... trimmed ...>
 
 List of commands and functions
 ------------------------------
diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 8638f61..37eca00 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -263,19 +263,23 @@
 
  3. scmd recovered
     ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
-	- shost->host_failed--
 	- clear scmd->eh_eflags
 	- scsi_setup_cmd_retry()
 	- move from local eh_work_q to local eh_done_q
     LOCKING: none
+    CONCURRENCY: at most one thread per separate eh_work_q to
+		 keep queue manipulation lockless
 
  4. EH completes
     ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
-	    layer of failure.
+	    layer of failure. May be called concurrently but must have
+	    a no more than one thread per separate eh_work_q to
+	    manipulate the queue locklessly
 	- scmd is removed from eh_done_q and scmd->eh_entry is cleared
 	- if retry is necessary, scmd is requeued using
           scsi_queue_insert()
 	- otherwise, scsi_finish_command() is invoked for scmd
+	- zero shost->host_failed
     LOCKING: queue or finish function performs appropriate locking
 
 
diff --git a/Documentation/x86/intel_mpx.txt b/Documentation/x86/intel_mpx.txt
index 1a5a121..85d0549 100644
--- a/Documentation/x86/intel_mpx.txt
+++ b/Documentation/x86/intel_mpx.txt
@@ -45,7 +45,7 @@
    MPX-instrumented.
 3) The kernel detects that the CPU has MPX, allows the new prctl() to
    succeed, and notes the location of the bounds directory. Userspace is
-   expected to keep the bounds directory at that locationWe note it
+   expected to keep the bounds directory at that location. We note it
    instead of reading it each time because the 'xsave' operation needed
    to access the bounds directory register is an expensive operation.
 4) If the application needs to spill bounds out of the 4 registers, it
@@ -167,7 +167,7 @@
 We need to decode MPX instructions to get violation address and
 set this address into extended struct siginfo.
 
-The _sigfault feild of struct siginfo is extended as follow:
+The _sigfault field of struct siginfo is extended as follow:
 
 87		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 88		struct {
@@ -240,5 +240,5 @@
 This is allowed architecturally.  See more information "Intel(R) Architecture
 Instruction Set Extensions Programming Reference" (9.3.4).
 
-However, if users did this, the kernel might be fooled in to unmaping an
+However, if users did this, the kernel might be fooled in to unmapping an
 in-use bounds table since it does not recognize sharing.
diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt
index 39d1723..6a0607b 100644
--- a/Documentation/x86/tlb.txt
+++ b/Documentation/x86/tlb.txt
@@ -5,7 +5,7 @@
     from areas other than the one we are trying to flush will be
     destroyed and must be refilled later, at some cost.
  2. Use the invlpg instruction to invalidate a single page at a
-    time.  This could potentialy cost many more instructions, but
+    time.  This could potentially cost many more instructions, but
     it is a much more precise operation, causing no collateral
     damage to other TLB entries.
 
@@ -19,7 +19,7 @@
     work.
  3. The size of the TLB.  The larger the TLB, the more collateral
     damage we do with a full flush.  So, the larger the TLB, the
-    more attrative an individual flush looks.  Data and
+    more attractive an individual flush looks.  Data and
     instructions have separate TLBs, as do different page sizes.
  4. The microarchitecture.  The TLB has become a multi-level
     cache on modern CPUs, and the global flushes have become more
diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck
index b1fb302..d0648a7 100644
--- a/Documentation/x86/x86_64/machinecheck
+++ b/Documentation/x86/x86_64/machinecheck
@@ -36,7 +36,7 @@
 
 check_interval
 	How often to poll for corrected machine check errors, in seconds
-	(Note output is hexademical). Default 5 minutes.  When the poller
+	(Note output is hexadecimal). Default 5 minutes.  When the poller
 	finds MCEs it triggers an exponential speedup (poll more often) on
 	the polling interval.  When the poller stops finding MCEs, it
 	triggers an exponential backoff (poll less often) on the polling
diff --git a/MAINTAINERS b/MAINTAINERS
index 5ec852e..6d3e135 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -595,6 +595,10 @@
 L:	linux-alpha@vger.kernel.org
 F:	arch/alpha/
 
+ALPS PS/2 TOUCHPAD DRIVER
+R:	Pali Rohár <pali.rohar@gmail.com>
+F:	drivers/input/mouse/alps.*
+
 ALTERA MAILBOX DRIVER
 M:	Ley Foon Tan <lftan@altera.com>
 L:	nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
@@ -1690,8 +1694,6 @@
 F:	drivers/edac/altera_edac.
 
 ARM/STI ARCHITECTURE
-M:	Srinivas Kandagatla <srinivas.kandagatla@gmail.com>
-M:	Maxime Coquelin <maxime.coquelin@st.com>
 M:	Patrice Chotard <patrice.chotard@st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kernel@stlinux.com
@@ -1724,6 +1726,7 @@
 
 ARM/STM32 ARCHITECTURE
 M:	Maxime Coquelin <mcoquelin.stm32@gmail.com>
+M:	Alexandre Torgue <alexandre.torgue@st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git
@@ -2776,9 +2779,9 @@
 F:	net/caif/
 
 CALGARY x86-64 IOMMU
-M:	Muli Ben-Yehuda <muli@il.ibm.com>
-M:	"Jon D. Mason" <jdmason@kudzu.us>
-L:	discuss@x86-64.org
+M:	Muli Ben-Yehuda <mulix@mulix.org>
+M:	Jon Mason <jdmason@kudzu.us>
+L:	iommu@lists.linux-foundation.org
 S:	Maintained
 F:	arch/x86/kernel/pci-calgary_64.c
 F:	arch/x86/kernel/tce_64.c
@@ -4473,7 +4476,7 @@
 F:	fs/efs/
 
 EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER
-M:	Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
+M:	Douglas Miller <dougmill@linux.vnet.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/ibm/ehea/
@@ -7420,7 +7423,7 @@
 F:	drivers/scsi/megaraid/
 
 MELLANOX ETHERNET DRIVER (mlx4_en)
-M: 	Eugenia Emantayev <eugenia@mellanox.com>
+M:	Tariq Toukan <tariqt@mellanox.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -7472,6 +7475,7 @@
 T:	git git://git.infradead.org/linux-mtd.git
 T:	git git://git.infradead.org/l2-mtd.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/mtd/
 F:	drivers/mtd/
 F:	include/linux/mtd/
 F:	include/uapi/mtd/
@@ -8959,6 +8963,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/pinctrl/
+F:	Documentation/pinctrl.txt
 F:	drivers/pinctrl/
 F:	include/linux/pinctrl/
 
diff --git a/Makefile b/Makefile
index 4fb6bea..66da9a3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION =
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
@@ -363,11 +363,13 @@
 
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void $(CF)
+NOSTDINC_FLAGS  =
 CFLAGS_MODULE   =
 AFLAGS_MODULE   =
 LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
+LDFLAGS_vmlinux =
 CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
 CFLAGS_KCOV	= -fsanitize-coverage=trace-pc
 
diff --git a/arch/Kconfig b/arch/Kconfig
index e973479..1599629 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -226,8 +226,8 @@
 config ARCH_TASK_STRUCT_ALLOCATOR
 	bool
 
-# Select if arch has its private alloc_thread_info() function
-config ARCH_THREAD_INFO_ALLOCATOR
+# Select if arch has its private alloc_thread_stack() function
+config ARCH_THREAD_STACK_ALLOCATOR
 	bool
 
 # Select if arch wants to size task_struct dynamically via arch_task_struct_size:
diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h
index aab14a0..c2ebb6f 100644
--- a/arch/alpha/include/asm/pgalloc.h
+++ b/arch/alpha/include/asm/pgalloc.h
@@ -40,7 +40,7 @@
 static inline pmd_t *
 pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return ret;
 }
 
@@ -53,7 +53,7 @@
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return pte;
 }
 
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index d4df6be..85814e7 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -66,8 +66,6 @@
 
 endif
 
-cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
-
 # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok
 ifeq ($(atleast_gcc48),y)
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -gdwarf-2
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 86ed671..3749234 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -95,7 +95,7 @@
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO,
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
 					 __get_order_pte());
 
 	return pte;
@@ -107,7 +107,7 @@
 	pgtable_t pte_pg;
 	struct page *page;
 
-	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte());
+	pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte());
 	if (!pte_pg)
 		return 0;
 	memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t));
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index e0efff1..b9192a6 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -142,7 +142,7 @@
 	 * prelogue is setup (callee regs saved and then fp set and not other
 	 * way around
 	 */
-	pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
+	pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n");
 	return 0;
 
 #endif
diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi
index 8450944..22f7a13 100644
--- a/arch/arm/boot/dts/armada-385-linksys.dtsi
+++ b/arch/arm/boot/dts/armada-385-linksys.dtsi
@@ -58,8 +58,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0xf1100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0xf1110000 0x10000>;
+			  MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
 
 		internal-regs {
 
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index a03e56f..ca58eb2 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -65,8 +65,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-hdmi";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>,
-				 <&ahb_gates 44>, <&dram_gates 26>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 43>, <&ahb_gates 44>,
+				 <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -74,8 +75,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>,
-				 <&ahb_gates 44>, <&ahb_gates 46>,
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 43>, <&ahb_gates 44>,
+				 <&ahb_gates 46>,
 				 <&dram_gates 25>, <&dram_gates 26>;
 			status = "disabled";
 		};
@@ -84,9 +86,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_fe0-de_be0-lcd0";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>,
-				 <&ahb_gates 46>, <&dram_gates 25>,
-				 <&dram_gates 26>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 44>, <&ahb_gates 46>,
+				 <&dram_gates 25>, <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -94,8 +96,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0";
-			clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>,
-				 <&ahb_gates 44>, <&ahb_gates 46>,
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>,
+				 <&ahb_gates 36>, <&ahb_gates 44>,
+				 <&ahb_gates 46>,
 				 <&dram_gates 5>, <&dram_gates 25>, <&dram_gates 26>;
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index bddd0de..367f330 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -65,8 +65,8 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-hdmi";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>,
-				 <&ahb_gates 44>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 43>, <&ahb_gates 44>;
 			status = "disabled";
 		};
 
@@ -74,7 +74,8 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 44>;
 			status = "disabled";
 		};
 
@@ -82,8 +83,8 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-tve0";
-			clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>,
-				 <&ahb_gates 44>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>,
+				 <&ahb_gates 36>, <&ahb_gates 44>;
 			status = "disabled";
 		};
 	};
diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts
index a8d8b45..f694482 100644
--- a/arch/arm/boot/dts/sun5i-r8-chip.dts
+++ b/arch/arm/boot/dts/sun5i-r8-chip.dts
@@ -52,7 +52,7 @@
 
 / {
 	model = "NextThing C.H.I.P.";
-	compatible = "nextthing,chip", "allwinner,sun5i-r8";
+	compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13";
 
 	aliases {
 		i2c0 = &i2c0;
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index febdf4c..2c34bbb 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -67,8 +67,9 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-hdmi";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>,
-				 <&ahb_gates 44>, <&dram_gates 26>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 43>, <&ahb_gates 44>,
+				 <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -76,8 +77,8 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0";
-			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>,
-				 <&dram_gates 26>;
+			clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>,
+				 <&ahb_gates 44>, <&dram_gates 26>;
 			status = "disabled";
 		};
 
@@ -85,7 +86,7 @@
 			compatible = "allwinner,simple-framebuffer",
 				     "simple-framebuffer";
 			allwinner,pipeline = "de_be0-lcd0-tve0";
-			clocks = <&pll5 1>,
+			clocks = <&pll3>, <&pll5 1>,
 				 <&ahb_gates 34>, <&ahb_gates 36>, <&ahb_gates 44>,
 				 <&dram_gates 5>, <&dram_gates 26>;
 			status = "disabled";
@@ -231,6 +232,7 @@
 		pll3x2: pll3x2_clk {
 			#clock-cells = <0>;
 			compatible = "fixed-factor-clock";
+			clocks = <&pll3>;
 			clock-div = <1>;
 			clock-mult = <2>;
 			clock-output-names = "pll3-2x";
@@ -272,6 +274,7 @@
 		pll7x2: pll7x2_clk {
 			#clock-cells = <0>;
 			compatible = "fixed-factor-clock";
+			clocks = <&pll7>;
 			clock-div = <1>;
 			clock-mult = <2>;
 			clock-output-names = "pll7-2x";
diff --git a/arch/arm/boot/dts/tegra30-beaver.dts b/arch/arm/boot/dts/tegra30-beaver.dts
index 1eca3b2..b6da15d 100644
--- a/arch/arm/boot/dts/tegra30-beaver.dts
+++ b/arch/arm/boot/dts/tegra30-beaver.dts
@@ -1843,7 +1843,7 @@
 
 				ldo5_reg: ldo5 {
 					regulator-name = "vddio_sdmmc,avdd_vdac";
-					regulator-min-microvolt = <3300000>;
+					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <3300000>;
 					regulator-always-on;
 				};
@@ -1914,6 +1914,7 @@
 
 	sdhci@78000000 {
 		status = "okay";
+		vqmmc-supply = <&ldo5_reg>;
 		cd-gpios = <&gpio TEGRA_GPIO(I, 5) GPIO_ACTIVE_LOW>;
 		wp-gpios = <&gpio TEGRA_GPIO(T, 3) GPIO_ACTIVE_HIGH>;
 		power-gpios = <&gpio TEGRA_GPIO(D, 7) GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 19cfab5..20febb3 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -29,7 +29,7 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 893941e..f1bde7c 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -263,6 +263,7 @@
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
+	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index ecf9e0c..e53c6cf 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -7,9 +7,15 @@
 obj-$(CONFIG_MACH_MVEBU_ANY)	 += system-controller.o mvebu-soc-id.o
 
 ifeq ($(CONFIG_MACH_MVEBU_V7),y)
-obj-y				 += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o pm.o pm-board.o
+obj-y				 += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o
+
+obj-$(CONFIG_PM)		 += pm.o pm-board.o
 obj-$(CONFIG_SMP)		 += platsmp.o headsmp.o platsmp-a9.o headsmp-a9.o
 endif
 
 obj-$(CONFIG_MACH_DOVE)		 += dove.o
-obj-$(CONFIG_MACH_KIRKWOOD)	 += kirkwood.o kirkwood-pm.o
+
+ifeq ($(CONFIG_MACH_KIRKWOOD),y)
+obj-y				 += kirkwood.o
+obj-$(CONFIG_PM)		 += kirkwood-pm.o
+endif
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 7e989d6..e80f0dd 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -162,22 +162,16 @@
 }
 
 /*
- * This ioremap hook is used on Armada 375/38x to ensure that PCIe
- * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This
- * is needed as a workaround for a deadlock issue between the PCIe
- * interface and the cache controller.
+ * This ioremap hook is used on Armada 375/38x to ensure that all MMIO
+ * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is
+ * needed for the HW I/O coherency mechanism to work properly without
+ * deadlock.
  */
 static void __iomem *
-armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size,
-			      unsigned int mtype, void *caller)
+armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size,
+			 unsigned int mtype, void *caller)
 {
-	struct resource pcie_mem;
-
-	mvebu_mbus_get_pcie_mem_aperture(&pcie_mem);
-
-	if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end)
-		mtype = MT_UNCACHED;
-
+	mtype = MT_UNCACHED;
 	return __arm_ioremap_caller(phys_addr, size, mtype, caller);
 }
 
@@ -186,7 +180,8 @@
 	struct device_node *cache_dn;
 
 	coherency_cpu_base = of_iomap(np, 0);
-	arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
+	arch_ioremap_caller = armada_wa_ioremap_caller;
+	pci_ioremap_set_mem_type(MT_UNCACHED);
 
 	/*
 	 * We should switch the PL310 to I/O coherency mode only if
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 7085e32..648a32c 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -95,7 +95,7 @@
 Image: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-Image.%: vmlinux
+Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zinstall install:
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 87e1985..9d9fd4b 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -80,12 +80,14 @@
 #define APM_CPU_PART_POTENZA		0x000
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585..d25f4f1 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 #define check_pgt_cache()		do { } while (0)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index a307eb6..7f94755 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -117,6 +117,8 @@
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e504..0226447 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@
 	cpu_park_loop();
 }
 
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index f8e5d47..2f4ba77 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -60,6 +60,7 @@
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index d427894..af716b6 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -98,6 +98,12 @@
 		MIDR_RANGE(MIDR_THUNDERX, 0x00,
 			   (1 << MIDR_VARIANT_SHIFT) | 1),
 	},
+	{
+	/* Cavium ThunderX, T81 pass 1.0 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
+	},
 #endif
 	{
 	}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 12e8d2b..6c3b734 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,6 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -97,7 +98,14 @@
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -128,6 +136,14 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+
+	/* No need to restore UAO, it will be restored from SPSR_EL1 */
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -406,7 +422,6 @@
 	bl	trace_hardirqs_off
 #endif
 
-	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d..21ab5df 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
+#include <asm/smp.h>
 #include <asm/suspend.h>
 #include <asm/virt.h>
 
@@ -236,6 +237,11 @@
 	unsigned long flags;
 	struct sleep_stack_data state;
 
+	if (cpus_are_stuck_in_kernel()) {
+		pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+		return -EBUSY;
+	}
+
 	local_dbg_save(flags);
 
 	if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e084..62ff3c0 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -909,3 +909,21 @@
 {
 	return -EINVAL;
 }
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int any_cpu = raw_smp_processor_id();
+
+	if (cpu_ops[any_cpu]->cpu_die)
+		return true;
+#endif
+	return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+	bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+	return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b3978..efcf1f7 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@
 						 &asid_generation);
 	flush_context(cpu);
 
-	/* We have at least 1 ASID per CPU, so this will always succeed */
+	/* We have more ASIDs than CPUs, so this will always succeed */
 	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 
 set_asid:
@@ -227,8 +227,11 @@
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
-	/* If we end up with more CPUs than ASIDs, expect things to crash */
-	WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+	/*
+	 * Expect allocation after rollover to fail if we don't have at least
+	 * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+	 */
+	WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
 	atomic64_set(&asid_generation, ASID_FIRST_VERSION);
 	asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
 			   GFP_KERNEL);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 013e2cb..b1166d1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -280,7 +280,8 @@
 	}
 
 	if (permission_fault(esr) && (addr < USER_DS)) {
-		if (get_fs() == KERNEL_DS)
+		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
+		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
 		if (!search_exception_tables(regs->pc))
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea..43a76b0 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@
 {
 	struct page *page = pte_page(pte);
 
-	/* no flushing needed for anonymous pages */
-	if (!page_mapping(page))
-		return;
-
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		sync_icache_aliases(page_address(page),
 				    PAGE_SIZE << compound_order(page));
diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h
index 1aba19d6..db039cb 100644
--- a/arch/avr32/include/asm/pgalloc.h
+++ b/arch/avr32/include/asm/pgalloc.h
@@ -43,7 +43,7 @@
  */
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return quicklist_alloc(QUICK_PGD, GFP_KERNEL | __GFP_REPEAT, pgd_ctor);
+	return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -54,7 +54,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -63,7 +63,7 @@
 	struct page *page;
 	void *pg;
 
-	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 	if (!pg)
 		return NULL;
 
diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h
index 235ece4..42f1aff 100644
--- a/arch/cris/include/asm/pgalloc.h
+++ b/arch/cris/include/asm/pgalloc.h
@@ -24,14 +24,14 @@
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-  	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
  	return pte;
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	struct page *pte;
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+	pte = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 41907d2..c9ed14f 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -22,7 +22,7 @@
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
 	if (pte)
 		clear_page(pte);
 	return pte;
@@ -33,9 +33,9 @@
 	struct page *page;
 
 #ifdef CONFIG_HIGHPTE
-	page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+	page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
 #else
-	page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	page = alloc_pages(GFP_KERNEL, 0);
 #endif
 	if (!page)
 		return NULL;
diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h
index 77da3b0..eeebf86 100644
--- a/arch/hexagon/include/asm/pgalloc.h
+++ b/arch/hexagon/include/asm/pgalloc.h
@@ -64,7 +64,7 @@
 {
 	struct page *pte;
 
-	pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	pte = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
@@ -78,7 +78,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	gfp_t flags =  GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+	gfp_t flags =  GFP_KERNEL | __GFP_ZERO;
 	return (pte_t *) __get_free_page(flags);
 }
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index f80758c..e109ee9 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -45,7 +45,7 @@
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_INIT_TASK
 	select ARCH_TASK_STRUCT_ALLOCATOR
-	select ARCH_THREAD_INFO_ALLOCATOR
+	select ARCH_THREAD_STACK_ALLOCATOR
 	select ARCH_CLOCKSOURCE_DATA
 	select GENERIC_TIME_VSYSCALL_OLD
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index aa995b6..d1212b8 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -48,15 +48,15 @@
 #ifndef ASM_OFFSETS_C
 /* how to get the thread information struct from C */
 #define current_thread_info()	((struct thread_info *) ((char *) current + IA64_TASK_SIZE))
-#define alloc_thread_info_node(tsk, node)	\
-		((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
+#define alloc_thread_stack_node(tsk, node)	\
+		((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE))
 #define task_thread_info(tsk)	((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE))
 #else
 #define current_thread_info()	((struct thread_info *) 0)
-#define alloc_thread_info_node(tsk, node)	((struct thread_info *) 0)
+#define alloc_thread_stack_node(tsk, node)	((unsigned long *) 0)
 #define task_thread_info(tsk)	((struct thread_info *) 0)
 #endif
-#define free_thread_info(ti)	/* nothing */
+#define free_thread_stack(ti)	/* nothing */
 #define task_stack_page(tsk)	((void *)(tsk))
 
 #define __HAVE_THREAD_FUNCTIONS
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index f9efe973..0eaa89f 100644
--- a/arch/ia64/kernel/init_task.c
+++ b/arch/ia64/kernel/init_task.c
@@ -26,6 +26,7 @@
  * handled. This is done by having a special ".data..init_task" section...
  */
 #define init_thread_info	init_task_mem.s.thread_info
+#define init_stack		init_task_mem.stack
 
 union {
 	struct {
diff --git a/arch/m32r/boot/compressed/m32r_sio.c b/arch/m32r/boot/compressed/m32r_sio.c
index 01d877c..cf3023d 100644
--- a/arch/m32r/boot/compressed/m32r_sio.c
+++ b/arch/m32r/boot/compressed/m32r_sio.c
@@ -8,12 +8,13 @@
 
 #include <asm/processor.h>
 
-static void putc(char c);
+static void m32r_putc(char c);
 
 static int puts(const char *s)
 {
 	char c;
-	while ((c = *s++)) putc(c);
+	while ((c = *s++))
+		m32r_putc(c);
 	return 0;
 }
 
@@ -41,7 +42,7 @@
 #define BOOT_SIO0TXB	PLD_ESIO0TXB
 #endif
 
-static void putc(char c)
+static void m32r_putc(char c)
 {
 	while ((*BOOT_SIO0STS & 0x3) != 0x3)
 		cpu_relax();
@@ -61,7 +62,7 @@
 #define SIO0TXB	(volatile unsigned short *)(0x00efd000 + 30)
 #endif
 
-static void putc(char c)
+static void m32r_putc(char c)
 {
 	while ((*SIO0STS & 0x1) == 0)
 		cpu_relax();
diff --git a/arch/m68k/coldfire/head.S b/arch/m68k/coldfire/head.S
index fa31be2..73d92ea 100644
--- a/arch/m68k/coldfire/head.S
+++ b/arch/m68k/coldfire/head.S
@@ -288,7 +288,7 @@
 #endif
 
 	/*
-	 *	Assember start up done, start code proper.
+	 *	Assembler start up done, start code proper.
 	 */
 	jsr	start_kernel			/* start Linux kernel */
 
diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c
index c525e4c..9abb1a4 100644
--- a/arch/m68k/coldfire/m5272.c
+++ b/arch/m68k/coldfire/m5272.c
@@ -111,7 +111,7 @@
 /***************************************************************************/
 
 /*
- * Some 5272 based boards have the FEC ethernet diectly connected to
+ * Some 5272 based boards have the FEC ethernet directly connected to
  * an ethernet switch. In this case we need to use the fixed phy type,
  * and we need to declare it early in boot.
  */
diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index 821de92..6a640be 100644
--- a/arch/m68k/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
@@ -42,7 +42,7 @@
 
 /*
  * We need to be carefull probing on bus 0 (directly connected to host
- * bridge). We should only acccess the well defined possible devices in
+ * bridge). We should only access the well defined possible devices in
  * use, ignore aliases and the like.
  */
 static unsigned char mcf_host_slot2sid[32] = {
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 3ee6976..8f5b6f7 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -359,6 +360,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -553,7 +555,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index e96787f..31bded9 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -341,6 +342,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -512,7 +514,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 083fe6b..0d7739e 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -350,6 +351,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -533,7 +535,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 475130c..2cbb5c4 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -340,6 +341,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -504,7 +506,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 4339658c..96102a4 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -341,6 +342,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -514,7 +516,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 831cc8c..97d88f7 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -357,6 +358,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -536,7 +538,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 6377afe..be25ef2 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -390,6 +391,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -616,7 +618,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 4304b3d..a008344 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -339,6 +340,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -504,7 +506,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 074bda4..6735a25 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -340,6 +341,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -504,7 +506,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 07b9fa8..780c6e9 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -346,6 +347,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -527,7 +529,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 36e6fae0..44693cf 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -337,6 +338,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -506,7 +508,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 903acf9..ef0071d 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -9,6 +9,7 @@
 # CONFIG_PID_NS is not set
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_USERFAULTFD=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -337,6 +338,7 @@
 CONFIG_IPVLAN=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
@@ -506,7 +508,9 @@
 CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
+CONFIG_TEST_UUID=m
 CONFIG_TEST_RHASHTABLE=m
+CONFIG_TEST_HASH=m
 CONFIG_TEST_LKM=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
diff --git a/arch/m68k/ifpsp060/src/fpsp.S b/arch/m68k/ifpsp060/src/fpsp.S
index 78cb60f..9bbffeb 100644
--- a/arch/m68k/ifpsp060/src/fpsp.S
+++ b/arch/m68k/ifpsp060/src/fpsp.S
@@ -10191,7 +10191,7 @@
 xdnrm_sd:
 	mov.l		%a1,-(%sp)
 	tst.b		LOCAL_EX(%a0)		# is denorm pos or neg?
-	smi.b		%d1			# set d0 accodingly
+	smi.b		%d1			# set d0 accordingly
 	bsr.l		unf_sub
 	mov.l		(%sp)+,%a1
 xdnrm_exit:
@@ -10990,7 +10990,7 @@
 # routines where an instruction is selected by an index into
 # a large jump table corresponding to a given instruction which
 # has been decoded. Flow continues here where we now decode
-# further accoding to the source operand type.
+# further according to the source operand type.
 #
 
 	global		fsinh
@@ -23196,14 +23196,14 @@
 #
 #  1. Branch on the sign of the adjusted exponent.
 #  2p.(positive exp)
-#   2. Check M16 and the digits in lwords 2 and 3 in decending order.
+#   2. Check M16 and the digits in lwords 2 and 3 in descending order.
 #   3. Add one for each zero encountered until a non-zero digit.
 #   4. Subtract the count from the exp.
 #   5. Check if the exp has crossed zero in #3 above; make the exp abs
 #	   and set SE.
 #	6. Multiply the mantissa by 10**count.
 #  2n.(negative exp)
-#   2. Check the digits in lwords 3 and 2 in decending order.
+#   2. Check the digits in lwords 3 and 2 in descending order.
 #   3. Add one for each zero encountered until a non-zero digit.
 #   4. Add the count to the exp.
 #   5. Check if the exp has crossed zero in #3 above; clear SE.
diff --git a/arch/m68k/ifpsp060/src/pfpsp.S b/arch/m68k/ifpsp060/src/pfpsp.S
index 4aedef9..3535e6c 100644
--- a/arch/m68k/ifpsp060/src/pfpsp.S
+++ b/arch/m68k/ifpsp060/src/pfpsp.S
@@ -13156,14 +13156,14 @@
 #
 #  1. Branch on the sign of the adjusted exponent.
 #  2p.(positive exp)
-#   2. Check M16 and the digits in lwords 2 and 3 in decending order.
+#   2. Check M16 and the digits in lwords 2 and 3 in descending order.
 #   3. Add one for each zero encountered until a non-zero digit.
 #   4. Subtract the count from the exp.
 #   5. Check if the exp has crossed zero in #3 above; make the exp abs
 #	   and set SE.
 #	6. Multiply the mantissa by 10**count.
 #  2n.(negative exp)
-#   2. Check the digits in lwords 3 and 2 in decending order.
+#   2. Check the digits in lwords 3 and 2 in descending order.
 #   3. Add one for each zero encountered until a non-zero digit.
 #   4. Add the count to the exp.
 #   5. Check if the exp has crossed zero in #3 above; clear SE.
diff --git a/arch/m68k/include/asm/dma.h b/arch/m68k/include/asm/dma.h
index 429fe26..208b4da 100644
--- a/arch/m68k/include/asm/dma.h
+++ b/arch/m68k/include/asm/dma.h
@@ -18,7 +18,7 @@
  * AUG/22/2000 : added support for 32-bit Dual-Address-Mode (K) 2000
  *               Oliver Kamphenkel (O.Kamphenkel@tu-bs.de)
  *
- * AUG/25/2000 : addad support for 8, 16 and 32-bit Single-Address-Mode (K)2000
+ * AUG/25/2000 : added support for 8, 16 and 32-bit Single-Address-Mode (K)2000
  *               Oliver Kamphenkel (O.Kamphenkel@tu-bs.de)
  *
  * APR/18/2002 : added proper support for MCF5272 DMA controller.
diff --git a/arch/m68k/include/asm/m525xsim.h b/arch/m68k/include/asm/m525xsim.h
index f186459..699f20c 100644
--- a/arch/m68k/include/asm/m525xsim.h
+++ b/arch/m68k/include/asm/m525xsim.h
@@ -123,10 +123,10 @@
 /*
  *	I2C module.
  */
-#define MCFI2C_BASE0		(MCF_MBAR + 0x280)	/* Base addreess I2C0 */
+#define MCFI2C_BASE0		(MCF_MBAR + 0x280)	/* Base address I2C0 */
 #define MCFI2C_SIZE0		0x20			/* Register set size */
 
-#define MCFI2C_BASE1		(MCF_MBAR2 + 0x440)	/* Base addreess I2C1 */
+#define MCFI2C_BASE1		(MCF_MBAR2 + 0x440)	/* Base address I2C1 */
 #define MCFI2C_SIZE1		0x20			/* Register set size */
 
 /*
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index f9924fb..fb95aed 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -14,7 +14,7 @@
 extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 	unsigned long address)
 {
-	unsigned long page = __get_free_page(GFP_DMA|__GFP_REPEAT);
+	unsigned long page = __get_free_page(GFP_DMA);
 
 	if (!page)
 		return NULL;
@@ -51,7 +51,7 @@
 static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	unsigned long address)
 {
-	struct page *page = alloc_pages(GFP_DMA|__GFP_REPEAT, 0);
+	struct page *page = alloc_pages(GFP_DMA, 0);
 	pte_t *pte;
 
 	if (!page)
diff --git a/arch/m68k/include/asm/mcfmmu.h b/arch/m68k/include/asm/mcfmmu.h
index 26cc3d5..8824236e 100644
--- a/arch/m68k/include/asm/mcfmmu.h
+++ b/arch/m68k/include/asm/mcfmmu.h
@@ -38,7 +38,7 @@
 /*
  *	MMU Operation register.
  */
-#define	MMUOR_UAA	0x00000001		/* Update allocatiom address */
+#define	MMUOR_UAA	0x00000001		/* Update allocation address */
 #define	MMUOR_ACC	0x00000002		/* TLB access */
 #define	MMUOR_RD	0x00000004		/* TLB access read */
 #define	MMUOR_WR	0x00000000		/* TLB access write */
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 24bcba4..c895b98 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -11,7 +11,7 @@
 {
 	pte_t *pte;
 
-	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (pte) {
 		__flush_page_to_ram(pte);
 		flush_tlb_kernel_page(pte);
@@ -32,7 +32,7 @@
 	struct page *page;
 	pte_t *pte;
 
-	page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+	page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0);
 	if(!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/m68k/include/asm/q40_master.h b/arch/m68k/include/asm/q40_master.h
index fc5b362..c48d21b 100644
--- a/arch/m68k/include/asm/q40_master.h
+++ b/arch/m68k/include/asm/q40_master.h
@@ -1,6 +1,6 @@
 /*
  * Q40 master Chip Control
- * RTC stuff merged for compactnes..
+ * RTC stuff merged for compactness.
 */
 
 #ifndef _Q40_MASTER_H
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index 0931388..1901f61 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -37,7 +37,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	unsigned long page = __get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	unsigned long page = __get_free_page(GFP_KERNEL);
 
 	if (!page)
 		return NULL;
@@ -49,7 +49,7 @@
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 					unsigned long address)
 {
-        struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+        struct page *page = alloc_pages(GFP_KERNEL, 0);
 
 	if (page == NULL)
 		return NULL;
diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index 4d2adfb..7990b6f 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -60,7 +60,7 @@
  *
  * The host talks to the IOPs using a rather simple message-passing scheme via
  * a shared memory area in the IOP RAM. Each IOP has seven "channels"; each
- * channel is conneced to a specific software driver on the IOP. For example
+ * channel is connected to a specific software driver on the IOP. For example
  * on the SCC IOP there is one channel for each serial port. Each channel has
  * an incoming and and outgoing message queue with a depth of one.
  *
diff --git a/arch/m68k/math-emu/fp_decode.h b/arch/m68k/math-emu/fp_decode.h
index 759679d..6d1e760 100644
--- a/arch/m68k/math-emu/fp_decode.h
+++ b/arch/m68k/math-emu/fp_decode.h
@@ -130,7 +130,7 @@
 	bfextu	%d2{#13,#3},%d0
 .endm
 
-| decode the 8bit diplacement from the brief extension word
+| decode the 8bit displacement from the brief extension word
 .macro	fp_decode_disp8
 	move.b	%d2,%d0
 	ext.w	%d0
diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h
index 3104df0..c2caa1e 100644
--- a/arch/metag/include/asm/pgalloc.h
+++ b/arch/metag/include/asm/pgalloc.h
@@ -42,8 +42,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT |
-					      __GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	return pte;
 }
 
@@ -51,7 +50,7 @@
 				      unsigned long address)
 {
 	struct page *pte;
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	pte = alloc_pages(GFP_KERNEL  | __GFP_ZERO, 0);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index 61436d6..7c89390 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -116,9 +116,9 @@
 	struct page *ptepage;
 
 #ifdef CONFIG_HIGHPTE
-	int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT;
+	int flags = GFP_KERNEL | __GFP_HIGHMEM;
 #else
-	int flags = GFP_KERNEL | __GFP_REPEAT;
+	int flags = GFP_KERNEL;
 #endif
 
 	ptepage = alloc_pages(flags, 0);
diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c
index 4f4520e..eb99fcc 100644
--- a/arch/microblaze/mm/pgtable.c
+++ b/arch/microblaze/mm/pgtable.c
@@ -239,8 +239,7 @@
 {
 	pte_t *pte;
 	if (mem_init_done) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL |
-					__GFP_REPEAT | __GFP_ZERO);
+		pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	} else {
 		pte = (pte_t *)early_get_page();
 		if (pte)
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index b336037..93c079a 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -69,7 +69,7 @@
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, PTE_ORDER);
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
 
 	return pte;
 }
@@ -79,7 +79,7 @@
 {
 	struct page *pte;
 
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+	pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
 	if (!pte)
 		return NULL;
 	clear_highpage(pte);
@@ -113,7 +113,7 @@
 {
 	pmd_t *pmd;
 
-	pmd = (pmd_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PMD_ORDER);
+	pmd = (pmd_t *) __get_free_pages(GFP_KERNEL, PMD_ORDER);
 	if (pmd)
 		pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table);
 	return pmd;
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index a6b611f..7d44e88 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -24,7 +24,7 @@
 struct vm_area_struct;
 
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \
-				 _CACHE_CACHABLE_NONCOHERENT)
+				 _page_cachable_default)
 #define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_WRITE | \
 				 _page_cachable_default)
 #define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \
@@ -476,7 +476,7 @@
 	pte.pte_low  &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK);
 	pte.pte_high &= (_PFN_MASK | _CACHE_MASK);
 	pte.pte_low  |= pgprot_val(newprot) & ~_PFNX_MASK;
-	pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK;
+	pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK);
 	return pte;
 }
 #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
@@ -491,7 +491,8 @@
 #else
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
+		     (pgprot_val(newprot) & ~_PAGE_CHG_MASK));
 }
 #endif
 
@@ -632,7 +633,8 @@
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot);
+	pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) |
+		       (pgprot_val(newprot) & ~_PAGE_CHG_MASK);
 	return pmd;
 }
 
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index 4861a78..f5f90bb 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -115,7 +115,7 @@
 }
 
 #ifndef CONFIG_KGDB
-void arch_release_thread_info(struct thread_info *ti);
+void arch_release_thread_stack(unsigned long *stack);
 #endif
 #define get_thread_info(ti)	get_task_struct((ti)->task)
 #define put_thread_info(ti)	put_task_struct((ti)->task)
diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c
index 9977082..2d7986c 100644
--- a/arch/mn10300/kernel/kgdb.c
+++ b/arch/mn10300/kernel/kgdb.c
@@ -397,8 +397,9 @@
  * single-step state is cleared.  At this point the breakpoints should have
  * been removed by __switch_to().
  */
-void arch_release_thread_info(struct thread_info *ti)
+void arch_release_thread_stack(unsigned long *stack)
 {
+	struct thread_info *ti = (void *)stack;
 	if (kgdb_sstep_thread == ti) {
 		kgdb_sstep_thread = NULL;
 
diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c
index e77a7c7..9577cf7 100644
--- a/arch/mn10300/mm/pgtable.c
+++ b/arch/mn10300/mm/pgtable.c
@@ -63,7 +63,7 @@
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
 	if (pte)
 		clear_page(pte);
 	return pte;
@@ -74,9 +74,9 @@
 	struct page *pte;
 
 #ifdef CONFIG_HIGHPTE
-	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
+	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
 #else
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	pte = alloc_pages(GFP_KERNEL, 0);
 #endif
 	if (!pte)
 		return NULL;
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index 6e2985e..bb47d08 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -42,8 +42,7 @@
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
-					PTE_ORDER);
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
 
 	return pte;
 }
@@ -53,7 +52,7 @@
 {
 	struct page *pte;
 
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+	pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
 	if (pte) {
 		if (!pgtable_page_ctor(pte)) {
 			__free_page(pte);
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 21484e5b..87eebd1 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -77,7 +77,7 @@
 					 unsigned long address)
 {
 	struct page *pte;
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	pte = alloc_pages(GFP_KERNEL, 0);
 	if (!pte)
 		return NULL;
 	clear_page(page_address(pte));
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index 62b08ef..5b2a9511 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -122,7 +122,7 @@
 	pte_t *pte;
 
 	if (likely(mem_init_done)) {
-		pte = (pte_t *) __get_free_page(GFP_KERNEL | __GFP_REPEAT);
+		pte = (pte_t *) __get_free_page(GFP_KERNEL);
 	} else {
 		pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
 #if 0
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f2fd327..f08dda3f0 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -63,8 +63,7 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
-					       PMD_ORDER);
+	pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER);
 	if (pmd)
 		memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
 	return pmd;
@@ -124,7 +123,7 @@
 static inline pgtable_t
 pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
@@ -137,7 +136,7 @@
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
 {
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return pte;
 }
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 01f7464..0a9d439 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -128,7 +128,7 @@
 	select IRQ_FORCED_THREADING
 	select HAVE_RCU_TABLE_FREE if SMP
 	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT
+	select HAVE_CBPF_JIT if CPU_BIG_ENDIAN
 	select HAVE_ARCH_JUMP_LABEL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index a2350194..8e21bb4 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -102,7 +102,6 @@
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	tlb_flush_pgtable(tlb, address);
 	pgtable_page_dtor(table);
 	pgtable_free_tlb(tlb, page_address(table), 0);
 }
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 290157e..74839f24 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -88,6 +88,7 @@
 #define HPTE_R_RPN_SHIFT	12
 #define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
 #define HPTE_R_PP		ASM_CONST(0x0000000000000003)
+#define HPTE_R_PPP		ASM_CONST(0x8000000000000003)
 #define HPTE_R_N		ASM_CONST(0x0000000000000004)
 #define HPTE_R_G		ASM_CONST(0x0000000000000008)
 #define HPTE_R_M		ASM_CONST(0x0000000000000010)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 488279e..cd5e7aa 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -41,7 +41,7 @@
 			pgtable_cache[(shift) - 1];	\
 		})
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
 
 extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int);
 extern void pte_fragment_free(unsigned long *, int);
@@ -56,7 +56,7 @@
 	return (pgd_t *)__get_free_page(PGALLOC_GFP);
 #else
 	struct page *page;
-	page = alloc_pages(PGALLOC_GFP, 4);
+	page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4);
 	if (!page)
 		return NULL;
 	return (pgd_t *) page_address(page);
@@ -93,8 +93,7 @@
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -110,13 +109,17 @@
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
                                   unsigned long address)
 {
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
         pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE);
 }
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
@@ -127,6 +130,11 @@
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
                                   unsigned long address)
 {
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
         return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX);
 }
 
@@ -151,7 +159,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -198,7 +206,11 @@
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	tlb_flush_pgtable(tlb, address);
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
 	pgtable_free_tlb(tlb, table, 0);
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 88a5eca..ab84c89 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -230,6 +230,7 @@
 #define KERN_VIRT_SIZE  __kernel_virt_size
 extern struct page *vmemmap;
 extern unsigned long ioremap_bot;
+extern unsigned long pci_io_base;
 #endif /* __ASSEMBLY__ */
 
 #include <asm/book3s/64/hash.h>
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 937d4e2..df29422 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -228,5 +228,20 @@
 
 extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 				 pgprot_t flags, unsigned int psz);
+
+static inline unsigned long radix__get_tree_size(void)
+{
+	unsigned long rts_field;
+	/*
+	 * we support 52 bits, hence 52-31 = 21, 0b10101
+	 * RTS encoding details
+	 * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
+	 * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
+	 */
+	rts_field = (0x5UL << 5); /* 6 - 8 bits */
+	rts_field |= (0x2UL << 61);
+
+	return rts_field;
+}
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 13ef388..3fa94fca 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -18,16 +18,19 @@
 extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 				    unsigned long ap, int nid);
+extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__tlb_flush(struct mmu_gather *tlb);
 #ifdef CONFIG_SMP
 extern void radix__flush_tlb_mm(struct mm_struct *mm);
 extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 			      unsigned long ap, int nid);
+extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 #else
 #define radix__flush_tlb_mm(mm)		radix__local_flush_tlb_mm(mm)
 #define radix__flush_tlb_page(vma,addr)	radix__local_flush_tlb_page(vma,addr)
 #define radix___flush_tlb_page(mm,addr,p,i)	radix___local_flush_tlb_page(mm,addr,p,i)
+#define radix__flush_tlb_pwc(tlb, addr)	radix__local_flush_tlb_pwc(tlb, addr)
 #endif
 
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index d98424a..96e5769 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -72,5 +72,19 @@
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
 #define flush_tlb_page(vma, addr)	local_flush_tlb_page(vma, addr)
 #endif /* CONFIG_SMP */
+/*
+ * flush the page walk cache for the address
+ */
+static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+	/*
+	 * Flush the page table walk cache on freeing a page table. We already
+	 * have marked the upper/higher level page table entry none by now.
+	 * So it is safe to flush PWC here.
+	 */
+	if (!radix_enabled())
+		return;
 
+	radix__flush_tlb_pwc(tlb, address);
+}
 #endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */
diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h
index 54f591e..c0a69ae 100644
--- a/arch/powerpc/include/asm/book3s/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/pgalloc.h
@@ -4,11 +4,6 @@
 #include <linux/mm.h>
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
-				     unsigned long address)
-{
-
-}
 
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/pgalloc.h>
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 069369f..897d2e1 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -57,8 +57,7 @@
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -88,7 +87,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -190,8 +189,7 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2714a3b..d70101e 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -642,13 +642,12 @@
 		if (pe->type & EEH_PE_VF) {
 			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
 		} else {
-			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_lock_rescan_remove();
 			pci_hp_remove_devices(bus);
 			pci_unlock_rescan_remove();
 		}
 	} else if (frozen_bus) {
-		eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data);
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
 	}
 
 	/*
@@ -692,10 +691,12 @@
 		 */
 		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
-		if (pe->type & EEH_PE_VF)
+		if (pe->type & EEH_PE_VF) {
 			eeh_add_virt_device(edev, NULL);
-		else
+		} else {
+			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 			pci_hp_add_devices(bus);
+		}
 	} else if (frozen_bus && rmv_data->removed) {
 		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
 		ssleep(5);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4c94406..8bcc1b4 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1399,11 +1399,12 @@
 	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
 
 	mtlr	r10
-BEGIN_MMU_FTR_SECTION
-	b	2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
 	andi.	r10,r12,MSR_RI	/* check for unrecoverable exception */
+BEGIN_MMU_FTR_SECTION
 	beq-	2f
+FTR_SECTION_ELSE
+	b	2f
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
 
 .machine	push
 .machine	"power4"
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3759df5..a5ae49a 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -47,7 +47,6 @@
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
-	pci_io_base = ISA_IO_BASE;
 	/* For now, override phys_mem_access_prot. If we need it,g
 	 * later, we may move that initialization to each ppc_md
 	 */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e2f12cb..0b93893 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1505,6 +1505,16 @@
 		current->thread.regs = regs - 1;
 	}
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Clear any transactional state, we're exec()ing. The cause is
+	 * not important as there will never be a recheckpoint so it's not
+	 * user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+#endif
+
 	memset(regs->gpr, 0, sizeof(regs->gpr));
 	regs->ctr = 0;
 	regs->link = 0;
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index bf8f34a..b7019b5 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@
 	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
-	/* We need to setup MSR for VSX register save instructions.  Here we
-	 * also clear the MSR RI since when we do the treclaim, we won't have a
-	 * valid kernel pointer for a while.  We clear RI here as it avoids
-	 * adding another mtmsr closer to the treclaim.  This makes the region
-	 * maked as non-recoverable wider than it needs to be but it saves on
-	 * inserting another mtmsrd later.
-	 */
+	/* We need to setup MSR for VSX register save instructions. */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
-	li	r16, MSR_RI
+	li	r16, 0
 	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@
 1:	tdeqi   r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* The moment we treclaim, ALL of our GPRs will switch
+	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	li	r4, 0
+	mtmsrd	r4, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 *
+	 * The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
 	 */
@@ -197,6 +201,11 @@
 
 	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
+
+	/* Reset MSR RI so we can take SLB faults again */
+	li	r11, MSR_RI
+	mtmsrd	r11, 1
+
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -397,11 +406,6 @@
 	ld	r5, THREAD_TM_DSCR(r3)
 	ld	r6, THREAD_TM_PPR(r3)
 
-	/* Clear the MSR RI since we are about to change R1.  EE is already off
-	 */
-	li	r4, 0
-	mtmsrd	r4, 1
-
 	REST_GPR(0, r7)				/* GPR0 */
 	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
@@ -439,10 +443,33 @@
 	ld	r6, _CCR(r7)
 	mtcr    r6
 
-	REST_GPR(1, r7)				/* GPR1 */
-	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
-	ld	r7, GPR7(r7)
+
+	/*
+	 * Store r1 and r5 on the stack so that we can access them
+	 * after we clear MSR RI.
+	 */
+
+	REST_GPR(5, r7)
+	std	r5, -8(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -16(r1)
+
+	REST_GPR(7, r7)
+
+	/* Clear MSR RI since we are about to change r1. EE is already off */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 */
+
+	ld	r5, -8(r1)
+	ld	r1, -16(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 40e05e7..f8a871a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -316,8 +316,8 @@
 			DBG_LOW(" -> hit\n");
 			/* Update the HPTE */
 			hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-						~(HPTE_R_PP | HPTE_R_N)) |
-					       (newpp & (HPTE_R_PP | HPTE_R_N |
+						~(HPTE_R_PPP | HPTE_R_N)) |
+					       (newpp & (HPTE_R_PPP | HPTE_R_N |
 							 HPTE_R_C)));
 		}
 		native_unlock_hpte(hptep);
@@ -385,8 +385,8 @@
 
 	/* Update the HPTE */
 	hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-			~(HPTE_R_PP | HPTE_R_N)) |
-		(newpp & (HPTE_R_PP | HPTE_R_N)));
+				~(HPTE_R_PPP | HPTE_R_N)) |
+			       (newpp & (HPTE_R_PPP | HPTE_R_N)));
 	/*
 	 * Ensure it is out of the tlb too. Bolted entries base and
 	 * actual page size will be same.
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index b2740c6..2971ea1 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -201,9 +201,8 @@
 	/*
 	 * We can't allow hardware to update hpte bits. Hence always
 	 * set 'R' bit and set 'C' if it is a write fault
-	 * Memory coherence is always enabled
 	 */
-	rflags |=  HPTE_R_R | HPTE_R_M;
+	rflags |=  HPTE_R_R;
 
 	if (pteflags & _PAGE_DIRTY)
 		rflags |= HPTE_R_C;
@@ -213,10 +212,15 @@
 
 	if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT)
 		rflags |= HPTE_R_I;
-	if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT)
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
 		rflags |= (HPTE_R_I | HPTE_R_G);
-	if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
-		rflags |= (HPTE_R_I | HPTE_R_W);
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
+	else
+		/*
+		 * Add memory coherence if cache inhibited is not set
+		 */
+		rflags |= HPTE_R_M;
 
 	return rflags;
 }
@@ -918,6 +922,10 @@
 	vmemmap = (struct page *)H_VMEMMAP_BASE;
 	ioremap_bot = IOREMAP_BASE;
 
+#ifdef CONFIG_PCI
+	pci_io_base = ISA_IO_BASE;
+#endif
+
 	/* Initialize the MMU Hash table and create the linear mapping
 	 * of memory. Has to be done before SLB initialization as this is
 	 * currently where the page size encoding is obtained.
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5aac1a3..119d186 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -73,7 +73,7 @@
 	cachep = PGT_CACHE(pdshift - pshift);
 #endif
 
-	new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
+	new = kmem_cache_zalloc(cachep, GFP_KERNEL);
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 227b2a6..19622222 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -65,7 +65,7 @@
 	/*
 	 * set the process table entry,
 	 */
-	rts_field = 3ull << PPC_BITLSHIFT(2);
+	rts_field = radix__get_tree_size();
 	process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE);
 	return 0;
 }
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index c939e6e..7931e14 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -160,9 +160,8 @@
 	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
 	/*
 	 * Fill in the process table.
-	 * we support 52 bits, hence 52-28 = 24, 11000
 	 */
-	rts_field = 3ull << PPC_BITLSHIFT(2);
+	rts_field = radix__get_tree_size();
 	process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);
 	/*
 	 * Fill in the partition table. We are suppose to use effective address
@@ -176,10 +175,8 @@
 static void __init radix_init_partition_table(void)
 {
 	unsigned long rts_field;
-	/*
-	 * we support 52 bits, hence 52-28 = 24, 11000
-	 */
-	rts_field = 3ull << PPC_BITLSHIFT(2);
+
+	rts_field = radix__get_tree_size();
 
 	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
 	partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
@@ -331,6 +328,11 @@
 	__vmalloc_end = RADIX_VMALLOC_END;
 	vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
 	ioremap_bot = IOREMAP_BASE;
+
+#ifdef CONFIG_PCI
+	pci_io_base = ISA_IO_BASE;
+#endif
+
 	/*
 	 * For now radix also use the same frag size
 	 */
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index bf7bf32..7f922f5 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -84,7 +84,7 @@
 	pte_t *pte;
 
 	if (slab_is_available()) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	} else {
 		pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 		if (pte)
@@ -97,7 +97,7 @@
 {
 	struct page *ptepage;
 
-	gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO;
+	gfp_t flags = GFP_KERNEL | __GFP_ZERO;
 
 	ptepage = alloc_pages(flags, 0);
 	if (!ptepage)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index e009e06..f5e8d4e 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -350,8 +350,7 @@
 static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 {
 	void *ret = NULL;
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
-				       __GFP_REPEAT | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!kernel && !pgtable_page_ctor(page)) {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 54efba2..ab2f60e 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -18,16 +18,20 @@
 
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbiel_pid(unsigned long pid, int set)
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
+static inline void __tlbiel_pid(unsigned long pid, int set,
+				unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rb |= set << PPC_BITLSHIFT(51);
 	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -39,25 +43,24 @@
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
-static inline void _tlbiel_pid(unsigned long pid)
+static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 {
 	int set;
 
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
-		__tlbiel_pid(pid, set);
+		__tlbiel_pid(pid, set, ric);
 	}
 	return;
 }
 
-static inline void _tlbie_pid(unsigned long pid)
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -67,16 +70,15 @@
 }
 
 static inline void _tlbiel_va(unsigned long va, unsigned long pid,
-			      unsigned long ap)
+			      unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = va & ~(PPC_BITMASK(52, 63));
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
@@ -86,16 +88,15 @@
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
-			     unsigned long ap)
+			     unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = va & ~(PPC_BITMASK(52, 63));
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
@@ -122,11 +123,26 @@
 	preempt_disable();
 	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
+void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	unsigned long pid;
+	struct mm_struct *mm = tlb->mm;
+
+	preempt_disable();
+
+	pid = mm->context.id;
+	if (pid != MMU_NO_CONTEXT)
+		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+
+	preempt_enable();
+}
+EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
+
 void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 			    unsigned long ap, int nid)
 {
@@ -135,7 +151,7 @@
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_va(vmaddr, pid, ap);
+		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 
@@ -172,16 +188,42 @@
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
-		_tlbie_pid(pid);
+		_tlbie_pid(pid, RIC_FLUSH_ALL);
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_pid(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 no_context:
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
+void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	unsigned long pid;
+	struct mm_struct *mm = tlb->mm;
+
+	preempt_disable();
+
+	pid = mm->context.id;
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		goto no_context;
+
+	if (!mm_is_core_local(mm)) {
+		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+		if (lock_tlbie)
+			raw_spin_lock(&native_tlbie_lock);
+		_tlbie_pid(pid, RIC_FLUSH_PWC);
+		if (lock_tlbie)
+			raw_spin_unlock(&native_tlbie_lock);
+	} else
+		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+no_context:
+	preempt_enable();
+}
+EXPORT_SYMBOL(radix__flush_tlb_pwc);
+
 void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 		       unsigned long ap, int nid)
 {
@@ -196,11 +238,11 @@
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
-		_tlbie_va(vmaddr, pid, ap);
+		_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_va(vmaddr, pid, ap);
+		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 bail:
 	preempt_enable();
 }
@@ -224,7 +266,7 @@
 
 	if (lock_tlbie)
 		raw_spin_lock(&native_tlbie_lock);
-	_tlbie_pid(0);
+	_tlbie_pid(0, RIC_FLUSH_ALL);
 	if (lock_tlbie)
 		raw_spin_unlock(&native_tlbie_lock);
 }
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index 5e04f3c..8ae236b0 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -22,7 +22,7 @@
 		"	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "=d" (rc), "=d" (orig_fpc)
+		: "=d" (rc), "=&d" (orig_fpc)
 		: "d" (fpc), "0" (-EINVAL));
 	return rc;
 }
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f20abdb..d14069d 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2064,12 +2064,5 @@
 	S390_lowcore.program_new_psw.addr =
 		(unsigned long) s390_base_pgm_handler;
 
-	/*
-	 * Clear subchannel ID and number to signal new kernel that no CCW or
-	 * SCSI IPL has been done (for kexec and kdump)
-	 */
-	S390_lowcore.subchannel_id = 0;
-	S390_lowcore.subchannel_nr = 0;
-
 	do_reset_calls();
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 59215c5..7ec63b1 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -649,6 +649,8 @@
 
 /* Performance monitoring unit for s390x */
 static struct pmu cpumf_pmu = {
+	.task_ctx_nr  = perf_sw_context,
+	.capabilities = PERF_PMU_CAP_NO_INTERRUPT,
 	.pmu_enable   = cpumf_pmu_enable,
 	.pmu_disable  = cpumf_pmu_disable,
 	.event_init   = cpumf_pmu_event_init,
@@ -708,12 +710,6 @@
 		goto out;
 	}
 
-	/* The CPU measurement counter facility does not have overflow
-	 * interrupts to do sampling.  Sampling must be provided by
-	 * external means, for example, by timers.
-	 */
-	cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
-
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
 	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
 	if (rc) {
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e8b5962..e2565d2 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -169,7 +169,7 @@
 			return table;
 	}
 	/* Allocate a fresh page */
-	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	page = alloc_page(GFP_KERNEL);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4324b87..9f0ce0e 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -437,7 +437,7 @@
 	pgste = pgste_get_lock(ptep);
 	pgstev = pgste_val(pgste);
 	pte = *ptep;
-	if (pte_swap(pte) &&
+	if (!reset && pte_swap(pte) &&
 	    ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
 	     (pgstev & _PGSTE_GPS_ZERO))) {
 		ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 2e06765..49b012d 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -42,8 +42,7 @@
 {
 	pte_t *pte;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO,
-					PTE_ORDER);
+	pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
 
 	return pte;
 }
@@ -53,7 +52,7 @@
 {
 	struct page *pte;
 
-	pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER);
+	pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
 	if (!pte)
 		return NULL;
 	clear_highpage(pte);
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index a33673b..f3f42c8 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -34,7 +34,7 @@
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
@@ -43,7 +43,7 @@
 	struct page *page;
 	void *pg;
 
-	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL);
+	pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
 	if (!pg)
 		return NULL;
 	page = virt_to_page(pg);
diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c
index 26e03a1..a62bd86 100644
--- a/arch/sh/mm/pgtable.c
+++ b/arch/sh/mm/pgtable.c
@@ -1,7 +1,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO
 
 static struct kmem_cache *pgd_cachep;
 #if PAGETABLE_LEVELS > 2
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 5e31871..3529f13 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -41,8 +41,7 @@
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache,
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
@@ -52,8 +51,7 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache,
-				GFP_KERNEL|__GFP_REPEAT);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 14bb0d5..aec508e 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2704,8 +2704,7 @@
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 			    unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
-				       __GFP_REPEAT | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	pte_t *pte = NULL;
 
 	if (page)
@@ -2717,8 +2716,7 @@
 pgtable_t pte_alloc_one(struct mm_struct *mm,
 			unsigned long address)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
-				       __GFP_REPEAT | __GFP_ZERO);
+	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 4b7cef9..c1467ac 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -78,7 +78,7 @@
 
 #ifndef __ASSEMBLY__
 
-void arch_release_thread_info(struct thread_info *info);
+void arch_release_thread_stack(unsigned long *stack);
 
 /* How to get the thread information struct from C. */
 register unsigned long stack_pointer __asm__("sp");
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 6b705cc..a465d83 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -73,8 +73,9 @@
 /*
  * Release a thread_info structure
  */
-void arch_release_thread_info(struct thread_info *info)
+void arch_release_thread_stack(unsigned long *stack)
 {
+	struct thread_info *info = (void *)stack;
 	struct single_step_state *step_state = info->step_state;
 
 	if (step_state) {
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 7bf2491..c4d5bf8 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -231,7 +231,7 @@
 struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address,
 			       int order)
 {
-	gfp_t flags = GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO;
+	gfp_t flags = GFP_KERNEL|__GFP_ZERO;
 	struct page *p;
 	int i;
 
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index b2a2dff..e7437ec 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -204,7 +204,7 @@
 {
 	pte_t *pte;
 
-	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	return pte;
 }
 
@@ -212,7 +212,7 @@
 {
 	struct page *pte;
 
-	pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (!pte)
 		return NULL;
 	if (!pgtable_page_ctor(pte)) {
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
index 2e02d13..2677579 100644
--- a/arch/unicore32/include/asm/pgalloc.h
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -28,7 +28,7 @@
 #define pgd_alloc(mm)			get_pgd_slow(mm)
 #define pgd_free(mm, pgd)		free_pgd_slow(mm, pgd)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 /*
  * Allocate one PTE table.
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 33787ee..91eac39 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -263,7 +263,7 @@
 
 msr_fail:
 	pr_cont("Broken PMU hardware detected, using software events only.\n");
-	pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n",
+	printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n",
 		boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR,
 		reg, val_new);
 
@@ -2319,7 +2319,7 @@
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
-	const void __user *fp;
+	const unsigned long __user *fp;
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2332,7 +2332,7 @@
 	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
 		return;
 
-	fp = (void __user *)regs->bp;
+	fp = (unsigned long __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
 
@@ -2345,16 +2345,17 @@
 	pagefault_disable();
 	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
+
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 16))
+		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
 			break;
 
-		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
 		if (bytes != 0)
 			break;
-		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
+		bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
 		if (bytes != 0)
 			break;
 
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3660b2c..06c2baa 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -1,8 +1,8 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
-intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
+intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7c66695..9b4f9d3 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -115,6 +115,10 @@
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
 	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -139,6 +143,10 @@
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -182,6 +190,16 @@
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc6, 0xf),	/* FRONTEND_RETIRED.* */
+
 	EVENT_CONSTRAINT_END
 };
 
@@ -250,6 +268,10 @@
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -264,6 +286,13 @@
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4a41348..c64b1e9 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -301,10 +301,6 @@
 #define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
-
-
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
@@ -312,5 +308,7 @@
  */
 #define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
+#define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4421b5d..d1d1e50 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -38,12 +38,11 @@
 #define RELATIVECALL_OPCODE 0xe8
 #define RELATIVE_ADDR_SIZE 4
 #define MAX_STACK_SIZE 64
-#define MIN_STACK_SIZE(ADDR)					       \
-	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
-			      THREAD_SIZE - (unsigned long)(ADDR)))    \
-	 ? (MAX_STACK_SIZE)					       \
-	 : (((unsigned long)current_thread_info()) +		       \
-	    THREAD_SIZE - (unsigned long)(ADDR)))
+#define CUR_STACK_SIZE(ADDR) \
+	(current_top_of_stack() - (unsigned long)(ADDR))
+#define MIN_STACK_SIZE(ADDR)				\
+	(MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ?	\
+	 MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR))
 
 #define flush_insn_slot(p)	do { } while (0)
 
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index bf7f8b5..574c23c 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -81,7 +81,7 @@
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
 	struct page *page;
-	page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	page = alloc_pages(GFP_KERNEL |  __GFP_ZERO, 0);
 	if (!page)
 		return NULL;
 	if (!pgtable_pmd_page_ctor(page)) {
@@ -125,7 +125,7 @@
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+	return (pud_t *)get_zeroed_page(GFP_KERNEL);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index fdcc040..7c1c895 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -69,29 +69,22 @@
 }
 
 static __always_inline
-u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
-{
-	u64 delta = rdtsc_ordered() - src->tsc_timestamp;
-	return pvclock_scale_delta(delta, src->tsc_to_system_mul,
-				   src->tsc_shift);
-}
-
-static __always_inline
 unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 			       cycle_t *cycles, u8 *flags)
 {
 	unsigned version;
-	cycle_t ret, offset;
-	u8 ret_flags;
+	cycle_t offset;
+	u64 delta;
 
 	version = src->version;
+	/* Make the latest version visible */
+	smp_rmb();
 
-	offset = pvclock_get_nsec_offset(src);
-	ret = src->system_time + offset;
-	ret_flags = src->flags;
-
-	*cycles = ret;
-	*flags = ret_flags;
+	delta = rdtsc_ordered() - src->tsc_timestamp;
+	offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+				   src->tsc_shift);
+	*cycles = src->system_time + offset;
+	*flags = src->flags;
 	return version;
 }
 
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 7c247e7..0944218 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -14,7 +14,7 @@
 struct thread_info;
 struct stacktrace_ops;
 
-typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo,
+typedef unsigned long (*walk_stack_t)(struct task_struct *task,
 				      unsigned long *stack,
 				      unsigned long bp,
 				      const struct stacktrace_ops *ops,
@@ -23,13 +23,13 @@
 				      int *graph);
 
 extern unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
 		    unsigned long *stack, unsigned long bp,
 		    const struct stacktrace_ops *ops, void *data,
 		    unsigned long *end, int *graph);
 
 extern unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
 		       unsigned long *stack, unsigned long bp,
 		       const struct stacktrace_ops *ops, void *data,
 		       unsigned long *end, int *graph);
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index a147e67..e991d5c 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@
 	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
 		i++;
 
-	if (i == 0)
-		return 0;
+	if (!i)
+		return -ENODEV;
 
 	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
 	if (!nb)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2bb25c3f..ef8017c 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -42,16 +42,14 @@
 static void
 print_ftrace_graph_addr(unsigned long addr, void *data,
 			const struct stacktrace_ops *ops,
-			struct thread_info *tinfo, int *graph)
+			struct task_struct *task, int *graph)
 {
-	struct task_struct *task;
 	unsigned long ret_addr;
 	int index;
 
 	if (addr != (unsigned long)return_to_handler)
 		return;
 
-	task = tinfo->task;
 	index = task->curr_ret_stack;
 
 	if (!task->ret_stack || index < *graph)
@@ -68,7 +66,7 @@
 static inline void
 print_ftrace_graph_addr(unsigned long addr, void *data,
 			const struct stacktrace_ops *ops,
-			struct thread_info *tinfo, int *graph)
+			struct task_struct *task, int *graph)
 { }
 #endif
 
@@ -79,10 +77,10 @@
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-static inline int valid_stack_ptr(struct thread_info *tinfo,
+static inline int valid_stack_ptr(struct task_struct *task,
 			void *p, unsigned int size, void *end)
 {
-	void *t = tinfo;
+	void *t = task_stack_page(task);
 	if (end) {
 		if (p < end && p >= (end-THREAD_SIZE))
 			return 1;
@@ -93,14 +91,14 @@
 }
 
 unsigned long
-print_context_stack(struct thread_info *tinfo,
+print_context_stack(struct task_struct *task,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data,
 		unsigned long *end, int *graph)
 {
 	struct stack_frame *frame = (struct stack_frame *)bp;
 
-	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+	while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
 		unsigned long addr;
 
 		addr = *stack;
@@ -112,7 +110,7 @@
 			} else {
 				ops->address(data, addr, 0);
 			}
-			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+			print_ftrace_graph_addr(addr, data, ops, task, graph);
 		}
 		stack++;
 	}
@@ -121,7 +119,7 @@
 EXPORT_SYMBOL_GPL(print_context_stack);
 
 unsigned long
-print_context_stack_bp(struct thread_info *tinfo,
+print_context_stack_bp(struct task_struct *task,
 		       unsigned long *stack, unsigned long bp,
 		       const struct stacktrace_ops *ops, void *data,
 		       unsigned long *end, int *graph)
@@ -129,7 +127,7 @@
 	struct stack_frame *frame = (struct stack_frame *)bp;
 	unsigned long *ret_addr = &frame->return_address;
 
-	while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
+	while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) {
 		unsigned long addr = *ret_addr;
 
 		if (!__kernel_text_address(addr))
@@ -139,7 +137,7 @@
 			break;
 		frame = frame->next_frame;
 		ret_addr = &frame->return_address;
-		print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
+		print_ftrace_graph_addr(addr, data, ops, task, graph);
 	}
 
 	return (unsigned long)frame;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 464ffd6..fef917e 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -61,15 +61,13 @@
 		bp = stack_frame(task, regs);
 
 	for (;;) {
-		struct thread_info *context;
 		void *end_stack;
 
 		end_stack = is_hardirq_stack(stack, cpu);
 		if (!end_stack)
 			end_stack = is_softirq_stack(stack, cpu);
 
-		context = task_thread_info(task);
-		bp = ops->walk_stack(context, stack, bp, ops, data,
+		bp = ops->walk_stack(task, stack, bp, ops, data,
 				     end_stack, &graph);
 
 		/* Stop if not on irq stack */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5f1c626..d558a8a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -153,7 +153,6 @@
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
-	struct thread_info *tinfo;
 	unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
 	unsigned long dummy;
 	unsigned used = 0;
@@ -179,7 +178,6 @@
 	 * current stack address. If the stacks consist of nested
 	 * exceptions
 	 */
-	tinfo = task_thread_info(task);
 	while (!done) {
 		unsigned long *stack_end;
 		enum stack_type stype;
@@ -202,7 +200,7 @@
 			if (ops->stack(data, id) < 0)
 				break;
 
-			bp = ops->walk_stack(tinfo, stack, bp, ops,
+			bp = ops->walk_stack(task, stack, bp, ops,
 					     data, stack_end, &graph);
 			ops->stack(data, "<EOE>");
 			/*
@@ -218,7 +216,7 @@
 
 			if (ops->stack(data, "IRQ") < 0)
 				break;
-			bp = ops->walk_stack(tinfo, stack, bp,
+			bp = ops->walk_stack(task, stack, bp,
 				     ops, data, stack_end, &graph);
 			/*
 			 * We link to the next stack (which would be
@@ -240,7 +238,7 @@
 	/*
 	 * This handles the process stack:
 	 */
-	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+	bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
 	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bca14c8..57b7137 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -11,7 +11,11 @@
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/pci_ids.h>
+#include <linux/bcma/bcma.h>
+#include <linux/bcma/bcma_regs.h>
 #include <drm/i915_drm.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
@@ -21,6 +25,9 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/irq_remapping.h>
+#include <asm/early_ioremap.h>
+
+#define dev_err(msg)  pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -76,6 +83,13 @@
 #ifdef CONFIG_ACPI
 #ifdef CONFIG_X86_IO_APIC
 	/*
+	 * Only applies to Nvidia root ports (bus 0) and not to
+	 * Nvidia graphics cards with PCI ports on secondary buses.
+	 */
+	if (num)
+		return;
+
+	/*
 	 * All timer overrides on Nvidia are
 	 * wrong unless HPET is enabled.
 	 * Unfortunately that's not true on many Asus boards.
@@ -590,6 +604,61 @@
 #endif
 }
 
+#define BCM4331_MMIO_SIZE	16384
+#define BCM4331_PM_CAP		0x40
+#define bcma_aread32(reg)	ioread32(mmio + 1 * BCMA_CORE_SIZE + reg)
+#define bcma_awrite32(reg, val)	iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg)
+
+static void __init apple_airport_reset(int bus, int slot, int func)
+{
+	void __iomem *mmio;
+	u16 pmcsr;
+	u64 addr;
+	int i;
+
+	if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc."))
+		return;
+
+	/* Card may have been put into PCI_D3hot by grub quirk */
+	pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+
+	if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+		pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
+		write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr);
+		mdelay(10);
+
+		pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
+		if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
+			dev_err("Cannot power up Apple AirPort card\n");
+			return;
+		}
+	}
+
+	addr  =      read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
+	addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32;
+	addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+	mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
+	if (!mmio) {
+		dev_err("Cannot iomap Apple AirPort card\n");
+		return;
+	}
+
+	pr_info("Resetting Apple AirPort card (left enabled by EFI)\n");
+
+	for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++)
+		udelay(10);
+
+	bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET);
+	bcma_aread32(BCMA_RESET_CTL);
+	udelay(1);
+
+	bcma_awrite32(BCMA_RESET_CTL, 0);
+	bcma_aread32(BCMA_RESET_CTL);
+	udelay(10);
+
+	early_iounmap(mmio, BCM4331_MMIO_SIZE);
+}
 
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
@@ -603,12 +672,6 @@
 	void (*f)(int num, int slot, int func);
 };
 
-/*
- * Only works for devices on the root bus. If you add any devices
- * not on bus 0 readd another loop level in early_quirks(). But
- * be careful because at least the Nvidia quirk here relies on
- * only matching on bus 0.
- */
 static struct chipset early_qrk[] __initdata = {
 	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs },
@@ -638,9 +701,13 @@
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
+	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
+	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}
 };
 
+static void __init early_pci_scan_bus(int bus);
+
 /**
  * check_dev_quirk - apply early quirks to a given PCI device
  * @num: bus number
@@ -649,7 +716,7 @@
  *
  * Check the vendor & device ID against the early quirks table.
  *
- * If the device is single function, let early_quirks() know so we don't
+ * If the device is single function, let early_pci_scan_bus() know so we don't
  * poke at this device again.
  */
 static int __init check_dev_quirk(int num, int slot, int func)
@@ -658,6 +725,7 @@
 	u16 vendor;
 	u16 device;
 	u8 type;
+	u8 sec;
 	int i;
 
 	class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE);
@@ -685,25 +753,36 @@
 
 	type = read_pci_config_byte(num, slot, func,
 				    PCI_HEADER_TYPE);
+
+	if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) {
+		sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS);
+		if (sec > num)
+			early_pci_scan_bus(sec);
+	}
+
 	if (!(type & 0x80))
 		return -1;
 
 	return 0;
 }
 
-void __init early_quirks(void)
+static void __init early_pci_scan_bus(int bus)
 {
 	int slot, func;
 
-	if (!early_pci_allowed())
-		return;
-
 	/* Poor man's PCI discovery */
-	/* Only scan the root bus */
 	for (slot = 0; slot < 32; slot++)
 		for (func = 0; func < 8; func++) {
 			/* Only probe function 0 on single fn devices */
-			if (check_dev_quirk(0, slot, func))
+			if (check_dev_quirk(bus, slot, func))
 				break;
 		}
 }
+
+void __init early_quirks(void)
+{
+	if (!early_pci_allowed())
+		return;
+
+	early_pci_scan_bus(0);
+}
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 4d38416..04f89ca 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -57,7 +57,7 @@
 # error "Need more than one PGD for the ESPFIX hack"
 #endif
 
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 /* This contains the *bottom* address of the espfix stack */
 DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f2..c627bf8 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -130,11 +130,9 @@
 
 void do_softirq_own_stack(void)
 {
-	struct thread_info *curstk;
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	curstk = current_stack();
 	irqstk = __this_cpu_read(softirq_stack);
 
 	/* build the stack frame on the softirq stack */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 38cf7a7..7847e5c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -961,7 +961,19 @@
 		 * normal page fault.
 		 */
 		regs->ip = (unsigned long)cur->addr;
+		/*
+		 * Trap flag (TF) has been set here because this fault
+		 * happened where the single stepping will be done.
+		 * So clear it by resetting the current kprobe:
+		 */
+		regs->flags &= ~X86_EFLAGS_TF;
+
+		/*
+		 * If the TF flag was set before the kprobe hit,
+		 * don't touch it:
+		 */
 		regs->flags |= kcb->kprobe_old_flags;
+
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
 		else
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 99bfc02..06c58ce 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -61,11 +61,16 @@
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 {
 	unsigned version;
-	cycle_t ret;
 	u8 flags;
 
 	do {
-		version = __pvclock_read_cycles(src, &ret, &flags);
+		version = src->version;
+		/* Make the latest version visible */
+		smp_rmb();
+
+		flags = src->flags;
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
 	} while ((src->version & 1) || version != src->version);
 
 	return flags & valid_flags;
@@ -80,6 +85,8 @@
 
 	do {
 		version = __pvclock_read_cycles(src, &ret, &flags);
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
 	} while ((src->version & 1) || version != src->version);
 
 	if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bbb5b28..a397200 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1310,7 +1310,8 @@
 
 	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
 	if (guest_tsc < tsc_deadline)
-		__delay(tsc_deadline - guest_tsc);
+		__delay(min(tsc_deadline - guest_tsc,
+			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 003618e..64a79f2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6671,7 +6671,13 @@
 
 	/* Checks for #GP/#SS exceptions. */
 	exn = false;
-	if (is_protmode(vcpu)) {
+	if (is_long_mode(vcpu)) {
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is the only check on the memory
+		 * destination for long mode!
+		 */
+		exn = is_noncanonical_address(*ret);
+	} else if (is_protmode(vcpu)) {
 		/* Protected mode: apply checks for segment validity in the
 		 * following order:
 		 * - segment type check (#GP(0) may be thrown)
@@ -6688,17 +6694,10 @@
 			 * execute-only code segment
 			 */
 			exn = ((s.type & 0xa) == 8);
-	}
-	if (exn) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-		return 1;
-	}
-	if (is_long_mode(vcpu)) {
-		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
-		 * non-canonical form. This is an only check for long mode.
-		 */
-		exn = is_noncanonical_address(*ret);
-	} else if (is_protmode(vcpu)) {
+		if (exn) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+			return 1;
+		}
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 902d9da..7da5dd2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1244,12 +1244,6 @@
 static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
 static unsigned long max_tsc_khz;
 
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
-{
-	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
-				   vcpu->arch.virtual_tsc_shift);
-}
-
 static u32 adjust_tsc_khz(u32 khz, s32 ppm)
 {
 	u64 v = (u64)khz * (1000000 + ppm);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7ce3634..a82ca46 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -2,6 +2,7 @@
 #define ARCH_X86_KVM_X86_H
 
 #include <linux/kvm_host.h>
+#include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
@@ -195,6 +196,12 @@
 
 extern struct static_key kvm_no_apic_vcpu;
 
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
+{
+	return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
+				   vcpu->arch.virtual_tsc_shift);
+}
+
 /* Same "calling convention" as do_div:
  * - divide (n << 32) by base
  * - put result in n
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 1b1110f..0493c17 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -54,8 +54,8 @@
 			     void *data)
 {
 	if (val == DIE_GPF) {
-		pr_emerg("CONFIG_KASAN_INLINE enabled");
-		pr_emerg("GPF could be caused by NULL-ptr deref or user memory access");
+		pr_emerg("CONFIG_KASAN_INLINE enabled\n");
+		pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n");
 	}
 	return NOTIFY_OK;
 }
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e..aa0ff4b 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
 #include <asm/fixmap.h>
 #include <asm/mtrr.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
 
 #ifdef CONFIG_HIGHPTE
 #define PGALLOC_USER_GFP __GFP_HIGHMEM
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index b2a4e2a..3cd6983 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -396,6 +396,7 @@
 		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
+	acpi_irq_penalty_init();
 	pcibios_enable_irq = acpi_pci_irq_enable;
 	pcibios_disable_irq = acpi_pci_irq_disable;
 	x86_init.pci.init_irq = x86_init_noop;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6e7242b..b226b3f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -139,7 +139,7 @@
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
 
-	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
+	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
 	efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
 	if (!efi_pgd)
 		return -ENOMEM;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 009947d..f2b5e6a 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 #include <asm/sections.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
@@ -28,6 +29,7 @@
  * kernel's text (this value is passed in the image header).
  */
 unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
@@ -37,7 +39,43 @@
 
 pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code __visible;
+unsigned long relocated_restore_code __visible;
+
+static int set_up_temporary_text_mapping(void)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+
+	/*
+	 * The new mapping only has to cover the page containing the image
+	 * kernel's entry point (jump_address_phys), because the switch over to
+	 * it is carried out by relocated code running from a page allocated
+	 * specifically for this purpose and covered by the identity mapping, so
+	 * the temporary kernel text mapping is only needed for the final jump.
+	 * Moreover, in that mapping the virtual address of the image kernel's
+	 * entry point must be the same as its virtual address in the image
+	 * kernel (restore_jump_address), so the image kernel's
+	 * restore_registers() code doesn't find itself in a different area of
+	 * the virtual address space after switching over to the original page
+	 * tables used by the image kernel.
+	 */
+	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+	if (!pud)
+		return -ENOMEM;
+
+	pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd)
+		return -ENOMEM;
+
+	set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
+	set_pud(pud + pud_index(restore_jump_address),
+		__pud(__pa(pmd) | _KERNPG_TABLE));
+	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+		__pgd(__pa(pud) | _KERNPG_TABLE));
+
+	return 0;
+}
 
 static void *alloc_pgt_page(void *context)
 {
@@ -59,9 +97,10 @@
 	if (!temp_level4_pgt)
 		return -ENOMEM;
 
-	/* It is safe to reuse the original kernel mapping */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+	/* Prepare a temporary mapping for the kernel text */
+	result = set_up_temporary_text_mapping();
+	if (result)
+		return result;
 
 	/* Set up the direct mapping from scratch */
 	for (i = 0; i < nr_pfn_mapped; i++) {
@@ -78,19 +117,50 @@
 	return 0;
 }
 
+static int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
+	pud = pud_offset(pgd, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+	} else {
+		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
+
+		if (pmd_large(*pmd)) {
+			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		} else {
+			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
+
+			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+		}
+	}
+	__flush_tlb_all();
+
+	return 0;
+}
+
 int swsusp_arch_resume(void)
 {
 	int error;
 
 	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
+	error = set_up_temporary_mappings();
+	if (error)
 		return error;
 
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
+	error = relocate_restore_code();
+	if (error)
+		return error;
 
 	restore_image();
 	return 0;
@@ -109,11 +179,12 @@
 
 struct restore_data_record {
 	unsigned long jump_address;
+	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
 };
 
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+#define RESTORE_MAGIC	0x123456789ABCDEF0UL
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -126,7 +197,8 @@
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
+	rdr->jump_address = (unsigned long)&restore_registers;
+	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
 	return 0;
@@ -142,6 +214,7 @@
 	struct restore_data_record *rdr = addr;
 
 	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
 	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
 }
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 4400a43..3177c2b 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -44,9 +44,6 @@
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	/* save the address of restore_registers */
-	movq	$restore_registers, %rax
-	movq	%rax, restore_jump_address(%rip)
 	/* save cr3 */
 	movq	%cr3, %rax
 	movq	%rax, restore_cr3(%rip)
@@ -57,31 +54,34 @@
 ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
-	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rdx
-	movq	temp_level4_pgt(%rip), %rax
-	subq	%rdx, %rax
-	movq	%rax, %cr3
-	/* Flush TLB */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3;
-	movq	%rax, %cr4;  # turn PGE back on
-
 	/* prepare to jump to the image kernel */
-	movq	restore_jump_address(%rip), %rax
-	movq	restore_cr3(%rip), %rbx
+	movq	restore_jump_address(%rip), %r8
+	movq	restore_cr3(%rip), %r9
+
+	/* prepare to switch to temporary page tables */
+	movq	temp_level4_pgt(%rip), %rax
+	movq	mmu_cr4_features(%rip), %rbx
 
 	/* prepare to copy image data to their original locations */
 	movq	restore_pblist(%rip), %rdx
+
+	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
 	jmpq	*%rcx
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
+	/* switch to temporary page tables */
+	movq	$__PAGE_OFFSET, %rcx
+	subq	%rcx, %rax
+	movq	%rax, %cr3
+	/* flush TLB */
+	movq	%rbx, %rcx
+	andq	$~(X86_CR4_PGE), %rcx
+	movq	%rcx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3;
+	movq	%rbx, %cr4;  # turn PGE back on
 .Lloop:
 	testq	%rdx, %rdx
 	jz	.Ldone
@@ -96,24 +96,17 @@
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
 	jmp	.Lloop
+
 .Ldone:
 	/* jump to the restore_registers address from the image header */
-	jmpq	*%rax
-	/*
-	 * NOTE: This assumes that the boot kernel's text mapping covers the
-	 * image kernel's page containing restore_registers and the address of
-	 * this page is the same as in the image kernel's text mapping (it
-	 * should always be true, because the text mapping is linear, starting
-	 * from 0, and is supposed to cover the entire kernel text for every
-	 * kernel).
-	 *
-	 * code below belongs to the image kernel
-	 */
+	jmpq	*%r8
 
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
 ENTRY(restore_registers)
 	FRAME_BEGIN
 	/* go back to the original page tables */
-	movq    %rbx, %cr3
+	movq    %r9, %cr3
 
 	/* Flush TLB, including "global" things (vmalloc) */
 	movq	mmu_cr4_features(%rip), %rax
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 478a2de..6743371 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1113,7 +1113,7 @@
 
 	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
 	 * We include the PMD passed in on _both_ boundaries. */
-	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
 			pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
@@ -1551,41 +1551,6 @@
 #endif
 }
 
-#ifdef CONFIG_X86_32
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
-	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
-		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
-			       pte_val_ma(pte));
-
-	return pte;
-}
-#else /* CONFIG_X86_64 */
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-	unsigned long pfn;
-
-	if (xen_feature(XENFEAT_writable_page_tables) ||
-	    xen_feature(XENFEAT_auto_translated_physmap) ||
-	    xen_start_info->mfn_list >= __START_KERNEL_map)
-		return pte;
-
-	/*
-	 * Pages belonging to the initial p2m list mapped outside the default
-	 * address range must be mapped read-only. This region contains the
-	 * page tables for mapping the p2m list, too, and page tables MUST be
-	 * mapped read-only.
-	 */
-	pfn = pte_pfn(pte);
-	if (pfn >= xen_start_info->first_p2m_pfn &&
-	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
-		pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
-
-	return pte;
-}
-#endif /* CONFIG_X86_64 */
-
 /*
  * Init-time set_pte while constructing initial pagetables, which
  * doesn't allow RO page table pages to be remapped RW.
@@ -1600,13 +1565,37 @@
  * so always write the PTE directly and rely on Xen trapping and
  * emulating any updates as necessary.
  */
+__visible pte_t xen_make_pte_init(pteval_t pte)
+{
+#ifdef CONFIG_X86_64
+	unsigned long pfn;
+
+	/*
+	 * Pages belonging to the initial p2m list mapped outside the default
+	 * address range must be mapped read-only. This region contains the
+	 * page tables for mapping the p2m list, too, and page tables MUST be
+	 * mapped read-only.
+	 */
+	pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+	if (xen_start_info->mfn_list < __START_KERNEL_map &&
+	    pfn >= xen_start_info->first_p2m_pfn &&
+	    pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
+		pte &= ~_PAGE_RW;
+#endif
+	pte = pte_pfn_to_mfn(pte);
+	return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
+
 static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
-	if (pte_mfn(pte) != INVALID_P2M_ENTRY)
-		pte = mask_rw_pte(ptep, pte);
-	else
-		pte = __pte_ma(0);
-
+#ifdef CONFIG_X86_32
+	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
+	if (pte_mfn(pte) != INVALID_P2M_ENTRY
+	    && pte_val_ma(*ptep) & _PAGE_PRESENT)
+		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
+			       pte_val_ma(pte));
+#endif
 	native_set_pte(ptep, pte);
 }
 
@@ -2407,6 +2396,7 @@
 	pv_mmu_ops.alloc_pud = xen_alloc_pud;
 	pv_mmu_ops.release_pud = xen_release_pud;
 #endif
+	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
 
 #ifdef CONFIG_X86_64
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
@@ -2455,7 +2445,7 @@
 	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
 	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
 
-	.make_pte = PV_CALLEE_SAVE(xen_make_pte),
+	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
 	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
 
 #ifdef CONFIG_X86_PAE
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index cab9f76..dd2a49a 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -182,7 +182,7 @@
 	if (unlikely(!slab_is_available()))
 		return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE);
 
-	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
+	return (void *)__get_free_page(GFP_KERNEL);
 }
 
 static void __ref free_p2m_page(void *p)
diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index d38eb92..1065bc8 100644
--- a/arch/xtensa/include/asm/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
@@ -44,7 +44,7 @@
 	pte_t *ptep;
 	int i;
 
-	ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	ptep = (pte_t *)__get_free_page(GFP_KERNEL);
 	if (!ptep)
 		return NULL;
 	for (i = 0; i < 1024; i++)
diff --git a/block/ioprio.c b/block/ioprio.c
index cc7800e..01b8116 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -150,8 +150,10 @@
 	if (ret)
 		goto out;
 	ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
+	task_lock(p);
 	if (p->io_context)
 		ret = p->io_context->ioprio;
+	task_unlock(p);
 out:
 	return ret;
 }
diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c
index 6a76d5c..9492e1c 100644
--- a/crypto/asymmetric_keys/mscode_parser.c
+++ b/crypto/asymmetric_keys/mscode_parser.c
@@ -124,5 +124,10 @@
 	struct pefile_context *ctx = context;
 
 	ctx->digest = kmemdup(value, vlen, GFP_KERNEL);
-	return ctx->digest ? 0 : -ENOMEM;
+	if (!ctx->digest)
+		return -ENOMEM;
+
+	ctx->digest_len = vlen;
+
+	return 0;
 }
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index 44b746e..2ffd697 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -227,7 +227,7 @@
 				if (asymmetric_key_id_same(p->id, auth))
 					goto found_issuer_check_skid;
 			}
-		} else {
+		} else if (sig->auth_ids[1]) {
 			auth = sig->auth_ids[1];
 			pr_debug("- want %*phN\n", auth->len, auth->data);
 			for (p = pkcs7->certs; p; p = p->next) {
diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c
index ac4bddf..19d1afb9 100644
--- a/crypto/asymmetric_keys/restrict.c
+++ b/crypto/asymmetric_keys/restrict.c
@@ -87,7 +87,7 @@
 
 	sig = payload->data[asym_auth];
 	if (!sig->auth_ids[0] && !sig->auth_ids[1])
-		return 0;
+		return -ENOKEY;
 
 	if (ca_keyid && !asymmetric_key_id_partial(sig->auth_ids[1], ca_keyid))
 		return -EPERM;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 43fe85f2..7097a33 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -455,6 +455,7 @@
 	[CRYPTO_MSG_NEWALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_UPDATEALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
+	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = 0,
 };
 
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index ead8dc0..8ba4266 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -102,10 +102,10 @@
 };
 
 struct pkcs1pad_request {
-	struct akcipher_request child_req;
-
 	struct scatterlist in_sg[3], out_sg[2];
 	uint8_t *in_buf, *out_buf;
+
+	struct akcipher_request child_req;
 };
 
 static int pkcs1pad_set_pub_key(struct crypto_akcipher *tfm, const void *key,
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index 1f41284..dee8692 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -602,7 +602,7 @@
 	crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1);
 	ret = n;
 out:
-	acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret);
+	acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, ret >= 0);
 	return ret;
 }
 
@@ -672,7 +672,7 @@
 	crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1);
 	ret = n;
 out:
-	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret);
+	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0);
 	return n;
 }
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 73c76d6..290d6f5 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1331,8 +1331,6 @@
 
 static void ec_remove_handlers(struct acpi_ec *ec)
 {
-	acpi_ec_stop(ec, false);
-
 	if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) {
 		if (ACPI_FAILURE(acpi_remove_address_space_handler(ec->handle,
 					ACPI_ADR_SPACE_EC, &acpi_ec_space_handler)))
@@ -1340,6 +1338,19 @@
 		clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags);
 	}
 
+	/*
+	 * Stops handling the EC transactions after removing the operation
+	 * region handler. This is required because _REG(DISCONNECT)
+	 * invoked during the removal can result in new EC transactions.
+	 *
+	 * Flushes the EC requests and thus disables the GPE before
+	 * removing the GPE handler. This is required by the current ACPICA
+	 * GPE core. ACPICA GPE core will automatically disable a GPE when
+	 * it is indicated but there is no way to handle it. So the drivers
+	 * must disable the GPEs prior to removing the GPE handlers.
+	 */
+	acpi_ec_stop(ec, false);
+
 	if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags)) {
 		if (ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe,
 					&acpi_ec_gpe_handler)))
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 2215fc8..1f0e060 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -928,7 +928,7 @@
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->code));
+	return sprintf(buf, "0x%04x\n", le16_to_cpu(dcr->code));
 }
 static DEVICE_ATTR_RO(format);
 
@@ -961,8 +961,8 @@
 				continue;
 			if (nfit_dcr->dcr->code == dcr->code)
 				continue;
-			rc = sprintf(buf, "%#x\n",
-					be16_to_cpu(nfit_dcr->dcr->code));
+			rc = sprintf(buf, "0x%04x\n",
+					le16_to_cpu(nfit_dcr->dcr->code));
 			break;
 		}
 		if (rc != ENXIO)
@@ -1151,9 +1151,10 @@
 		if (disable_vendor_specific)
 			dsm_mask &= ~(1 << 8);
 	} else {
-		dev_err(dev, "unknown dimm command family\n");
+		dev_dbg(dev, "unknown dimm command family\n");
 		nfit_mem->family = -1;
-		return force_enable_dimms ? 0 : -ENODEV;
+		/* DSMs are optional, continue loading the driver... */
+		return 0;
 	}
 
 	uuid = to_nfit_uuid(nfit_mem->family);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 11cb383..02b9ea1 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -53,12 +53,12 @@
 };
 
 /*
- * Region format interface codes are stored as an array of bytes in the
- * NFIT DIMM Control Region structure
+ * Region format interface codes are stored with the interface as the
+ * LSB and the function as the MSB.
  */
-#define NFIT_FIC_BYTE cpu_to_be16(0x101) /* byte-addressable energy backed */
-#define NFIT_FIC_BLK cpu_to_be16(0x201) /* block-addressable non-energy backed */
-#define NFIT_FIC_BYTEN cpu_to_be16(0x301) /* byte-addressable non-energy backed */
+#define NFIT_FIC_BYTE cpu_to_le16(0x101) /* byte-addressable energy backed */
+#define NFIT_FIC_BLK cpu_to_le16(0x201) /* block-addressable non-energy backed */
+#define NFIT_FIC_BYTEN cpu_to_le16(0x301) /* byte-addressable non-energy backed */
 
 enum {
 	NFIT_BLK_READ_FLUSH = 1,
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 8fc7323..c983bf7 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -470,6 +470,7 @@
 {
 	struct acpi_pci_link *link;
 	int penalty = 0;
+	int i;
 
 	list_for_each_entry(link, &acpi_link_list, list) {
 		/*
@@ -478,18 +479,14 @@
 		 */
 		if (link->irq.active && link->irq.active == irq)
 			penalty += PIRQ_PENALTY_PCI_USING;
-		else {
-			int i;
 
-			/*
-			 * If a link is inactive, penalize the IRQs it
-			 * might use, but not as severely.
-			 */
-			for (i = 0; i < link->irq.possible_count; i++)
-				if (link->irq.possible[i] == irq)
-					penalty += PIRQ_PENALTY_PCI_POSSIBLE /
-						link->irq.possible_count;
-		}
+		/*
+		 * penalize the IRQs PCI might use, but not as severely.
+		 */
+		for (i = 0; i < link->irq.possible_count; i++)
+			if (link->irq.possible[i] == irq)
+				penalty += PIRQ_PENALTY_PCI_POSSIBLE /
+					link->irq.possible_count;
 	}
 
 	return penalty;
@@ -499,9 +496,6 @@
 {
 	int penalty = 0;
 
-	if (irq < ACPI_MAX_ISA_IRQS)
-		penalty += acpi_isa_irq_penalty[irq];
-
 	/*
 	* Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict
 	* with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be
@@ -516,10 +510,49 @@
 			penalty += PIRQ_PENALTY_PCI_USING;
 	}
 
+	if (irq < ACPI_MAX_ISA_IRQS)
+		return penalty + acpi_isa_irq_penalty[irq];
+
 	penalty += acpi_irq_pci_sharing_penalty(irq);
 	return penalty;
 }
 
+int __init acpi_irq_penalty_init(void)
+{
+	struct acpi_pci_link *link;
+	int i;
+
+	/*
+	 * Update penalties to facilitate IRQ balancing.
+	 */
+	list_for_each_entry(link, &acpi_link_list, list) {
+
+		/*
+		 * reflect the possible and active irqs in the penalty table --
+		 * useful for breaking ties.
+		 */
+		if (link->irq.possible_count) {
+			int penalty =
+			    PIRQ_PENALTY_PCI_POSSIBLE /
+			    link->irq.possible_count;
+
+			for (i = 0; i < link->irq.possible_count; i++) {
+				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS)
+					acpi_isa_irq_penalty[link->irq.
+							 possible[i]] +=
+					    penalty;
+			}
+
+		} else if (link->irq.active &&
+				(link->irq.active < ACPI_MAX_ISA_IRQS)) {
+			acpi_isa_irq_penalty[link->irq.active] +=
+			    PIRQ_PENALTY_PCI_POSSIBLE;
+		}
+	}
+
+	return 0;
+}
+
 static int acpi_irq_balance = -1;	/* 0: static, 1: balance */
 
 static int acpi_pci_link_allocate(struct acpi_pci_link *link)
@@ -839,7 +872,7 @@
 {
 	if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty)))
 		acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) +
-			active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING;
+		  (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
 }
 
 bool acpi_isa_irq_available(int irq)
diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c
index 6e702ab..1d31c0c 100644
--- a/drivers/ata/ahci_seattle.c
+++ b/drivers/ata/ahci_seattle.c
@@ -137,7 +137,7 @@
 	u32 val;
 
 	plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL);
-	if (IS_ERR(plat_data))
+	if (!plat_data)
 		return &ahci_port_info;
 
 	plat_data->sgpio_ctrl = devm_ioremap_resource(dev,
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6be7770..31c183a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4314,6 +4314,12 @@
 	 */
 	{ "ST380013AS",		"3.20",		ATA_HORKAGE_MAX_SEC_1024 },
 
+	/*
+	 * Device times out with higher max sects.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
+	 */
+	{ "LITEON CX1-JB256-HP", NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+
 	/* Devices we expect to fail diagnostics */
 
 	/* Devices where NCQ should be avoided */
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 61dc7a9..c6f0174 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -606,7 +606,7 @@
 	ata_scsi_port_error_handler(host, ap);
 
 	/* finish or retry handled scmd's and clean up */
-	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+	WARN_ON(!list_empty(&eh_work_q));
 
 	DPRINTK("EXIT\n");
 }
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index bd74ee5..745489a 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -986,7 +986,7 @@
 		 * Looks like a lot of fuss, but it avoids an unnecessary
 		 * +1 usec read-after-write delay for unaffected registers.
 		 */
-		laddr = (long)addr & 0xffff;
+		laddr = (unsigned long)addr & 0xffff;
 		if (laddr >= 0x300 && laddr <= 0x33c) {
 			laddr &= 0x000f;
 			if (laddr == 0x4 || laddr == 0xc) {
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index eda0909..f642c42 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -8,8 +8,6 @@
 #include <linux/bcma/bcma.h>
 #include <linux/delay.h>
 
-#define BCMA_CORE_SIZE		0x1000
-
 #define bcma_err(bus, fmt, ...) \
 	pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__)
 #define bcma_warn(bus, fmt, ...) \
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index d597e43..ab19adb 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1750,7 +1750,7 @@
 	int ret;
 
 	/* get_zeroed_page returns page with ref count 1 */
-	p = (void *) get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+	p = (void *) get_zeroed_page(GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 	empty_page = virt_to_page(p);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2e6d1e9..fcc5b4e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -207,6 +207,9 @@
 	struct blk_mq_tag_set tag_set;
 	struct blkfront_ring_info *rinfo;
 	unsigned int nr_rings;
+	/* Save uncomplete reqs and bios for migration. */
+	struct list_head requests;
+	struct bio_list bio_list;
 };
 
 static unsigned int nr_minors;
@@ -2002,69 +2005,22 @@
 {
 	unsigned int i, r_index;
 	struct request *req, *n;
-	struct blk_shadow *copy;
 	int rc;
 	struct bio *bio, *cloned_bio;
-	struct bio_list bio_list, merge_bio;
 	unsigned int segs, offset;
 	int pending, size;
 	struct split_bio *split_bio;
-	struct list_head requests;
 
 	blkfront_gather_backend_features(info);
 	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
 	blk_queue_max_segments(info->rq, segs);
-	bio_list_init(&bio_list);
-	INIT_LIST_HEAD(&requests);
 
 	for (r_index = 0; r_index < info->nr_rings; r_index++) {
-		struct blkfront_ring_info *rinfo;
-
-		rinfo = &info->rinfo[r_index];
-		/* Stage 1: Make a safe copy of the shadow state. */
-		copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow),
-			       GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
-		if (!copy)
-			return -ENOMEM;
-
-		/* Stage 2: Set up free list. */
-		memset(&rinfo->shadow, 0, sizeof(rinfo->shadow));
-		for (i = 0; i < BLK_RING_SIZE(info); i++)
-			rinfo->shadow[i].req.u.rw.id = i+1;
-		rinfo->shadow_free = rinfo->ring.req_prod_pvt;
-		rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
+		struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
 
 		rc = blkfront_setup_indirect(rinfo);
-		if (rc) {
-			kfree(copy);
+		if (rc)
 			return rc;
-		}
-
-		for (i = 0; i < BLK_RING_SIZE(info); i++) {
-			/* Not in use? */
-			if (!copy[i].request)
-				continue;
-
-			/*
-			 * Get the bios in the request so we can re-queue them.
-			 */
-			if (copy[i].request->cmd_flags &
-			    (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
-				/*
-				 * Flush operations don't contain bios, so
-				 * we need to requeue the whole request
-				 */
-				list_add(&copy[i].request->queuelist, &requests);
-				continue;
-			}
-			merge_bio.head = copy[i].request->bio;
-			merge_bio.tail = copy[i].request->biotail;
-			bio_list_merge(&bio_list, &merge_bio);
-			copy[i].request->bio = NULL;
-			blk_end_request_all(copy[i].request, 0);
-		}
-
-		kfree(copy);
 	}
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
 
@@ -2079,7 +2035,7 @@
 		kick_pending_request_queues(rinfo);
 	}
 
-	list_for_each_entry_safe(req, n, &requests, queuelist) {
+	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
 		BUG_ON(req->nr_phys_segments > segs);
@@ -2087,7 +2043,7 @@
 	}
 	blk_mq_kick_requeue_list(info->rq);
 
-	while ((bio = bio_list_pop(&bio_list)) != NULL) {
+	while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
 		/* Traverse the list of pending bios and re-queue them */
 		if (bio_segments(bio) > segs) {
 			/*
@@ -2133,9 +2089,42 @@
 {
 	struct blkfront_info *info = dev_get_drvdata(&dev->dev);
 	int err = 0;
+	unsigned int i, j;
 
 	dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
 
+	bio_list_init(&info->bio_list);
+	INIT_LIST_HEAD(&info->requests);
+	for (i = 0; i < info->nr_rings; i++) {
+		struct blkfront_ring_info *rinfo = &info->rinfo[i];
+		struct bio_list merge_bio;
+		struct blk_shadow *shadow = rinfo->shadow;
+
+		for (j = 0; j < BLK_RING_SIZE(info); j++) {
+			/* Not in use? */
+			if (!shadow[j].request)
+				continue;
+
+			/*
+			 * Get the bios in the request so we can re-queue them.
+			 */
+			if (shadow[j].request->cmd_flags &
+					(REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+				/*
+				 * Flush operations don't contain bios, so
+				 * we need to requeue the whole request
+				 */
+				list_add(&shadow[j].request->queuelist, &info->requests);
+				continue;
+			}
+			merge_bio.head = shadow[j].request->bio;
+			merge_bio.tail = shadow[j].request->biotail;
+			bio_list_merge(&info->bio_list, &merge_bio);
+			shadow[j].request->bio = NULL;
+			blk_mq_end_request(shadow[j].request, 0);
+		}
+	}
+
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
 	err = negotiate_mq(info);
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 10f846c..25d5906 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -99,7 +99,7 @@
 	struct clk_programmable *prog = to_clk_programmable(hw);
 	const struct clk_programmable_layout *layout = prog->layout;
 	unsigned int mask = layout->css_mask;
-	unsigned int pckr = 0;
+	unsigned int pckr = index;
 
 	if (layout->have_slck_mck)
 		mask |= AT91_PMC_CSSMCK_MCK;
diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c
index efba7d4..79bcb2e 100644
--- a/drivers/clk/clk-oxnas.c
+++ b/drivers/clk/clk-oxnas.c
@@ -144,9 +144,9 @@
 		return -ENOMEM;
 
 	regmap = syscon_node_to_regmap(of_get_parent(np));
-	if (!regmap) {
+	if (IS_ERR(regmap)) {
 		dev_err(&pdev->dev, "failed to have parent regmap\n");
-		return -EINVAL;
+		return PTR_ERR(regmap);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(clk_oxnas_init); i++) {
diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c
index 4bb130c..05b3d73 100644
--- a/drivers/clk/rockchip/clk-cpu.c
+++ b/drivers/clk/rockchip/clk-cpu.c
@@ -321,9 +321,9 @@
 	}
 
 	cclk = clk_register(NULL, &cpuclk->hw);
-	if (IS_ERR(clk)) {
+	if (IS_ERR(cclk)) {
 		pr_err("%s: could not register cpuclk %s\n", __func__,	name);
-		ret = PTR_ERR(clk);
+		ret = PTR_ERR(cclk);
 		goto free_rate_table;
 	}
 
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index bc856f2..077fcdc 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -41,8 +41,6 @@
 #define ROCKCHIP_MMC_DEGREE_MASK 0x3
 #define ROCKCHIP_MMC_DELAYNUM_OFFSET 2
 #define ROCKCHIP_MMC_DELAYNUM_MASK (0xff << ROCKCHIP_MMC_DELAYNUM_OFFSET)
-#define ROCKCHIP_MMC_INIT_STATE_RESET 0x1
-#define ROCKCHIP_MMC_INIT_STATE_SHIFT 1
 
 #define PSECS_PER_SEC 1000000000000LL
 
@@ -154,6 +152,7 @@
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
+	init.flags = 0;
 	init.num_parents = num_parents;
 	init.parent_names = parent_names;
 	init.ops = &rockchip_mmc_clk_ops;
@@ -162,15 +161,6 @@
 	mmc_clock->reg = reg;
 	mmc_clock->shift = shift;
 
-	/*
-	 * Assert init_state to soft reset the CLKGEN
-	 * for mmc tuning phase and degree
-	 */
-	if (mmc_clock->shift == ROCKCHIP_MMC_INIT_STATE_SHIFT)
-		writel(HIWORD_UPDATE(ROCKCHIP_MMC_INIT_STATE_RESET,
-				     ROCKCHIP_MMC_INIT_STATE_RESET,
-				     mmc_clock->shift), mmc_clock->reg);
-
 	clk = clk_register(NULL, &mmc_clock->hw);
 	if (IS_ERR(clk))
 		kfree(mmc_clock);
diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index 291543f..8059a8d 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -832,9 +832,9 @@
 			RK3399_CLKGATE_CON(13), 1, GFLAGS),
 
 	/* perihp */
-	GATE(0, "cpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
+	GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
 			RK3399_CLKGATE_CON(5), 0, GFLAGS),
-	GATE(0, "gpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
+	GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
 			RK3399_CLKGATE_CON(5), 1, GFLAGS),
 	COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED,
 			RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS,
@@ -1466,6 +1466,8 @@
 
 static const char *const rk3399_cru_critical_clocks[] __initconst = {
 	"aclk_cci_pre",
+	"aclk_gic",
+	"aclk_gic_noc",
 	"pclk_perilp0",
 	"pclk_perilp0",
 	"hclk_perilp0",
@@ -1508,6 +1510,7 @@
 	ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
 	if (IS_ERR(ctx)) {
 		pr_err("%s: rockchip clk init failed\n", __func__);
+		iounmap(reg_base);
 		return;
 	}
 
@@ -1553,6 +1556,7 @@
 	ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS);
 	if (IS_ERR(ctx)) {
 		pr_err("%s: rockchip pmu clk init failed\n", __func__);
+		iounmap(reg_base);
 		return;
 	}
 
diff --git a/drivers/clk/sunxi/clk-sun4i-display.c b/drivers/clk/sunxi/clk-sun4i-display.c
index 445a749..9780fac 100644
--- a/drivers/clk/sunxi/clk-sun4i-display.c
+++ b/drivers/clk/sunxi/clk-sun4i-display.c
@@ -33,6 +33,8 @@
 
 	u8	width_div;
 	u8	width_mux;
+
+	u32	flags;
 };
 
 struct reset_data {
@@ -166,7 +168,7 @@
 				     data->has_div ? &div->hw : NULL,
 				     data->has_div ? &clk_divider_ops : NULL,
 				     &gate->hw, &clk_gate_ops,
-				     0);
+				     data->flags);
 	if (IS_ERR(clk)) {
 		pr_err("%s: Couldn't register the clock\n", clk_name);
 		goto free_div;
@@ -232,6 +234,7 @@
 	.offset_rst	= 29,
 	.offset_mux	= 24,
 	.width_mux	= 2,
+	.flags		= CLK_SET_RATE_PARENT,
 };
 
 static void __init sun4i_a10_tcon_ch0_setup(struct device_node *node)
diff --git a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c
index 98a4582..b6d29d1 100644
--- a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c
+++ b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c
@@ -79,15 +79,11 @@
 static u8 tcon_ch1_get_parent(struct clk_hw *hw)
 {
 	struct tcon_ch1_clk *tclk = hw_to_tclk(hw);
-	int num_parents = clk_hw_get_num_parents(hw);
 	u32 reg;
 
 	reg = readl(tclk->reg) >> TCON_CH1_SCLK2_MUX_SHIFT;
 	reg &= reg >> TCON_CH1_SCLK2_MUX_MASK;
 
-	if (reg >= num_parents)
-		return -EINVAL;
-
 	return reg;
 }
 
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 15d06fc..b02f9c6 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -56,11 +56,21 @@
 /* proc_event_counts is used as the sequence number of the netlink message */
 static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
 
-static inline void get_seq(__u32 *ts, int *cpu)
+static inline void send_msg(struct cn_msg *msg)
 {
 	preempt_disable();
-	*ts = __this_cpu_inc_return(proc_event_counts) - 1;
-	*cpu = smp_processor_id();
+
+	msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
+	((struct proc_event *)msg->data)->cpu = smp_processor_id();
+
+	/*
+	 * Preemption remains disabled during send to ensure the messages are
+	 * ordered according to their sequence numbers.
+	 *
+	 * If cn_netlink_send() fails, the data is not sent.
+	 */
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
+
 	preempt_enable();
 }
 
@@ -77,7 +87,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_FORK;
 	rcu_read_lock();
@@ -92,8 +101,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	/*  If cn_netlink_send() failed, the data is not sent */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_exec_connector(struct task_struct *task)
@@ -108,7 +116,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_EXEC;
 	ev->event_data.exec.process_pid = task->pid;
@@ -118,7 +125,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_id_connector(struct task_struct *task, int which_id)
@@ -150,14 +157,13 @@
 		return;
 	}
 	rcu_read_unlock();
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_sid_connector(struct task_struct *task)
@@ -172,7 +178,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_SID;
 	ev->event_data.sid.process_pid = task->pid;
@@ -182,7 +187,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
@@ -197,7 +202,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_PTRACE;
 	ev->event_data.ptrace.process_pid  = task->pid;
@@ -215,7 +219,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_comm_connector(struct task_struct *task)
@@ -230,7 +234,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_COMM;
 	ev->event_data.comm.process_pid  = task->pid;
@@ -241,7 +244,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_coredump_connector(struct task_struct *task)
@@ -256,7 +259,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_COREDUMP;
 	ev->event_data.coredump.process_pid = task->pid;
@@ -266,7 +268,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 void proc_exit_connector(struct task_struct *task)
@@ -281,7 +283,6 @@
 	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
-	get_seq(&msg->seq, &ev->cpu);
 	ev->timestamp_ns = ktime_get_ns();
 	ev->what = PROC_EVENT_EXIT;
 	ev->event_data.exit.process_pid = task->pid;
@@ -293,7 +294,7 @@
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 /*
@@ -325,7 +326,7 @@
 	msg->ack = rcvd_ack + 1;
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
+	send_msg(msg);
 }
 
 /**
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3646b14..0bb44d5 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -79,15 +79,16 @@
 static int __init cpufreq_dt_platdev_init(void)
 {
 	struct device_node *np = of_find_node_by_path("/");
+	const struct of_device_id *match;
 
 	if (!np)
 		return -ENODEV;
 
-	if (!of_match_node(machines, np))
+	match = of_match_node(machines, np);
+	of_node_put(np);
+	if (!match)
 		return -ENODEV;
 
-	of_node_put(of_root);
-
 	return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1,
 							       NULL, 0));
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 9009295..5617c70 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2261,6 +2261,10 @@
 	 * -> ask driver for current freq and notify governors about a change
 	 */
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
+		if (cpufreq_suspended) {
+			ret = -EAGAIN;
+			goto unlock;
+		}
 		new_policy.cur = cpufreq_update_current_freq(policy);
 		if (WARN_ON(!new_policy.cur)) {
 			ret = -EIO;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fe9dc17..1fa1a32 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1400,6 +1400,9 @@
 {
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
+	if (cpu->update_util_set)
+		return;
+
 	/* Prevent intel_pstate_update_util() from using stale data. */
 	cpu->sample.time = 0;
 	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
@@ -1440,8 +1443,6 @@
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
-	intel_pstate_clear_update_util_hook(policy->cpu);
-
 	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
 		 policy->cpuinfo.max_freq, policy->max);
 
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 808a320..a7ecb9a 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -487,7 +487,7 @@
 	doorbell.space_id = reg_resource->space_id;
 	doorbell.bit_width = reg_resource->bit_width;
 	doorbell.bit_offset = reg_resource->bit_offset;
-	doorbell.access_width = 64;
+	doorbell.access_width = 4;
 	doorbell.address = reg_resource->address;
 
 	pr_debug("probe: doorbell: space_id is %d, bit_width is %d, "
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index a4d0059..c73207a 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -173,7 +173,7 @@
 
 	struct cpuidle_state *target_state = &drv->states[index];
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
-	u64 time_start, time_end;
+	ktime_t time_start, time_end;
 	s64 diff;
 
 	/*
@@ -195,13 +195,13 @@
 	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
-	time_start = local_clock();
+	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
-	time_end = local_clock();
+	time_end = ns_to_ktime(local_clock());
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
 	/* The cpu is no longer idle or about to enter idle. */
@@ -217,11 +217,7 @@
 	if (!cpuidle_state_is_coupled(drv, index))
 		local_irq_enable();
 
-	/*
-	 * local_clock() returns the time in nanosecond, let's shift
-	 * by 10 (divide by 1024) to have microsecond based time.
-	 */
-	diff = (time_end - time_start) >> 10;
+	diff = ktime_us_delta(time_end, time_start);
 	if (diff > INT_MAX)
 		diff = INT_MAX;
 
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index 6d74b91..5fc3dbb 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -2,6 +2,7 @@
 			     $(obj)/qat_rsapubkey-asn1.h
 $(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \
 			      $(obj)/qat_rsaprivkey-asn1.h
+$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h
 
 clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h
 clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 574e87c..9acccad 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -781,7 +781,7 @@
 						&device_data->state);
 				memmove(req_ctx->state.buffer,
 					device_data->state.buffer,
-					HASH_BLOCK_SIZE / sizeof(u32));
+					HASH_BLOCK_SIZE);
 				if (ret) {
 					dev_err(device_data->dev,
 						"%s: hash_resume_state() failed!\n",
@@ -832,7 +832,7 @@
 
 			memmove(device_data->state.buffer,
 				req_ctx->state.buffer,
-				HASH_BLOCK_SIZE / sizeof(u32));
+				HASH_BLOCK_SIZE);
 			if (ret) {
 				dev_err(device_data->dev, "%s: hash_save_state() failed!\n",
 					__func__);
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 495577b..94ad5c0 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -182,7 +182,7 @@
 	.cra_name = "cbc(aes)",
 	.cra_driver_name = "p8_aes_cbc",
 	.cra_module = THIS_MODULE,
-	.cra_priority = 1000,
+	.cra_priority = 2000,
 	.cra_type = &crypto_blkcipher_type,
 	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
 	.cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 0a3c1b0..38ed10d 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -166,7 +166,7 @@
 	.cra_name = "ctr(aes)",
 	.cra_driver_name = "p8_aes_ctr",
 	.cra_module = THIS_MODULE,
-	.cra_priority = 1000,
+	.cra_priority = 2000,
 	.cra_type = &crypto_blkcipher_type,
 	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
 	.cra_alignmask = 0,
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index 9f4994c..b18e67d 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -141,7 +141,7 @@
 
 # Some ABIs specify vrsave, special-purpose register #256, as reserved
 # for system use.
-my $no_vrsave = ($flavour =~ /aix|linux64le/);
+my $no_vrsave = ($flavour =~ /linux-ppc64le/);
 my $mtspr = sub {
     my ($f,$idx,$ra) = @_;
     if ($idx == 256 && $no_vrsave) {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 1d6c803..e92418f 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -268,8 +268,11 @@
 	devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE);
 
 	err = devfreq->profile->target(devfreq->dev.parent, &freq, flags);
-	if (err)
+	if (err) {
+		freqs.new = cur_freq;
+		devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
 		return err;
+	}
 
 	freqs.new = freq;
 	devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
@@ -552,6 +555,7 @@
 	devfreq->profile = profile;
 	strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
+	devfreq->last_status.current_frequency = profile->initial_freq;
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
@@ -561,23 +565,22 @@
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->trans_table =	devm_kzalloc(dev, sizeof(unsigned int) *
-						devfreq->profile->max_state *
-						devfreq->profile->max_state,
-						GFP_KERNEL);
-	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) *
-						devfreq->profile->max_state,
-						GFP_KERNEL);
-	devfreq->last_stat_updated = jiffies;
-
 	dev_set_name(&devfreq->dev, "%s", dev_name(dev));
 	err = device_register(&devfreq->dev);
 	if (err) {
-		put_device(&devfreq->dev);
 		mutex_unlock(&devfreq->lock);
 		goto err_out;
 	}
 
+	devfreq->trans_table =	devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
+						devfreq->profile->max_state *
+						devfreq->profile->max_state,
+						GFP_KERNEL);
+	devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) *
+						devfreq->profile->max_state,
+						GFP_KERNEL);
+	devfreq->last_stat_updated = jiffies;
+
 	srcu_init_notifier_head(&devfreq->transition_notifier_list);
 
 	mutex_unlock(&devfreq->lock);
@@ -603,7 +606,6 @@
 err_init:
 	list_del(&devfreq->node);
 	device_unregister(&devfreq->dev);
-	kfree(devfreq);
 err_out:
 	return ERR_PTR(err);
 }
@@ -621,7 +623,6 @@
 		return -EINVAL;
 
 	device_unregister(&devfreq->dev);
-	put_device(&devfreq->dev);
 
 	return 0;
 }
diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c
index 6b6a5f3..a584140 100644
--- a/drivers/devfreq/event/exynos-nocp.c
+++ b/drivers/devfreq/event/exynos-nocp.c
@@ -220,9 +220,6 @@
 
 	/* Maps the memory mapped IO to control nocp register */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (IS_ERR(res))
-		return PTR_ERR(res);
-
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 6744d88..4fb2eb7 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -2378,22 +2378,19 @@
  * @num_mc: pointer to the memory controllers count, to be incremented in case
  *	    of success.
  * @table: model specific table
- * @allow_dups: allow for multiple devices to exist with the same device id
- *              (as implemented, this isn't expected to work correctly in the
- *              multi-socket case).
- * @multi_bus: don't assume devices on different buses belong to different
- *             memory controllers.
  *
  * returns 0 in case of success or error code
  */
-static int sbridge_get_all_devices_full(u8 *num_mc,
-					const struct pci_id_table *table,
-					int allow_dups,
-					int multi_bus)
+static int sbridge_get_all_devices(u8 *num_mc,
+					const struct pci_id_table *table)
 {
 	int i, rc;
 	struct pci_dev *pdev = NULL;
+	int allow_dups = 0;
+	int multi_bus = 0;
 
+	if (table->type == KNIGHTS_LANDING)
+		allow_dups = multi_bus = 1;
 	while (table && table->descr) {
 		for (i = 0; i < table->n_devs; i++) {
 			if (!allow_dups || i == 0 ||
@@ -2420,11 +2417,6 @@
 	return 0;
 }
 
-#define sbridge_get_all_devices(num_mc, table) \
-		sbridge_get_all_devices_full(num_mc, table, 0, 0)
-#define sbridge_get_all_devices_knl(num_mc, table) \
-		sbridge_get_all_devices_full(num_mc, table, 1, 1)
-
 static int sbridge_mci_bind_devs(struct mem_ctl_info *mci,
 				 struct sbridge_dev *sbridge_dev)
 {
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index cebcb40..d786061 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -49,7 +49,7 @@
 
 config OF_GPIO
 	def_bool y
-	depends on OF || COMPILE_TEST
+	depends on OF
 
 config GPIO_ACPI
 	def_bool y
@@ -402,9 +402,12 @@
 	select OF_GPIO
 
 config GPIO_TEGRA
-	bool
-	default y
+	bool "NVIDIA Tegra GPIO support"
+	default ARCH_TEGRA
 	depends on ARCH_TEGRA || COMPILE_TEST
+	depends on OF
+	help
+	  Say yes here to support GPIO pins on NVIDIA Tegra SoCs.
 
 config GPIO_TS4800
 	tristate "TS-4800 DIO blocks and compatibles"
diff --git a/drivers/gpio/gpio-104-idi-48.c b/drivers/gpio/gpio-104-idi-48.c
index 6c75c83..2d2763e 100644
--- a/drivers/gpio/gpio-104-idi-48.c
+++ b/drivers/gpio/gpio-104-idi-48.c
@@ -247,6 +247,7 @@
 	idi48gpio->irq = irq[id];
 
 	spin_lock_init(&idi48gpio->lock);
+	spin_lock_init(&idi48gpio->ack_lock);
 
 	dev_set_drvdata(dev, idi48gpio);
 
diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index e85e753..eb43ae4 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -61,9 +61,8 @@
 	return gpio % 8;
 }
 
-static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg)
+static int sch_gpio_reg_get(struct sch_gpio *sch, unsigned gpio, unsigned reg)
 {
-	struct sch_gpio *sch = gpiochip_get_data(gc);
 	unsigned short offset, bit;
 	u8 reg_val;
 
@@ -75,10 +74,9 @@
 	return reg_val;
 }
 
-static void sch_gpio_reg_set(struct gpio_chip *gc, unsigned gpio, unsigned reg,
+static void sch_gpio_reg_set(struct sch_gpio *sch, unsigned gpio, unsigned reg,
 			     int val)
 {
-	struct sch_gpio *sch = gpiochip_get_data(gc);
 	unsigned short offset, bit;
 	u8 reg_val;
 
@@ -98,14 +96,15 @@
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GIO, 1);
+	sch_gpio_reg_set(sch, gpio_num, GIO, 1);
 	spin_unlock(&sch->lock);
 	return 0;
 }
 
 static int sch_gpio_get(struct gpio_chip *gc, unsigned gpio_num)
 {
-	return sch_gpio_reg_get(gc, gpio_num, GLV);
+	struct sch_gpio *sch = gpiochip_get_data(gc);
+	return sch_gpio_reg_get(sch, gpio_num, GLV);
 }
 
 static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val)
@@ -113,7 +112,7 @@
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GLV, val);
+	sch_gpio_reg_set(sch, gpio_num, GLV, val);
 	spin_unlock(&sch->lock);
 }
 
@@ -123,7 +122,7 @@
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GIO, 0);
+	sch_gpio_reg_set(sch, gpio_num, GIO, 0);
 	spin_unlock(&sch->lock);
 
 	/*
@@ -182,13 +181,13 @@
 		 * GPIO7 is configured by the CMC as SLPIOVR
 		 * Enable GPIO[9:8] core powered gpios explicitly
 		 */
-		sch_gpio_reg_set(&sch->chip, 8, GEN, 1);
-		sch_gpio_reg_set(&sch->chip, 9, GEN, 1);
+		sch_gpio_reg_set(sch, 8, GEN, 1);
+		sch_gpio_reg_set(sch, 9, GEN, 1);
 		/*
 		 * SUS_GPIO[2:0] enabled by default
 		 * Enable SUS_GPIO3 resume powered gpio explicitly
 		 */
-		sch_gpio_reg_set(&sch->chip, 13, GEN, 1);
+		sch_gpio_reg_set(sch, 13, GEN, 1);
 		break;
 
 	case PCI_DEVICE_ID_INTEL_ITC_LPC:
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index ec891a27..661b0e3 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -98,7 +98,6 @@
 	const struct tegra_gpio_soc_config	*soc;
 	struct gpio_chip			gc;
 	struct irq_chip				ic;
-	struct lock_class_key			lock_class;
 	u32					bank_count;
 };
 
@@ -547,6 +546,12 @@
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume)
 };
 
+/*
+ * This lock class tells lockdep that GPIO irqs are in a different category
+ * than their parents, so it won't report false recursion.
+ */
+static struct lock_class_key gpio_lock_class;
+
 static int tegra_gpio_probe(struct platform_device *pdev)
 {
 	const struct tegra_gpio_soc_config *config;
@@ -660,7 +665,7 @@
 
 		bank = &tgi->bank_info[GPIO_BANK(gpio)];
 
-		irq_set_lockdep_class(irq, &tgi->lock_class);
+		irq_set_lockdep_class(irq, &gpio_lock_class);
 		irq_set_chip_data(irq, bank);
 		irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq);
 	}
diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c
index 3a5c701..8b83099 100644
--- a/drivers/gpio/gpiolib-legacy.c
+++ b/drivers/gpio/gpiolib-legacy.c
@@ -28,6 +28,10 @@
 	if (!desc && gpio_is_valid(gpio))
 		return -EPROBE_DEFER;
 
+	err = gpiod_request(desc, label);
+	if (err)
+		return err;
+
 	if (flags & GPIOF_OPEN_DRAIN)
 		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
 
@@ -37,10 +41,6 @@
 	if (flags & GPIOF_ACTIVE_LOW)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
-	err = gpiod_request(desc, label);
-	if (err)
-		return err;
-
 	if (flags & GPIOF_DIR_IN)
 		err = gpiod_direction_input(desc);
 	else
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 58d822d..be74bd3 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1352,14 +1352,6 @@
 		spin_lock_irqsave(&gpio_lock, flags);
 	}
 done:
-	if (status < 0) {
-		/* Clear flags that might have been set by the caller before
-		 * requesting the GPIO.
-		 */
-		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
-		clear_bit(FLAG_OPEN_DRAIN, &desc->flags);
-		clear_bit(FLAG_OPEN_SOURCE, &desc->flags);
-	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
 	return status;
 }
@@ -1373,8 +1365,12 @@
 #define VALIDATE_DESC(desc) do { \
 	if (!desc) \
 		return 0; \
+	if (IS_ERR(desc)) {						\
+		pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
+		return PTR_ERR(desc); \
+	} \
 	if (!desc->gdev) { \
-		pr_warn("%s: invalid GPIO\n", __func__); \
+		pr_warn("%s: invalid GPIO (no device)\n", __func__); \
 		return -EINVAL; \
 	} \
 	if ( !desc->gdev->chip ) { \
@@ -1386,8 +1382,12 @@
 #define VALIDATE_DESC_VOID(desc) do { \
 	if (!desc) \
 		return; \
+	if (IS_ERR(desc)) {						\
+		pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \
+		return; \
+	} \
 	if (!desc->gdev) { \
-		pr_warn("%s: invalid GPIO\n", __func__); \
+		pr_warn("%s: invalid GPIO (no device)\n", __func__); \
 		return; \
 	} \
 	if (!desc->gdev->chip) { \
@@ -2056,7 +2056,14 @@
 	struct gpio_chip *chip;
 	int offset;
 
-	VALIDATE_DESC(desc);
+	/*
+	 * Cannot VALIDATE_DESC() here as gpiod_to_irq() consumer semantics
+	 * requires this function to not return zero on an invalid descriptor
+	 * but rather a negative error number.
+	 */
+	if (!desc || IS_ERR(desc) || !desc->gdev || !desc->gdev->chip)
+		return -EINVAL;
+
 	chip = desc->gdev->chip;
 	offset = gpio_chip_hwgpio(desc);
 	if (chip->to_irq) {
@@ -2572,28 +2579,13 @@
 }
 EXPORT_SYMBOL_GPL(gpiod_get_optional);
 
-/**
- * gpiod_parse_flags - helper function to parse GPIO lookup flags
- * @desc:	gpio to be setup
- * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
- *		of_get_gpio_hog()
- *
- * Set the GPIO descriptor flags based on the given GPIO lookup flags.
- */
-static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
-{
-	if (lflags & GPIO_ACTIVE_LOW)
-		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
-	if (lflags & GPIO_OPEN_DRAIN)
-		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
-	if (lflags & GPIO_OPEN_SOURCE)
-		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
-}
 
 /**
  * gpiod_configure_flags - helper function to configure a given GPIO
  * @desc:	gpio whose value will be assigned
  * @con_id:	function within the GPIO consumer
+ * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
+ *		of_get_gpio_hog()
  * @dflags:	gpiod_flags - optional GPIO initialization flags
  *
  * Return 0 on success, -ENOENT if no GPIO has been assigned to the
@@ -2601,10 +2593,17 @@
  * occurred while trying to acquire the GPIO.
  */
 static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
-				 enum gpiod_flags dflags)
+		unsigned long lflags, enum gpiod_flags dflags)
 {
 	int status;
 
+	if (lflags & GPIO_ACTIVE_LOW)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+	if (lflags & GPIO_OPEN_DRAIN)
+		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
+	if (lflags & GPIO_OPEN_SOURCE)
+		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
+
 	/* No particular flag request, return here... */
 	if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
 		pr_debug("no flags found for %s\n", con_id);
@@ -2671,13 +2670,11 @@
 		return desc;
 	}
 
-	gpiod_parse_flags(desc, lookupflags);
-
 	status = gpiod_request(desc, con_id);
 	if (status < 0)
 		return ERR_PTR(status);
 
-	status = gpiod_configure_flags(desc, con_id, flags);
+	status = gpiod_configure_flags(desc, con_id, lookupflags, flags);
 	if (status < 0) {
 		dev_dbg(dev, "setup of GPIO %s failed\n", con_id);
 		gpiod_put(desc);
@@ -2733,6 +2730,10 @@
 	if (IS_ERR(desc))
 		return desc;
 
+	ret = gpiod_request(desc, NULL);
+	if (ret)
+		return ERR_PTR(ret);
+
 	if (active_low)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
@@ -2743,10 +2744,6 @@
 			set_bit(FLAG_OPEN_SOURCE, &desc->flags);
 	}
 
-	ret = gpiod_request(desc, NULL);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return desc;
 }
 EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod);
@@ -2799,8 +2796,6 @@
 	chip = gpiod_to_chip(desc);
 	hwnum = gpio_chip_hwgpio(desc);
 
-	gpiod_parse_flags(desc, lflags);
-
 	local_desc = gpiochip_request_own_desc(chip, hwnum, name);
 	if (IS_ERR(local_desc)) {
 		status = PTR_ERR(local_desc);
@@ -2809,7 +2804,7 @@
 		return status;
 	}
 
-	status = gpiod_configure_flags(desc, name, dflags);
+	status = gpiod_configure_flags(desc, name, lflags, dflags);
 	if (status < 0) {
 		pr_err("setup of hog GPIO %s (chip %s, offset %d) failed, %d\n",
 		       name, chip->label, hwnum, status);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 8943099..cf6f49f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -909,7 +909,7 @@
 	struct cgs_acpi_method_argument *argument = NULL;
 	uint32_t i, count;
 	acpi_status status;
-	int result;
+	int result = 0;
 	uint32_t func_no = 0xFFFFFFFF;
 
 	handle = ACPI_HANDLE(&adev->pdev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 66482b4..6e92008 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1535,7 +1535,7 @@
 	/* Post card if necessary */
 	if (!amdgpu_card_posted(adev) ||
 	    (adev->virtualization.is_virtual &&
-	     !adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN)) {
+	     !(adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN))) {
 		if (!adev->bios) {
 			dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n");
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 40a2370..d851ea1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -447,7 +447,8 @@
 			dev_info.max_memory_clock = adev->pm.default_mclk * 10;
 		}
 		dev_info.enabled_rb_pipes_mask = adev->gfx.config.backend_enable_mask;
-		dev_info.num_rb_pipes = adev->gfx.config.num_rbs;
+		dev_info.num_rb_pipes = adev->gfx.config.max_backends_per_se *
+			adev->gfx.config.max_shader_engines;
 		dev_info.num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts;
 		dev_info._pad = 0;
 		dev_info.ids_flags = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 589b36e..0e13d80 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -270,30 +270,28 @@
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_pm_state_type state = 0;
-	long idx;
+	unsigned long idx;
 	int ret;
 
 	if (strlen(buf) == 1)
 		adev->pp_force_state_enabled = false;
-	else {
-		ret = kstrtol(buf, 0, &idx);
+	else if (adev->pp_enabled) {
+		struct pp_states_info data;
 
-		if (ret) {
+		ret = kstrtoul(buf, 0, &idx);
+		if (ret || idx >= ARRAY_SIZE(data.states)) {
 			count = -EINVAL;
 			goto fail;
 		}
 
-		if (adev->pp_enabled) {
-			struct pp_states_info data;
-			amdgpu_dpm_get_pp_num_states(adev, &data);
-			state = data.states[idx];
-			/* only set user selected power states */
-			if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
-				state != POWER_STATE_TYPE_DEFAULT) {
-				amdgpu_dpm_dispatch_task(adev,
-						AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL);
-				adev->pp_force_state_enabled = true;
-			}
+		amdgpu_dpm_get_pp_num_states(adev, &data);
+		state = data.states[idx];
+		/* only set user selected power states */
+		if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
+		    state != POWER_STATE_TYPE_DEFAULT) {
+			amdgpu_dpm_dispatch_task(adev,
+					AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL);
+			adev->pp_force_state_enabled = true;
 		}
 	}
 fail:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index e19520c..d9c88d13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1106,6 +1106,10 @@
 	if (fences == 0 && handles == 0) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, false);
+			/* just work around for uvd clock remain high even
+			 * when uvd dpm disabled on Polaris10 */
+			if (adev->asic_type == CHIP_POLARIS10)
+				amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 		} else {
 			amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
index 13cdb01..bc56c8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
@@ -156,3 +156,18 @@
 	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
 }
 
+void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, u8 slave_addr, u8 line_number, u8 offset, u8 data)
+{
+	PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args;
+	int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction);
+
+	args.ucRegIndex = offset;
+	args.lpI2CDataOut = data;
+	args.ucFlag = 1;
+	args.ucI2CSpeed = TARGET_HW_I2C_CLOCK;
+	args.ucTransBytes = 1;
+	args.ucSlaveAddr = slave_addr;
+	args.ucLineNumber = line_number;
+
+	amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h
index d6128d9d..251aaf4 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h
@@ -27,5 +27,7 @@
 int amdgpu_atombios_i2c_xfer(struct i2c_adapter *i2c_adap,
 		      struct i2c_msg *msgs, int num);
 u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap);
+void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev,
+		u8 slave_addr, u8 line_number, u8 offset, u8 data);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 9f6f866..c2ef945 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -28,6 +28,7 @@
 #include "vid.h"
 #include "amdgpu_ucode.h"
 #include "amdgpu_atombios.h"
+#include "atombios_i2c.h"
 #include "clearstate_vi.h"
 
 #include "gmc/gmc_8_2_d.h"
@@ -47,6 +48,8 @@
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
+#include "smu/smu_7_1_3_d.h"
+
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
 
@@ -282,6 +285,7 @@
 	mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3,
 	mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000,
 	mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003210,
+	mmVGT_RESET_DEBUG, 0x00000004, 0x00000004,
 };
 
 static const u32 polaris11_golden_common_all[] =
@@ -297,7 +301,8 @@
 static const u32 golden_settings_polaris10_a11[] =
 {
 	mmATC_MISC_CG, 0x000c0fc0, 0x000c0200,
-	mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208,
+	mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208,
+	mmCB_HW_CONTROL_2, 0, 0x0f000000,
 	mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
 	mmDB_DEBUG2, 0xf00fffff, 0x00000400,
 	mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
@@ -311,6 +316,7 @@
 	mmTCC_CTRL, 0x00100000, 0xf31fff7f,
 	mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f7,
 	mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000,
+	mmVGT_RESET_DEBUG, 0x00000004, 0x00000004,
 };
 
 static const u32 polaris10_golden_common_all[] =
@@ -692,6 +698,11 @@
 		amdgpu_program_register_sequence(adev,
 						 polaris10_golden_common_all,
 						 (const u32)ARRAY_SIZE(polaris10_golden_common_all));
+		WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C);
+		if (adev->pdev->revision == 0xc7) {
+			amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1E, 0xDD);
+			amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1F, 0xD0);
+		}
 		break;
 	case CHIP_CARRIZO:
 		amdgpu_program_register_sequence(adev,
diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h
index 32f3e34..3493da5 100644
--- a/drivers/gpu/drm/amd/include/atombios.h
+++ b/drivers/gpu/drm/amd/include/atombios.h
@@ -5538,6 +5538,78 @@
   ULONG  ulReserved[12];
 }ATOM_ASIC_PROFILING_INFO_V3_5;
 
+/* for Polars10/11 AVFS parameters */
+typedef struct  _ATOM_ASIC_PROFILING_INFO_V3_6
+{
+  ATOM_COMMON_TABLE_HEADER         asHeader;
+  ULONG  ulMaxVddc;
+  ULONG  ulMinVddc;
+  USHORT usLkgEuseIndex;
+  UCHAR  ucLkgEfuseBitLSB;
+  UCHAR  ucLkgEfuseLength;
+  ULONG  ulLkgEncodeLn_MaxDivMin;
+  ULONG  ulLkgEncodeMax;
+  ULONG  ulLkgEncodeMin;
+  EFUSE_LINEAR_FUNC_PARAM sRoFuse;
+  ULONG  ulEvvDefaultVddc;
+  ULONG  ulEvvNoCalcVddc;
+  ULONG  ulSpeed_Model;
+  ULONG  ulSM_A0;
+  ULONG  ulSM_A1;
+  ULONG  ulSM_A2;
+  ULONG  ulSM_A3;
+  ULONG  ulSM_A4;
+  ULONG  ulSM_A5;
+  ULONG  ulSM_A6;
+  ULONG  ulSM_A7;
+  UCHAR  ucSM_A0_sign;
+  UCHAR  ucSM_A1_sign;
+  UCHAR  ucSM_A2_sign;
+  UCHAR  ucSM_A3_sign;
+  UCHAR  ucSM_A4_sign;
+  UCHAR  ucSM_A5_sign;
+  UCHAR  ucSM_A6_sign;
+  UCHAR  ucSM_A7_sign;
+  ULONG  ulMargin_RO_a;
+  ULONG  ulMargin_RO_b;
+  ULONG  ulMargin_RO_c;
+  ULONG  ulMargin_fixed;
+  ULONG  ulMargin_Fmax_mean;
+  ULONG  ulMargin_plat_mean;
+  ULONG  ulMargin_Fmax_sigma;
+  ULONG  ulMargin_plat_sigma;
+  ULONG  ulMargin_DC_sigma;
+  ULONG  ulLoadLineSlop;
+  ULONG  ulaTDClimitPerDPM[8];
+  ULONG  ulaNoCalcVddcPerDPM[8];
+  ULONG  ulAVFS_meanNsigma_Acontant0;
+  ULONG  ulAVFS_meanNsigma_Acontant1;
+  ULONG  ulAVFS_meanNsigma_Acontant2;
+  USHORT usAVFS_meanNsigma_DC_tol_sigma;
+  USHORT usAVFS_meanNsigma_Platform_mean;
+  USHORT usAVFS_meanNsigma_Platform_sigma;
+  ULONG  ulGB_VDROOP_TABLE_CKSOFF_a0;
+  ULONG  ulGB_VDROOP_TABLE_CKSOFF_a1;
+  ULONG  ulGB_VDROOP_TABLE_CKSOFF_a2;
+  ULONG  ulGB_VDROOP_TABLE_CKSON_a0;
+  ULONG  ulGB_VDROOP_TABLE_CKSON_a1;
+  ULONG  ulGB_VDROOP_TABLE_CKSON_a2;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+  USHORT usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSON_m1;
+  USHORT usAVFSGB_FUSE_TABLE_CKSON_m2;
+  ULONG  ulAVFSGB_FUSE_TABLE_CKSON_b;
+  USHORT usMaxVoltage_0_25mv;
+  UCHAR  ucEnableGB_VDROOP_TABLE_CKSOFF;
+  UCHAR  ucEnableGB_VDROOP_TABLE_CKSON;
+  UCHAR  ucEnableGB_FUSE_TABLE_CKSOFF;
+  UCHAR  ucEnableGB_FUSE_TABLE_CKSON;
+  USHORT usPSM_Age_ComFactor;
+  UCHAR  ucEnableApplyAVFS_CKS_OFF_Voltage;
+  UCHAR  ucReserved;
+}ATOM_ASIC_PROFILING_INFO_V3_6;
+
 
 typedef struct _ATOM_SCLK_FCW_RANGE_ENTRY_V1{
   ULONG  ulMaxSclkFreq;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
index 586f732..92912ab 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
@@ -633,6 +633,8 @@
 	data->vddci_control = FIJI_VOLTAGE_CONTROL_NONE;
 	data->mvdd_control = FIJI_VOLTAGE_CONTROL_NONE;
 
+	data->force_pcie_gen = PP_PCIEGenInvalid;
+
 	if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
 			VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
 		data->voltage_control = FIJI_VOLTAGE_CONTROL_BY_SVID2;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index fa208ad..efb77ed 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -306,10 +306,14 @@
 {
 	PHM_FUNC_CHECK(hwmgr);
 
-	if (hwmgr->hwmgr_func->store_cc6_data == NULL)
+	if (display_config == NULL)
 		return -EINVAL;
 
 	hwmgr->display_config = *display_config;
+
+	if (hwmgr->hwmgr_func->store_cc6_data == NULL)
+		return -EINVAL;
+
 	/* to do pass other display configuration in furture */
 
 	if (hwmgr->hwmgr_func->store_cc6_data)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
index 1400bc4..91e25f9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
@@ -732,7 +732,7 @@
 			table->Smio[level] |=
 				data->mvdd_voltage_table.entries[level].smio_low;
 		}
-		table->SmioMask2 = data->vddci_voltage_table.mask_low;
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
 
 		table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count);
 	}
@@ -1296,7 +1296,6 @@
 	}
 
 	mem_level->MclkFrequency = clock;
-	mem_level->StutterEnable = 0;
 	mem_level->EnabledForThrottle = 1;
 	mem_level->EnabledForActivity = 0;
 	mem_level->UpHyst = 0;
@@ -1304,7 +1303,6 @@
 	mem_level->VoltageDownHyst = 0;
 	mem_level->ActivityLevel = (uint16_t)data->mclk_activity_target;
 	mem_level->StutterEnable = false;
-
 	mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
 
 	data->display_timing.num_existing_displays = info.display_count;
@@ -1363,7 +1361,7 @@
 	 * a higher state by default such that we are not effected by
 	 * up threshold or and MCLK DPM latency.
 	 */
-	levels[0].ActivityLevel = (uint16_t)data->mclk_dpm0_activity_target;
+	levels[0].ActivityLevel = 0x1f;
 	CONVERT_FROM_HOST_TO_SMC_US(levels[0].ActivityLevel);
 
 	data->smc_state_table.MemoryDpmLevelCount =
@@ -1424,22 +1422,19 @@
 
 	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
 
-	if (!data->sclk_dpm_key_disabled) {
-		/* Get MinVoltage and Frequency from DPM0,
-		 * already converted to SMC_UL */
-		sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
-		result = polaris10_get_dependency_volt_by_clk(hwmgr,
-				table_info->vdd_dep_on_sclk,
-				table->ACPILevel.SclkFrequency,
-				&table->ACPILevel.MinVoltage, &mvdd);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"Cannot find ACPI VDDC voltage value "
-				"in Clock Dependency Table", );
-	} else {
-		sclk_frequency = data->vbios_boot_state.sclk_bootup_value;
-		table->ACPILevel.MinVoltage =
-				data->vbios_boot_state.vddc_bootup_value * VOLTAGE_SCALE;
-	}
+
+	/* Get MinVoltage and Frequency from DPM0,
+	 * already converted to SMC_UL */
+	sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
+	result = polaris10_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_sclk,
+			sclk_frequency,
+			&table->ACPILevel.MinVoltage, &mvdd);
+	PP_ASSERT_WITH_CODE((0 == result),
+			"Cannot find ACPI VDDC voltage value "
+			"in Clock Dependency Table",
+			);
+
 
 	result = polaris10_calculate_sclk_params(hwmgr, sclk_frequency,  &(table->ACPILevel.SclkSetting));
 	PP_ASSERT_WITH_CODE(result == 0, "Error retrieving Engine Clock dividers from VBIOS.", return result);
@@ -1464,24 +1459,18 @@
 	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_frac);
 	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_ss_slew_rate);
 
-	if (!data->mclk_dpm_key_disabled) {
-		/* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
-		table->MemoryACPILevel.MclkFrequency =
-				data->dpm_table.mclk_table.dpm_levels[0].value;
-		result = polaris10_get_dependency_volt_by_clk(hwmgr,
-				table_info->vdd_dep_on_mclk,
-				table->MemoryACPILevel.MclkFrequency,
-				&table->MemoryACPILevel.MinVoltage, &mvdd);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"Cannot find ACPI VDDCI voltage value "
-				"in Clock Dependency Table",
-				);
-	} else {
-		table->MemoryACPILevel.MclkFrequency =
-				data->vbios_boot_state.mclk_bootup_value;
-		table->MemoryACPILevel.MinVoltage =
-				data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE;
-	}
+
+	/* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
+	table->MemoryACPILevel.MclkFrequency =
+			data->dpm_table.mclk_table.dpm_levels[0].value;
+	result = polaris10_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_mclk,
+			table->MemoryACPILevel.MclkFrequency,
+			&table->MemoryACPILevel.MinVoltage, &mvdd);
+	PP_ASSERT_WITH_CODE((0 == result),
+			"Cannot find ACPI VDDCI voltage value "
+			"in Clock Dependency Table",
+			);
 
 	us_mvdd = 0;
 	if ((POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
@@ -1526,6 +1515,7 @@
 	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
 			table_info->mm_dep_table;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
 
 	table->VceLevelCount = (uint8_t)(mm_table->count);
 	table->VceBootLevel = 0;
@@ -1535,9 +1525,18 @@
 		table->VceLevel[count].MinVoltage = 0;
 		table->VceLevel[count].MinVoltage |=
 				(mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
+
+		if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+
 		table->VceLevel[count].MinVoltage |=
-				((mm_table->entries[count].vddc - data->vddc_vddci_delta) *
-						VOLTAGE_SCALE) << VDDCI_SHIFT;
+				(vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 		table->VceLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
 
 		/*retrieve divider value for VBIOS */
@@ -1566,6 +1565,7 @@
 	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
 			table_info->mm_dep_table;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
 
 	table->SamuBootLevel = 0;
 	table->SamuLevelCount = (uint8_t)(mm_table->count);
@@ -1576,8 +1576,16 @@
 		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
 		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-		table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
-				data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
 
 		/* retrieve divider value for VBIOS */
@@ -1660,6 +1668,7 @@
 	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
 			table_info->mm_dep_table;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
 
 	table->UvdLevelCount = (uint8_t)(mm_table->count);
 	table->UvdBootLevel = 0;
@@ -1670,8 +1679,16 @@
 		table->UvdLevel[count].DclkFrequency = mm_table->entries[count].dclk;
 		table->UvdLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-		table->UvdLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
-				data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		table->UvdLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 		table->UvdLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
 
 		/* retrieve divider value for VBIOS */
@@ -1692,8 +1709,8 @@
 		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].VclkFrequency);
 		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].DclkFrequency);
 		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].MinVoltage);
-
 	}
+
 	return result;
 }
 
@@ -1761,12 +1778,9 @@
 
 static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 {
-	uint32_t ro, efuse, efuse2, clock_freq, volt_without_cks,
-			volt_with_cks, value;
-	uint16_t clock_freq_u16;
+	uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
-	uint8_t type, i, j, cks_setting, stretch_amount, stretch_amount2,
-			volt_offset = 0;
+	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1778,50 +1792,44 @@
 	 * if the part is SS or FF. if RO >= 1660MHz, part is FF.
 	 */
 	efuse = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixSMU_EFUSE_0 + (146 * 4));
-	efuse2 = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixSMU_EFUSE_0 + (148 * 4));
+			ixSMU_EFUSE_0 + (67 * 4));
 	efuse &= 0xFF000000;
 	efuse = efuse >> 24;
-	efuse2 &= 0xF;
 
-	if (efuse2 == 1)
-		ro = (2300 - 1350) * efuse / 255 + 1350;
-	else
-		ro = (2500 - 1000) * efuse / 255 + 1000;
+	if (hwmgr->chip_id == CHIP_POLARIS10) {
+		min = 1000;
+		max = 2300;
+	} else {
+		min = 1100;
+		max = 2100;
+	}
 
-	if (ro >= 1660)
-		type = 0;
-	else
-		type = 1;
-
-	/* Populate Stretch amount */
-	data->smc_state_table.ClockStretcherAmount = stretch_amount;
+	ro = efuse * (max -min)/255 + min;
 
 	/* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */
 	for (i = 0; i < sclk_table->count; i++) {
 		data->smc_state_table.Sclk_CKS_masterEn0_7 |=
 				sclk_table->entries[i].cks_enable << i;
-		volt_without_cks = (uint32_t)((14041 *
-			(sclk_table->entries[i].clk/100) / 10000 + 3571 + 75 - ro) * 1000 /
-			(4026 - (13924 * (sclk_table->entries[i].clk/100) / 10000)));
-		volt_with_cks = (uint32_t)((13946 *
-			(sclk_table->entries[i].clk/100) / 10000 + 3320 + 45 - ro) * 1000 /
-			(3664 - (11454 * (sclk_table->entries[i].clk/100) / 10000)));
+		if (hwmgr->chip_id == CHIP_POLARIS10) {
+			volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \
+						(2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000));
+			volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \
+					(2522480 - sclk_table->entries[i].clk/100 * 115764/100));
+		} else {
+			volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \
+						(2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000)));
+			volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \
+					(3422454 - sclk_table->entries[i].clk/100 * (18886376/10000)));
+		}
+
 		if (volt_without_cks >= volt_with_cks)
 			volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks +
-					sclk_table->entries[i].cks_voffset) * 100 / 625) + 1);
+					sclk_table->entries[i].cks_voffset) * 100 + 624) / 625);
+
 		data->smc_state_table.Sclk_voltageOffset[i] = volt_offset;
 	}
 
-	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
-			STRETCH_ENABLE, 0x0);
-	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
-			masterReset, 0x1);
-	/* PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, staticEnable, 0x1); */
-	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE,
-			masterReset, 0x0);
-
+	data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6;
 	/* Populate CKS Lookup Table */
 	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
 		stretch_amount2 = 0;
@@ -1835,69 +1843,6 @@
 				return -EINVAL);
 	}
 
-	value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixPWR_CKS_CNTL);
-	value &= 0xFFC2FF87;
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq =
-			polaris10_clock_stretcher_lookup_table[stretch_amount2][0];
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq =
-			polaris10_clock_stretcher_lookup_table[stretch_amount2][1];
-	clock_freq_u16 = (uint16_t)(PP_SMC_TO_HOST_UL(data->smc_state_table.
-			GraphicsLevel[data->smc_state_table.GraphicsDpmLevelCount - 1].SclkSetting.SclkFrequency) / 100);
-	if (polaris10_clock_stretcher_lookup_table[stretch_amount2][0] < clock_freq_u16
-	&& polaris10_clock_stretcher_lookup_table[stretch_amount2][1] > clock_freq_u16) {
-		/* Program PWR_CKS_CNTL. CKS_USE_FOR_LOW_FREQ */
-		value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 16;
-		/* Program PWR_CKS_CNTL. CKS_LDO_REFSEL */
-		value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][2]) << 18;
-		/* Program PWR_CKS_CNTL. CKS_STRETCH_AMOUNT */
-		value |= (polaris10_clock_stretch_amount_conversion
-				[polaris10_clock_stretcher_lookup_table[stretch_amount2][3]]
-				 [stretch_amount]) << 3;
-	}
-	CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq);
-	CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq);
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting =
-			polaris10_clock_stretcher_lookup_table[stretch_amount2][2] & 0x7F;
-	data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting |=
-			(polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 7;
-
-	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
-			ixPWR_CKS_CNTL, value);
-
-	/* Populate DDT Lookup Table */
-	for (i = 0; i < 4; i++) {
-		/* Assign the minimum and maximum VID stored
-		 * in the last row of Clock Stretcher Voltage Table.
-		 */
-		data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].minVID =
-				(uint8_t) polaris10_clock_stretcher_ddt_table[type][i][2];
-		data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].maxVID =
-				(uint8_t) polaris10_clock_stretcher_ddt_table[type][i][3];
-		/* Loop through each SCLK and check the frequency
-		 * to see if it lies within the frequency for clock stretcher.
-		 */
-		for (j = 0; j < data->smc_state_table.GraphicsDpmLevelCount; j++) {
-			cks_setting = 0;
-			clock_freq = PP_SMC_TO_HOST_UL(
-					data->smc_state_table.GraphicsLevel[j].SclkSetting.SclkFrequency);
-			/* Check the allowed frequency against the sclk level[j].
-			 *  Sclk's endianness has already been converted,
-			 *  and it's in 10Khz unit,
-			 *  as opposed to Data table, which is in Mhz unit.
-			 */
-			if (clock_freq >= (polaris10_clock_stretcher_ddt_table[type][i][0]) * 100) {
-				cks_setting |= 0x2;
-				if (clock_freq < (polaris10_clock_stretcher_ddt_table[type][i][1]) * 100)
-					cks_setting |= 0x1;
-			}
-			data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting
-							|= cks_setting << (j * 2);
-		}
-		CONVERT_FROM_HOST_TO_SMC_US(
-			data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting);
-	}
-
 	value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL);
 	value &= 0xFFFFFFFE;
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL, value);
@@ -1956,6 +1901,90 @@
 	return 0;
 }
 
+
+int polaris10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	SMU74_Discrete_DpmTable  *table = &(data->smc_state_table);
+	int result = 0;
+	struct pp_atom_ctrl__avfs_parameters avfs_params = {0};
+	AVFS_meanNsigma_t AVFS_meanNsigma = { {0} };
+	AVFS_Sclk_Offset_t AVFS_SclkOffset = { {0} };
+	uint32_t tmp, i;
+	struct pp_smumgr *smumgr = hwmgr->smumgr;
+	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend);
+
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
+			table_info->vdd_dep_on_sclk;
+
+
+	if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED)
+		return result;
+
+	result = atomctrl_get_avfs_information(hwmgr, &avfs_params);
+
+	if (0 == result) {
+		table->BTCGB_VDROOP_TABLE[0].a0  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a0);
+		table->BTCGB_VDROOP_TABLE[0].a1  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a1);
+		table->BTCGB_VDROOP_TABLE[0].a2  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a2);
+		table->BTCGB_VDROOP_TABLE[1].a0  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a0);
+		table->BTCGB_VDROOP_TABLE[1].a1  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a1);
+		table->BTCGB_VDROOP_TABLE[1].a2  = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a2);
+		table->AVFSGB_VDROOP_TABLE[0].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_m1);
+		table->AVFSGB_VDROOP_TABLE[0].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSON_m2);
+		table->AVFSGB_VDROOP_TABLE[0].b  = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_b);
+		table->AVFSGB_VDROOP_TABLE[0].m1_shift = 24;
+		table->AVFSGB_VDROOP_TABLE[0].m2_shift  = 12;
+		table->AVFSGB_VDROOP_TABLE[1].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_m1);
+		table->AVFSGB_VDROOP_TABLE[1].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSOFF_m2);
+		table->AVFSGB_VDROOP_TABLE[1].b  = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_b);
+		table->AVFSGB_VDROOP_TABLE[1].m1_shift = 24;
+		table->AVFSGB_VDROOP_TABLE[1].m2_shift  = 12;
+		table->MaxVoltage                = PP_HOST_TO_SMC_US(avfs_params.usMaxVoltage_0_25mv);
+		AVFS_meanNsigma.Aconstant[0]      = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant0);
+		AVFS_meanNsigma.Aconstant[1]      = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant1);
+		AVFS_meanNsigma.Aconstant[2]      = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant2);
+		AVFS_meanNsigma.DC_tol_sigma      = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_DC_tol_sigma);
+		AVFS_meanNsigma.Platform_mean     = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_mean);
+		AVFS_meanNsigma.PSM_Age_CompFactor = PP_HOST_TO_SMC_US(avfs_params.usPSM_Age_ComFactor);
+		AVFS_meanNsigma.Platform_sigma     = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_sigma);
+
+		for (i = 0; i < NUM_VFT_COLUMNS; i++) {
+			AVFS_meanNsigma.Static_Voltage_Offset[i] = (uint8_t)(sclk_table->entries[i].cks_voffset * 100 / 625);
+			AVFS_SclkOffset.Sclk_Offset[i] = PP_HOST_TO_SMC_US((uint16_t)(sclk_table->entries[i].sclk_offset) / 100);
+		}
+
+		result = polaris10_read_smc_sram_dword(smumgr,
+				SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsMeanNSigma),
+				&tmp, data->sram_end);
+
+		polaris10_copy_bytes_to_smc(smumgr,
+					tmp,
+					(uint8_t *)&AVFS_meanNsigma,
+					sizeof(AVFS_meanNsigma_t),
+					data->sram_end);
+
+		result = polaris10_read_smc_sram_dword(smumgr,
+				SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsSclkOffsetTable),
+				&tmp, data->sram_end);
+		polaris10_copy_bytes_to_smc(smumgr,
+					tmp,
+					(uint8_t *)&AVFS_SclkOffset,
+					sizeof(AVFS_Sclk_Offset_t),
+					data->sram_end);
+
+		data->avfs_vdroop_override_setting = (avfs_params.ucEnableGB_VDROOP_TABLE_CKSON << BTCGB0_Vdroop_Enable_SHIFT) |
+						(avfs_params.ucEnableGB_VDROOP_TABLE_CKSOFF << BTCGB1_Vdroop_Enable_SHIFT) |
+						(avfs_params.ucEnableGB_FUSE_TABLE_CKSON << AVFSGB0_Vdroop_Enable_SHIFT) |
+						(avfs_params.ucEnableGB_FUSE_TABLE_CKSOFF << AVFSGB1_Vdroop_Enable_SHIFT);
+		data->apply_avfs_cks_off_voltage = (avfs_params.ucEnableApplyAVFS_CKS_OFF_Voltage == 1) ? true : false;
+	}
+	return result;
+}
+
+
 /**
 * Initializes the SMC table and uploads it
 *
@@ -2056,6 +2085,10 @@
 				"Failed to populate Clock Stretcher Data Table!",
 				return result);
 	}
+
+	result = polaris10_populate_avfs_parameters(hwmgr);
+	PP_ASSERT_WITH_CODE(0 == result, "Failed to populate AVFS Parameters!", return result;);
+
 	table->CurrSclkPllRange = 0xff;
 	table->GraphicsVoltageChangeEnable  = 1;
 	table->GraphicsThermThrottleEnable  = 1;
@@ -2252,6 +2285,9 @@
 static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t soft_register_value = 0;
+	uint32_t handshake_disables_offset = data->soft_regs_start
+				+ offsetof(SMU74_SoftRegisters, HandshakeDisables);
 
 	/* enable SCLK dpm */
 	if (!data->sclk_dpm_key_disabled)
@@ -2262,6 +2298,12 @@
 
 	/* enable MCLK dpm */
 	if (0 == data->mclk_dpm_key_disabled) {
+/* Disable UVD - SMU handshake for MCLK. */
+		soft_register_value = cgs_read_ind_register(hwmgr->device,
+					CGS_IND_REG__SMC, handshake_disables_offset);
+		soft_register_value |= SMU7_UVD_MCLK_HANDSHAKE_DISABLE;
+		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
+				handshake_disables_offset, soft_register_value);
 
 		PP_ASSERT_WITH_CODE(
 				(0 == smum_send_msg_to_smc(hwmgr->smumgr,
@@ -2269,7 +2311,6 @@
 				"Failed to enable MCLK DPM during DPM Start Function!",
 				return -1);
 
-
 		PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
 
 		cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x5);
@@ -2471,6 +2512,8 @@
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to enable VR hot GPIO interrupt!", result = tmp_result);
 
+	smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay);
+
 	tmp_result = polaris10_enable_sclk_control(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to enable SCLK control!", result = tmp_result);
@@ -2606,6 +2649,7 @@
 
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 						PHM_PlatformCaps_FanSpeedInTableIsRPM);
+
 	if (hwmgr->chip_id == CHIP_POLARIS11)
 		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_SPLLShutdownSupport);
@@ -2638,7 +2682,7 @@
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 	uint16_t vv_id;
-	uint16_t vddc = 0;
+	uint32_t vddc = 0;
 	uint16_t i, j;
 	uint32_t sclk = 0;
 	struct phm_ppt_v1_information *table_info =
@@ -2669,8 +2713,9 @@
 						continue);
 
 
-			/* need to make sure vddc is less than 2v or else, it could burn the ASIC. */
-			PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0),
+			/* need to make sure vddc is less than 2v or else, it could burn the ASIC.
+			 * real voltage level in unit of 0.01mv */
+			PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0),
 					"Invalid VDDC value", result = -EINVAL;);
 
 			/* the voltage should not be zero nor equal to leakage ID */
@@ -2896,6 +2941,31 @@
 	return 0;
 }
 
+int polaris10_patch_voltage_workaround(struct pp_hwmgr *hwmgr)
+{
+	struct phm_ppt_v1_information *table_info =
+		       (struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_mclk_table =
+			table_info->vdd_dep_on_mclk;
+	struct phm_ppt_v1_voltage_lookup_table *lookup_table =
+			table_info->vddc_lookup_table;
+	uint32_t i;
+
+	if (hwmgr->chip_id == CHIP_POLARIS10 && hwmgr->hw_revision == 0xC7) {
+		if (lookup_table->entries[dep_mclk_table->entries[dep_mclk_table->count-1].vddInd].us_vdd >= 1000)
+			return 0;
+
+		for (i = 0; i < lookup_table->count; i++) {
+			if (lookup_table->entries[i].us_vdd < 0xff01 && lookup_table->entries[i].us_vdd >= 1000) {
+				dep_mclk_table->entries[dep_mclk_table->count-1].vddInd = (uint8_t) i;
+				return 0;
+			}
+		}
+	}
+	return 0;
+}
+
+
 int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -2938,6 +3008,11 @@
 	data->vddci_control = POLARIS10_VOLTAGE_CONTROL_NONE;
 	data->mvdd_control = POLARIS10_VOLTAGE_CONTROL_NONE;
 
+	data->enable_tdc_limit_feature = true;
+	data->enable_pkg_pwr_tracking_feature = true;
+	data->force_pcie_gen = PP_PCIEGenInvalid;
+	data->mclk_stutter_mode_threshold = 40000;
+
 	if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
 			VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2))
 		data->voltage_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2;
@@ -2962,8 +3037,13 @@
 			data->vddci_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2;
 	}
 
+	if (table_info->cac_dtp_table->usClockStretchAmount != 0)
+		phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+					PHM_PlatformCaps_ClockStretcher);
+
 	polaris10_set_features_platform_caps(hwmgr);
 
+	polaris10_patch_voltage_workaround(hwmgr);
 	polaris10_init_dpm_defaults(hwmgr);
 
 	/* Get leakage voltage based on leakage ID. */
@@ -4333,6 +4413,15 @@
 	return 0;
 }
 
+static int polaris10_notify_smc_display(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+
+	smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+		(PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2);
+	return (smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ?  0 : -EINVAL;
+}
+
 static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input)
 {
 	int tmp_result, result = 0;
@@ -4381,6 +4470,11 @@
 			"Failed to program memory timing parameters!",
 			result = tmp_result);
 
+	tmp_result = polaris10_notify_smc_display(hwmgr);
+	PP_ASSERT_WITH_CODE((0 == tmp_result),
+			"Failed to notify smc display settings!",
+			result = tmp_result);
+
 	tmp_result = polaris10_unfreeze_sclk_mclk_dpm(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to unfreeze SCLK MCLK DPM!",
@@ -4415,6 +4509,7 @@
 			PPSMC_MSG_SetFanPwmMax, us_max_fan_pwm);
 }
 
+
 int polaris10_notify_smc_display_change(struct pp_hwmgr *hwmgr, bool has_display)
 {
 	PPSMC_Msg msg = has_display ? (PPSMC_Msg)PPSMC_HasDisplay : (PPSMC_Msg)PPSMC_NoDisplay;
@@ -4434,8 +4529,6 @@
 
 	if (num_active_displays > 1)  /* to do && (pHwMgr->pPECI->displayConfiguration.bMultiMonitorInSync != TRUE)) */
 		polaris10_notify_smc_display_change(hwmgr, false);
-	else
-		polaris10_notify_smc_display_change(hwmgr, true);
 
 	return 0;
 }
@@ -4476,6 +4569,8 @@
 	frame_time_in_us = 1000000 / refresh_rate;
 
 	pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us;
+	data->frame_time_x2 = frame_time_in_us * 2 / 100;
+
 	display_gap2 = pre_vbi_time_in_us * (ref_clock / 100);
 
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL2, display_gap2);
@@ -4484,8 +4579,6 @@
 
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + offsetof(SMU74_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us));
 
-	polaris10_notify_smc_display_change(hwmgr, num_active_displays != 0);
-
 	return 0;
 }
 
@@ -4597,7 +4690,7 @@
 		return 0;
 	}
 
-	data->need_long_memory_training = true;
+	data->need_long_memory_training = false;
 
 /*
  *	PPMCME_FirmwareDescriptorEntry *pfd = NULL;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
index beedf35..afc3434 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
@@ -312,6 +312,10 @@
 
 	/* soft pptable for re-uploading into smu */
 	void *soft_pp_table;
+
+	uint32_t                              avfs_vdroop_override_setting;
+	bool                                  apply_avfs_cks_off_voltage;
+	uint32_t                              frame_time_x2;
 };
 
 /* To convert to Q8.8 format for firmware */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
index aba167f..b206632 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c
@@ -625,10 +625,14 @@
 	int ret;
 	struct pp_smumgr *smumgr = (struct pp_smumgr *)(hwmgr->smumgr);
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend);
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 
-	if (smu_data->avfs.avfs_btc_status != AVFS_BTC_ENABLEAVFS)
+	if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED)
 		return 0;
 
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+			PPSMC_MSG_SetGBDroopSettings, data->avfs_vdroop_override_setting);
+
 	ret = (smum_send_msg_to_smc(smumgr, PPSMC_MSG_EnableAvfs) == 0) ?
 			0 : -1;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
index 58742e0..a3c38bb 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
@@ -44,6 +44,20 @@
 	return result == 0 ? (output_buf.function_bits & (1 << (index - 1))) != 0 : false;
 }
 
+bool acpi_atcs_notify_pcie_device_ready(void *device)
+{
+	int32_t temp_buffer = 1;
+
+	return cgs_call_acpi_method(device, CGS_ACPI_METHOD_ATCS,
+				ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION,
+						&temp_buffer,
+						NULL,
+						0,
+						sizeof(temp_buffer),
+						0);
+}
+
+
 int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise)
 {
 	struct atcs_pref_req_input atcs_input;
@@ -52,7 +66,7 @@
 	int result;
 	struct cgs_system_info info = {0};
 
-	if (!acpi_atcs_functions_supported(device, ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST))
+	if( 0 != acpi_atcs_notify_pcie_device_ready(device))
 		return -EINVAL;
 
 	info.size = sizeof(struct cgs_system_info);
@@ -77,7 +91,7 @@
 						ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST,
 						&atcs_input,
 						&atcs_output,
-						0,
+						1,
 						sizeof(atcs_input),
 						sizeof(atcs_output));
 		if (result != 0)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index da9f5f1..90b35c5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1256,7 +1256,7 @@
 }
 
 int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
-				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage)
+				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage)
 {
 
 	int result;
@@ -1274,7 +1274,7 @@
 	if (0 != result)
 		return result;
 
-	*voltage = get_voltage_info_param_space.usVoltageLevel;
+	*voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel;
 
 	return result;
 }
@@ -1302,3 +1302,46 @@
 
 	return 0;
 }
+
+int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param)
+{
+	ATOM_ASIC_PROFILING_INFO_V3_6 *profile = NULL;
+
+	if (param == NULL)
+		return -EINVAL;
+
+	profile = (ATOM_ASIC_PROFILING_INFO_V3_6 *)
+			cgs_atom_get_data_table(hwmgr->device,
+					GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo),
+					NULL, NULL, NULL);
+	if (!profile)
+		return -1;
+
+	param->ulAVFS_meanNsigma_Acontant0 = profile->ulAVFS_meanNsigma_Acontant0;
+	param->ulAVFS_meanNsigma_Acontant1 = profile->ulAVFS_meanNsigma_Acontant1;
+	param->ulAVFS_meanNsigma_Acontant2 = profile->ulAVFS_meanNsigma_Acontant2;
+	param->usAVFS_meanNsigma_DC_tol_sigma = profile->usAVFS_meanNsigma_DC_tol_sigma;
+	param->usAVFS_meanNsigma_Platform_mean = profile->usAVFS_meanNsigma_Platform_mean;
+	param->usAVFS_meanNsigma_Platform_sigma = profile->usAVFS_meanNsigma_Platform_sigma;
+	param->ulGB_VDROOP_TABLE_CKSOFF_a0 = profile->ulGB_VDROOP_TABLE_CKSOFF_a0;
+	param->ulGB_VDROOP_TABLE_CKSOFF_a1 = profile->ulGB_VDROOP_TABLE_CKSOFF_a1;
+	param->ulGB_VDROOP_TABLE_CKSOFF_a2 = profile->ulGB_VDROOP_TABLE_CKSOFF_a2;
+	param->ulGB_VDROOP_TABLE_CKSON_a0 = profile->ulGB_VDROOP_TABLE_CKSON_a0;
+	param->ulGB_VDROOP_TABLE_CKSON_a1 = profile->ulGB_VDROOP_TABLE_CKSON_a1;
+	param->ulGB_VDROOP_TABLE_CKSON_a2 = profile->ulGB_VDROOP_TABLE_CKSON_a2;
+	param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+	param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+	param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+	param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = profile->ulAVFSGB_FUSE_TABLE_CKSON_m1;
+	param->usAVFSGB_FUSE_TABLE_CKSON_m2 = profile->usAVFSGB_FUSE_TABLE_CKSON_m2;
+	param->ulAVFSGB_FUSE_TABLE_CKSON_b = profile->ulAVFSGB_FUSE_TABLE_CKSON_b;
+	param->usMaxVoltage_0_25mv = profile->usMaxVoltage_0_25mv;
+	param->ucEnableGB_VDROOP_TABLE_CKSOFF = profile->ucEnableGB_VDROOP_TABLE_CKSOFF;
+	param->ucEnableGB_VDROOP_TABLE_CKSON = profile->ucEnableGB_VDROOP_TABLE_CKSON;
+	param->ucEnableGB_FUSE_TABLE_CKSOFF = profile->ucEnableGB_FUSE_TABLE_CKSOFF;
+	param->ucEnableGB_FUSE_TABLE_CKSON = profile->ucEnableGB_FUSE_TABLE_CKSON;
+	param->usPSM_Age_ComFactor = profile->usPSM_Age_ComFactor;
+	param->ucEnableApplyAVFS_CKS_OFF_Voltage = profile->ucEnableApplyAVFS_CKS_OFF_Voltage;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
index d24ebb5..1e35a96 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
@@ -250,6 +250,35 @@
 };
 typedef struct pp_atomctrl_gpio_pin_assignment pp_atomctrl_gpio_pin_assignment;
 
+struct pp_atom_ctrl__avfs_parameters {
+	uint32_t  ulAVFS_meanNsigma_Acontant0;
+	uint32_t  ulAVFS_meanNsigma_Acontant1;
+	uint32_t  ulAVFS_meanNsigma_Acontant2;
+	uint16_t usAVFS_meanNsigma_DC_tol_sigma;
+	uint16_t usAVFS_meanNsigma_Platform_mean;
+	uint16_t usAVFS_meanNsigma_Platform_sigma;
+	uint32_t  ulGB_VDROOP_TABLE_CKSOFF_a0;
+	uint32_t  ulGB_VDROOP_TABLE_CKSOFF_a1;
+	uint32_t  ulGB_VDROOP_TABLE_CKSOFF_a2;
+	uint32_t  ulGB_VDROOP_TABLE_CKSON_a0;
+	uint32_t  ulGB_VDROOP_TABLE_CKSON_a1;
+	uint32_t  ulGB_VDROOP_TABLE_CKSON_a2;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSOFF_m1;
+	uint16_t  usAVFSGB_FUSE_TABLE_CKSOFF_m2;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSOFF_b;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSON_m1;
+	uint16_t  usAVFSGB_FUSE_TABLE_CKSON_m2;
+	uint32_t  ulAVFSGB_FUSE_TABLE_CKSON_b;
+	uint16_t  usMaxVoltage_0_25mv;
+	uint8_t  ucEnableGB_VDROOP_TABLE_CKSOFF;
+	uint8_t  ucEnableGB_VDROOP_TABLE_CKSON;
+	uint8_t  ucEnableGB_FUSE_TABLE_CKSOFF;
+	uint8_t  ucEnableGB_FUSE_TABLE_CKSON;
+	uint16_t usPSM_Age_ComFactor;
+	uint8_t  ucEnableApplyAVFS_CKS_OFF_Voltage;
+	uint8_t  ucReserved;
+};
+
 extern bool atomctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment);
 extern int atomctrl_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
 extern uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr);
@@ -276,7 +305,10 @@
 extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 								uint8_t level);
 extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
-				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
+				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage);
 extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table);
+
+extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param);
+
 #endif
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index d27e8c4..5d0f655 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -1302,7 +1302,7 @@
 			table->Smio[count] |=
 				data->mvdd_voltage_table.entries[count].smio_low;
 		}
-		table->SmioMask2 = data->vddci_voltage_table.mask_low;
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
 
 		CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount);
 	}
@@ -4489,6 +4489,7 @@
 	data->vdd_ci_control = TONGA_VOLTAGE_CONTROL_NONE;
 	data->vdd_gfx_control = TONGA_VOLTAGE_CONTROL_NONE;
 	data->mvdd_control = TONGA_VOLTAGE_CONTROL_NONE;
+	data->force_pcie_gen = PP_PCIEGenInvalid;
 
 	if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr,
 				VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) {
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
index 671fdb4..dccc859f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
@@ -302,7 +302,7 @@
 			(((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset));
 
 		if (0 != powerplay_table->usPPMTableOffset) {
-			if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) {
+			if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) {
 				phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_EnablePlatformPowerManagement);
 			}
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 28f5714..77e8e33 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -411,6 +411,8 @@
 	uint8_t  ucVr_I2C_Line;
 	uint8_t  ucPlx_I2C_address;
 	uint8_t  ucPlx_I2C_Line;
+	uint32_t usBoostPowerLimit;
+	uint8_t  ucCKS_LDO_REFSEL;
 };
 
 struct phm_ppm_table {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
index 0c6a413..b8f4b73 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
@@ -27,6 +27,7 @@
 
 #pragma pack(push, 1)
 
+#define PPSMC_MSG_SetGBDroopSettings          ((uint16_t) 0x305)
 
 #define PPSMC_SWSTATE_FLAG_DC                           0x01
 #define PPSMC_SWSTATE_FLAG_UVD                          0x02
@@ -391,6 +392,8 @@
 #define PPSMC_MSG_SetGpuPllDfsForSclk         ((uint16_t) 0x300)
 #define PPSMC_MSG_Didt_Block_Function		  ((uint16_t) 0x301)
 
+#define PPSMC_MSG_SetVBITimeout               ((uint16_t) 0x306)
+
 #define PPSMC_MSG_SecureSRBMWrite             ((uint16_t) 0x600)
 #define PPSMC_MSG_SecureSRBMRead              ((uint16_t) 0x601)
 #define PPSMC_MSG_SetAddress                  ((uint16_t) 0x800)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
index 3bd5e69..3df5de2 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h
@@ -26,3 +26,4 @@
 extern int acpi_pcie_perf_request(void *device,
 						uint8_t perf_req,
 						bool advertise);
+extern bool acpi_atcs_notify_pcie_device_ready(void *device);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74.h b/drivers/gpu/drm/amd/powerplay/inc/smu74.h
index 1a12d85..fd10a9f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74.h
@@ -34,6 +34,30 @@
 #define SMU__NUM_LCLK_DPM_LEVELS 8
 #define SMU__NUM_PCIE_DPM_LEVELS 8
 
+#define EXP_M1  35
+#define EXP_M2  92821
+#define EXP_B   66629747
+
+#define EXP_M1_1  365
+#define EXP_M2_1  658700
+#define EXP_B_1   305506134
+
+#define EXP_M1_2  189
+#define EXP_M2_2  379692
+#define EXP_B_2   194609469
+
+#define EXP_M1_3  99
+#define EXP_M2_3  217915
+#define EXP_B_3   122255994
+
+#define EXP_M1_4  51
+#define EXP_M2_4  122643
+#define EXP_B_4   74893384
+
+#define EXP_M1_5  423
+#define EXP_M2_5  1103326
+#define EXP_B_5   728122621
+
 enum SID_OPTION {
 	SID_OPTION_HI,
 	SID_OPTION_LO,
@@ -548,20 +572,20 @@
 	uint32_t CacConfigTable;
 	uint32_t CacStatusTable;
 
-
 	uint32_t mcRegisterTable;
 
-
 	uint32_t mcArbDramTimingTable;
 
-
-
-
 	uint32_t PmFuseTable;
 	uint32_t Globals;
 	uint32_t ClockStretcherTable;
 	uint32_t VftTable;
-	uint32_t Reserved[21];
+	uint32_t Reserved1;
+	uint32_t AvfsTable;
+	uint32_t AvfsCksOffGbvTable;
+	uint32_t AvfsMeanNSigma;
+	uint32_t AvfsSclkOffsetTable;
+	uint32_t Reserved[16];
 	uint32_t Signature;
 };
 
@@ -701,8 +725,6 @@
 struct SMU_ClockStretcherDataTableEntry {
 	uint8_t minVID;
 	uint8_t maxVID;
-
-
 	uint16_t setting;
 };
 typedef struct SMU_ClockStretcherDataTableEntry SMU_ClockStretcherDataTableEntry;
@@ -769,6 +791,43 @@
 typedef struct VFT_TABLE_t VFT_TABLE_t;
 
 
+/* Total margin, root mean square of Fmax + DC + Platform */
+struct AVFS_Margin_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_Margin_t AVFS_Margin_t;
+
+#define BTCGB_VDROOP_TABLE_MAX_ENTRIES 2
+#define AVFSGB_VDROOP_TABLE_MAX_ENTRIES 2
+
+struct GB_VDROOP_TABLE_t {
+	int32_t a0;
+	int32_t a1;
+	int32_t a2;
+	uint32_t spare;
+};
+typedef struct GB_VDROOP_TABLE_t GB_VDROOP_TABLE_t;
+
+struct AVFS_CksOff_Gbv_t {
+	VFT_CELL_t Cell[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_CksOff_Gbv_t AVFS_CksOff_Gbv_t;
+
+struct AVFS_meanNsigma_t {
+	uint32_t Aconstant[3];
+	uint16_t DC_tol_sigma;
+	uint16_t Platform_mean;
+	uint16_t Platform_sigma;
+	uint16_t PSM_Age_CompFactor;
+	uint8_t  Static_Voltage_Offset[NUM_VFT_COLUMNS];
+};
+typedef struct AVFS_meanNsigma_t AVFS_meanNsigma_t;
+
+struct AVFS_Sclk_Offset_t {
+	uint16_t Sclk_Offset[8];
+};
+typedef struct AVFS_Sclk_Offset_t AVFS_Sclk_Offset_t;
+
 #endif
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
index 0dfe823..899d6d8 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
@@ -223,6 +223,16 @@
 
 typedef struct SMU74_Discrete_StateInfo SMU74_Discrete_StateInfo;
 
+struct SMU_QuadraticCoeffs {
+	int32_t m1;
+	uint32_t b;
+
+	int16_t m2;
+	uint8_t m1_shift;
+	uint8_t m2_shift;
+};
+typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
+
 struct SMU74_Discrete_DpmTable {
 
 	SMU74_PIDController                  GraphicsPIDController;
@@ -258,7 +268,15 @@
 	uint8_t                             ThermOutPolarity;
 	uint8_t                             ThermOutMode;
 	uint8_t                             BootPhases;
-	uint32_t                            Reserved[4];
+
+	uint8_t                             VRHotLevel;
+	uint8_t                             LdoRefSel;
+	uint8_t                             Reserved1[2];
+	uint16_t                            FanStartTemperature;
+	uint16_t                            FanStopTemperature;
+	uint16_t                            MaxVoltage;
+	uint16_t                            Reserved2;
+	uint32_t                            Reserved[1];
 
 	SMU74_Discrete_GraphicsLevel        GraphicsLevel[SMU74_MAX_LEVELS_GRAPHICS];
 	SMU74_Discrete_MemoryLevel          MemoryACPILevel;
@@ -347,6 +365,8 @@
 
 	uint32_t                            CurrSclkPllRange;
 	sclkFcwRange_t                      SclkFcwRangeTable[NUM_SCLK_RANGE];
+	GB_VDROOP_TABLE_t                   BTCGB_VDROOP_TABLE[BTCGB_VDROOP_TABLE_MAX_ENTRIES];
+	SMU_QuadraticCoeffs                 AVFSGB_VDROOP_TABLE[AVFSGB_VDROOP_TABLE_MAX_ENTRIES];
 };
 
 typedef struct SMU74_Discrete_DpmTable SMU74_Discrete_DpmTable;
@@ -550,16 +570,6 @@
 
 typedef struct SMU7_AcpiScoreboard SMU7_AcpiScoreboard;
 
-struct SMU_QuadraticCoeffs {
-	int32_t m1;
-	uint32_t b;
-
-	int16_t m2;
-	uint8_t m1_shift;
-	uint8_t m2_shift;
-};
-typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs;
-
 struct SMU74_Discrete_PmFuses {
 	uint8_t BapmVddCVidHiSidd[8];
 	uint8_t BapmVddCVidLoSidd[8];
@@ -821,6 +831,17 @@
 #define DB_PCC_SHIFT 26 
 #define DB_EDC_SHIFT 27
 
+#define BTCGB0_Vdroop_Enable_MASK  0x1
+#define BTCGB1_Vdroop_Enable_MASK  0x2
+#define AVFSGB0_Vdroop_Enable_MASK 0x4
+#define AVFSGB1_Vdroop_Enable_MASK 0x8
+
+#define BTCGB0_Vdroop_Enable_SHIFT  0
+#define BTCGB1_Vdroop_Enable_SHIFT  1
+#define AVFSGB0_Vdroop_Enable_SHIFT 2
+#define AVFSGB1_Vdroop_Enable_SHIFT 3
+
+
 #pragma pack(pop)
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index 043b6ac..5dba7c5 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -52,19 +52,18 @@
 static const SMU74_Discrete_GraphicsLevel avfs_graphics_level_polaris10[8] = {
 	/*  Min      pcie   DeepSleep Activity  CgSpll      CgSpll    CcPwr  CcPwr  Sclk         Enabled      Enabled                       Voltage    Power */
 	/* Voltage, DpmLevel, DivId,  Level,  FuncCntl3,  FuncCntl4,  DynRm, DynRm1 Did, Padding,ForActivity, ForThrottle, UpHyst, DownHyst, DownHyst, Throttle */
-	{ 0x3c0fd047, 0x00, 0x03, 0x1e00, 0x00200410, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x30750000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0xa00fd047, 0x01, 0x04, 0x1e00, 0x00800510, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x409c0000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x0410d047, 0x01, 0x00, 0x1e00, 0x00600410, 0x87020000, 0, 0, 0x0e, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x50c30000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x6810d047, 0x01, 0x00, 0x1e00, 0x00800410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x60ea0000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0xcc10d047, 0x01, 0x00, 0x1e00, 0x00e00410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xe8fd0000, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x3011d047, 0x01, 0x00, 0x1e00, 0x00400510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x70110100, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0x9411d047, 0x01, 0x00, 0x1e00, 0x00a00510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xf8240100, 0, 0, 0, 0, 0, 0, 0 } },
-	{ 0xf811d047, 0x01, 0x00, 0x1e00, 0x00000610, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x80380100, 0, 0, 0, 0, 0, 0, 0 } }
+	{ 0x100ea446, 0x00, 0x03, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x30750000, 0x3000, 0, 0x2600, 0, 0, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } },
+	{ 0x400ea446, 0x01, 0x04, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x409c0000, 0x2000, 0, 0x1e00, 1, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } },
+	{ 0x740ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x50c30000, 0x2800, 0, 0x2000, 1, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } },
+	{ 0xa40ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x60ea0000, 0x3000, 0, 0x2600, 1, 1, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } },
+	{ 0xd80ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x70110100, 0x3800, 0, 0x2c00, 1, 1, 0x0004, 0x1203, 0xffff, 0x3600, 0xc9e2, 0x2e00 } },
+	{ 0x3c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x80380100, 0x2000, 0, 0x1e00, 2, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } },
+	{ 0x6c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x905f0100, 0x2400, 0, 0x1e00, 2, 1, 0x0004, 0x8901, 0xffff, 0x2300, 0x314c, 0x1d00 } },
+	{ 0xa00fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0xa0860100, 0x2800, 0, 0x2000, 2, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } }
 };
 
 static const SMU74_Discrete_MemoryLevel avfs_memory_level_polaris10 =
-	{0x50140000, 0x50140000, 0x00320000, 0x00, 0x00,
-	 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x0000, 0x00, 0x00};
+	{0x100ea446, 0, 0x30750000, 0x01, 0x01, 0x01, 0x00, 0x00, 0x64, 0x00, 0x00, 0x1f00, 0x00, 0x00};
 
 /**
 * Set the address for reading/writing the SMC SRAM space.
@@ -219,6 +218,18 @@
 	&& (0x20100 <= cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMC_PC_C)));
 }
 
+static bool polaris10_is_hw_avfs_present(struct pp_smumgr *smumgr)
+{
+	uint32_t efuse;
+
+	efuse = cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMU_EFUSE_0 + (49*4));
+	efuse &= 0x00000001;
+	if (efuse)
+		return true;
+
+	return false;
+}
+
 /**
 * Send a message to the SMC, and wait for its response.
 *
@@ -228,21 +239,27 @@
 */
 int polaris10_send_msg_to_smc(struct pp_smumgr *smumgr, uint16_t msg)
 {
+	int ret;
+
 	if (!polaris10_is_smc_ram_running(smumgr))
 		return -1;
 
+
 	SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0);
 
-	if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP))
-		printk("Failed to send Previous Message.\n");
+	ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP);
 
+	if (ret != 1)
+		printk("\n failed to send pre message %x ret is %d \n",  msg, ret);
 
 	cgs_write_register(smumgr->device, mmSMC_MESSAGE_0, msg);
 
 	SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0);
 
-	if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP))
-		printk("Failed to send Message.\n");
+	ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP);
+
+	if (ret != 1)
+		printk("\n failed to send message %x ret is %d \n",  msg, ret);
 
 	return 0;
 }
@@ -953,6 +970,11 @@
 		(cgs_handle_t)smu_data->smu_buffer.handle);
 		return -1;);
 
+	if (polaris10_is_hw_avfs_present(smumgr))
+		smu_data->avfs.avfs_btc_status = AVFS_BTC_BOOT;
+	else
+		smu_data->avfs.avfs_btc_status = AVFS_BTC_NOTSUPPORTED;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
index 39802c0..3d34fc4 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c
@@ -266,9 +266,10 @@
 		if (!ret)
 			ret = atmel_hlcdc_check_endpoint(dev, &ep);
 
-		of_node_put(ep_np);
-		if (ret)
+		if (ret) {
+			of_node_put(ep_np);
 			return ret;
+		}
 	}
 
 	for_each_endpoint_of_node(dev->dev->of_node, ep_np) {
@@ -276,9 +277,10 @@
 		if (!ret)
 			ret = atmel_hlcdc_attach_endpoint(dev, &ep);
 
-		of_node_put(ep_np);
-		if (ret)
+		if (ret) {
+			of_node_put(ep_np);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index aef3ca8..016c191 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -339,6 +339,8 @@
 
 		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff,
 					     factor_reg);
+	} else {
+		atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index c204ef3..9bb99e2 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1296,14 +1296,39 @@
  */
 void drm_atomic_legacy_backoff(struct drm_atomic_state *state)
 {
+	struct drm_device *dev = state->dev;
+	unsigned crtc_mask = 0;
+	struct drm_crtc *crtc;
 	int ret;
+	bool global = false;
+
+	drm_for_each_crtc(crtc, dev) {
+		if (crtc->acquire_ctx != state->acquire_ctx)
+			continue;
+
+		crtc_mask |= drm_crtc_mask(crtc);
+		crtc->acquire_ctx = NULL;
+	}
+
+	if (WARN_ON(dev->mode_config.acquire_ctx == state->acquire_ctx)) {
+		global = true;
+
+		dev->mode_config.acquire_ctx = NULL;
+	}
 
 retry:
 	drm_modeset_backoff(state->acquire_ctx);
 
-	ret = drm_modeset_lock_all_ctx(state->dev, state->acquire_ctx);
+	ret = drm_modeset_lock_all_ctx(dev, state->acquire_ctx);
 	if (ret)
 		goto retry;
+
+	drm_for_each_crtc(crtc, dev)
+		if (drm_crtc_mask(crtc) & crtc_mask)
+			crtc->acquire_ctx = state->acquire_ctx;
+
+	if (global)
+		dev->mode_config.acquire_ctx = state->acquire_ctx;
 }
 EXPORT_SYMBOL(drm_atomic_legacy_backoff);
 
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f6223f9..7f9901b 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -31,7 +31,6 @@
 #include "exynos_drm_plane.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
-#include "exynos_drm_fbdev.h"
 #include "exynos_drm_iommu.h"
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 468498e..4c1fb3f 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -34,7 +34,7 @@
 
 struct exynos_dp_device {
 	struct drm_encoder         encoder;
-	struct drm_connector       connector;
+	struct drm_connector       *connector;
 	struct drm_bridge          *ptn_bridge;
 	struct drm_device          *drm_dev;
 	struct device              *dev;
@@ -70,7 +70,7 @@
 static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data)
 {
 	struct exynos_dp_device *dp = to_dp(plat_data);
-	struct drm_connector *connector = &dp->connector;
+	struct drm_connector *connector = dp->connector;
 	struct drm_display_mode *mode;
 	int num_modes = 0;
 
@@ -103,6 +103,7 @@
 	int ret;
 
 	drm_connector_register(connector);
+	dp->connector = connector;
 
 	/* Pre-empt DP connector creation if there's a bridge */
 	if (dp->ptn_bridge) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index 011211e..edbd98f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -15,7 +15,6 @@
 #include <drm/drmP.h>
 #include "exynos_drm_drv.h"
 #include "exynos_drm_crtc.h"
-#include "exynos_drm_fbdev.h"
 
 static LIST_HEAD(exynos_drm_subdrv_list);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 3efe1aa..d472164 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -30,7 +30,6 @@
 
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
-#include "exynos_drm_fbdev.h"
 #include "exynos_drm_crtc.h"
 #include "exynos_drm_plane.h"
 #include "exynos_drm_iommu.h"
@@ -120,7 +119,6 @@
 	.timing_base = 0x0,
 	.has_clksel = 1,
 	.has_limited_fmt = 1,
-	.has_hw_trigger = 1,
 };
 
 static struct fimd_driver_data exynos3_fimd_driver_data = {
@@ -171,14 +169,11 @@
 	.lcdblk_vt_shift = 24,
 	.lcdblk_bypass_shift = 15,
 	.lcdblk_mic_bypass_shift = 11,
-	.trg_type = I80_HW_TRG,
 	.has_shadowcon = 1,
 	.has_vidoutcon = 1,
 	.has_vtsel = 1,
 	.has_mic_bypass = 1,
 	.has_dp_clk = 1,
-	.has_hw_trigger = 1,
-	.has_trigger_per_te = 1,
 };
 
 struct fimd_context {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 4935523..8564c3d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -48,13 +48,13 @@
 
 /* registers for base address */
 #define G2D_SRC_BASE_ADDR		0x0304
-#define G2D_SRC_STRIDE_REG		0x0308
+#define G2D_SRC_STRIDE			0x0308
 #define G2D_SRC_COLOR_MODE		0x030C
 #define G2D_SRC_LEFT_TOP		0x0310
 #define G2D_SRC_RIGHT_BOTTOM		0x0314
 #define G2D_SRC_PLANE2_BASE_ADDR	0x0318
 #define G2D_DST_BASE_ADDR		0x0404
-#define G2D_DST_STRIDE_REG		0x0408
+#define G2D_DST_STRIDE			0x0408
 #define G2D_DST_COLOR_MODE		0x040C
 #define G2D_DST_LEFT_TOP		0x0410
 #define G2D_DST_RIGHT_BOTTOM		0x0414
@@ -563,7 +563,7 @@
 
 	switch (reg_offset) {
 	case G2D_SRC_BASE_ADDR:
-	case G2D_SRC_STRIDE_REG:
+	case G2D_SRC_STRIDE:
 	case G2D_SRC_COLOR_MODE:
 	case G2D_SRC_LEFT_TOP:
 	case G2D_SRC_RIGHT_BOTTOM:
@@ -573,7 +573,7 @@
 		reg_type = REG_TYPE_SRC_PLANE2;
 		break;
 	case G2D_DST_BASE_ADDR:
-	case G2D_DST_STRIDE_REG:
+	case G2D_DST_STRIDE:
 	case G2D_DST_COLOR_MODE:
 	case G2D_DST_LEFT_TOP:
 	case G2D_DST_RIGHT_BOTTOM:
@@ -968,8 +968,8 @@
 			} else
 				buf_info->types[reg_type] = BUF_TYPE_GEM;
 			break;
-		case G2D_SRC_STRIDE_REG:
-		case G2D_DST_STRIDE_REG:
+		case G2D_SRC_STRIDE:
+		case G2D_DST_STRIDE:
 			if (for_addr)
 				goto err;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 55f1d37..77f12c0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -242,7 +242,7 @@
 	    state->v_ratio == (1 << 15))
 		height_ok = true;
 
-	if (width_ok & height_ok)
+	if (width_ok && height_ok)
 		return 0;
 
 	DRM_DEBUG_KMS("scaling mode is not supported");
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3269033..1035468 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2365,16 +2365,16 @@
 		task = get_pid_task(file->pid, PIDTYPE_PID);
 		if (!task) {
 			ret = -ESRCH;
-			goto out_put;
+			goto out_unlock;
 		}
 		seq_printf(m, "\nproc: %s\n", task->comm);
 		put_task_struct(task);
 		idr_for_each(&file_priv->context_idr, per_file_ctx,
 			     (void *)(unsigned long)m);
 	}
+out_unlock:
 	mutex_unlock(&dev->filelist_mutex);
 
-out_put:
 	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f313b4d..85c4deb 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -512,6 +512,10 @@
 				DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
 				WARN_ON(!IS_SKYLAKE(dev) &&
 					!IS_KABYLAKE(dev));
+			} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
+				dev_priv->pch_type = PCH_KBP;
+				DRM_DEBUG_KMS("Found KabyPoint PCH\n");
+				WARN_ON(!IS_KABYLAKE(dev));
 			} else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) ||
 				   (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) ||
 				   ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) &&
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7c334e9..bc3f2e6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -990,6 +990,7 @@
 	PCH_CPT,	/* Cougarpoint PCH */
 	PCH_LPT,	/* Lynxpoint PCH */
 	PCH_SPT,        /* Sunrisepoint PCH */
+	PCH_KBP,        /* Kabypoint PCH */
 	PCH_NOP,
 };
 
@@ -2600,6 +2601,15 @@
 
 #define IS_BXT_REVID(p, since, until) (IS_BROXTON(p) && IS_REVID(p, since, until))
 
+#define KBL_REVID_A0		0x0
+#define KBL_REVID_B0		0x1
+#define KBL_REVID_C0		0x2
+#define KBL_REVID_D0		0x3
+#define KBL_REVID_E0		0x4
+
+#define IS_KBL_REVID(p, since, until) \
+	(IS_KABYLAKE(p) && IS_REVID(p, since, until))
+
 /*
  * The genX designation typically refers to the render engine, so render
  * capability related checks should use IS_GEN, while display and other checks
@@ -2708,11 +2718,13 @@
 #define INTEL_PCH_LPT_LP_DEVICE_ID_TYPE		0x9c00
 #define INTEL_PCH_SPT_DEVICE_ID_TYPE		0xA100
 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE		0x9D00
+#define INTEL_PCH_KBP_DEVICE_ID_TYPE		0xA200
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
 #define INTEL_PCH_P3X_DEVICE_ID_TYPE		0x7000
 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE		0x2900 /* qemu q35 has 2918 */
 
 #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type)
+#define HAS_PCH_KBP(dev) (INTEL_PCH_TYPE(dev) == PCH_KBP)
 #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT)
 #define HAS_PCH_LPT(dev) (INTEL_PCH_TYPE(dev) == PCH_LPT)
 #define HAS_PCH_LPT_LP(dev) (__I915__(dev)->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE)
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 425e721..6657146 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -40,7 +40,7 @@
 	if (!mutex_is_locked(mutex))
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
 	return mutex->owner == task;
 #else
 	/* Since UP may be pre-empted, we cannot assume that we own the lock */
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index b7ce963..44004e3 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -55,8 +55,10 @@
 		return -ENODEV;
 
 	/* See the comment at the drm_mm_init() call for more about this check.
-	 * WaSkipStolenMemoryFirstPage:bdw,chv (incomplete) */
-	if (INTEL_INFO(dev_priv)->gen == 8 && start < 4096)
+	 * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete)
+	 */
+	if (start < 4096 && (IS_GEN8(dev_priv) ||
+			     IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)))
 		start = 4096;
 
 	mutex_lock(&dev_priv->mm.stolen_lock);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2f6fd33..aab47f7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2471,7 +2471,7 @@
 			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (HAS_PCH_SPT(dev_priv))
+			if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv))
 				spt_irq_handler(dev, iir);
 			else
 				cpt_irq_handler(dev, iir);
@@ -4661,7 +4661,7 @@
 		dev->driver->disable_vblank = gen8_disable_vblank;
 		if (IS_BROXTON(dev))
 			dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup;
-		else if (HAS_PCH_SPT(dev))
+		else if (HAS_PCH_SPT(dev) || HAS_PCH_KBP(dev))
 			dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup;
 		else
 			dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b407411..3fcf7dd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -220,6 +220,9 @@
 #define   ECOCHK_PPGTT_WT_HSW		(0x2<<3)
 #define   ECOCHK_PPGTT_WB_HSW		(0x3<<3)
 
+#define GEN8_CONFIG0			_MMIO(0xD00)
+#define  GEN9_DEFAULT_FIXES		(1 << 3 | 1 << 2 | 1 << 1)
+
 #define GAC_ECO_BITS			_MMIO(0x14090)
 #define   ECOBITS_SNB_BIT		(1<<13)
 #define   ECOBITS_PPGTT_CACHE64B	(3<<8)
@@ -1669,6 +1672,9 @@
 
 #define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
 
+#define GAMT_CHKN_BIT_REG	_MMIO(0x4ab8)
+#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1<<28)
+
 #if 0
 #define PRB0_TAIL	_MMIO(0x2030)
 #define PRB0_HEAD	_MMIO(0x2034)
@@ -1804,6 +1810,10 @@
 #define   GEN9_IZ_HASHING_MASK(slice)			(0x3 << ((slice) * 2))
 #define   GEN9_IZ_HASHING(slice, val)			((val) << ((slice) * 2))
 
+/* chicken reg for WaConextSwitchWithConcurrentTLBInvalidate */
+#define GEN9_CSFE_CHICKEN1_RCS _MMIO(0x20D4)
+#define   GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE (1 << 2)
+
 /* WaClearTdlStateAckDirtyBits */
 #define GEN8_STATE_ACK		_MMIO(0x20F0)
 #define GEN9_STATE_ACK_SLICE1	_MMIO(0x20F8)
@@ -2200,6 +2210,8 @@
 #define ILK_DPFC_STATUS		_MMIO(0x43210)
 #define ILK_DPFC_FENCE_YOFF	_MMIO(0x43218)
 #define ILK_DPFC_CHICKEN	_MMIO(0x43224)
+#define   ILK_DPFC_DISABLE_DUMMY0 (1<<8)
+#define   ILK_DPFC_NUKE_ON_ANY_MODIFICATION	(1<<23)
 #define ILK_FBC_RT_BASE		_MMIO(0x2128)
 #define   ILK_FBC_RT_VALID	(1<<0)
 #define   SNB_FBC_FRONT_BUFFER	(1<<1)
@@ -6031,6 +6043,7 @@
 #define CHICKEN_PAR1_1		_MMIO(0x42080)
 #define  DPA_MASK_VBLANK_SRD	(1 << 15)
 #define  FORCE_ARB_IDLE_PLANES	(1 << 14)
+#define  SKL_EDP_PSR_FIX_RDWRAP	(1 << 3)
 
 #define _CHICKEN_PIPESL_1_A	0x420b0
 #define _CHICKEN_PIPESL_1_B	0x420b4
@@ -6039,6 +6052,7 @@
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
 
 #define DISP_ARB_CTL	_MMIO(0x45000)
+#define  DISP_FBC_MEMORY_WAKE		(1<<31)
 #define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
 #define  DISP_FBC_WM_DIS		(1<<15)
 #define DISP_ARB_CTL2	_MMIO(0x45004)
@@ -6052,6 +6066,9 @@
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
 #define  RESET_PCH_HANDSHAKE_ENABLE	(1<<4)
 
+#define GEN8_CHICKEN_DCPR_1		_MMIO(0x46430)
+#define   MASK_WAKEMEM			(1<<13)
+
 #define SKL_DFSM			_MMIO(0x51000)
 #define SKL_DFSM_CDCLK_LIMIT_MASK	(3 << 23)
 #define SKL_DFSM_CDCLK_LIMIT_675	(0 << 23)
@@ -6069,6 +6086,7 @@
 #define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
 
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
+#define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
 #define GEN8_CS_CHICKEN1		_MMIO(0x2580)
 
 /* GEN7 chicken */
@@ -6076,6 +6094,7 @@
 # define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
 # define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
 #define COMMON_SLICE_CHICKEN2			_MMIO(0x7014)
+# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8)
 # define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1<<0)
 
 #define HIZ_CHICKEN					_MMIO(0x7018)
@@ -6921,6 +6940,7 @@
 #define    EDRAM_SETS_IDX(cap)			(((cap) >> 8) & 0x3)
 
 #define GEN6_UCGCTL1				_MMIO(0x9400)
+# define GEN6_GAMUNIT_CLOCK_GATE_DISABLE		(1 << 22)
 # define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE		(1 << 16)
 # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE		(1 << 5)
 # define GEN6_CSUNIT_CLOCK_GATE_DISABLE			(1 << 7)
@@ -6937,6 +6957,7 @@
 
 #define GEN7_UCGCTL4				_MMIO(0x940c)
 #define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)
+#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1<<14)
 
 #define GEN6_RCGCTL1				_MMIO(0x9410)
 #define GEN6_RCGCTL2				_MMIO(0x9414)
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index a34c23e..2b3b428 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -41,16 +41,22 @@
  * be moved to FW_FAILED.
  */
 
+#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin"
+MODULE_FIRMWARE(I915_CSR_KBL);
+#define KBL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 1)
+
 #define I915_CSR_SKL "i915/skl_dmc_ver1.bin"
+MODULE_FIRMWARE(I915_CSR_SKL);
+#define SKL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 23)
+
 #define I915_CSR_BXT "i915/bxt_dmc_ver1.bin"
+MODULE_FIRMWARE(I915_CSR_BXT);
+#define BXT_CSR_VERSION_REQUIRED	CSR_VERSION(1, 7)
 
 #define FIRMWARE_URL  "https://01.org/linuxgraphics/intel-linux-graphics-firmwares"
 
-MODULE_FIRMWARE(I915_CSR_SKL);
-MODULE_FIRMWARE(I915_CSR_BXT);
 
-#define SKL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 23)
-#define BXT_CSR_VERSION_REQUIRED	CSR_VERSION(1, 7)
+
 
 #define CSR_MAX_FW_SIZE			0x2FFF
 #define CSR_DEFAULT_FW_OFFSET		0xFFFFFFFF
@@ -169,12 +175,10 @@
 	char substepping;
 };
 
-/*
- * Kabylake derivated from Skylake H0, so SKL H0
- * is the right firmware for KBL A0 (revid 0).
- */
 static const struct stepping_info kbl_stepping_info[] = {
-	{'H', '0'}, {'I', '0'}
+	{'A', '0'}, {'B', '0'}, {'C', '0'},
+	{'D', '0'}, {'E', '0'}, {'F', '0'},
+	{'G', '0'}, {'H', '0'}, {'I', '0'},
 };
 
 static const struct stepping_info skl_stepping_info[] = {
@@ -298,7 +302,9 @@
 
 	csr->version = css_header->version;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_KABYLAKE(dev_priv)) {
+		required_min_version = KBL_CSR_VERSION_REQUIRED;
+	} else if (IS_SKYLAKE(dev_priv)) {
 		required_min_version = SKL_CSR_VERSION_REQUIRED;
 	} else if (IS_BROXTON(dev_priv)) {
 		required_min_version = BXT_CSR_VERSION_REQUIRED;
@@ -446,7 +452,9 @@
 	if (!HAS_CSR(dev_priv))
 		return;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_KABYLAKE(dev_priv))
+		csr->fw_path = I915_CSR_KBL;
+	else if (IS_SKYLAKE(dev_priv))
 		csr->fw_path = I915_CSR_SKL;
 	else if (IS_BROXTON(dev_priv))
 		csr->fw_path = I915_CSR_BXT;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 56a1637..3074c56 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8447,16 +8447,16 @@
 	tmp |= FDI_MPHY_IOSFSB_RESET_CTL;
 	I915_WRITE(SOUTH_CHICKEN2, tmp);
 
-	if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) &
-			       FDI_MPHY_IOSFSB_RESET_STATUS, 100))
+	if (wait_for_us(I915_READ(SOUTH_CHICKEN2) &
+			FDI_MPHY_IOSFSB_RESET_STATUS, 100))
 		DRM_ERROR("FDI mPHY reset assert timeout\n");
 
 	tmp = I915_READ(SOUTH_CHICKEN2);
 	tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL;
 	I915_WRITE(SOUTH_CHICKEN2, tmp);
 
-	if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) &
-				FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
+	if (wait_for_us((I915_READ(SOUTH_CHICKEN2) &
+			 FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
 		DRM_ERROR("FDI mPHY reset de-assert timeout\n");
 }
 
@@ -9440,8 +9440,8 @@
 		val |= LCPLL_CD_SOURCE_FCLK;
 		I915_WRITE(LCPLL_CTL, val);
 
-		if (wait_for_atomic_us(I915_READ(LCPLL_CTL) &
-				       LCPLL_CD_SOURCE_FCLK_DONE, 1))
+		if (wait_for_us(I915_READ(LCPLL_CTL) &
+				LCPLL_CD_SOURCE_FCLK_DONE, 1))
 			DRM_ERROR("Switching to FCLK failed\n");
 
 		val = I915_READ(LCPLL_CTL);
@@ -9514,8 +9514,8 @@
 		val &= ~LCPLL_CD_SOURCE_FCLK;
 		I915_WRITE(LCPLL_CTL, val);
 
-		if (wait_for_atomic_us((I915_READ(LCPLL_CTL) &
-					LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+		if (wait_for_us((I915_READ(LCPLL_CTL) &
+				 LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
 			DRM_ERROR("Switching back to LCPLL failed\n");
 	}
 
@@ -11997,6 +11997,12 @@
 		ret = intel_color_check(crtc, crtc_state);
 		if (ret)
 			return ret;
+
+		/*
+		 * Changing color management on Intel hardware is
+		 * handled as part of planes update.
+		 */
+		crtc_state->planes_changed = true;
 	}
 
 	ret = 0;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index ffe5f84..891107f 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -663,7 +663,7 @@
 		done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
 					  msecs_to_jiffies_timeout(10));
 	else
-		done = wait_for_atomic(C, 10) == 0;
+		done = wait_for(C, 10) == 0;
 	if (!done)
 		DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n",
 			  has_aux_irq);
@@ -4645,7 +4645,7 @@
 
 	intel_dp->detect_done = false;
 
-	if (intel_connector->detect_edid)
+	if (is_edp(intel_dp) || intel_connector->detect_edid)
 		return connector_status_connected;
 	else
 		return connector_status_disconnected;
@@ -4899,13 +4899,15 @@
 
 void intel_dp_encoder_reset(struct drm_encoder *encoder)
 {
-	struct intel_dp *intel_dp;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+	if (!HAS_DDI(dev_priv))
+		intel_dp->DP = I915_READ(intel_dp->output_reg);
 
 	if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP)
 		return;
 
-	intel_dp = enc_to_intel_dp(encoder);
-
 	pps_lock(intel_dp);
 
 	/*
@@ -4977,9 +4979,6 @@
 	intel_display_power_get(dev_priv, power_domain);
 
 	if (long_hpd) {
-		/* indicate that we need to restart link training */
-		intel_dp->train_set_valid = false;
-
 		intel_dp_long_pulse(intel_dp->attached_connector);
 		if (intel_dp->is_mst)
 			ret = IRQ_HANDLED;
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 0b8eefc..60fb39c 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -85,8 +85,7 @@
 intel_dp_reset_link_train(struct intel_dp *intel_dp,
 			uint8_t dp_train_pat)
 {
-	if (!intel_dp->train_set_valid)
-		memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
+	memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
 	intel_dp_set_signal_levels(intel_dp);
 	return intel_dp_set_link_train(intel_dp, dp_train_pat);
 }
@@ -161,23 +160,6 @@
 			break;
 		}
 
-		/*
-		 * if we used previously trained voltage and pre-emphasis values
-		 * and we don't get clock recovery, reset link training values
-		 */
-		if (intel_dp->train_set_valid) {
-			DRM_DEBUG_KMS("clock recovery not ok, reset");
-			/* clear the flag as we are not reusing train set */
-			intel_dp->train_set_valid = false;
-			if (!intel_dp_reset_link_train(intel_dp,
-						       DP_TRAINING_PATTERN_1 |
-						       DP_LINK_SCRAMBLING_DISABLE)) {
-				DRM_ERROR("failed to enable link training\n");
-				return;
-			}
-			continue;
-		}
-
 		/* Check to see if we've tried the max voltage */
 		for (i = 0; i < intel_dp->lane_count; i++)
 			if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0)
@@ -284,7 +266,6 @@
 		/* Make sure clock is still ok */
 		if (!drm_dp_clock_recovery_ok(link_status,
 					      intel_dp->lane_count)) {
-			intel_dp->train_set_valid = false;
 			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp,
 						training_pattern |
@@ -301,7 +282,6 @@
 
 		/* Try 5 times, then try clock recovery if that fails */
 		if (tries > 5) {
-			intel_dp->train_set_valid = false;
 			intel_dp_link_training_clock_recovery(intel_dp);
 			intel_dp_set_link_train(intel_dp,
 						training_pattern |
@@ -322,10 +302,8 @@
 
 	intel_dp_set_idle_link_train(intel_dp);
 
-	if (channel_eq) {
-		intel_dp->train_set_valid = true;
+	if (channel_eq)
 		DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n");
-	}
 }
 
 void intel_dp_stop_link_train(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index baf6f55..58f60b2 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1377,8 +1377,8 @@
 	I915_WRITE(BXT_PORT_PLL_ENABLE(port), temp);
 	POSTING_READ(BXT_PORT_PLL_ENABLE(port));
 
-	if (wait_for_atomic_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) &
-			PORT_PLL_LOCK), 200))
+	if (wait_for_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) & PORT_PLL_LOCK),
+			200))
 		DRM_ERROR("PLL %d not locked\n", port);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 4a24b00..f7f0f01 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -863,8 +863,6 @@
 	/* This is called before a link training is starterd */
 	void (*prepare_link_retrain)(struct intel_dp *intel_dp);
 
-	bool train_set_valid;
-
 	/* Displayport compliance testing */
 	unsigned long compliance_test_type;
 	unsigned long compliance_test_data;
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index d5a7cfe..647127f 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -824,8 +824,7 @@
 {
 	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	bool enable_by_default = IS_HASWELL(dev_priv) ||
-				 IS_BROADWELL(dev_priv);
+	bool enable_by_default = IS_BROADWELL(dev_priv);
 
 	if (intel_vgpu_active(dev_priv->dev)) {
 		fbc->no_fbc_reason = "VGPU is active";
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 42eac37..7f2d841 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1103,15 +1103,17 @@
 						uint32_t *const batch,
 						uint32_t index)
 {
+	struct drm_i915_private *dev_priv = engine->dev->dev_private;
 	uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
 
 	/*
-	 * WaDisableLSQCROPERFforOCL:skl
+	 * WaDisableLSQCROPERFforOCL:skl,kbl
 	 * This WA is implemented in skl_init_clock_gating() but since
 	 * this batch updates GEN8_L3SQCREG4 with default value we need to
 	 * set this bit here to retain the WA during flush.
 	 */
-	if (IS_SKL_REVID(engine->dev, 0, SKL_REVID_E0))
+	if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) ||
+	    IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
 		l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
 
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
@@ -1273,6 +1275,7 @@
 {
 	int ret;
 	struct drm_device *dev = engine->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
 	/* WaDisableCtxRestoreArbitration:skl,bxt */
@@ -1286,6 +1289,22 @@
 		return ret;
 	index = ret;
 
+	/* WaClearSlmSpaceAtContextSwitch:kbl */
+	/* Actual scratch location is at 128 bytes offset */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
+		uint32_t scratch_addr
+			= engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+
+		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
+		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
+					   PIPE_CONTROL_GLOBAL_GTT_IVB |
+					   PIPE_CONTROL_CS_STALL |
+					   PIPE_CONTROL_QW_WRITE));
+		wa_ctx_emit(batch, index, scratch_addr);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+	}
 	/* Pad to end of cacheline */
 	while (index % CACHELINE_DWORDS)
 		wa_ctx_emit(batch, index, MI_NOOP);
@@ -1687,9 +1706,10 @@
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	struct intel_engine_cs *engine = ringbuf->engine;
 	u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
-	bool vf_flush_wa = false;
+	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 flags = 0;
 	int ret;
+	int len;
 
 	flags |= PIPE_CONTROL_CS_STALL;
 
@@ -1716,9 +1736,21 @@
 		 */
 		if (IS_GEN9(engine->dev))
 			vf_flush_wa = true;
+
+		/* WaForGAMHang:kbl */
+		if (IS_KBL_REVID(request->i915, 0, KBL_REVID_B0))
+			dc_flush_wa = true;
 	}
 
-	ret = intel_ring_begin(request, vf_flush_wa ? 12 : 6);
+	len = 6;
+
+	if (vf_flush_wa)
+		len += 6;
+
+	if (dc_flush_wa)
+		len += 12;
+
+	ret = intel_ring_begin(request, len);
 	if (ret)
 		return ret;
 
@@ -1731,12 +1763,31 @@
 		intel_logical_ring_emit(ringbuf, 0);
 	}
 
+	if (dc_flush_wa) {
+		intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+		intel_logical_ring_emit(ringbuf, PIPE_CONTROL_DC_FLUSH_ENABLE);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+	}
+
 	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
 	intel_logical_ring_emit(ringbuf, flags);
 	intel_logical_ring_emit(ringbuf, scratch_addr);
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, 0);
+
+	if (dc_flush_wa) {
+		intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+		intel_logical_ring_emit(ringbuf, PIPE_CONTROL_CS_STALL);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+		intel_logical_ring_emit(ringbuf, 0);
+	}
+
 	intel_logical_ring_advance(ringbuf);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 99e2603..16e209d3 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -1038,5 +1038,16 @@
 		return -ENODEV;
 	}
 
+	/*
+	 * FIXME On Dell XPS 13 9350 the OpRegion panel type (0) gives us
+	 * low vswing for eDP, whereas the VBT panel type (2) gives us normal
+	 * vswing instead. Low vswing results in some display flickers, so
+	 * let's simply ignore the OpRegion panel type on SKL for now.
+	 */
+	if (IS_SKYLAKE(dev)) {
+		DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1);
+		return -ENODEV;
+	}
+
 	return ret - 1;
 }
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 8357d57..aba9409 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1731,7 +1731,8 @@
 		panel->backlight.set = bxt_set_backlight;
 		panel->backlight.get = bxt_get_backlight;
 		panel->backlight.hz_to_pwm = bxt_hz_to_pwm;
-	} else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv)) {
+	} else if (HAS_PCH_LPT(dev_priv) || HAS_PCH_SPT(dev_priv) ||
+		   HAS_PCH_KBP(dev_priv)) {
 		panel->backlight.setup = lpt_setup_backlight;
 		panel->backlight.enable = lpt_enable_backlight;
 		panel->backlight.disable = lpt_disable_backlight;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index a7ef45d..2863b92 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -54,10 +54,38 @@
 #define INTEL_RC6p_ENABLE			(1<<1)
 #define INTEL_RC6pp_ENABLE			(1<<2)
 
+static void gen9_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */
+	I915_WRITE(CHICKEN_PAR1_1,
+		   I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);
+
+	I915_WRITE(GEN8_CONFIG0,
+		   I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES);
+
+	/* WaEnableChickenDCPR:skl,bxt,kbl */
+	I915_WRITE(GEN8_CHICKEN_DCPR_1,
+		   I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);
+
+	/* WaFbcTurnOffFbcWatermark:skl,bxt,kbl */
+	/* WaFbcWakeMemOn:skl,bxt,kbl */
+	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
+		   DISP_FBC_WM_DIS |
+		   DISP_FBC_MEMORY_WAKE);
+
+	/* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_DISABLE_DUMMY0);
+}
+
 static void bxt_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	gen9_init_clock_gating(dev);
+
 	/* WaDisableSDEUnitClockGating:bxt */
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
@@ -6698,6 +6726,38 @@
 	}
 }
 
+static void kabylake_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	gen9_init_clock_gating(dev);
+
+	/* WaDisableSDEUnitClockGating:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaDisableGamClockGating:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
+			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaFbcNukeOnHostModify:kbl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
+}
+
+static void skylake_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	gen9_init_clock_gating(dev);
+
+	/* WaFbcNukeOnHostModify:skl */
+	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
+		   ILK_DPFC_NUKE_ON_ANY_MODIFICATION);
+}
+
 static void broadwell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -7163,9 +7223,9 @@
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 {
 	if (IS_SKYLAKE(dev_priv))
-		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+		dev_priv->display.init_clock_gating = skylake_init_clock_gating;
 	else if (IS_KABYLAKE(dev_priv))
-		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+		dev_priv->display.init_clock_gating = kabylake_init_clock_gating;
 	else if (IS_BROXTON(dev_priv))
 		dev_priv->display.init_clock_gating = bxt_init_clock_gating;
 	else if (IS_BROADWELL(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 04402bb..68c5af0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -913,24 +913,26 @@
 {
 	struct drm_device *dev = engine->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t tmp;
 	int ret;
 
-	/* WaEnableLbsSlaRetryTimerDecrement:skl */
+	/* WaConextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl */
+	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE));
+
+	/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl */
 	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
 		   GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
 
-	/* WaDisableKillLogic:bxt,skl */
+	/* WaDisableKillLogic:bxt,skl,kbl */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
 		   ECOCHK_DIS_TLB);
 
-	/* WaClearFlowControlGpgpuContextSave:skl,bxt */
-	/* WaDisablePartialInstShootdown:skl,bxt */
+	/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl */
+	/* WaDisablePartialInstShootdown:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
 			  FLOW_CONTROL_ENABLE |
 			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
 
-	/* Syncing dependencies between camera and graphics:skl,bxt */
+	/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
 			  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
 
@@ -952,18 +954,18 @@
 		 */
 	}
 
-	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */
-	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt */
+	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl */
+	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
 			  GEN9_ENABLE_YV12_BUGFIX |
 			  GEN9_ENABLE_GPGPU_PREEMPTION);
 
-	/* Wa4x4STCOptimizationDisable:skl,bxt */
-	/* WaDisablePartialResolveInVc:skl,bxt */
+	/* Wa4x4STCOptimizationDisable:skl,bxt,kbl */
+	/* WaDisablePartialResolveInVc:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(CACHE_MODE_1, (GEN8_4x4_STC_OPTIMIZATION_DISABLE |
 					 GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE));
 
-	/* WaCcsTlbPrefetchDisable:skl,bxt */
+	/* WaCcsTlbPrefetchDisable:skl,bxt,kbl */
 	WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
 			  GEN9_CCS_TLB_PREFETCH_ENABLE);
 
@@ -973,31 +975,57 @@
 		WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0,
 				  PIXEL_MASK_CAMMING_DISABLE);
 
-	/* WaForceContextSaveRestoreNonCoherent:skl,bxt */
-	tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
-	if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) ||
-	    IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
-		tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
-	WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
+	/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
+			  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
 
-	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt */
-	if (IS_SKYLAKE(dev) || IS_BXT_REVID(dev, 0, BXT_REVID_B0))
+	/* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
+	 * both tied to WaForceContextSaveRestoreNonCoherent
+	 * in some hsds for skl. We keep the tie for all gen9. The
+	 * documentation is a bit hazy and so we want to get common behaviour,
+	 * even though there is no clear evidence we would need both on kbl/bxt.
+	 * This area has been source of system hangs so we play it safe
+	 * and mimic the skl regardless of what bspec says.
+	 *
+	 * Use Force Non-Coherent whenever executing a 3D context. This
+	 * is a workaround for a possible hang in the unlikely event
+	 * a TLB invalidation occurs during a PSD flush.
+	 */
+
+	/* WaForceEnableNonCoherent:skl,bxt,kbl */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_NON_COHERENT);
+
+	/* WaDisableHDCInvalidation:skl,bxt,kbl */
+	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
+		   BDW_DISABLE_HDC_INVALIDATION);
+
+	/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl */
+	if (IS_SKYLAKE(dev_priv) ||
+	    IS_KABYLAKE(dev_priv) ||
+	    IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
 		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
 				  GEN8_SAMPLER_POWER_BYPASS_DIS);
 
-	/* WaDisableSTUnitPowerOptimization:skl,bxt */
+	/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
 
-	/* WaOCLCoherentLineFlush:skl,bxt */
+	/* WaOCLCoherentLineFlush:skl,bxt,kbl */
 	I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
 				    GEN8_LQSC_FLUSH_COHERENT_LINES));
 
-	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt */
+	/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt */
+	ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG);
+	if (ret)
+		return ret;
+
+	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl */
 	ret= wa_ring_whitelist_reg(engine, GEN8_CS_CHICKEN1);
 	if (ret)
 		return ret;
 
-	/* WaAllowUMDToModifyHDCChicken1:skl,bxt */
+	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl */
 	ret = wa_ring_whitelist_reg(engine, GEN8_HDC_CHICKEN1);
 	if (ret)
 		return ret;
@@ -1092,22 +1120,6 @@
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
-	/* This is tied to WaForceContextSaveRestoreNonCoherent */
-	if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) {
-		/*
-		 *Use Force Non-Coherent whenever executing a 3D context. This
-		 * is a workaround for a possible hang in the unlikely event
-		 * a TLB invalidation occurs during a PSD flush.
-		 */
-		/* WaForceEnableNonCoherent:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FORCE_NON_COHERENT);
-
-		/* WaDisableHDCInvalidation:skl */
-		I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) |
-			   BDW_DISABLE_HDC_INVALIDATION);
-	}
-
 	/* WaBarrierPerformanceFixDisable:skl */
 	if (IS_SKL_REVID(dev, SKL_REVID_C0, SKL_REVID_D0))
 		WA_SET_BIT_MASKED(HDC_CHICKEN0,
@@ -1120,6 +1132,9 @@
 			GEN7_HALF_SLICE_CHICKEN1,
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 
+	/* WaDisableGafsUnitClkGating:skl */
+	WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
 	/* WaDisableLSQCROPERFforOCL:skl */
 	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
 	if (ret)
@@ -1174,6 +1189,63 @@
 			return ret;
 	}
 
+	/* WaInsertDummyPushConstPs:bxt */
+	if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	return 0;
+}
+
+static int kbl_init_workarounds(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->dev->dev_private;
+	int ret;
+
+	ret = gen9_init_workarounds(engine);
+	if (ret)
+		return ret;
+
+	/* WaEnableGapsTsvCreditFix:kbl */
+	I915_WRITE(GEN8_GARBCNTL, (I915_READ(GEN8_GARBCNTL) |
+				   GEN9_GAPS_TSV_CREDIT_DISABLE));
+
+	/* WaDisableDynamicCreditSharing:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		WA_SET_BIT(GAMT_CHKN_BIT_REG,
+			   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
+
+	/* WaDisableFenceDestinationToSLM:kbl (pre-prod) */
+	if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0))
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE);
+
+	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
+	 * involving this register should also be added to WA batch as required.
+	 */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
+		/* WaDisableLSQCROPERFforOCL:kbl */
+		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
+			   GEN8_LQSC_RO_PERF_DIS);
+
+	/* WaInsertDummyPushConstPs:kbl */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
+				  GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
+
+	/* WaDisableGafsUnitClkGating:kbl */
+	WA_SET_BIT(GEN7_UCGCTL4, GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaDisableSbeCacheDispatchPortSharing:kbl */
+	WA_SET_BIT_MASKED(
+		GEN7_HALF_SLICE_CHICKEN1,
+		GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+
+	/* WaDisableLSQCROPERFforOCL:kbl */
+	ret = wa_ring_whitelist_reg(engine, GEN8_L3SQCREG4);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -1199,6 +1271,9 @@
 	if (IS_BROXTON(dev))
 		return bxt_init_workarounds(engine);
 
+	if (IS_KABYLAKE(dev_priv))
+		return kbl_init_workarounds(engine);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 300ea03..d1f248f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -552,7 +552,8 @@
 	if (ret)
 		goto fini;
 
-	fbcon->helper.fbdev->pixmap.buf_align = 4;
+	if (fbcon->helper.fbdev)
+		fbcon->helper.fbdev->pixmap.buf_align = 4;
 	return 0;
 
 fini:
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index 22706c0..49bd5da 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -40,7 +40,8 @@
 gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern);
+	const u32 soff = gf119_sor_soff(outp);
+	nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 99510e6..a4b357d 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -1,6 +1,6 @@
 config DRM_SUN4I
 	tristate "DRM Support for Allwinner A10 Display Engine"
-	depends on DRM && ARM
+	depends on DRM && ARM && COMMON_CLK
 	depends on ARCH_SUNXI || COMPILE_TEST
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index f7a15c1..3ab5604 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -190,7 +190,7 @@
 	/* Get the physical address of the buffer in memory */
 	gem = drm_fb_cma_get_gem_obj(fb, 0);
 
-	DRM_DEBUG_DRIVER("Using GEM @ 0x%x\n", gem->paddr);
+	DRM_DEBUG_DRIVER("Using GEM @ %pad\n", &gem->paddr);
 
 	/* Compute the start of the displayed memory */
 	bpp = drm_format_plane_cpp(fb->pixel_format, 0);
@@ -198,7 +198,7 @@
 	paddr += (state->src_x >> 16) * bpp;
 	paddr += (state->src_y >> 16) * fb->pitches[0];
 
-	DRM_DEBUG_DRIVER("Setting buffer address to 0x%x\n", paddr);
+	DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr);
 
 	/* Write the 32 lower bits of the address (in bits) */
 	lo_paddr = paddr << 3;
diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c
index 4182a21..41cacec 100644
--- a/drivers/gpu/drm/sun4i/sun4i_crtc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c
@@ -65,6 +65,14 @@
 	DRM_DEBUG_DRIVER("Disabling the CRTC\n");
 
 	sun4i_tcon_disable(drv->tcon);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+
+		crtc->state->event = NULL;
+	}
 }
 
 static void sun4i_crtc_enable(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/sun4i/sun4i_dotclock.c b/drivers/gpu/drm/sun4i/sun4i_dotclock.c
index 3ff668c..5b34631 100644
--- a/drivers/gpu/drm/sun4i/sun4i_dotclock.c
+++ b/drivers/gpu/drm/sun4i/sun4i_dotclock.c
@@ -72,14 +72,40 @@
 static long sun4i_dclk_round_rate(struct clk_hw *hw, unsigned long rate,
 				  unsigned long *parent_rate)
 {
-	return *parent_rate / DIV_ROUND_CLOSEST(*parent_rate, rate);
+	unsigned long best_parent = 0;
+	u8 best_div = 1;
+	int i;
+
+	for (i = 6; i < 127; i++) {
+		unsigned long ideal = rate * i;
+		unsigned long rounded;
+
+		rounded = clk_hw_round_rate(clk_hw_get_parent(hw),
+					    ideal);
+
+		if (rounded == ideal) {
+			best_parent = rounded;
+			best_div = i;
+			goto out;
+		}
+
+		if ((rounded < ideal) && (rounded > best_parent)) {
+			best_parent = rounded;
+			best_div = i;
+		}
+	}
+
+out:
+	*parent_rate = best_parent;
+
+	return best_parent / best_div;
 }
 
 static int sun4i_dclk_set_rate(struct clk_hw *hw, unsigned long rate,
 			       unsigned long parent_rate)
 {
 	struct sun4i_dclk *dclk = hw_to_dclk(hw);
-	int div = DIV_ROUND_CLOSEST(parent_rate, rate);
+	u8 div = parent_rate / rate;
 
 	return regmap_update_bits(dclk->regmap, SUN4I_TCON0_DCLK_REG,
 				  GENMASK(6, 0), div);
@@ -127,10 +153,14 @@
 	const char *clk_name, *parent_name;
 	struct clk_init_data init;
 	struct sun4i_dclk *dclk;
+	int ret;
 
 	parent_name = __clk_get_name(tcon->sclk0);
-	of_property_read_string_index(dev->of_node, "clock-output-names", 0,
-				      &clk_name);
+	ret = of_property_read_string_index(dev->of_node,
+					    "clock-output-names", 0,
+					    &clk_name);
+	if (ret)
+		return ret;
 
 	dclk = devm_kzalloc(dev, sizeof(*dclk), GFP_KERNEL);
 	if (!dclk)
@@ -140,6 +170,7 @@
 	init.ops = &sun4i_dclk_ops;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
+	init.flags = CLK_SET_RATE_PARENT;
 
 	dclk->regmap = tcon->regs;
 	dclk->hw.init = &init;
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 76e922b..937394c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -24,34 +24,6 @@
 #include "sun4i_layer.h"
 #include "sun4i_tcon.h"
 
-static int sun4i_drv_connector_plug_all(struct drm_device *drm)
-{
-	struct drm_connector *connector, *failed;
-	int ret;
-
-	mutex_lock(&drm->mode_config.mutex);
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		ret = drm_connector_register(connector);
-		if (ret) {
-			failed = connector;
-			goto err;
-		}
-	}
-	mutex_unlock(&drm->mode_config.mutex);
-	return 0;
-
-err:
-	list_for_each_entry(connector, &drm->mode_config.connector_list, head) {
-		if (failed == connector)
-			break;
-
-		drm_connector_unregister(connector);
-	}
-	mutex_unlock(&drm->mode_config.mutex);
-
-	return ret;
-}
-
 static int sun4i_drv_enable_vblank(struct drm_device *drm, unsigned int pipe)
 {
 	struct sun4i_drv *drv = drm->dev_private;
@@ -120,11 +92,27 @@
 	/* Frame Buffer Operations */
 
 	/* VBlank Operations */
-	.get_vblank_counter	= drm_vblank_count,
+	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= sun4i_drv_enable_vblank,
 	.disable_vblank		= sun4i_drv_disable_vblank,
 };
 
+static void sun4i_remove_framebuffers(void)
+{
+	struct apertures_struct *ap;
+
+	ap = alloc_apertures(1);
+	if (!ap)
+		return;
+
+	/* The framebuffer can be located anywhere in RAM */
+	ap->ranges[0].base = 0;
+	ap->ranges[0].size = ~0;
+
+	remove_conflicting_framebuffers(ap, "sun4i-drm-fb", false);
+	kfree(ap);
+}
+
 static int sun4i_drv_bind(struct device *dev)
 {
 	struct drm_device *drm;
@@ -172,6 +160,9 @@
 	}
 	drm->irq_enabled = true;
 
+	/* Remove early framebuffers (ie. simplefb) */
+	sun4i_remove_framebuffers();
+
 	/* Create our framebuffer */
 	drv->fbdev = sun4i_framebuffer_init(drm);
 	if (IS_ERR(drv->fbdev)) {
@@ -187,7 +178,7 @@
 	if (ret)
 		goto free_drm;
 
-	ret = sun4i_drv_connector_plug_all(drm);
+	ret = drm_connector_register_all(drm);
 	if (ret)
 		goto unregister_drm;
 
@@ -204,6 +195,7 @@
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 
+	drm_connector_unregister_all(drm);
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
 	sun4i_framebuffer_free(drm);
@@ -318,6 +310,7 @@
 
 		count += sun4i_drv_add_endpoints(&pdev->dev, &match,
 						pipeline);
+		of_node_put(pipeline);
 
 		DRM_DEBUG_DRIVER("Queued %d outputs on pipeline %d\n",
 				 count, i);
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index ab64948..aaffe9e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -54,8 +54,13 @@
 static int sun4i_rgb_mode_valid(struct drm_connector *connector,
 				struct drm_display_mode *mode)
 {
+	struct sun4i_rgb *rgb = drm_connector_to_sun4i_rgb(connector);
+	struct sun4i_drv *drv = rgb->drv;
+	struct sun4i_tcon *tcon = drv->tcon;
 	u32 hsync = mode->hsync_end - mode->hsync_start;
 	u32 vsync = mode->vsync_end - mode->vsync_start;
+	unsigned long rate = mode->clock * 1000;
+	long rounded_rate;
 
 	DRM_DEBUG_DRIVER("Validating modes...\n");
 
@@ -87,6 +92,15 @@
 
 	DRM_DEBUG_DRIVER("Vertical parameters OK\n");
 
+	rounded_rate = clk_round_rate(tcon->dclk, rate);
+	if (rounded_rate < rate)
+		return MODE_CLOCK_LOW;
+
+	if (rounded_rate > rate)
+		return MODE_CLOCK_HIGH;
+
+	DRM_DEBUG_DRIVER("Clock rate OK\n");
+
 	return MODE_OK;
 }
 
@@ -203,7 +217,7 @@
 	int ret;
 
 	/* If we don't have a panel, there's no point in going on */
-	if (!tcon->panel)
+	if (IS_ERR(tcon->panel))
 		return -ENODEV;
 
 	rgb = devm_kzalloc(drm->dev, sizeof(*rgb), GFP_KERNEL);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 9f19b0e..652385f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -425,11 +425,11 @@
 
 	remote = of_graph_get_remote_port_parent(end_node);
 	if (!remote) {
-		DRM_DEBUG_DRIVER("Enable to parse remote node\n");
+		DRM_DEBUG_DRIVER("Unable to parse remote node\n");
 		return ERR_PTR(-EINVAL);
 	}
 
-	return of_drm_find_panel(remote);
+	return of_drm_find_panel(remote) ?: ERR_PTR(-EPROBE_DEFER);
 }
 
 static int sun4i_tcon_bind(struct device *dev, struct device *master,
@@ -490,7 +490,11 @@
 		return 0;
 	}
 
-	return sun4i_rgb_init(drm);
+	ret = sun4i_rgb_init(drm);
+	if (ret < 0)
+		goto err_free_clocks;
+
+	return 0;
 
 err_free_clocks:
 	sun4i_tcon_free_clocks(tcon);
@@ -522,12 +526,13 @@
 	 * Defer the probe.
 	 */
 	panel = sun4i_tcon_find_panel(node);
-	if (IS_ERR(panel)) {
-		/*
-		 * If we don't have a panel endpoint, just go on
-		 */
-		if (PTR_ERR(panel) != -ENODEV)
-			return -EPROBE_DEFER;
+
+	/*
+	 * If we don't have a panel endpoint, just go on
+	 */
+	if (PTR_ERR(panel) == -EPROBE_DEFER) {
+		DRM_DEBUG_DRIVER("Still waiting for our panel. Deferring...\n");
+		return -EPROBE_DEFER;
 	}
 
 	return component_add(&pdev->dev, &sun4i_tcon_ops);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 39386f5..a71cf98 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1034,9 +1034,9 @@
 	return ret;
 }
 
-static bool ttm_bo_mem_compat(struct ttm_placement *placement,
-			      struct ttm_mem_reg *mem,
-			      uint32_t *new_flags)
+bool ttm_bo_mem_compat(struct ttm_placement *placement,
+		       struct ttm_mem_reg *mem,
+		       uint32_t *new_flags)
 {
 	int i;
 
@@ -1068,6 +1068,7 @@
 
 	return false;
 }
+EXPORT_SYMBOL(ttm_bo_mem_compat);
 
 int ttm_bo_validate(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
index 9b078a4..0cd8890 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
@@ -49,6 +49,7 @@
 {
 	struct ttm_buffer_object *bo = &buf->base;
 	int ret;
+	uint32_t new_flags;
 
 	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
 	if (unlikely(ret != 0))
@@ -60,7 +61,12 @@
 	if (unlikely(ret != 0))
 		goto err;
 
-	ret = ttm_bo_validate(bo, placement, interruptible, false);
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, placement, interruptible, false);
+
 	if (!ret)
 		vmw_bo_pin_reserved(buf, true);
 
@@ -91,6 +97,7 @@
 {
 	struct ttm_buffer_object *bo = &buf->base;
 	int ret;
+	uint32_t new_flags;
 
 	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
 	if (unlikely(ret != 0))
@@ -102,6 +109,12 @@
 	if (unlikely(ret != 0))
 		goto err;
 
+	if (buf->pin_count > 0) {
+		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+		goto out_unreserve;
+	}
+
 	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, interruptible,
 			      false);
 	if (likely(ret == 0) || ret == -ERESTARTSYS)
@@ -161,6 +174,7 @@
 	struct ttm_placement placement;
 	struct ttm_place place;
 	int ret = 0;
+	uint32_t new_flags;
 
 	place = vmw_vram_placement.placement[0];
 	place.lpfn = bo->num_pages;
@@ -185,10 +199,15 @@
 	 */
 	if (bo->mem.mem_type == TTM_PL_VRAM &&
 	    bo->mem.start < bo->num_pages &&
-	    bo->mem.start > 0)
+	    bo->mem.start > 0 &&
+	    buf->pin_count == 0)
 		(void) ttm_bo_validate(bo, &vmw_sys_placement, false, false);
 
-	ret = ttm_bo_validate(bo, &placement, interruptible, false);
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(&placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, &placement, interruptible, false);
 
 	/* For some reason we didn't end up at the start of vram */
 	WARN_ON(ret == 0 && bo->offset != 0);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 9fcd820..8d528fc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -233,6 +233,7 @@
 static int vmw_restrict_iommu;
 static int vmw_force_coherent;
 static int vmw_restrict_dma_mask;
+static int vmw_assume_16bpp;
 
 static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
 static void vmw_master_init(struct vmw_master *);
@@ -249,6 +250,8 @@
 module_param_named(force_coherent, vmw_force_coherent, int, 0600);
 MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU");
 module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600);
+MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
+module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
 
 static void vmw_print_capabilities(uint32_t capabilities)
@@ -660,6 +663,8 @@
 	dev_priv->vram_start = pci_resource_start(dev->pdev, 1);
 	dev_priv->mmio_start = pci_resource_start(dev->pdev, 2);
 
+	dev_priv->assume_16bpp = !!vmw_assume_16bpp;
+
 	dev_priv->enable_fb = enable_fbdev;
 
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
@@ -706,6 +711,13 @@
 			vmw_read(dev_priv,
 				 SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB);
 
+		/*
+		 * Workaround for low memory 2D VMs to compensate for the
+		 * allocation taken by fbdev
+		 */
+		if (!(dev_priv->capabilities & SVGA_CAP_3D))
+			mem_size *= 2;
+
 		dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE;
 		dev_priv->prim_bb_mem =
 			vmw_read(dev_priv,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 1980e2a..89fb194 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -386,6 +386,7 @@
 	spinlock_t hw_lock;
 	spinlock_t cap_lock;
 	bool has_dx;
+	bool assume_16bpp;
 
 	/*
 	 * VGA registers.
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 679a4cb..d2d9395 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -517,28 +517,6 @@
 
 	par->set_fb = &vfb->base;
 
-	if (!par->bo_ptr) {
-		/*
-		 * Pin before mapping. Since we don't know in what placement
-		 * to pin, call into KMS to do it for us.
-		 */
-		ret = vfb->pin(vfb);
-		if (ret) {
-			DRM_ERROR("Could not pin the fbdev framebuffer.\n");
-			return ret;
-		}
-
-		ret = ttm_bo_kmap(&par->vmw_bo->base, 0,
-				  par->vmw_bo->base.num_pages, &par->map);
-		if (ret) {
-			vfb->unpin(vfb);
-			DRM_ERROR("Could not map the fbdev framebuffer.\n");
-			return ret;
-		}
-
-		par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite);
-	}
-
 	return 0;
 }
 
@@ -601,6 +579,31 @@
 	if (ret)
 		goto out_unlock;
 
+	if (!par->bo_ptr) {
+		struct vmw_framebuffer *vfb = vmw_framebuffer_to_vfb(set.fb);
+
+		/*
+		 * Pin before mapping. Since we don't know in what placement
+		 * to pin, call into KMS to do it for us.
+		 */
+		ret = vfb->pin(vfb);
+		if (ret) {
+			DRM_ERROR("Could not pin the fbdev framebuffer.\n");
+			goto out_unlock;
+		}
+
+		ret = ttm_bo_kmap(&par->vmw_bo->base, 0,
+				  par->vmw_bo->base.num_pages, &par->map);
+		if (ret) {
+			vfb->unpin(vfb);
+			DRM_ERROR("Could not map the fbdev framebuffer.\n");
+			goto out_unlock;
+		}
+
+		par->bo_ptr = ttm_kmap_obj_virtual(&par->map, &par->bo_iowrite);
+	}
+
+
 	vmw_fb_dirty_mark(par, par->fb_x, par->fb_y,
 			  par->set_fb->width, par->set_fb->height);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 55231cc..e29da45 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1553,14 +1553,10 @@
 		DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC)
 	};
 	int i;
-	u32 assumed_bpp = 2;
+	u32 assumed_bpp = 4;
 
-	/*
-	 * If using screen objects, then assume 32-bpp because that's what the
-	 * SVGA device is assuming
-	 */
-	if (dev_priv->active_display_unit == vmw_du_screen_object)
-		assumed_bpp = 4;
+	if (dev_priv->assume_16bpp)
+		assumed_bpp = 2;
 
 	if (dev_priv->active_display_unit == vmw_du_screen_target) {
 		max_width  = min(max_width,  dev_priv->stdu_max_width);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index f0374f9..e57a0ba 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -300,6 +300,9 @@
 		break;
 	}
 
+	if (retries == RETRIES)
+		return -EINVAL;
+
 	*msg_len = reply_len;
 	*msg     = reply;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 9ca818f..41932a7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -399,8 +399,10 @@
 
 	WARN_ON_ONCE(!stdu->defined);
 
-	if (!vfb->dmabuf && new_fb->width == mode->hdisplay &&
-	    new_fb->height == mode->vdisplay)
+	new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
+
+	if (new_vfbs && new_vfbs->surface->base_size.width == mode->hdisplay &&
+	    new_vfbs->surface->base_size.height == mode->vdisplay)
 		new_content_type = SAME_AS_DISPLAY;
 	else if (vfb->dmabuf)
 		new_content_type = SEPARATE_DMA;
@@ -444,7 +446,6 @@
 			content_srf.mip_levels[0]     = 1;
 			content_srf.multisample_count = 0;
 		} else {
-			new_vfbs = vmw_framebuffer_to_vfbs(new_fb);
 			content_srf = *new_vfbs->surface;
 		}
 
@@ -464,7 +465,6 @@
 			return ret;
 		}
 	} else if (new_content_type == SAME_AS_DISPLAY) {
-		new_vfbs = vmw_framebuffer_to_vfbs(new_fb);
 		new_display_srf = vmw_surface_reference(new_vfbs->surface);
 	}
 
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 95b7d61..fb6f1f4 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -61,6 +61,7 @@
 #define MT_QUIRK_ALWAYS_VALID		(1 << 4)
 #define MT_QUIRK_VALID_IS_INRANGE	(1 << 5)
 #define MT_QUIRK_VALID_IS_CONFIDENCE	(1 << 6)
+#define MT_QUIRK_CONFIDENCE		(1 << 7)
 #define MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE	(1 << 8)
 #define MT_QUIRK_NO_AREA		(1 << 9)
 #define MT_QUIRK_IGNORE_DUPLICATES	(1 << 10)
@@ -78,6 +79,7 @@
 	__s32 contactid;	/* the device ContactID assigned to this slot */
 	bool touch_state;	/* is the touch valid? */
 	bool inrange_state;	/* is the finger in proximity of the sensor? */
+	bool confidence_state;  /* is the touch made by a finger? */
 };
 
 struct mt_class {
@@ -503,10 +505,8 @@
 			return 1;
 		case HID_DG_CONFIDENCE:
 			if (cls->name == MT_CLS_WIN_8 &&
-				field->application == HID_DG_TOUCHPAD) {
-				cls->quirks &= ~MT_QUIRK_ALWAYS_VALID;
-				cls->quirks |= MT_QUIRK_VALID_IS_CONFIDENCE;
-			}
+				field->application == HID_DG_TOUCHPAD)
+				cls->quirks |= MT_QUIRK_CONFIDENCE;
 			mt_store_field(usage, td, hi);
 			return 1;
 		case HID_DG_TIPSWITCH:
@@ -619,6 +619,7 @@
 		return;
 
 	if (td->curvalid || (td->mtclass.quirks & MT_QUIRK_ALWAYS_VALID)) {
+		int active;
 		int slotnum = mt_compute_slot(td, input);
 		struct mt_slot *s = &td->curdata;
 		struct input_mt *mt = input->mt;
@@ -633,10 +634,14 @@
 				return;
 		}
 
+		if (!(td->mtclass.quirks & MT_QUIRK_CONFIDENCE))
+			s->confidence_state = 1;
+		active = (s->touch_state || s->inrange_state) &&
+							s->confidence_state;
+
 		input_mt_slot(input, slotnum);
-		input_mt_report_slot_state(input, MT_TOOL_FINGER,
-			s->touch_state || s->inrange_state);
-		if (s->touch_state || s->inrange_state) {
+		input_mt_report_slot_state(input, MT_TOOL_FINGER, active);
+		if (active) {
 			/* this finger is in proximity of the sensor */
 			int wide = (s->w > s->h);
 			/* divided by two to match visual scale of touch */
@@ -701,6 +706,8 @@
 			td->curdata.touch_state = value;
 			break;
 		case HID_DG_CONFIDENCE:
+			if (quirks & MT_QUIRK_CONFIDENCE)
+				td->curdata.confidence_state = value;
 			if (quirks & MT_QUIRK_VALID_IS_CONFIDENCE)
 				td->curvalid = value;
 			break;
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 2f1ddca..700145b 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -516,13 +516,13 @@
 					goto inval;
 			} else if (uref->usage_index >= field->report_count)
 				goto inval;
-
-			else if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
-				 (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
-				  uref->usage_index + uref_multi->num_values > field->report_count))
-				goto inval;
 		}
 
+		if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) &&
+		    (uref_multi->num_values > HID_MAX_MULTI_USAGES ||
+		     uref->usage_index + uref_multi->num_values > field->report_count))
+			goto inval;
+
 		switch (cmd) {
 		case HIDIOCGUSAGE:
 			uref->value = field->value[uref->usage_index];
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index c43318d..2ac87d5 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -35,6 +35,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/sched.h>
+#include <linux/ctype.h>
 
 #include <linux/i8k.h>
 
@@ -66,11 +67,13 @@
 
 static DEFINE_MUTEX(i8k_mutex);
 static char bios_version[4];
+static char bios_machineid[16];
 static struct device *i8k_hwmon_dev;
 static u32 i8k_hwmon_flags;
 static uint i8k_fan_mult = I8K_FAN_MULT;
 static uint i8k_pwm_mult;
 static uint i8k_fan_max = I8K_FAN_HIGH;
+static bool disallow_fan_type_call;
 
 #define I8K_HWMON_HAVE_TEMP1	(1 << 0)
 #define I8K_HWMON_HAVE_TEMP2	(1 << 1)
@@ -94,13 +97,13 @@
 MODULE_PARM_DESC(ignore_dmi, "Continue probing hardware even if DMI data does not match");
 
 #if IS_ENABLED(CONFIG_I8K)
-static bool restricted;
+static bool restricted = true;
 module_param(restricted, bool, 0);
-MODULE_PARM_DESC(restricted, "Allow fan control if SYS_ADMIN capability set");
+MODULE_PARM_DESC(restricted, "Restrict fan control and serial number to CAP_SYS_ADMIN (default: 1)");
 
 static bool power_status;
 module_param(power_status, bool, 0600);
-MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k");
+MODULE_PARM_DESC(power_status, "Report power status in /proc/i8k (default: 0)");
 #endif
 
 static uint fan_mult;
@@ -235,14 +238,28 @@
 /*
  * Read the fan type.
  */
-static int i8k_get_fan_type(int fan)
+static int _i8k_get_fan_type(int fan)
 {
 	struct smm_regs regs = { .eax = I8K_SMM_GET_FAN_TYPE, };
 
+	if (disallow_fan_type_call)
+		return -EINVAL;
+
 	regs.ebx = fan & 0xff;
 	return i8k_smm(&regs) ? : regs.eax & 0xff;
 }
 
+static int i8k_get_fan_type(int fan)
+{
+	/* I8K_SMM_GET_FAN_TYPE SMM call is expensive, so cache values */
+	static int types[2] = { INT_MIN, INT_MIN };
+
+	if (types[fan] == INT_MIN)
+		types[fan] = _i8k_get_fan_type(fan);
+
+	return types[fan];
+}
+
 /*
  * Read the fan nominal rpm for specific fan speed.
  */
@@ -387,14 +404,20 @@
 
 	switch (cmd) {
 	case I8K_BIOS_VERSION:
+		if (!isdigit(bios_version[0]) || !isdigit(bios_version[1]) ||
+		    !isdigit(bios_version[2]))
+			return -EINVAL;
+
 		val = (bios_version[0] << 16) |
 				(bios_version[1] << 8) | bios_version[2];
 		break;
 
 	case I8K_MACHINE_ID:
-		memset(buff, 0, 16);
-		strlcpy(buff, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
-			sizeof(buff));
+		if (restricted && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		memset(buff, 0, sizeof(buff));
+		strlcpy(buff, bios_machineid, sizeof(buff));
 		break;
 
 	case I8K_FN_STATUS:
@@ -511,7 +534,7 @@
 	seq_printf(seq, "%s %s %s %d %d %d %d %d %d %d\n",
 		   I8K_PROC_FMT,
 		   bios_version,
-		   i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+		   (restricted && !capable(CAP_SYS_ADMIN)) ? "-1" : bios_machineid,
 		   cpu_temp,
 		   left_fan, right_fan, left_speed, right_speed,
 		   ac_power, fn_key);
@@ -718,6 +741,9 @@
 static umode_t i8k_is_visible(struct kobject *kobj, struct attribute *attr,
 			      int index)
 {
+	if (disallow_fan_type_call &&
+	    (index == 9 || index == 12))
+		return 0;
 	if (index >= 0 && index <= 1 &&
 	    !(i8k_hwmon_flags & I8K_HWMON_HAVE_TEMP1))
 		return 0;
@@ -767,13 +793,17 @@
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_TEMP4;
 
-	/* First fan attributes, if fan type is OK */
-	err = i8k_get_fan_type(0);
+	/* First fan attributes, if fan status or type is OK */
+	err = i8k_get_fan_status(0);
+	if (err < 0)
+		err = i8k_get_fan_type(0);
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN1;
 
-	/* Second fan attributes, if fan type is OK */
-	err = i8k_get_fan_type(1);
+	/* Second fan attributes, if fan status or type is OK */
+	err = i8k_get_fan_status(1);
+	if (err < 0)
+		err = i8k_get_fan_type(1);
 	if (err >= 0)
 		i8k_hwmon_flags |= I8K_HWMON_HAVE_FAN2;
 
@@ -929,12 +959,14 @@
 
 MODULE_DEVICE_TABLE(dmi, i8k_dmi_table);
 
-static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
+/*
+ * On some machines once I8K_SMM_GET_FAN_TYPE is issued then CPU fan speed
+ * randomly going up and down due to bug in Dell SMM or BIOS. Here is blacklist
+ * of affected Dell machines for which we disallow I8K_SMM_GET_FAN_TYPE call.
+ * See bug: https://bugzilla.kernel.org/show_bug.cgi?id=100121
+ */
+static struct dmi_system_id i8k_blacklist_fan_type_dmi_table[] __initdata = {
 	{
-		/*
-		 * CPU fan speed going up and down on Dell Studio XPS 8000
-		 * for unknown reasons.
-		 */
 		.ident = "Dell Studio XPS 8000",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -942,16 +974,19 @@
 		},
 	},
 	{
-		/*
-		 * CPU fan speed going up and down on Dell Studio XPS 8100
-		 * for unknown reasons.
-		 */
 		.ident = "Dell Studio XPS 8100",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"),
 		},
 	},
+	{
+		.ident = "Dell Inspiron 580",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Inspiron 580 "),
+		},
+	},
 	{ }
 };
 
@@ -966,8 +1001,7 @@
 	/*
 	 * Get DMI information
 	 */
-	if (!dmi_check_system(i8k_dmi_table) ||
-	    dmi_check_system(i8k_blacklist_dmi_table)) {
+	if (!dmi_check_system(i8k_dmi_table)) {
 		if (!ignore_dmi && !force)
 			return -ENODEV;
 
@@ -978,8 +1012,13 @@
 			i8k_get_dmi_data(DMI_BIOS_VERSION));
 	}
 
+	if (dmi_check_system(i8k_blacklist_fan_type_dmi_table))
+		disallow_fan_type_call = true;
+
 	strlcpy(bios_version, i8k_get_dmi_data(DMI_BIOS_VERSION),
 		sizeof(bios_version));
+	strlcpy(bios_machineid, i8k_get_dmi_data(DMI_PRODUCT_SERIAL),
+		sizeof(bios_machineid));
 
 	/*
 	 * Get SMM Dell signature
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index cc6439a..041050e 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -1268,6 +1268,8 @@
 		}
 	}
 
+	idx = 0;
+
 	do {
 		if (msgs[idx].len == 0) {
 			ret = -EINVAL;
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 445398c3..b126dba 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -912,7 +912,7 @@
 	ret = tegra_i2c_init(i2c_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize i2c controller");
-		goto unprepare_div_clk;
+		goto disable_div_clk;
 	}
 
 	ret = devm_request_irq(&pdev->dev, i2c_dev->irq,
diff --git a/drivers/i2c/i2c-boardinfo.c b/drivers/i2c/i2c-boardinfo.c
index e33022e..6e5fac6 100644
--- a/drivers/i2c/i2c-boardinfo.c
+++ b/drivers/i2c/i2c-boardinfo.c
@@ -56,9 +56,7 @@
  * The board info passed can safely be __initdata, but be careful of embedded
  * pointers (for platform_data, functions, etc) since that won't be copied.
  */
-int __init
-i2c_register_board_info(int busnum,
-	struct i2c_board_info const *info, unsigned len)
+int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned len)
 {
 	int status;
 
diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 26e7c51..c6a90b4 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -145,7 +145,7 @@
 		mux->data.idle_in_use = true;
 
 	/* map address from "reg" if exists */
-	if (of_address_to_resource(np, 0, &res)) {
+	if (of_address_to_resource(np, 0, &res) == 0) {
 		mux->data.reg_size = resource_size(&res);
 		mux->data.reg = devm_ioremap_resource(&pdev->dev, &res);
 		if (IS_ERR(mux->data.reg))
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 923f565..3a9f106 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -81,7 +81,7 @@
 
 	mutex_lock(&st->buf_lock);
 	ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	st->tx[0] = KXSD9_WRITE(KXSD9_REG_CTRL_C);
 	st->tx[1] = (ret & ~KXSD9_FS_MASK) | i;
@@ -163,7 +163,7 @@
 		break;
 	case IIO_CHAN_INFO_SCALE:
 		ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-		if (ret)
+		if (ret < 0)
 			goto error_ret;
 		*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
 		ret = IIO_VAL_INT_PLUS_MICRO;
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 21e19b6..2123f0a 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -396,8 +396,8 @@
 
 	st = iio_priv(indio_dev);
 
-	st->reg = devm_regulator_get(&spi->dev, "vref");
-	if (!IS_ERR_OR_NULL(st->reg)) {
+	st->reg = devm_regulator_get_optional(&spi->dev, "vref");
+	if (!IS_ERR(st->reg)) {
 		ret = regulator_enable(st->reg);
 		if (ret)
 			return ret;
@@ -408,6 +408,9 @@
 
 		st->vref_mv = ret / 1000;
 	} else {
+		/* Any other error indicates that the regulator does exist */
+		if (PTR_ERR(st->reg) != -ENODEV)
+			return PTR_ERR(st->reg);
 		/* Use internal reference */
 		st->vref_mv = 2500;
 	}
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
index f62b8bd..dd6fc6d 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
@@ -56,6 +56,7 @@
 	int i;
 	acpi_status status;
 	union acpi_object *cpm;
+	int ret;
 
 	status = acpi_evaluate_object(adev->handle, "CNF0", NULL, &buffer);
 	if (ACPI_FAILURE(status))
@@ -82,10 +83,10 @@
 			}
 		}
 	}
-
+	ret = cpm->package.count;
 	kfree(buffer.pointer);
 
-	return cpm->package.count;
+	return ret;
 }
 
 static int acpi_i2c_check_resource(struct acpi_resource *ares, void *data)
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 0409667..1a2984c 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -411,7 +411,9 @@
 
 	for (ix = 0; ix < table->sz; ix++)
 		if (table->data_vec[ix].attr.ndev == ndev)
-			if (!del_gid(ib_dev, port, table, ix, false))
+			if (!del_gid(ib_dev, port, table, ix,
+				     !!(table->data_vec[ix].props &
+					GID_TABLE_ENTRY_DEFAULT)))
 				deleted = true;
 
 	write_unlock_irq(&table->rwlock);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f0c91ba..ad1b1ad 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -708,17 +708,6 @@
 		complete(&id_priv->comp);
 }
 
-static int cma_disable_callback(struct rdma_id_private *id_priv,
-				enum rdma_cm_state state)
-{
-	mutex_lock(&id_priv->handler_mutex);
-	if (id_priv->state != state) {
-		mutex_unlock(&id_priv->handler_mutex);
-		return -EINVAL;
-	}
-	return 0;
-}
-
 struct rdma_cm_id *rdma_create_id(struct net *net,
 				  rdma_cm_event_handler event_handler,
 				  void *context, enum rdma_port_space ps,
@@ -1671,11 +1660,12 @@
 	struct rdma_cm_event event;
 	int ret = 0;
 
+	mutex_lock(&id_priv->handler_mutex);
 	if ((ib_event->event != IB_CM_TIMEWAIT_EXIT &&
-		cma_disable_callback(id_priv, RDMA_CM_CONNECT)) ||
+	     id_priv->state != RDMA_CM_CONNECT) ||
 	    (ib_event->event == IB_CM_TIMEWAIT_EXIT &&
-		cma_disable_callback(id_priv, RDMA_CM_DISCONNECT)))
-		return 0;
+	     id_priv->state != RDMA_CM_DISCONNECT))
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (ib_event->event) {
@@ -1870,7 +1860,7 @@
 
 static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 {
-	struct rdma_id_private *listen_id, *conn_id;
+	struct rdma_id_private *listen_id, *conn_id = NULL;
 	struct rdma_cm_event event;
 	struct net_device *net_dev;
 	int offset, ret;
@@ -1884,9 +1874,10 @@
 		goto net_dev_put;
 	}
 
-	if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) {
+	mutex_lock(&listen_id->handler_mutex);
+	if (listen_id->state != RDMA_CM_LISTEN) {
 		ret = -ECONNABORTED;
-		goto net_dev_put;
+		goto err1;
 	}
 
 	memset(&event, 0, sizeof event);
@@ -1976,8 +1967,9 @@
 	struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
 	struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
 
-	if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_CONNECT)
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (iw_event->event) {
@@ -2029,6 +2021,7 @@
 		return ret;
 	}
 
+out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return ret;
 }
@@ -2039,13 +2032,15 @@
 	struct rdma_cm_id *new_cm_id;
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event;
-	int ret;
+	int ret = -ECONNABORTED;
 	struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr;
 	struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr;
 
 	listen_id = cm_id->context;
-	if (cma_disable_callback(listen_id, RDMA_CM_LISTEN))
-		return -ECONNABORTED;
+
+	mutex_lock(&listen_id->handler_mutex);
+	if (listen_id->state != RDMA_CM_LISTEN)
+		goto out;
 
 	/* Create a new RDMA id for the new IW CM ID */
 	new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,
@@ -3216,8 +3211,9 @@
 	struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd;
 	int ret = 0;
 
-	if (cma_disable_callback(id_priv, RDMA_CM_CONNECT))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_CONNECT)
+		goto out;
 
 	memset(&event, 0, sizeof event);
 	switch (ib_event->event) {
@@ -3673,12 +3669,13 @@
 	struct rdma_id_private *id_priv;
 	struct cma_multicast *mc = multicast->context;
 	struct rdma_cm_event event;
-	int ret;
+	int ret = 0;
 
 	id_priv = mc->id_priv;
-	if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) &&
-	    cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED))
-		return 0;
+	mutex_lock(&id_priv->handler_mutex);
+	if (id_priv->state != RDMA_CM_ADDR_BOUND &&
+	    id_priv->state != RDMA_CM_ADDR_RESOLVED)
+		goto out;
 
 	if (!status)
 		status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey));
@@ -3720,6 +3717,7 @@
 		return 0;
 	}
 
+out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return 0;
 }
@@ -3878,12 +3876,12 @@
 	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
 		   rdma_start_port(id_priv->cma_dev->device)];
 	if (addr->sa_family == AF_INET) {
-		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
 			err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,
 					    true);
-		if (!err) {
-			mc->igmp_joined = true;
-			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
+			if (!err)
+				mc->igmp_joined = true;
 		}
 	} else {
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index a5793c8..60df4f8 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -530,6 +530,7 @@
 static PORT_PMA_ATTR(port_rcv_data		    , 13, 32, 224);
 static PORT_PMA_ATTR(port_xmit_packets		    , 14, 32, 256);
 static PORT_PMA_ATTR(port_rcv_packets		    , 15, 32, 288);
+static PORT_PMA_ATTR(port_xmit_wait		    ,  0, 32, 320);
 
 /*
  * Counters added by extended set
@@ -560,6 +561,7 @@
 	&port_pma_attr_port_rcv_data.attr.attr,
 	&port_pma_attr_port_xmit_packets.attr.attr,
 	&port_pma_attr_port_rcv_packets.attr.attr,
+	&port_pma_attr_port_xmit_wait.attr.attr,
 	NULL
 };
 
@@ -579,6 +581,7 @@
 	&port_pma_attr_ext_port_xmit_data.attr.attr,
 	&port_pma_attr_ext_port_rcv_data.attr.attr,
 	&port_pma_attr_ext_port_xmit_packets.attr.attr,
+	&port_pma_attr_port_xmit_wait.attr.attr,
 	&port_pma_attr_ext_port_rcv_packets.attr.attr,
 	&port_pma_attr_ext_unicast_rcv_packets.attr.attr,
 	&port_pma_attr_ext_unicast_xmit_packets.attr.attr,
@@ -604,6 +607,7 @@
 	&port_pma_attr_ext_port_rcv_data.attr.attr,
 	&port_pma_attr_ext_port_xmit_packets.attr.attr,
 	&port_pma_attr_ext_port_rcv_packets.attr.attr,
+	&port_pma_attr_port_xmit_wait.attr.attr,
 	NULL
 };
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 1a8babb..825021d 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1747,7 +1747,7 @@
 	struct ib_srq			*srq = NULL;
 	struct ib_qp			*qp;
 	char				*buf;
-	struct ib_qp_init_attr		attr;
+	struct ib_qp_init_attr		attr = {};
 	struct ib_uverbs_ex_create_qp_resp resp;
 	int				ret;
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 1d7d4cf..6298f54 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -511,12 +511,16 @@
 		ah_attr->grh.dgid = sgid;
 
 		if (!rdma_cap_eth_ah(device, port_num)) {
-			ret = ib_find_cached_gid_by_port(device, &dgid,
-							 IB_GID_TYPE_IB,
-							 port_num, NULL,
-							 &gid_index);
-			if (ret)
-				return ret;
+			if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) {
+				ret = ib_find_cached_gid_by_port(device, &dgid,
+								 IB_GID_TYPE_IB,
+								 port_num, NULL,
+								 &gid_index);
+				if (ret)
+					return ret;
+			} else {
+				gid_index = 0;
+			}
 		}
 
 		ah_attr->grh.sgid_index = (u8) gid_index;
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 81619fb..dad4d0e 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1037,7 +1037,7 @@
 static void dc_start(struct hfi1_devdata *);
 static int qos_rmt_entries(struct hfi1_devdata *dd, unsigned int *mp,
 			   unsigned int *np);
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd);
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd);
 
 /*
  * Error interrupt table entry.  This is used as input to the interrupt
@@ -6962,8 +6962,6 @@
 	}
 
 	reset_neighbor_info(ppd);
-	if (ppd->mgmt_allowed)
-		remove_full_mgmt_pkey(ppd);
 
 	/* disable the port */
 	clear_rcvctrl(ppd->dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
@@ -7070,12 +7068,16 @@
 			    __func__, ppd->pkeys[2], FULL_MGMT_P_KEY);
 	ppd->pkeys[2] = FULL_MGMT_P_KEY;
 	(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+	hfi1_event_pkey_change(ppd->dd, ppd->port);
 }
 
-static void remove_full_mgmt_pkey(struct hfi1_pportdata *ppd)
+static void clear_full_mgmt_pkey(struct hfi1_pportdata *ppd)
 {
-	ppd->pkeys[2] = 0;
-	(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+	if (ppd->pkeys[2] != 0) {
+		ppd->pkeys[2] = 0;
+		(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
+		hfi1_event_pkey_change(ppd->dd, ppd->port);
+	}
 }
 
 /*
@@ -9168,6 +9170,13 @@
 		return 0;
 	}
 
+	/*
+	 * FULL_MGMT_P_KEY is cleared from the pkey table, so that the
+	 * pkey table can be configured properly if the HFI unit is connected
+	 * to switch port with MgmtAllowed=NO
+	 */
+	clear_full_mgmt_pkey(ppd);
+
 	return set_link_state(ppd, HLS_DN_POLL);
 }
 
@@ -9777,7 +9786,7 @@
 	u64 len1 = 0, len2 = (((dd->vld[15].mtu + max_hb) >> 2)
 			      & SEND_LEN_CHECK1_LEN_VL15_MASK) <<
 		SEND_LEN_CHECK1_LEN_VL15_SHIFT;
-	int i;
+	int i, j;
 	u32 thres;
 
 	for (i = 0; i < ppd->vls_supported; i++) {
@@ -9801,7 +9810,10 @@
 			    sc_mtu_to_threshold(dd->vld[i].sc,
 						dd->vld[i].mtu,
 						dd->rcd[0]->rcvhdrqentsize));
-		sc_set_cr_threshold(dd->vld[i].sc, thres);
+		for (j = 0; j < INIT_SC_PER_VL; j++)
+			sc_set_cr_threshold(
+					pio_select_send_context_vl(dd, j, i),
+					    thres);
 	}
 	thres = min(sc_percent_to_threshold(dd->vld[15].sc, 50),
 		    sc_mtu_to_threshold(dd->vld[15].sc,
@@ -14101,8 +14113,14 @@
 {
 	unsigned long flags;
 	struct hfi1_devdata *tmp, *peer = NULL;
+	struct hfi1_asic_data *asic_data;
 	int ret = 0;
 
+	/* pre-allocate the asic structure in case we are the first device */
+	asic_data = kzalloc(sizeof(*dd->asic_data), GFP_KERNEL);
+	if (!asic_data)
+		return -ENOMEM;
+
 	spin_lock_irqsave(&hfi1_devs_lock, flags);
 	/* Find our peer device */
 	list_for_each_entry(tmp, &hfi1_dev_list, list) {
@@ -14114,18 +14132,14 @@
 	}
 
 	if (peer) {
+		/* use already allocated structure */
 		dd->asic_data = peer->asic_data;
+		kfree(asic_data);
 	} else {
-		dd->asic_data = kzalloc(sizeof(*dd->asic_data), GFP_KERNEL);
-		if (!dd->asic_data) {
-			ret = -ENOMEM;
-			goto done;
-		}
+		dd->asic_data = asic_data;
 		mutex_init(&dd->asic_data->asic_resource_mutex);
 	}
 	dd->asic_data->dds[dd->hfi1_id] = dd; /* self back-pointer */
-
-done:
 	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
 	return ret;
 }
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 7a5b0e6..c702a00 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -203,6 +203,9 @@
 
 	switch (cmd) {
 	case HFI1_IOCTL_ASSIGN_CTXT:
+		if (uctxt)
+			return -EINVAL;
+
 		if (copy_from_user(&uinfo,
 				   (struct hfi1_user_info __user *)arg,
 				   sizeof(uinfo)))
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 0d28a5a..eed971c 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1383,7 +1383,7 @@
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
-	struct hfi1_devdata *dd = NULL;
+	struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
 	struct hfi1_pportdata *ppd;
 
 	/* First, lock the non-writable module parameters */
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 21902957..fca07a1 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -78,6 +78,16 @@
 	memset(data, 0, size);
 }
 
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port)
+{
+	struct ib_event event;
+
+	event.event = IB_EVENT_PKEY_CHANGE;
+	event.device = &dd->verbs_dev.rdi.ibdev;
+	event.element.port_num = port;
+	ib_dispatch_event(&event);
+}
+
 static void send_trap(struct hfi1_ibport *ibp, void *data, unsigned len)
 {
 	struct ib_mad_send_buf *send_buf;
@@ -1418,15 +1428,10 @@
 	}
 
 	if (changed) {
-		struct ib_event event;
-
 		(void)hfi1_set_ib_cfg(ppd, HFI1_IB_CFG_PKEYS, 0);
-
-		event.event = IB_EVENT_PKEY_CHANGE;
-		event.device = &dd->verbs_dev.rdi.ibdev;
-		event.element.port_num = port;
-		ib_dispatch_event(&event);
+		hfi1_event_pkey_change(dd, port);
 	}
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/mad.h b/drivers/infiniband/hw/hfi1/mad.h
index 55ee086..8b734aa 100644
--- a/drivers/infiniband/hw/hfi1/mad.h
+++ b/drivers/infiniband/hw/hfi1/mad.h
@@ -434,4 +434,6 @@
 		    COUNTER_MASK(1, 3) | \
 		    COUNTER_MASK(1, 4))
 
+void hfi1_event_pkey_change(struct hfi1_devdata *dd, u8 port);
+
 #endif				/* _HFI1_MAD_H */
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index d5edb1a..d402245 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -995,7 +995,7 @@
 		/* counter is reset if occupancy count changes */
 		if (reg != reg_prev)
 			loop = 0;
-		if (loop > 500) {
+		if (loop > 50000) {
 			/* timed out - bounce the link */
 			dd_dev_err(dd,
 				   "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
@@ -1798,6 +1798,21 @@
 }
 
 /*
+ * Set credit return threshold for the kernel send context
+ */
+static void set_threshold(struct hfi1_devdata *dd, int scontext, int i)
+{
+	u32 thres;
+
+	thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext],
+					    50),
+		    sc_mtu_to_threshold(dd->kernel_send_context[scontext],
+					dd->vld[i].mtu,
+					dd->rcd[0]->rcvhdrqentsize));
+	sc_set_cr_threshold(dd->kernel_send_context[scontext], thres);
+}
+
+/*
  * pio_map_init - called when #vls change
  * @dd: hfi1_devdata
  * @port: port number
@@ -1872,11 +1887,16 @@
 			if (!newmap->map[i])
 				goto bail;
 			newmap->map[i]->mask = (1 << ilog2(sz)) - 1;
-			/* assign send contexts */
+			/*
+			 * assign send contexts and
+			 * adjust credit return threshold
+			 */
 			for (j = 0; j < sz; j++) {
-				if (dd->kernel_send_context[scontext])
+				if (dd->kernel_send_context[scontext]) {
 					newmap->map[i]->ksc[j] =
 					dd->kernel_send_context[scontext];
+					set_threshold(dd, scontext, i);
+				}
 				if (++scontext >= first_scontext +
 						  vl_scontexts[i])
 					/* wrap back to first send context */
diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index 2441669..9fb5616 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -579,7 +579,8 @@
 
 	if (ppd->qsfp_info.cache_valid) {
 		if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
-			sprintf(lenstr, "%dM ", cache[QSFP_MOD_LEN_OFFS]);
+			snprintf(lenstr, sizeof(lenstr), "%dM ",
+				 cache[QSFP_MOD_LEN_OFFS]);
 
 		power_byte = cache[QSFP_MOD_PWR_OFFS];
 		sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n",
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 1e503ad..be91f6f 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -678,8 +678,7 @@
 	u32 tlen = packet->tlen;
 	struct rvt_qp *qp = packet->qp;
 	bool has_grh = rcv_flags & HFI1_HAS_GRH;
-	bool sc4_bit = has_sc4_bit(packet);
-	u8 sc;
+	u8 sc5 = hdr2sc((struct hfi1_message_header *)hdr, packet->rhf);
 	u32 bth1;
 	int is_mcast;
 	struct ib_grh *grh = NULL;
@@ -697,10 +696,8 @@
 		 */
 		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 		u32 lqpn =  be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
-		u8 sl, sc5;
+		u8 sl;
 
-		sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf;
-		sc5 |= sc4_bit;
 		sl = ibp->sc_to_sl[sc5];
 
 		process_becn(ppd, sl, 0, lqpn, 0, IB_CC_SVCTYPE_UD);
@@ -717,10 +714,6 @@
 
 	if (!is_mcast && (opcode != IB_OPCODE_CNP) && bth1 & HFI1_FECN_SMASK) {
 		u16 slid = be16_to_cpu(hdr->lrh[3]);
-		u8 sc5;
-
-		sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf;
-		sc5 |= sc4_bit;
 
 		return_cnp(ibp, qp, src_qp, pkey, dlid, slid, sc5, grh);
 	}
@@ -745,10 +738,6 @@
 		if (qp->ibqp.qp_num > 1) {
 			struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 			u16 slid;
-			u8 sc5;
-
-			sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf;
-			sc5 |= sc4_bit;
 
 			slid = be16_to_cpu(hdr->lrh[3]);
 			if (unlikely(rcv_pkey_check(ppd, pkey, sc5, slid))) {
@@ -790,10 +779,6 @@
 		/* Received on QP0, and so by definition, this is an SMP */
 		struct opa_smp *smp = (struct opa_smp *)data;
 		u16 slid = be16_to_cpu(hdr->lrh[3]);
-		u8 sc5;
-
-		sc5 = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf;
-		sc5 |= sc4_bit;
 
 		if (opa_smp_check(ibp, pkey, sc5, qp, slid, smp))
 			goto drop;
@@ -890,9 +875,7 @@
 	}
 
 	wc.slid = be16_to_cpu(hdr->lrh[3]);
-	sc = (be16_to_cpu(hdr->lrh[0]) >> 12) & 0xf;
-	sc |= sc4_bit;
-	wc.sl = ibp->sc_to_sl[sc];
+	wc.sl = ibp->sc_to_sl[sc5];
 
 	/*
 	 * Save the LMC lower bits if the destination LID is a unicast LID.
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c
index bc95c41..d8fb056 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.c
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
@@ -92,11 +92,10 @@
 
 struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 				struct rvt_qp *qp)
+	__must_hold(&qp->s_lock)
 {
 	struct verbs_txreq *tx = ERR_PTR(-EBUSY);
-	unsigned long flags;
 
-	spin_lock_irqsave(&qp->s_lock, flags);
 	write_seqlock(&dev->iowait_lock);
 	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
 		struct hfi1_qp_priv *priv;
@@ -116,7 +115,6 @@
 	}
 out:
 	write_sequnlock(&dev->iowait_lock);
-	spin_unlock_irqrestore(&qp->s_lock, flags);
 	return tx;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index 1cf69b2..a1d6e080 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -73,6 +73,7 @@
 
 static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 					    struct rvt_qp *qp)
+	__must_hold(&qp->slock)
 {
 	struct verbs_txreq *tx;
 	struct hfi1_qp_priv *priv = qp->priv;
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index 8b95320..b738acd 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -113,6 +113,8 @@
 
 #define IW_HMC_OBJ_TYPE_NUM ARRAY_SIZE(iw_hmc_obj_types)
 #define IW_CFG_FPM_QP_COUNT		32768
+#define I40IW_MAX_PAGES_PER_FMR		512
+#define I40IW_MIN_PAGES_PER_FMR		1
 
 #define I40IW_MTU_TO_MSS		40
 #define I40IW_DEFAULT_MSS		1460
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index c963cad..6e90813 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -600,8 +600,7 @@
 	cqp_init_info.scratch_array = cqp->scratch_array;
 	status = dev->cqp_ops->cqp_init(dev->cqp, &cqp_init_info);
 	if (status) {
-		i40iw_pr_err("cqp init status %d maj_err %d min_err %d\n",
-			     status, maj_err, min_err);
+		i40iw_pr_err("cqp init status %d\n", status);
 		goto exit;
 	}
 	status = dev->cqp_ops->cqp_create(dev->cqp, true, &maj_err, &min_err);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 02a735b..283b64c 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -79,6 +79,7 @@
 	props->max_qp_init_rd_atom = props->max_qp_rd_atom;
 	props->atomic_cap = IB_ATOMIC_NONE;
 	props->max_map_per_fmr = 1;
+	props->max_fast_reg_page_list_len = I40IW_MAX_PAGES_PER_FMR;
 	return 0;
 }
 
@@ -1473,6 +1474,7 @@
 	info->stag_idx = iwmr->stag >> I40IW_CQPSQ_STAG_IDX_SHIFT;
 	info->pd_id = iwpd->sc_pd.pd_id;
 	info->total_len = iwmr->length;
+	info->remote_access = true;
 	cqp_info->cqp_cmd = OP_ALLOC_STAG;
 	cqp_info->post_sq = 1;
 	cqp_info->in.u.alloc_stag.dev = &iwdev->sc_dev;
@@ -1527,7 +1529,7 @@
 	mutex_lock(&iwdev->pbl_mutex);
 	status = i40iw_get_pble(&iwdev->sc_dev, iwdev->pble_rsrc, palloc, iwmr->page_cnt);
 	mutex_unlock(&iwdev->pbl_mutex);
-	if (!status)
+	if (status)
 		goto err1;
 
 	if (palloc->level != I40IW_LEVEL_1)
@@ -2149,6 +2151,7 @@
 			struct i40iw_sc_dev *dev = &iwqp->iwdev->sc_dev;
 			struct i40iw_fast_reg_stag_info info;
 
+			memset(&info, 0, sizeof(info));
 			info.access_rights = I40IW_ACCESS_FLAGS_LOCALREAD;
 			info.access_rights |= i40iw_get_user_access(flags);
 			info.stag_key = reg_wr(ib_wr)->key & 0xff;
@@ -2158,10 +2161,14 @@
 			info.addr_type = I40IW_ADDR_TYPE_VA_BASED;
 			info.va = (void *)(uintptr_t)iwmr->ibmr.iova;
 			info.total_len = iwmr->ibmr.length;
+			info.reg_addr_pa = *(u64 *)palloc->level1.addr;
 			info.first_pm_pbl_index = palloc->level1.idx;
 			info.local_fence = ib_wr->send_flags & IB_SEND_FENCE;
 			info.signaled = ib_wr->send_flags & IB_SEND_SIGNALED;
 
+			if (iwmr->npages > I40IW_MIN_PAGES_PER_FMR)
+				info.chunk_size = 1;
+
 			if (page_shift == 21)
 				info.page_size = 1; /* 2M page */
 
@@ -2327,13 +2334,16 @@
 {
 	struct i40iw_cq *iwcq;
 	struct i40iw_cq_uk *ukcq;
-	enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_SOLICITED;
+	unsigned long flags;
+	enum i40iw_completion_notify cq_notify = IW_CQ_COMPL_EVENT;
 
 	iwcq = (struct i40iw_cq *)ibcq;
 	ukcq = &iwcq->sc_cq.cq_uk;
-	if (notify_flags == IB_CQ_NEXT_COMP)
-		cq_notify = IW_CQ_COMPL_EVENT;
+	if (notify_flags == IB_CQ_SOLICITED)
+		cq_notify = IW_CQ_COMPL_SOLICITED;
+	spin_lock_irqsave(&iwcq->lock, flags);
 	ukcq->ops.iw_cq_request_notification(ukcq, cq_notify);
+	spin_unlock_irqrestore(&iwcq->lock, flags);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 105246f..5fc6233 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -47,6 +47,7 @@
 
 	ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
 	ah->av.ib.g_slid  = ah_attr->src_path_bits;
+	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 	if (ah_attr->ah_flags & IB_AH_GRH) {
 		ah->av.ib.g_slid   |= 0x80;
 		ah->av.ib.gid_index = ah_attr->grh.sgid_index;
@@ -64,7 +65,6 @@
 		       !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.ib.stat_rate;
 	}
-	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 
 	return &ah->ibah;
 }
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index d68f506..9c2e53d 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -527,7 +527,7 @@
 		tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
 	spin_unlock(&tun_qp->tx_lock);
 	if (ret)
-		goto out;
+		goto end;
 
 	tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr);
 	if (tun_qp->tx_ring[tun_tx_ix].ah)
@@ -596,9 +596,15 @@
 	wr.wr.send_flags = IB_SEND_SIGNALED;
 
 	ret = ib_post_send(src_qp, &wr.wr, &bad_wr);
-out:
-	if (ret)
-		ib_destroy_ah(ah);
+	if (!ret)
+		return 0;
+ out:
+	spin_lock(&tun_qp->tx_lock);
+	tun_qp->tx_ix_tail++;
+	spin_unlock(&tun_qp->tx_lock);
+	tun_qp->tx_ring[tun_tx_ix].ah = NULL;
+end:
+	ib_destroy_ah(ah);
 	return ret;
 }
 
@@ -1326,9 +1332,15 @@
 
 
 	ret = ib_post_send(send_qp, &wr.wr, &bad_wr);
+	if (!ret)
+		return 0;
+
+	spin_lock(&sqp->tx_lock);
+	sqp->tx_ix_tail++;
+	spin_unlock(&sqp->tx_lock);
+	sqp->tx_ring[wire_tx_ix].ah = NULL;
 out:
-	if (ret)
-		ib_destroy_ah(ah);
+	ib_destroy_ah(ah);
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 0eb09e1..42a4607 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1704,6 +1704,9 @@
 	struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
 	int is_bonded = mlx4_is_bonded(dev);
 
+	if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
+		return ERR_PTR(-EINVAL);
+
 	if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
 	    (flow_attr->type != IB_FLOW_ATTR_NORMAL))
 		return ERR_PTR(-EOPNOTSUPP);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6c5ac5d..29acda2 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -139,7 +139,7 @@
 	u32			max_pages;
 	struct mlx4_mr		mmr;
 	struct ib_umem	       *umem;
-	void			*pages_alloc;
+	size_t			page_map_size;
 };
 
 struct mlx4_ib_mw {
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 6312721..5d73989 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -277,20 +277,23 @@
 		      struct mlx4_ib_mr *mr,
 		      int max_pages)
 {
-	int size = max_pages * sizeof(u64);
-	int add_size;
 	int ret;
 
-	add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0);
+	/* Ensure that size is aligned to DMA cacheline
+	 * requirements.
+	 * max_pages is limited to MLX4_MAX_FAST_REG_PAGES
+	 * so page_map_size will never cross PAGE_SIZE.
+	 */
+	mr->page_map_size = roundup(max_pages * sizeof(u64),
+				    MLX4_MR_PAGES_ALIGN);
 
-	mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL);
-	if (!mr->pages_alloc)
+	/* Prevent cross page boundary allocation. */
+	mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL);
+	if (!mr->pages)
 		return -ENOMEM;
 
-	mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN);
-
 	mr->page_map = dma_map_single(device->dma_device, mr->pages,
-				      size, DMA_TO_DEVICE);
+				      mr->page_map_size, DMA_TO_DEVICE);
 
 	if (dma_mapping_error(device->dma_device, mr->page_map)) {
 		ret = -ENOMEM;
@@ -298,9 +301,9 @@
 	}
 
 	return 0;
-err:
-	kfree(mr->pages_alloc);
 
+err:
+	free_page((unsigned long)mr->pages);
 	return ret;
 }
 
@@ -309,11 +312,10 @@
 {
 	if (mr->pages) {
 		struct ib_device *device = mr->ibmr.device;
-		int size = mr->max_pages * sizeof(u64);
 
 		dma_unmap_single(device->dma_device, mr->page_map,
-				 size, DMA_TO_DEVICE);
-		kfree(mr->pages_alloc);
+				 mr->page_map_size, DMA_TO_DEVICE);
+		free_page((unsigned long)mr->pages);
 		mr->pages = NULL;
 	}
 }
@@ -537,14 +539,12 @@
 	mr->npages = 0;
 
 	ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
-				   sizeof(u64) * mr->max_pages,
-				   DMA_TO_DEVICE);
+				   mr->page_map_size, DMA_TO_DEVICE);
 
 	rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page);
 
 	ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
-				      sizeof(u64) * mr->max_pages,
-				      DMA_TO_DEVICE);
+				      mr->page_map_size, DMA_TO_DEVICE);
 
 	return rc;
 }
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 81b0e1fb..8db8405 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -362,7 +362,7 @@
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_RC:
 		return sizeof (struct mlx4_wqe_ctrl_seg) +
-			sizeof (struct mlx4_wqe_atomic_seg) +
+			sizeof (struct mlx4_wqe_masked_atomic_seg) +
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_SMI:
 	case MLX4_IB_QPT_GSI:
@@ -1191,8 +1191,10 @@
 	{
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
 				       udata, 0, &qp, gfp);
-		if (err)
+		if (err) {
+			kfree(qp);
 			return ERR_PTR(err);
+		}
 
 		qp->ibqp.qp_num = qp->mqp.qpn;
 		qp->xrcdn = xrcdn;
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 1534af1..364aab9 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -121,7 +121,7 @@
 	pma_cnt_ext->port_xmit_data =
 		cpu_to_be64(MLX5_SUM_CNT(out, transmitted_ib_unicast.octets,
 					 transmitted_ib_multicast.octets) >> 2);
-	pma_cnt_ext->port_xmit_data =
+	pma_cnt_ext->port_rcv_data =
 		cpu_to_be64(MLX5_SUM_CNT(out, received_ib_unicast.octets,
 					 received_ib_multicast.octets) >> 2);
 	pma_cnt_ext->port_xmit_packets =
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ce43422..ce0a7ab 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3332,10 +3332,11 @@
 			return MLX5_FENCE_MODE_SMALL_AND_FENCE;
 		else
 			return fence;
-
-	} else {
-		return 0;
+	} else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
+		return MLX5_FENCE_MODE_FENCE;
 	}
+
+	return 0;
 }
 
 static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index ff946d5..382466a 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -2178,6 +2178,11 @@
 
 	switch (cmd.type) {
 	case QIB_CMD_ASSIGN_CTXT:
+		if (rcd) {
+			ret = -EINVAL;
+			goto bail;
+		}
+
 		ret = qib_assign_ctxt(fp, &cmd.cmd.user_info);
 		if (ret)
 			goto bail;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 7de5134..41ba7e9 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -369,8 +369,8 @@
 			/* wrap to first map page, invert bit 0 */
 			offset = qpt->incr | ((offset & 1) ^ 1);
 		}
-		/* there can be no bits at shift and below */
-		WARN_ON(offset & (rdi->dparms.qos_shift - 1));
+		/* there can be no set bits in low-order QoS bits */
+		WARN_ON(offset & (BIT(rdi->dparms.qos_shift) - 1));
 		qpn = mk_qpn(qpt, map, offset);
 	}
 
@@ -576,12 +576,6 @@
 	qp->s_ssn = 1;
 	qp->s_lsn = 0;
 	qp->s_mig_state = IB_MIG_MIGRATED;
-	if (qp->s_ack_queue)
-		memset(
-			qp->s_ack_queue,
-			0,
-			rvt_max_atomic(rdi) *
-				sizeof(*qp->s_ack_queue));
 	qp->r_head_ack_queue = 0;
 	qp->s_tail_ack_queue = 0;
 	qp->s_num_rd_atomic = 0;
@@ -705,8 +699,10 @@
 		 * initialization that is needed.
 		 */
 		priv = rdi->driver_f.qp_priv_alloc(rdi, qp, gfp);
-		if (!priv)
+		if (IS_ERR(priv)) {
+			ret = priv;
 			goto bail_qp;
+		}
 		qp->priv = priv;
 		qp->timeout_jiffies =
 			usecs_to_jiffies((4096UL * (1UL << qp->timeout)) /
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index e1cc2cc..30c4fda 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -501,9 +501,7 @@
 			    !rdi->driver_f.quiesce_qp ||
 			    !rdi->driver_f.notify_error_qp ||
 			    !rdi->driver_f.mtu_from_qp ||
-			    !rdi->driver_f.mtu_to_path_mtu ||
-			    !rdi->driver_f.shut_down_port ||
-			    !rdi->driver_f.cap_mask_chg)
+			    !rdi->driver_f.mtu_to_path_mtu)
 				return -EINVAL;
 		break;
 
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index e68b20cb..4a41556 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1638,8 +1638,7 @@
 	 */
 	qp_init->cap.max_send_wr = srp_sq_size / 2;
 	qp_init->cap.max_rdma_ctxs = srp_sq_size / 2;
-	qp_init->cap.max_send_sge = max(sdev->device->attrs.max_sge_rd,
-					sdev->device->attrs.max_sge);
+	qp_init->cap.max_send_sge = SRPT_DEF_SG_PER_WQE;
 	qp_init->port_num = ch->sport->port;
 
 	ch->qp = ib_create_qp(sdev->pd, qp_init);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index fee6bfd..38903048 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -106,6 +106,7 @@
 	SRP_LOGIN_RSP_MULTICHAN_MAINTAINED = 0x2,
 
 	SRPT_DEF_SG_TABLESIZE = 128,
+	SRPT_DEF_SG_PER_WQE = 16,
 
 	MIN_SRPT_SQ_SIZE = 16,
 	DEF_SRPT_SQ_SIZE = 4096,
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 804dbcc..a529a45 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1031,17 +1031,17 @@
 
 	case XTYPE_XBOXONE:
 		packet->data[0] = 0x09; /* activate rumble */
-		packet->data[1] = 0x08;
+		packet->data[1] = 0x00;
 		packet->data[2] = xpad->odata_serial++;
-		packet->data[3] = 0x08; /* continuous effect */
-		packet->data[4] = 0x00; /* simple rumble mode */
-		packet->data[5] = 0x03; /* L and R actuator only */
-		packet->data[6] = 0x00; /* TODO: LT actuator */
-		packet->data[7] = 0x00; /* TODO: RT actuator */
+		packet->data[3] = 0x09;
+		packet->data[4] = 0x00;
+		packet->data[5] = 0x0F;
+		packet->data[6] = 0x00;
+		packet->data[7] = 0x00;
 		packet->data[8] = strong / 512;	/* left actuator */
 		packet->data[9] = weak / 512;	/* right actuator */
-		packet->data[10] = 0x80;	/* length of pulse */
-		packet->data[11] = 0x00;	/* stop period of pulse */
+		packet->data[10] = 0xFF;
+		packet->data[11] = 0x00;
 		packet->data[12] = 0x00;
 		packet->len = 13;
 		packet->pending = true;
@@ -1431,22 +1431,15 @@
 	int ep_irq_in_idx;
 	int i, error;
 
+	if (intf->cur_altsetting->desc.bNumEndpoints != 2)
+		return -ENODEV;
+
 	for (i = 0; xpad_device[i].idVendor; i++) {
 		if ((le16_to_cpu(udev->descriptor.idVendor) == xpad_device[i].idVendor) &&
 		    (le16_to_cpu(udev->descriptor.idProduct) == xpad_device[i].idProduct))
 			break;
 	}
 
-	if (xpad_device[i].xtype == XTYPE_XBOXONE &&
-	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
-		/*
-		 * The Xbox One controller lists three interfaces all with the
-		 * same interface class, subclass and protocol. Differentiate by
-		 * interface number.
-		 */
-		return -ENODEV;
-	}
-
 	xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL);
 	if (!xpad)
 		return -ENOMEM;
@@ -1478,6 +1471,8 @@
 		if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) {
 			if (intf->cur_altsetting->desc.bInterfaceProtocol == 129)
 				xpad->xtype = XTYPE_XBOX360W;
+			else if (intf->cur_altsetting->desc.bInterfaceProtocol == 208)
+				xpad->xtype = XTYPE_XBOXONE;
 			else
 				xpad->xtype = XTYPE_XBOX360;
 		} else {
@@ -1492,6 +1487,17 @@
 			xpad->mapping |= MAP_STICKS_TO_NULL;
 	}
 
+	if (xpad->xtype == XTYPE_XBOXONE &&
+	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
+		/*
+		 * The Xbox One controller lists three interfaces all with the
+		 * same interface class, subclass and protocol. Differentiate by
+		 * interface number.
+		 */
+		error = -ENODEV;
+		goto err_free_in_urb;
+	}
+
 	error = xpad_init_output(intf, xpad);
 	if (error)
 		goto err_free_in_urb;
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 78f93cf..be5b399 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1568,13 +1568,7 @@
 		case 5:
 			etd->hw_version = 3;
 			break;
-		case 6:
-		case 7:
-		case 8:
-		case 9:
-		case 10:
-		case 13:
-		case 14:
+		case 6 ... 14:
 			etd->hw_version = 4;
 			break;
 		default:
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index a3f0f5a..0f58678 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -355,18 +355,11 @@
 		return -ENXIO;
 	}
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	/* Check if the device is present */
 	response = ~VMMOUSE_PROTO_MAGIC;
 	VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2);
-	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) {
-		release_region(VMMOUSE_PROTO_PORT, 4);
+	if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU)
 		return -ENXIO;
-	}
 
 	if (set_properties) {
 		psmouse->vendor = VMMOUSE_VENDOR;
@@ -374,8 +367,6 @@
 		psmouse->model = version;
 	}
 
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return 0;
 }
 
@@ -394,7 +385,6 @@
 	psmouse_reset(psmouse);
 	input_unregister_device(priv->abs_dev);
 	kfree(priv);
-	release_region(VMMOUSE_PROTO_PORT, 4);
 }
 
 /**
@@ -438,15 +428,10 @@
 	struct input_dev *rel_dev = psmouse->dev, *abs_dev;
 	int error;
 
-	if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) {
-		psmouse_dbg(psmouse, "VMMouse port in use.\n");
-		return -EBUSY;
-	}
-
 	psmouse_reset(psmouse);
 	error = vmmouse_enable(psmouse);
 	if (error)
-		goto release_region;
+		return error;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	abs_dev = input_allocate_device();
@@ -502,8 +487,5 @@
 	kfree(priv);
 	psmouse->private = NULL;
 
-release_region:
-	release_region(VMMOUSE_PROTO_PORT, 4);
-
 	return error;
 }
diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c
index b368b05..253df96 100644
--- a/drivers/input/rmi4/rmi_bus.c
+++ b/drivers/input/rmi4/rmi_bus.c
@@ -157,11 +157,11 @@
 static void rmi_function_of_probe(struct rmi_function *fn)
 {
 	char of_name[9];
+	struct device_node *node = fn->rmi_dev->xport->dev->of_node;
 
 	snprintf(of_name, sizeof(of_name), "rmi4-f%02x",
 		fn->fd.function_number);
-	fn->dev.of_node = of_find_node_by_name(
-				fn->rmi_dev->xport->dev->of_node, of_name);
+	fn->dev.of_node = of_get_child_by_name(node, of_name);
 }
 #else
 static inline void rmi_function_of_probe(struct rmi_function *fn)
diff --git a/drivers/input/rmi4/rmi_f12.c b/drivers/input/rmi4/rmi_f12.c
index 8dd3fb5..88e9155 100644
--- a/drivers/input/rmi4/rmi_f12.c
+++ b/drivers/input/rmi4/rmi_f12.c
@@ -66,7 +66,7 @@
 	struct rmi_device *rmi_dev = fn->rmi_dev;
 	int ret;
 	int offset;
-	u8 buf[14];
+	u8 buf[15];
 	int pitch_x = 0;
 	int pitch_y = 0;
 	int clip_x_low = 0;
@@ -86,9 +86,10 @@
 
 	offset = rmi_register_desc_calc_reg_offset(&f12->control_reg_desc, 8);
 
-	if (item->reg_size > 14) {
-		dev_err(&fn->dev, "F12 control8 should be 14 bytes, not: %ld\n",
-			item->reg_size);
+	if (item->reg_size > sizeof(buf)) {
+		dev_err(&fn->dev,
+			"F12 control8 should be no bigger than %zd bytes, not: %ld\n",
+			sizeof(buf), item->reg_size);
 		return -ENODEV;
 	}
 
diff --git a/drivers/input/touchscreen/ts4800-ts.c b/drivers/input/touchscreen/ts4800-ts.c
index 3c3dd78..fed73ee 100644
--- a/drivers/input/touchscreen/ts4800-ts.c
+++ b/drivers/input/touchscreen/ts4800-ts.c
@@ -118,6 +118,13 @@
 		return -ENODEV;
 	}
 
+	ts->regmap = syscon_node_to_regmap(syscon_np);
+	of_node_put(syscon_np);
+	if (IS_ERR(ts->regmap)) {
+		dev_err(dev, "cannot get parent's regmap\n");
+		return PTR_ERR(ts->regmap);
+	}
+
 	error = of_property_read_u32_index(np, "syscon", 1, &reg);
 	if (error < 0) {
 		dev_err(dev, "no offset in syscon\n");
@@ -134,12 +141,6 @@
 
 	ts->bit = BIT(bit);
 
-	ts->regmap = syscon_node_to_regmap(syscon_np);
-	if (IS_ERR(ts->regmap)) {
-		dev_err(dev, "cannot get parent's regmap\n");
-		return PTR_ERR(ts->regmap);
-	}
-
 	return 0;
 }
 
diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c
index 7295c19..6fe55d5 100644
--- a/drivers/input/touchscreen/tsc2004.c
+++ b/drivers/input/touchscreen/tsc2004.c
@@ -22,6 +22,11 @@
 #include <linux/regmap.h>
 #include "tsc200x-core.h"
 
+static const struct input_id tsc2004_input_id = {
+	.bustype = BUS_I2C,
+	.product = 2004,
+};
+
 static int tsc2004_cmd(struct device *dev, u8 cmd)
 {
 	u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd;
@@ -42,7 +47,7 @@
 			 const struct i2c_device_id *id)
 
 {
-	return tsc200x_probe(&i2c->dev, i2c->irq, BUS_I2C,
+	return tsc200x_probe(&i2c->dev, i2c->irq, &tsc2004_input_id,
 			     devm_regmap_init_i2c(i2c, &tsc200x_regmap_config),
 			     tsc2004_cmd);
 }
diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c
index b9f593d..f2c5f0e47 100644
--- a/drivers/input/touchscreen/tsc2005.c
+++ b/drivers/input/touchscreen/tsc2005.c
@@ -24,6 +24,11 @@
 #include <linux/regmap.h>
 #include "tsc200x-core.h"
 
+static const struct input_id tsc2005_input_id = {
+	.bustype = BUS_SPI,
+	.product = 2005,
+};
+
 static int tsc2005_cmd(struct device *dev, u8 cmd)
 {
 	u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd;
@@ -62,7 +67,7 @@
 	if (error)
 		return error;
 
-	return tsc200x_probe(&spi->dev, spi->irq, BUS_SPI,
+	return tsc200x_probe(&spi->dev, spi->irq, &tsc2005_input_id,
 			     devm_regmap_init_spi(spi, &tsc200x_regmap_config),
 			     tsc2005_cmd);
 }
diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c
index 15240c1..dfa7f1c 100644
--- a/drivers/input/touchscreen/tsc200x-core.c
+++ b/drivers/input/touchscreen/tsc200x-core.c
@@ -450,7 +450,7 @@
 	mutex_unlock(&ts->mutex);
 }
 
-int tsc200x_probe(struct device *dev, int irq, __u16 bustype,
+int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id,
 		  struct regmap *regmap,
 		  int (*tsc200x_cmd)(struct device *dev, u8 cmd))
 {
@@ -547,9 +547,18 @@
 	snprintf(ts->phys, sizeof(ts->phys),
 		 "%s/input-ts", dev_name(dev));
 
-	input_dev->name = "TSC200X touchscreen";
+	if (tsc_id->product == 2004) {
+		input_dev->name = "TSC200X touchscreen";
+	} else {
+		input_dev->name = devm_kasprintf(dev, GFP_KERNEL,
+						 "TSC%04d touchscreen",
+						 tsc_id->product);
+		if (!input_dev->name)
+			return -ENOMEM;
+	}
+
 	input_dev->phys = ts->phys;
-	input_dev->id.bustype = bustype;
+	input_dev->id = *tsc_id;
 	input_dev->dev.parent = dev;
 	input_dev->evbit[0] = BIT(EV_ABS) | BIT(EV_KEY);
 	input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
diff --git a/drivers/input/touchscreen/tsc200x-core.h b/drivers/input/touchscreen/tsc200x-core.h
index 7a482d10..49a63a3 100644
--- a/drivers/input/touchscreen/tsc200x-core.h
+++ b/drivers/input/touchscreen/tsc200x-core.h
@@ -70,7 +70,7 @@
 extern const struct regmap_config tsc200x_regmap_config;
 extern const struct dev_pm_ops tsc200x_pm_ops;
 
-int tsc200x_probe(struct device *dev, int irq, __u16 bustype,
+int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id,
 		  struct regmap *regmap,
 		  int (*tsc200x_cmd)(struct device *dev, u8 cmd));
 int tsc200x_remove(struct device *dev);
diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c
index bab3c6acf..b6fc4bd 100644
--- a/drivers/input/touchscreen/wacom_w8001.c
+++ b/drivers/input/touchscreen/wacom_w8001.c
@@ -27,7 +27,7 @@
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-#define W8001_MAX_LENGTH	11
+#define W8001_MAX_LENGTH	13
 #define W8001_LEAD_MASK		0x80
 #define W8001_LEAD_BYTE		0x80
 #define W8001_TAB_MASK		0x40
@@ -155,6 +155,7 @@
 		bool touch = data[0] & (1 << i);
 
 		input_mt_slot(dev, i);
+		input_mt_report_slot_state(dev, MT_TOOL_FINGER, touch);
 		if (touch) {
 			x = (data[6 * i + 1] << 7) | data[6 * i + 2];
 			y = (data[6 * i + 3] << 7) | data[6 * i + 4];
@@ -339,6 +340,15 @@
 		w8001->idx = 0;
 		parse_multi_touch(w8001);
 		break;
+
+	default:
+		/*
+		 * ThinkPad X60 Tablet PC (pen only device) sometimes
+		 * sends invalid data packets that are larger than
+		 * W8001_PKTLEN_TPCPEN. Let's start over again.
+		 */
+		if (!w8001->touch_dev && w8001->idx > W8001_PKTLEN_TPCPEN - 1)
+			w8001->idx = 0;
 	}
 
 	return IRQ_HANDLED;
@@ -513,6 +523,8 @@
 					0, touch.x, 0, 0);
 		input_set_abs_params(dev, ABS_MT_POSITION_Y,
 					0, touch.y, 0, 0);
+		input_set_abs_params(dev, ABS_MT_TOOL_TYPE,
+					0, MT_TOOL_MAX, 0, 0);
 
 		strlcat(basename, " 2FG", basename_sz);
 		if (w8001->max_pen_x && w8001->max_pen_y)
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 9e00341..59741ea 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1107,13 +1107,13 @@
 				break;
 			}
 
+			devid = e->devid;
 			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n",
 				    hid, uid,
 				    PCI_BUS_NUM(devid),
 				    PCI_SLOT(devid),
 				    PCI_FUNC(devid));
 
-			devid  = e->devid;
 			flags = e->flags;
 
 			ret = add_acpi_hid_device(hid, uid, &devid, false);
@@ -1568,13 +1568,23 @@
 			break;
 	}
 
+	/*
+	 * Order is important here to make sure any unity map requirements are
+	 * fulfilled. The unity mappings are created and written to the device
+	 * table during the amd_iommu_init_api() call.
+	 *
+	 * After that we call init_device_table_dma() to make sure any
+	 * uninitialized DTE will block DMA, and in the end we flush the caches
+	 * of all IOMMUs to make sure the changes to the device table are
+	 * active.
+	 */
+	ret = amd_iommu_init_api();
+
 	init_device_table_dma();
 
 	for_each_iommu(iommu)
 		iommu_flush_all_caches(iommu);
 
-	ret = amd_iommu_init_api();
-
 	if (!ret)
 		print_iommu_info();
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1070094..323dac9 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4602,13 +4602,13 @@
 	for (i = 0; i < g_num_of_iommus; i++) {
 		struct intel_iommu *iommu = g_iommus[i];
 		struct dmar_domain *domain;
-		u16 did;
+		int did;
 
 		if (!iommu)
 			continue;
 
-		for (did = 0; did < 0xffff; did++) {
-			domain = get_iommu_domain(iommu, did);
+		for (did = 0; did < cap_ndoms(iommu->cap); did++) {
+			domain = get_iommu_domain(iommu, (u16)did);
 
 			if (!domain)
 				continue;
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index ba764a0..e23001b 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -420,8 +420,10 @@
 
 		/* Try replenishing IOVAs by flushing rcache. */
 		flushed_rcache = true;
+		preempt_disable();
 		for_each_online_cpu(cpu)
 			free_cpu_cached_iovas(cpu, iovad);
+		preempt_enable();
 		goto retry;
 	}
 
@@ -749,7 +751,7 @@
 	bool can_insert = false;
 	unsigned long flags;
 
-	cpu_rcache = this_cpu_ptr(rcache->cpu_rcaches);
+	cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
 	spin_lock_irqsave(&cpu_rcache->lock, flags);
 
 	if (!iova_magazine_full(cpu_rcache->loaded)) {
@@ -779,6 +781,7 @@
 		iova_magazine_push(cpu_rcache->loaded, iova_pfn);
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	put_cpu_ptr(rcache->cpu_rcaches);
 
 	if (mag_to_free) {
 		iova_magazine_free_pfns(mag_to_free, iovad);
@@ -812,7 +815,7 @@
 	bool has_pfn = false;
 	unsigned long flags;
 
-	cpu_rcache = this_cpu_ptr(rcache->cpu_rcaches);
+	cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
 	spin_lock_irqsave(&cpu_rcache->lock, flags);
 
 	if (!iova_magazine_empty(cpu_rcache->loaded)) {
@@ -834,6 +837,7 @@
 		iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	put_cpu_ptr(rcache->cpu_rcaches);
 
 	return iova_pfn;
 }
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 3b5e10a..70ed1d0 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -718,7 +718,7 @@
 
 	spin_lock_irqsave(&gic_lock, flags);
 	gic_map_to_pin(intr, gic_cpu_pin);
-	gic_map_to_vpe(intr, vpe);
+	gic_map_to_vpe(intr, mips_cm_vp_id(vpe));
 	for (i = 0; i < min(gic_vpes, NR_CPUS); i++)
 		clear_bit(intr, pcpu_masks[i].pcpu_mask);
 	set_bit(intr, pcpu_masks[vpe].pcpu_mask);
@@ -746,6 +746,12 @@
 		/* verify that it doesn't conflict with an IPI irq */
 		if (test_bit(spec->hwirq, ipi_resrv))
 			return -EBUSY;
+
+		hwirq = GIC_SHARED_TO_HWIRQ(spec->hwirq);
+
+		return irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+						     &gic_level_irq_controller,
+						     NULL);
 	} else {
 		base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
 		if (base_hwirq == gic_shared_intrs) {
@@ -867,10 +873,14 @@
 						    &gic_level_irq_controller,
 						    NULL);
 		if (ret)
-			return ret;
+			goto error;
 	}
 
 	return 0;
+
+error:
+	irq_domain_free_irqs_parent(d, virq, nr_irqs);
+	return ret;
 }
 
 void gic_dev_domain_free(struct irq_domain *d, unsigned int virq,
@@ -949,7 +959,7 @@
 	switch (bus_token) {
 	case DOMAIN_BUS_IPI:
 		is_ipi = d->bus_token == bus_token;
-		return to_of_node(d->fwnode) == node && is_ipi;
+		return (!node || to_of_node(d->fwnode) == node) && is_ipi;
 		break;
 	default:
 		return 0;
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index beb2841..3f1ab49 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -779,11 +779,31 @@
 			V4L2_DV_BT_CAP_CUSTOM)
 };
 
-static inline const struct v4l2_dv_timings_cap *
-adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd)
+/*
+ * Return the DV timings capabilities for the requested sink pad. As a special
+ * case, pad value -1 returns the capabilities for the currently selected input.
+ */
+static const struct v4l2_dv_timings_cap *
+adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd, int pad)
 {
-	return is_digital_input(sd) ? &adv76xx_timings_cap_digital :
-				      &adv7604_timings_cap_analog;
+	if (pad == -1) {
+		struct adv76xx_state *state = to_state(sd);
+
+		pad = state->selected_input;
+	}
+
+	switch (pad) {
+	case ADV76XX_PAD_HDMI_PORT_A:
+	case ADV7604_PAD_HDMI_PORT_B:
+	case ADV7604_PAD_HDMI_PORT_C:
+	case ADV7604_PAD_HDMI_PORT_D:
+		return &adv76xx_timings_cap_digital;
+
+	case ADV7604_PAD_VGA_RGB:
+	case ADV7604_PAD_VGA_COMP:
+	default:
+		return &adv7604_timings_cap_analog;
+	}
 }
 
 
@@ -1329,7 +1349,7 @@
 		const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt;
 
 		if (!v4l2_valid_dv_timings(&v4l2_dv_timings_presets[i],
-					   adv76xx_get_dv_timings_cap(sd),
+					   adv76xx_get_dv_timings_cap(sd, -1),
 					   adv76xx_check_dv_timings, NULL))
 			continue;
 		if (vtotal(bt) != stdi->lcf + 1)
@@ -1430,18 +1450,22 @@
 		return -EINVAL;
 
 	return v4l2_enum_dv_timings_cap(timings,
-		adv76xx_get_dv_timings_cap(sd), adv76xx_check_dv_timings, NULL);
+		adv76xx_get_dv_timings_cap(sd, timings->pad),
+		adv76xx_check_dv_timings, NULL);
 }
 
 static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd,
 			struct v4l2_dv_timings_cap *cap)
 {
 	struct adv76xx_state *state = to_state(sd);
+	unsigned int pad = cap->pad;
 
 	if (cap->pad >= state->source_pad)
 		return -EINVAL;
 
-	*cap = *adv76xx_get_dv_timings_cap(sd);
+	*cap = *adv76xx_get_dv_timings_cap(sd, pad);
+	cap->pad = pad;
+
 	return 0;
 }
 
@@ -1450,9 +1474,9 @@
 static void adv76xx_fill_optional_dv_timings_fields(struct v4l2_subdev *sd,
 		struct v4l2_dv_timings *timings)
 {
-	v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd),
-			is_digital_input(sd) ? 250000 : 1000000,
-			adv76xx_check_dv_timings, NULL);
+	v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd, -1),
+				 is_digital_input(sd) ? 250000 : 1000000,
+				 adv76xx_check_dv_timings, NULL);
 }
 
 static unsigned int adv7604_read_hdmi_pixelclock(struct v4l2_subdev *sd)
@@ -1620,7 +1644,7 @@
 
 	bt = &timings->bt;
 
-	if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd),
+	if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd, -1),
 				   adv76xx_check_dv_timings, NULL))
 		return -ERANGE;
 
diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c
index 87c1293..92d9d42 100644
--- a/drivers/media/usb/airspy/airspy.c
+++ b/drivers/media/usb/airspy/airspy.c
@@ -1072,7 +1072,7 @@
 	if (ret) {
 		dev_err(s->dev, "Failed to register as video device (%d)\n",
 				ret);
-		goto err_unregister_v4l2_dev;
+		goto err_free_controls;
 	}
 	dev_info(s->dev, "Registered as %s\n",
 			video_device_node_name(&s->vdev));
@@ -1081,7 +1081,6 @@
 
 err_free_controls:
 	v4l2_ctrl_handler_free(&s->hdl);
-err_unregister_v4l2_dev:
 	v4l2_device_unregister(&s->v4l2_dev);
 err_free_mem:
 	kfree(s);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 28e5be2..528390f 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -2171,7 +2171,7 @@
 	 * The determine_valid_ioctls() call already should ensure
 	 * that this can never happen, but just in case...
 	 */
-	if (WARN_ON(!ops->vidioc_cropcap && !ops->vidioc_cropcap))
+	if (WARN_ON(!ops->vidioc_cropcap && !ops->vidioc_g_selection))
 		return -ENOTTY;
 
 	if (ops->vidioc_cropcap)
diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c
index 199d261..f32fbb8 100644
--- a/drivers/mfd/max77620.c
+++ b/drivers/mfd/max77620.c
@@ -203,6 +203,7 @@
 		break;
 	case MAX77620:
 		fps_min_period = MAX77620_FPS_PERIOD_MIN_US;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -236,6 +237,7 @@
 		break;
 	case MAX77620:
 		fps_max_period = MAX77620_FPS_PERIOD_MAX_US;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index e62fde3..c5472e3 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -355,8 +355,10 @@
 		goto idata_err;
 	}
 
-	if (!idata->buf_bytes)
+	if (!idata->buf_bytes) {
+		idata->buf = NULL;
 		return idata;
+	}
 
 	idata->buf = kmalloc(idata->buf_bytes, GFP_KERNEL);
 	if (!idata->buf) {
@@ -1786,8 +1788,8 @@
 
 	packed_cmd_hdr = packed->cmd_hdr;
 	memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr));
-	packed_cmd_hdr[0] = (packed->nr_entries << 16) |
-		(PACKED_CMD_WR << 8) | PACKED_CMD_VER;
+	packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) |
+		(PACKED_CMD_WR << 8) | PACKED_CMD_VER);
 	hdr_blocks = mmc_large_sector(card) ? 8 : 1;
 
 	/*
@@ -1801,14 +1803,14 @@
 			((brq->data.blocks * brq->data.blksz) >=
 			 card->ext_csd.data_tag_unit_size);
 		/* Argument of CMD23 */
-		packed_cmd_hdr[(i * 2)] =
+		packed_cmd_hdr[(i * 2)] = cpu_to_le32(
 			(do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) |
 			(do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) |
-			blk_rq_sectors(prq);
+			blk_rq_sectors(prq));
 		/* Argument of CMD18 or CMD25 */
-		packed_cmd_hdr[((i * 2)) + 1] =
+		packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32(
 			mmc_card_blockaddr(card) ?
-			blk_rq_pos(prq) : blk_rq_pos(prq) << 9;
+			blk_rq_pos(prq) : blk_rq_pos(prq) << 9);
 		packed->blocks += blk_rq_sectors(prq);
 		i++;
 	}
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 86fac3e..c763b40 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -789,14 +789,16 @@
 		gpio_direction_output(gpio_power,
 				      host->pdata->gpio_power_invert);
 	}
-	if (gpio_is_valid(gpio_ro))
+	if (gpio_is_valid(gpio_ro)) {
 		ret = mmc_gpio_request_ro(mmc, gpio_ro);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
-		goto out;
-	} else {
-		mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
-			0 : MMC_CAP2_RO_ACTIVE_HIGH;
+		if (ret) {
+			dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n",
+				gpio_ro);
+			goto out;
+		} else {
+			mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
+				0 : MMC_CAP2_RO_ACTIVE_HIGH;
+		}
 	}
 
 	if (gpio_is_valid(gpio_cd))
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 08e1588..a136da8 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1657,8 +1657,11 @@
 
 	/* detect availability of ELM module. Won't be present pre-OMAP4 */
 	info->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0);
-	if (!info->elm_of_node)
-		dev_dbg(dev, "ti,elm-id not in DT\n");
+	if (!info->elm_of_node) {
+		info->elm_of_node = of_parse_phandle(child, "elm_id", 0);
+		if (!info->elm_of_node)
+			dev_dbg(dev, "ti,elm-id not in DT\n");
+	}
 
 	/* select ecc-scheme for NAND */
 	if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) {
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 5780dd1..ebf5172 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -575,6 +575,7 @@
 	int err, idx = vol_id2idx(ubi, vol_id), new_pnum, data_size, tries = 0;
 	struct ubi_volume *vol = ubi->volumes[idx];
 	struct ubi_vid_hdr *vid_hdr;
+	uint32_t crc;
 
 	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
 	if (!vid_hdr)
@@ -599,14 +600,8 @@
 		goto out_put;
 	}
 
-	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
-	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
-	if (err) {
-		up_read(&ubi->fm_eba_sem);
-		goto write_error;
-	}
+	ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
 
-	data_size = offset + len;
 	mutex_lock(&ubi->buf_mutex);
 	memset(ubi->peb_buf + offset, 0xFF, len);
 
@@ -621,6 +616,19 @@
 
 	memcpy(ubi->peb_buf + offset, buf, len);
 
+	data_size = offset + len;
+	crc = crc32(UBI_CRC32_INIT, ubi->peb_buf, data_size);
+	vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi));
+	vid_hdr->copy_flag = 1;
+	vid_hdr->data_size = cpu_to_be32(data_size);
+	vid_hdr->data_crc = cpu_to_be32(crc);
+	err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr);
+	if (err) {
+		mutex_unlock(&ubi->buf_mutex);
+		up_read(&ubi->fm_eba_sem);
+		goto write_error;
+	}
+
 	err = ubi_io_write_data(ubi, ubi->peb_buf, new_pnum, 0, data_size);
 	if (err) {
 		mutex_unlock(&ubi->buf_mutex);
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index b9304a2..edc70ff 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -101,11 +101,14 @@
 #define MAC_ADDRESS_EQUAL(A, B)	\
 	ether_addr_equal_64bits((const u8 *)A, (const u8 *)B)
 
-static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } };
+static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
+	0, 0, 0, 0, 0, 0
+};
 static u16 ad_ticks_per_sec;
 static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
 
-static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned =
+	MULTICAST_LACPDU_ADDR;
 
 /* ================= main 802.3ad protocol functions ================== */
 static int ad_lacpdu_send(struct port *port);
@@ -657,6 +660,20 @@
 	}
 }
 
+static int __agg_active_ports(struct aggregator *agg)
+{
+	struct port *port;
+	int active = 0;
+
+	for (port = agg->lag_ports; port;
+	     port = port->next_port_in_aggregator) {
+		if (port->is_enabled)
+			active++;
+	}
+
+	return active;
+}
+
 /**
  * __get_agg_bandwidth - get the total bandwidth of an aggregator
  * @aggregator: the aggregator we're looking at
@@ -664,39 +681,40 @@
  */
 static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 {
+	int nports = __agg_active_ports(aggregator);
 	u32 bandwidth = 0;
 
-	if (aggregator->num_of_ports) {
+	if (nports) {
 		switch (__get_link_speed(aggregator->lag_ports)) {
 		case AD_LINK_SPEED_1MBPS:
-			bandwidth = aggregator->num_of_ports;
+			bandwidth = nports;
 			break;
 		case AD_LINK_SPEED_10MBPS:
-			bandwidth = aggregator->num_of_ports * 10;
+			bandwidth = nports * 10;
 			break;
 		case AD_LINK_SPEED_100MBPS:
-			bandwidth = aggregator->num_of_ports * 100;
+			bandwidth = nports * 100;
 			break;
 		case AD_LINK_SPEED_1000MBPS:
-			bandwidth = aggregator->num_of_ports * 1000;
+			bandwidth = nports * 1000;
 			break;
 		case AD_LINK_SPEED_2500MBPS:
-			bandwidth = aggregator->num_of_ports * 2500;
+			bandwidth = nports * 2500;
 			break;
 		case AD_LINK_SPEED_10000MBPS:
-			bandwidth = aggregator->num_of_ports * 10000;
+			bandwidth = nports * 10000;
 			break;
 		case AD_LINK_SPEED_20000MBPS:
-			bandwidth = aggregator->num_of_ports * 20000;
+			bandwidth = nports * 20000;
 			break;
 		case AD_LINK_SPEED_40000MBPS:
-			bandwidth = aggregator->num_of_ports * 40000;
+			bandwidth = nports * 40000;
 			break;
 		case AD_LINK_SPEED_56000MBPS:
-			bandwidth = aggregator->num_of_ports * 56000;
+			bandwidth = nports * 56000;
 			break;
 		case AD_LINK_SPEED_100000MBPS:
-			bandwidth = aggregator->num_of_ports * 100000;
+			bandwidth = nports * 100000;
 			break;
 		default:
 			bandwidth = 0; /* to silence the compiler */
@@ -1530,10 +1548,10 @@
 
 	switch (__get_agg_selection_mode(curr->lag_ports)) {
 	case BOND_AD_COUNT:
-		if (curr->num_of_ports > best->num_of_ports)
+		if (__agg_active_ports(curr) > __agg_active_ports(best))
 			return curr;
 
-		if (curr->num_of_ports < best->num_of_ports)
+		if (__agg_active_ports(curr) < __agg_active_ports(best))
 			return best;
 
 		/*FALLTHROUGH*/
@@ -1561,8 +1579,14 @@
 	if (!port)
 		return 0;
 
-	return netif_running(port->slave->dev) &&
-	       netif_carrier_ok(port->slave->dev);
+	for (port = agg->lag_ports; port;
+	     port = port->next_port_in_aggregator) {
+		if (netif_running(port->slave->dev) &&
+		    netif_carrier_ok(port->slave->dev))
+			return 1;
+	}
+
+	return 0;
 }
 
 /**
@@ -1610,7 +1634,7 @@
 
 		agg->is_active = 0;
 
-		if (agg->num_of_ports && agg_device_up(agg))
+		if (__agg_active_ports(agg) && agg_device_up(agg))
 			best = ad_agg_selection_test(best, agg);
 	}
 
@@ -1622,7 +1646,7 @@
 		 * answering partner.
 		 */
 		if (active && active->lag_ports &&
-		    active->lag_ports->is_enabled &&
+		    __agg_active_ports(active) &&
 		    (__agg_has_partner(active) ||
 		     (!__agg_has_partner(active) &&
 		     !__agg_has_partner(best)))) {
@@ -1718,7 +1742,7 @@
 		aggregator->is_individual = false;
 		aggregator->actor_admin_aggregator_key = 0;
 		aggregator->actor_oper_aggregator_key = 0;
-		aggregator->partner_system = null_mac_addr;
+		eth_zero_addr(aggregator->partner_system.mac_addr_value);
 		aggregator->partner_system_priority = 0;
 		aggregator->partner_oper_aggregator_key = 0;
 		aggregator->receive_state = 0;
@@ -1740,7 +1764,7 @@
 	if (aggregator) {
 		ad_clear_agg(aggregator);
 
-		aggregator->aggregator_mac_address = null_mac_addr;
+		eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value);
 		aggregator->aggregator_identifier = 0;
 		aggregator->slave = NULL;
 	}
@@ -2133,7 +2157,7 @@
 				else
 					temp_aggregator->lag_ports = temp_port->next_port_in_aggregator;
 				temp_aggregator->num_of_ports--;
-				if (temp_aggregator->num_of_ports == 0) {
+				if (__agg_active_ports(temp_aggregator) == 0) {
 					select_new_active_agg = temp_aggregator->is_active;
 					ad_clear_agg(temp_aggregator);
 					if (select_new_active_agg) {
@@ -2432,7 +2456,9 @@
  */
 void bond_3ad_handle_link_change(struct slave *slave, char link)
 {
+	struct aggregator *agg;
 	struct port *port;
+	bool dummy;
 
 	port = &(SLAVE_AD_INFO(slave)->port);
 
@@ -2459,6 +2485,9 @@
 		port->is_enabled = false;
 		ad_update_actor_keys(port, true);
 	}
+	agg = __get_first_agg(port);
+	ad_agg_selection_logic(agg, &dummy);
+
 	netdev_dbg(slave->bond->dev, "Port %d changed link status to %s\n",
 		   port->actor_port_number,
 		   link == BOND_LINK_UP ? "UP" : "DOWN");
@@ -2499,7 +2528,7 @@
 	active = __get_active_agg(&(SLAVE_AD_INFO(first_slave)->aggregator));
 	if (active) {
 		/* are enough slaves available to consider link up? */
-		if (active->num_of_ports < bond->params.min_links) {
+		if (__agg_active_ports(active) < bond->params.min_links) {
 			if (netif_carrier_ok(bond->dev)) {
 				netif_carrier_off(bond->dev);
 				goto out;
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c5ac160..551f0f8 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -42,13 +42,10 @@
 
 
 
-#ifndef __long_aligned
-#define __long_aligned __attribute__((aligned((sizeof(long)))))
-#endif
-static const u8 mac_bcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = {
 	0xff, 0xff, 0xff, 0xff, 0xff, 0xff
 };
-static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {
 	0x33, 0x33, 0x00, 0x00, 0x00, 0x01
 };
 static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 941ec99..a2afa3b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1584,6 +1584,7 @@
 	}
 
 	/* check for initial state */
+	new_slave->link = BOND_LINK_NOCHANGE;
 	if (bond->params.miimon) {
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index db760e8..b8df0f5 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -446,7 +446,11 @@
 	if (err < 0)
 		return err;
 
-	return register_netdevice(bond_dev);
+	err = register_netdevice(bond_dev);
+
+	netif_carrier_off(bond_dev);
+
+	return err;
 }
 
 static size_t bond_get_size(const struct net_device *bond_dev)
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 8b3275d..8f5e93c 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -712,9 +712,10 @@
 
 	/* upper group completed, look again in lower */
 	if (priv->rx_next > get_mb_rx_low_last(priv) &&
-	    quota > 0 && mb > get_mb_rx_last(priv)) {
+	    mb > get_mb_rx_last(priv)) {
 		priv->rx_next = get_mb_rx_first(priv);
-		goto again;
+		if (quota > 0)
+			goto again;
 	}
 
 	return received;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index f91b094..e3dccd3 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -332,9 +332,23 @@
 
 	priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl);
 
-	for (i = 0; i < frame->can_dlc; i += 2) {
-		priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2,
-				frame->data[i] | (frame->data[i + 1] << 8));
+	if (priv->type == BOSCH_D_CAN) {
+		u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
+
+		for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+			data = (u32)frame->data[i];
+			data |= (u32)frame->data[i + 1] << 8;
+			data |= (u32)frame->data[i + 2] << 16;
+			data |= (u32)frame->data[i + 3] << 24;
+			priv->write_reg32(priv, dreg, data);
+		}
+	} else {
+		for (i = 0; i < frame->can_dlc; i += 2) {
+			priv->write_reg(priv,
+					C_CAN_IFACE(DATA1_REG, iface) + i / 2,
+					frame->data[i] |
+					(frame->data[i + 1] << 8));
+		}
 	}
 }
 
@@ -402,10 +416,20 @@
 	} else {
 		int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
 
-		for (i = 0; i < frame->can_dlc; i += 2, dreg ++) {
-			data = priv->read_reg(priv, dreg);
-			frame->data[i] = data;
-			frame->data[i + 1] = data >> 8;
+		if (priv->type == BOSCH_D_CAN) {
+			for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+				data = priv->read_reg32(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+				frame->data[i + 2] = data >> 16;
+				frame->data[i + 3] = data >> 24;
+			}
+		} else {
+			for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+				data = priv->read_reg(priv, dreg);
+				frame->data[i] = data;
+				frame->data[i + 1] = data >> 8;
+			}
 		}
 	}
 
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 910c12e..ad535a8 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -798,6 +798,9 @@
 	 * - control mode with CAN_CTRLMODE_FD set
 	 */
 
+	if (!data)
+		return 0;
+
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
 
@@ -1008,6 +1011,11 @@
 	return -EOPNOTSUPP;
 }
 
+static void can_dellink(struct net_device *dev, struct list_head *head)
+{
+	return;
+}
+
 static struct rtnl_link_ops can_link_ops __read_mostly = {
 	.kind		= "can",
 	.maxtype	= IFLA_CAN_MAX,
@@ -1016,6 +1024,7 @@
 	.validate	= can_validate,
 	.newlink	= can_newlink,
 	.changelink	= can_changelink,
+	.dellink	= can_dellink,
 	.get_size	= can_get_size,
 	.fill_info	= can_fill_info,
 	.get_xstats_size = can_get_xstats_size,
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index bcb272f..8483a40 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -16,7 +16,8 @@
 config CAN_GS_USB
 	tristate "Geschwister Schneider UG interfaces"
 	---help---
-	  This driver supports the Geschwister Schneider USB/CAN devices.
+	  This driver supports the Geschwister Schneider and bytewerk.org
+	  candleLight USB CAN interfaces USB/CAN devices
 	  If unsure choose N,
 	  choose Y for built in support,
 	  M to compile as module (module will be named: gs_usb).
@@ -46,6 +47,8 @@
 	    - Kvaser USBcan R
 	    - Kvaser Leaf Light v2
 	    - Kvaser Mini PCI Express HS
+	    - Kvaser Mini PCI Express 2xHS
+	    - Kvaser USBcan Light 2xHS
 	    - Kvaser USBcan II HS/HS
 	    - Kvaser USBcan II HS/LS
 	    - Kvaser USBcan Rugged ("USBcan Rev B")
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 1556d42..acb0c84 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -1,7 +1,9 @@
-/* CAN driver for Geschwister Schneider USB/CAN devices.
+/* CAN driver for Geschwister Schneider USB/CAN devices
+ * and bytewerk.org candleLight USB CAN interfaces.
  *
- * Copyright (C) 2013 Geschwister Schneider Technologie-,
+ * Copyright (C) 2013-2016 Geschwister Schneider Technologie-,
  * Entwicklungs- und Vertriebs UG (Haftungsbeschränkt).
+ * Copyright (C) 2016 Hubert Denkmair
  *
  * Many thanks to all socketcan devs!
  *
@@ -29,6 +31,9 @@
 #define USB_GSUSB_1_VENDOR_ID      0x1d50
 #define USB_GSUSB_1_PRODUCT_ID     0x606f
 
+#define USB_CANDLELIGHT_VENDOR_ID  0x1209
+#define USB_CANDLELIGHT_PRODUCT_ID 0x2323
+
 #define GSUSB_ENDPOINT_IN          1
 #define GSUSB_ENDPOINT_OUT         2
 
@@ -952,6 +957,8 @@
 static const struct usb_device_id gs_usb_table[] = {
 	{ USB_DEVICE_INTERFACE_NUMBER(USB_GSUSB_1_VENDOR_ID,
 				      USB_GSUSB_1_PRODUCT_ID, 0) },
+	{ USB_DEVICE_INTERFACE_NUMBER(USB_CANDLELIGHT_VENDOR_ID,
+				      USB_CANDLELIGHT_PRODUCT_ID, 0) },
 	{} /* Terminating entry */
 };
 
@@ -969,5 +976,6 @@
 MODULE_AUTHOR("Maximilian Schneider <mws@schneidersoft.net>");
 MODULE_DESCRIPTION(
 "Socket CAN device driver for Geschwister Schneider Technologie-, "
-"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces.");
+"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces\n"
+"and bytewerk.org candleLight USB CAN interfaces.");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 022bfa1..6f1f3b6 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -59,11 +59,14 @@
 #define USB_CAN_R_PRODUCT_ID		39
 #define USB_LEAF_LITE_V2_PRODUCT_ID	288
 #define USB_MINI_PCIE_HS_PRODUCT_ID	289
+#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290
+#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID	291
+#define USB_MINI_PCIE_2HS_PRODUCT_ID	292
 
 static inline bool kvaser_is_leaf(const struct usb_device_id *id)
 {
 	return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
-	       id->idProduct <= USB_MINI_PCIE_HS_PRODUCT_ID;
+	       id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
 }
 
 /* Kvaser USBCan-II devices */
@@ -537,6 +540,9 @@
 		.driver_info = KVASER_HAS_TXRX_ERRORS },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
 
 	/* USBCANII family IDs */
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 30defe6..821d86c 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3851,7 +3851,7 @@
 	unsigned long flags;
 
 	/* If the device is closed, ignore the timeout */
-	if (~(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE))
+	if (!(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE))
 		return;
 
 	/* Any nonrecoverable hardware error?
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index e0fb0f1..20760e1 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -509,8 +509,8 @@
 	 * on the current MAC's MII bus
 	 */
 	for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++)
-		if (mdiobus_get_phy(aup->mii_bus, aup->phy_addr)) {
-			phydev = mdiobus_get_phy(aup->mii_bus, aup->phy_addr);
+		if (mdiobus_get_phy(aup->mii_bus, phy_addr)) {
+			phydev = mdiobus_get_phy(aup->mii_bus, phy_addr);
 			if (!aup->phy_search_highest_addr)
 				/* break out with first one found */
 				break;
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index d02c424..8fc93c5 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -96,10 +96,6 @@
 	unsigned int rx_ringsz;
 	unsigned int rxbuf_size;
 
-	struct page  *rx_page;
-	unsigned int rx_page_offset;
-	unsigned int rx_frag_size;
-
 	struct napi_struct napi;
 	struct alx_tx_queue txq;
 	struct alx_rx_queue rxq;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c98acdc..e708e36 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -70,35 +70,6 @@
 	}
 }
 
-static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp)
-{
-	struct sk_buff *skb;
-	struct page *page;
-
-	if (alx->rx_frag_size > PAGE_SIZE)
-		return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
-
-	page = alx->rx_page;
-	if (!page) {
-		alx->rx_page = page = alloc_page(gfp);
-		if (unlikely(!page))
-			return NULL;
-		alx->rx_page_offset = 0;
-	}
-
-	skb = build_skb(page_address(page) + alx->rx_page_offset,
-			alx->rx_frag_size);
-	if (likely(skb)) {
-		alx->rx_page_offset += alx->rx_frag_size;
-		if (alx->rx_page_offset >= PAGE_SIZE)
-			alx->rx_page = NULL;
-		else
-			get_page(page);
-	}
-	return skb;
-}
-
-
 static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
@@ -115,9 +86,22 @@
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = alx_alloc_skb(alx, gfp);
+		/*
+		 * When DMA RX address is set to something like
+		 * 0x....fc0, it will be very likely to cause DMA
+		 * RFD overflow issue.
+		 *
+		 * To work around it, we apply rx skb with 64 bytes
+		 * longer space, and offset the address whenever
+		 * 0x....fc0 is detected.
+		 */
+		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp);
 		if (!skb)
 			break;
+
+		if (((unsigned long)skb->data & 0xfff) == 0xfc0)
+			skb_reserve(skb, 64);
+
 		dma = dma_map_single(&alx->hw.pdev->dev,
 				     skb->data, alx->rxbuf_size,
 				     DMA_FROM_DEVICE);
@@ -153,7 +137,6 @@
 		alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur);
 	}
 
-
 	return count;
 }
 
@@ -622,11 +605,6 @@
 	kfree(alx->txq.bufs);
 	kfree(alx->rxq.bufs);
 
-	if (alx->rx_page) {
-		put_page(alx->rx_page);
-		alx->rx_page = NULL;
-	}
-
 	dma_free_coherent(&alx->hw.pdev->dev,
 			  alx->descmem.size,
 			  alx->descmem.virt,
@@ -681,7 +659,6 @@
 				  alx->dev->name, alx);
 		if (!err)
 			goto out;
-
 		/* fall back to legacy interrupt */
 		pci_disable_msi(alx->hw.pdev);
 	}
@@ -725,7 +702,6 @@
 	struct pci_dev *pdev = alx->hw.pdev;
 	struct alx_hw *hw = &alx->hw;
 	int err;
-	unsigned int head_size;
 
 	err = alx_identify_hw(alx);
 	if (err) {
@@ -741,12 +717,7 @@
 
 	hw->smb_timer = 400;
 	hw->mtu = alx->dev->mtu;
-
 	alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu);
-	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	alx->rx_frag_size = roundup_pow_of_two(head_size);
-
 	alx->tx_ringsz = 256;
 	alx->rx_ringsz = 512;
 	hw->imt = 200;
@@ -848,7 +819,6 @@
 {
 	struct alx_priv *alx = netdev_priv(netdev);
 	int max_frame = ALX_MAX_FRAME_LEN(mtu);
-	unsigned int head_size;
 
 	if ((max_frame < ALX_MIN_FRAME_SIZE) ||
 	    (max_frame > ALX_MAX_FRAME_SIZE))
@@ -860,9 +830,6 @@
 	netdev->mtu = mtu;
 	alx->hw.mtu = mtu;
 	alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE);
-	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	alx->rx_frag_size = roundup_pow_of_two(head_size);
 	netdev_update_features(netdev);
 	if (netif_running(netdev))
 		alx_reinit(alx);
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 08a23e6..1a3555d 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -259,6 +259,7 @@
 		if (err) {
 			netdev_err(dev, "rx buffer allocation failed\n");
 			dev->stats.rx_dropped++;
+			dev_kfree_skb(skb);
 			return;
 		}
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 543bf38..bfa26a2 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -392,7 +392,7 @@
 		else
 			p = (char *)priv;
 		p += s->stat_offset;
-		data[i] = *(u32 *)p;
+		data[i] = *(unsigned long *)p;
 	}
 }
 
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index ee5f431..25bbae5 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -231,7 +231,7 @@
 	dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb),
 			 DMA_TO_DEVICE);
 
-	while (i > 0) {
+	while (i-- > 0) {
 		int index = (ring->end + i) % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[index];
 		u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1);
@@ -267,15 +267,16 @@
 	while (ring->start != ring->end) {
 		int slot_idx = ring->start % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[slot_idx];
-		u32 ctl1;
+		u32 ctl0, ctl1;
 		int len;
 
 		if (slot_idx == empty_slot)
 			break;
 
+		ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0);
 		ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1);
 		len = ctl1 & BGMAC_DESC_CTL1_LEN;
-		if (ctl1 & BGMAC_DESC_CTL0_SOF)
+		if (ctl0 & BGMAC_DESC_CTL0_SOF)
 			/* Unmap no longer used buffer */
 			dma_unmap_single(dma_dev, slot->dma_addr, len,
 					 DMA_TO_DEVICE);
@@ -1312,7 +1313,8 @@
 
 	phy_start(bgmac->phy_dev);
 
-	netif_carrier_on(net_dev);
+	netif_start_queue(net_dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a38cb04..1b0ae4a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1591,7 +1591,7 @@
 {
 	struct bnxt *bp = netdev_priv(dev);
 	u16  start = eeprom->offset, length = eeprom->len;
-	int rc;
+	int rc = 0;
 
 	memset(data, 0, eeprom->len);
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8de79ae..0e7e7da 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2821,7 +2821,7 @@
 		if (!g) {
 			netif_info(lio, tx_err, lio->netdev,
 				   "Transmit scatter gather: glist null!\n");
-			goto lio_xmit_failed;
+			goto lio_xmit_dma_failed;
 		}
 
 		cmdsetup.s.gather = 1;
@@ -2892,7 +2892,7 @@
 	else
 		status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more);
 	if (status == IQ_SEND_FAILED)
-		goto lio_xmit_failed;
+		goto lio_xmit_dma_failed;
 
 	netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n");
 
@@ -2906,12 +2906,13 @@
 
 	return NETDEV_TX_OK;
 
+lio_xmit_dma_failed:
+	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
+			 ndata.datasize, DMA_TO_DEVICE);
 lio_xmit_failed:
 	stats->tx_dropped++;
 	netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n",
 		   iq_no, stats->tx_dropped);
-	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
-			 ndata.datasize, DMA_TO_DEVICE);
 	recv_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 95f17f8..16ed203 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -499,6 +499,7 @@
 	u32 rr_quantum;
 	u8 sq_idx = sq->sq_num;
 	u8 pqs_vnic;
+	int svf;
 
 	if (sq->sqs_mode)
 		pqs_vnic = nic->pqs_vf[vnic];
@@ -511,10 +512,19 @@
 	/* 24 bytes for FCS, IPG and preamble */
 	rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
 
-	tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	if (!sq->sqs_mode) {
+		tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	} else {
+		for (svf = 0; svf < MAX_SQS_PER_VF; svf++) {
+			if (nic->vf_sqs[pqs_vnic][svf] == vnic)
+				break;
+		}
+		tl4 = (MAX_LMAC_PER_BGX * NIC_TL4_PER_LMAC);
+		tl4 += (lmac * NIC_TL4_PER_LMAC * MAX_SQS_PER_VF);
+		tl4 += (svf * NIC_TL4_PER_LMAC);
+		tl4 += (bgx * NIC_TL4_PER_BGX);
+	}
 	tl4 += sq_idx;
-	if (sq->sqs_mode)
-		tl4 += vnic * 8;
 
 	tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3);
 	nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 |
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 3ed2198..63a39ac 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -551,7 +551,9 @@
 	}
 
 	/* Clear rcvflt bit (latching high) and read it back */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT)
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
 	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
 		dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
 		if (bgx->use_training) {
@@ -570,13 +572,6 @@
 		return -1;
 	}
 
-	/* Wait for MAC RX to be ready */
-	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
-			 SMU_RX_CTL_STATUS, true)) {
-		dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
-		return -1;
-	}
-
 	/* Wait for BGX RX to be idle */
 	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
 		dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
@@ -589,29 +584,30 @@
 		return -1;
 	}
 
-	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
-		dev_err(&bgx->pdev->dev, "Receive fault\n");
-		return -1;
-	}
-
-	/* Receive link is latching low. Force it high and verify it */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
-	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
-			 SPU_STATUS1_RCV_LNK, false)) {
-		dev_err(&bgx->pdev->dev, "SPU receive link down\n");
-		return -1;
-	}
-
+	/* Clear receive packet disable */
 	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
 	cfg &= ~SPU_MISC_CTL_RX_DIS;
 	bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
-	return 0;
+
+	/* Check for MAC RX faults */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL);
+	/* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */
+	cfg &= SMU_RX_CTL_STATUS;
+	if (!cfg)
+		return 0;
+
+	/* Rx local/remote fault seen.
+	 * Do lmac reinit to see if condition recovers
+	 */
+	bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type);
+
+	return -1;
 }
 
 static void bgx_poll_for_link(struct work_struct *work)
 {
 	struct lmac *lmac;
-	u64 link;
+	u64 spu_link, smu_link;
 
 	lmac = container_of(work, struct lmac, dwork.work);
 
@@ -621,8 +617,11 @@
 	bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
 		     SPU_STATUS1_RCV_LNK, false);
 
-	link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
-	if (link & SPU_STATUS1_RCV_LNK) {
+	spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+	smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL);
+
+	if ((spu_link & SPU_STATUS1_RCV_LNK) &&
+	    !(smu_link & SMU_RX_CTL_STATUS)) {
 		lmac->link_up = 1;
 		if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
 			lmac->last_speed = 40000;
@@ -636,9 +635,15 @@
 	}
 
 	if (lmac->last_link != lmac->link_up) {
+		if (lmac->link_up) {
+			if (bgx_xaui_check_link(lmac)) {
+				/* Errors, clear link_up state */
+				lmac->link_up = 0;
+				lmac->last_speed = SPEED_UNKNOWN;
+				lmac->last_duplex = DUPLEX_UNKNOWN;
+			}
+		}
 		lmac->last_link = lmac->link_up;
-		if (lmac->link_up)
-			bgx_xaui_check_link(lmac);
 	}
 
 	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
@@ -710,7 +715,7 @@
 static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 {
 	struct lmac *lmac;
-	u64 cmrx_cfg;
+	u64 cfg;
 
 	lmac = &bgx->lmac[lmacid];
 	if (lmac->check_link) {
@@ -719,9 +724,33 @@
 		destroy_workqueue(lmac->check_link);
 	}
 
-	cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	cmrx_cfg &= ~(1 << 15);
-	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+	/* Disable packet reception */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_RX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Give chance for Rx/Tx FIFO to get drained */
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true);
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true);
+
+	/* Disable packet transmission */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_TX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Disable serdes lanes */
+        if (!lmac->is_sgmii)
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+        else
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN);
+
+	/* Disable LMAC */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
 	if ((bgx->lmac_type != BGX_MODE_XFI) &&
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 149e179..42010d2 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -41,6 +41,7 @@
 #define BGX_CMRX_RX_STAT10		0xC0
 #define BGX_CMRX_RX_BP_DROP		0xC8
 #define BGX_CMRX_RX_DMAC_CTL		0x0E8
+#define BGX_CMRX_RX_FIFO_LEN		0x108
 #define BGX_CMR_RX_DMACX_CAM		0x200
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(x << 49)
@@ -50,6 +51,7 @@
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
 #define BGX_CMR_RX_LMACS		0x468
+#define BGX_CMRX_TX_FIFO_LEN		0x518
 #define BGX_CMRX_TX_STAT0		0x600
 #define BGX_CMRX_TX_STAT1		0x608
 #define BGX_CMRX_TX_STAT2		0x610
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index c4b262c..2accab3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x0E
-#define T4FW_VERSION_MICRO 0x04
+#define T4FW_VERSION_MINOR 0x0F
+#define T4FW_VERSION_MICRO 0x25
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x0E
-#define T5FW_VERSION_MICRO 0x04
+#define T5FW_VERSION_MINOR 0x0F
+#define T5FW_VERSION_MICRO 0x25
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x0E
-#define T6FW_VERSION_MICRO 0x04
+#define T6FW_VERSION_MINOR 0x0F
+#define T6FW_VERSION_MICRO 0x25
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 4edb98c..4466a11 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -860,6 +860,11 @@
 	unsigned int entry;
 	void *dest;
 
+	if (skb_put_padto(skb, ETHOC_ZLEN)) {
+		dev->stats.tx_errors++;
+		goto out_no_free;
+	}
+
 	if (unlikely(skb->len > ETHOC_BUFSIZ)) {
 		dev->stats.tx_errors++;
 		goto out;
@@ -894,6 +899,7 @@
 	skb_tx_timestamp(skb);
 out:
 	dev_kfree_skb(skb);
+out_no_free:
 	return NETDEV_TX_OK;
 }
 
@@ -1086,7 +1092,7 @@
 	if (!priv->iobase) {
 		dev_err(&pdev->dev, "cannot remap I/O memory space\n");
 		ret = -ENXIO;
-		goto error;
+		goto free;
 	}
 
 	if (netdev->mem_end) {
@@ -1095,7 +1101,7 @@
 		if (!priv->membase) {
 			dev_err(&pdev->dev, "cannot remap memory space\n");
 			ret = -ENXIO;
-			goto error;
+			goto free;
 		}
 	} else {
 		/* Allocate buffer memory */
@@ -1106,7 +1112,7 @@
 			dev_err(&pdev->dev, "cannot allocate %dB buffer\n",
 				buffer_size);
 			ret = -ENOMEM;
-			goto error;
+			goto free;
 		}
 		netdev->mem_end = netdev->mem_start + buffer_size;
 		priv->dma_alloc = buffer_size;
@@ -1120,7 +1126,7 @@
 		128, (netdev->mem_end - netdev->mem_start + 1) / ETHOC_BUFSIZ);
 	if (num_bd < 4) {
 		ret = -ENODEV;
-		goto error;
+		goto free;
 	}
 	priv->num_bd = num_bd;
 	/* num_tx must be a power of two */
@@ -1133,7 +1139,7 @@
 	priv->vma = devm_kzalloc(&pdev->dev, num_bd*sizeof(void *), GFP_KERNEL);
 	if (!priv->vma) {
 		ret = -ENOMEM;
-		goto error;
+		goto free;
 	}
 
 	/* Allow the platform setup code to pass in a MAC address. */
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 06f0317..9b7a3f5 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -285,6 +285,7 @@
 	ge_rst_value |= NPS_ENET_ENABLE << RST_GMAC_0_SHIFT;
 	nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value);
 	usleep_range(10, 20);
+	ge_rst_value = 0;
 	nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value);
 
 	/* Tx fifo reset sequence */
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 864cb21..88f3c85 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -75,6 +75,7 @@
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
 #include <linux/seq_file.h>
+#include <linux/workqueue.h>
 
 #include "ibmvnic.h"
 
@@ -89,6 +90,7 @@
 static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
 static int ibmvnic_remove(struct vio_dev *);
 static void release_sub_crqs(struct ibmvnic_adapter *);
+static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *);
 static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
 static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
 static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
@@ -469,7 +471,8 @@
 	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP;
 	ibmvnic_send_crq(adapter, &crq);
 
-	netif_start_queue(netdev);
+	netif_tx_start_all_queues(netdev);
+
 	return 0;
 
 bounce_map_failed:
@@ -519,7 +522,7 @@
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_disable(&adapter->napi[i]);
 
-	netif_stop_queue(netdev);
+	netif_tx_stop_all_queues(netdev);
 
 	if (adapter->bounce_buffer) {
 		if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
@@ -1212,12 +1215,6 @@
 		goto reg_failed;
 	}
 
-	scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
-	if (scrq->irq == NO_IRQ) {
-		dev_err(dev, "Error mapping irq\n");
-		goto map_irq_failed;
-	}
-
 	scrq->adapter = adapter;
 	scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
 	scrq->cur = 0;
@@ -1230,12 +1227,6 @@
 
 	return scrq;
 
-map_irq_failed:
-	do {
-		rc = plpar_hcall_norets(H_FREE_SUB_CRQ,
-					adapter->vdev->unit_address,
-					scrq->crq_num);
-	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
 reg_failed:
 	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);
@@ -1256,6 +1247,7 @@
 			if (adapter->tx_scrq[i]) {
 				free_irq(adapter->tx_scrq[i]->irq,
 					 adapter->tx_scrq[i]);
+				irq_dispose_mapping(adapter->tx_scrq[i]->irq);
 				release_sub_crq_queue(adapter,
 						      adapter->tx_scrq[i]);
 			}
@@ -1267,6 +1259,7 @@
 			if (adapter->rx_scrq[i]) {
 				free_irq(adapter->rx_scrq[i]->irq,
 					 adapter->rx_scrq[i]);
+				irq_dispose_mapping(adapter->rx_scrq[i]->irq);
 				release_sub_crq_queue(adapter,
 						      adapter->rx_scrq[i]);
 			}
@@ -1276,6 +1269,29 @@
 	adapter->requested_caps = 0;
 }
 
+static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter)
+{
+	int i;
+
+	if (adapter->tx_scrq) {
+		for (i = 0; i < adapter->req_tx_queues; i++)
+			if (adapter->tx_scrq[i])
+				release_sub_crq_queue(adapter,
+						      adapter->tx_scrq[i]);
+		adapter->tx_scrq = NULL;
+	}
+
+	if (adapter->rx_scrq) {
+		for (i = 0; i < adapter->req_rx_queues; i++)
+			if (adapter->rx_scrq[i])
+				release_sub_crq_queue(adapter,
+						      adapter->rx_scrq[i]);
+		adapter->rx_scrq = NULL;
+	}
+
+	adapter->requested_caps = 0;
+}
+
 static int disable_scrq_irq(struct ibmvnic_adapter *adapter,
 			    struct ibmvnic_sub_crq_queue *scrq)
 {
@@ -1395,6 +1411,66 @@
 	return IRQ_HANDLED;
 }
 
+static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+	struct ibmvnic_sub_crq_queue *scrq;
+	int i = 0, j = 0;
+	int rc = 0;
+
+	for (i = 0; i < adapter->req_tx_queues; i++) {
+		scrq = adapter->tx_scrq[i];
+		scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
+
+		if (scrq->irq == NO_IRQ) {
+			rc = -EINVAL;
+			dev_err(dev, "Error mapping irq\n");
+			goto req_tx_irq_failed;
+		}
+
+		rc = request_irq(scrq->irq, ibmvnic_interrupt_tx,
+				 0, "ibmvnic_tx", scrq);
+
+		if (rc) {
+			dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n",
+				scrq->irq, rc);
+			irq_dispose_mapping(scrq->irq);
+			goto req_rx_irq_failed;
+		}
+	}
+
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		scrq = adapter->rx_scrq[i];
+		scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
+		if (scrq->irq == NO_IRQ) {
+			rc = -EINVAL;
+			dev_err(dev, "Error mapping irq\n");
+			goto req_rx_irq_failed;
+		}
+		rc = request_irq(scrq->irq, ibmvnic_interrupt_rx,
+				 0, "ibmvnic_rx", scrq);
+		if (rc) {
+			dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n",
+				scrq->irq, rc);
+			irq_dispose_mapping(scrq->irq);
+			goto req_rx_irq_failed;
+		}
+	}
+	return rc;
+
+req_rx_irq_failed:
+	for (j = 0; j < i; j++)
+		free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
+		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+	i = adapter->req_tx_queues;
+req_tx_irq_failed:
+	for (j = 0; j < i; j++)
+		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
+		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+	release_sub_crqs_no_irqs(adapter);
+	return rc;
+}
+
 static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 {
 	struct device *dev = &adapter->vdev->dev;
@@ -1403,8 +1479,7 @@
 	union ibmvnic_crq crq;
 	int total_queues;
 	int more = 0;
-	int i, j;
-	int rc;
+	int i;
 
 	if (!retry) {
 		/* Sub-CRQ entries are 32 byte long */
@@ -1483,13 +1558,6 @@
 	for (i = 0; i < adapter->req_tx_queues; i++) {
 		adapter->tx_scrq[i] = allqueues[i];
 		adapter->tx_scrq[i]->pool_index = i;
-		rc = request_irq(adapter->tx_scrq[i]->irq, ibmvnic_interrupt_tx,
-				 0, "ibmvnic_tx", adapter->tx_scrq[i]);
-		if (rc) {
-			dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n",
-				adapter->tx_scrq[i]->irq, rc);
-			goto req_tx_irq_failed;
-		}
 	}
 
 	adapter->rx_scrq = kcalloc(adapter->req_rx_queues,
@@ -1500,13 +1568,6 @@
 	for (i = 0; i < adapter->req_rx_queues; i++) {
 		adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues];
 		adapter->rx_scrq[i]->scrq_num = i;
-		rc = request_irq(adapter->rx_scrq[i]->irq, ibmvnic_interrupt_rx,
-				 0, "ibmvnic_rx", adapter->rx_scrq[i]);
-		if (rc) {
-			dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n",
-				adapter->rx_scrq[i]->irq, rc);
-			goto req_rx_irq_failed;
-		}
 	}
 
 	memset(&crq, 0, sizeof(crq));
@@ -1559,15 +1620,6 @@
 
 	return;
 
-req_rx_irq_failed:
-	for (j = 0; j < i; j++)
-		free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
-	i = adapter->req_tx_queues;
-req_tx_irq_failed:
-	for (j = 0; j < i; j++)
-		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
-	kfree(adapter->rx_scrq);
-	adapter->rx_scrq = NULL;
 rx_failed:
 	kfree(adapter->tx_scrq);
 	adapter->tx_scrq = NULL;
@@ -2121,7 +2173,7 @@
 				  struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff;
+	struct ibmvnic_error_buff *error_buff, *tmp;
 	unsigned long flags;
 	bool found = false;
 	int i;
@@ -2133,7 +2185,7 @@
 	}
 
 	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry(error_buff, &adapter->errors, list)
+	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
 		if (error_buff->error_id == crq->request_error_rsp.error_id) {
 			found = true;
 			list_del(&error_buff->list);
@@ -2348,9 +2400,9 @@
 			 *req_value,
 			 (long int)be32_to_cpu(crq->request_capability_rsp.
 					       number), name);
-		release_sub_crqs(adapter);
+		release_sub_crqs_no_irqs(adapter);
 		*req_value = be32_to_cpu(crq->request_capability_rsp.number);
-		complete(&adapter->init_done);
+		init_sub_crqs(adapter, 1);
 		return;
 	default:
 		dev_err(dev, "Error %d in request cap rsp\n",
@@ -2659,7 +2711,7 @@
 
 out:
 	if (atomic_read(&adapter->running_cap_queries) == 0)
-		complete(&adapter->init_done);
+		init_sub_crqs(adapter, 0);
 		/* We're done querying the capabilities, initialize sub-crqs */
 }
 
@@ -3141,14 +3193,14 @@
 
 static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 {
-	struct ibmvnic_inflight_cmd *inflight_cmd;
+	struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff;
+	struct ibmvnic_error_buff *error_buff, *tmp2;
 	unsigned long flags;
 	unsigned long flags2;
 
 	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_for_each_entry(inflight_cmd, &adapter->inflight, list) {
+	list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) {
 		switch (inflight_cmd->crq.generic.cmd) {
 		case LOGIN:
 			dma_unmap_single(dev, adapter->login_buf_token,
@@ -3165,8 +3217,8 @@
 			break;
 		case REQUEST_ERROR_INFO:
 			spin_lock_irqsave(&adapter->error_list_lock, flags2);
-			list_for_each_entry(error_buff, &adapter->errors,
-					    list) {
+			list_for_each_entry_safe(error_buff, tmp2,
+						 &adapter->errors, list) {
 				dma_unmap_single(dev, error_buff->dma,
 						 error_buff->len,
 						 DMA_FROM_DEVICE);
@@ -3202,8 +3254,8 @@
 			dev_info(dev, "Partner initialized\n");
 			/* Send back a response */
 			rc = ibmvnic_send_crq_init_complete(adapter);
-			if (rc == 0)
-				send_version_xchg(adapter);
+			if (!rc)
+				schedule_work(&adapter->vnic_crq_init);
 			else
 				dev_err(dev, "Can't send initrsp rc=%ld\n", rc);
 			break;
@@ -3555,8 +3607,63 @@
 	.release        = single_release,
 };
 
+static void handle_crq_init_rsp(struct work_struct *work)
+{
+	struct ibmvnic_adapter *adapter = container_of(work,
+						       struct ibmvnic_adapter,
+						       vnic_crq_init);
+	struct device *dev = &adapter->vdev->dev;
+	struct net_device *netdev = adapter->netdev;
+	unsigned long timeout = msecs_to_jiffies(30000);
+	int rc;
+
+	send_version_xchg(adapter);
+	reinit_completion(&adapter->init_done);
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+		dev_err(dev, "Passive init timeout\n");
+		goto task_failed;
+	}
+
+	do {
+		if (adapter->renegotiate) {
+			adapter->renegotiate = false;
+			release_sub_crqs_no_irqs(adapter);
+			send_cap_queries(adapter);
+
+			reinit_completion(&adapter->init_done);
+			if (!wait_for_completion_timeout(&adapter->init_done,
+							 timeout)) {
+				dev_err(dev, "Passive init timeout\n");
+				goto task_failed;
+			}
+		}
+	} while (adapter->renegotiate);
+	rc = init_sub_crq_irqs(adapter);
+
+	if (rc)
+		goto task_failed;
+
+	netdev->real_num_tx_queues = adapter->req_tx_queues;
+
+	rc = register_netdev(netdev);
+	if (rc) {
+		dev_err(dev,
+			"failed to register netdev rc=%d\n", rc);
+		goto register_failed;
+	}
+	dev_info(dev, "ibmvnic registered\n");
+
+	return;
+
+register_failed:
+	release_sub_crqs(adapter);
+task_failed:
+	dev_err(dev, "Passive initialization was not successful\n");
+}
+
 static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 {
+	unsigned long timeout = msecs_to_jiffies(30000);
 	struct ibmvnic_adapter *adapter;
 	struct net_device *netdev;
 	unsigned char *mac_addr_p;
@@ -3593,6 +3700,8 @@
 	netdev->ethtool_ops = &ibmvnic_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
+	INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
+
 	spin_lock_init(&adapter->stats_lock);
 
 	rc = ibmvnic_init_crq_queue(adapter);
@@ -3635,30 +3744,26 @@
 	ibmvnic_send_crq_init(adapter);
 
 	init_completion(&adapter->init_done);
-	wait_for_completion(&adapter->init_done);
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout))
+		return 0;
 
 	do {
-		adapter->renegotiate = false;
-
-		init_sub_crqs(adapter, 0);
-		reinit_completion(&adapter->init_done);
-		wait_for_completion(&adapter->init_done);
-
 		if (adapter->renegotiate) {
-			release_sub_crqs(adapter);
+			adapter->renegotiate = false;
+			release_sub_crqs_no_irqs(adapter);
 			send_cap_queries(adapter);
 
 			reinit_completion(&adapter->init_done);
-			wait_for_completion(&adapter->init_done);
+			if (!wait_for_completion_timeout(&adapter->init_done,
+							 timeout))
+				return 0;
 		}
 	} while (adapter->renegotiate);
 
-	/* if init_sub_crqs is partially successful, retry */
-	while (!adapter->tx_scrq || !adapter->rx_scrq) {
-		init_sub_crqs(adapter, 1);
-
-		reinit_completion(&adapter->init_done);
-		wait_for_completion(&adapter->init_done);
+	rc = init_sub_crq_irqs(adapter);
+	if (rc) {
+		dev_err(&dev->dev, "failed to initialize sub crq irqs\n");
+		goto free_debugfs;
 	}
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
@@ -3666,12 +3771,14 @@
 	rc = register_netdev(netdev);
 	if (rc) {
 		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
-		goto free_debugfs;
+		goto free_sub_crqs;
 	}
 	dev_info(&dev->dev, "ibmvnic registered\n");
 
 	return 0;
 
+free_sub_crqs:
+	release_sub_crqs(adapter);
 free_debugfs:
 	if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
 		debugfs_remove_recursive(adapter->debugfs_dir);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 0b66a50..e82898f 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1045,4 +1045,6 @@
 	u64 opt_rxba_entries_per_subcrq;
 	__be64 tx_rx_desc_req;
 	u8 map_id;
+
+	struct work_struct vnic_crq_init;
 };
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 75e6089..2b2e2f8 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2789,7 +2789,7 @@
 }
 
 /**
- * e1000e_vlan_strip_enable - helper to disable HW VLAN stripping
+ * e1000e_vlan_strip_disable - helper to disable HW VLAN stripping
  * @adapter: board private structure to initialize
  **/
 static void e1000e_vlan_strip_disable(struct e1000_adapter *adapter)
@@ -6915,6 +6915,14 @@
 	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
 		features &= ~NETIF_F_RXFCS;
 
+	/* Since there is no support for separate Rx/Tx vlan accel
+	 * enable/disable make sure Tx flag is always in same state as Rx.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	else
+		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
 	return features;
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5ea2200..501f15d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1344,6 +1344,13 @@
 	if (!vsi || !macaddr)
 		return NULL;
 
+	/* Do not allow broadcast filter to be added since broadcast filter
+	 * is added as part of add VSI for any newly created VSI except
+	 * FDIR VSI
+	 */
+	if (is_broadcast_ether_addr(macaddr))
+		return NULL;
+
 	f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev);
 	if (!f) {
 		f = kzalloc(sizeof(*f), GFP_ATOMIC);
@@ -2151,18 +2158,6 @@
 					 aq_ret, pf->hw.aq.asq_last_status);
 			}
 		}
-		aq_ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw,
-						   vsi->seid,
-						   cur_promisc, NULL);
-		if (aq_ret) {
-			retval = i40e_aq_rc_to_posix(aq_ret,
-						     pf->hw.aq.asq_last_status);
-			dev_info(&pf->pdev->dev,
-				 "set brdcast promisc failed, err %s, aq_err %s\n",
-				 i40e_stat_str(&pf->hw, aq_ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
-		}
 	}
 out:
 	/* if something went wrong then set the changed flag so we try again */
@@ -7726,10 +7721,11 @@
  * i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector
  * @vsi: the VSI being configured
  * @v_idx: index of the vector in the vsi struct
+ * @cpu: cpu to be used on affinity_mask
  *
  * We allocate one q_vector.  If allocation fails we return -ENOMEM.
  **/
-static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
+static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu)
 {
 	struct i40e_q_vector *q_vector;
 
@@ -7740,7 +7736,8 @@
 
 	q_vector->vsi = vsi;
 	q_vector->v_idx = v_idx;
-	cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
+	cpumask_set_cpu(cpu, &q_vector->affinity_mask);
+
 	if (vsi->netdev)
 		netif_napi_add(vsi->netdev, &q_vector->napi,
 			       i40e_napi_poll, NAPI_POLL_WEIGHT);
@@ -7764,8 +7761,7 @@
 static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
-	int v_idx, num_q_vectors;
-	int err;
+	int err, v_idx, num_q_vectors, current_cpu;
 
 	/* if not MSIX, give the one vector only to the LAN VSI */
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
@@ -7775,10 +7771,15 @@
 	else
 		return -EINVAL;
 
+	current_cpu = cpumask_first(cpu_online_mask);
+
 	for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
-		err = i40e_vsi_alloc_q_vector(vsi, v_idx);
+		err = i40e_vsi_alloc_q_vector(vsi, v_idx, current_cpu);
 		if (err)
 			goto err_out;
+		current_cpu = cpumask_next(current_cpu, cpu_online_mask);
+		if (unlikely(current_cpu >= nr_cpu_ids))
+			current_cpu = cpumask_first(cpu_online_mask);
 	}
 
 	return 0;
@@ -9224,6 +9225,7 @@
 static int i40e_add_vsi(struct i40e_vsi *vsi)
 {
 	int ret = -ENODEV;
+	i40e_status aq_ret = 0;
 	u8 laa_macaddr[ETH_ALEN];
 	bool found_laa_mac_filter = false;
 	struct i40e_pf *pf = vsi->back;
@@ -9413,6 +9415,18 @@
 		vsi->seid = ctxt.seid;
 		vsi->id = ctxt.vsi_number;
 	}
+	/* Except FDIR VSI, for all othet VSI set the broadcast filter */
+	if (vsi->type != I40E_VSI_FDIR) {
+		aq_ret = i40e_aq_set_vsi_broadcast(hw, vsi->seid, true, NULL);
+		if (aq_ret) {
+			ret = i40e_aq_rc_to_posix(aq_ret,
+						  hw->aq.asq_last_status);
+			dev_info(&pf->pdev->dev,
+				 "set brdcast promisc failed, err %s, aq_err %s\n",
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+		}
+	}
 
 	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* If macvlan filters already exist, force them to get loaded */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 55f151f..a8868e1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1280,8 +1280,8 @@
 				    union i40e_rx_desc *rx_desc)
 {
 	struct i40e_rx_ptype_decoded decoded;
-	bool ipv4, ipv6, tunnel = false;
 	u32 rx_error, rx_status;
+	bool ipv4, ipv6;
 	u8 ptype;
 	u64 qword;
 
@@ -1336,19 +1336,23 @@
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* The hardware supported by this driver does not validate outer
-	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
-	 * with it but the specification states that you "MAY validate", it
-	 * doesn't make it a hard requirement so if we have validated the
-	 * inner checksum report CHECKSUM_UNNECESSARY.
+	/* If there is an outer header present that might contain a checksum
+	 * we need to bump the checksum level by 1 to reflect the fact that
+	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP |
-				  I40E_RX_PTYPE_INNER_PROT_UDP |
-				  I40E_RX_PTYPE_INNER_PROT_SCTP))
-		tunnel = true;
+	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
+		skb->csum_level = 1;
 
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	skb->csum_level = tunnel ? 1 : 0;
+	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
+	switch (decoded.inner_prot) {
+	case I40E_RX_PTYPE_INNER_PROT_TCP:
+	case I40E_RX_PTYPE_INNER_PROT_UDP:
+	case I40E_RX_PTYPE_INNER_PROT_SCTP:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		/* fall though */
+	default:
+		break;
+	}
 
 	return;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index be99189..79d99cd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -752,8 +752,8 @@
 				    union i40e_rx_desc *rx_desc)
 {
 	struct i40e_rx_ptype_decoded decoded;
-	bool ipv4, ipv6, tunnel = false;
 	u32 rx_error, rx_status;
+	bool ipv4, ipv6;
 	u8 ptype;
 	u64 qword;
 
@@ -808,19 +808,23 @@
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* The hardware supported by this driver does not validate outer
-	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
-	 * with it but the specification states that you "MAY validate", it
-	 * doesn't make it a hard requirement so if we have validated the
-	 * inner checksum report CHECKSUM_UNNECESSARY.
+	/* If there is an outer header present that might contain a checksum
+	 * we need to bump the checksum level by 1 to reflect the fact that
+	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP |
-				  I40E_RX_PTYPE_INNER_PROT_UDP |
-				  I40E_RX_PTYPE_INNER_PROT_SCTP))
-		tunnel = true;
+	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
+		skb->csum_level = 1;
 
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	skb->csum_level = tunnel ? 1 : 0;
+	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
+	switch (decoded.inner_prot) {
+	case I40E_RX_PTYPE_INNER_PROT_TCP:
+	case I40E_RX_PTYPE_INNER_PROT_UDP:
+	case I40E_RX_PTYPE_INNER_PROT_SCTP:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		/* fall though */
+	default:
+		break;
+	}
 
 	return;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 088c47c..8bebd86 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2887,7 +2887,7 @@
 	if (!test_bit(__IXGBE_DOWN, &adapter->state))
 		ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx));
 
-	return 0;
+	return min(work_done, budget - 1);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index 61a80da..2819abc 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -85,7 +85,7 @@
 static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	if (!mbx->ops.read)
 		goto out;
@@ -111,7 +111,7 @@
 static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	/* exit if either we can't write or there isn't a defined timeout */
 	if (!mbx->ops.write || !mbx->timeout)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a6d26d3..f92018b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -244,7 +244,7 @@
 /* Various constants */
 
 /* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS		1
+#define MVNETA_TXDONE_COAL_PKTS		0	/* interrupt per packet */
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
@@ -3458,6 +3458,8 @@
 	return 0;
 
 err_free_irq:
+	unregister_cpu_notifier(&pp->cpu_notifier);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 4763252..d1cdc2d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -481,20 +481,23 @@
 /* the qdma core needs scratch memory to be setup */
 static int mtk_init_fq_dma(struct mtk_eth *eth)
 {
-	dma_addr_t phy_ring_head, phy_ring_tail;
+	dma_addr_t phy_ring_tail;
 	int cnt = MTK_DMA_SIZE;
 	dma_addr_t dma_addr;
 	int i;
 
 	eth->scratch_ring = dma_alloc_coherent(eth->dev,
 					       cnt * sizeof(struct mtk_tx_dma),
-					       &phy_ring_head,
+					       &eth->phy_scratch_ring,
 					       GFP_ATOMIC | __GFP_ZERO);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
 	eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE,
 				    GFP_KERNEL);
+	if (unlikely(!eth->scratch_head))
+		return -ENOMEM;
+
 	dma_addr = dma_map_single(eth->dev,
 				  eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE,
 				  DMA_FROM_DEVICE);
@@ -502,19 +505,19 @@
 		return -ENOMEM;
 
 	memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
-	phy_ring_tail = phy_ring_head +
+	phy_ring_tail = eth->phy_scratch_ring +
 			(sizeof(struct mtk_tx_dma) * (cnt - 1));
 
 	for (i = 0; i < cnt; i++) {
 		eth->scratch_ring[i].txd1 =
 					(dma_addr + (i * MTK_QDMA_PAGE_SIZE));
 		if (i < cnt - 1)
-			eth->scratch_ring[i].txd2 = (phy_ring_head +
+			eth->scratch_ring[i].txd2 = (eth->phy_scratch_ring +
 				((i + 1) * sizeof(struct mtk_tx_dma)));
 		eth->scratch_ring[i].txd3 = TX_DMA_SDL(MTK_QDMA_PAGE_SIZE);
 	}
 
-	mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD);
+	mtk_w32(eth, eth->phy_scratch_ring, MTK_QDMA_FQ_HEAD);
 	mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL);
 	mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT);
 	mtk_w32(eth, MTK_QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN);
@@ -671,7 +674,7 @@
 
 err_dma:
 	do {
-		tx_buf = mtk_desc_to_tx_buf(ring, txd);
+		tx_buf = mtk_desc_to_tx_buf(ring, itxd);
 
 		/* unmap dma */
 		mtk_tx_unmap(&dev->dev, tx_buf);
@@ -701,6 +704,20 @@
 	return nfrags;
 }
 
+static int mtk_queue_stopped(struct mtk_eth *eth)
+{
+	int i;
+
+	for (i = 0; i < MTK_MAC_COUNT; i++) {
+		if (!eth->netdev[i])
+			continue;
+		if (netif_queue_stopped(eth->netdev[i]))
+			return 1;
+	}
+
+	return 0;
+}
+
 static void mtk_wake_queue(struct mtk_eth *eth)
 {
 	int i;
@@ -766,12 +783,9 @@
 	if (mtk_tx_map(skb, dev, tx_num, ring, gso) < 0)
 		goto drop;
 
-	if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) {
+	if (unlikely(atomic_read(&ring->free_count) <= ring->thresh))
 		mtk_stop_queue(eth);
-		if (unlikely(atomic_read(&ring->free_count) >
-			     ring->thresh))
-			mtk_wake_queue(eth);
-	}
+
 	spin_unlock_irqrestore(&eth->page_lock, flags);
 
 	return NETDEV_TX_OK;
@@ -826,6 +840,7 @@
 					  DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
 			skb_free_frag(new_data);
+			netdev->stats.rx_dropped++;
 			goto release_desc;
 		}
 
@@ -833,6 +848,7 @@
 		skb = build_skb(data, ring->frag_size);
 		if (unlikely(!skb)) {
 			put_page(virt_to_head_page(new_data));
+			netdev->stats.rx_dropped++;
 			goto release_desc;
 		}
 		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
@@ -921,7 +937,6 @@
 		}
 		mtk_tx_unmap(eth->dev, tx_buf);
 
-		ring->last_free->txd2 = next_cpu;
 		ring->last_free = desc;
 		atomic_inc(&ring->free_count);
 
@@ -946,7 +961,8 @@
 	if (!total)
 		return 0;
 
-	if (atomic_read(&ring->free_count) > ring->thresh)
+	if (mtk_queue_stopped(eth) &&
+	    (atomic_read(&ring->free_count) > ring->thresh))
 		mtk_wake_queue(eth);
 
 	return total;
@@ -1027,9 +1043,8 @@
 
 	atomic_set(&ring->free_count, MTK_DMA_SIZE - 2);
 	ring->next_free = &ring->dma[0];
-	ring->last_free = &ring->dma[MTK_DMA_SIZE - 2];
-	ring->thresh = max((unsigned long)MTK_DMA_SIZE >> 2,
-			      MAX_SKB_FRAGS);
+	ring->last_free = &ring->dma[MTK_DMA_SIZE - 1];
+	ring->thresh = MAX_SKB_FRAGS;
 
 	/* make sure that all changes to the dma ring are flushed before we
 	 * continue
@@ -1207,6 +1222,14 @@
 	for (i = 0; i < MTK_MAC_COUNT; i++)
 		if (eth->netdev[i])
 			netdev_reset_queue(eth->netdev[i]);
+	if (eth->scratch_ring) {
+		dma_free_coherent(eth->dev,
+				  MTK_DMA_SIZE * sizeof(struct mtk_tx_dma),
+				  eth->scratch_ring,
+				  eth->phy_scratch_ring);
+		eth->scratch_ring = NULL;
+		eth->phy_scratch_ring = 0;
+	}
 	mtk_tx_clean(eth);
 	mtk_rx_clean(eth);
 	kfree(eth->scratch_head);
@@ -1269,7 +1292,7 @@
 	mtk_w32(eth,
 		MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN |
 		MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS |
-		MTK_RX_BT_32DWORDS,
+		MTK_RX_BT_32DWORDS | MTK_NDP_CO_PRO,
 		MTK_QDMA_GLO_CFG);
 
 	return 0;
@@ -1383,7 +1406,7 @@
 
 	/* disable delay and normal interrupt */
 	mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
-	mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+	mtk_irq_disable(eth, ~0);
 	mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
 	mtk_w32(eth, 0, MTK_RST_GL);
 
@@ -1697,7 +1720,7 @@
 	mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
 
 	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
-	eth->netdev[id]->watchdog_timeo = HZ;
+	eth->netdev[id]->watchdog_timeo = 5 * HZ;
 	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
 	eth->netdev[id]->base_addr = (unsigned long)eth->base;
 	eth->netdev[id]->vlan_features = MTK_HW_FEATURES &
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index eed626d..a5eb7c6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -91,6 +91,7 @@
 #define MTK_QDMA_GLO_CFG	0x1A04
 #define MTK_RX_2B_OFFSET	BIT(31)
 #define MTK_RX_BT_32DWORDS	(3 << 11)
+#define MTK_NDP_CO_PRO		BIT(10)
 #define MTK_TX_WB_DDONE		BIT(6)
 #define MTK_DMA_SIZE_16DWORDS	(2 << 4)
 #define MTK_RX_DMA_BUSY		BIT(3)
@@ -357,6 +358,7 @@
  * @rx_ring:		Pointer to the memore holding info about the RX ring
  * @rx_napi:		The NAPI struct
  * @scratch_ring:	Newer SoCs need memory for a second HW managed TX ring
+ * @phy_scratch_ring:	physical address of scratch_ring
  * @scratch_head:	The scratch memory that scratch_ring points to.
  * @clk_ethif:		The ethif clock
  * @clk_esw:		The switch clock
@@ -384,6 +386,7 @@
 	struct mtk_rx_ring		rx_ring;
 	struct napi_struct		rx_napi;
 	struct mtk_tx_dma		*scratch_ring;
+	dma_addr_t			phy_scratch_ring;
 	void				*scratch_head;
 	struct clk			*clk_ethif;
 	struct clk			*clk_esw;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e94ca1c..f04a423 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2597,7 +2597,6 @@
 	priv->cmd.free_head = 0;
 
 	sema_init(&priv->cmd.event_sem, priv->cmd.max_cmds);
-	spin_lock_init(&priv->cmd.context_lock);
 
 	for (priv->cmd.token_mask = 1;
 	     priv->cmd.token_mask < priv->cmd.max_cmds;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index fc95aff..44cf16d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1042,6 +1042,8 @@
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	u32 rx_size, tx_size;
 	int port_up = 0;
 	int err = 0;
@@ -1061,22 +1063,25 @@
 	    tx_size == priv->tx_ring[0]->size)
 		return 0;
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	new_prof.tx_ring_size = tx_size;
+	new_prof.rx_ring_size = rx_size;
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
+	mlx4_en_safe_replace_resources(priv, tmp);
 
-	priv->prof->tx_ring_size = tx_size;
-	priv->prof->rx_ring_size = rx_size;
-
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
 		if (err)
@@ -1084,8 +1089,8 @@
 	}
 
 	err = mlx4_en_moderation_update(priv);
-
 out:
+	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
 	return err;
 }
@@ -1714,6 +1719,8 @@
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	int port_up = 0;
 	int err = 0;
 
@@ -1723,23 +1730,26 @@
 	    !channel->tx_count || !channel->rx_count)
 		return -EINVAL;
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	new_prof.num_tx_rings_p_up = channel->tx_count;
+	new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
+	new_prof.rx_ring_num = channel->rx_count;
+
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
-	priv->num_tx_rings_p_up = channel->tx_count;
-	priv->tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
-	priv->rx_ring_num = channel->rx_count;
-
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
+	mlx4_en_safe_replace_resources(priv, tmp);
 
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
@@ -1757,8 +1767,8 @@
 	}
 
 	err = mlx4_en_moderation_update(priv);
-
 out:
+	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 19ceced..8359e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -406,14 +406,18 @@
 	mutex_lock(&mdev->state_lock);
 	if (mdev->device_up && priv->port_up) {
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
-		if (err)
+		if (err) {
 			en_err(priv, "Failed configuring VLAN filter\n");
+			goto out;
+		}
 	}
-	if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
-		en_dbg(HW, priv, "failed adding vlan %d\n", vid);
-	mutex_unlock(&mdev->state_lock);
+	err = mlx4_register_vlan(mdev->dev, priv->port, vid, &idx);
+	if (err)
+		en_dbg(HW, priv, "Failed adding vlan %d\n", vid);
 
-	return 0;
+out:
+	mutex_unlock(&mdev->state_lock);
+	return err;
 }
 
 static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
@@ -421,7 +425,7 @@
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err;
+	int err = 0;
 
 	en_dbg(HW, priv, "Killing VID:%d\n", vid);
 
@@ -438,7 +442,7 @@
 	}
 	mutex_unlock(&mdev->state_lock);
 
-	return 0;
+	return err;
 }
 
 static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
@@ -1950,7 +1954,7 @@
 	return 0;
 }
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv)
+static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 {
 	int i;
 
@@ -1975,7 +1979,7 @@
 
 }
 
-int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
+static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
@@ -2032,11 +2036,91 @@
 	return -ENOMEM;
 }
 
+static void mlx4_en_shutdown(struct net_device *dev)
+{
+	rtnl_lock();
+	netif_device_detach(dev);
+	mlx4_en_close(dev);
+	rtnl_unlock();
+}
+
+static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
+			     struct mlx4_en_priv *src,
+			     struct mlx4_en_port_profile *prof)
+{
+	memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config,
+	       sizeof(dst->hwtstamp_config));
+	dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up;
+	dst->tx_ring_num = prof->tx_ring_num;
+	dst->rx_ring_num = prof->rx_ring_num;
+	dst->flags = prof->flags;
+	dst->mdev = src->mdev;
+	dst->port = src->port;
+	dst->dev = src->dev;
+	dst->prof = prof;
+	dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
+					 DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
+
+	dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
+				GFP_KERNEL);
+	if (!dst->tx_ring)
+		return -ENOMEM;
+
+	dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
+			      GFP_KERNEL);
+	if (!dst->tx_cq) {
+		kfree(dst->tx_ring);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void mlx4_en_update_priv(struct mlx4_en_priv *dst,
+				struct mlx4_en_priv *src)
+{
+	memcpy(dst->rx_ring, src->rx_ring,
+	       sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num);
+	memcpy(dst->rx_cq, src->rx_cq,
+	       sizeof(struct mlx4_en_cq *) * src->rx_ring_num);
+	memcpy(&dst->hwtstamp_config, &src->hwtstamp_config,
+	       sizeof(dst->hwtstamp_config));
+	dst->tx_ring_num = src->tx_ring_num;
+	dst->rx_ring_num = src->rx_ring_num;
+	dst->tx_ring = src->tx_ring;
+	dst->tx_cq = src->tx_cq;
+	memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile));
+}
+
+int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
+				struct mlx4_en_priv *tmp,
+				struct mlx4_en_port_profile *prof)
+{
+	mlx4_en_copy_priv(tmp, priv, prof);
+
+	if (mlx4_en_alloc_resources(tmp)) {
+		en_warn(priv,
+			"%s: Resource allocation failed, using previous configuration\n",
+			__func__);
+		kfree(tmp->tx_ring);
+		kfree(tmp->tx_cq);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
+				    struct mlx4_en_priv *tmp)
+{
+	mlx4_en_free_resources(priv);
+	mlx4_en_update_priv(priv, tmp);
+}
 
 void mlx4_en_destroy_netdev(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	bool shutdown = mdev->dev->persist->interface_state &
+					    MLX4_INTERFACE_STATE_SHUTDOWN;
 
 	en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
 
@@ -2044,7 +2128,10 @@
 	if (priv->registered) {
 		devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev,
 							      priv->port));
-		unregister_netdev(dev);
+		if (shutdown)
+			mlx4_en_shutdown(dev);
+		else
+			unregister_netdev(dev);
 	}
 
 	if (priv->allocated)
@@ -2064,12 +2151,17 @@
 	mdev->upper[priv->port] = NULL;
 	mutex_unlock(&mdev->state_lock);
 
+#ifdef CONFIG_RFS_ACCEL
+	mlx4_en_cleanup_filters(priv);
+#endif
+
 	mlx4_en_free_resources(priv);
 
 	kfree(priv->tx_ring);
 	kfree(priv->tx_cq);
 
-	free_netdev(dev);
+	if (!shutdown)
+		free_netdev(dev);
 }
 
 static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
@@ -2447,9 +2539,14 @@
 	 * strip that feature if this is an IPv6 encapsulated frame.
 	 */
 	if (skb->encapsulation &&
-	    (skb->ip_summed == CHECKSUM_PARTIAL) &&
-	    (ip_hdr(skb)->version != 4))
-		features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+	    (skb->ip_summed == CHECKSUM_PARTIAL)) {
+		struct mlx4_en_priv *priv = netdev_priv(dev);
+
+		if (!priv->vxlan_port ||
+		    (ip_hdr(skb)->version != 4) ||
+		    (udp_hdr(skb)->dest != priv->vxlan_port))
+			features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+	}
 
 	return features;
 }
@@ -3102,6 +3199,8 @@
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	int port_up = 0;
 	int err = 0;
 
@@ -3118,19 +3217,29 @@
 		return -EINVAL;
 	}
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config));
+
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
 	en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n",
-		ts_config.rx_filter, !!(features & NETIF_F_HW_VLAN_CTAG_RX));
+		ts_config.rx_filter,
+		!!(features & NETIF_F_HW_VLAN_CTAG_RX));
 
-	priv->hwtstamp_config.tx_type = ts_config.tx_type;
-	priv->hwtstamp_config.rx_filter = ts_config.rx_filter;
+	mlx4_en_safe_replace_resources(priv, tmp);
 
 	if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) {
 		if (features & NETIF_F_HW_VLAN_CTAG_RX)
@@ -3164,11 +3273,6 @@
 		dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 	}
 
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
 		if (err)
@@ -3177,6 +3281,8 @@
 
 out:
 	mutex_unlock(&mdev->state_lock);
-	netdev_features_change(dev);
+	kfree(tmp);
+	if (!err)
+		netdev_features_change(dev);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index c1b3a9c..99b5407 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -514,9 +514,6 @@
 	ring->rx_info = NULL;
 	kfree(ring);
 	*pring = NULL;
-#ifdef CONFIG_RFS_ACCEL
-	mlx4_en_cleanup_filters(priv);
-#endif
 }
 
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12c77a7..546fab0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3222,6 +3222,7 @@
 
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
+	spin_lock_init(&priv->cmd.context_lock);
 
 	INIT_LIST_HEAD(&priv->bf_list);
 	mutex_init(&priv->bf_mutex);
@@ -4134,8 +4135,11 @@
 
 	mlx4_info(persist->dev, "mlx4_shutdown was called\n");
 	mutex_lock(&persist->interface_state_mutex);
-	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
+	if (persist->interface_state & MLX4_INTERFACE_STATE_UP) {
+		/* Notify mlx4 clients that the kernel is being shut down */
+		persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN;
 		mlx4_unload_one(pdev);
+	}
 	mutex_unlock(&persist->interface_state_mutex);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 467d47e..13d297e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -353,12 +353,14 @@
 	u32 rx_ring_num;
 	u32 tx_ring_size;
 	u32 rx_ring_size;
+	u8 num_tx_rings_p_up;
 	u8 rx_pause;
 	u8 rx_ppp;
 	u8 tx_pause;
 	u8 tx_ppp;
 	int rss_rings;
 	int inline_thold;
+	struct hwtstamp_config hwtstamp_config;
 };
 
 struct mlx4_en_profile {
@@ -623,8 +625,11 @@
 			      u8 rx_ppp, u8 rx_pause,
 			      u8 tx_ppp, u8 tx_pause);
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv);
-int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
+int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
+				struct mlx4_en_priv *tmp,
+				struct mlx4_en_port_profile *prof);
+void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
+				    struct mlx4_en_priv *tmp);
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq,
 		      int entries, int ring, enum cq_type mode, int node);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index dcd2df6..d6e2a1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -295,6 +295,12 @@
 	case MLX5_CMD_OP_DESTROY_FLOW_GROUP:
 	case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_DEALLOC_FLOW_COUNTER:
+	case MLX5_CMD_OP_2ERR_QP:
+	case MLX5_CMD_OP_2RST_QP:
+	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
+	case MLX5_CMD_OP_MODIFY_FLOW_TABLE:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -321,8 +327,6 @@
 	case MLX5_CMD_OP_RTR2RTS_QP:
 	case MLX5_CMD_OP_RTS2RTS_QP:
 	case MLX5_CMD_OP_SQERR2RTS_QP:
-	case MLX5_CMD_OP_2ERR_QP:
-	case MLX5_CMD_OP_2RST_QP:
 	case MLX5_CMD_OP_QUERY_QP:
 	case MLX5_CMD_OP_SQD_RTS_QP:
 	case MLX5_CMD_OP_INIT2INIT_QP:
@@ -342,7 +346,6 @@
 	case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT:
-	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_ROCE_ADDRESS:
 	case MLX5_CMD_OP_SET_ROCE_ADDRESS:
 	case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT:
@@ -390,11 +393,12 @@
 	case MLX5_CMD_OP_CREATE_RQT:
 	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
+
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE:
 	case MLX5_CMD_OP_CREATE_FLOW_GROUP:
 	case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
@@ -545,6 +549,7 @@
 	MLX5_COMMAND_STR_CASE(ALLOC_FLOW_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_FLOW_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_FLOW_COUNTER);
+	MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
 	default: return "unknown command opcode";
 	}
 }
@@ -601,11 +606,36 @@
 		pr_debug("\n");
 }
 
+static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
+{
+	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
+
+	return be16_to_cpu(hdr->opcode);
+}
+
+static void cb_timeout_handler(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+						  work);
+	struct mlx5_cmd_work_ent *ent = container_of(dwork,
+						     struct mlx5_cmd_work_ent,
+						     cb_timeout_work);
+	struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
+						 cmd);
+
+	ent->ret = -ETIMEDOUT;
+	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
+		       mlx5_command_str(msg_to_opcode(ent->in)),
+		       msg_to_opcode(ent->in));
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
 	struct mlx5_cmd *cmd = ent->cmd;
 	struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
@@ -646,6 +676,9 @@
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
 
+	if (ent->callback)
+		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -690,13 +723,6 @@
 	}
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
-
-	return be16_to_cpu(hdr->opcode);
-}
-
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -705,13 +731,13 @@
 
 	if (cmd->mode == CMD_MODE_POLLING) {
 		wait_for_completion(&ent->done);
-		err = ent->ret;
-	} else {
-		if (!wait_for_completion_timeout(&ent->done, timeout))
-			err = -ETIMEDOUT;
-		else
-			err = 0;
+	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
+		ent->ret = -ETIMEDOUT;
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
 	}
+
+	err = ent->ret;
+
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
@@ -760,6 +786,7 @@
 	if (!callback)
 		init_completion(&ent->done);
 
+	INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler);
 	INIT_WORK(&ent->work, cmd_work_handler);
 	if (page_queue) {
 		cmd_work_handler(&ent->work);
@@ -769,28 +796,26 @@
 		goto out_free;
 	}
 
-	if (!callback) {
-		err = wait_func(dev, ent);
-		if (err == -ETIMEDOUT)
-			goto out;
+	if (callback)
+		goto out;
 
-		ds = ent->ts2 - ent->ts1;
-		op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
-		if (op < ARRAY_SIZE(cmd->stats)) {
-			stats = &cmd->stats[op];
-			spin_lock_irq(&stats->lock);
-			stats->sum += ds;
-			++stats->n;
-			spin_unlock_irq(&stats->lock);
-		}
-		mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
-				   "fw exec time for %s is %lld nsec\n",
-				   mlx5_command_str(op), ds);
-		*status = ent->status;
-		free_cmd(ent);
+	err = wait_func(dev, ent);
+	if (err == -ETIMEDOUT)
+		goto out_free;
+
+	ds = ent->ts2 - ent->ts1;
+	op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
+	if (op < ARRAY_SIZE(cmd->stats)) {
+		stats = &cmd->stats[op];
+		spin_lock_irq(&stats->lock);
+		stats->sum += ds;
+		++stats->n;
+		spin_unlock_irq(&stats->lock);
 	}
-
-	return err;
+	mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
+			   "fw exec time for %s is %lld nsec\n",
+			   mlx5_command_str(op), ds);
+	*status = ent->status;
 
 out_free:
 	free_cmd(ent);
@@ -1180,41 +1205,30 @@
 	return err;
 }
 
-void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
+static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		down(&cmd->sem);
-
 	down(&cmd->pages_sem);
 
-	flush_workqueue(cmd->wq);
-
-	cmd->mode = CMD_MODE_EVENTS;
+	cmd->mode = mode;
 
 	up(&cmd->pages_sem);
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		up(&cmd->sem);
 }
 
+void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
+{
+	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
+}
+
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd *cmd = &dev->cmd;
-	int i;
-
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-
-	down(&cmd->pages_sem);
-
-	flush_workqueue(cmd->wq);
-	cmd->mode = CMD_MODE_POLLING;
-
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1250,6 +1264,8 @@
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+			if (ent->callback)
+				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
 				sem = &cmd->pages_sem;
 			else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e8a6c33..943b1bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -145,7 +145,6 @@
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
-#define MLX5E_MIN_BW_ALLOC 1   /* Min percentage of BW allocation */
 #endif
 
 struct mlx5e_params {
@@ -191,6 +190,7 @@
 enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
+	MLX5E_RQ_STATE_FLUSH_TIMEOUT,
 };
 
 struct mlx5e_cq {
@@ -220,6 +220,8 @@
 typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
 				  u16 ix);
 
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
@@ -241,6 +243,7 @@
 	struct mlx5e_cq        cq;
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_alloc_wqe     alloc_wqe;
+	mlx5e_fp_dealloc_wqe   dealloc_wqe;
 
 	unsigned long          state;
 	int                    ix;
@@ -305,6 +308,7 @@
 enum {
 	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
 	MLX5E_SQ_STATE_BF_ENABLE,
+	MLX5E_SQ_STATE_TX_TIMEOUT,
 };
 
 struct mlx5e_ico_wqe_info {
@@ -401,7 +405,7 @@
 };
 
 enum {
-	MLX5E_STATE_ASYNC_EVENTS_ENABLE,
+	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
@@ -538,6 +542,7 @@
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
+	struct work_struct         tx_timeout_work;
 	struct delayed_work        update_stats_work;
 
 	struct mlx5_core_dev      *mdev;
@@ -589,12 +594,16 @@
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
 int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq);
 void mlx5e_complete_rx_linear_mpwqe(struct mlx5e_rq *rq,
 				    struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net