Index: linux-3.18.13-rt10-r7s4/Documentation/devicetree/bindings/i2c/i2c-designware.txt
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/Documentation/devicetree/bindings/i2c/i2c-designware.txt
+++ linux-3.18.13-rt10-r7s4/Documentation/devicetree/bindings/i2c/i2c-designware.txt
@@ -14,10 +14,10 @@ Optional properties :
  - i2c-sda-hold-time-ns : should contain the SDA hold time in nanoseconds.
    This option is only supported in hardware blocks version 1.11a or newer.
 
- - i2c-scl-falling-time : should contain the SCL falling time in nanoseconds.
+ - i2c-scl-falling-time-ns : should contain the SCL falling time in nanoseconds.
    This value which is by default 300ns is used to compute the tLOW period.
 
- - i2c-sda-falling-time : should contain the SDA falling time in nanoseconds.
+ - i2c-sda-falling-time-ns : should contain the SDA falling time in nanoseconds.
    This value which is by default 300ns is used to compute the tHIGH period.
 
 Example :
Index: linux-3.18.13-rt10-r7s4/Documentation/kernel-parameters.txt
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/Documentation/kernel-parameters.txt
+++ linux-3.18.13-rt10-r7s4/Documentation/kernel-parameters.txt
@@ -1270,6 +1270,7 @@ bytes respectively. Such letter suffixes
 	i8042.notimeout	[HW] Ignore timeout condition signalled by controller
 	i8042.reset	[HW] Reset the controller during init and cleanup
 	i8042.unlock	[HW] Unlock (ignore) the keylock
+	i8042.kbdreset  [HW] Reset device connected to KBD port
 
 	i810=		[HW,DRM]
 
Index: linux-3.18.13-rt10-r7s4/Documentation/ramoops.txt
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/Documentation/ramoops.txt
+++ linux-3.18.13-rt10-r7s4/Documentation/ramoops.txt
@@ -14,11 +14,19 @@ survive after a restart.
 
 1. Ramoops concepts
 
-Ramoops uses a predefined memory area to store the dump. The start and size of
-the memory area are set using two variables:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
   * "mem_address" for the start
   * "mem_size" for the size. The memory size will be rounded down to a
   power of two.
+  * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
 
 The memory area is divided into "record_size" chunks (also rounded down to
 power of two) and each oops/panic writes a "record_size" chunk of
@@ -55,6 +63,7 @@ Setting the ramoops parameters can be do
 static struct ramoops_platform_data ramoops_data = {
         .mem_size               = <...>,
         .mem_address            = <...>,
+        .mem_type               = <...>,
         .record_size            = <...>,
         .dump_oops              = <...>,
         .ecc                    = <...>,
Index: linux-3.18.13-rt10-r7s4/Documentation/stable_kernel_rules.txt
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/Documentation/stable_kernel_rules.txt
+++ linux-3.18.13-rt10-r7s4/Documentation/stable_kernel_rules.txt
@@ -32,18 +32,42 @@ Procedure for submitting patches to the
  - If the patch covers files in net/ or drivers/net please follow netdev stable
    submission guidelines as described in
    Documentation/networking/netdev-FAQ.txt
- - Send the patch, after verifying that it follows the above rules, to
-   stable@vger.kernel.org.  You must note the upstream commit ID in the
-   changelog of your submission, as well as the kernel version you wish
-   it to be applied to.
- - To have the patch automatically included in the stable tree, add the tag
+ - Security patches should not be handled (solely) by the -stable review
+   process but should follow the procedures in Documentation/SecurityBugs.
+
+For all other submissions, choose one of the following procedures:
+
+   --- Option 1 ---
+
+   To have the patch automatically included in the stable tree, add the tag
      Cc: stable@vger.kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
    or subsystem maintainer.
- - If the patch requires other patches as prerequisites which can be
-   cherry-picked, then this can be specified in the following format in
-   the sign-off area:
+
+   --- Option 2 ---
+
+   After the patch has been merged to Linus' tree, send an email to
+   stable@vger.kernel.org containing the subject of the patch, the commit ID,
+   why you think it should be applied, and what kernel version you wish it to
+   be applied to.
+
+   --- Option 3 ---
+
+   Send the patch, after verifying that it follows the above rules, to
+   stable@vger.kernel.org.  You must note the upstream commit ID in the
+   changelog of your submission, as well as the kernel version you wish
+   it to be applied to.
+
+Option 1 is probably the easiest and most common. Options 2 and 3 are more
+useful if the patch isn't deemed worthy at the time it is applied to a public
+git tree (for instance, because it deserves more regression testing first).
+Option 3 is especially useful if the patch needs some special handling to apply
+to an older kernel (e.g., if API's have changed in the meantime).
+
+Additionally, some patches submitted via Option 1 may have additional patch
+prerequisites which can be cherry-picked. This can be specified in the following
+format in the sign-off area:
 
      Cc: <stable@vger.kernel.org> # 3.3.x: a1f84a3: sched: Check for idle
      Cc: <stable@vger.kernel.org> # 3.3.x: 1b9508f: sched: Rate-limit newidle
@@ -57,13 +81,13 @@ Procedure for submitting patches to the
      git cherry-pick fd21073
      git cherry-pick <this commit>
 
+Following the submission:
+
  - The sender will receive an ACK when the patch has been accepted into the
    queue, or a NAK if the patch is rejected.  This response might take a few
    days, according to the developer's schedules.
  - If accepted, the patch will be added to the -stable queue, for review by
    other developers and by the relevant subsystem maintainer.
- - Security patches should not be sent to this alias, but instead to the
-   documented security@kernel.org address.
 
 
 Review cycle:
Index: linux-3.18.13-rt10-r7s4/Makefile
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/Makefile
+++ linux-3.18.13-rt10-r7s4/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 18
-SUBLEVEL = 0
-EXTRAVERSION = -linux4sam_4.7
+SUBLEVEL = 13
+EXTRAVERSION =
 NAME = Diseased Newt
 
 # *DOCUMENTATION*
Index: linux-3.18.13-rt10-r7s4/arch/alpha/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/alpha/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/alpha/mm/fault.c
@@ -156,6 +156,8 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/arc/boot/dts/nsimosci.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arc/boot/dts/nsimosci.dts
+++ linux-3.18.13-rt10-r7s4/arch/arc/boot/dts/nsimosci.dts
@@ -20,7 +20,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
 	};
 
 	aliases {
@@ -41,9 +41,9 @@
 			#interrupt-cells = <1>;
 		};
 
-		uart0: serial@c0000000 {
+		uart0: serial@f0000000 {
 			compatible = "ns8250";
-			reg = <0xc0000000 0x2000>;
+			reg = <0xf0000000 0x2000>;
 			interrupts = <11>;
 			clock-frequency = <3686400>;
 			baud = <115200>;
@@ -52,21 +52,21 @@
 			no-loopback-test = <1>;
 		};
 
-		pgu0: pgu@c9000000 {
+		pgu0: pgu@f9000000 {
 			compatible = "snps,arcpgufb";
-			reg = <0xc9000000 0x400>;
+			reg = <0xf9000000 0x400>;
 		};
 
-		ps2: ps2@c9001000 {
+		ps2: ps2@f9001000 {
 			compatible = "snps,arc_ps2";
-			reg = <0xc9000400 0x14>;
+			reg = <0xf9000400 0x14>;
 			interrupts = <13>;
 			interrupt-names = "arc_ps2_irq";
 		};
 
-		eth0: ethernet@c0003000 {
+		eth0: ethernet@f0003000 {
 			compatible = "snps,oscilan";
-			reg = <0xc0003000 0x44>;
+			reg = <0xf0003000 0x44>;
 			interrupts = <7>, <8>;
 			interrupt-names = "rx", "tx";
 		};
Index: linux-3.18.13-rt10-r7s4/arch/arc/include/asm/pgtable.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arc/include/asm/pgtable.h
+++ linux-3.18.13-rt10-r7s4/arch/arc/include/asm/pgtable.h
@@ -259,7 +259,8 @@ static inline void pmd_set(pmd_t *pmdp,
 #define pmd_clear(xp)			do { pmd_val(*(xp)) = 0; } while (0)
 
 #define pte_page(x) (mem_map + \
-		(unsigned long)(((pte_val(x) - PAGE_OFFSET) >> PAGE_SHIFT)))
+		(unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \
+				PAGE_SHIFT)))
 
 #define mk_pte(page, pgprot)						\
 ({									\
Index: linux-3.18.13-rt10-r7s4/arch/arc/include/asm/processor.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arc/include/asm/processor.h
+++ linux-3.18.13-rt10-r7s4/arch/arc/include/asm/processor.h
@@ -75,18 +75,19 @@ unsigned long thread_saved_pc(struct tas
 #define release_segments(mm)        do { } while (0)
 
 #define KSTK_EIP(tsk)   (task_pt_regs(tsk)->ret)
+#define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
  * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
-#define KSTK_ESP(tsk)   (tsk->thread.ksp)
+#define TSK_K_ESP(tsk)		(tsk->thread.ksp)
 
-#define KSTK_REG(tsk, off)	(*((unsigned int *)(KSTK_ESP(tsk) + \
+#define TSK_K_REG(tsk, off)	(*((unsigned int *)(TSK_K_ESP(tsk) + \
 					sizeof(struct callee_regs) + off)))
 
-#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4)
-#define KSTK_FP(tsk)    KSTK_REG(tsk, 0)
+#define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
+#define TSK_K_FP(tsk)		TSK_K_REG(tsk, 0)
 
 extern void start_thread(struct pt_regs * regs, unsigned long pc,
 			 unsigned long usp);
Index: linux-3.18.13-rt10-r7s4/arch/arc/kernel/signal.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arc/kernel/signal.c
+++ linux-3.18.13-rt10-r7s4/arch/arc/kernel/signal.c
@@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user
 	       sigset_t *set)
 {
 	int err;
-	err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs,
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
@@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_re
 	if (!err)
 		set_current_blocked(&set);
 
-	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs),
+	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 
 	return err;
@@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	/* Don't restart from sigreturn */
 	syscall_wont_restart(regs);
 
+	/*
+	 * Ensure that sigreturn always returns to user mode (in case the
+	 * regs saved on user stack got fudged between save and sigreturn)
+	 * Otherwise it is easy to panic the kernel with a custom
+	 * signal handler and/or restorer which clobberes the status32/ret
+	 * to return to a bogus location in kernel mode.
+	 */
+	regs->status32 |= STATUS_U_MASK;
+
 	return regs->r0;
 
 badframe:
@@ -229,8 +238,11 @@ setup_rt_frame(struct ksignal *ksig, sig
 
 	/*
 	 * handler returns using sigreturn stub provided already by userpsace
+	 * If not, nuke the process right away
 	 */
-	BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER));
+	if(!(ksig->ka.sa.sa_flags & SA_RESTORER))
+		return 1;
+
 	regs->blink = (unsigned long)ksig->ka.sa.sa_restorer;
 
 	/* User Stack for signal handler will be above the frame just carved */
@@ -296,12 +308,12 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	sigset_t *oldset = sigmask_to_save();
-	int ret;
+	int failed;
 
 	/* Set up the stack frame */
-	ret = setup_rt_frame(ksig, oldset, regs);
+	failed = setup_rt_frame(ksig, oldset, regs);
 
-	signal_setup_done(ret, ksig, 0);
+	signal_setup_done(failed, ksig, 0);
 }
 
 void do_signal(struct pt_regs *regs)
Index: linux-3.18.13-rt10-r7s4/arch/arc/kernel/stacktrace.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arc/kernel/stacktrace.c
+++ linux-3.18.13-rt10-r7s4/arch/arc/kernel/stacktrace.c
@@ -64,9 +64,9 @@ static void seed_unwind_frame_info(struc
 
 		frame_info->task = tsk;
 
-		frame_info->regs.r27 = KSTK_FP(tsk);
-		frame_info->regs.r28 = KSTK_ESP(tsk);
-		frame_info->regs.r31 = KSTK_BLINK(tsk);
+		frame_info->regs.r27 = TSK_K_FP(tsk);
+		frame_info->regs.r28 = TSK_K_ESP(tsk);
+		frame_info->regs.r31 = TSK_K_BLINK(tsk);
 		frame_info->regs.r63 = (unsigned int)__switch_to;
 
 		/* In the prologue of __switch_to, first FP is saved on stack
Index: linux-3.18.13-rt10-r7s4/arch/arc/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arc/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/arc/mm/fault.c
@@ -161,6 +161,8 @@ good_area:
 
 	if (fault & VM_FAULT_OOM)
 		goto out_of_memory;
+	else if (fault & VM_FAULT_SIGSEGV)
+		goto bad_area;
 	else if (fault & VM_FAULT_SIGBUS)
 		goto do_sigbus;
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am335x-bone-common.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -195,6 +195,7 @@
 
 &usb0 {
 	status = "okay";
+	dr_mode = "peripheral";
 };
 
 &usb1 {
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am33xx-clocks.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/am33xx-clocks.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am33xx-clocks.dtsi
@@ -99,7 +99,7 @@
 	ehrpwm0_tbclk: ehrpwm0_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <0>;
 		reg = <0x0664>;
 	};
@@ -107,7 +107,7 @@
 	ehrpwm1_tbclk: ehrpwm1_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <1>;
 		reg = <0x0664>;
 	};
@@ -115,7 +115,7 @@
 	ehrpwm2_tbclk: ehrpwm2_tbclk@44e10664 {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <2>;
 		reg = <0x0664>;
 	};
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am437x-sk-evm.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/am437x-sk-evm.dts
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -100,7 +100,7 @@
 	};
 
 	lcd0: display {
-		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		compatible = "newhaven,nhd-4.3-480272ef-atxl", "panel-dpi";
 		label = "lcd";
 
 		pinctrl-names = "default";
@@ -112,11 +112,11 @@
 			clock-frequency = <9000000>;
 			hactive = <480>;
 			vactive = <272>;
-			hfront-porch = <8>;
-			hback-porch = <43>;
-			hsync-len = <4>;
-			vback-porch = <12>;
-			vfront-porch = <4>;
+			hfront-porch = <2>;
+			hback-porch = <2>;
+			hsync-len = <41>;
+			vfront-porch = <2>;
+			vback-porch = <2>;
 			vsync-len = <10>;
 			hsync-active = <0>;
 			vsync-active = <0>;
@@ -320,8 +320,7 @@
 
 	lcd_pins: lcd_pins {
 		pinctrl-single,pins = <
-			/* GPIO 5_8 to select LCD / HDMI */
-			0x238 (PIN_OUTPUT_PULLUP | MUX_MODE7)
+			0x1c (PIN_OUTPUT_PULLDOWN | MUX_MODE7) /* gpcm_ad7.gpio1_7 */
 		>;
 	};
 };
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am43xx-clocks.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -107,7 +107,7 @@
 	ehrpwm0_tbclk: ehrpwm0_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <0>;
 		reg = <0x0664>;
 	};
@@ -115,7 +115,7 @@
 	ehrpwm1_tbclk: ehrpwm1_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <1>;
 		reg = <0x0664>;
 	};
@@ -123,7 +123,7 @@
 	ehrpwm2_tbclk: ehrpwm2_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <2>;
 		reg = <0x0664>;
 	};
@@ -131,7 +131,7 @@
 	ehrpwm3_tbclk: ehrpwm3_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <4>;
 		reg = <0x0664>;
 	};
@@ -139,7 +139,7 @@
 	ehrpwm4_tbclk: ehrpwm4_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <5>;
 		reg = <0x0664>;
 	};
@@ -147,7 +147,7 @@
 	ehrpwm5_tbclk: ehrpwm5_tbclk {
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
-		clocks = <&dpll_per_m2_ck>;
+		clocks = <&l4ls_gclk>;
 		ti,bit-shift = <6>;
 		reg = <0x0664>;
 	};
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/armada-370-db.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/armada-370-db.dts
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/armada-370-db.dts
@@ -102,30 +102,6 @@
 				broken-cd;
 			};
 
-			pinctrl {
-				/*
-				 * These pins might be muxed as I2S by
-				 * the bootloader, but it conflicts
-				 * with the real I2S pins that are
-				 * muxed using i2s_pins. We must mux
-				 * those pins to a function other than
-				 * I2S.
-				 */
-				pinctrl-0 = <&hog_pins1 &hog_pins2>;
-				pinctrl-names = "default";
-
-				hog_pins1: hog-pins1 {
-					marvell,pins = "mpp6",  "mpp8", "mpp10",
-						       "mpp12", "mpp13";
-					marvell,function = "gpio";
-				};
-
-				hog_pins2: hog-pins2 {
-					marvell,pins = "mpp5", "mpp7", "mpp9";
-					marvell,function = "gpo";
-				};
-			};
-
 			usb@50000 {
 				status = "okay";
 			};
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/armada-370.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/armada-370.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/armada-370.dtsi
@@ -106,11 +106,6 @@
 				reg = <0x11100 0x20>;
 			};
 
-			system-controller@18200 {
-				compatible = "marvell,armada-370-xp-system-controller";
-				reg = <0x18200 0x100>;
-			};
-
 			pinctrl {
 				compatible = "marvell,mv88f6710-pinctrl";
 				reg = <0x18000 0x38>;
@@ -205,6 +200,11 @@
 				interrupts = <91>;
 			};
 
+			system-controller@18200 {
+				compatible = "marvell,armada-370-xp-system-controller";
+				reg = <0x18200 0x100>;
+			};
+
 			gateclk: clock-gating-control@18220 {
 				compatible = "marvell,armada-370-gating-clock";
 				reg = <0x18220 0x4>;
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/bcm63138.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/bcm63138.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/bcm63138.dtsi
@@ -66,8 +66,9 @@
 			reg = <0x1d000 0x1000>;
 			cache-unified;
 			cache-level = <2>;
-			cache-sets = <16>;
-			cache-size = <0x80000>;
+			cache-size = <524288>;
+			cache-sets = <1024>;
+			cache-line-size = <32>;
 			interrupts = <GIC_PPI 0 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
@@ -30,6 +30,8 @@
 };
 
 &sdhci2 {
+	broken-cd;
+	bus-width = <8>;
 	non-removable;
 	status = "okay";
 };
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/berlin2q.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/berlin2q.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/berlin2q.dtsi
@@ -83,7 +83,8 @@
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab1000 0x200>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&chip CLKID_SDIO1XIN>;
+			clocks = <&chip CLKID_NFC_ECC>, <&chip CLKID_NFC>;
+			clock-names = "io", "core";
 			status = "disabled";
 		};
 
@@ -314,36 +315,6 @@
 				interrupt-parent = <&gic>;
 				interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
 			};
-
-			gpio4: gpio@5000 {
-				compatible = "snps,dw-apb-gpio";
-				reg = <0x5000 0x400>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				porte: gpio-port@4 {
-					compatible = "snps,dw-apb-gpio-port";
-					gpio-controller;
-					#gpio-cells = <2>;
-					snps,nr-gpios = <32>;
-					reg = <0>;
-				};
-			};
-
-			gpio5: gpio@c000 {
-				compatible = "snps,dw-apb-gpio";
-				reg = <0xc000 0x400>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				portf: gpio-port@5 {
-					compatible = "snps,dw-apb-gpio-port";
-					gpio-controller;
-					#gpio-cells = <2>;
-					snps,nr-gpios = <32>;
-					reg = <0>;
-				};
-			};
 		};
 
 		chip: chip-control@ea0000 {
@@ -372,6 +343,21 @@
 			ranges = <0 0xfc0000 0x10000>;
 			interrupt-parent = <&sic>;
 
+			sm_gpio1: gpio@5000 {
+				compatible = "snps,dw-apb-gpio";
+				reg = <0x5000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				portf: gpio-port@5 {
+					compatible = "snps,dw-apb-gpio-port";
+					gpio-controller;
+					#gpio-cells = <2>;
+					snps,nr-gpios = <32>;
+					reg = <0>;
+				};
+			};
+
 			i2c2: i2c@7000 {
 				compatible = "snps,designware-i2c";
 				#address-cells = <1>;
@@ -422,6 +408,21 @@
 				status = "disabled";
 			};
 
+			sm_gpio0: gpio@c000 {
+				compatible = "snps,dw-apb-gpio";
+				reg = <0xc000 0x400>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				porte: gpio-port@4 {
+					compatible = "snps,dw-apb-gpio-port";
+					gpio-controller;
+					#gpio-cells = <2>;
+					snps,nr-gpios = <32>;
+					reg = <0>;
+				};
+			};
+
 			sysctrl: pin-controller@d000 {
 				compatible = "marvell,berlin2q-system-ctrl";
 				reg = <0xd000 0x100>;
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/dra7-evm.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/dra7-evm.dts
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/dra7-evm.dts
@@ -399,23 +399,23 @@
 		};
 		partition@5 {
 			label = "QSPI.u-boot-spl-os";
-			reg = <0x00140000 0x00010000>;
+			reg = <0x00140000 0x00080000>;
 		};
 		partition@6 {
 			label = "QSPI.u-boot-env";
-			reg = <0x00150000 0x00010000>;
+			reg = <0x001c0000 0x00010000>;
 		};
 		partition@7 {
 			label = "QSPI.u-boot-env.backup1";
-			reg = <0x00160000 0x0010000>;
+			reg = <0x001d0000 0x0010000>;
 		};
 		partition@8 {
 			label = "QSPI.kernel";
-			reg = <0x00170000 0x0800000>;
+			reg = <0x001e0000 0x0800000>;
 		};
 		partition@9 {
 			label = "QSPI.file-system";
-			reg = <0x00970000 0x01690000>;
+			reg = <0x009e0000 0x01620000>;
 		};
 	};
 };
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/dra7.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/dra7.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/dra7.dtsi
@@ -653,7 +653,7 @@
 		};
 
 		wdt2: wdt@4ae14000 {
-			compatible = "ti,omap4-wdt";
+			compatible = "ti,omap3-wdt";
 			reg = <0x4ae14000 0x80>;
 			interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "wd_timer2";
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/dra7xx-clocks.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -243,10 +243,18 @@
 		ti,invert-autoidle-bit;
 	};
 
+	dpll_core_byp_mux: dpll_core_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x012c>;
+	};
+
 	dpll_core_ck: dpll_core_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-core-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_core_byp_mux>;
 		reg = <0x0120>, <0x0124>, <0x012c>, <0x0128>;
 	};
 
@@ -309,10 +317,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_dsp_byp_mux: dpll_dsp_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x0240>;
+	};
+
 	dpll_dsp_ck: dpll_dsp_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dsp_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_dsp_byp_mux>;
 		reg = <0x0234>, <0x0238>, <0x0240>, <0x023c>;
 	};
 
@@ -335,10 +351,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_iva_byp_mux: dpll_iva_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x01ac>;
+	};
+
 	dpll_iva_ck: dpll_iva_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&iva_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_iva_byp_mux>;
 		reg = <0x01a0>, <0x01a4>, <0x01ac>, <0x01a8>;
 	};
 
@@ -361,10 +385,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_gpu_byp_mux: dpll_gpu_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x02e4>;
+	};
+
 	dpll_gpu_ck: dpll_gpu_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_gpu_byp_mux>;
 		reg = <0x02d8>, <0x02dc>, <0x02e4>, <0x02e0>;
 	};
 
@@ -398,10 +430,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_ddr_byp_mux: dpll_ddr_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x021c>;
+	};
+
 	dpll_ddr_ck: dpll_ddr_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_ddr_byp_mux>;
 		reg = <0x0210>, <0x0214>, <0x021c>, <0x0218>;
 	};
 
@@ -416,10 +456,18 @@
 		ti,invert-autoidle-bit;
 	};
 
+	dpll_gmac_byp_mux: dpll_gmac_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		ti,bit-shift = <23>;
+		reg = <0x02b4>;
+	};
+
 	dpll_gmac_ck: dpll_gmac_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&dpll_abe_m3x2_ck>;
+		clocks = <&sys_clkin1>, <&dpll_gmac_byp_mux>;
 		reg = <0x02a8>, <0x02ac>, <0x02b4>, <0x02b0>;
 	};
 
@@ -482,10 +530,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_eve_byp_mux: dpll_eve_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x0290>;
+	};
+
 	dpll_eve_ck: dpll_eve_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&eve_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_eve_byp_mux>;
 		reg = <0x0284>, <0x0288>, <0x0290>, <0x028c>;
 	};
 
@@ -1249,10 +1305,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_per_byp_mux: dpll_per_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x014c>;
+	};
+
 	dpll_per_ck: dpll_per_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-clock";
-		clocks = <&sys_clkin1>, <&per_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_per_byp_mux>;
 		reg = <0x0140>, <0x0144>, <0x014c>, <0x0148>;
 	};
 
@@ -1275,10 +1339,18 @@
 		clock-div = <1>;
 	};
 
+	dpll_usb_byp_mux: dpll_usb_byp_mux {
+		#clock-cells = <0>;
+		compatible = "ti,mux-clock";
+		clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>;
+		ti,bit-shift = <23>;
+		reg = <0x018c>;
+	};
+
 	dpll_usb_ck: dpll_usb_ck {
 		#clock-cells = <0>;
 		compatible = "ti,omap4-dpll-j-type-clock";
-		clocks = <&sys_clkin1>, <&usb_dpll_hs_clk_div>;
+		clocks = <&sys_clkin1>, <&dpll_usb_byp_mux>;
 		reg = <0x0180>, <0x0184>, <0x018c>, <0x0188>;
 	};
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/exynos4.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/exynos4.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/exynos4.dtsi
@@ -368,7 +368,7 @@
 	};
 
 	i2s1: i2s@13960000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13960000 0x100>;
 		clocks = <&clock CLK_I2S1>;
 		clock-names = "iis";
@@ -378,7 +378,7 @@
 	};
 
 	i2s2: i2s@13970000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13970000 0x100>;
 		clocks = <&clock CLK_I2S2>;
 		clock-names = "iis";
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/imx25.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/imx25.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/imx25.dtsi
@@ -162,7 +162,7 @@
 				#size-cells = <0>;
 				compatible = "fsl,imx25-cspi", "fsl,imx35-cspi";
 				reg = <0x43fa4000 0x4000>;
-				clocks = <&clks 62>, <&clks 62>;
+				clocks = <&clks 78>, <&clks 78>;
 				clock-names = "ipg", "per";
 				interrupts = <14>;
 				status = "disabled";
@@ -369,7 +369,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa0000 0x4000>;
-				clocks = <&clks 106>, <&clks 36>;
+				clocks = <&clks 106>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <36>;
 			};
@@ -388,7 +388,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa8000 0x4000>;
-				clocks = <&clks 107>, <&clks 36>;
+				clocks = <&clks 107>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <41>;
 			};
@@ -429,7 +429,7 @@
 			pwm4: pwm@53fc8000 {
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				reg = <0x53fc8000 0x4000>;
-				clocks = <&clks 108>, <&clks 36>;
+				clocks = <&clks 108>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <42>;
 			};
@@ -476,7 +476,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fe0000 0x4000>;
-				clocks = <&clks 105>, <&clks 36>;
+				clocks = <&clks 105>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <26>;
 			};
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/imx51-babbage.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/imx51-babbage.dts
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/imx51-babbage.dts
@@ -127,24 +127,12 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		reg_usbh1_vbus: regulator@0 {
-			compatible = "regulator-fixed";
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbh1reg>;
-			reg = <0>;
-			regulator-name = "usbh1_vbus";
-			regulator-min-microvolt = <5000000>;
-			regulator-max-microvolt = <5000000>;
-			gpio = <&gpio2 5 GPIO_ACTIVE_HIGH>;
-			enable-active-high;
-		};
-
-		reg_usbotg_vbus: regulator@1 {
+		reg_hub_reset: regulator@0 {
 			compatible = "regulator-fixed";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_usbotgreg>;
-			reg = <1>;
-			regulator-name = "usbotg_vbus";
+			reg = <0>;
+			regulator-name = "hub_reset";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 7 GPIO_ACTIVE_HIGH>;
@@ -176,6 +164,7 @@
 			reg = <0>;
 			clocks = <&clks IMX5_CLK_DUMMY>;
 			clock-names = "main_clk";
+			reset-gpios = <&gpio2 5 GPIO_ACTIVE_LOW>;
 		};
 	};
 };
@@ -419,7 +408,7 @@
 &usbh1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usbh1>;
-	vbus-supply = <&reg_usbh1_vbus>;
+	vbus-supply = <&reg_hub_reset>;
 	fsl,usbphy = <&usbh1phy>;
 	phy_type = "ulpi";
 	status = "okay";
@@ -429,7 +418,6 @@
 	dr_mode = "otg";
 	disable-over-current;
 	phy_type = "utmi_wide";
-	vbus-supply = <&reg_usbotg_vbus>;
 	status = "okay";
 };
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -35,6 +35,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio3 22 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_usb_h1_vbus: regulator@1 {
@@ -45,6 +46,7 @@
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 29 0>;
 			enable-active-high;
+			vin-supply = <&swbst_reg>;
 		};
 
 		reg_audio: regulator@2 {
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/s3c6410-mini6410.dts
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/s3c6410-mini6410.dts
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/s3c6410-mini6410.dts
@@ -198,10 +198,6 @@
 	status = "okay";
 };
 
-&pwm {
-	status = "okay";
-};
-
 &pinctrl0 {
 	gpio_leds: gpio-leds {
 		samsung,pins = "gpk-4", "gpk-5", "gpk-6", "gpk-7";
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/s3c64xx.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/s3c64xx.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/s3c64xx.dtsi
@@ -172,7 +172,6 @@
 			clocks = <&clocks PCLK_PWM>;
 			samsung,pwm-outputs = <0>, <1>;
 			#pwm-cells = <3>;
-			status = "disabled";
 		};
 
 		pinctrl0: pinctrl@7f008000 {
Index: linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/tegra20.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/boot/dts/tegra20.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/arm/boot/dts/tegra20.dtsi
@@ -68,9 +68,9 @@
 			reset-names = "2d";
 		};
 
-		gr3d@54140000 {
+		gr3d@54180000 {
 			compatible = "nvidia,tegra20-gr3d";
-			reg = <0x54140000 0x00040000>;
+			reg = <0x54180000 0x00040000>;
 			clocks = <&tegra_car TEGRA20_CLK_GR3D>;
 			resets = <&tegra_car 24>;
 			reset-names = "3d";
@@ -130,9 +130,9 @@
 			status = "disabled";
 		};
 
-		dsi@542c0000 {
+		dsi@54300000 {
 			compatible = "nvidia,tegra20-dsi";
-			reg = <0x542c0000 0x00040000>;
+			reg = <0x54300000 0x00040000>;
 			clocks = <&tegra_car TEGRA20_CLK_DSI>;
 			resets = <&tegra_car 48>;
 			reset-names = "dsi";
Index: linux-3.18.13-rt10-r7s4/arch/arm/configs/multi_v7_defconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/configs/multi_v7_defconfig
+++ linux-3.18.13-rt10-r7s4/arch/arm/configs/multi_v7_defconfig
@@ -320,6 +320,7 @@ CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_XHCI_MVEBU=y
 CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_ISP1760_HCD=y
@@ -445,4 +446,4 @@ CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_LOCKUP_DETECTOR=y
 CONFIG_CRYPTO_DEV_TEGRA_AES=y
-CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_CPUFREQ_DT=y
Index: linux-3.18.13-rt10-r7s4/arch/arm/configs/omap2plus_defconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/configs/omap2plus_defconfig
+++ linux-3.18.13-rt10-r7s4/arch/arm/configs/omap2plus_defconfig
@@ -68,7 +68,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
-CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_CPUFREQ_DT=y
 # CONFIG_ARM_OMAP2PLUS_CPUFREQ is not set
 CONFIG_CPU_IDLE=y
 CONFIG_BINFMT_MISC=y
Index: linux-3.18.13-rt10-r7s4/arch/arm/configs/shmobile_defconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/configs/shmobile_defconfig
+++ linux-3.18.13-rt10-r7s4/arch/arm/configs/shmobile_defconfig
@@ -176,5 +176,5 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 CONFIG_CPU_THERMAL=y
-CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_CPUFREQ_DT=y
 CONFIG_REGULATOR_DA9210=y
Index: linux-3.18.13-rt10-r7s4/arch/arm/crypto/aes_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/crypto/aes_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/crypto/aes_glue.c
@@ -93,6 +93,6 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
 MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
Index: linux-3.18.13-rt10-r7s4/arch/arm/crypto/aesbs-core.S_shipped
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/crypto/aesbs-core.S_shipped
+++ linux-3.18.13-rt10-r7s4/arch/arm/crypto/aesbs-core.S_shipped
@@ -58,14 +58,18 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -74,8 +78,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2095,9 +2097,11 @@ bsaes_xts_decrypt:
 	vld1.8	{q8}, [r0]			@ initial tweak
 	adr	r2, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	r9, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	r9, #0x10			@ subtract another 16 bytes
+#endif
 	subs	r9, #0x80
 
 	blo	.Lxts_dec_short
Index: linux-3.18.13-rt10-r7s4/arch/arm/crypto/bsaes-armv7.pl
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/crypto/bsaes-armv7.pl
+++ linux-3.18.13-rt10-r7s4/arch/arm/crypto/bsaes-armv7.pl
@@ -701,14 +701,18 @@ $code.=<<___;
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -717,8 +721,6 @@ $code.=<<___;
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2076,9 +2078,11 @@ bsaes_xts_decrypt:
 	vld1.8	{@XMM[8]}, [r0]			@ initial tweak
 	adr	$magic, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	$len, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	$len, #0x10			@ subtract another 16 bytes
+#endif
 	subs	$len, #0x80
 
 	blo	.Lxts_dec_short
Index: linux-3.18.13-rt10-r7s4/arch/arm/crypto/sha1_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/crypto/sha1_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/crypto/sha1_glue.c
@@ -171,5 +171,5 @@ module_exit(sha1_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
Index: linux-3.18.13-rt10-r7s4/arch/arm/crypto/sha1_neon_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/crypto/sha1_neon_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/crypto/sha1_neon_glue.c
@@ -194,4 +194,4 @@ module_exit(sha1_neon_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
Index: linux-3.18.13-rt10-r7s4/arch/arm/crypto/sha512_neon_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/crypto/sha512_neon_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/crypto/sha512_neon_glue.c
@@ -301,5 +301,5 @@ module_exit(sha512_neon_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
 
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
Index: linux-3.18.13-rt10-r7s4/arch/arm/include/asm/arch_timer.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/include/asm/arch_timer.h
+++ linux-3.18.13-rt10-r7s4/arch/arm/include/asm/arch_timer.h
@@ -78,6 +78,15 @@ static inline u32 arch_timer_get_cntfrq(
 	return val;
 }
 
+static inline u64 arch_counter_get_cntpct(void)
+{
+	u64 cval;
+
+	isb();
+	asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
+	return cval;
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
Index: linux-3.18.13-rt10-r7s4/arch/arm/include/asm/xen/page.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/include/asm/xen/page.h
+++ linux-3.18.13-rt10-r7s4/arch/arm/include/asm/xen/page.h
@@ -107,4 +107,8 @@ static inline bool set_phys_to_machine(u
 #define xen_remap(cookie, size) ioremap_cache((cookie), (size))
 #define xen_unmap(cookie) iounmap((cookie))
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn);
+
 #endif /* _ASM_ARM_XEN_PAGE_H */
Index: linux-3.18.13-rt10-r7s4/arch/arm/kernel/setup.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/kernel/setup.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/kernel/setup.c
@@ -1043,6 +1043,15 @@ static int c_show(struct seq_file *m, vo
 		seq_printf(m, "model name\t: %s rev %d (%s)\n",
 			   cpu_name, cpuid & 15, elf_platform);
 
+#if defined(CONFIG_SMP)
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
+			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
+#else
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000/HZ),
+			   (loops_per_jiffy / (5000/HZ)) % 100);
+#endif
 		/* dump out the processor features */
 		seq_puts(m, "Features\t: ");
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/kernel/smp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/kernel/smp.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/kernel/smp.c
@@ -387,8 +387,17 @@ asmlinkage void secondary_start_kernel(v
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
-	       num_online_cpus());
+	int cpu;
+	unsigned long bogosum = 0;
+
+	for_each_online_cpu(cpu)
+		bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy;
+
+	printk(KERN_INFO "SMP: Total of %d processors activated "
+	       "(%lu.%02lu BogoMIPS).\n",
+	       num_online_cpus(),
+	       bogosum / (500000/HZ),
+	       (bogosum / (5000/HZ)) % 100);
 
 	hyp_mode_check();
 }
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-at91/pm.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-at91/pm.h
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-at91/pm.h
@@ -56,7 +56,7 @@ static inline void at91rm9200_standby(vo
 		"    mcr    p15, 0, %0, c7, c0, 4\n\t"
 		"    str    %5, [%1, %2]"
 		:
-		: "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR),
+		: "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR),
 		  "r" (1), "r" (AT91RM9200_SDRAMC_SRR),
 		  "r" (lpr));
 }
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-imx/clk-imx6q.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-imx/clk-imx6q.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-imx/clk-imx6q.c
@@ -144,8 +144,8 @@ static void __init imx6q_clocks_init(str
 		post_div_table[1].div = 1;
 		post_div_table[2].div = 1;
 		video_div_table[1].div = 1;
-		video_div_table[2].div = 1;
-	};
+		video_div_table[3].div = 1;
+	}
 
 	clk[IMX6QDL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
 	clk[IMX6QDL_PLL2_BYPASS_SRC] = imx_clk_mux("pll2_bypass_src", base + 0x30, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-imx/clk-imx6sx.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-imx/clk-imx6sx.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-imx/clk-imx6sx.c
@@ -558,6 +558,9 @@ static void __init imx6sx_clocks_init(st
 	clk_set_parent(clks[IMX6SX_CLK_GPU_CORE_SEL], clks[IMX6SX_CLK_PLL3_PFD0]);
 	clk_set_parent(clks[IMX6SX_CLK_GPU_AXI_SEL], clks[IMX6SX_CLK_PLL3_PFD0]);
 
+	clk_set_parent(clks[IMX6SX_CLK_QSPI1_SEL], clks[IMX6SX_CLK_PLL2_BUS]);
+	clk_set_parent(clks[IMX6SX_CLK_QSPI2_SEL], clks[IMX6SX_CLK_PLL2_BUS]);
+
 	/* Set initial power mode */
 	imx6q_set_lpm(WAIT_CLOCKED);
 }
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-mvebu/coherency.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-mvebu/coherency.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-mvebu/coherency.c
@@ -342,6 +342,13 @@ static void __init armada_375_380_cohere
 	arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
 
 	/*
+	 * We should switch the PL310 to I/O coherency mode only if
+	 * I/O coherency is actually enabled.
+	 */
+	if (!coherency_available())
+		return;
+
+	/*
 	 * Add the PL310 property "arm,io-coherent". This makes sure the
 	 * outer sync operation is not used, which allows to
 	 * workaround the system erratum that causes deadlocks when
@@ -361,30 +368,51 @@ static int coherency_type(void)
 {
 	struct device_node *np;
 	const struct of_device_id *match;
+	int type;
+
+	/*
+	 * The coherency fabric is needed:
+	 * - For coherency between processors on Armada XP, so only
+	 *   when SMP is enabled.
+	 * - For coherency between the processor and I/O devices, but
+	 *   this coherency requires many pre-requisites (write
+	 *   allocate cache policy, shareable pages, SMP bit set) that
+	 *   are only meant in SMP situations.
+	 *
+	 * Note that this means that on Armada 370, there is currently
+	 * no way to use hardware I/O coherency, because even when
+	 * CONFIG_SMP is enabled, is_smp() returns false due to the
+	 * Armada 370 being a single-core processor. To lift this
+	 * limitation, we would have to find a way to make the cache
+	 * policy set to write-allocate (on all Armada SoCs), and to
+	 * set the shareable attribute in page tables (on all Armada
+	 * SoCs except the Armada 370). Unfortunately, such decisions
+	 * are taken very early in the kernel boot process, at a point
+	 * where we don't know yet on which SoC we are running.
+
+	 */
+	if (!is_smp())
+		return COHERENCY_FABRIC_TYPE_NONE;
 
 	np = of_find_matching_node_and_match(NULL, of_coherency_table, &match);
-	if (np) {
-		int type = (int) match->data;
+	if (!np)
+		return COHERENCY_FABRIC_TYPE_NONE;
 
-		/* Armada 370/XP coherency works in both UP and SMP */
-		if (type == COHERENCY_FABRIC_TYPE_ARMADA_370_XP)
-			return type;
-
-		/* Armada 375 coherency works only on SMP */
-		else if (type == COHERENCY_FABRIC_TYPE_ARMADA_375 && is_smp())
-			return type;
-
-		/* Armada 380 coherency works only on SMP */
-		else if (type == COHERENCY_FABRIC_TYPE_ARMADA_380 && is_smp())
-			return type;
-	}
+	type = (int) match->data;
+
+	of_node_put(np);
 
-	return COHERENCY_FABRIC_TYPE_NONE;
+	return type;
 }
 
+/*
+ * As a precaution, we currently completely disable hardware I/O
+ * coherency, until enough testing is done with automatic I/O
+ * synchronization barriers to validate that it is a proper solution.
+ */
 int coherency_available(void)
 {
-	return coherency_type() != COHERENCY_FABRIC_TYPE_NONE;
+	return false;
 }
 
 int __init coherency_init(void)
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-mvebu/coherency_ll.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-mvebu/coherency_ll.S
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-mvebu/coherency_ll.S
@@ -24,7 +24,10 @@
 #include <asm/cp15.h>
 
 	.text
-/* Returns the coherency base address in r1 (r0 is untouched) */
+/*
+ * Returns the coherency base address in r1 (r0 is untouched), or 0 if
+ * the coherency fabric is not enabled.
+ */
 ENTRY(ll_get_coherency_base)
 	mrc	p15, 0, r1, c1, c0, 0
 	tst	r1, #CR_M @ Check MMU bit enabled
@@ -32,8 +35,13 @@ ENTRY(ll_get_coherency_base)
 
 	/*
 	 * MMU is disabled, use the physical address of the coherency
-	 * base address.
+	 * base address. However, if the coherency fabric isn't mapped
+	 * (i.e its virtual address is zero), it means coherency is
+	 * not enabled, so we return 0.
 	 */
+	ldr	r1, =coherency_base
+	cmp	r1, #0
+	beq	2f
 	adr	r1, 3f
 	ldr	r3, [r1]
 	ldr	r1, [r1, r3]
@@ -85,6 +93,9 @@ ENTRY(ll_add_cpu_to_smp_group)
 	 */
 	mov 	r0, lr
 	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
 	bl	ll_get_coherency_cpumask
 	mov 	lr, r0
 	add	r0, r1, #ARMADA_XP_CFB_CFG_REG_OFFSET
@@ -107,6 +118,9 @@ ENTRY(ll_enable_coherency)
 	 */
 	mov r0, lr
 	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
 	bl	ll_get_coherency_cpumask
 	mov lr, r0
 	add	r0, r1, #ARMADA_XP_CFB_CTL_REG_OFFSET
@@ -131,6 +145,9 @@ ENTRY(ll_disable_coherency)
 	 */
 	mov 	r0, lr
 	bl	ll_get_coherency_base
+	/* Bail out if the coherency is not enabled */
+	cmp	r1, #0
+	reteq	r0
 	bl	ll_get_coherency_cpumask
 	mov 	lr, r0
 	add	r0, r1, #ARMADA_XP_CFB_CTL_REG_OFFSET
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-mvebu/system-controller.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-mvebu/system-controller.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-mvebu/system-controller.c
@@ -126,7 +126,7 @@ int mvebu_system_controller_get_soc_id(u
 		return -ENODEV;
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_MACH_MVEBU_V7)
 void mvebu_armada375_smp_wa_init(void)
 {
 	u32 dev, rev;
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/common.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-omap2/common.h
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/common.h
@@ -249,6 +249,7 @@ extern void omap4_cpu_die(unsigned int c
 extern struct smp_operations omap4_smp_ops;
 
 extern void omap5_secondary_startup(void);
+extern void omap5_secondary_hyp_startup(void);
 #endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PM)
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/omap-headsmp.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-omap2/omap-headsmp.S
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/omap-headsmp.S
@@ -22,6 +22,7 @@
 
 /* Physical address needed since MMU not enabled yet on secondary core */
 #define AUX_CORE_BOOT0_PA			0x48281800
+#define API_HYP_ENTRY				0x102
 
 /*
  * OMAP5 specific entry point for secondary CPU to jump from ROM
@@ -41,6 +42,26 @@ wait:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read
 	b	secondary_startup
 ENDPROC(omap5_secondary_startup)
 /*
+ * Same as omap5_secondary_startup except we call into the ROM to
+ * enable HYP mode first.  This is called instead of
+ * omap5_secondary_startup if the primary CPU was put into HYP mode by
+ * the boot loader.
+ */
+ENTRY(omap5_secondary_hyp_startup)
+wait_2:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
+	ldr	r0, [r2]
+	mov	r0, r0, lsr #5
+	mrc	p15, 0, r4, c0, c0, 5
+	and	r4, r4, #0x0f
+	cmp	r0, r4
+	bne	wait_2
+	ldr	r12, =API_HYP_ENTRY
+	adr	r0, hyp_boot
+	smc	#0
+hyp_boot:
+	b	secondary_startup
+ENDPROC(omap5_secondary_hyp_startup)
+/*
  * OMAP4 specific entry point for secondary CPU to jump from ROM
  * code.  This routine also provides a holding flag into which
  * secondary core is held until we're ready for it to initialise.
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/omap-smp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-omap2/omap-smp.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/omap-smp.c
@@ -22,6 +22,7 @@
 #include <linux/irqchip/arm-gic.h>
 
 #include <asm/smp_scu.h>
+#include <asm/virt.h>
 
 #include "omap-secure.h"
 #include "omap-wakeupgen.h"
@@ -227,8 +228,16 @@ static void __init omap4_smp_prepare_cpu
 	if (omap_secure_apis_support())
 		omap_auxcoreboot_addr(virt_to_phys(startup_addr));
 	else
-		writel_relaxed(virt_to_phys(omap5_secondary_startup),
-			       base + OMAP_AUX_CORE_BOOT_1);
+		/*
+		 * If the boot CPU is in HYP mode then start secondary
+		 * CPU in HYP mode as well.
+		 */
+		if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
+			writel_relaxed(virt_to_phys(omap5_secondary_hyp_startup),
+				       base + OMAP_AUX_CORE_BOOT_1);
+		else
+			writel_relaxed(virt_to_phys(omap5_secondary_startup),
+				       base + OMAP_AUX_CORE_BOOT_1);
 
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -2017,7 +2017,7 @@ static struct omap_hwmod dra7xx_uart3_hw
 	.class		= &dra7xx_uart_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
 	.main_clk	= "uart3_gfclk_mux",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP4UART3_FLAGS,
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = DRA7XX_CM_L4PER_UART3_CLKCTRL_OFFSET,
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/pm44xx.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-omap2/pm44xx.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/pm44xx.c
@@ -160,26 +160,6 @@ static inline int omap4_init_static_deps
 	struct clockdomain *ducati_clkdm, *l3_2_clkdm;
 	int ret = 0;
 
-	if (omap_rev() == OMAP4430_REV_ES1_0) {
-		WARN(1, "Power Management not supported on OMAP4430 ES1.0\n");
-		return -ENODEV;
-	}
-
-	pr_err("Power Management for TI OMAP4.\n");
-	/*
-	 * OMAP4 chip PM currently works only with certain (newer)
-	 * versions of bootloaders. This is due to missing code in the
-	 * kernel to properly reset and initialize some devices.
-	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
-	 */
-	pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
-
-	ret = pwrdm_for_each(pwrdms_setup, NULL);
-	if (ret) {
-		pr_err("Failed to setup powerdomains\n");
-		return ret;
-	}
-
 	/*
 	 * The dynamic dependency between MPUSS -> MEMIF and
 	 * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as
@@ -272,6 +252,15 @@ int __init omap4_pm_init(void)
 
 	pr_info("Power Management for TI OMAP4+ devices.\n");
 
+	/*
+	 * OMAP4 chip PM currently works only with certain (newer)
+	 * versions of bootloaders. This is due to missing code in the
+	 * kernel to properly reset and initialize some devices.
+	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
+	 */
+	if (cpu_is_omap44xx())
+		pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
+
 	ret = pwrdm_for_each(pwrdms_setup, NULL);
 	if (ret) {
 		pr_err("Failed to setup powerdomains.\n");
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/timer.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-omap2/timer.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-omap2/timer.c
@@ -513,11 +513,11 @@ static void __init realtime_counter_init
 	rate = clk_get_rate(sys_clk);
 	/* Numerator/denumerator values refer TRM Realtime Counter section */
 	switch (rate) {
-	case 1200000:
+	case 12000000:
 		num = 64;
 		den = 125;
 		break;
-	case 1300000:
+	case 13000000:
 		num = 768;
 		den = 1625;
 		break;
@@ -529,11 +529,11 @@ static void __init realtime_counter_init
 		num = 192;
 		den = 625;
 		break;
-	case 2600000:
+	case 26000000:
 		num = 384;
 		den = 1625;
 		break;
-	case 2700000:
+	case 27000000:
 		num = 256;
 		den = 1125;
 		break;
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-pxa/corgi.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-pxa/corgi.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-pxa/corgi.c
@@ -26,6 +26,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/io.h>
+#include <linux/regulator/machine.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/spi/corgi_lcd.h>
@@ -752,6 +753,8 @@ static void __init corgi_init(void)
 		sharpsl_nand_partitions[1].size = 53 * 1024 * 1024;
 
 	platform_add_devices(devices, ARRAY_SIZE(devices));
+
+	regulator_has_full_constraints();
 }
 
 static void __init fixup_corgi(struct tag *tags, char **cmdline)
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-pxa/hx4700.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-pxa/hx4700.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-pxa/hx4700.c
@@ -893,6 +893,8 @@ static void __init hx4700_init(void)
 	mdelay(10);
 	gpio_set_value(GPIO71_HX4700_ASIC3_nRESET, 1);
 	mdelay(10);
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(H4700, "HP iPAQ HX4700")
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-pxa/poodle.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-pxa/poodle.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-pxa/poodle.c
@@ -25,6 +25,7 @@
 #include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pxa-i2c.h>
+#include <linux/regulator/machine.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/spi/pxa2xx_spi.h>
@@ -455,6 +456,7 @@ static void __init poodle_init(void)
 	pxa_set_i2c_info(NULL);
 	i2c_register_board_info(0, ARRAY_AND_SIZE(poodle_i2c_devices));
 	poodle_init_spi();
+	regulator_has_full_constraints();
 }
 
 static void __init fixup_poodle(struct tag *tags, char **cmdline)
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-sa1100/pm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-sa1100/pm.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-sa1100/pm.c
@@ -81,6 +81,7 @@ static int sa11x0_pm_enter(suspend_state
 	/*
 	 * Ensure not to come back here if it wasn't intended
 	 */
+	RCSR = RCSR_SMR;
 	PSPR = 0;
 
 	/*
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-shmobile/setup-sh73a0.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-shmobile/setup-sh73a0.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -598,6 +598,7 @@ static struct platform_device ipmmu_devi
 
 static struct renesas_intc_irqpin_config irqpin0_platform_data = {
 	.irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */
+	.control_parent = true,
 };
 
 static struct resource irqpin0_resources[] = {
@@ -659,6 +660,7 @@ static struct platform_device irqpin1_de
 
 static struct renesas_intc_irqpin_config irqpin2_platform_data = {
 	.irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */
+	.control_parent = true,
 };
 
 static struct resource irqpin2_resources[] = {
@@ -689,6 +691,7 @@ static struct platform_device irqpin2_de
 
 static struct renesas_intc_irqpin_config irqpin3_platform_data = {
 	.irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */
+	.control_parent = true,
 };
 
 static struct resource irqpin3_resources[] = {
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-sunxi/Kconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-sunxi/Kconfig
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-sunxi/Kconfig
@@ -1,10 +1,12 @@
 menuconfig ARCH_SUNXI
 	bool "Allwinner SoCs" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
+	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
 	select PINCTRL
 	select SUN4I_TIMER
+	select RESET_CONTROLLER
 
 if ARCH_SUNXI
 
@@ -20,10 +22,8 @@ config MACH_SUN5I
 config MACH_SUN6I
 	bool "Allwinner A31 (sun6i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 	select SUN5I_HSTIMER
 
 config MACH_SUN7I
@@ -37,9 +37,7 @@ config MACH_SUN7I
 config MACH_SUN8I
 	bool "Allwinner A23 (sun8i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 
 endif
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-tegra/reset-handler.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-tegra/reset-handler.S
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-tegra/reset-handler.S
@@ -51,6 +51,7 @@ ENTRY(tegra_resume)
  THUMB(	it	ne )
 	bne	cpu_resume			@ no
 
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r6
 	/* Are we on Tegra20? */
 	cmp	r6, #TEGRA20
 	beq	1f				@ Yes
Index: linux-3.18.13-rt10-r7s4/arch/arm/mach-vexpress/Kconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mach-vexpress/Kconfig
+++ linux-3.18.13-rt10-r7s4/arch/arm/mach-vexpress/Kconfig
@@ -75,6 +75,7 @@ config ARCH_VEXPRESS_TC2_PM
 	depends on MCPM
 	select ARM_CCI
 	select ARCH_VEXPRESS_SPC
+	select ARM_CPU_SUSPEND
 	help
 	  Support for CPU and cluster power management on Versatile Express
 	  with a TC2 (A15x2 A7x3) big.LITTLE core tile.
Index: linux-3.18.13-rt10-r7s4/arch/arm/mm/context.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/mm/context.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/mm/context.c
@@ -144,21 +144,17 @@ static void flush_context(unsigned int c
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 	for_each_possible_cpu(i) {
-		if (i == cpu) {
-			asid = 0;
-		} else {
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			/*
-			 * If this CPU has already been through a
-			 * rollover, but hasn't run another task in
-			 * the meantime, we must preserve its reserved
-			 * ASID, as this is the only trace we have of
-			 * the process it is still running.
-			 */
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
+		asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, i);
+		__set_bit(asid & ~ASID_MASK, asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
Index: linux-3.18.13-rt10-r7s4/arch/arm/xen/mm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm/xen/mm.c
+++ linux-3.18.13-rt10-r7s4/arch/arm/xen/mm.c
@@ -16,6 +16,13 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
+bool xen_arch_need_swiotlb(struct device *dev,
+			   unsigned long pfn,
+			   unsigned long mfn)
+{
+	return (pfn != mfn);
+}
+
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/Kconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/Kconfig
+++ linux-3.18.13-rt10-r7s4/arch/arm64/Kconfig
@@ -193,6 +193,135 @@ endmenu
 
 menu "Kernel Features"
 
+menu "ARM errata workarounds via the alternatives framework"
+
+config ARM64_ERRATUM_826319
+	bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 826319 on Cortex-A53 parts up to r0p2 with an AMBA 4 ACE or
+	  AXI master interface and an L2 cache.
+
+	  If a Cortex-A53 uses an AMBA AXI4 ACE interface to other processors
+	  and is unable to accept a certain write via this interface, it will
+	  not progress on read data presented on the read data channel and the
+	  system can deadlock.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_827319
+	bool "Cortex-A53: 827319: Data cache clean instructions might cause overlapping transactions to the interconnect"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 827319 on Cortex-A53 parts up to r0p2 with an AMBA 5 CHI
+	  master interface and an L2 cache.
+
+	  Under certain conditions this erratum can cause a clean line eviction
+	  to occur at the same time as another transaction to the same address
+	  on the AMBA 5 CHI interface, which can cause data corruption if the
+	  interconnect reorders the two transactions.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_824069
+	bool "Cortex-A53: 824069: Cache line might not be marked as clean after a CleanShared snoop"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 824069 on Cortex-A53 parts up to r0p2 when it is connected
+	  to a coherent interconnect.
+
+	  If a Cortex-A53 processor is executing a store or prefetch for
+	  write instruction at the same time as a processor in another
+	  cluster is executing a cache maintenance operation to the same
+	  address, then this erratum might cause a clean cache line to be
+	  incorrectly marked as dirty.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this option does not necessarily enable the
+	  workaround, as it depends on the alternative framework, which will
+	  only patch the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_819472
+	bool "Cortex-A53: 819472: Store exclusive instructions might cause data corruption"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 819472 on Cortex-A53 parts up to r0p1 with an L2 cache
+	  present when it is connected to a coherent interconnect.
+
+	  If the processor is executing a load and store exclusive sequence at
+	  the same time as a processor in another cluster is executing a cache
+	  maintenance operation to the same address, then this erratum might
+	  cause data corruption.
+
+	  The workaround promotes data cache clean instructions to
+	  data cache clean-and-invalidate.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_832075
+	bool "Cortex-A57: 832075: possible deadlock on mixing exclusive memory accesses with device loads"
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 832075 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might deadlock when exclusive load/store
+	  instructions to Write-Back memory are mixed with Device loads.
+
+	  The workaround is to promote device loads to use Load-Acquire
+	  semantics.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_845719
+	bool "Cortex-A53: 845719: a load might read incorrect data"
+	depends on COMPAT
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 845719 on Cortex-A53 parts up to r0p4.
+
+	  When running a compat (AArch32) userspace on an affected Cortex-A53
+	  part, a load at EL0 from a virtual address that matches the bottom 32
+	  bits of the virtual address used by a recent load at (AArch64) EL1
+	  might return incorrect data.
+
+	  The workaround is to write the contextidr_el1 register on exception
+	  return to a 32-bit task.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
+endmenu
+
+
 choice
 	prompt "Page size"
 	default ARM64_4K_PAGES
Index: linux-3.18.13-rt10-r7s4/arch/arm64/crypto/aes-ce-ccm-glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -294,4 +294,4 @@ module_exit(aes_mod_exit);
 MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("ccm(aes)");
+MODULE_ALIAS_CRYPTO("ccm(aes)");
Index: linux-3.18.13-rt10-r7s4/arch/arm64/crypto/aes-glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/crypto/aes-glue.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/crypto/aes-glue.c
@@ -38,10 +38,10 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS
 #define aes_xts_encrypt		neon_aes_xts_encrypt
 #define aes_xts_decrypt		neon_aes_xts_decrypt
 MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
-MODULE_ALIAS("ecb(aes)");
-MODULE_ALIAS("cbc(aes)");
-MODULE_ALIAS("ctr(aes)");
-MODULE_ALIAS("xts(aes)");
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
 #endif
 
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/alternative-asm.h
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/alternative-asm.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ALTERNATIVE_ASM_H
+#define __ASM_ALTERNATIVE_ASM_H
+
+#ifdef __ASSEMBLY__
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+	.word \orig_offset - .
+	.word \alt_offset - .
+	.hword \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+.macro alternative_insn insn1 insn2 cap
+661:	\insn1
+662:	.pushsection .altinstructions, "a"
+	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+663:	\insn2
+664:	.popsection
+	.if ((664b-663b) != (662b-661b))
+		.error "Alternatives instruction length mismatch"
+	.endif
+.endm
+
+#endif  /*  __ASSEMBLY__  */
+
+#endif /* __ASM_ALTERNATIVE_ASM_H */
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/alternative.h
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/alternative.h
@@ -0,0 +1,43 @@
+#ifndef __ASM_ALTERNATIVE_H
+#define __ASM_ALTERNATIVE_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+
+struct alt_instr {
+	s32 orig_offset;	/* offset to original instruction */
+	s32 alt_offset;		/* offset to replacement instruction */
+	u16 cpufeature;		/* cpufeature bit set for replacement */
+	u8  orig_len;		/* size of original instruction(s) */
+	u8  alt_len;		/* size of new instruction(s), <= orig_len */
+};
+
+void apply_alternatives(void);
+void free_alternatives_memory(void);
+
+#define ALTINSTR_ENTRY(feature)						      \
+	" .word 661b - .\n"				/* label           */ \
+	" .word 663f - .\n"				/* new instruction */ \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature)						\
+	".popsection\n"							\
+	".pushsection .altinstr_replacement, \"a\"\n"			\
+	"663:\n\t"							\
+	newinstr "\n"							\
+	"664:\n\t"							\
+	".popsection\n\t"						\
+	".if ((664b-663b) != (662b-661b))\n\t"				\
+	"	.error \"Alternatives instruction length mismatch\"\n\t"\
+	".endif\n"
+
+#endif /* __ASM_ALTERNATIVE_H */
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/arch_timer.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/arch_timer.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/arch_timer.h
@@ -104,6 +104,15 @@ static inline void arch_timer_set_cntkct
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
+static inline u64 arch_counter_get_cntpct(void)
+{
+	/*
+	 * AArch64 kernel and user space mandate the use of CNTVCT.
+	 */
+	BUG();
+	return 0;
+}
+
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/cpufeature.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/cpufeature.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/cpufeature.h
@@ -21,9 +21,39 @@
 #define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
 #define cpu_feature(x)		ilog2(HWCAP_ ## x)
 
+#define ARM64_WORKAROUND_CLEAN_CACHE		0
+#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
+#define ARM64_WORKAROUND_845719			2
+
+#define NCAPS					3
+
+#ifndef __ASSEMBLY__
+
+extern DECLARE_BITMAP(cpu_hwcaps, NCAPS);
+
 static inline bool cpu_have_feature(unsigned int num)
 {
 	return elf_hwcap & (1UL << num);
 }
 
+static inline bool cpus_have_cap(unsigned int num)
+{
+	if (num >= NCAPS)
+		return false;
+	return test_bit(num, cpu_hwcaps);
+}
+
+static inline void cpus_set_cap(unsigned int num)
+{
+	if (num >= NCAPS)
+		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
+			num, NCAPS);
+	else
+		__set_bit(num, cpu_hwcaps);
+}
+
+void check_local_cpu_errata(void);
+
+#endif /* __ASSEMBLY__ */
+
 #endif
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/cputype.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/cputype.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/cputype.h
@@ -57,6 +57,11 @@
 #define MIDR_IMPLEMENTOR(midr)	\
 	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
 
+#define MIDR_CPU_PART(imp, partnum) \
+	(((imp)			<< MIDR_IMPLEMENTOR_SHIFT) | \
+	(0xf			<< MIDR_ARCHITECTURE_SHIFT) | \
+	((partnum)		<< MIDR_PARTNUM_SHIFT))
+
 #define ARM_CPU_IMP_ARM		0x41
 #define ARM_CPU_IMP_APM		0x50
 
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/hwcap.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/hwcap.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/hwcap.h
@@ -30,6 +30,7 @@
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_LPAE	(1 << 20)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
 #define COMPAT_HWCAP2_AES	(1 << 0)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/io.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/io.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/io.h
@@ -28,6 +28,8 @@
 #include <asm/barrier.h>
 #include <asm/pgtable.h>
 #include <asm/early_ioremap.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
 
 #include <xen/xen.h>
 
@@ -57,28 +59,41 @@ static inline void __raw_writeq(u64 val,
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile("ldrb %w0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
+				 "ldarb %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
-	asm volatile("ldrh %w0, [%1]" : "=r" (val) : "r" (addr));
+
+	asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
+				 "ldarh %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldr %w0, [%1]",
+				 "ldar %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	u64 val;
-	asm volatile("ldr %0, [%1]" : "=r" (val) : "r" (addr));
+	asm volatile(ALTERNATIVE("ldr %0, [%1]",
+				 "ldar %0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
 	return val;
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/mmu_context.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/mmu_context.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct
 {
 	unsigned int cpu = smp_processor_id();
 
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/tlb.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/tlb.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/tlb.h
@@ -19,10 +19,6 @@
 #ifndef __ASM_TLB_H
 #define __ASM_TLB_H
 
-#define  __tlb_remove_pmd_tlb_entry __tlb_remove_pmd_tlb_entry
-
-#include <asm-generic/tlb.h>
-
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 
@@ -37,71 +33,23 @@ static inline void __tlb_remove_table(vo
 #define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
-/*
- * There's three ways the TLB shootdown code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     Page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- */
+#include <asm-generic/tlb.h>
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (tlb->fullmm) {
 		flush_tlb_mm(tlb->mm);
-	} else if (tlb->end > 0) {
+	} else {
 		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
 		flush_tlb_range(&vma, tlb->start, tlb->end);
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		tlb->start = min(tlb->start, addr);
-		tlb->end = max(tlb->end, addr + PAGE_SIZE);
-	}
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void tlb_start_vma(struct mmu_gather *tlb,
-				 struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		tlb->start = TASK_SIZE;
-		tlb->end = 0;
 	}
 }
 
-static inline void tlb_end_vma(struct mmu_gather *tlb,
-			       struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	pgtable_page_dtor(pte);
-	tlb_add_flush(tlb, addr);
 	tlb_remove_entry(tlb, pte);
 }
 
@@ -109,7 +57,7 @@ static inline void __pte_free_tlb(struct
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -118,15 +66,9 @@ static inline void __pmd_free_tlb(struct
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
-static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp,
-						unsigned long address)
-{
-	tlb_add_flush(tlb, address);
-}
-
 #endif
Index: linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/tlbflush.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/include/asm/tlbflush.h
+++ linux-3.18.13-rt10-r7s4/arch/arm64/include/asm/tlbflush.h
@@ -149,6 +149,19 @@ static inline void flush_tlb_kernel_rang
 }
 
 /*
+ * Used to invalidate the TLB (walk caches) corresponding to intermediate page
+ * table levels (pgd/pud/pmd).
+ */
+static inline void __flush_tlb_pgtable(struct mm_struct *mm,
+				       unsigned long uaddr)
+{
+	unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48);
+
+	dsb(ishst);
+	asm("tlbi	vae1is, %0" : : "r" (addr));
+	dsb(ish);
+}
+/*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */
 static inline void update_mmu_cache(struct vm_area_struct *vma,
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/Makefile
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/Makefile
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/Makefile
@@ -15,7 +15,7 @@ arm64-obj-y		:= cputable.o debug-monitor
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
 			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o	\
-			   cpuinfo.o
+			   cpuinfo.o cpu_errata.o alternative.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/alternative.c
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/alternative.c
@@ -0,0 +1,64 @@
+/*
+ * alternative runtime patching
+ * inspired by the x86 version
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) "alternatives: " fmt
+
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <asm/cacheflush.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+#include <linux/stop_machine.h>
+
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
+static int __apply_alternatives(void *dummy)
+{
+	struct alt_instr *alt;
+	u8 *origptr, *replptr;
+
+	for (alt = __alt_instructions; alt < __alt_instructions_end; alt++) {
+		if (!cpus_have_cap(alt->cpufeature))
+			continue;
+
+		BUG_ON(alt->alt_len > alt->orig_len);
+
+		pr_info_once("patching kernel code\n");
+
+		origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
+		replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
+		memcpy(origptr, replptr, alt->alt_len);
+		flush_icache_range((uintptr_t)origptr,
+				   (uintptr_t)(origptr + alt->alt_len));
+	}
+
+	return 0;
+}
+
+void apply_alternatives(void)
+{
+	/* better not try code patching on a live SMP system */
+	stop_machine(__apply_alternatives, NULL, NULL);
+}
+
+void free_alternatives_memory(void)
+{
+	free_reserved_area(__alt_instructions, __alt_instructions_end,
+			   0, "alternatives");
+}
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/cpu_errata.c
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/cpu_errata.c
@@ -0,0 +1,120 @@
+/*
+ * Contains CPU specific errata definitions
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) "alternative: " fmt
+
+#include <linux/types.h>
+#include <asm/cpu.h>
+#include <asm/cputype.h>
+#include <asm/cpufeature.h>
+
+#define MIDR_CORTEX_A53 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
+#define MIDR_CORTEX_A57 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+
+/*
+ * Add a struct or another datatype to the union below if you need
+ * different means to detect an affected CPU.
+ */
+struct arm64_cpu_capabilities {
+	const char *desc;
+	u16 capability;
+	bool (*is_affected)(struct arm64_cpu_capabilities *);
+	union {
+		struct {
+			u32 midr_model;
+			u32 midr_range_min, midr_range_max;
+		};
+	};
+};
+
+#define CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \
+			MIDR_ARCHITECTURE_MASK)
+
+static bool __maybe_unused
+is_affected_midr_range(struct arm64_cpu_capabilities *entry)
+{
+	u32 midr = read_cpuid_id();
+
+	if ((midr & CPU_MODEL_MASK) != entry->midr_model)
+		return false;
+
+	midr &= MIDR_REVISION_MASK | MIDR_VARIANT_MASK;
+
+	return (midr >= entry->midr_range_min && midr <= entry->midr_range_max);
+}
+
+#define MIDR_RANGE(model, min, max) \
+	.is_affected = is_affected_midr_range, \
+	.midr_model = model, \
+	.midr_range_min = min, \
+	.midr_range_max = max
+
+struct arm64_cpu_capabilities arm64_errata[] = {
+#if	defined(CONFIG_ARM64_ERRATUM_826319) || \
+	defined(CONFIG_ARM64_ERRATUM_827319) || \
+	defined(CONFIG_ARM64_ERRATUM_824069)
+	{
+	/* Cortex-A53 r0p[012] */
+		.desc = "ARM errata 826319, 827319, 824069",
+		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
+		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x02),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_819472
+	{
+	/* Cortex-A53 r0p[01] */
+		.desc = "ARM errata 819472",
+		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
+		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x01),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_832075
+	{
+	/* Cortex-A57 r0p0 - r1p2 */
+		.desc = "ARM erratum 832075",
+		.capability = ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE,
+		MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 2),
+	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_845719
+	{
+	/* Cortex-A53 r0p[01234] */
+		.desc = "ARM erratum 845719",
+		.capability = ARM64_WORKAROUND_845719,
+		MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x04),
+	},
+#endif
+	{
+	}
+};
+
+void check_local_cpu_errata(void)
+{
+	struct arm64_cpu_capabilities *cpus = arm64_errata;
+	int i;
+
+	for (i = 0; cpus[i].desc; i++) {
+		if (!cpus[i].is_affected(&cpus[i]))
+			continue;
+
+		if (!cpus_have_cap(cpus[i].capability))
+			pr_info("enabling workaround for %s\n", cpus[i].desc);
+		cpus_set_cap(cpus[i].capability);
+	}
+}
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/cpuinfo.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/cpuinfo.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/cpuinfo.c
@@ -18,6 +18,7 @@
 #include <asm/cachetype.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/cpufeature.h>
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
@@ -186,6 +187,8 @@ static void __cpuinfo_store_cpu(struct c
 	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
 
 	cpuinfo_detect_icache_policy(info);
+
+	check_local_cpu_errata();
 }
 
 void cpuinfo_store_cpu(void)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/efi.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/efi.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/efi.c
@@ -327,6 +327,7 @@ void __init efi_idmap_init(void)
 
 	/* boot time idmap_pg_dir is incomplete, so fill in missing parts */
 	efi_setup_idmap();
+	early_memunmap(memmap.map, memmap.map_end - memmap.map);
 }
 
 static int __init remap_region(efi_memory_desc_t *md, void **new)
@@ -381,7 +382,6 @@ static int __init arm64_enter_virtual_mo
 	}
 
 	mapsize = memmap.map_end - memmap.map;
-	early_memunmap(memmap.map, mapsize);
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/entry.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/entry.S
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/entry.S
@@ -21,8 +21,10 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 
+#include <asm/alternative-asm.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/thread_info.h>
@@ -118,6 +120,24 @@
 	.if	\el == 0
 	ct_user_enter
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
+
+#ifdef CONFIG_ARM64_ERRATUM_845719
+	alternative_insn						\
+	"nop",								\
+	"tbz x22, #4, 1f",						\
+	ARM64_WORKAROUND_845719
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+	alternative_insn						\
+	"nop; nop",							\
+	"mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:",		\
+	ARM64_WORKAROUND_845719
+#else
+	alternative_insn						\
+	"nop",								\
+	"msr contextidr_el1, xzr; 1:",					\
+	ARM64_WORKAROUND_845719
+#endif
+#endif
 	.endif
 	.if	\ret
 	ldr	x1, [sp, #S_X1]			// preserve x0 (syscall return)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/setup.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/setup.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/setup.c
@@ -43,12 +43,14 @@
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
 #include <linux/efi.h>
+#include <linux/personality.h>
 
 #include <asm/fixmap.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
@@ -72,13 +74,15 @@ EXPORT_SYMBOL_GPL(elf_hwcap);
 				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
 				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
 				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
-				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
+				 COMPAT_HWCAP_LPAE)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
 unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
+DECLARE_BITMAP(cpu_hwcaps, NCAPS);
+
 static const char *cpu_name;
-static const char *machine_name;
 phys_addr_t __fdt_pointer __initdata;
 
 /*
@@ -310,8 +314,6 @@ static void __init setup_machine_fdt(phy
 		while (true)
 			cpu_relax();
 	}
-
-	machine_name = of_flat_dt_get_machine_name();
 }
 
 /*
@@ -393,6 +395,7 @@ void __init setup_arch(char **cmdline_p)
 	request_standard_resources();
 
 	efi_idmap_init();
+	early_ioremap_reset();
 
 	unflatten_device_tree();
 
@@ -447,14 +450,50 @@ static const char *hwcap_str[] = {
 	NULL
 };
 
+#ifdef CONFIG_COMPAT
+static const char *compat_hwcap_str[] = {
+	"swp",
+	"half",
+	"thumb",
+	"26bit",
+	"fastmult",
+	"fpa",
+	"vfp",
+	"edsp",
+	"java",
+	"iwmmxt",
+	"crunch",
+	"thumbee",
+	"neon",
+	"vfpv3",
+	"vfpv3d16",
+	"tls",
+	"vfpv4",
+	"idiva",
+	"idivt",
+	"vfpd32",
+	"lpae",
+	"evtstrm"
+};
+
+static const char *compat_hwcap2_str[] = {
+	"aes",
+	"pmull",
+	"sha1",
+	"sha2",
+	"crc32",
+	NULL
+};
+#endif /* CONFIG_COMPAT */
+
 static int c_show(struct seq_file *m, void *v)
 {
-	int i;
-
-	seq_printf(m, "Processor\t: %s rev %d (%s)\n",
-		   cpu_name, read_cpuid_id() & 15, ELF_PLATFORM);
+	int i, j;
 
 	for_each_online_cpu(i) {
+		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
+		u32 midr = cpuinfo->reg_midr;
+
 		/*
 		 * glibc reads /proc/cpuinfo to determine the number of
 		 * online processors, looking for lines beginning with
@@ -463,24 +502,38 @@ static int c_show(struct seq_file *m, vo
 #ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
 #endif
-	}
-
-	/* dump out the processor features */
-	seq_puts(m, "Features\t: ");
 
-	for (i = 0; hwcap_str[i]; i++)
-		if (elf_hwcap & (1 << i))
-			seq_printf(m, "%s ", hwcap_str[i]);
-
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
-	seq_printf(m, "CPU architecture: AArch64\n");
-	seq_printf(m, "CPU variant\t: 0x%x\n", (read_cpuid_id() >> 20) & 15);
-	seq_printf(m, "CPU part\t: 0x%03x\n", (read_cpuid_id() >> 4) & 0xfff);
-	seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
-
-	seq_puts(m, "\n");
+		/*
+		 * Dump out the common processor features in a single line.
+		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)
+		 * rather than attempting to parse this, but there's a body of
+		 * software which does already (at least for 32-bit).
+		 */
+		seq_puts(m, "Features\t:");
+		if (personality(current->personality) == PER_LINUX32) {
+#ifdef CONFIG_COMPAT
+			for (j = 0; compat_hwcap_str[j]; j++)
+				if (compat_elf_hwcap & (1 << j))
+					seq_printf(m, " %s", compat_hwcap_str[j]);
+
+			for (j = 0; compat_hwcap2_str[j]; j++)
+				if (compat_elf_hwcap2 & (1 << j))
+					seq_printf(m, " %s", compat_hwcap2_str[j]);
+#endif /* CONFIG_COMPAT */
+		} else {
+			for (j = 0; hwcap_str[j]; j++)
+				if (elf_hwcap & (1 << j))
+					seq_printf(m, " %s", hwcap_str[j]);
+		}
+		seq_puts(m, "\n");
 
-	seq_printf(m, "Hardware\t: %s\n", machine_name);
+		seq_printf(m, "CPU implementer\t: 0x%02x\n",
+			   MIDR_IMPLEMENTOR(midr));
+		seq_printf(m, "CPU architecture: 8\n");
+		seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
+		seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
+		seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
+	}
 
 	return 0;
 }
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/signal32.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/signal32.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/signal32.c
@@ -154,8 +154,7 @@ int copy_siginfo_to_user32(compat_siginf
 	case __SI_TIMER:
 		 err |= __put_user(from->si_tid, &to->si_tid);
 		 err |= __put_user(from->si_overrun, &to->si_overrun);
-		 err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr,
-				   &to->si_ptr);
+		 err |= __put_user(from->si_int, &to->si_int);
 		break;
 	case __SI_POLL:
 		err |= __put_user(from->si_band, &to->si_band);
@@ -184,7 +183,7 @@ int copy_siginfo_to_user32(compat_siginf
 	case __SI_MESGQ: /* But this is */
 		err |= __put_user(from->si_pid, &to->si_pid);
 		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr);
+		err |= __put_user(from->si_int, &to->si_int);
 		break;
 	default: /* this is just in case for now ... */
 		err |= __put_user(from->si_pid, &to->si_pid);
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/sleep.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/sleep.S
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/sleep.S
@@ -147,14 +147,12 @@ cpu_resume_after_mmu:
 	ret
 ENDPROC(cpu_resume_after_mmu)
 
-	.data
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 #ifdef CONFIG_SMP
 	mrs	x1, mpidr_el1
-	adr	x4, mpidr_hash_ptr
-	ldr	x5, [x4]
-	add	x8, x4, x5		// x8 = struct mpidr_hash phys address
+	adrp	x8, mpidr_hash
+	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
         /* retrieve mpidr_hash members to compute the hash */
 	ldr	x2, [x8, #MPIDR_HASH_MASK]
 	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
@@ -164,14 +162,15 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adr	x0, sleep_save_sp
+	adrp	x0, sleep_save_sp
+	add	x0, x0, #:lo12:sleep_save_sp
 	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adr	x1, sleep_idmap_phys
+	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1]
+	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
@@ -180,26 +179,3 @@ ENTRY(cpu_resume)
 	bl	cpu_do_resume		// PC relative jump, MMU off
 	b	cpu_resume_mmu		// Resume MMU, never returns
 ENDPROC(cpu_resume)
-
-	.align 3
-mpidr_hash_ptr:
-	/*
-	 * offset of mpidr_hash symbol from current location
-	 * used to obtain run-time mpidr_hash address with MMU off
-         */
-	.quad	mpidr_hash - .
-/*
- * physical address of identity mapped page tables
- */
-	.type	sleep_idmap_phys, #object
-ENTRY(sleep_idmap_phys)
-	.quad	0
-/*
- * struct sleep_save_sp {
- *	phys_addr_t *save_ptr_stash;
- *	phys_addr_t save_ptr_stash_phys;
- * };
- */
-	.type	sleep_save_sp, #object
-ENTRY(sleep_save_sp)
-	.space	SLEEP_SAVE_SP_SZ	// struct sleep_save_sp
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/smp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/smp.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/smp.c
@@ -37,6 +37,7 @@
 #include <linux/of.h>
 #include <linux/irq_work.h>
 
+#include <asm/alternative.h>
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cpu.h>
@@ -309,6 +310,7 @@ void cpu_die(void)
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
+	apply_alternatives();
 }
 
 void __init smp_prepare_boot_cpu(void)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/suspend.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/suspend.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/suspend.c
@@ -5,6 +5,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
+#include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
@@ -98,7 +99,18 @@ int __cpu_suspend(unsigned long arg, int
 	 */
 	ret = __cpu_suspend_enter(arg, fn);
 	if (ret == 0) {
-		cpu_switch_mm(mm->pgd, mm);
+		/*
+		 * We are resuming from reset with TTBR0_EL1 set to the
+		 * idmap to enable the MMU; restore the active_mm mappings in
+		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
+		 * the thread entered __cpu_suspend with TTBR0_EL1 set to
+		 * reserved TTBR0 page tables and should be restored as such.
+		 */
+		if (mm == &init_mm)
+			cpu_set_reserved_ttbr0();
+		else
+			cpu_switch_mm(mm->pgd, mm);
+
 		flush_tlb_all();
 
 		/*
@@ -126,8 +138,8 @@ int __cpu_suspend(unsigned long arg, int
 	return ret;
 }
 
-extern struct sleep_save_sp sleep_save_sp;
-extern phys_addr_t sleep_idmap_phys;
+struct sleep_save_sp sleep_save_sp;
+phys_addr_t sleep_idmap_phys;
 
 static int __init cpu_suspend_init(void)
 {
Index: linux-3.18.13-rt10-r7s4/arch/arm64/kernel/vmlinux.lds.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/kernel/vmlinux.lds.S
+++ linux-3.18.13-rt10-r7s4/arch/arm64/kernel/vmlinux.lds.S
@@ -100,6 +100,17 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 
+	. = ALIGN(4);
+	.altinstructions : {
+		__alt_instructions = .;
+		*(.altinstructions)
+		__alt_instructions_end = .;
+	}
+	.altinstr_replacement : {
+		*(.altinstr_replacement)
+	}
+
+	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/mm/cache.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/mm/cache.S
+++ linux-3.18.13-rt10-r7s4/arch/arm64/mm/cache.S
@@ -20,6 +20,8 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
 #include "proc-macros.S"
 
@@ -210,7 +212,7 @@ __dma_clean_range:
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x0, x0, x3
-1:	dc	cvac, x0			// clean D / U line
+1:	alternative_insn "dc cvac, x0", "dc civac, x0", ARM64_WORKAROUND_CLEAN_CACHE
 	add	x0, x0, x2
 	cmp	x0, x1
 	b.lo	1b
Index: linux-3.18.13-rt10-r7s4/arch/arm64/mm/dma-mapping.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/mm/dma-mapping.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/mm/dma-mapping.c
@@ -51,7 +51,7 @@ static int __init early_coherent_pool(ch
 }
 early_param("coherent_pool", early_coherent_pool);
 
-static void *__alloc_from_pool(size_t size, struct page **ret_page)
+static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
 {
 	unsigned long val;
 	void *ptr = NULL;
@@ -67,6 +67,8 @@ static void *__alloc_from_pool(size_t si
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
+		if (flags & __GFP_ZERO)
+			memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -101,6 +103,7 @@ static void *__dma_alloc_coherent(struct
 		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
+		void *addr;
 
 		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
@@ -109,7 +112,10 @@ static void *__dma_alloc_coherent(struct
 			return NULL;
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-		return page_address(page);
+		addr = page_address(page);
+		if (flags & __GFP_ZERO)
+			memset(addr, 0, size);
+		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
 	}
@@ -145,7 +151,7 @@ static void *__dma_alloc_noncoherent(str
 
 	if (!(flags & __GFP_WAIT)) {
 		struct page *page = NULL;
-		void *addr = __alloc_from_pool(size, &page);
+		void *addr = __alloc_from_pool(size, &page, flags);
 
 		if (addr)
 			*dma_handle = phys_to_dma(dev, page_to_phys(page));
Index: linux-3.18.13-rt10-r7s4/arch/arm64/mm/init.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/mm/init.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/mm/init.c
@@ -39,6 +39,7 @@
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
+#include <asm/alternative.h>
 
 #include "mm.h"
 
@@ -325,6 +326,7 @@ void __init mem_init(void)
 void free_initmem(void)
 {
 	free_initmem_default(0);
+	free_alternatives_memory();
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -333,14 +335,8 @@ static int keep_initrd;
 
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd) {
-		if (start == initrd_start)
-			start = round_down(start, PAGE_SIZE);
-		if (end == initrd_end)
-			end = round_up(end, PAGE_SIZE);
-
+	if (!keep_initrd)
 		free_reserved_area((void *)start, (void *)end, 0, "initrd");
-	}
 }
 
 static int __init keepinitrd_setup(char *__unused)
Index: linux-3.18.13-rt10-r7s4/arch/arm64/net/bpf_jit_comp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/arm64/net/bpf_jit_comp.c
+++ linux-3.18.13-rt10-r7s4/arch/arm64/net/bpf_jit_comp.c
@@ -60,7 +60,7 @@ struct jit_ctx {
 	const struct bpf_prog *prog;
 	int idx;
 	int tmp_used;
-	int body_offset;
+	int epilogue_offset;
 	int *offset;
 	u32 *image;
 };
@@ -130,8 +130,8 @@ static void jit_fill_hole(void *area, un
 
 static inline int epilogue_offset(const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[ctx->prog->len - 1];
-	int from = ctx->idx - ctx->body_offset;
+	int to = ctx->epilogue_offset;
+	int from = ctx->idx;
 
 	return to - from;
 }
@@ -463,6 +463,8 @@ emit_cond_jmp:
 	}
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
+		/* Optimization: when last instruction is EXIT,
+		   simply fallthrough to epilogue. */
 		if (i == ctx->prog->len - 1)
 			break;
 		jmp_offset = epilogue_offset(ctx);
@@ -685,11 +687,13 @@ void bpf_int_jit_compile(struct bpf_prog
 
 	/* 1. Initial fake pass to compute ctx->idx. */
 
-	/* Fake pass to fill in ctx->offset. */
+	/* Fake pass to fill in ctx->offset and ctx->tmp_used. */
 	if (build_body(&ctx))
 		goto out;
 
 	build_prologue(&ctx);
+
+	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
 
 	/* Now we know the actual image size. */
@@ -706,7 +710,6 @@ void bpf_int_jit_compile(struct bpf_prog
 
 	build_prologue(&ctx);
 
-	ctx.body_offset = ctx.idx;
 	if (build_body(&ctx)) {
 		bpf_jit_binary_free(header);
 		goto out;
Index: linux-3.18.13-rt10-r7s4/arch/avr32/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/avr32/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/avr32/mm/fault.c
@@ -142,6 +142,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/cris/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/cris/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/cris/mm/fault.c
@@ -176,6 +176,8 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/frv/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/frv/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/frv/mm/fault.c
@@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datamm
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/ia64/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/ia64/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/ia64/mm/fault.c
@@ -172,6 +172,8 @@ retry:
 		 */
 		if (fault & VM_FAULT_OOM) {
 			goto out_of_memory;
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			goto bad_area;
 		} else if (fault & VM_FAULT_SIGBUS) {
 			signal = SIGBUS;
 			goto bad_area;
Index: linux-3.18.13-rt10-r7s4/arch/m32r/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/m32r/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/m32r/mm/fault.c
@@ -200,6 +200,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/m68k/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/m68k/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/m68k/mm/fault.c
@@ -145,6 +145,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto map_err;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bus_err;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/metag/include/asm/processor.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/metag/include/asm/processor.h
+++ linux-3.18.13-rt10-r7s4/arch/metag/include/asm/processor.h
@@ -149,8 +149,8 @@ extern void exit_thread(void);
 
 unsigned long get_wchan(struct task_struct *p);
 
-#define	KSTK_EIP(tsk)	((tsk)->thread.kernel_context->CurrPC)
-#define	KSTK_ESP(tsk)	((tsk)->thread.kernel_context->AX[0].U0)
+#define	KSTK_EIP(tsk)	(task_pt_regs(tsk)->ctx.CurrPC)
+#define	KSTK_ESP(tsk)	(task_pt_regs(tsk)->ctx.AX[0].U0)
 
 #define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
 
Index: linux-3.18.13-rt10-r7s4/arch/metag/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/metag/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/metag/mm/fault.c
@@ -141,6 +141,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/microblaze/include/asm/tlb.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/microblaze/include/asm/tlb.h
+++ linux-3.18.13-rt10-r7s4/arch/microblaze/include/asm/tlb.h
@@ -14,7 +14,6 @@
 #define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
 
 #include <linux/pagemap.h>
-#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_MMU
 #define tlb_start_vma(tlb, vma)		do { } while (0)
@@ -22,4 +21,6 @@
 #define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
 #endif
 
+#include <asm-generic/tlb.h>
+
 #endif /* _ASM_MICROBLAZE_TLB_H */
Index: linux-3.18.13-rt10-r7s4/arch/microblaze/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/microblaze/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/microblaze/mm/fault.c
@@ -224,6 +224,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/mips/alchemy/common/clock.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/alchemy/common/clock.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/alchemy/common/clock.c
@@ -128,6 +128,8 @@ static unsigned long alchemy_clk_cpu_rec
 		t = 396000000;
 	else {
 		t = alchemy_rdsys(AU1000_SYS_CPUPLL) & 0x7f;
+		if (alchemy_get_cputype() < ALCHEMY_CPU_AU1300)
+			t &= 0x3f;
 		t *= parent_rate;
 	}
 
Index: linux-3.18.13-rt10-r7s4/arch/mips/cavium-octeon/smp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/cavium-octeon/smp.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/cavium-octeon/smp.c
@@ -240,9 +240,7 @@ static int octeon_cpu_disable(void)
 
 	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
-	local_irq_disable();
 	octeon_fixup_irqs();
-	local_irq_enable();
 
 	flush_cache_all();
 	local_flush_tlb_all();
Index: linux-3.18.13-rt10-r7s4/arch/mips/include/asm/asmmacro.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/include/asm/asmmacro.h
+++ linux-3.18.13-rt10-r7s4/arch/mips/include/asm/asmmacro.h
@@ -304,7 +304,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@@ -313,7 +313,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	add	$1, \base, \off
+	addu	$1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
Index: linux-3.18.13-rt10-r7s4/arch/mips/include/asm/cpu-info.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/include/asm/cpu-info.h
+++ linux-3.18.13-rt10-r7s4/arch/mips/include/asm/cpu-info.h
@@ -84,6 +84,11 @@ struct cpuinfo_mips {
 	 * (shifted by _CACHE_SHIFT)
 	 */
 	unsigned int		writecombine;
+	/*
+	 * Simple counter to prevent enabling HTW in nested
+	 * htw_start/htw_stop calls
+	 */
+	unsigned int		htw_seq;
 } __attribute__((aligned(SMP_CACHE_BYTES)));
 
 extern struct cpuinfo_mips cpu_data[];
Index: linux-3.18.13-rt10-r7s4/arch/mips/include/asm/mipsregs.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/include/asm/mipsregs.h
+++ linux-3.18.13-rt10-r7s4/arch/mips/include/asm/mipsregs.h
@@ -1343,12 +1343,27 @@ do {									\
 	__res;								\
 })
 
+#define _write_32bit_cp1_register(dest, val, gas_hardfloat)		\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	reorder					\n"	\
+	"	"STR(gas_hardfloat)"				\n"	\
+	"	ctc1	%0,"STR(dest)"				\n"	\
+	"	.set	pop					\n"	\
+	: : "r" (val));							\
+} while (0)
+
 #ifdef GAS_HAS_SET_HARDFLOAT
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, .set hardfloat)
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, .set hardfloat)
 #else
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, )
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, )
 #endif
 
 #ifdef HAVE_AS_DSP
Index: linux-3.18.13-rt10-r7s4/arch/mips/include/asm/mmu_context.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/include/asm/mmu_context.h
+++ linux-3.18.13-rt10-r7s4/arch/mips/include/asm/mmu_context.h
@@ -25,7 +25,6 @@ do {									\
 	if (cpu_has_htw) {						\
 		write_c0_pwbase(pgd);					\
 		back_to_back_c0_hazard();				\
-		htw_reset();						\
 	}								\
 } while (0)
 
@@ -142,6 +141,7 @@ static inline void switch_mm(struct mm_s
 	unsigned long flags;
 	local_irq_save(flags);
 
+	htw_stop();
 	/* Check if our ASID is of an older version and thus invalid */
 	if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & ASID_VERSION_MASK)
 		get_new_mmu_context(next, cpu);
@@ -154,6 +154,7 @@ static inline void switch_mm(struct mm_s
 	 */
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
+	htw_start();
 
 	local_irq_restore(flags);
 }
@@ -180,6 +181,7 @@ activate_mm(struct mm_struct *prev, stru
 
 	local_irq_save(flags);
 
+	htw_stop();
 	/* Unconditionally get a new ASID.  */
 	get_new_mmu_context(next, cpu);
 
@@ -189,6 +191,7 @@ activate_mm(struct mm_struct *prev, stru
 	/* mark mmu ownership change */
 	cpumask_clear_cpu(cpu, mm_cpumask(prev));
 	cpumask_set_cpu(cpu, mm_cpumask(next));
+	htw_start();
 
 	local_irq_restore(flags);
 }
@@ -203,6 +206,7 @@ drop_mmu_context(struct mm_struct *mm, u
 	unsigned long flags;
 
 	local_irq_save(flags);
+	htw_stop();
 
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
 		get_new_mmu_context(mm, cpu);
@@ -211,6 +215,7 @@ drop_mmu_context(struct mm_struct *mm, u
 		/* will get a new context next time */
 		cpu_context(cpu, mm) = 0;
 	}
+	htw_start();
 	local_irq_restore(flags);
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/mips/include/asm/pgtable.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/include/asm/pgtable.h
+++ linux-3.18.13-rt10-r7s4/arch/mips/include/asm/pgtable.h
@@ -99,29 +99,35 @@ extern void paging_init(void);
 
 #define htw_stop()							\
 do {									\
-	if (cpu_has_htw)						\
-		write_c0_pwctl(read_c0_pwctl() &			\
-			       ~(1 << MIPS_PWCTL_PWEN_SHIFT));		\
+	unsigned long flags;						\
+									\
+	if (cpu_has_htw) {						\
+		local_irq_save(flags);					\
+		if(!raw_current_cpu_data.htw_seq++) {			\
+			write_c0_pwctl(read_c0_pwctl() &		\
+				       ~(1 << MIPS_PWCTL_PWEN_SHIFT));	\
+			back_to_back_c0_hazard();			\
+		}							\
+		local_irq_restore(flags);				\
+	}								\
 } while(0)
 
 #define htw_start()							\
 do {									\
-	if (cpu_has_htw)						\
-		write_c0_pwctl(read_c0_pwctl() |			\
-			       (1 << MIPS_PWCTL_PWEN_SHIFT));		\
-} while(0)
-
-
-#define htw_reset()							\
-do {									\
+	unsigned long flags;						\
+									\
 	if (cpu_has_htw) {						\
-		htw_stop();						\
-		back_to_back_c0_hazard();				\
-		htw_start();						\
-		back_to_back_c0_hazard();				\
+		local_irq_save(flags);					\
+		if (!--raw_current_cpu_data.htw_seq) {			\
+			write_c0_pwctl(read_c0_pwctl() |		\
+				       (1 << MIPS_PWCTL_PWEN_SHIFT));	\
+			back_to_back_c0_hazard();			\
+		}							\
+		local_irq_restore(flags);				\
 	}								\
 } while(0)
 
+
 extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	pte_t pteval);
 
@@ -153,12 +159,13 @@ static inline void pte_clear(struct mm_s
 {
 	pte_t null = __pte(0);
 
+	htw_stop();
 	/* Preserve global status for the pair */
 	if (ptep_buddy(ptep)->pte_low & _PAGE_GLOBAL)
 		null.pte_low = null.pte_high = _PAGE_GLOBAL;
 
 	set_pte_at(mm, addr, ptep, null);
-	htw_reset();
+	htw_start();
 }
 #else
 
@@ -188,6 +195,7 @@ static inline void set_pte(pte_t *ptep,
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
+	htw_stop();
 #if !defined(CONFIG_CPU_R3000) && !defined(CONFIG_CPU_TX39XX)
 	/* Preserve global status for the pair */
 	if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL)
@@ -195,7 +203,7 @@ static inline void pte_clear(struct mm_s
 	else
 #endif
 		set_pte_at(mm, addr, ptep, __pte(0));
-	htw_reset();
+	htw_start();
 }
 #endif
 
Index: linux-3.18.13-rt10-r7s4/arch/mips/kernel/cps-vec.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kernel/cps-vec.S
+++ linux-3.18.13-rt10-r7s4/arch/mips/kernel/cps-vec.S
@@ -99,11 +99,11 @@ not_nmi:
 	xori	t2, t1, 0x7
 	beqz	t2, 1f
 	 li	t3, 32
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 	sllv	t1, t3, t1
 1:	/* At this point t1 == I-cache sets per way */
 	_EXT	t2, v0, MIPS_CONF1_IA_SHF, MIPS_CONF1_IA_SZ
-	addi	t2, t2, 1
+	addiu	t2, t2, 1
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
@@ -126,11 +126,11 @@ icache_done:
 	xori	t2, t1, 0x7
 	beqz	t2, 1f
 	 li	t3, 32
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 	sllv	t1, t3, t1
 1:	/* At this point t1 == D-cache sets per way */
 	_EXT	t2, v0, MIPS_CONF1_DA_SHF, MIPS_CONF1_DA_SZ
-	addi	t2, t2, 1
+	addiu	t2, t2, 1
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
@@ -250,7 +250,7 @@ LEAF(mips_cps_core_init)
 	mfc0	t0, CP0_MVPCONF0
 	srl	t0, t0, MVPCONF0_PVPE_SHIFT
 	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
-	addi	t7, t0, 1
+	addiu	t7, t0, 1
 
 	/* If there's only 1, we're done */
 	beqz	t0, 2f
@@ -280,7 +280,7 @@ LEAF(mips_cps_core_init)
 	mttc0	t0, CP0_TCHALT
 
 	/* Next VPE */
-	addi	t5, t5, 1
+	addiu	t5, t5, 1
 	slt	t0, t5, t7
 	bnez	t0, 1b
 	 nop
@@ -317,7 +317,7 @@ LEAF(mips_cps_boot_vpes)
 	mfc0	t1, CP0_MVPCONF0
 	srl	t1, t1, MVPCONF0_PVPE_SHIFT
 	andi	t1, t1, MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT
-	addi	t1, t1, 1
+	addiu	t1, t1, 1
 
 	/* Calculate a mask for the VPE ID from EBase.CPUNum */
 	clz	t1, t1
@@ -424,7 +424,7 @@ LEAF(mips_cps_boot_vpes)
 
 	/* Next VPE */
 2:	srl	t6, t6, 1
-	addi	t5, t5, 1
+	addiu	t5, t5, 1
 	bnez	t6, 1b
 	 nop
 
Index: linux-3.18.13-rt10-r7s4/arch/mips/kernel/cpu-probe.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kernel/cpu-probe.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/kernel/cpu-probe.c
@@ -367,8 +367,10 @@ static inline unsigned int decode_config
 	if (config3 & MIPS_CONF3_MSA)
 		c->ases |= MIPS_ASE_MSA;
 	/* Only tested on 32-bit cores */
-	if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT))
+	if ((config3 & MIPS_CONF3_PW) && config_enabled(CONFIG_32BIT)) {
+		c->htw_seq = 0;
 		c->options |= MIPS_CPU_HTW;
+	}
 
 	return config3 & MIPS_CONF_M;
 }
Index: linux-3.18.13-rt10-r7s4/arch/mips/kernel/irq_cpu.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kernel/irq_cpu.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/kernel/irq_cpu.c
@@ -56,6 +56,8 @@ static struct irq_chip mips_cpu_irq_cont
 	.irq_mask_ack	= mask_mips_irq,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 /*
@@ -92,6 +94,8 @@ static struct irq_chip mips_mt_cpu_irq_c
 	.irq_mask_ack	= mips_mt_cpu_irq_ack,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 void __init mips_cpu_irq_init(void)
Index: linux-3.18.13-rt10-r7s4/arch/mips/kernel/mips_ksyms.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kernel/mips_ksyms.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/kernel/mips_ksyms.c
@@ -14,6 +14,8 @@
 #include <linux/mm.h>
 #include <asm/uaccess.h>
 #include <asm/ftrace.h>
+#include <asm/fpu.h>
+#include <asm/msa.h>
 
 extern void *__bzero(void *__s, size_t __count);
 extern long __strncpy_from_kernel_nocheck_asm(char *__to,
@@ -34,6 +36,14 @@ extern long __strnlen_user_nocheck_asm(c
 extern long __strnlen_user_asm(const char *s);
 
 /*
+ * Core architecture code
+ */
+EXPORT_SYMBOL_GPL(_save_fp);
+#ifdef CONFIG_CPU_HAS_MSA
+EXPORT_SYMBOL_GPL(_save_msa);
+#endif
+
+/*
  * String functions
  */
 EXPORT_SYMBOL(memset);
Index: linux-3.18.13-rt10-r7s4/arch/mips/kernel/smp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kernel/smp.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/kernel/smp.c
@@ -123,10 +123,10 @@ asmlinkage void start_secondary(void)
 	unsigned int cpu;
 
 	cpu_probe();
-	cpu_report();
 	per_cpu_trap_init(false);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
+	cpu_report();
 
 	/*
 	 * XXX parity protection should be folded in here when it's converted
Index: linux-3.18.13-rt10-r7s4/arch/mips/kernel/traps.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kernel/traps.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/kernel/traps.c
@@ -1184,7 +1184,8 @@ static int enable_restore_fp_context(int
 
 		/* Restore the scalar FP control & status register */
 		if (!was_fpu_owner)
-			asm volatile("ctc1 %0, $31" : : "r"(current->thread.fpu.fcr31));
+			write_32bit_cp1_register(CP1_STATUS,
+						 current->thread.fpu.fcr31);
 	}
 
 out:
Index: linux-3.18.13-rt10-r7s4/arch/mips/kvm/locore.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kvm/locore.S
+++ linux-3.18.13-rt10-r7s4/arch/mips/kvm/locore.S
@@ -434,7 +434,7 @@ __kvm_mips_return_to_guest:
 	/* Setup status register for running guest in UM */
 	.set	at
 	or	v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
-	and	v1, v1, ~ST0_CU0
+	and	v1, v1, ~(ST0_CU0 | ST0_MX)
 	.set	noat
 	mtc0	v1, CP0_STATUS
 	ehb
Index: linux-3.18.13-rt10-r7s4/arch/mips/kvm/mips.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kvm/mips.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/kvm/mips.c
@@ -15,9 +15,11 @@
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>
+#include <asm/fpu.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/pgtable.h>
 
 #include <linux/kvm_host.h>
 
@@ -378,6 +380,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 		vcpu->mmio_needed = 0;
 	}
 
+	lose_fpu(1);
+
 	local_irq_disable();
 	/* Check if we have any exceptions/interrupts pending */
 	kvm_mips_deliver_interrupts(vcpu,
@@ -385,8 +389,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 
 	kvm_guest_enter();
 
+	/* Disable hardware page table walking while in guest */
+	htw_stop();
+
 	r = __kvm_mips_vcpu_run(run, vcpu);
 
+	/* Re-enable HTW before enabling interrupts */
+	htw_start();
+
 	kvm_guest_exit();
 	local_irq_enable();
 
@@ -980,9 +990,6 @@ static void kvm_mips_set_c0_status(void)
 {
 	uint32_t status = read_c0_status();
 
-	if (cpu_has_fpu)
-		status |= (ST0_CU1);
-
 	if (cpu_has_dsp)
 		status |= (ST0_MX);
 
@@ -1002,6 +1009,9 @@ int kvm_mips_handle_exit(struct kvm_run
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
+	/* re-enable HTW before enabling interrupts */
+	htw_start();
+
 	/* Set a default exit reason */
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
@@ -1136,6 +1146,9 @@ skip_emul:
 		}
 	}
 
+	/* Disable HTW before returning to guest or host */
+	htw_stop();
+
 	return ret;
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/mips/kvm/trace.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/kvm/trace.h
+++ linux-3.18.13-rt10-r7s4/arch/mips/kvm/trace.h
@@ -24,18 +24,18 @@ TRACE_EVENT(kvm_exit,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason),
 	    TP_ARGS(vcpu, reason),
 	    TP_STRUCT__entry(
-			__field(struct kvm_vcpu *, vcpu)
+			__field(unsigned long, pc)
 			__field(unsigned int, reason)
 	    ),
 
 	    TP_fast_assign(
-			__entry->vcpu = vcpu;
+			__entry->pc = vcpu->arch.pc;
 			__entry->reason = reason;
 	    ),
 
 	    TP_printk("[%s]PC: 0x%08lx",
 		      kvm_mips_exit_types_str[__entry->reason],
-		      __entry->vcpu->arch.pc)
+		      __entry->pc)
 );
 
 #endif /* _TRACE_KVM_H */
Index: linux-3.18.13-rt10-r7s4/arch/mips/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/mm/fault.c
@@ -158,6 +158,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/mips/mm/tlb-r4k.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/mm/tlb-r4k.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/mm/tlb-r4k.c
@@ -489,6 +489,8 @@ static void r4k_tlb_configure(void)
 #ifdef CONFIG_64BIT
 		pg |= PG_ELPA;
 #endif
+		if (cpu_has_rixiex)
+			pg |= PG_IEC;
 		write_c0_pagegrain(pg);
 	}
 
Index: linux-3.18.13-rt10-r7s4/arch/mips/net/bpf_jit.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mips/net/bpf_jit.c
+++ linux-3.18.13-rt10-r7s4/arch/mips/net/bpf_jit.c
@@ -426,7 +426,7 @@ static inline void emit_mod(unsigned int
 		u32 *p = &ctx->target[ctx->idx];
 		uasm_i_divu(&p, dst, src);
 		p = &ctx->target[ctx->idx + 1];
-		uasm_i_mflo(&p, dst);
+		uasm_i_mfhi(&p, dst);
 	}
 	ctx->idx += 2; /* 2 insts */
 }
@@ -971,7 +971,7 @@ load_ind:
 			break;
 		case BPF_ALU | BPF_MOD | BPF_K:
 			/* A %= k */
-			if (k == 1 || optimize_div(&k)) {
+			if (k == 1) {
 				ctx->flags |= SEEN_A;
 				emit_jit_reg_move(r_A, r_zero, ctx);
 			} else {
Index: linux-3.18.13-rt10-r7s4/arch/mn10300/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/mn10300/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/mn10300/mm/fault.c
@@ -262,6 +262,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/openrisc/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/openrisc/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/openrisc/mm/fault.c
@@ -171,6 +171,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/parisc/include/asm/ldcw.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/parisc/include/asm/ldcw.h
+++ linux-3.18.13-rt10-r7s4/arch/parisc/include/asm/ldcw.h
@@ -33,11 +33,18 @@
 
 #endif /*!CONFIG_PA20*/
 
-/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.  */
+/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.
+   We don't explicitly expose that "*a" may be written as reload
+   fails to find a register in class R1_REGS when "a" needs to be
+   reloaded when generating 64-bit PIC code.  Instead, we clobber
+   memory to indicate to the compiler that the assembly code reads
+   or writes to items other than those listed in the input and output
+   operands.  This may pessimize the code somewhat but __ldcw is
+   usually used within code blocks surrounded by memory barriors.  */
 #define __ldcw(a) ({						\
 	unsigned __ret;						\
-	__asm__ __volatile__(__LDCW " 0(%2),%0"			\
-		: "=r" (__ret), "+m" (*(a)) : "r" (a));		\
+	__asm__ __volatile__(__LDCW " 0(%1),%0"			\
+		: "=r" (__ret) : "r" (a) : "memory");		\
 	__ret;							\
 })
 
Index: linux-3.18.13-rt10-r7s4/arch/parisc/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/parisc/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/parisc/mm/fault.c
@@ -256,6 +256,8 @@ good_area:
 		 */
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bad_area;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
@@ -50,6 +50,7 @@ ethernet@b0000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b0000 {
 		#address-cells = <1>;
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
@@ -50,6 +50,7 @@ ethernet@b1000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b1000 {
 		#address-cells = <1>;
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
@@ -49,6 +49,7 @@ ethernet@b2000 {
 	fsl,num_tx_queues = <0x8>;
 	fsl,magic-packet;
 	local-mac-address = [ 00 00 00 00 00 00 ];
+	ranges;
 
 	queue-group@b2000 {
 		#address-cells = <1>;
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/crypto/sha1.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/crypto/sha1.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/crypto/sha1.c
@@ -154,4 +154,5 @@ module_exit(sha1_powerpc_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha1-powerpc");
+MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-powerpc");
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/cputhreads.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/include/asm/cputhreads.h
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/cputhreads.h
@@ -55,7 +55,7 @@ static inline cpumask_t cpu_thread_mask_
 
 static inline int cpu_nr_cores(void)
 {
-	return NR_CPUS >> threads_shift;
+	return nr_cpu_ids >> threads_shift;
 }
 
 static inline cpumask_t cpu_online_cores_map(void)
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/irq_work.h
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/irq_work.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_POWERPC_IRQ_WORK_H
+#define _ASM_POWERPC_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return true;
+}
+
+#endif /* _ASM_POWERPC_IRQ_WORK_H */
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/pgalloc.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/include/asm/pgalloc.h
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/pgalloc.h
@@ -3,7 +3,6 @@
 #ifdef __KERNEL__
 
 #include <linux/mm.h>
-#include <asm-generic/tlb.h>
 
 #ifdef CONFIG_PPC_BOOK3E
 extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
@@ -14,6 +13,8 @@ static inline void tlb_flush_pgtable(str
 }
 #endif /* !CONFIG_PPC_BOOK3E */
 
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/pnv-pci.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/include/asm/pnv-pci.h
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/pnv-pci.h
@@ -19,7 +19,7 @@ int pnv_cxl_ioda_msi_setup(struct pci_de
 int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
 void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
 int pnv_cxl_get_irq_count(struct pci_dev *dev);
-struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev);
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev);
 
 #ifdef CONFIG_CXL_BASE
 int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/reg.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/include/asm/reg.h
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/reg.h
@@ -118,8 +118,10 @@
 #define __MSR		(MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
 #ifdef __BIG_ENDIAN__
 #define MSR_		__MSR
+#define MSR_IDLE	(MSR_ME | MSR_SF | MSR_HV)
 #else
 #define MSR_		(__MSR | MSR_LE)
+#define MSR_IDLE	(MSR_ME | MSR_SF | MSR_HV | MSR_LE)
 #endif
 #define MSR_KERNEL	(MSR_ | MSR_64BIT)
 #define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/syscall.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/include/asm/syscall.h
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/syscall.h
@@ -90,6 +90,10 @@ static inline void syscall_set_arguments
 
 static inline int syscall_get_arch(void)
 {
-	return is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+	int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+#ifdef __LITTLE_ENDIAN__
+	arch |= __AUDIT_ARCH_LE;
+#endif
+	return arch;
 }
 #endif	/* _ASM_SYSCALL_H */
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/tlb.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/include/asm/tlb.h
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/include/asm/tlb.h
@@ -27,6 +27,7 @@
 
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
+#define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
 
 extern void tlb_flush(struct mmu_gather *tlb);
 
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/exceptions-64s.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/kernel/exceptions-64s.S
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/exceptions-64s.S
@@ -1399,7 +1399,7 @@ machine_check_handle_early:
 	bne	9f			/* continue in V mode if we are. */
 
 5:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
 	 * We are coming from kernel context. Check if we are coming from
 	 * guest. if yes, then we can continue. We will fall through
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/idle_power7.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/kernel/idle_power7.S
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/idle_power7.S
@@ -101,7 +101,23 @@ _GLOBAL(power7_powersave_common)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-_GLOBAL(power7_enter_nap_mode)
+	/*
+	 * Go to real mode to do the nap, as required by the architecture.
+	 * Also, we need to be in real mode before setting hwthread_state,
+	 * because as soon as we do that, another thread can switch
+	 * the MMU context to the guest.
+	 */
+	LOAD_REG_IMMEDIATE(r5, MSR_IDLE)
+	li	r6, MSR_RI
+	andc	r6, r9, r6
+	LOAD_REG_ADDR(r7, power7_enter_nap_mode)
+	mtmsrd	r6, 1		/* clear RI before setting SRR0/1 */
+	mtspr	SPRN_SRR0, r7
+	mtspr	SPRN_SRR1, r5
+	rfid
+
+	.globl	power7_enter_nap_mode
+power7_enter_nap_mode:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	/* Tell KVM we're napping */
 	li	r4,KVM_HWTHREAD_IN_NAP
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/mce_power.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/kernel/mce_power.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/mce_power.c
@@ -79,7 +79,7 @@ static long mce_handle_derror(uint64_t d
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -110,7 +110,7 @@ static long mce_handle_common_ierror(uin
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 			handled = 1;
 		}
 		break;
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/udbg_16550.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/kernel/udbg_16550.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/kernel/udbg_16550.c
@@ -69,8 +69,12 @@ static void udbg_uart_putc(char c)
 
 static int udbg_uart_getc_poll(void)
 {
-	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+	if (!udbg_uart_in)
+		return -1;
+
+	if (!(udbg_uart_in(UART_LSR) & LSR_DR))
 		return udbg_uart_in(UART_RBR);
+
 	return -1;
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/mm/copro_fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/mm/copro_fault.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/mm/copro_fault.c
@@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_stru
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
 			goto out_unlock;
-		} else if (*flt & VM_FAULT_SIGBUS) {
+		} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 			ret = -EFAULT;
 			goto out_unlock;
 		}
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/mm/fault.c
@@ -444,6 +444,8 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
 			goto bail;
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/mm/hugetlbpage.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/mm/hugetlbpage.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/mm/hugetlbpage.c
@@ -517,8 +517,6 @@ static void free_hugepd_range(struct mmu
 	for (i = 0; i < num_hugepd; i++, hpdp++)
 		hpdp->pd = 0;
 
-	tlb->need_flush = 1;
-
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	hugepd_free(tlb, hugepte);
 #else
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/perf/hv-24x7.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/perf/hv-24x7.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/perf/hv-24x7.c
@@ -217,11 +217,14 @@ static bool is_physical_domain(int domai
 		domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE;
 }
 
+DEFINE_PER_CPU(char, hv_24x7_reqb[4096]) __aligned(4096);
+DEFINE_PER_CPU(char, hv_24x7_resb[4096]) __aligned(4096);
+
 static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 					 u16 lpar, u64 *res,
 					 bool success_expected)
 {
-	unsigned long ret = -ENOMEM;
+	unsigned long ret;
 
 	/*
 	 * request_buffer and result_buffer are not required to be 4k aligned,
@@ -243,13 +246,11 @@ static unsigned long single_24x7_request
 	BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
 	BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
 
-	request_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
-	if (!request_buffer)
-		goto out;
+	request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+	result_buffer = (void *)get_cpu_var(hv_24x7_resb);
 
-	result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
-	if (!result_buffer)
-		goto out_free_request_buffer;
+	memset(request_buffer, 0, 4096);
+	memset(result_buffer, 0, 4096);
 
 	*request_buffer = (struct reqb) {
 		.buf = {
@@ -278,15 +279,11 @@ static unsigned long single_24x7_request
 				domain, offset, ix, lpar, ret, ret,
 				result_buffer->buf.detailed_rc,
 				result_buffer->buf.failing_request_ix);
-		goto out_free_result_buffer;
+		goto out;
 	}
 
 	*res = be64_to_cpu(result_buffer->result);
 
-out_free_result_buffer:
-	kfree(result_buffer);
-out_free_request_buffer:
-	kfree(request_buffer);
 out:
 	return ret;
 }
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/cell/spufs/inode.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/platforms/cell/spufs/inode.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/cell/spufs/inode.c
@@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentr
 	struct dentry *dentry, *tmp;
 
 	mutex_lock(&dir->d_inode->i_mutex);
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) {
+	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		spin_lock(&dentry->d_lock);
 		if (!(d_unhashed(dentry)) && dentry->d_inode) {
 			dget_dlock(dentry);
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/powernv/opal-wrappers.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -40,7 +40,6 @@ BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
 	ld	r12,opal_tracepoint_refcount@toc(r2);		\
-	std	r12,32(r1);					\
 	cmpdi	r12,0;						\
 	bne-	LABEL;						\
 1:
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/powernv/pci-ioda.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/platforms/powernv/pci-ioda.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1355,13 +1355,13 @@ static void set_msi_irq_chip(struct pnv_
 
 #ifdef CONFIG_CXL_BASE
 
-struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 
-	return hose->dn;
+	return of_node_get(hose->dn);
 }
-EXPORT_SYMBOL(pnv_pci_to_phb_node);
+EXPORT_SYMBOL(pnv_pci_get_phb_node);
 
 int pnv_phb_to_cxl(struct pci_dev *dev)
 {
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/pseries/mobility.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/platforms/pseries/mobility.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/platforms/pseries/mobility.c
@@ -25,10 +25,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-	u32 phandle;
-	u32 state;
-	u64 reserved;
-	u32 nprops;
+	__be32 phandle;
+	__be32 state;
+	__be64 reserved;
+	__be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK	0xff000000
@@ -54,11 +54,11 @@ static int mobility_rtas_call(int token,
 	return rc;
 }
 
-static int delete_dt_node(u32 phandle)
+static int delete_dt_node(__be32 phandle)
 {
 	struct device_node *dn;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn)
 		return -ENOENT;
 
@@ -127,7 +127,7 @@ static int update_dt_property(struct dev
 	return 0;
 }
 
-static int update_dt_node(u32 phandle, s32 scope)
+static int update_dt_node(__be32 phandle, s32 scope)
 {
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
@@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
+	u32 nprops;
 	u32 vd;
 
 	update_properties_token = rtas_token("ibm,update-properties");
@@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s
 	if (!rtas_buf)
 		return -ENOMEM;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn) {
 		kfree(rtas_buf);
 		return -ENOENT;
@@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
+		nprops = be32_to_cpu(upwa->nprops);
 
 		/* On the first call to ibm,update-properties for a node the
 		 * the first property value descriptor contains an empty
@@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s
 		 */
 		if (*prop_data == 0) {
 			prop_data++;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += vd + sizeof(vd);
-			upwa->nprops--;
+			nprops--;
 		}
 
-		for (i = 0; i < upwa->nprops; i++) {
+		for (i = 0; i < nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
 			prop_data += strlen(prop_name) + 1;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += sizeof(vd);
 
 			switch (vd) {
@@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s
 	return 0;
 }
 
-static int add_dt_node(u32 parent_phandle, u32 drc_index)
+static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
 {
 	struct device_node *dn;
 	struct device_node *parent_dn;
 	int rc;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
+	parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle));
 	if (!parent_dn)
 		return -ENOENT;
 
@@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandl
 int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
-	u32 *data;
+	__be32 *data;
 	int update_nodes_token;
 	int rc;
 
@@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope)
 		if (rc && rc != 1)
 			break;
 
-		data = (u32 *)rtas_buf + 4;
-		while (*data & NODE_ACTION_MASK) {
+		data = (__be32 *)rtas_buf + 4;
+		while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
 			int i;
-			u32 action = *data & NODE_ACTION_MASK;
-			int node_count = *data & NODE_COUNT_MASK;
+			u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
+			u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
 			data++;
 
 			for (i = 0; i < node_count; i++) {
-				u32 phandle = *data++;
-				u32 drc_index;
+				__be32 phandle = *data++;
+				__be32 drc_index;
 
 				switch (action) {
 				case DELETE_DT_NODE:
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/sysdev/axonram.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/sysdev/axonram.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/sysdev/axonram.c
@@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_devi
 	}
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
 	return 0;
 }
Index: linux-3.18.13-rt10-r7s4/arch/powerpc/xmon/xmon.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/powerpc/xmon/xmon.c
+++ linux-3.18.13-rt10-r7s4/arch/powerpc/xmon/xmon.c
@@ -293,6 +293,7 @@ static inline void disable_surveillance(
 	args.token = rtas_token("set-indicator");
 	if (args.token == RTAS_UNKNOWN_SERVICE)
 		return;
+	args.token = cpu_to_be32(args.token);
 	args.nargs = cpu_to_be32(3);
 	args.nret = cpu_to_be32(1);
 	args.rets = &args.args[3];
Index: linux-3.18.13-rt10-r7s4/arch/s390/crypto/aes_s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/crypto/aes_s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/crypto/aes_s390.c
@@ -979,7 +979,7 @@ static void __exit aes_s390_fini(void)
 module_init(aes_s390_init);
 module_exit(aes_s390_fini);
 
-MODULE_ALIAS("aes-all");
+MODULE_ALIAS_CRYPTO("aes-all");
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("GPL");
Index: linux-3.18.13-rt10-r7s4/arch/s390/crypto/des_s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/crypto/des_s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/crypto/des_s390.c
@@ -619,8 +619,8 @@ static void __exit des_s390_exit(void)
 module_init(des_s390_init);
 module_exit(des_s390_exit);
 
-MODULE_ALIAS("des");
-MODULE_ALIAS("des3_ede");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des3_ede");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
Index: linux-3.18.13-rt10-r7s4/arch/s390/crypto/ghash_s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/crypto/ghash_s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/crypto/ghash_s390.c
@@ -160,7 +160,7 @@ static void __exit ghash_mod_exit(void)
 module_init(ghash_mod_init);
 module_exit(ghash_mod_exit);
 
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation");
Index: linux-3.18.13-rt10-r7s4/arch/s390/crypto/sha1_s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/crypto/sha1_s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/crypto/sha1_s390.c
@@ -103,6 +103,6 @@ static void __exit sha1_s390_fini(void)
 module_init(sha1_s390_init);
 module_exit(sha1_s390_fini);
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
Index: linux-3.18.13-rt10-r7s4/arch/s390/crypto/sha256_s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/crypto/sha256_s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/crypto/sha256_s390.c
@@ -143,7 +143,7 @@ static void __exit sha256_s390_fini(void
 module_init(sha256_s390_init);
 module_exit(sha256_s390_fini);
 
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm");
Index: linux-3.18.13-rt10-r7s4/arch/s390/crypto/sha512_s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/crypto/sha512_s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/crypto/sha512_s390.c
@@ -86,7 +86,7 @@ static struct shash_alg sha512_alg = {
 	}
 };
 
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha512");
 
 static int sha384_init(struct shash_desc *desc)
 {
@@ -126,7 +126,7 @@ static struct shash_alg sha384_alg = {
 	}
 };
 
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha384");
 
 static int __init init(void)
 {
Index: linux-3.18.13-rt10-r7s4/arch/s390/kernel/compat_linux.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/kernel/compat_linux.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/kernel/compat_linux.c
@@ -249,7 +249,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16,
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
Index: linux-3.18.13-rt10-r7s4/arch/s390/kvm/gaccess.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/kvm/gaccess.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/kvm/gaccess.c
@@ -229,10 +229,12 @@ static void ipte_lock_simple(struct kvm_
 		goto out;
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
 		while (old.k) {
 			cond_resched();
-			old = ACCESS_ONCE(*ic);
+			old = *ic;
+			barrier();
 		}
 		new = old;
 		new.k = 1;
@@ -251,7 +253,9 @@ static void ipte_unlock_simple(struct kv
 		goto out;
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		new = old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
+		new = old;
 		new.k = 0;
 	} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
 	wake_up(&vcpu->kvm->arch.ipte_wq);
@@ -265,10 +269,12 @@ static void ipte_lock_siif(struct kvm_vc
 
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
 		while (old.kg) {
 			cond_resched();
-			old = ACCESS_ONCE(*ic);
+			old = *ic;
+			barrier();
 		}
 		new = old;
 		new.k = 1;
@@ -282,7 +288,9 @@ static void ipte_unlock_siif(struct kvm_
 
 	ic = &vcpu->kvm->arch.sca->ipte_control;
 	do {
-		new = old = ACCESS_ONCE(*ic);
+		old = *ic;
+		barrier();
+		new = old;
 		new.kh--;
 		if (!new.kh)
 			new.k = 0;
Index: linux-3.18.13-rt10-r7s4/arch/s390/kvm/interrupt.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/kvm/interrupt.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/kvm/interrupt.c
@@ -270,7 +270,7 @@ static int __must_check __deliver_prog_i
 		break;
 	case PGM_MONITOR:
 		rc = put_guest_lc(vcpu, pgm_info->mon_class_nr,
-				  (u64 *)__LC_MON_CLASS_NR);
+				  (u16 *)__LC_MON_CLASS_NR);
 		rc |= put_guest_lc(vcpu, pgm_info->mon_code,
 				   (u64 *)__LC_MON_CODE);
 		break;
@@ -613,7 +613,7 @@ no_timer:
 	__unset_cpu_idle(vcpu);
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
-	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
+	hrtimer_cancel(&vcpu->arch.ckc_timer);
 	return 0;
 }
 
@@ -633,10 +633,20 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcp
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
+	u64 now, sltime;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
-	kvm_s390_vcpu_wakeup(vcpu);
+	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
+	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
+	/*
+	 * If the monotonic clock runs faster than the tod clock we might be
+	 * woken up too early and have to go back to sleep to avoid deadlocks.
+	 */
+	if (vcpu->arch.sie_block->ckc > now &&
+	    hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+		return HRTIMER_RESTART;
+	kvm_s390_vcpu_wakeup(vcpu);
 	return HRTIMER_NORESTART;
 }
 
@@ -840,6 +850,8 @@ static int __inject_vm(struct kvm *kvm,
 		list_add_tail(&inti->list, &iter->list);
 	}
 	atomic_set(&fi->active, 1);
+	if (atomic_read(&kvm->online_vcpus) == 0)
+		goto unlock_fi;
 	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
 	if (sigcpu == KVM_MAX_VCPUS) {
 		do {
@@ -864,6 +876,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		       struct kvm_s390_interrupt *s390int)
 {
 	struct kvm_s390_interrupt_info *inti;
+	int rc;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)
@@ -911,7 +924,10 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
 				 2);
 
-	return __inject_vm(kvm, inti);
+	rc = __inject_vm(kvm, inti);
+	if (rc)
+		kfree(inti);
+	return rc;
 }
 
 void kvm_s390_reinject_io_int(struct kvm *kvm,
Index: linux-3.18.13-rt10-r7s4/arch/s390/kvm/kvm-s390.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/kvm/kvm-s390.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/kvm/kvm-s390.c
@@ -152,7 +152,6 @@ int kvm_vm_ioctl_check_extension(struct
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
@@ -662,7 +661,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu
 		if (rc)
 			return rc;
 	}
-	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 	get_cpu_id(&vcpu->arch.cpu_id);
 	vcpu->arch.cpu_id.version = 0xff;
Index: linux-3.18.13-rt10-r7s4/arch/s390/kvm/priv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/kvm/priv.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/kvm/priv.c
@@ -791,7 +791,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu
 			break;
 		reg = (reg + 1) % 16;
 	} while (1);
-
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	return 0;
 }
 
@@ -863,7 +863,7 @@ static int handle_lctlg(struct kvm_vcpu
 			break;
 		reg = (reg + 1) % 16;
 	} while (1);
-
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/s390/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/s390/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/s390/mm/fault.c
@@ -374,6 +374,12 @@ static noinline void do_fault_error(stru
 				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			/* Kernel mode? Handle exceptions or die */
+			if (!user_mode(regs))
+				do_no_context(regs);
+			else
+				do_sigsegv(regs, SEGV_MAPERR);
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!user_mode(regs))
Index: linux-3.18.13-rt10-r7s4/arch/score/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/score/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/score/mm/fault.c
@@ -114,6 +114,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/sh/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sh/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/sh/mm/fault.c
@@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, uns
 	} else {
 		if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(regs, error_code, address);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area(regs, error_code, address);
 		else
 			BUG();
 	}
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/aes_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/aes_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/aes_glue.c
@@ -499,6 +499,6 @@ module_exit(aes_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/camellia_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/camellia_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/camellia_glue.c
@@ -322,6 +322,6 @@ module_exit(camellia_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/crc32c_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/crc32c_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/crc32c_glue.c
@@ -176,6 +176,6 @@ module_exit(crc32c_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated");
 
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/des_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/des_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/des_glue.c
@@ -532,6 +532,6 @@ module_exit(des_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated");
 
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/md5_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/md5_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/md5_glue.c
@@ -185,6 +185,6 @@ module_exit(md5_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated");
 
-MODULE_ALIAS("md5");
+MODULE_ALIAS_CRYPTO("md5");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/sha1_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/sha1_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/sha1_glue.c
@@ -180,6 +180,6 @@ module_exit(sha1_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/sha256_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/sha256_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/sha256_glue.c
@@ -237,7 +237,7 @@ module_exit(sha256_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated");
 
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/crypto/sha512_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/crypto/sha512_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/crypto/sha512_glue.c
@@ -222,7 +222,7 @@ module_exit(sha512_sparc64_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 opcode accelerated");
 
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
 
 #include "crop_devid.c"
Index: linux-3.18.13-rt10-r7s4/arch/sparc/kernel/perf_event.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/kernel/perf_event.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/kernel/perf_event.c
@@ -960,6 +960,8 @@ out:
 	cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags);
+
 /* On this PMU each PIC has it's own PCR control register.  */
 static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 {
@@ -972,20 +974,13 @@ static void calculate_multiple_pcrs(stru
 		struct perf_event *cp = cpuc->event[i];
 		struct hw_perf_event *hwc = &cp->hw;
 		int idx = hwc->idx;
-		u64 enc;
 
 		if (cpuc->current_idx[i] != PIC_NO_INDEX)
 			continue;
 
-		sparc_perf_event_set_period(cp, hwc, idx);
 		cpuc->current_idx[i] = idx;
 
-		enc = perf_event_get_enc(cpuc->events[i]);
-		cpuc->pcr[idx] &= ~mask_for_index(idx);
-		if (hwc->state & PERF_HES_STOPPED)
-			cpuc->pcr[idx] |= nop_for_index(idx);
-		else
-			cpuc->pcr[idx] |= event_encoding(enc, idx);
+		sparc_pmu_start(cp, PERF_EF_RELOAD);
 	}
 out:
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1096,6 @@ static void sparc_pmu_del(struct perf_ev
 	int i;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event[i]) {
@@ -1127,7 +1121,6 @@ static void sparc_pmu_del(struct perf_ev
 		}
 	}
 
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -1361,7 +1354,6 @@ static int sparc_pmu_add(struct perf_eve
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
 	if (n0 >= sparc_pmu->max_hw_events)
@@ -1394,7 +1386,6 @@ nocheck:
 
 	ret = 0;
 out:
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
Index: linux-3.18.13-rt10-r7s4/arch/sparc/kernel/process_64.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/kernel/process_64.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/kernel/process_64.c
@@ -287,6 +287,8 @@ void arch_trigger_all_cpu_backtrace(bool
 			printk("             TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
 			       gp->tpc, gp->o7, gp->i7, gp->rpc);
 		}
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
@@ -362,6 +364,8 @@ static void pmu_snapshot_all_cpus(void)
 		       (cpu == this_cpu ? '*' : ' '), cpu,
 		       pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
 		       pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
Index: linux-3.18.13-rt10-r7s4/arch/sparc/kernel/sys_sparc_64.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/kernel/sys_sparc_64.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/kernel/sys_sparc_64.c
@@ -333,7 +333,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int,
 	long err;
 
 	/* No need for backward compatibility. We can start fresh... */
-	if (call <= SEMCTL) {
+	if (call <= SEMTIMEDOP) {
 		switch (call) {
 		case SEMOP:
 			err = sys_semtimedop(first, ptr,
Index: linux-3.18.13-rt10-r7s4/arch/sparc/lib/memmove.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/lib/memmove.S
+++ linux-3.18.13-rt10-r7s4/arch/sparc/lib/memmove.S
@@ -8,9 +8,11 @@
 
 	.text
 ENTRY(memmove) /* o0=dst o1=src o2=len */
-	mov		%o0, %g1
+	brz,pn		%o2, 99f
+	 mov		%o0, %g1
+
 	cmp		%o0, %o1
-	bleu,pt		%xcc, memcpy
+	bleu,pt		%xcc, 2f
 	 add		%o1, %o2, %g7
 	cmp		%g7, %o0
 	bleu,pt		%xcc, memcpy
@@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len *
 	stb		%g7, [%o0]
 	bne,pt		%icc, 1b
 	 sub		%o0, 1, %o0
-
+99:
 	retl
 	 mov		%g1, %o0
+
+	/* We can't just call memcpy for these memmove cases.  On some
+	 * chips the memcpy uses cache initializing stores and when dst
+	 * and src are close enough, those can clobber the source data
+	 * before we've loaded it in.
+	 */
+2:	or		%o0, %o1, %g7
+	or		%o2, %g7, %g7
+	andcc		%g7, 0x7, %g0
+	bne,pn		%xcc, 4f
+	 nop
+
+3:	ldx		[%o1], %g7
+	add		%o1, 8, %o1
+	subcc		%o2, 8, %o2
+	add		%o0, 8, %o0
+	bne,pt		%icc, 3b
+	 stx		%g7, [%o0 - 0x8]
+	ba,a,pt		%xcc, 99b
+
+4:	ldub		[%o1], %g7
+	add		%o1, 1, %o1
+	subcc		%o2, 1, %o2
+	add		%o0, 1, %o0
+	bne,pt		%icc, 4b
+	 stb		%g7, [%o0 - 0x1]
+	ba,a,pt		%xcc, 99b
 ENDPROC(memmove)
Index: linux-3.18.13-rt10-r7s4/arch/sparc/mm/fault_32.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/mm/fault_32.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/mm/fault_32.c
@@ -249,6 +249,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/sparc/mm/fault_64.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/mm/fault_64.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/mm/fault_64.c
@@ -446,6 +446,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/sparc/mm/srmmu.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/sparc/mm/srmmu.c
+++ linux-3.18.13-rt10-r7s4/arch/sparc/mm/srmmu.c
@@ -460,10 +460,12 @@ static void __init sparc_context_init(in
 void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
 	       struct task_struct *tsk)
 {
+	unsigned long flags;
+
 	if (mm->context == NO_CONTEXT) {
-		spin_lock(&srmmu_context_spinlock);
+		spin_lock_irqsave(&srmmu_context_spinlock, flags);
 		alloc_context(old_mm, mm);
-		spin_unlock(&srmmu_context_spinlock);
+		spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
 		srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd);
 	}
 
@@ -986,14 +988,15 @@ int init_new_context(struct task_struct
 
 void destroy_context(struct mm_struct *mm)
 {
+	unsigned long flags;
 
 	if (mm->context != NO_CONTEXT) {
 		flush_cache_mm(mm);
 		srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir);
 		flush_tlb_mm(mm);
-		spin_lock(&srmmu_context_spinlock);
+		spin_lock_irqsave(&srmmu_context_spinlock, flags);
 		free_context(mm->context);
-		spin_unlock(&srmmu_context_spinlock);
+		spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
 		mm->context = NO_CONTEXT;
 	}
 }
Index: linux-3.18.13-rt10-r7s4/arch/tile/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/tile/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/tile/mm/fault.c
@@ -444,6 +444,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/arch/um/Kconfig.common
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/um/Kconfig.common
+++ linux-3.18.13-rt10-r7s4/arch/um/Kconfig.common
@@ -3,6 +3,7 @@ config UML
 	default y
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_UID16
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_IO
Index: linux-3.18.13-rt10-r7s4/arch/um/kernel/trap.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/um/kernel/trap.c
+++ linux-3.18.13-rt10-r7s4/arch/um/kernel/trap.c
@@ -80,6 +80,8 @@ good_area:
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
+			} else if (fault & VM_FAULT_SIGSEGV) {
+				goto out;
 			} else if (fault & VM_FAULT_SIGBUS) {
 				err = -EACCES;
 				goto out;
Index: linux-3.18.13-rt10-r7s4/arch/x86/Kconfig
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/Kconfig
+++ linux-3.18.13-rt10-r7s4/arch/x86/Kconfig
@@ -856,7 +856,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -867,6 +867,10 @@ config X86_UP_APIC
 	  performance counters), and the NMI watchdog which detects hard
 	  lockups.
 
+config X86_UP_APIC_MSI
+	def_bool y
+	select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI
+
 config X86_UP_IOAPIC
 	bool "IO-APIC support on uniprocessors"
 	depends on X86_UP_APIC
Index: linux-3.18.13-rt10-r7s4/arch/x86/boot/Makefile
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/boot/Makefile
+++ linux-3.18.13-rt10-r7s4/arch/x86/boot/Makefile
@@ -51,6 +51,7 @@ targets += cpustr.h
 $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 	$(call if_changed,cpustr)
 endif
+clean-files += cpustr.h
 
 # ---------------------------------------------------------------------------
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/Makefile
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/boot/compressed/Makefile
+++ linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/Makefile
@@ -36,6 +36,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) +=
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
 vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
 	$(call if_changed,ld)
@@ -77,7 +78,7 @@ suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
 RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
-	     perl $(srctree)/arch/x86/tools/calc_run_size.pl)
+	     $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
 quiet_cmd_mkpiggy = MKPIGGY $@
       cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/efi_stub_64.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/boot/compressed/efi_stub_64.S
+++ linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/efi_stub_64.S
@@ -3,28 +3,3 @@
 #include <asm/processor-flags.h>
 
 #include "../../platform/efi/efi_stub_64.S"
-
-#ifdef CONFIG_EFI_MIXED
-	.code64
-	.text
-ENTRY(efi64_thunk)
-	push	%rbp
-	push	%rbx
-
-	subq	$16, %rsp
-	leaq	efi_exit32(%rip), %rax
-	movl	%eax, 8(%rsp)
-	leaq	efi_gdt64(%rip), %rax
-	movl	%eax, 4(%rsp)
-	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
-	leaq	efi32_boot_gdt(%rip), %rax
-	movl	%eax, (%rsp)
-
-	call	__efi64_thunk
-
-	addq	$16, %rsp
-	pop	%rbx
-	pop	%rbp
-	ret
-ENDPROC(efi64_thunk)
-#endif /* CONFIG_EFI_MIXED */
Index: linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/efi_thunk_64.S
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/efi_thunk_64.S
@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT before we make EFI serivce calls,
+ * since the firmware's 32-bit IDT is still currently installed and it
+ * needs to be able to service interrupts.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identify
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+	.code64
+	.text
+ENTRY(efi64_thunk)
+	push	%rbp
+	push	%rbx
+
+	subq	$8, %rsp
+	leaq	efi_exit32(%rip), %rax
+	movl	%eax, 4(%rsp)
+	leaq	efi_gdt64(%rip), %rax
+	movl	%eax, (%rsp)
+	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
+
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	/*
+	 * Convert x86-64 ABI params to i386 ABI
+	 */
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	sgdt	save_gdt(%rip)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/*
+	 * Switch to gdt with 32-bit segments. This is the firmware GDT
+	 * that was installed when the kernel started executing. This
+	 * pointer was saved at the EFI stub entry point in head_64.S.
+	 */
+	leaq	efi32_boot_gdt(%rip), %rax
+	lgdt	(%rax)
+
+	pushq	$__KERNEL_CS
+	leaq	efi_enter32(%rip), %rax
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	lgdt	save_gdt(%rip)
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
+
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	addq	$8, %rsp
+	pop	%rbx
+	pop	%rbp
+	ret
+ENDPROC(efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	/* Reload pgtables */
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Disable long mode via EFER */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btrl	$_EFER_LME, %eax
+	wrmsr
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	/*
+	 * Some firmware will return with interrupts enabled. Be sure to
+	 * disable them before we switch GDTs.
+	 */
+	cli
+
+	movl	56(%esp), %eax
+	movl	%eax, 2(%eax)
+	lgdtl	(%eax)
+
+	movl	%cr4, %eax
+	btsl	$(X86_CR4_PAE_BIT), %eax
+	movl	%eax, %cr4
+
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	xorl	%eax, %eax
+	lldt	%ax
+
+	movl	60(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	/* Enable paging */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+	.global	efi32_boot_gdt
+efi32_boot_gdt:	.word	0
+		.quad	0
+
+save_gdt:	.word	0
+		.quad	0
+func_rt_ptr:	.quad	0
+
+	.global efi_gdt64
+efi_gdt64:
+	.word	efi_gdt64_end - efi_gdt64
+	.long	0			/* Filled out by user */
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+	.quad	0x0080890000000000	/* TS descriptor */
+	.quad   0x0000000000000000	/* TS continued */
+efi_gdt64_end:
Index: linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/misc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/boot/compressed/misc.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/boot/compressed/misc.c
@@ -361,6 +361,8 @@ asmlinkage __visible void *decompress_ke
 				  unsigned long output_len,
 				  unsigned long run_size)
 {
+	unsigned char *output_orig = output;
+
 	real_mode = rmode;
 
 	sanitize_boot_params(real_mode);
@@ -409,7 +411,12 @@ asmlinkage __visible void *decompress_ke
 	debug_putstr("\nDecompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
-	handle_relocations(output, output_len);
+	/*
+	 * 32-bit always performs relocations. 64-bit relocations are only
+	 * needed if kASLR has chosen a different load address.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig)
+		handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
 	return output;
 }
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/Makefile
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/Makefile
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/Makefile
@@ -26,7 +26,6 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL
 
 obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
-obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
@@ -46,6 +45,7 @@ endif
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -208,7 +208,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	3*16(p_keys), xkeyA
+			vmovdqa	3*16(p_keys), xkey4
 		.endif
 	.else
 		vmovdqa	3*16(p_keys), xkeyA
@@ -224,7 +224,7 @@ ddq_add_8:
 	add	$(16*by), p_in
 
 	.if (klen == KEY_128)
-		vmovdqa	4*16(p_keys), xkey4
+		vmovdqa	4*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	4*16(p_keys), xkey4
@@ -234,7 +234,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 3 */
+		/* key 3 */
+		.if (klen == KEY_128)
+			vaesenc	xkey4, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -243,13 +248,18 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey4, var_xdata, var_xdata		/* key 4 */
+		/* key 4 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey4, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	6*16(p_keys), xkeyB
+			vmovdqa	6*16(p_keys), xkey8
 		.endif
 	.else
 		vmovdqa	6*16(p_keys), xkeyB
@@ -267,12 +277,17 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyB, var_xdata, var_xdata		/* key 6 */
+		/* key 6 */
+		.if (klen == KEY_128)
+			vaesenc	xkey8, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
-		vmovdqa	8*16(p_keys), xkey8
+		vmovdqa	8*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	8*16(p_keys), xkey8
@@ -288,7 +303,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	9*16(p_keys), xkeyA
+			vmovdqa	9*16(p_keys), xkey12
 		.endif
 	.else
 		vmovdqa	9*16(p_keys), xkeyA
@@ -297,7 +312,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey8, var_xdata, var_xdata		/* key 8 */
+		/* key 8 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey8, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -306,7 +326,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 9 */
+		/* key 9 */
+		.if (klen == KEY_128)
+			vaesenc	xkey12, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -412,7 +437,6 @@ ddq_add_8:
 /* main body of aes ctr load */
 
 .macro do_aes_ctrmain key_len
-
 	cmp	$16, num_bytes
 	jb	.Ldo_return2\key_len
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/aes_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/aes_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/aes_glue.c
@@ -66,5 +66,5 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/aesni-intel_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/aesni-intel_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/aesni-intel_glue.c
@@ -1137,7 +1137,7 @@ static int __driver_rfc4106_decrypt(stru
 		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
 		if (!src)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
+		assoc = (src + req->cryptlen);
 		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
 		scatterwalk_map_and_copy(assoc, req->assoc, 0,
 			req->assoclen, 0);
@@ -1162,7 +1162,7 @@ static int __driver_rfc4106_decrypt(stru
 		scatterwalk_done(&src_sg_walk, 0, 0);
 		scatterwalk_done(&assoc_sg_walk, 0, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1);
+		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
 		kfree(src);
 	}
 	return retval;
@@ -1550,4 +1550,4 @@ module_exit(aesni_exit);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/blowfish_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/blowfish_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/blowfish_glue.c
@@ -478,5 +478,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("blowfish");
-MODULE_ALIAS("blowfish-asm");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/camellia_aesni_avx2_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/camellia_aesni_avx_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/camellia_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/camellia_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/camellia_glue.c
@@ -1725,5 +1725,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/cast5_avx_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/cast5_avx_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/cast5_avx_glue.c
@@ -491,4 +491,4 @@ module_exit(cast5_exit);
 
 MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/cast6_avx_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/cast6_avx_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/cast6_avx_glue.c
@@ -611,4 +611,4 @@ module_exit(cast6_exit);
 
 MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/crc32-pclmul_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/crc32-pclmul_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/crc32-pclmul_glue.c
@@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini);
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crc32");
-MODULE_ALIAS("crc32-pclmul");
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-pclmul");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/crc32c-intel_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/crc32c-intel_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/crc32c-intel_glue.c
@@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang <austin.zhan
 MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crc32c");
-MODULE_ALIAS("crc32c-intel");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-intel");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/crct10dif-pclmul_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -147,5 +147,5 @@ MODULE_AUTHOR("Tim Chen <tim.c.chen@linu
 MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("crct10dif");
-MODULE_ALIAS("crct10dif-pclmul");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-pclmul");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/des3_ede_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/des3_ede_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/des3_ede_glue.c
@@ -502,8 +502,8 @@ module_exit(des3_ede_x86_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
-MODULE_ALIAS("des3_ede");
-MODULE_ALIAS("des3_ede-asm");
-MODULE_ALIAS("des");
-MODULE_ALIAS("des-asm");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-asm");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-asm");
 MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/fpu.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/fpu.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/fpu.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/crypto.h>
 #include <asm/i387.h>
 
 struct crypto_fpu_ctx {
@@ -159,3 +160,5 @@ void __exit crypto_fpu_exit(void)
 {
 	crypto_unregister_template(&crypto_fpu_tmpl);
 }
+
+MODULE_ALIAS_CRYPTO("fpu");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/ghash-clmulni-intel_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -341,4 +341,4 @@ module_exit(ghash_pclmulqdqni_mod_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
 		   "acclerated by PCLMULQDQ-NI");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/salsa20_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/salsa20_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/salsa20_glue.c
@@ -119,5 +119,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)");
-MODULE_ALIAS("salsa20");
-MODULE_ALIAS("salsa20-asm");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/serpent_avx2_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/serpent_avx2_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/serpent_avx2_glue.c
@@ -558,5 +558,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("serpent");
-MODULE_ALIAS("serpent-asm");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/serpent_avx_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/serpent_avx_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/serpent_avx_glue.c
@@ -617,4 +617,4 @@ module_exit(serpent_exit);
 
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/serpent_sse2_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/serpent_sse2_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/serpent_sse2_glue.c
@@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit);
 
 MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha-mb/sha1_mb.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/sha-mb/sha1_mb.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -932,4 +932,4 @@ module_exit(sha1_mb_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, multi buffer accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha1_ssse3_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/sha1_ssse3_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha1_ssse3_glue.c
@@ -278,4 +278,4 @@ module_exit(sha1_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha256_ssse3_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/sha256_ssse3_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha256_ssse3_glue.c
@@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha512_ssse3_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/sha512_ssse3_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/sha512_ssse3_glue.c
@@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/twofish_avx_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/twofish_avx_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/twofish_avx_glue.c
@@ -579,4 +579,4 @@ module_exit(twofish_exit);
 
 MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/twofish_glue.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/twofish_glue.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/twofish_glue.c
@@ -96,5 +96,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/crypto/twofish_glue_3way.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/crypto/twofish_glue_3way.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/crypto/twofish_glue_3way.c
@@ -495,5 +495,5 @@ module_exit(fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/desc.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/desc.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/desc.h
@@ -251,7 +251,8 @@ static inline void native_load_tls(struc
 		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
 }
 
-#define _LDT_empty(info)				\
+/* This intentionally ignores lm, since 32-bit apps don't have that field. */
+#define LDT_empty(info)					\
 	((info)->base_addr		== 0	&&	\
 	 (info)->limit			== 0	&&	\
 	 (info)->contents		== 0	&&	\
@@ -261,11 +262,18 @@ static inline void native_load_tls(struc
 	 (info)->seg_not_present	== 1	&&	\
 	 (info)->useable		== 0)
 
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
+/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */
+static inline bool LDT_zero(const struct user_desc *info)
+{
+	return (info->base_addr		== 0 &&
+		info->limit		== 0 &&
+		info->contents		== 0 &&
+		info->read_exec_only	== 0 &&
+		info->seg_32bit		== 0 &&
+		info->limit_in_pages	== 0 &&
+		info->seg_not_present	== 0 &&
+		info->useable		== 0);
+}
 
 static inline void clear_LDT(void)
 {
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/fpu-internal.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/fpu-internal.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/fpu-internal.h
@@ -368,7 +368,7 @@ static inline void drop_fpu(struct task_
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
-	clear_used_math();
+	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/microcode.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/microcode.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/microcode.h
@@ -78,6 +78,7 @@ static inline void __exit exit_amd_micro
 extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
+void reload_early_microcode(void);
 #else
 static inline void __init load_ucode_bsp(void) {}
 static inline void load_ucode_ap(void) {}
@@ -85,6 +86,7 @@ static inline int __init save_microcode_
 {
 	return 0;
 }
+static inline void reload_early_microcode(void) {}
 #endif
 
 #endif /* _ASM_X86_MICROCODE_H */
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/microcode_amd.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/microcode_amd.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct e
 
 extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
+extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
 
 #define PATCH_MAX_SIZE PAGE_SIZE
 extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -68,10 +68,12 @@ extern u8 amd_ucode_patch[PATCH_MAX_SIZE
 extern void __init load_ucode_amd_bsp(void);
 extern void load_ucode_amd_ap(void);
 extern int __init save_microcode_in_initrd_amd(void);
+void reload_ucode_amd(void);
 #else
 static inline void __init load_ucode_amd_bsp(void) {}
 static inline void load_ucode_amd_ap(void) {}
 static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
+void reload_ucode_amd(void) {}
 #endif
 
 #endif /* _ASM_X86_MICROCODE_AMD_H */
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/microcode_intel.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/microcode_intel.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/microcode_intel.h
@@ -68,11 +68,13 @@ extern void __init load_ucode_intel_bsp(
 extern void load_ucode_intel_ap(void);
 extern void show_ucode_info_early(void);
 extern int __init save_microcode_in_initrd_intel(void);
+void reload_ucode_intel(void);
 #else
 static inline __init void load_ucode_intel_bsp(void) {}
 static inline void load_ucode_intel_ap(void) {}
 static inline void show_ucode_info_early(void) {}
 static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; }
+static inline void reload_ucode_intel(void) {}
 #endif
 
 #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/vsyscall.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/vsyscall.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void
 		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
-		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+		asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 	}
 
 	return p;
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/xen/page.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/xen/page.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/xen/page.h
@@ -236,4 +236,11 @@ void make_lowmem_page_readwrite(void *va
 #define xen_remap(cookie, size) ioremap((cookie), (size));
 #define xen_unmap(cookie) iounmap((cookie))
 
+static inline bool xen_arch_need_swiotlb(struct device *dev,
+					 unsigned long pfn,
+					 unsigned long mfn)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/asm/xsave.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/asm/xsave.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/asm/xsave.h
@@ -81,18 +81,15 @@ static inline int xsave_state_booting(st
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XSAVES"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XSAVE"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -111,18 +108,15 @@ static inline int xrstor_state_booting(s
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XRSTORS"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XRSTOR"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -148,9 +142,9 @@ static inline int xsave_state(struct xsa
 	 */
 	alternative_input_2(
 		"1:"XSAVE,
-		"1:"XSAVEOPT,
+		XSAVEOPT,
 		X86_FEATURE_XSAVEOPT,
-		"1:"XSAVES,
+		XSAVES,
 		X86_FEATURE_XSAVES,
 		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
 		"memory");
@@ -177,7 +171,7 @@ static inline int xrstor_state(struct xs
 	 */
 	alternative_input(
 		"1: " XRSTOR,
-		"1: " XRSTORS,
+		XRSTORS,
 		X86_FEATURE_XSAVES,
 		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 		: "memory");
Index: linux-3.18.13-rt10-r7s4/arch/x86/include/uapi/asm/ldt.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/include/uapi/asm/ldt.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/include/uapi/asm/ldt.h
@@ -28,6 +28,13 @@ struct user_desc {
 	unsigned int  seg_not_present:1;
 	unsigned int  useable:1;
 #ifdef __x86_64__
+	/*
+	 * Because this bit is not present in 32-bit user code, user
+	 * programs can pass uninitialized values here.  Therefore, in
+	 * any context in which a user_desc comes from a 32-bit program,
+	 * the kernel must act as though lm == 0, regardless of the
+	 * actual value.
+	 */
 	unsigned int  lm:1;
 #endif
 };
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/acpi/boot.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/acpi/boot.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/acpi/boot.c
@@ -604,18 +604,24 @@ void __init acpi_pic_sci_set_trigger(uns
 
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-	int irq;
+	int rc, irq, trigger, polarity;
 
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
 		*irqp = gsi;
-	} else {
-		irq = mp_map_gsi_to_irq(gsi,
-					IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
-		if (irq < 0)
-			return -1;
-		*irqp = irq;
+		return 0;
 	}
-	return 0;
+
+	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
+	if (rc == 0) {
+		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+		polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+		irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+		if (irq >= 0) {
+			*irqp = irq;
+			return 0;
+		}
+	}
+	return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/apic/apic_numachip.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/apic/apic_numachip.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/apic/apic_numachip.c
@@ -40,7 +40,7 @@ static unsigned int get_apic_id(unsigned
 	unsigned int id;
 
 	rdmsrl(MSR_FAM10H_NODE_ID, value);
-	id = ((x >> 24) & 0xffU) | ((value << 2) & 0x3f00U);
+	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
 
 	return id;
 }
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/Makefile
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/Makefile
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/Makefile
@@ -66,3 +66,4 @@ targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
 	$(call if_changed,mkcapflags)
 endif
+clean-files += capflags.c
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/amd.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/microcode/amd.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/amd.c
@@ -376,7 +376,7 @@ static enum ucode_state __load_microcode
 	return UCODE_OK;
 }
 
-enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
+enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
@@ -390,8 +390,8 @@ enum ucode_state load_microcode_amd(u8 f
 
 #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
 	/* save BSP's matching patch for early load */
-	if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(smp_processor_id());
+	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
+		struct ucode_patch *p = find_patch(cpu);
 		if (p) {
 			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
 			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -444,7 +444,7 @@ static enum ucode_state request_microcod
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/amd_early.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/microcode/amd_early.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -389,7 +389,7 @@ int __init save_microcode_in_initrd_amd(
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
-	ret = load_microcode_amd(eax, container, container_size);
+	ret = load_microcode_amd(smp_processor_id(), eax, container, container_size);
 	if (ret != UCODE_OK)
 		retval = -EINVAL;
 
@@ -402,3 +402,21 @@ int __init save_microcode_in_initrd_amd(
 
 	return retval;
 }
+
+void reload_ucode_amd(void)
+{
+	struct microcode_amd *mc;
+	u32 rev, eax;
+
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
+
+	mc = (struct microcode_amd *)amd_ucode_patch;
+
+	if (mc && rev < mc->hdr.patch_id) {
+		if (!__apply_microcode_amd(mc)) {
+			ucode_new_rev = mc->hdr.patch_id;
+			pr_info("microcode: reload patch_level=0x%08x\n",
+				ucode_new_rev);
+		}
+	}
+}
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/core.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/microcode/core.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/core.c
@@ -465,16 +465,8 @@ static void mc_bp_resume(void)
 
 	if (uci->valid && uci->mc)
 		microcode_ops->apply_microcode(cpu);
-#ifdef CONFIG_X86_64
 	else if (!uci->mc)
-		/*
-		 * We might resume and not have applied late microcode but still
-		 * have a newer patch stashed from the early loader. We don't
-		 * have it in uci->mc so we have to load it the same way we're
-		 * applying patches early on the APs.
-		 */
-		load_ucode_ap();
-#endif
+		reload_early_microcode();
 }
 
 static struct syscore_ops mc_syscore_ops = {
@@ -559,8 +551,8 @@ static int __init microcode_init(void)
 	struct cpuinfo_x86 *c = &cpu_data(0);
 	int error;
 
-	if (dis_ucode_ldr)
-		return 0;
+	if (paravirt_enabled() || dis_ucode_ldr)
+		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
 		microcode_ops = init_intel_microcode();
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/core_early.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/microcode/core_early.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/core_early.c
@@ -176,3 +176,24 @@ int __init save_microcode_in_initrd(void
 
 	return 0;
 }
+
+void reload_early_microcode(void)
+{
+	int vendor, x86;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	switch (vendor) {
+	case X86_VENDOR_INTEL:
+		if (x86 >= 6)
+			reload_ucode_intel();
+		break;
+	case X86_VENDOR_AMD:
+		if (x86 >= 0x10)
+			reload_ucode_amd();
+		break;
+	default:
+		break;
+	}
+}
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/intel_early.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/microcode/intel_early.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -650,8 +650,7 @@ static inline void print_ucode(struct uc
 }
 #endif
 
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
-				 struct ucode_cpu_info *uci)
+static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 {
 	struct microcode_intel *mc_intel;
 	unsigned int val[2];
@@ -680,7 +679,10 @@ static int apply_microcode_early(struct
 #endif
 	uci->cpu_sig.rev = val[1];
 
-	print_ucode(uci);
+	if (early)
+		print_ucode(uci);
+	else
+		print_ucode_info(uci, mc_intel->hdr.date);
 
 	return 0;
 }
@@ -715,12 +717,17 @@ _load_ucode_intel_bsp(struct mc_saved_da
 		      unsigned long initrd_end_early,
 		      struct ucode_cpu_info *uci)
 {
+	enum ucode_state ret;
+
 	collect_cpu_info_early(uci);
 	scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data,
 		       mc_saved_in_initrd, uci);
-	load_microcode(mc_saved_data, mc_saved_in_initrd,
-		       initrd_start_early, uci);
-	apply_microcode_early(mc_saved_data, uci);
+
+	ret = load_microcode(mc_saved_data, mc_saved_in_initrd,
+			     initrd_start_early, uci);
+
+	if (ret == UCODE_OK)
+		apply_microcode_early(uci, true);
 }
 
 void __init
@@ -749,7 +756,8 @@ load_ucode_intel_bsp(void)
 	initrd_end_early = initrd_start_early + ramdisk_size;
 
 	_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd,
-			      initrd_start_early, initrd_end_early, &uci);
+			      initrd_start_early, initrd_end_early,
+			      &uci);
 #endif
 }
 
@@ -783,5 +791,23 @@ void load_ucode_intel_ap(void)
 	collect_cpu_info_early(&uci);
 	load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
 		       initrd_start_addr, &uci);
-	apply_microcode_early(mc_saved_data_p, &uci);
+	apply_microcode_early(&uci, true);
+}
+
+void reload_ucode_intel(void)
+{
+	struct ucode_cpu_info uci;
+	enum ucode_state ret;
+
+	if (!mc_saved_data.mc_saved_count)
+		return;
+
+	collect_cpu_info_early(&uci);
+
+	ret = generic_load_microcode_early(mc_saved_data.mc_saved,
+					   mc_saved_data.mc_saved_count, &uci);
+	if (ret != UCODE_OK)
+		return;
+
+	apply_microcode_early(&uci, false);
 }
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/mshyperv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/mshyperv.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/mshyperv.c
@@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = {
 	.rating		= 400, /* use this when running on Hyperv*/
 	.read		= read_hv_clock,
 	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static void __init ms_hyperv_init_platform(void)
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/perf_event_intel.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
 	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_rapl.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+	return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_uncore.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -276,6 +276,17 @@ static struct intel_uncore_box *uncore_a
 	return box;
 }
 
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+	return event->pmu->event_init == uncore_pmu_event_init;
+}
+
 static int
 uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
@@ -290,13 +301,18 @@ uncore_collect_events(struct intel_uncor
 		return -EINVAL;
 
 	n = box->n_events;
-	box->event_list[n] = leader;
-	n++;
+
+	if (is_uncore_event(leader)) {
+		box->event_list[n] = leader;
+		n++;
+	}
+
 	if (!dogrp)
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (event->state <= PERF_EVENT_STATE_OFF)
+		if (!is_uncore_event(event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
 		if (n >= max_count)
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_uncore.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	2
+#define UNCORE_EXTRA_PCI_DEV_MAX	3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX		8
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -887,6 +887,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2022,6 +2023,17 @@ void hswep_uncore_cpu_init(void)
 {
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+	/* Detect 6-8 core systems with only two SBOXes */
+	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+		u32 capid4;
+
+		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+				      0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			hswep_uncore_sbox.num_boxes = 2;
+	}
+
 	uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2279,6 +2291,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_unc
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
 						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/entry_64.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/entry_64.S
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/entry_64.S
@@ -334,11 +334,14 @@ ENTRY(ret_from_fork)
 	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
 	jz   1f
 
-	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
-	jnz  int_ret_from_sys_call
-
-	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
-	jmp ret_from_sys_call			# go to the SYSRET fastpath
+	/*
+	 * By the time we get here, we have no idea whether our pt_regs,
+	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+	 * the slow path, or one of the ia32entry paths.
+	 * Use int_ret_from_sys_call to return, since it can safely handle
+	 * all of the above.
+	 */
+	jmp  int_ret_from_sys_call
 
 1:
 	subq $REST_SKIP, %rsp	# leave space for volatiles
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/irq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/irq.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/irq.c
@@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file
 	seq_printf(p, "  Machine check polls\n");
 #endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
-	seq_printf(p, "%*s: ", prec, "THR");
+	seq_printf(p, "%*s: ", prec, "HYP");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
 	seq_printf(p, "  Hypervisor callback interrupts\n");
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/kprobes/core.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/kprobes/core.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/kprobes/core.c
@@ -1018,6 +1018,15 @@ int setjmp_pre_handler(struct kprobe *p,
 	regs->flags &= ~X86_EFLAGS_IF;
 	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
+
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer to get messed up.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -1046,24 +1055,25 @@ int longjmp_break_handler(struct kprobe
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	u8 *addr = (u8 *) (regs->ip - 1);
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	void *saved_sp = kcb->jprobe_saved_sp;
 
 	if ((addr > (u8 *) jprobe_return) &&
 	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+		if (stack_addr(regs) != saved_sp) {
 			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
 			printk(KERN_ERR
 			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), kcb->jprobe_saved_sp);
+			       stack_addr(regs), saved_sp);
 			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
 			show_regs(saved_regs);
 			printk(KERN_ERR "Current registers\n");
 			show_regs(regs);
 			BUG();
 		}
+		/* It's OK to start function graph tracing again */
+		unpause_graph_tracing();
 		*regs = kcb->jprobe_saved_regs;
-		memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
-		       kcb->jprobes_stack,
-		       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+		memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
 		preempt_enable_no_resched();
 		return 1;
 	}
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/kvm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/kvm.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/kvm.c
@@ -283,7 +283,14 @@ NOKPROBE_SYMBOL(do_async_page_fault);
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
-	pv_info.paravirt_enabled = 1;
+
+	/*
+	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
+	 * guest kernel works like a bare metal kernel with additional
+	 * features, and paravirt_enabled is about features that are
+	 * missing.
+	 */
+	pv_info.paravirt_enabled = 0;
 
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/kvmclock.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/kvmclock.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/kvmclock.c
@@ -263,7 +263,6 @@ void __init kvmclock_init(void)
 #endif
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
-	pv_info.paravirt_enabled = 1;
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/pmc_atom.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/pmc_atom.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/pmc_atom.c
@@ -217,6 +217,8 @@ static int pmc_dbgfs_register(struct pmc
 	if (!dir)
 		return -ENOMEM;
 
+	pmc->dbgfs_dir = dir;
+
 	f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO,
 				dir, pmc, &pmc_dev_state_ops);
 	if (!f) {
@@ -229,7 +231,7 @@ static int pmc_dbgfs_register(struct pmc
 		dev_err(&pdev->dev, "sleep_state register failed\n");
 		goto err;
 	}
-	pmc->dbgfs_dir = dir;
+
 	return 0;
 err:
 	pmc_dbgfs_unregister(pmc);
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/process_64.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/process_64.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/process_64.c
@@ -283,24 +283,9 @@ __switch_to(struct task_struct *prev_p,
 
 	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
-	/*
-	 * Reload esp0, LDT and the page table pointer:
-	 */
+	/* Reload esp0 and ss1. */
 	load_sp0(tss, next);
 
-	/*
-	 * Switch DS and ES.
-	 * This won't pick up thread selector changes, but I guess that is ok.
-	 */
-	savesegment(es, prev->es);
-	if (unlikely(next->es | prev->es))
-		loadsegment(es, next->es);
-
-	savesegment(ds, prev->ds);
-	if (unlikely(next->ds | prev->ds))
-		loadsegment(ds, next->ds);
-
-
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
 	 *
@@ -309,41 +294,101 @@ __switch_to(struct task_struct *prev_p,
 	savesegment(fs, fsindex);
 	savesegment(gs, gsindex);
 
+	/*
+	 * Load TLS before restoring any segments so that segment loads
+	 * reference the correct GDT entries.
+	 */
 	load_TLS(next, cpu);
 
 	/*
-	 * Leave lazy mode, flushing any hypercalls made here.
-	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
-	 * to date.
+	 * Leave lazy mode, flushing any hypercalls made here.  This
+	 * must be done after loading TLS entries in the GDT but before
+	 * loading segments that might reference them, and and it must
+	 * be done before math_state_restore, so the TS bit is up to
+	 * date.
 	 */
 	arch_end_context_switch(next_p);
 
+	/* Switch DS and ES.
+	 *
+	 * Reading them only returns the selectors, but writing them (if
+	 * nonzero) loads the full descriptor from the GDT or LDT.  The
+	 * LDT for next is loaded in switch_mm, and the GDT is loaded
+	 * above.
+	 *
+	 * We therefore need to write new values to the segment
+	 * registers on every context switch unless both the new and old
+	 * values are zero.
+	 *
+	 * Note that we don't need to do anything for CS and SS, as
+	 * those are saved and restored as part of pt_regs.
+	 */
+	savesegment(es, prev->es);
+	if (unlikely(next->es | prev->es))
+		loadsegment(es, next->es);
+
+	savesegment(ds, prev->ds);
+	if (unlikely(next->ds | prev->ds))
+		loadsegment(ds, next->ds);
+
 	/*
 	 * Switch FS and GS.
 	 *
-	 * Segment register != 0 always requires a reload.  Also
-	 * reload when it has changed.  When prev process used 64bit
-	 * base always reload to avoid an information leak.
+	 * These are even more complicated than FS and GS: they have
+	 * 64-bit bases are that controlled by arch_prctl.  Those bases
+	 * only differ from the values in the GDT or LDT if the selector
+	 * is 0.
+	 *
+	 * Loading the segment register resets the hidden base part of
+	 * the register to 0 or the value from the GDT / LDT.  If the
+	 * next base address zero, writing 0 to the segment register is
+	 * much faster than using wrmsr to explicitly zero the base.
+	 *
+	 * The thread_struct.fs and thread_struct.gs values are 0
+	 * if the fs and gs bases respectively are not overridden
+	 * from the values implied by fsindex and gsindex.  They
+	 * are nonzero, and store the nonzero base addresses, if
+	 * the bases are overridden.
+	 *
+	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+	 * be impossible.
+	 *
+	 * Therefore we need to reload the segment registers if either
+	 * the old or new selector is nonzero, and we need to override
+	 * the base address if next thread expects it to be overridden.
+	 *
+	 * This code is unnecessarily slow in the case where the old and
+	 * new indexes are zero and the new base is nonzero -- it will
+	 * unnecessarily write 0 to the selector before writing the new
+	 * base address.
+	 *
+	 * Note: This all depends on arch_prctl being the only way that
+	 * user code can override the segment base.  Once wrfsbase and
+	 * wrgsbase are enabled, most of this code will need to change.
 	 */
 	if (unlikely(fsindex | next->fsindex | prev->fs)) {
 		loadsegment(fs, next->fsindex);
+
 		/*
-		 * Check if the user used a selector != 0; if yes
-		 *  clear 64bit base, since overloaded base is always
-		 *  mapped to the Null selector
+		 * If user code wrote a nonzero value to FS, then it also
+		 * cleared the overridden base address.
+		 *
+		 * XXX: if user code wrote 0 to FS and cleared the base
+		 * address itself, we won't notice and we'll incorrectly
+		 * restore the prior base address next time we reschdule
+		 * the process.
 		 */
 		if (fsindex)
 			prev->fs = 0;
 	}
-	/* when next process has a 64bit base use it */
 	if (next->fs)
 		wrmsrl(MSR_FS_BASE, next->fs);
 	prev->fsindex = fsindex;
 
 	if (unlikely(gsindex | next->gsindex | prev->gs)) {
 		load_gs_index(next->gsindex);
+
+		/* This works (and fails) the same way as fsindex above. */
 		if (gsindex)
 			prev->gs = 0;
 	}
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/reboot.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/reboot.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/reboot.c
@@ -182,6 +182,16 @@ static struct dmi_system_id __initdata r
 		},
 	},
 
+	/* ASRock */
+	{	/* Handle problems with rebooting on ASRock Q1900DC-ITX */
+		.callback = set_pci_reboot,
+		.ident = "ASRock Q1900DC-ITX",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"),
+			DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"),
+		},
+	},
+
 	/* ASUS */
 	{	/* Handle problems with rebooting on ASUS P4S800 */
 		.callback = set_bios_reboot,
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/tls.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/tls.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/tls.c
@@ -27,6 +27,58 @@ static int get_free_idx(void)
 	return -ESRCH;
 }
 
+static bool tls_desc_okay(const struct user_desc *info)
+{
+	/*
+	 * For historical reasons (i.e. no one ever documented how any
+	 * of the segmentation APIs work), user programs can and do
+	 * assume that a struct user_desc that's all zeros except for
+	 * entry_number means "no segment at all".  This never actually
+	 * worked.  In fact, up to Linux 3.19, a struct user_desc like
+	 * this would create a 16-bit read-write segment with base and
+	 * limit both equal to zero.
+	 *
+	 * That was close enough to "no segment at all" until we
+	 * hardened this function to disallow 16-bit TLS segments.  Fix
+	 * it up by interpreting these zeroed segments the way that they
+	 * were almost certainly intended to be interpreted.
+	 *
+	 * The correct way to ask for "no segment at all" is to specify
+	 * a user_desc that satisfies LDT_empty.  To keep everything
+	 * working, we accept both.
+	 *
+	 * Note that there's a similar kludge in modify_ldt -- look at
+	 * the distinction between modes 1 and 0x11.
+	 */
+	if (LDT_empty(info) || LDT_zero(info))
+		return true;
+
+	/*
+	 * espfix is required for 16-bit data segments, but espfix
+	 * only works for LDT segments.
+	 */
+	if (!info->seg_32bit)
+		return false;
+
+	/* Only allow data segments in the TLS array. */
+	if (info->contents > 1)
+		return false;
+
+	/*
+	 * Non-present segments with DPL 3 present an interesting attack
+	 * surface.  The kernel should handle such segments correctly,
+	 * but TLS is very difficult to protect in a sandbox, so prevent
+	 * such segments from being created.
+	 *
+	 * If userspace needs to remove a TLS entry, it can still delete
+	 * it outright.
+	 */
+	if (info->seg_not_present)
+		return false;
+
+	return true;
+}
+
 static void set_tls_desc(struct task_struct *p, int idx,
 			 const struct user_desc *info, int n)
 {
@@ -40,7 +92,7 @@ static void set_tls_desc(struct task_str
 	cpu = get_cpu();
 
 	while (n-- > 0) {
-		if (LDT_empty(info))
+		if (LDT_empty(info) || LDT_zero(info))
 			desc->a = desc->b = 0;
 		else
 			fill_ldt(desc, info);
@@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struc
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
 
+	if (!tls_desc_okay(&info))
+		return -EINVAL;
+
 	if (idx == -1)
 		idx = info.entry_number;
 
@@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *t
 {
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
+	int i;
 
 	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *t
 	else
 		info = infobuf;
 
+	for (i = 0; i < count / sizeof(struct user_desc); i++)
+		if (!tls_desc_okay(info + i))
+			return -EINVAL;
+
 	set_tls_desc(target,
 		     GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
 		     info, count / sizeof(struct user_desc));
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/traps.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/traps.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/traps.c
@@ -387,7 +387,7 @@ NOKPROBE_SYMBOL(do_int3);
  * for scheduling or signal handling. The actual stack switch is done in
  * entry.S
  */
-asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
 	struct pt_regs *regs = eregs;
 	/* Did already sync */
@@ -413,7 +413,7 @@ struct bad_iret_stack {
 	struct pt_regs regs;
 };
 
-asmlinkage __visible
+asmlinkage __visible notrace
 struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 {
 	/*
@@ -436,6 +436,7 @@ struct bad_iret_stack *fixup_bad_iret(st
 	BUG_ON(!user_mode_vm(&new_stack->regs));
 	return new_stack;
 }
+NOKPROBE_SYMBOL(fixup_bad_iret);
 #endif
 
 /*
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/tsc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/tsc.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/tsc.c
@@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate
 			goto success;
 		}
 	}
-	pr_err("Fast TSC calibration failed\n");
+	pr_info("Fast TSC calibration failed\n");
 	return 0;
 
 success:
Index: linux-3.18.13-rt10-r7s4/arch/x86/kernel/xsave.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kernel/xsave.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kernel/xsave.c
@@ -378,7 +378,7 @@ int __restore_xstate_sig(void __user *bu
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Sanitize the copied state etc.
 		 */
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
@@ -392,14 +392,15 @@ int __restore_xstate_sig(void __user *bu
 		 */
 		drop_fpu(tsk);
 
-		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
 		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpu_finit(fpu);
 			err = -1;
 		} else {
 			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-			set_used_math();
 		}
 
+		set_used_math();
 		if (use_eager_fpu()) {
 			preempt_disable();
 			math_state_restore();
@@ -738,3 +739,4 @@ void *get_xsave_addr(struct xsave_struct
 
 	return (void *)xsave + xstate_comp_offsets[feature];
 }
+EXPORT_SYMBOL_GPL(get_xsave_addr);
Index: linux-3.18.13-rt10-r7s4/arch/x86/kvm/cpuid.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kvm/cpuid.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kvm/cpuid.c
@@ -319,6 +319,10 @@ static inline int __do_cpuid_ent(struct
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
 		F(ADX) | F(SMAP);
 
+	/* cpuid 0xD.1.eax */
+	const u32 kvm_supported_word10_x86_features =
+		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -455,13 +459,18 @@ static inline int __do_cpuid_ent(struct
 		entry->eax &= supported;
 		entry->edx &= supported >> 32;
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+		if (!supported)
+			break;
+
 		for (idx = 1, i = 1; idx < 64; ++idx) {
 			u64 mask = ((u64)1 << idx);
 			if (*nent >= maxnent)
 				goto out;
 
 			do_cpuid_1_ent(&entry[i], function, idx);
-			if (entry[i].eax == 0 || !(supported & mask))
+			if (idx == 1)
+				entry[i].eax &= kvm_supported_word10_x86_features;
+			else if (entry[i].eax == 0 || !(supported & mask))
 				continue;
 			entry[i].flags |=
 			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
Index: linux-3.18.13-rt10-r7s4/arch/x86/kvm/emulate.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kvm/emulate.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kvm/emulate.c
@@ -2128,7 +2128,7 @@ static int em_ret_far(struct x86_emulate
 	/* Outer-privilege level return is not implemented */
 	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
 		return X86EMUL_UNHANDLEABLE;
-	rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, 0, false,
+	rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, cpl, false,
 				       &new_desc);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
@@ -2345,7 +2345,7 @@ static int em_sysenter(struct x86_emulat
 	 * Not recognized on AMD in compat mode (but is recognized in legacy
 	 * mode).
 	 */
-	if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA)
+	if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
 	    && !vendor_intel(ctxt))
 		return emulate_ud(ctxt);
 
@@ -2358,25 +2358,13 @@ static int em_sysenter(struct x86_emulat
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
-	switch (ctxt->mode) {
-	case X86EMUL_MODE_PROT32:
-		if ((msr_data & 0xfffc) == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	case X86EMUL_MODE_PROT64:
-		if (msr_data == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	default:
-		break;
-	}
+	if ((msr_data & 0xfffc) == 0x0)
+		return emulate_gp(ctxt, 0);
 
 	ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
-	cs_sel = (u16)msr_data;
-	cs_sel &= ~SELECTOR_RPL_MASK;
+	cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK;
 	ss_sel = cs_sel + 8;
-	ss_sel &= ~SELECTOR_RPL_MASK;
-	if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) {
+	if (efer & EFER_LMA) {
 		cs.d = 0;
 		cs.l = 1;
 	}
@@ -2385,10 +2373,11 @@ static int em_sysenter(struct x86_emulat
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data);
-	ctxt->_eip = msr_data;
+	ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data;
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
-	*reg_write(ctxt, VCPU_REGS_RSP) = msr_data;
+	*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
+							      (u32)msr_data;
 
 	return X86EMUL_CONTINUE;
 }
@@ -3788,8 +3777,8 @@ static const struct opcode group5[] = {
 };
 
 static const struct opcode group6[] = {
-	DI(Prot,	sldt),
-	DI(Prot,	str),
+	DI(Prot | DstMem,	sldt),
+	DI(Prot | DstMem,	str),
 	II(Prot | Priv | SrcMem16, em_lldt, lldt),
 	II(Prot | Priv | SrcMem16, em_ltr, ltr),
 	N, N, N, N,
@@ -4840,7 +4829,8 @@ int x86_emulate_insn(struct x86_emulate_
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 	}
-	ctxt->dst.orig_val = ctxt->dst.val;
+	/* Copy full 64-bit value for CMPXCHG8B.  */
+	ctxt->dst.orig_val64 = ctxt->dst.val64;
 
 special_insn:
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/kvm/mmu.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kvm/mmu.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kvm/mmu.c
@@ -4449,7 +4449,7 @@ void kvm_mmu_invalidate_mmio_sptes(struc
 	 * zap all shadow pages.
 	 */
 	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
-		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
+		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }
Index: linux-3.18.13-rt10-r7s4/arch/x86/kvm/vmx.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kvm/vmx.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kvm/vmx.c
@@ -2377,12 +2377,12 @@ static __init void nested_vmx_setup_ctls
 	nested_vmx_secondary_ctls_low = 0;
 	nested_vmx_secondary_ctls_high &=
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
-		SECONDARY_EXEC_UNRESTRICTED_GUEST |
 		SECONDARY_EXEC_WBINVD_EXITING;
 
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
-		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
+		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT |
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
 		nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
 			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
 			 VMX_EPT_INVEPT_BIT;
Index: linux-3.18.13-rt10-r7s4/arch/x86/kvm/x86.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/kvm/x86.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/kvm/x86.c
@@ -1237,21 +1237,22 @@ void kvm_track_tsc_matching(struct kvm_v
 {
 #ifdef CONFIG_X86_64
 	bool vcpus_matched;
-	bool do_request = false;
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 
 	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
 			 atomic_read(&vcpu->kvm->online_vcpus));
 
-	if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC)
-		if (!ka->use_master_clock)
-			do_request = 1;
-
-	if (!vcpus_matched && ka->use_master_clock)
-			do_request = 1;
-
-	if (do_request)
+	/*
+	 * Once the masterclock is enabled, always perform request in
+	 * order to update it.
+	 *
+	 * In order to enable masterclock, the host clocksource must be TSC
+	 * and the vcpus need to have matched TSCs.  When that happens,
+	 * perform request to enable masterclock.
+	 */
+	if (ka->use_master_clock ||
+	    (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -2712,7 +2713,6 @@ int kvm_vm_ioctl_check_extension(struct
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
@@ -3128,15 +3128,89 @@ static int kvm_vcpu_ioctl_x86_set_debugr
 	return 0;
 }
 
+#define XSTATE_COMPACTION_ENABLED (1ULL << 63)
+
+static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
+{
+	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+	u64 valid;
+
+	/*
+	 * Copy legacy XSAVE area, to avoid complications with CPUID
+	 * leaves 0 and 1 in the loop below.
+	 */
+	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
+
+	/* Set XSTATE_BV */
+	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
+
+	/*
+	 * Copy each region from the possibly compacted offset to the
+	 * non-compacted offset.
+	 */
+	valid = xstate_bv & ~XSTATE_FPSSE;
+	while (valid) {
+		u64 feature = valid & -valid;
+		int index = fls64(feature) - 1;
+		void *src = get_xsave_addr(xsave, feature);
+
+		if (src) {
+			u32 size, offset, ecx, edx;
+			cpuid_count(XSTATE_CPUID, index,
+				    &size, &offset, &ecx, &edx);
+			memcpy(dest + offset, src, size);
+		}
+
+		valid -= feature;
+	}
+}
+
+static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
+{
+	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
+	u64 valid;
+
+	/*
+	 * Copy legacy XSAVE area, to avoid complications with CPUID
+	 * leaves 0 and 1 in the loop below.
+	 */
+	memcpy(xsave, src, XSAVE_HDR_OFFSET);
+
+	/* Set XSTATE_BV and possibly XCOMP_BV.  */
+	xsave->xsave_hdr.xstate_bv = xstate_bv;
+	if (cpu_has_xsaves)
+		xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+
+	/*
+	 * Copy each region from the non-compacted offset to the
+	 * possibly compacted offset.
+	 */
+	valid = xstate_bv & ~XSTATE_FPSSE;
+	while (valid) {
+		u64 feature = valid & -valid;
+		int index = fls64(feature) - 1;
+		void *dest = get_xsave_addr(xsave, feature);
+
+		if (dest) {
+			u32 size, offset, ecx, edx;
+			cpuid_count(XSTATE_CPUID, index,
+				    &size, &offset, &ecx, &edx);
+			memcpy(dest, src + offset, size);
+		} else
+			WARN_ON_ONCE(1);
+
+		valid -= feature;
+	}
+}
+
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
 	if (cpu_has_xsave) {
-		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state->xsave,
-			vcpu->arch.guest_xstate_size);
-		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &=
-			vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE;
+		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
+		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->fxsave,
@@ -3160,8 +3234,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(
 		 */
 		if (xstate_bv & ~kvm_supported_xcr0())
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state->xsave,
-			guest_xsave->region, vcpu->arch.guest_xstate_size);
+		load_xsave(vcpu, (u8 *)guest_xsave->region);
 	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
@@ -6873,6 +6946,9 @@ int fx_init(struct kvm_vcpu *vcpu)
 		return err;
 
 	fpu_finit(&vcpu->arch.guest_fpu);
+	if (cpu_has_xsaves)
+		vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
 	 * Ensure guest xcr0 is valid for loading
Index: linux-3.18.13-rt10-r7s4/arch/x86/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/mm/fault.c
@@ -844,11 +844,8 @@ do_sigbus(struct pt_regs *regs, unsigned
 	  unsigned int fault)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
 	int code = BUS_ADRERR;
 
-	up_read(&mm->mmap_sem);
-
 	/* Kernel mode? Handle exceptions or die: */
 	if (!(error_code & PF_USER)) {
 		no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
@@ -879,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, uns
 	       unsigned long address, unsigned int fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
-		up_read(&current->mm->mmap_sem);
 		no_context(regs, error_code, address, 0, 0);
 		return;
 	}
@@ -887,14 +883,11 @@ mm_fault_error(struct pt_regs *regs, uns
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
 		if (!(error_code & PF_USER)) {
-			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address,
 				   SIGSEGV, SEGV_MAPERR);
 			return;
 		}
 
-		up_read(&current->mm->mmap_sem);
-
 		/*
 		 * We ran out of memory, call the OOM killer, and return the
 		 * userspace (which will retry the fault, or kill us if we got
@@ -905,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, uns
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
 			do_sigbus(regs, error_code, address, fault);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area_nosemaphore(regs, error_code, address);
 		else
 			BUG();
 	}
@@ -1247,6 +1242,7 @@ good_area:
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
+		up_read(&mm->mmap_sem);
 		mm_fault_error(regs, error_code, address, fault);
 		return;
 	}
Index: linux-3.18.13-rt10-r7s4/arch/x86/mm/gup.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/mm/gup.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/mm/gup.c
@@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsi
 		 */
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (unlikely(pmd_large(pmd))) {
+		if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) {
 			/*
 			 * NUMA hinting faults need to be handled in the GUP
 			 * slowpath for accounting purposes and so that they
Index: linux-3.18.13-rt10-r7s4/arch/x86/mm/hugetlbpage.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/mm/hugetlbpage.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/mm/hugetlbpage.c
@@ -66,9 +66,15 @@ follow_huge_addr(struct mm_struct *mm, u
 	return ERR_PTR(-EINVAL);
 }
 
+/*
+ * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
+ * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
+ * Otherwise, returns 0.
+ */
 int pmd_huge(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PSE);
+	return !pmd_none(pmd) &&
+		(pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
 }
 
 int pud_huge(pud_t pud)
Index: linux-3.18.13-rt10-r7s4/arch/x86/mm/mmap.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/mm/mmap.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/mm/mmap.c
@@ -35,12 +35,12 @@ struct va_alignment __read_mostly va_ali
 	.flags = -1,
 };
 
-static unsigned int stack_maxrandom_size(void)
+static unsigned long stack_maxrandom_size(void)
 {
-	unsigned int max = 0;
+	unsigned long max = 0;
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT;
+		max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
 	}
 
 	return max;
Index: linux-3.18.13-rt10-r7s4/arch/x86/pci/common.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/pci/common.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/pci/common.c
@@ -448,6 +448,22 @@ static const struct dmi_system_id pcipro
 			DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
 		},
 	},
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+                },
+        },
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+                },
+        },
 	{}
 };
 
Index: linux-3.18.13-rt10-r7s4/arch/x86/pci/i386.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/pci/i386.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/pci/i386.c
@@ -216,7 +216,7 @@ static void pcibios_allocate_bridge_reso
 			continue;
 		if (r->parent)	/* Already allocated */
 			continue;
-		if (!r->start || pci_claim_resource(dev, idx) < 0) {
+		if (!r->start || pci_claim_bridge_resource(dev, idx) < 0) {
 			/*
 			 * Something is wrong with the region.
 			 * Invalidate the resource to prevent
Index: linux-3.18.13-rt10-r7s4/arch/x86/pci/xen.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/pci/xen.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/pci/xen.c
@@ -452,52 +452,6 @@ int __init pci_xen_hvm_init(void)
 }
 
 #ifdef CONFIG_XEN_DOM0
-static __init void xen_setup_acpi_sci(void)
-{
-	int rc;
-	int trigger, polarity;
-	int gsi = acpi_sci_override_gsi;
-	int irq = -1;
-	int gsi_override = -1;
-
-	if (!gsi)
-		return;
-
-	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
-	if (rc) {
-		printk(KERN_WARNING "xen: acpi_get_override_irq failed for acpi"
-				" sci, rc=%d\n", rc);
-		return;
-	}
-	trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
-	polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
-
-	printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d "
-			"polarity=%d\n", gsi, trigger, polarity);
-
-	/* Before we bind the GSI to a Linux IRQ, check whether
-	 * we need to override it with bus_irq (IRQ) value. Usually for
-	 * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so:
-	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level)
-	 * but there are oddballs where the IRQ != GSI:
-	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level)
-	 * which ends up being: gsi_to_irq[9] == 20
-	 * (which is what acpi_gsi_to_irq ends up calling when starting the
-	 * the ACPI interpreter and keels over since IRQ 9 has not been
-	 * setup as we had setup IRQ 20 for it).
-	 */
-	if (acpi_gsi_to_irq(gsi, &irq) == 0) {
-		/* Use the provided value if it's valid. */
-		if (irq >= 0)
-			gsi_override = irq;
-	}
-
-	gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity);
-	printk(KERN_INFO "xen: acpi sci %d\n", gsi);
-
-	return;
-}
-
 int __init pci_xen_initial_domain(void)
 {
 	int irq;
@@ -509,7 +463,6 @@ int __init pci_xen_initial_domain(void)
 	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
 	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
 #endif
-	xen_setup_acpi_sci();
 	__acpi_register_gsi = acpi_register_gsi_xen;
 	/* Pre-allocate legacy irqs */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++) {
Index: linux-3.18.13-rt10-r7s4/arch/x86/platform/efi/efi_stub_64.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/platform/efi/efi_stub_64.S
+++ linux-3.18.13-rt10-r7s4/arch/x86/platform/efi/efi_stub_64.S
@@ -91,167 +91,6 @@ ENTRY(efi_call)
 	ret
 ENDPROC(efi_call)
 
-#ifdef CONFIG_EFI_MIXED
-
-/*
- * We run this function from the 1:1 mapping.
- *
- * This function must be invoked with a 1:1 mapped stack.
- */
-ENTRY(__efi64_thunk)
-	movl	%ds, %eax
-	push	%rax
-	movl	%es, %eax
-	push	%rax
-	movl	%ss, %eax
-	push	%rax
-
-	subq	$32, %rsp
-	movl	%esi, 0x0(%rsp)
-	movl	%edx, 0x4(%rsp)
-	movl	%ecx, 0x8(%rsp)
-	movq	%r8, %rsi
-	movl	%esi, 0xc(%rsp)
-	movq	%r9, %rsi
-	movl	%esi,  0x10(%rsp)
-
-	sgdt	save_gdt(%rip)
-
-	leaq	1f(%rip), %rbx
-	movq	%rbx, func_rt_ptr(%rip)
-
-	/* Switch to gdt with 32-bit segments */
-	movl	64(%rsp), %eax
-	lgdt	(%rax)
-
-	leaq	efi_enter32(%rip), %rax
-	pushq	$__KERNEL_CS
-	pushq	%rax
-	lretq
-
-1:	addq	$32, %rsp
-
-	lgdt	save_gdt(%rip)
-
-	pop	%rbx
-	movl	%ebx, %ss
-	pop	%rbx
-	movl	%ebx, %es
-	pop	%rbx
-	movl	%ebx, %ds
-
-	/*
-	 * Convert 32-bit status code into 64-bit.
-	 */
-	test	%rax, %rax
-	jz	1f
-	movl	%eax, %ecx
-	andl	$0x0fffffff, %ecx
-	andl	$0xf0000000, %eax
-	shl	$32, %rax
-	or	%rcx, %rax
-1:
-	ret
-ENDPROC(__efi64_thunk)
-
-ENTRY(efi_exit32)
-	movq	func_rt_ptr(%rip), %rax
-	push	%rax
-	mov	%rdi, %rax
-	ret
-ENDPROC(efi_exit32)
-
-	.code32
-/*
- * EFI service pointer must be in %edi.
- *
- * The stack should represent the 32-bit calling convention.
- */
-ENTRY(efi_enter32)
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %es
-	movl	%eax, %ss
-
-	/* Reload pgtables */
-	movl	%cr3, %eax
-	movl	%eax, %cr3
-
-	/* Disable paging */
-	movl	%cr0, %eax
-	btrl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-
-	/* Disable long mode via EFER */
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btrl	$_EFER_LME, %eax
-	wrmsr
-
-	call	*%edi
-
-	/* We must preserve return value */
-	movl	%eax, %edi
-
-	/*
-	 * Some firmware will return with interrupts enabled. Be sure to
-	 * disable them before we switch GDTs.
-	 */
-	cli
-
-	movl	68(%esp), %eax
-	movl	%eax, 2(%eax)
-	lgdtl	(%eax)
-
-	movl	%cr4, %eax
-	btsl	$(X86_CR4_PAE_BIT), %eax
-	movl	%eax, %cr4
-
-	movl	%cr3, %eax
-	movl	%eax, %cr3
-
-	movl	$MSR_EFER, %ecx
-	rdmsr
-	btsl	$_EFER_LME, %eax
-	wrmsr
-
-	xorl	%eax, %eax
-	lldt	%ax
-
-	movl	72(%esp), %eax
-	pushl	$__KERNEL_CS
-	pushl	%eax
-
-	/* Enable paging */
-	movl	%cr0, %eax
-	btsl	$X86_CR0_PG_BIT, %eax
-	movl	%eax, %cr0
-	lret
-ENDPROC(efi_enter32)
-
-	.data
-	.balign	8
-	.global	efi32_boot_gdt
-efi32_boot_gdt:	.word	0
-		.quad	0
-
-save_gdt:	.word	0
-		.quad	0
-func_rt_ptr:	.quad	0
-
-	.global efi_gdt64
-efi_gdt64:
-	.word	efi_gdt64_end - efi_gdt64
-	.long	0			/* Filled out by user */
-	.word	0
-	.quad	0x0000000000000000	/* NULL descriptor */
-	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
-	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
-	.quad	0x0080890000000000	/* TS descriptor */
-	.quad   0x0000000000000000	/* TS continued */
-efi_gdt64_end:
-#endif /* CONFIG_EFI_MIXED */
-
 	.data
 ENTRY(efi_scratch)
 	.fill 3,8,0
Index: linux-3.18.13-rt10-r7s4/arch/x86/platform/efi/efi_thunk_64.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/platform/efi/efi_thunk_64.S
+++ linux-3.18.13-rt10-r7s4/arch/x86/platform/efi/efi_thunk_64.S
@@ -1,9 +1,26 @@
 /*
  * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ *
+ * Support for invoking 32-bit EFI runtime services from a 64-bit
+ * kernel.
+ *
+ * The below thunking functions are only used after ExitBootServices()
+ * has been called. This simplifies things considerably as compared with
+ * the early EFI thunking because we can leave all the kernel state
+ * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime
+ * services from __KERNEL32_CS. This means we can continue to service
+ * interrupts across an EFI mixed mode call.
+ *
+ * We do however, need to handle the fact that we're running in a full
+ * 64-bit virtual address space. Things like the stack and instruction
+ * addresses need to be accessible by the 32-bit firmware, so we rely on
+ * using the identity mappings in the EFI page table to access the stack
+ * and kernel text (see efi_setup_page_tables()).
  */
 
 #include <linux/linkage.h>
 #include <asm/page_types.h>
+#include <asm/segment.h>
 
 	.text
 	.code64
@@ -33,14 +50,6 @@ ENTRY(efi64_thunk)
 	leaq	efi_exit32(%rip), %rbx
 	subq	%rax, %rbx
 	movl	%ebx, 8(%rsp)
-	leaq	efi_gdt64(%rip), %rbx
-	subq	%rax, %rbx
-	movl	%ebx, 2(%ebx)
-	movl	%ebx, 4(%rsp)
-	leaq	efi_gdt32(%rip), %rbx
-	subq	%rax, %rbx
-	movl	%ebx, 2(%ebx)
-	movl	%ebx, (%rsp)
 
 	leaq	__efi64_thunk(%rip), %rbx
 	subq	%rax, %rbx
@@ -52,14 +61,92 @@ ENTRY(efi64_thunk)
 	retq
 ENDPROC(efi64_thunk)
 
-	.data
-efi_gdt32:
-	.word 	efi_gdt32_end - efi_gdt32
-	.long	0			/* Filled out above */
-	.word	0
-	.quad	0x0000000000000000	/* NULL descriptor */
-	.quad	0x00cf9a000000ffff	/* __KERNEL_CS */
-	.quad	0x00cf93000000ffff	/* __KERNEL_DS */
-efi_gdt32_end:
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/* Switch to 32-bit descriptor */
+	pushq	$__KERNEL32_CS
+	leaq	efi_enter32(%rip), %rax
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
 
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	movl	72(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+func_rt_ptr:		.quad 0
 efi_saved_sp:		.quad 0
Index: linux-3.18.13-rt10-r7s4/arch/x86/tools/calc_run_size.pl
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/tools/calc_run_size.pl
+++ /dev/null
@@ -1,39 +0,0 @@
-#!/usr/bin/perl
-#
-# Calculate the amount of space needed to run the kernel, including room for
-# the .bss and .brk sections.
-#
-# Usage:
-# objdump -h a.out | perl calc_run_size.pl
-use strict;
-
-my $mem_size = 0;
-my $file_offset = 0;
-
-my $sections=" *[0-9]+ \.(?:bss|brk) +";
-while (<>) {
-	if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
-		my $size = hex($1);
-		my $offset = hex($2);
-		$mem_size += $size;
-		if ($file_offset == 0) {
-			$file_offset = $offset;
-		} elsif ($file_offset != $offset) {
-			# BFD linker shows the same file offset in ELF.
-			# Gold linker shows them as consecutive.
-			next if ($file_offset + $mem_size == $offset + $size);
-
-			printf STDERR "file_offset: 0x%lx\n", $file_offset;
-			printf STDERR "mem_size: 0x%lx\n", $mem_size;
-			printf STDERR "offset: 0x%lx\n", $offset;
-			printf STDERR "size: 0x%lx\n", $size;
-
-			die ".bss and .brk are non-contiguous\n";
-		}
-	}
-}
-
-if ($file_offset == 0) {
-	die "Never found .bss or .brk file offset\n";
-}
-printf("%d\n", $mem_size + $file_offset);
Index: linux-3.18.13-rt10-r7s4/arch/x86/tools/calc_run_size.sh
===================================================================
--- /dev/null
+++ linux-3.18.13-rt10-r7s4/arch/x86/tools/calc_run_size.sh
@@ -0,0 +1,42 @@
+#!/bin/sh
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | sh calc_run_size.sh
+
+NUM='\([0-9a-fA-F]*[ \t]*\)'
+OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p')
+if [ -z "$OUT" ] ; then
+	echo "Never found .bss or .brk file offset" >&2
+	exit 1
+fi
+
+OUT=$(echo ${OUT# })
+sizeA=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+offsetA=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+sizeB=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+offsetB=$(printf "%d" 0x${OUT%% *})
+
+run_size=$(( $offsetA + $sizeA + $sizeB ))
+
+# BFD linker shows the same file offset in ELF.
+if [ "$offsetA" -ne "$offsetB" ] ; then
+	# Gold linker shows them as consecutive.
+	endB=$(( $offsetB + $sizeB ))
+	if [ "$endB" != "$run_size" ] ; then
+		printf "sizeA: 0x%x\n" $sizeA >&2
+		printf "offsetA: 0x%x\n" $offsetA >&2
+		printf "sizeB: 0x%x\n" $sizeB >&2
+		printf "offsetB: 0x%x\n" $offsetB >&2
+		echo ".bss and .brk are non-contiguous" >&2
+		exit 1
+	fi
+fi
+
+printf "%d\n" $run_size
+exit 0
Index: linux-3.18.13-rt10-r7s4/arch/x86/um/sys_call_table_32.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/um/sys_call_table_32.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/um/sys_call_table_32.c
@@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t
 
 extern asmlinkage void sys_ni_syscall(void);
 
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
Index: linux-3.18.13-rt10-r7s4/arch/x86/um/sys_call_table_64.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/um/sys_call_table_64.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/um/sys_call_table_64.c
@@ -46,7 +46,7 @@ typedef void (*sys_call_ptr_t)(void);
 
 extern void sys_ni_syscall(void);
 
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
Index: linux-3.18.13-rt10-r7s4/arch/x86/vdso/vdso32/sigreturn.S
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/vdso/vdso32/sigreturn.S
+++ linux-3.18.13-rt10-r7s4/arch/x86/vdso/vdso32/sigreturn.S
@@ -17,6 +17,7 @@
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
 	ALIGN
 __kernel_sigreturn:
 .LSTART_sigreturn:
Index: linux-3.18.13-rt10-r7s4/arch/x86/vdso/vma.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/x86/vdso/vma.c
+++ linux-3.18.13-rt10-r7s4/arch/x86/vdso/vma.c
@@ -54,12 +54,17 @@ subsys_initcall(init_vdso);
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits.
-
-   Only used for the 64-bit and x32 vdsos. */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 #ifdef CONFIG_X86_32
@@ -67,22 +72,30 @@ static unsigned long vdso_addr(unsigned
 #else
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;
Index: linux-3.18.13-rt10-r7s4/arch/xtensa/include/asm/highmem.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/xtensa/include/asm/highmem.h
+++ linux-3.18.13-rt10-r7s4/arch/xtensa/include/asm/highmem.h
@@ -25,7 +25,7 @@
 #define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
-#define kmap_prot		PAGE_KERNEL
+#define kmap_prot		PAGE_KERNEL_EXEC
 
 #if DCACHE_WAY_SIZE > PAGE_SIZE
 #define get_pkmap_color get_pkmap_color
Index: linux-3.18.13-rt10-r7s4/arch/xtensa/mm/fault.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/arch/xtensa/mm/fault.c
+++ linux-3.18.13-rt10-r7s4/arch/xtensa/mm/fault.c
@@ -117,6 +117,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
Index: linux-3.18.13-rt10-r7s4/block/blk-core.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-core.c
+++ linux-3.18.13-rt10-r7s4/block/blk-core.c
@@ -525,6 +525,9 @@ void blk_cleanup_queue(struct request_qu
 	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
+	if (q->mq_ops)
+		blk_mq_free_queue(q);
+
 	spin_lock_irq(lock);
 	if (q->queue_lock != &q->__queue_lock)
 		q->queue_lock = &q->__queue_lock;
Index: linux-3.18.13-rt10-r7s4/block/blk-merge.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-merge.c
+++ linux-3.18.13-rt10-r7s4/block/blk-merge.c
@@ -609,7 +609,7 @@ bool blk_rq_merge_ok(struct request *rq,
 	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
 		struct bio_vec *bprev;
 
-		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
 		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
 			return false;
 	}
Index: linux-3.18.13-rt10-r7s4/block/blk-mq-cpumap.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-mq-cpumap.c
+++ linux-3.18.13-rt10-r7s4/block/blk-mq-cpumap.c
@@ -90,7 +90,7 @@ unsigned int *blk_mq_make_queue_map(stru
 	unsigned int *map;
 
 	/* If cpus are offline, map them to first hctx */
-	map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL,
+	map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
 				set->numa_node);
 	if (!map)
 		return NULL;
Index: linux-3.18.13-rt10-r7s4/block/blk-mq-sysfs.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-mq-sysfs.c
+++ linux-3.18.13-rt10-r7s4/block/blk-mq-sysfs.c
@@ -390,16 +390,15 @@ static void blk_mq_sysfs_init(struct req
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
-	int i, j;
+	int i;
 
 	kobject_init(&q->mq_kobj, &blk_mq_ktype);
 
-	queue_for_each_hw_ctx(q, hctx, i) {
+	queue_for_each_hw_ctx(q, hctx, i)
 		kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
 
-		hctx_for_each_ctx(hctx, ctx, j)
-			kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
-	}
+	queue_for_each_ctx(q, ctx, i)
+		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
 }
 
 /* see blk_register_queue() */
Index: linux-3.18.13-rt10-r7s4/block/blk-mq-tag.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-mq-tag.c
+++ linux-3.18.13-rt10-r7s4/block/blk-mq-tag.c
@@ -137,6 +137,7 @@ static inline bool hctx_may_queue(struct
 static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
 {
 	int tag, org_last_tag, end;
+	bool wrap = last_tag != 0;
 
 	org_last_tag = last_tag;
 	end = bm->depth;
@@ -148,15 +149,16 @@ restart:
 			 * We started with an offset, start from 0 to
 			 * exhaust the map.
 			 */
-			if (org_last_tag && last_tag) {
-				end = last_tag;
+			if (wrap) {
+				wrap = false;
+				end = org_last_tag;
 				last_tag = 0;
 				goto restart;
 			}
 			return -1;
 		}
 		last_tag = tag + 1;
-	} while (test_and_set_bit_lock(tag, &bm->word));
+	} while (test_and_set_bit(tag, &bm->word));
 
 	return tag;
 }
@@ -340,11 +342,10 @@ static void bt_clear_tag(struct blk_mq_b
 	struct bt_wait_state *bs;
 	int wait_cnt;
 
-	/*
-	 * The unlock memory barrier need to order access to req in free
-	 * path and clearing tag bit
-	 */
-	clear_bit_unlock(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+	clear_bit(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+
+	/* Ensure that the wait list checks occur after clear_bit(). */
+	smp_mb();
 
 	bs = bt_wake_ptr(bt);
 	if (!bs)
@@ -499,6 +500,7 @@ static int bt_alloc(struct blk_mq_bitmap
 	bt->bs = kzalloc(BT_WAIT_QUEUES * sizeof(*bt->bs), GFP_KERNEL);
 	if (!bt->bs) {
 		kfree(bt->map);
+		bt->map = NULL;
 		return -ENOMEM;
 	}
 
Index: linux-3.18.13-rt10-r7s4/block/blk-mq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-mq.c
+++ linux-3.18.13-rt10-r7s4/block/blk-mq.c
@@ -1831,7 +1831,7 @@ struct request_queue *blk_mq_init_queue(
 	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
 			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_map;
+		goto err_mq_usage;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
 	blk_queue_rq_timeout(q, 30000);
@@ -1874,7 +1874,7 @@ struct request_queue *blk_mq_init_queue(
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_hw;
+		goto err_mq_usage;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1886,7 +1886,7 @@ struct request_queue *blk_mq_init_queue(
 
 	return q;
 
-err_hw:
+err_mq_usage:
 	blk_cleanup_queue(q);
 err_hctxs:
 	kfree(map);
Index: linux-3.18.13-rt10-r7s4/block/blk-sysfs.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-sysfs.c
+++ linux-3.18.13-rt10-r7s4/block/blk-sysfs.c
@@ -492,17 +492,15 @@ static void blk_free_queue_rcu(struct rc
  *     Currently, its primary task it to free all the &struct request
  *     structures that were allocated to the queue and the queue itself.
  *
- * Caveat:
- *     Hopefully the low level driver will have finished any
- *     outstanding requests first...
+ * Note:
+ *     The low level driver must have finished any outstanding requests first
+ *     via blk_cleanup_queue().
  **/
 static void blk_release_queue(struct kobject *kobj)
 {
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
 
-	blk_sync_queue(q);
-
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
@@ -517,9 +515,7 @@ static void blk_release_queue(struct kob
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
-	if (q->mq_ops)
-		blk_mq_free_queue(q);
-	else
+	if (!q->mq_ops)
 		blk_free_flush_queue(q->fq);
 
 	blk_trace_shutdown(q);
Index: linux-3.18.13-rt10-r7s4/block/blk-throttle.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/blk-throttle.c
+++ linux-3.18.13-rt10-r7s4/block/blk-throttle.c
@@ -1292,6 +1292,9 @@ static u64 tg_prfill_cpu_rwstat(struct s
 	struct blkg_rwstat rwstat = { }, tmp;
 	int i, cpu;
 
+	if (tg->stats_cpu == NULL)
+		return 0;
+
 	for_each_possible_cpu(cpu) {
 		struct tg_stats_cpu *sc = per_cpu_ptr(tg->stats_cpu, cpu);
 
Index: linux-3.18.13-rt10-r7s4/block/cfq-iosched.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/cfq-iosched.c
+++ linux-3.18.13-rt10-r7s4/block/cfq-iosched.c
@@ -3590,6 +3590,11 @@ retry:
 
 	blkcg = bio_blkcg(bio);
 	cfqg = cfq_lookup_create_cfqg(cfqd, blkcg);
+	if (!cfqg) {
+		cfqq = &cfqd->oom_cfqq;
+		goto out;
+	}
+
 	cfqq = cic_to_cfqq(cic, is_sync);
 
 	/*
@@ -3626,7 +3631,7 @@ retry:
 		} else
 			cfqq = &cfqd->oom_cfqq;
 	}
-
+out:
 	if (new_cfqq)
 		kmem_cache_free(cfq_pool, new_cfqq);
 
@@ -3656,12 +3661,17 @@ static struct cfq_queue *
 cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 	      struct bio *bio, gfp_t gfp_mask)
 {
-	const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
-	const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
+	int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
+	int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
 	struct cfq_queue **async_cfqq = NULL;
 	struct cfq_queue *cfqq = NULL;
 
 	if (!is_sync) {
+		if (!ioprio_valid(cic->ioprio)) {
+			struct task_struct *tsk = current;
+			ioprio = task_nice_ioprio(tsk);
+			ioprio_class = task_nice_ioclass(tsk);
+		}
 		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
 		cfqq = *async_cfqq;
 	}
Index: linux-3.18.13-rt10-r7s4/block/genhd.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/block/genhd.c
+++ linux-3.18.13-rt10-r7s4/block/genhd.c
@@ -1070,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
 	struct disk_part_tbl *new_ptbl;
 	int len = old_ptbl ? old_ptbl->len : 0;
-	int target = partno + 1;
+	int i, target;
 	size_t size;
-	int i;
+
+	/*
+	 * check for int overflow, since we can get here from blkpg_ioctl()
+	 * with a user passed 'partno'.
+	 */
+	target = partno + 1;
+	if (target < 0)
+		return -EINVAL;
 
 	/* disk_max_parts() is zero during initialization, ignore if so */
 	if (disk_max_parts(disk) && target > disk_max_parts(disk))
Index: linux-3.18.13-rt10-r7s4/crypto/842.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/842.c
+++ linux-3.18.13-rt10-r7s4/crypto/842.c
@@ -180,3 +180,4 @@ module_exit(nx842_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("842 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("842");
Index: linux-3.18.13-rt10-r7s4/crypto/aes_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/aes_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/aes_generic.c
@@ -1474,4 +1474,5 @@ module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/af_alg.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/af_alg.c
+++ linux-3.18.13-rt10-r7s4/crypto/af_alg.c
@@ -449,6 +449,9 @@ void af_alg_complete(struct crypto_async
 {
 	struct af_alg_completion *completion = req->data;
 
+	if (err == -EINPROGRESS)
+		return;
+
 	completion->err = err;
 	complete(&completion->completion);
 }
Index: linux-3.18.13-rt10-r7s4/crypto/algapi.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/algapi.c
+++ linux-3.18.13-rt10-r7s4/crypto/algapi.c
@@ -509,8 +509,8 @@ static struct crypto_template *__crypto_
 
 struct crypto_template *crypto_lookup_template(const char *name)
 {
-	return try_then_request_module(__crypto_lookup_template(name), "%s",
-				       name);
+	return try_then_request_module(__crypto_lookup_template(name),
+				       "crypto-%s", name);
 }
 EXPORT_SYMBOL_GPL(crypto_lookup_template);
 
Index: linux-3.18.13-rt10-r7s4/crypto/ansi_cprng.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/ansi_cprng.c
+++ linux-3.18.13-rt10-r7s4/crypto/ansi_cprng.c
@@ -476,4 +476,5 @@ module_param(dbg, int, 0);
 MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)");
 module_init(prng_mod_init);
 module_exit(prng_mod_fini);
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_ALIAS_CRYPTO("ansi_cprng");
Index: linux-3.18.13-rt10-r7s4/crypto/anubis.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/anubis.c
+++ linux-3.18.13-rt10-r7s4/crypto/anubis.c
@@ -704,3 +704,4 @@ module_exit(anubis_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Anubis Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("anubis");
Index: linux-3.18.13-rt10-r7s4/crypto/api.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/api.c
+++ linux-3.18.13-rt10-r7s4/crypto/api.c
@@ -216,11 +216,11 @@ struct crypto_alg *crypto_larval_lookup(
 
 	alg = crypto_alg_lookup(name, type, mask);
 	if (!alg) {
-		request_module("%s", name);
+		request_module("crypto-%s", name);
 
 		if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask &
 		      CRYPTO_ALG_NEED_FALLBACK))
-			request_module("%s-all", name);
+			request_module("crypto-%s-all", name);
 
 		alg = crypto_alg_lookup(name, type, mask);
 	}
Index: linux-3.18.13-rt10-r7s4/crypto/arc4.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/arc4.c
+++ linux-3.18.13-rt10-r7s4/crypto/arc4.c
@@ -166,3 +166,4 @@ module_exit(arc4_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("ARC4 Cipher Algorithm");
 MODULE_AUTHOR("Jon Oberheide <jon@oberheide.org>");
+MODULE_ALIAS_CRYPTO("arc4");
Index: linux-3.18.13-rt10-r7s4/crypto/authenc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/authenc.c
+++ linux-3.18.13-rt10-r7s4/crypto/authenc.c
@@ -721,3 +721,4 @@ module_exit(crypto_authenc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Simple AEAD wrapper for IPsec");
+MODULE_ALIAS_CRYPTO("authenc");
Index: linux-3.18.13-rt10-r7s4/crypto/authencesn.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/authencesn.c
+++ linux-3.18.13-rt10-r7s4/crypto/authencesn.c
@@ -814,3 +814,4 @@ module_exit(crypto_authenc_esn_module_ex
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
 MODULE_DESCRIPTION("AEAD wrapper for IPsec with extended sequence numbers");
+MODULE_ALIAS_CRYPTO("authencesn");
Index: linux-3.18.13-rt10-r7s4/crypto/blowfish_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/blowfish_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/blowfish_generic.c
@@ -138,4 +138,5 @@ module_exit(blowfish_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Blowfish Cipher Algorithm");
-MODULE_ALIAS("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/camellia_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/camellia_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/camellia_generic.c
@@ -1098,4 +1098,5 @@ module_exit(camellia_fini);
 
 MODULE_DESCRIPTION("Camellia Cipher Algorithm");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("camellia");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/cast5_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/cast5_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/cast5_generic.c
@@ -549,4 +549,5 @@ module_exit(cast5_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cast5 Cipher Algorithm");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
+MODULE_ALIAS_CRYPTO("cast5-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/cast6_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/cast6_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/cast6_generic.c
@@ -291,4 +291,5 @@ module_exit(cast6_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Cast6 Cipher Algorithm");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
+MODULE_ALIAS_CRYPTO("cast6-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/cbc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/cbc.c
+++ linux-3.18.13-rt10-r7s4/crypto/cbc.c
@@ -289,3 +289,4 @@ module_exit(crypto_cbc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CBC block cipher algorithm");
+MODULE_ALIAS_CRYPTO("cbc");
Index: linux-3.18.13-rt10-r7s4/crypto/ccm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/ccm.c
+++ linux-3.18.13-rt10-r7s4/crypto/ccm.c
@@ -879,5 +879,6 @@ module_exit(crypto_ccm_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Counter with CBC MAC");
-MODULE_ALIAS("ccm_base");
-MODULE_ALIAS("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm_base");
+MODULE_ALIAS_CRYPTO("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm");
Index: linux-3.18.13-rt10-r7s4/crypto/chainiv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/chainiv.c
+++ linux-3.18.13-rt10-r7s4/crypto/chainiv.c
@@ -359,3 +359,4 @@ module_exit(chainiv_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Chain IV Generator");
+MODULE_ALIAS_CRYPTO("chainiv");
Index: linux-3.18.13-rt10-r7s4/crypto/cmac.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/cmac.c
+++ linux-3.18.13-rt10-r7s4/crypto/cmac.c
@@ -313,3 +313,4 @@ module_exit(crypto_cmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CMAC keyed hash algorithm");
+MODULE_ALIAS_CRYPTO("cmac");
Index: linux-3.18.13-rt10-r7s4/crypto/crc32.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/crc32.c
+++ linux-3.18.13-rt10-r7s4/crypto/crc32.c
@@ -156,3 +156,4 @@ module_exit(crc32_mod_fini);
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32");
Index: linux-3.18.13-rt10-r7s4/crypto/crc32c_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/crc32c_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/crc32c_generic.c
@@ -170,5 +170,6 @@ module_exit(crc32c_mod_fini);
 MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
 MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-generic");
 MODULE_SOFTDEP("pre: crc32c");
Index: linux-3.18.13-rt10-r7s4/crypto/crct10dif_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/crct10dif_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/crct10dif_generic.c
@@ -124,4 +124,5 @@ module_exit(crct10dif_mod_fini);
 MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
 MODULE_DESCRIPTION("T10 DIF CRC calculation.");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/cryptd.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/cryptd.c
+++ linux-3.18.13-rt10-r7s4/crypto/cryptd.c
@@ -955,3 +955,4 @@ module_exit(cryptd_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Software async crypto daemon");
+MODULE_ALIAS_CRYPTO("cryptd");
Index: linux-3.18.13-rt10-r7s4/crypto/crypto_null.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/crypto_null.c
+++ linux-3.18.13-rt10-r7s4/crypto/crypto_null.c
@@ -145,9 +145,9 @@ static struct crypto_alg null_algs[3] =
 	.coa_decompress		=	null_compress } }
 } };
 
-MODULE_ALIAS("compress_null");
-MODULE_ALIAS("digest_null");
-MODULE_ALIAS("cipher_null");
+MODULE_ALIAS_CRYPTO("compress_null");
+MODULE_ALIAS_CRYPTO("digest_null");
+MODULE_ALIAS_CRYPTO("cipher_null");
 
 static int __init crypto_null_mod_init(void)
 {
Index: linux-3.18.13-rt10-r7s4/crypto/ctr.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/ctr.c
+++ linux-3.18.13-rt10-r7s4/crypto/ctr.c
@@ -466,4 +466,5 @@ module_exit(crypto_ctr_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CTR Counter block mode");
-MODULE_ALIAS("rfc3686");
+MODULE_ALIAS_CRYPTO("rfc3686");
+MODULE_ALIAS_CRYPTO("ctr");
Index: linux-3.18.13-rt10-r7s4/crypto/cts.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/cts.c
+++ linux-3.18.13-rt10-r7s4/crypto/cts.c
@@ -351,3 +351,4 @@ module_exit(crypto_cts_module_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("CTS-CBC CipherText Stealing for CBC");
+MODULE_ALIAS_CRYPTO("cts");
Index: linux-3.18.13-rt10-r7s4/crypto/deflate.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/deflate.c
+++ linux-3.18.13-rt10-r7s4/crypto/deflate.c
@@ -222,4 +222,4 @@ module_exit(deflate_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP");
 MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
-
+MODULE_ALIAS_CRYPTO("deflate");
Index: linux-3.18.13-rt10-r7s4/crypto/des_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/des_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/des_generic.c
@@ -983,8 +983,6 @@ static struct crypto_alg des_algs[2] = {
 	.cia_decrypt		=	des3_ede_decrypt } }
 } };
 
-MODULE_ALIAS("des3_ede");
-
 static int __init des_generic_mod_init(void)
 {
 	return crypto_register_algs(des_algs, ARRAY_SIZE(des_algs));
@@ -1001,4 +999,7 @@ module_exit(des_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
 MODULE_AUTHOR("Dag Arne Osvik <da@osvik.no>");
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-generic");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/ecb.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/ecb.c
+++ linux-3.18.13-rt10-r7s4/crypto/ecb.c
@@ -185,3 +185,4 @@ module_exit(crypto_ecb_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("ECB block cipher algorithm");
+MODULE_ALIAS_CRYPTO("ecb");
Index: linux-3.18.13-rt10-r7s4/crypto/eseqiv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/eseqiv.c
+++ linux-3.18.13-rt10-r7s4/crypto/eseqiv.c
@@ -267,3 +267,4 @@ module_exit(eseqiv_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator");
+MODULE_ALIAS_CRYPTO("eseqiv");
Index: linux-3.18.13-rt10-r7s4/crypto/fcrypt.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/fcrypt.c
+++ linux-3.18.13-rt10-r7s4/crypto/fcrypt.c
@@ -420,3 +420,4 @@ module_exit(fcrypt_mod_fini);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("FCrypt Cipher Algorithm");
 MODULE_AUTHOR("David Howells <dhowells@redhat.com>");
+MODULE_ALIAS_CRYPTO("fcrypt");
Index: linux-3.18.13-rt10-r7s4/crypto/gcm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/gcm.c
+++ linux-3.18.13-rt10-r7s4/crypto/gcm.c
@@ -1441,6 +1441,7 @@ module_exit(crypto_gcm_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Galois/Counter Mode");
 MODULE_AUTHOR("Mikko Herranen <mh1@iki.fi>");
-MODULE_ALIAS("gcm_base");
-MODULE_ALIAS("rfc4106");
-MODULE_ALIAS("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm_base");
+MODULE_ALIAS_CRYPTO("rfc4106");
+MODULE_ALIAS_CRYPTO("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm");
Index: linux-3.18.13-rt10-r7s4/crypto/ghash-generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/ghash-generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/ghash-generic.c
@@ -172,4 +172,5 @@ module_exit(ghash_mod_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("GHASH Message Digest Algorithm");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
+MODULE_ALIAS_CRYPTO("ghash-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/hmac.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/hmac.c
+++ linux-3.18.13-rt10-r7s4/crypto/hmac.c
@@ -268,3 +268,4 @@ module_exit(hmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("HMAC hash algorithm");
+MODULE_ALIAS_CRYPTO("hmac");
Index: linux-3.18.13-rt10-r7s4/crypto/khazad.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/khazad.c
+++ linux-3.18.13-rt10-r7s4/crypto/khazad.c
@@ -880,3 +880,4 @@ module_exit(khazad_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Khazad Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("khazad");
Index: linux-3.18.13-rt10-r7s4/crypto/krng.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/krng.c
+++ linux-3.18.13-rt10-r7s4/crypto/krng.c
@@ -62,4 +62,5 @@ module_exit(krng_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Kernel Random Number Generator");
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_ALIAS_CRYPTO("krng");
Index: linux-3.18.13-rt10-r7s4/crypto/lrw.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/lrw.c
+++ linux-3.18.13-rt10-r7s4/crypto/lrw.c
@@ -400,3 +400,4 @@ module_exit(crypto_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LRW block cipher mode");
+MODULE_ALIAS_CRYPTO("lrw");
Index: linux-3.18.13-rt10-r7s4/crypto/lz4.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/lz4.c
+++ linux-3.18.13-rt10-r7s4/crypto/lz4.c
@@ -104,3 +104,4 @@ module_exit(lz4_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZ4 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4");
Index: linux-3.18.13-rt10-r7s4/crypto/lz4hc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/lz4hc.c
+++ linux-3.18.13-rt10-r7s4/crypto/lz4hc.c
@@ -104,3 +104,4 @@ module_exit(lz4hc_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZ4HC Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4hc");
Index: linux-3.18.13-rt10-r7s4/crypto/lzo.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/lzo.c
+++ linux-3.18.13-rt10-r7s4/crypto/lzo.c
@@ -107,3 +107,4 @@ module_exit(lzo_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("LZO Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lzo");
Index: linux-3.18.13-rt10-r7s4/crypto/mcryptd.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/mcryptd.c
+++ linux-3.18.13-rt10-r7s4/crypto/mcryptd.c
@@ -703,3 +703,4 @@ module_exit(mcryptd_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Software async multibuffer crypto daemon");
+MODULE_ALIAS_CRYPTO("mcryptd");
Index: linux-3.18.13-rt10-r7s4/crypto/md4.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/md4.c
+++ linux-3.18.13-rt10-r7s4/crypto/md4.c
@@ -255,4 +255,4 @@ module_exit(md4_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD4 Message Digest Algorithm");
-
+MODULE_ALIAS_CRYPTO("md4");
Index: linux-3.18.13-rt10-r7s4/crypto/md5.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/md5.c
+++ linux-3.18.13-rt10-r7s4/crypto/md5.c
@@ -168,3 +168,4 @@ module_exit(md5_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD5 Message Digest Algorithm");
+MODULE_ALIAS_CRYPTO("md5");
Index: linux-3.18.13-rt10-r7s4/crypto/michael_mic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/michael_mic.c
+++ linux-3.18.13-rt10-r7s4/crypto/michael_mic.c
@@ -184,3 +184,4 @@ module_exit(michael_mic_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Michael MIC");
 MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
+MODULE_ALIAS_CRYPTO("michael_mic");
Index: linux-3.18.13-rt10-r7s4/crypto/pcbc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/pcbc.c
+++ linux-3.18.13-rt10-r7s4/crypto/pcbc.c
@@ -295,3 +295,4 @@ module_exit(crypto_pcbc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCBC block cipher algorithm");
+MODULE_ALIAS_CRYPTO("pcbc");
Index: linux-3.18.13-rt10-r7s4/crypto/pcrypt.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/pcrypt.c
+++ linux-3.18.13-rt10-r7s4/crypto/pcrypt.c
@@ -565,3 +565,4 @@ module_exit(pcrypt_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
 MODULE_DESCRIPTION("Parallel crypto wrapper");
+MODULE_ALIAS_CRYPTO("pcrypt");
Index: linux-3.18.13-rt10-r7s4/crypto/rmd128.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/rmd128.c
+++ linux-3.18.13-rt10-r7s4/crypto/rmd128.c
@@ -327,3 +327,4 @@ module_exit(rmd128_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-128 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd128");
Index: linux-3.18.13-rt10-r7s4/crypto/rmd160.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/rmd160.c
+++ linux-3.18.13-rt10-r7s4/crypto/rmd160.c
@@ -371,3 +371,4 @@ module_exit(rmd160_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-160 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd160");
Index: linux-3.18.13-rt10-r7s4/crypto/rmd256.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/rmd256.c
+++ linux-3.18.13-rt10-r7s4/crypto/rmd256.c
@@ -346,3 +346,4 @@ module_exit(rmd256_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd256");
Index: linux-3.18.13-rt10-r7s4/crypto/rmd320.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/rmd320.c
+++ linux-3.18.13-rt10-r7s4/crypto/rmd320.c
@@ -395,3 +395,4 @@ module_exit(rmd320_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
 MODULE_DESCRIPTION("RIPEMD-320 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd320");
Index: linux-3.18.13-rt10-r7s4/crypto/salsa20_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/salsa20_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/salsa20_generic.c
@@ -248,4 +248,5 @@ module_exit(salsa20_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm");
-MODULE_ALIAS("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/seed.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/seed.c
+++ linux-3.18.13-rt10-r7s4/crypto/seed.c
@@ -476,3 +476,4 @@ module_exit(seed_fini);
 MODULE_DESCRIPTION("SEED Cipher Algorithm");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Hye-Shik Chang <perky@FreeBSD.org>, Kim Hyun <hkim@kisa.or.kr>");
+MODULE_ALIAS_CRYPTO("seed");
Index: linux-3.18.13-rt10-r7s4/crypto/seqiv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/seqiv.c
+++ linux-3.18.13-rt10-r7s4/crypto/seqiv.c
@@ -362,3 +362,4 @@ module_exit(seqiv_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Sequence Number IV Generator");
+MODULE_ALIAS_CRYPTO("seqiv");
Index: linux-3.18.13-rt10-r7s4/crypto/serpent_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/serpent_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/serpent_generic.c
@@ -665,5 +665,6 @@ module_exit(serpent_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm");
 MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>");
-MODULE_ALIAS("tnepres");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("tnepres");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/sha1_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/sha1_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/sha1_generic.c
@@ -153,4 +153,5 @@ module_exit(sha1_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/sha256_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/sha256_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/sha256_generic.c
@@ -384,5 +384,7 @@ module_exit(sha256_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm");
 
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha224-generic");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha256-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/sha512_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/sha512_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/sha512_generic.c
@@ -288,5 +288,7 @@ module_exit(sha512_generic_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms");
 
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha384-generic");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha512-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/tea.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/tea.c
+++ linux-3.18.13-rt10-r7s4/crypto/tea.c
@@ -270,8 +270,9 @@ static void __exit tea_mod_fini(void)
 	crypto_unregister_algs(tea_algs, ARRAY_SIZE(tea_algs));
 }
 
-MODULE_ALIAS("xtea");
-MODULE_ALIAS("xeta");
+MODULE_ALIAS_CRYPTO("tea");
+MODULE_ALIAS_CRYPTO("xtea");
+MODULE_ALIAS_CRYPTO("xeta");
 
 module_init(tea_mod_init);
 module_exit(tea_mod_fini);
Index: linux-3.18.13-rt10-r7s4/crypto/tgr192.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/tgr192.c
+++ linux-3.18.13-rt10-r7s4/crypto/tgr192.c
@@ -676,8 +676,9 @@ static void __exit tgr192_mod_fini(void)
 	crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs));
 }
 
-MODULE_ALIAS("tgr160");
-MODULE_ALIAS("tgr128");
+MODULE_ALIAS_CRYPTO("tgr192");
+MODULE_ALIAS_CRYPTO("tgr160");
+MODULE_ALIAS_CRYPTO("tgr128");
 
 module_init(tgr192_mod_init);
 module_exit(tgr192_mod_fini);
Index: linux-3.18.13-rt10-r7s4/crypto/twofish_generic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/twofish_generic.c
+++ linux-3.18.13-rt10-r7s4/crypto/twofish_generic.c
@@ -211,4 +211,5 @@ module_exit(twofish_mod_fini);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION ("Twofish Cipher Algorithm");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-generic");
Index: linux-3.18.13-rt10-r7s4/crypto/vmac.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/vmac.c
+++ linux-3.18.13-rt10-r7s4/crypto/vmac.c
@@ -713,3 +713,4 @@ module_exit(vmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VMAC hash algorithm");
+MODULE_ALIAS_CRYPTO("vmac");
Index: linux-3.18.13-rt10-r7s4/crypto/wp512.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/wp512.c
+++ linux-3.18.13-rt10-r7s4/crypto/wp512.c
@@ -1167,8 +1167,9 @@ static void __exit wp512_mod_fini(void)
 	crypto_unregister_shashes(wp_algs, ARRAY_SIZE(wp_algs));
 }
 
-MODULE_ALIAS("wp384");
-MODULE_ALIAS("wp256");
+MODULE_ALIAS_CRYPTO("wp512");
+MODULE_ALIAS_CRYPTO("wp384");
+MODULE_ALIAS_CRYPTO("wp256");
 
 module_init(wp512_mod_init);
 module_exit(wp512_mod_fini);
Index: linux-3.18.13-rt10-r7s4/crypto/xcbc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/xcbc.c
+++ linux-3.18.13-rt10-r7s4/crypto/xcbc.c
@@ -286,3 +286,4 @@ module_exit(crypto_xcbc_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("XCBC keyed hash algorithm");
+MODULE_ALIAS_CRYPTO("xcbc");
Index: linux-3.18.13-rt10-r7s4/crypto/xts.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/xts.c
+++ linux-3.18.13-rt10-r7s4/crypto/xts.c
@@ -362,3 +362,4 @@ module_exit(crypto_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("XTS block cipher mode");
+MODULE_ALIAS_CRYPTO("xts");
Index: linux-3.18.13-rt10-r7s4/crypto/zlib.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/crypto/zlib.c
+++ linux-3.18.13-rt10-r7s4/crypto/zlib.c
@@ -378,3 +378,4 @@ module_exit(zlib_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Zlib Compression Algorithm");
 MODULE_AUTHOR("Sony Corporation");
+MODULE_ALIAS_CRYPTO("zlib");
Index: linux-3.18.13-rt10-r7s4/drivers/acpi/acpi_lpss.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/acpi/acpi_lpss.c
+++ linux-3.18.13-rt10-r7s4/drivers/acpi/acpi_lpss.c
@@ -65,6 +65,7 @@ struct lpss_private_data;
 
 struct lpss_device_desc {
 	unsigned int flags;
+	const char *clk_con_id;
 	unsigned int prv_offset;
 	size_t prv_size_override;
 	void (*setup)(struct lpss_private_data *pdata);
@@ -105,7 +106,7 @@ static void lpss_uart_setup(struct lpss_
 	}
 }
 
-static void byt_i2c_setup(struct lpss_private_data *pdata)
+static void lpss_deassert_reset(struct lpss_private_data *pdata)
 {
 	unsigned int offset;
 	u32 val;
@@ -114,9 +115,18 @@ static void byt_i2c_setup(struct lpss_pr
 	val = readl(pdata->mmio_base + offset);
 	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
 	writel(val, pdata->mmio_base + offset);
+}
+
+#define LPSS_I2C_ENABLE			0x6c
+
+static void byt_i2c_setup(struct lpss_private_data *pdata)
+{
+	lpss_deassert_reset(pdata);
 
 	if (readl(pdata->mmio_base + pdata->dev_desc->prv_offset))
 		pdata->fixed_clk_rate = 133000000;
+
+	writel(0, pdata->mmio_base + LPSS_I2C_ENABLE);
 }
 
 static struct lpss_device_desc lpt_dev_desc = {
@@ -131,6 +141,7 @@ static struct lpss_device_desc lpt_i2c_d
 
 static struct lpss_device_desc lpt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
+	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
@@ -147,6 +158,7 @@ static struct lpss_device_desc byt_pwm_d
 
 static struct lpss_device_desc byt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
@@ -166,6 +178,12 @@ static struct lpss_device_desc byt_i2c_d
 	.setup = byt_i2c_setup,
 };
 
+static struct lpss_device_desc bsw_spi_dev_desc = {
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
+	.prv_offset = 0x400,
+	.setup = lpss_deassert_reset,
+};
+
 #else
 
 #define LPSS_ADDR(desc) (0UL)
@@ -198,7 +216,7 @@ static const struct acpi_device_id acpi_
 	/* Braswell LPSS devices */
 	{ "80862288", LPSS_ADDR(byt_pwm_dev_desc) },
 	{ "8086228A", LPSS_ADDR(byt_uart_dev_desc) },
-	{ "8086228E", LPSS_ADDR(byt_spi_dev_desc) },
+	{ "8086228E", LPSS_ADDR(bsw_spi_dev_desc) },
 	{ "808622C1", LPSS_ADDR(byt_i2c_dev_desc) },
 
 	{ "INT3430", LPSS_ADDR(lpt_dev_desc) },
@@ -298,7 +316,7 @@ out:
 		return PTR_ERR(clk);
 
 	pdata->clk = clk;
-	clk_register_clkdev(clk, NULL, devname);
+	clk_register_clkdev(clk, dev_desc->clk_con_id, devname);
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/acpi/device_pm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/acpi/device_pm.c
+++ linux-3.18.13-rt10-r7s4/drivers/acpi/device_pm.c
@@ -257,7 +257,7 @@ int acpi_bus_init_power(struct acpi_devi
 
 	device->power.state = ACPI_STATE_UNKNOWN;
 	if (!acpi_device_is_present(device))
-		return 0;
+		return -ENXIO;
 
 	result = acpi_device_get_power(device, &state);
 	if (result)
@@ -680,13 +680,21 @@ static int acpi_device_wakeup(struct acp
 		if (error)
 			return error;
 
+		if (adev->wakeup.flags.enabled)
+			return 0;
+
 		res = acpi_enable_gpe(wakeup->gpe_device, wakeup->gpe_number);
-		if (ACPI_FAILURE(res)) {
+		if (ACPI_SUCCESS(res)) {
+			adev->wakeup.flags.enabled = 1;
+		} else {
 			acpi_disable_wakeup_device_power(adev);
 			return -EIO;
 		}
 	} else {
-		acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+		if (adev->wakeup.flags.enabled) {
+			acpi_disable_gpe(wakeup->gpe_device, wakeup->gpe_number);
+			adev->wakeup.flags.enabled = 0;
+		}
 		acpi_disable_wakeup_device_power(adev);
 	}
 	return 0;
Index: linux-3.18.13-rt10-r7s4/drivers/acpi/processor_idle.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/acpi/processor_idle.c
+++ linux-3.18.13-rt10-r7s4/drivers/acpi/processor_idle.c
@@ -962,7 +962,7 @@ static int acpi_processor_setup_cpuidle_
 		return -EINVAL;
 
 	drv->safe_state_index = -1;
-	for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
+	for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) {
 		drv->states[i].name[0] = '\0';
 		drv->states[i].desc[0] = '\0';
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/acpi/scan.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/acpi/scan.c
+++ linux-3.18.13-rt10-r7s4/drivers/acpi/scan.c
@@ -909,7 +909,7 @@ static void acpi_free_power_resources_li
 	if (device->wakeup.flags.valid)
 		acpi_power_resources_list_free(&device->wakeup.resources);
 
-	if (!device->flags.power_manageable)
+	if (!device->power.flags.power_resources)
 		return;
 
 	for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) {
@@ -1631,10 +1631,8 @@ static void acpi_bus_get_power_flags(str
 			device->power.flags.power_resources)
 		device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1;
 
-	if (acpi_bus_init_power(device)) {
-		acpi_free_power_resources_lists(device);
+	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
-	}
 }
 
 static void acpi_bus_get_flags(struct acpi_device *device)
@@ -2202,13 +2200,18 @@ static void acpi_bus_attach(struct acpi_
 	/* Skip devices that are not present. */
 	if (!acpi_device_is_present(device)) {
 		device->flags.visited = false;
+		device->flags.power_manageable = 0;
 		return;
 	}
 	if (device->handler)
 		goto ok;
 
 	if (!device->flags.initialized) {
-		acpi_bus_update_power(device, NULL);
+		device->flags.power_manageable =
+			device->power.states[ACPI_STATE_D0].flags.valid;
+		if (acpi_bus_init_power(device))
+			device->flags.power_manageable = 0;
+
 		device->flags.initialized = true;
 	}
 	device->flags.visited = false;
Index: linux-3.18.13-rt10-r7s4/drivers/acpi/video.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/acpi/video.c
+++ linux-3.18.13-rt10-r7s4/drivers/acpi/video.c
@@ -155,6 +155,7 @@ struct acpi_video_bus {
 	u8 dos_setting;
 	struct acpi_video_enumerated_device *attached_array;
 	u8 attached_count;
+	u8 child_count;
 	struct acpi_video_bus_cap cap;
 	struct acpi_video_bus_flags flags;
 	struct list_head video_device_list;
@@ -504,6 +505,23 @@ static struct dmi_system_id video_dmi_ta
 		DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY 15 Notebook PC"),
 		},
 	},
+
+	{
+	 .callback = video_disable_native_backlight,
+	 .ident = "SAMSUNG 870Z5E/880Z5E/680Z5E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "870Z5E/880Z5E/680Z5E"),
+		},
+	},
+	{
+	 .callback = video_disable_native_backlight,
+	 .ident = "SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "370R4E/370R4V/370R5E/3570RE/370R5V"),
+		},
+	},
 	{}
 };
 
@@ -1159,8 +1177,12 @@ static bool acpi_video_device_in_dod(str
 	struct acpi_video_bus *video = device->video;
 	int i;
 
-	/* If we have a broken _DOD, no need to test */
-	if (!video->attached_count)
+	/*
+	 * If we have a broken _DOD or we have more than 8 output devices
+	 * under the graphics controller node that we can't proper deal with
+	 * in the operation region code currently, no need to test.
+	 */
+	if (!video->attached_count || video->child_count > 8)
 		return true;
 
 	for (i = 0; i < video->attached_count; i++) {
@@ -1413,6 +1435,7 @@ acpi_video_bus_get_devices(struct acpi_v
 			dev_err(&dev->dev, "Can't attach device\n");
 			break;
 		}
+		video->child_count++;
 	}
 	return status;
 }
@@ -2101,6 +2124,17 @@ EXPORT_SYMBOL(acpi_video_unregister_back
 
 static int __init acpi_video_init(void)
 {
+	/*
+	 * Let the module load even if ACPI is disabled (e.g. due to
+	 * a broken BIOS) so that i915.ko can still be loaded on such
+	 * old systems without an AcpiOpRegion.
+	 *
+	 * acpi_video_register() will report -ENODEV later as well due
+	 * to acpi_disabled when i915.ko tries to register itself afterwards.
+	 */
+	if (acpi_disabled)
+		return 0;
+
 	dmi_check_system(video_dmi_table);
 
 	if (intel_opregion_present())
Index: linux-3.18.13-rt10-r7s4/drivers/ata/ahci_xgene.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/ata/ahci_xgene.c
+++ linux-3.18.13-rt10-r7s4/drivers/ata/ahci_xgene.c
@@ -188,7 +188,7 @@ static unsigned int xgene_ahci_read_id(s
 	 *
 	 * Clear reserved bit 8 (DEVSLP bit) as we don't support DEVSLP
 	 */
-	id[ATA_ID_FEATURE_SUPP] &= ~(1 << 8);
+	id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
 
 	return 0;
 }
Index: linux-3.18.13-rt10-r7s4/drivers/ata/libata-core.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/ata/libata-core.c
+++ linux-3.18.13-rt10-r7s4/drivers/ata/libata-core.c
@@ -4740,7 +4740,10 @@ static struct ata_queued_cmd *ata_qc_new
 		return NULL;
 
 	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
-		tag = tag < max_queue ? tag : 0;
+		if (ap->flags & ATA_FLAG_LOWTAG)
+			tag = i;
+		else
+			tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
 		if (tag == ATA_TAG_INTERNAL)
Index: linux-3.18.13-rt10-r7s4/drivers/ata/libata-sff.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/ata/libata-sff.c
+++ linux-3.18.13-rt10-r7s4/drivers/ata/libata-sff.c
@@ -1333,7 +1333,19 @@ void ata_sff_flush_pio_task(struct ata_p
 	DPRINTK("ENTER\n");
 
 	cancel_delayed_work_sync(&ap->sff_pio_task);
+
+	/*
+	 * We wanna reset the HSM state to IDLE.  If we do so without
+	 * grabbing the port lock, critical sections protected by it which
+	 * expect the HSM state to stay stable may get surprised.  For
+	 * example, we may set IDLE in between the time
+	 * __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls
+	 * ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG().
+	 */
+	spin_lock_irq(ap->lock);
 	ap->hsm_task_state = HSM_ST_IDLE;
+	spin_unlock_irq(ap->lock);
+
 	ap->sff_pio_task_link = NULL;
 
 	if (ata_msg_ctl(ap))
Index: linux-3.18.13-rt10-r7s4/drivers/ata/sata_dwc_460ex.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/ata/sata_dwc_460ex.c
+++ linux-3.18.13-rt10-r7s4/drivers/ata/sata_dwc_460ex.c
@@ -797,7 +797,7 @@ static int dma_dwc_init(struct sata_dwc_
 	if (err) {
 		dev_err(host_pvt.dwc_dev, "%s: dma_request_interrupts returns"
 			" %d\n", __func__, err);
-		goto error_out;
+		return err;
 	}
 
 	/* Enabe DMA */
@@ -808,11 +808,6 @@ static int dma_dwc_init(struct sata_dwc_
 		sata_dma_regs);
 
 	return 0;
-
-error_out:
-	dma_dwc_exit(hsdev);
-
-	return err;
 }
 
 static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val)
@@ -1662,7 +1657,7 @@ static int sata_dwc_probe(struct platfor
 	char *ver = (char *)&versionr;
 	u8 *base = NULL;
 	int err = 0;
-	int irq, rc;
+	int irq;
 	struct ata_host *host;
 	struct ata_port_info pi = sata_dwc_port_info[0];
 	const struct ata_port_info *ppi[] = { &pi, NULL };
@@ -1725,7 +1720,7 @@ static int sata_dwc_probe(struct platfor
 	if (irq == NO_IRQ) {
 		dev_err(&ofdev->dev, "no SATA DMA irq\n");
 		err = -ENODEV;
-		goto error_out;
+		goto error_iomap;
 	}
 
 	/* Get physical SATA DMA register base address */
@@ -1734,14 +1729,16 @@ static int sata_dwc_probe(struct platfor
 		dev_err(&ofdev->dev, "ioremap failed for AHBDMA register"
 			" address\n");
 		err = -ENODEV;
-		goto error_out;
+		goto error_iomap;
 	}
 
 	/* Save dev for later use in dev_xxx() routines */
 	host_pvt.dwc_dev = &ofdev->dev;
 
 	/* Initialize AHB DMAC */
-	dma_dwc_init(hsdev, irq);
+	err = dma_dwc_init(hsdev, irq);
+	if (err)
+		goto error_dma_iomap;
 
 	/* Enable SATA Interrupts */
 	sata_dwc_enable_interrupts(hsdev);
@@ -1759,9 +1756,8 @@ static int sata_dwc_probe(struct platfor
 	 * device discovery process, invoking our port_start() handler &
 	 * error_handler() to execute a dummy Softreset EH session
 	 */
-	rc = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
-
-	if (rc != 0)
+	err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
+	if (err)
 		dev_err(&ofdev->dev, "failed to activate host");
 
 	dev_set_drvdata(&ofdev->dev, host);
@@ -1770,7 +1766,8 @@ static int sata_dwc_probe(struct platfor
 error_out:
 	/* Free SATA DMA resources */
 	dma_dwc_exit(hsdev);
-
+error_dma_iomap:
+	iounmap((void __iomem *)host_pvt.sata_dma_regs);
 error_iomap:
 	iounmap(base);
 error_kmalloc:
@@ -1791,6 +1788,7 @@ static int sata_dwc_remove(struct platfo
 	/* Free SATA DMA resources */
 	dma_dwc_exit(hsdev);
 
+	iounmap((void __iomem *)host_pvt.sata_dma_regs);
 	iounmap(hsdev->reg_base);
 	kfree(hsdev);
 	kfree(host);
Index: linux-3.18.13-rt10-r7s4/drivers/ata/sata_sil24.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/ata/sata_sil24.c
+++ linux-3.18.13-rt10-r7s4/drivers/ata/sata_sil24.c
@@ -246,7 +246,7 @@ enum {
 	/* host flags */
 	SIL24_COMMON_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
 				  ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA |
-				  ATA_FLAG_AN | ATA_FLAG_PMP,
+				  ATA_FLAG_AN | ATA_FLAG_PMP | ATA_FLAG_LOWTAG,
 	SIL24_FLAG_PCIX_IRQ_WOC	= (1 << 24), /* IRQ loss errata on PCI-X */
 
 	IRQ_STAT_4PORTS		= 0xf,
Index: linux-3.18.13-rt10-r7s4/drivers/base/bus.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/base/bus.c
+++ linux-3.18.13-rt10-r7s4/drivers/base/bus.c
@@ -254,13 +254,15 @@ static ssize_t store_drivers_probe(struc
 				   const char *buf, size_t count)
 {
 	struct device *dev;
+	int err = -EINVAL;
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
 	if (!dev)
 		return -ENODEV;
-	if (bus_rescan_devices_helper(dev, NULL) != 0)
-		return -EINVAL;
-	return count;
+	if (bus_rescan_devices_helper(dev, NULL) == 0)
+		err = count;
+	put_device(dev);
+	return err;
 }
 
 static struct device *next_device(struct klist_iter *i)
Index: linux-3.18.13-rt10-r7s4/drivers/base/regmap/internal.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/base/regmap/internal.h
+++ linux-3.18.13-rt10-r7s4/drivers/base/regmap/internal.h
@@ -237,4 +237,12 @@ extern struct regcache_ops regcache_rbtr
 extern struct regcache_ops regcache_lzo_ops;
 extern struct regcache_ops regcache_flat_ops;
 
+static inline const char *regmap_name(const struct regmap *map)
+{
+	if (map->dev)
+		return dev_name(map->dev);
+
+	return map->name;
+}
+
 #endif
Index: linux-3.18.13-rt10-r7s4/drivers/base/regmap/regcache-rbtree.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/base/regmap/regcache-rbtree.c
+++ linux-3.18.13-rt10-r7s4/drivers/base/regmap/regcache-rbtree.c
@@ -307,7 +307,7 @@ static int regcache_rbtree_insert_to_blo
 	if (pos == 0) {
 		memmove(blk + offset * map->cache_word_size,
 			blk, rbnode->blklen * map->cache_word_size);
-		bitmap_shift_right(present, present, offset, blklen);
+		bitmap_shift_left(present, present, offset, blklen);
 	}
 
 	/* update the rbnode block, its size and the base register */
Index: linux-3.18.13-rt10-r7s4/drivers/base/regmap/regcache.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/base/regmap/regcache.c
+++ linux-3.18.13-rt10-r7s4/drivers/base/regmap/regcache.c
@@ -213,7 +213,7 @@ int regcache_read(struct regmap *map,
 		ret = map->cache_ops->read(map, reg, value);
 
 		if (ret == 0)
-			trace_regmap_reg_read_cache(map->dev, reg, *value);
+			trace_regmap_reg_read_cache(map, reg, *value);
 
 		return ret;
 	}
@@ -306,7 +306,7 @@ int regcache_sync(struct regmap *map)
 	dev_dbg(map->dev, "Syncing %s cache\n",
 		map->cache_ops->name);
 	name = map->cache_ops->name;
-	trace_regcache_sync(map->dev, name, "start");
+	trace_regcache_sync(map, name, "start");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -341,7 +341,7 @@ out:
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop");
+	trace_regcache_sync(map, name, "stop");
 
 	return ret;
 }
@@ -376,7 +376,7 @@ int regcache_sync_region(struct regmap *
 	name = map->cache_ops->name;
 	dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max);
 
-	trace_regcache_sync(map->dev, name, "start region");
+	trace_regcache_sync(map, name, "start region");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -396,7 +396,7 @@ out:
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop region");
+	trace_regcache_sync(map, name, "stop region");
 
 	return ret;
 }
@@ -423,7 +423,7 @@ int regcache_drop_region(struct regmap *
 
 	map->lock(map->lock_arg);
 
-	trace_regcache_drop_region(map->dev, min, max);
+	trace_regcache_drop_region(map, min, max);
 
 	ret = map->cache_ops->drop(map, min, max);
 
@@ -450,7 +450,7 @@ void regcache_cache_only(struct regmap *
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_bypass && enable);
 	map->cache_only = enable;
-	trace_regmap_cache_only(map->dev, enable);
+	trace_regmap_cache_only(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_only);
@@ -488,7 +488,7 @@ void regcache_cache_bypass(struct regmap
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_only && enable);
 	map->cache_bypass = enable;
-	trace_regmap_cache_bypass(map->dev, enable);
+	trace_regmap_cache_bypass(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_bypass);
Index: linux-3.18.13-rt10-r7s4/drivers/base/regmap/regmap.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/base/regmap/regmap.c
+++ linux-3.18.13-rt10-r7s4/drivers/base/regmap/regmap.c
@@ -1280,7 +1280,7 @@ int _regmap_raw_write(struct regmap *map
 	if (map->async && map->bus->async_write) {
 		struct regmap_async *async;
 
-		trace_regmap_async_write_start(map->dev, reg, val_len);
+		trace_regmap_async_write_start(map, reg, val_len);
 
 		spin_lock_irqsave(&map->async_lock, flags);
 		async = list_first_entry_or_null(&map->async_free,
@@ -1338,8 +1338,7 @@ int _regmap_raw_write(struct regmap *map
 		return ret;
 	}
 
-	trace_regmap_hw_write_start(map->dev, reg,
-				    val_len / map->format.val_bytes);
+	trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes);
 
 	/* If we're doing a single register write we can probably just
 	 * send the work_buf directly, otherwise try to do a gather
@@ -1371,8 +1370,7 @@ int _regmap_raw_write(struct regmap *map
 		kfree(buf);
 	}
 
-	trace_regmap_hw_write_done(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -1406,12 +1404,12 @@ static int _regmap_bus_formatted_write(v
 
 	map->format.format_write(map, reg, val);
 
-	trace_regmap_hw_write_start(map->dev, reg, 1);
+	trace_regmap_hw_write_start(map, reg, 1);
 
 	ret = map->bus->write(map->bus_context, map->work_buf,
 			      map->format.buf_size);
 
-	trace_regmap_hw_write_done(map->dev, reg, 1);
+	trace_regmap_hw_write_done(map, reg, 1);
 
 	return ret;
 }
@@ -1469,7 +1467,7 @@ int _regmap_write(struct regmap *map, un
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
-	trace_regmap_reg_write(map->dev, reg, val);
+	trace_regmap_reg_write(map, reg, val);
 
 	return map->reg_write(context, reg, val);
 }
@@ -1772,7 +1770,7 @@ static int _regmap_raw_multi_reg_write(s
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
 		int val = regs[i].def;
-		trace_regmap_hw_write_start(map->dev, reg, 1);
+		trace_regmap_hw_write_start(map, reg, 1);
 		map->format.format_reg(u8, reg, map->reg_shift);
 		u8 += reg_bytes + pad_bytes;
 		map->format.format_val(u8, val, 0);
@@ -1787,7 +1785,7 @@ static int _regmap_raw_multi_reg_write(s
 
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
-		trace_regmap_hw_write_done(map->dev, reg, 1);
+		trace_regmap_hw_write_done(map, reg, 1);
 	}
 	return ret;
 }
@@ -2058,15 +2056,13 @@ static int _regmap_raw_read(struct regma
 	 */
 	u8[0] |= map->read_flag_mask;
 
-	trace_regmap_hw_read_start(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes);
 
 	ret = map->bus->read(map->bus_context, map->work_buf,
 			     map->format.reg_bytes + map->format.pad_bytes,
 			     val, val_len);
 
-	trace_regmap_hw_read_done(map->dev, reg,
-				  val_len / map->format.val_bytes);
+	trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -2122,7 +2118,7 @@ static int _regmap_read(struct regmap *m
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
-		trace_regmap_reg_read(map->dev, reg, *val);
+		trace_regmap_reg_read(map, reg, *val);
 
 		if (!map->cache_bypass)
 			regcache_write(map, reg, *val);
@@ -2479,7 +2475,7 @@ void regmap_async_complete_cb(struct reg
 	struct regmap *map = async->map;
 	bool wake;
 
-	trace_regmap_async_io_complete(map->dev);
+	trace_regmap_async_io_complete(map);
 
 	spin_lock(&map->async_lock);
 	list_move(&async->list, &map->async_free);
@@ -2524,7 +2520,7 @@ int regmap_async_complete(struct regmap
 	if (!map->bus || !map->bus->async_write)
 		return 0;
 
-	trace_regmap_async_complete_start(map->dev);
+	trace_regmap_async_complete_start(map);
 
 	wait_event(map->async_waitq, regmap_async_is_done(map));
 
@@ -2533,7 +2529,7 @@ int regmap_async_complete(struct regmap
 	map->async_ret = 0;
 	spin_unlock_irqrestore(&map->async_lock, flags);
 
-	trace_regmap_async_complete_done(map->dev);
+	trace_regmap_async_complete_done(map);
 
 	return ret;
 }
Index: linux-3.18.13-rt10-r7s4/drivers/block/drbd/drbd_req.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/block/drbd/drbd_req.c
+++ linux-3.18.13-rt10-r7s4/drivers/block/drbd/drbd_req.c
@@ -1545,6 +1545,7 @@ int drbd_merge_bvec(struct request_queue
 		struct request_queue * const b =
 			device->ldev->backing_bdev->bd_disk->queue;
 		if (b->merge_bvec_fn) {
+			bvm->bi_bdev = device->ldev->backing_bdev;
 			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
 			limit = min(limit, backing_limit);
 		}
@@ -1628,7 +1629,7 @@ void request_timer_fn(unsigned long data
 		 time_after(now, req_peer->pre_send_jif + ent) &&
 		!time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) {
 		drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n");
-		_drbd_set_state(_NS(device, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
+		_conn_request_state(connection, NS(conn, C_TIMEOUT), CS_VERBOSE | CS_HARD);
 	}
 	if (dt && oldest_submit_jif != now &&
 		 time_after(now, oldest_submit_jif + dt) &&
Index: linux-3.18.13-rt10-r7s4/drivers/block/nbd.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/block/nbd.c
+++ linux-3.18.13-rt10-r7s4/drivers/block/nbd.c
@@ -803,10 +803,6 @@ static int __init nbd_init(void)
 		return -EINVAL;
 	}
 
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-	if (!nbd_dev)
-		return -ENOMEM;
-
 	part_shift = 0;
 	if (max_part > 0) {
 		part_shift = fls(max_part);
@@ -828,6 +824,10 @@ static int __init nbd_init(void)
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
+	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+	if (!nbd_dev)
+		return -ENOMEM;
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
Index: linux-3.18.13-rt10-r7s4/drivers/block/rbd.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/block/rbd.c
+++ linux-3.18.13-rt10-r7s4/drivers/block/rbd.c
@@ -2098,32 +2098,26 @@ static void rbd_dev_parent_put(struct rb
  * If an image has a non-zero parent overlap, get a reference to its
  * parent.
  *
- * We must get the reference before checking for the overlap to
- * coordinate properly with zeroing the parent overlap in
- * rbd_dev_v2_parent_info() when an image gets flattened.  We
- * drop it again if there is no overlap.
- *
  * Returns true if the rbd device has a parent with a non-zero
  * overlap and a reference for it was successfully taken, or
  * false otherwise.
  */
 static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
 {
-	int counter;
+	int counter = 0;
 
 	if (!rbd_dev->parent_spec)
 		return false;
 
-	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
-	if (counter > 0 && rbd_dev->parent_overlap)
-		return true;
-
-	/* Image was flattened, but parent is not yet torn down */
+	down_read(&rbd_dev->header_rwsem);
+	if (rbd_dev->parent_overlap)
+		counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	up_read(&rbd_dev->header_rwsem);
 
 	if (counter < 0)
 		rbd_warn(rbd_dev, "parent reference overflow");
 
-	return false;
+	return counter > 0;
 }
 
 /*
@@ -4236,7 +4230,6 @@ static int rbd_dev_v2_parent_info(struct
 		 */
 		if (rbd_dev->parent_overlap) {
 			rbd_dev->parent_overlap = 0;
-			smp_mb();
 			rbd_dev_parent_put(rbd_dev);
 			pr_info("%s: clone image has been flattened\n",
 				rbd_dev->disk->disk_name);
@@ -4282,7 +4275,6 @@ static int rbd_dev_v2_parent_info(struct
 	 * treat it specially.
 	 */
 	rbd_dev->parent_overlap = overlap;
-	smp_mb();
 	if (!overlap) {
 
 		/* A null parent_spec indicates it's the initial probe */
@@ -5111,10 +5103,7 @@ static void rbd_dev_unprobe(struct rbd_d
 {
 	struct rbd_image_header	*header;
 
-	/* Drop parent reference unless it's already been done (or none) */
-
-	if (rbd_dev->parent_overlap)
-		rbd_dev_parent_put(rbd_dev);
+	rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 
Index: linux-3.18.13-rt10-r7s4/drivers/bluetooth/ath3k.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/bluetooth/ath3k.c
+++ linux-3.18.13-rt10-r7s4/drivers/bluetooth/ath3k.c
@@ -79,6 +79,7 @@ static const struct usb_device_id ath3k_
 	{ USB_DEVICE(0x0489, 0xe057) },
 	{ USB_DEVICE(0x0489, 0xe056) },
 	{ USB_DEVICE(0x0489, 0xe05f) },
+	{ USB_DEVICE(0x0489, 0xe078) },
 	{ USB_DEVICE(0x04c5, 0x1330) },
 	{ USB_DEVICE(0x04CA, 0x3004) },
 	{ USB_DEVICE(0x04CA, 0x3005) },
@@ -86,6 +87,7 @@ static const struct usb_device_id ath3k_
 	{ USB_DEVICE(0x04CA, 0x3007) },
 	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x04CA, 0x300b) },
+	{ USB_DEVICE(0x04CA, 0x3010) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0930, 0x0220) },
 	{ USB_DEVICE(0x0930, 0x0227) },
@@ -105,6 +107,8 @@ static const struct usb_device_id ath3k_
 	{ USB_DEVICE(0x13d3, 0x3375) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
 	{ USB_DEVICE(0x13d3, 0x3402) },
+	{ USB_DEVICE(0x13d3, 0x3408) },
+	{ USB_DEVICE(0x13d3, 0x3423) },
 	{ USB_DEVICE(0x13d3, 0x3432) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
@@ -130,6 +134,7 @@ static const struct usb_device_id ath3k_
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
@@ -137,6 +142,7 @@ static const struct usb_device_id ath3k_
 	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
@@ -156,6 +162,8 @@ static const struct usb_device_id ath3k_
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
@@ -168,6 +176,8 @@ static const struct usb_device_id ath3k_
 #define USB_REQ_DFU_DNLOAD	1
 #define BULK_SIZE		4096
 #define FW_HDR_SIZE		20
+#define TIMEGAP_USEC_MIN	50
+#define TIMEGAP_USEC_MAX	100
 
 static int ath3k_load_firmware(struct usb_device *udev,
 				const struct firmware *firmware)
@@ -199,6 +209,9 @@ static int ath3k_load_firmware(struct us
 	pipe = usb_sndbulkpipe(udev, 0x02);
 
 	while (count) {
+		/* workaround the compatibility issue with xHCI controller*/
+		usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX);
+
 		size = min_t(uint, count, BULK_SIZE);
 		memcpy(send_buf, firmware->data + sent, size);
 
@@ -296,6 +309,9 @@ static int ath3k_load_fwfile(struct usb_
 	pipe = usb_sndbulkpipe(udev, 0x02);
 
 	while (count) {
+		/* workaround the compatibility issue with xHCI controller*/
+		usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX);
+
 		size = min_t(uint, count, BULK_SIZE);
 		memcpy(send_buf, firmware->data + sent, size);
 
Index: linux-3.18.13-rt10-r7s4/drivers/bluetooth/btusb.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/bluetooth/btusb.c
+++ linux-3.18.13-rt10-r7s4/drivers/bluetooth/btusb.c
@@ -107,14 +107,25 @@ static const struct usb_device_id btusb_
 	{ USB_DEVICE(0x0b05, 0x17cb) },
 	{ USB_DEVICE(0x413c, 0x8197) },
 
+	/* Broadcom BCM20702B0 (Dynex/Insignia) */
+	{ USB_DEVICE(0x19ff, 0x0239), .driver_info = BTUSB_BCM_PATCHRAM },
+
 	/* Foxconn - Hon Hai */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0489, 0xff, 0x01, 0x01) },
 
+	/* Lite-On Technology - Broadcom based */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x04ca, 0xff, 0x01, 0x01),
+	  .driver_info = BTUSB_BCM_PATCHRAM },
+
 	/* Broadcom devices with vendor specific id */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01),
 	  .driver_info = BTUSB_BCM_PATCHRAM },
 
 	/* ASUSTek Computer - Broadcom based */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01),
+	  .driver_info = BTUSB_BCM_PATCHRAM },
+
+	/* ASUSTek Computer - Broadcom based */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01) },
 
 	/* Belkin F8065bf - Broadcom based */
@@ -156,6 +167,7 @@ static const struct usb_device_id blackl
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
@@ -163,6 +175,7 @@ static const struct usb_device_id blackl
 	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
@@ -182,6 +195,8 @@ static const struct usb_device_id blackl
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
Index: linux-3.18.13-rt10-r7s4/drivers/bus/mvebu-mbus.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/bus/mvebu-mbus.c
+++ linux-3.18.13-rt10-r7s4/drivers/bus/mvebu-mbus.c
@@ -182,12 +182,25 @@ static void mvebu_mbus_disable_window(st
 }
 
 /* Checks whether the given window number is available */
+
+/* On Armada XP, 375 and 38x the MBus window 13 has the remap
+ * capability, like windows 0 to 7. However, the mvebu-mbus driver
+ * isn't currently taking into account this special case, which means
+ * that when window 13 is actually used, the remap registers are left
+ * to 0, making the device using this MBus window unavailable. The
+ * quick fix for stable is to not use window 13. A follow up patch
+ * will correctly handle this window.
+*/
 static int mvebu_mbus_window_is_free(struct mvebu_mbus_state *mbus,
 				     const int win)
 {
 	void __iomem *addr = mbus->mbuswins_base +
 		mbus->soc->win_cfg_offset(win);
 	u32 ctrl = readl(addr + WIN_CTRL_OFF);
+
+	if (win == 13)
+		return false;
+
 	return !(ctrl & WIN_CTRL_ENABLE);
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/bus/omap_l3_noc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/bus/omap_l3_noc.c
+++ linux-3.18.13-rt10-r7s4/drivers/bus/omap_l3_noc.c
@@ -222,10 +222,14 @@ static irqreturn_t l3_interrupt_handler(
 			}
 
 			/* Error found so break the for loop */
-			break;
+			return IRQ_HANDLED;
 		}
 	}
-	return IRQ_HANDLED;
+
+	dev_err(l3->dev, "L3 %s IRQ not handled!!\n",
+		inttype ? "debug" : "application");
+
+	return IRQ_NONE;
 }
 
 static const struct of_device_id l3_noc_match[] = {
@@ -296,11 +300,66 @@ static int omap_l3_probe(struct platform
 	return ret;
 }
 
+#ifdef	CONFIG_PM
+
+/**
+ * l3_resume_noirq() - resume function for l3_noc
+ * @dev:	pointer to l3_noc device structure
+ *
+ * We only have the resume handler only since we
+ * have already maintained the delta register
+ * configuration as part of configuring the system
+ */
+static int l3_resume_noirq(struct device *dev)
+{
+	struct omap_l3 *l3 = dev_get_drvdata(dev);
+	int i;
+	struct l3_flagmux_data *flag_mux;
+	void __iomem *base, *mask_regx = NULL;
+	u32 mask_val;
+
+	for (i = 0; i < l3->num_modules; i++) {
+		base = l3->l3_base[i];
+		flag_mux = l3->l3_flagmux[i];
+		if (!flag_mux->mask_app_bits && !flag_mux->mask_dbg_bits)
+			continue;
+
+		mask_regx = base + flag_mux->offset + L3_FLAGMUX_MASK0 +
+			   (L3_APPLICATION_ERROR << 3);
+		mask_val = readl_relaxed(mask_regx);
+		mask_val &= ~(flag_mux->mask_app_bits);
+
+		writel_relaxed(mask_val, mask_regx);
+		mask_regx = base + flag_mux->offset + L3_FLAGMUX_MASK0 +
+			   (L3_DEBUG_ERROR << 3);
+		mask_val = readl_relaxed(mask_regx);
+		mask_val &= ~(flag_mux->mask_dbg_bits);
+
+		writel_relaxed(mask_val, mask_regx);
+	}
+
+	/* Dummy read to force OCP barrier */
+	if (mask_regx)
+		(void)readl(mask_regx);
+
+	return 0;
+}
+
+static const struct dev_pm_ops l3_dev_pm_ops = {
+	.resume_noirq		= l3_resume_noirq,
+};
+
+#define L3_DEV_PM_OPS (&l3_dev_pm_ops)
+#else
+#define L3_DEV_PM_OPS NULL
+#endif
+
 static struct platform_driver omap_l3_driver = {
 	.probe		= omap_l3_probe,
 	.driver		= {
 		.name		= "omap_l3_noc",
 		.owner		= THIS_MODULE,
+		.pm		= L3_DEV_PM_OPS,
 		.of_match_table = of_match_ptr(l3_noc_match),
 	},
 };
Index: linux-3.18.13-rt10-r7s4/drivers/char/i8k.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/i8k.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/i8k.c
@@ -711,6 +711,14 @@ static struct dmi_system_id i8k_dmi_tabl
 		.driver_data = (void *)&i8k_config_data[DELL_LATITUDE_D520],
 	},
 	{
+		.ident = "Dell Latitude E6440",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6440"),
+		},
+		.driver_data = (void *)&i8k_config_data[DELL_LATITUDE_E6540],
+	},
+	{
 		.ident = "Dell Latitude E6540",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
Index: linux-3.18.13-rt10-r7s4/drivers/char/random.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/random.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/random.c
@@ -569,19 +569,19 @@ static void fast_mix(struct fast_pool *f
 	__u32 c = f->pool[2],	d = f->pool[3];
 
 	a += b;			c += d;
-	b = rol32(a, 6);	d = rol32(c, 27);
+	b = rol32(b, 6);	d = rol32(d, 27);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 16);	d = rol32(c, 14);
+	b = rol32(b, 16);	d = rol32(d, 14);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 6);	d = rol32(c, 27);
+	b = rol32(b, 6);	d = rol32(d, 27);
 	d ^= a;			b ^= c;
 
 	a += b;			c += d;
-	b = rol32(a, 16);	d = rol32(c, 14);
+	b = rol32(b, 16);	d = rol32(d, 14);
 	d ^= a;			b ^= c;
 
 	f->pool[0] = a;  f->pool[1] = b;
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm-interface.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm-interface.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm-interface.c
@@ -1122,7 +1122,7 @@ struct tpm_chip *tpm_register_hardware(s
 
 	/* Make chip available */
 	spin_lock(&driver_lock);
-	list_add_rcu(&chip->list, &tpm_chip_list);
+	list_add_tail_rcu(&chip->list, &tpm_chip_list);
 	spin_unlock(&driver_lock);
 
 	return chip;
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_i2c_atmel.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm_i2c_atmel.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_i2c_atmel.c
@@ -168,6 +168,10 @@ static int i2c_atmel_probe(struct i2c_cl
 
 	chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data),
 					 GFP_KERNEL);
+	if (!chip->vendor.priv) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
 
 	/* Default timeouts */
 	chip->vendor.timeout_a = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_i2c_nuvoton.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -538,6 +538,11 @@ static int i2c_nuvoton_probe(struct i2c_
 
 	chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data),
 					 GFP_KERNEL);
+	if (!chip->vendor.priv) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
+
 	init_waitqueue_head(&chip->vendor.read_queue);
 	init_waitqueue_head(&chip->vendor.int_queue);
 
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_i2c_stm_st33.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -397,7 +397,7 @@ static int wait_for_stat(struct tpm_chip
  */
 static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
 {
-	int size = 0, burstcnt, len;
+	int size = 0, burstcnt, len, ret;
 	struct i2c_client *client;
 
 	client = (struct i2c_client *)TPM_VPRIV(chip);
@@ -406,13 +406,15 @@ static int recv_data(struct tpm_chip *ch
 	       wait_for_stat(chip,
 			     TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 			     chip->vendor.timeout_c,
-			     &chip->vendor.read_queue)
-	       == 0) {
+			     &chip->vendor.read_queue) == 0) {
 		burstcnt = get_burstcount(chip);
 		if (burstcnt < 0)
 			return burstcnt;
 		len = min_t(int, burstcnt, count - size);
-		I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
+		ret = I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
+		if (ret < 0)
+			return ret;
+
 		size += len;
 	}
 	return size;
@@ -487,7 +489,7 @@ static int tpm_stm_i2c_send(struct tpm_c
 		if (burstcnt < 0)
 			return burstcnt;
 		size = min_t(int, len - i - 1, burstcnt);
-		ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf, size);
+		ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + i, size);
 		if (ret < 0)
 			goto out_err;
 
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_ibmvtpm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm_ibmvtpm.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_ibmvtpm.c
@@ -124,7 +124,7 @@ static int tpm_ibmvtpm_send(struct tpm_c
 {
 	struct ibmvtpm_dev *ibmvtpm;
 	struct ibmvtpm_crq crq;
-	u64 *word = (u64 *) &crq;
+	__be64 *word = (__be64 *)&crq;
 	int rc;
 
 	ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip);
@@ -145,10 +145,11 @@ static int tpm_ibmvtpm_send(struct tpm_c
 	memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_TPM_COMMAND;
-	crq.len = (u16)count;
-	crq.data = ibmvtpm->rtce_dma_handle;
+	crq.len = cpu_to_be16(count);
+	crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, word[0], word[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
+			      be64_to_cpu(word[1]));
 	if (rc != H_SUCCESS) {
 		dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
 		rc = 0;
@@ -186,7 +187,8 @@ static int ibmvtpm_crq_get_rtce_size(str
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+			      cpu_to_be64(buf[1]));
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc);
@@ -212,7 +214,8 @@ static int ibmvtpm_crq_get_version(struc
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_GET_VERSION;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+			      cpu_to_be64(buf[1]));
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"ibmvtpm_crq_get_version failed rc=%d\n", rc);
@@ -307,6 +310,14 @@ static int tpm_ibmvtpm_remove(struct vio
 static unsigned long tpm_ibmvtpm_get_desired_dma(struct vio_dev *vdev)
 {
 	struct ibmvtpm_dev *ibmvtpm = ibmvtpm_get_data(&vdev->dev);
+
+	/* ibmvtpm initializes at probe time, so the data we are
+	* asking for may not be set yet. Estimate that 4K required
+	* for TCE-mapped buffer in addition to CRQ.
+	*/
+	if (!ibmvtpm)
+		return CRQ_RES_BUF_SIZE + PAGE_SIZE;
+
 	return CRQ_RES_BUF_SIZE + ibmvtpm->rtce_size;
 }
 
@@ -327,7 +338,8 @@ static int tpm_ibmvtpm_suspend(struct de
 	crq.valid = (u8)IBMVTPM_VALID_CMD;
 	crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+			      cpu_to_be64(buf[1]));
 	if (rc != H_SUCCESS)
 		dev_err(ibmvtpm->dev,
 			"tpm_ibmvtpm_suspend failed rc=%d\n", rc);
@@ -472,11 +484,11 @@ static void ibmvtpm_crq_process(struct i
 	case IBMVTPM_VALID_CMD:
 		switch (crq->msg) {
 		case VTPM_GET_RTCE_BUFFER_SIZE_RES:
-			if (crq->len <= 0) {
+			if (be16_to_cpu(crq->len) <= 0) {
 				dev_err(ibmvtpm->dev, "Invalid rtce size\n");
 				return;
 			}
-			ibmvtpm->rtce_size = crq->len;
+			ibmvtpm->rtce_size = be16_to_cpu(crq->len);
 			ibmvtpm->rtce_buf = kmalloc(ibmvtpm->rtce_size,
 						    GFP_KERNEL);
 			if (!ibmvtpm->rtce_buf) {
@@ -497,11 +509,11 @@ static void ibmvtpm_crq_process(struct i
 
 			return;
 		case VTPM_GET_VERSION_RES:
-			ibmvtpm->vtpm_version = crq->data;
+			ibmvtpm->vtpm_version = be32_to_cpu(crq->data);
 			return;
 		case VTPM_TPM_COMMAND_RES:
 			/* len of the data in rtce buffer */
-			ibmvtpm->res_len = crq->len;
+			ibmvtpm->res_len = be16_to_cpu(crq->len);
 			wake_up_interruptible(&ibmvtpm->wq);
 			return;
 		default:
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_ibmvtpm.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm_ibmvtpm.h
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_ibmvtpm.h
@@ -22,9 +22,9 @@
 struct ibmvtpm_crq {
 	u8 valid;
 	u8 msg;
-	u16 len;
-	u32 data;
-	u64 reserved;
+	__be16 len;
+	__be32 data;
+	__be64 reserved;
 } __attribute__((packed, aligned(8)));
 
 struct ibmvtpm_crq_queue {
Index: linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_tis.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/tpm/tpm_tis.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/tpm/tpm_tis.c
@@ -75,6 +75,10 @@ enum tis_defaults {
 #define	TPM_DID_VID(l)			(0x0F00 | ((l) << 12))
 #define	TPM_RID(l)			(0x0F04 | ((l) << 12))
 
+struct priv_data {
+	bool irq_tested;
+};
+
 static LIST_HEAD(tis_chips);
 static DEFINE_MUTEX(tis_lock);
 
@@ -338,12 +342,27 @@ out_err:
 	return rc;
 }
 
+static void disable_interrupts(struct tpm_chip *chip)
+{
+	u32 intmask;
+
+	intmask =
+	    ioread32(chip->vendor.iobase +
+		     TPM_INT_ENABLE(chip->vendor.locality));
+	intmask &= ~TPM_GLOBAL_INT_ENABLE;
+	iowrite32(intmask,
+		  chip->vendor.iobase +
+		  TPM_INT_ENABLE(chip->vendor.locality));
+	free_irq(chip->vendor.irq, chip);
+	chip->vendor.irq = 0;
+}
+
 /*
  * If interrupts are used (signaled by an irq set in the vendor structure)
  * tpm.c can skip polling for the data to be available as the interrupt is
  * waited for here
  */
-static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_send_main(struct tpm_chip *chip, u8 *buf, size_t len)
 {
 	int rc;
 	u32 ordinal;
@@ -373,6 +392,30 @@ out_err:
 	return rc;
 }
 
+static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+{
+	int rc, irq;
+	struct priv_data *priv = chip->vendor.priv;
+
+	if (!chip->vendor.irq || priv->irq_tested)
+		return tpm_tis_send_main(chip, buf, len);
+
+	/* Verify receipt of the expected IRQ */
+	irq = chip->vendor.irq;
+	chip->vendor.irq = 0;
+	rc = tpm_tis_send_main(chip, buf, len);
+	chip->vendor.irq = irq;
+	if (!priv->irq_tested)
+		msleep(1);
+	if (!priv->irq_tested) {
+		disable_interrupts(chip);
+		dev_err(chip->dev,
+			FW_BUG "TPM interrupt not working, polling instead\n");
+	}
+	priv->irq_tested = true;
+	return rc;
+}
+
 struct tis_vendor_timeout_override {
 	u32 did_vid;
 	unsigned long timeout_us[4];
@@ -505,6 +548,7 @@ static irqreturn_t tis_int_handler(int d
 	if (interrupt == 0)
 		return IRQ_NONE;
 
+	((struct priv_data *)chip->vendor.priv)->irq_tested = true;
 	if (interrupt & TPM_INTF_DATA_AVAIL_INT)
 		wake_up_interruptible(&chip->vendor.read_queue);
 	if (interrupt & TPM_INTF_LOCALITY_CHANGE_INT)
@@ -534,9 +578,14 @@ static int tpm_tis_init(struct device *d
 	u32 vendor, intfcaps, intmask;
 	int rc, i, irq_s, irq_e, probe;
 	struct tpm_chip *chip;
+	struct priv_data *priv;
 
+	priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL);
+	if (priv == NULL)
+		return -ENOMEM;
 	if (!(chip = tpm_register_hardware(dev, &tpm_tis)))
 		return -ENODEV;
+	chip->vendor.priv = priv;
 
 	chip->vendor.iobase = ioremap(start, len);
 	if (!chip->vendor.iobase) {
@@ -605,19 +654,6 @@ static int tpm_tis_init(struct device *d
 	if (intfcaps & TPM_INTF_DATA_AVAIL_INT)
 		dev_dbg(dev, "\tData Avail Int Support\n");
 
-	/* get the timeouts before testing for irqs */
-	if (tpm_get_timeouts(chip)) {
-		dev_err(dev, "Could not get TPM timeouts and durations\n");
-		rc = -ENODEV;
-		goto out_err;
-	}
-
-	if (tpm_do_selftest(chip)) {
-		dev_err(dev, "TPM self test failed\n");
-		rc = -ENODEV;
-		goto out_err;
-	}
-
 	/* INTERRUPT Setup */
 	init_waitqueue_head(&chip->vendor.read_queue);
 	init_waitqueue_head(&chip->vendor.int_queue);
@@ -719,6 +755,18 @@ static int tpm_tis_init(struct device *d
 		}
 	}
 
+	if (tpm_get_timeouts(chip)) {
+		dev_err(dev, "Could not get TPM timeouts and durations\n");
+		rc = -ENODEV;
+		goto out_err;
+	}
+
+	if (tpm_do_selftest(chip)) {
+		dev_err(dev, "TPM self test failed\n");
+		rc = -ENODEV;
+		goto out_err;
+	}
+
 	INIT_LIST_HEAD(&chip->vendor.list);
 	mutex_lock(&tis_lock);
 	list_add(&chip->vendor.list, &tis_chips);
Index: linux-3.18.13-rt10-r7s4/drivers/char/virtio_console.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/char/virtio_console.c
+++ linux-3.18.13-rt10-r7s4/drivers/char/virtio_console.c
@@ -142,6 +142,7 @@ struct ports_device {
 	 * notification
 	 */
 	struct work_struct control_work;
+	struct work_struct config_work;
 
 	struct list_head ports;
 
@@ -1832,10 +1833,21 @@ static void config_intr(struct virtio_de
 
 	portdev = vdev->priv;
 
+	if (!use_multiport(portdev))
+		schedule_work(&portdev->config_work);
+}
+
+static void config_work_handler(struct work_struct *work)
+{
+	struct ports_device *portdev;
+
+	portdev = container_of(work, struct ports_device, control_work);
 	if (!use_multiport(portdev)) {
+		struct virtio_device *vdev;
 		struct port *port;
 		u16 rows, cols;
 
+		vdev = portdev->vdev;
 		virtio_cread(vdev, struct virtio_console_config, cols, &cols);
 		virtio_cread(vdev, struct virtio_console_config, rows, &rows);
 
@@ -2026,12 +2038,14 @@ static int virtcons_probe(struct virtio_
 
 	virtio_device_ready(portdev->vdev);
 
+	INIT_WORK(&portdev->config_work, &config_work_handler);
+	INIT_WORK(&portdev->control_work, &control_work_handler);
+
 	if (multiport) {
 		unsigned int nr_added_bufs;
 
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
-		INIT_WORK(&portdev->control_work, &control_work_handler);
 
 		nr_added_bufs = fill_queue(portdev->c_ivq,
 					   &portdev->c_ivq_lock);
@@ -2099,6 +2113,8 @@ static void virtcons_remove(struct virti
 	/* Finish up work that's lined up */
 	if (use_multiport(portdev))
 		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);
@@ -2150,6 +2166,7 @@ static int virtcons_freeze(struct virtio
 
 	virtqueue_disable_cb(portdev->c_ivq);
 	cancel_work_sync(&portdev->control_work);
+	cancel_work_sync(&portdev->config_work);
 	/*
 	 * Once more: if control_work_handler() was running, it would
 	 * enable the cb as the last step.
Index: linux-3.18.13-rt10-r7s4/drivers/clk/berlin/bg2q.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/berlin/bg2q.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/berlin/bg2q.c
@@ -285,7 +285,6 @@ static const struct berlin2_gate_data bg
 	{ "pbridge",	"perif",	15, CLK_IGNORE_UNUSED },
 	{ "sdio",	"perif",	16, CLK_IGNORE_UNUSED },
 	{ "nfc",	"perif",	18 },
-	{ "smemc",	"perif",	19 },
 	{ "pcie",	"perif",	22 },
 };
 
Index: linux-3.18.13-rt10-r7s4/drivers/clk/clk-divider.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/clk-divider.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/clk-divider.c
@@ -129,12 +129,6 @@ static unsigned long clk_divider_recalc_
 	return DIV_ROUND_UP(parent_rate, div);
 }
 
-/*
- * The reverse of DIV_ROUND_UP: The maximum number which
- * divided by m is r
- */
-#define MULT_ROUND_UP(r, m) ((r) * (m) + (m) - 1)
-
 static bool _is_valid_table_div(const struct clk_div_table *table,
 							 unsigned int div)
 {
@@ -208,6 +202,7 @@ static int _div_round_closest(struct clk
 		unsigned long parent_rate, unsigned long rate)
 {
 	int up, down, div;
+	unsigned long up_rate, down_rate;
 
 	up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate);
 
@@ -219,7 +214,10 @@ static int _div_round_closest(struct clk
 		down = _round_down_table(divider->table, div);
 	}
 
-	return (up - div) <= (div - down) ? up : down;
+	up_rate = DIV_ROUND_UP(parent_rate, up);
+	down_rate = DIV_ROUND_UP(parent_rate, down);
+
+	return (rate - up_rate) <= (down_rate - rate) ? up : down;
 }
 
 static int _div_round(struct clk_divider *divider, unsigned long parent_rate,
@@ -300,7 +298,7 @@ static int clk_divider_bestdiv(struct cl
 			return i;
 		}
 		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
-				MULT_ROUND_UP(rate, i));
+					       rate * i);
 		now = DIV_ROUND_UP(parent_rate, i);
 		if (_is_best_div(divider, rate, now, best)) {
 			bestdiv = i;
Index: linux-3.18.13-rt10-r7s4/drivers/clk/clk-gate.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/clk-gate.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/clk-gate.c
@@ -128,7 +128,7 @@ struct clk *clk_register_gate(struct dev
 	struct clk_init_data init;
 
 	if (clk_gate_flags & CLK_GATE_HIWORD_MASK) {
-		if (bit_idx > 16) {
+		if (bit_idx > 15) {
 			pr_err("gate bit exceeds LOWORD field\n");
 			return ERR_PTR(-EINVAL);
 		}
Index: linux-3.18.13-rt10-r7s4/drivers/clk/clk-ppc-corenet.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/clk-ppc-corenet.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/clk-ppc-corenet.c
@@ -291,7 +291,7 @@ static const struct of_device_id ppc_clk
 	{}
 };
 
-static struct platform_driver ppc_corenet_clk_driver __initdata = {
+static struct platform_driver ppc_corenet_clk_driver = {
 	.driver = {
 		.name = "ppc_corenet_clock",
 		.owner = THIS_MODULE,
Index: linux-3.18.13-rt10-r7s4/drivers/clk/clk.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/clk.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/clk.c
@@ -240,7 +240,6 @@ static const struct file_operations clk_
 	.release	= single_release,
 };
 
-/* caller must hold prepare_lock */
 static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 {
 	struct dentry *d;
@@ -344,13 +343,9 @@ unlock:
 static void clk_debug_unregister(struct clk *clk)
 {
 	mutex_lock(&clk_debug_lock);
-	if (!clk->dentry)
-		goto out;
-
 	hlist_del_init(&clk->debug_node);
 	debugfs_remove_recursive(clk->dentry);
 	clk->dentry = NULL;
-out:
 	mutex_unlock(&clk_debug_lock);
 }
 
@@ -1944,7 +1939,6 @@ int __clk_init(struct device *dev, struc
 	else
 		clk->rate = 0;
 
-	clk_debug_register(clk);
 	/*
 	 * walk the list of orphan clocks and reparent any that are children of
 	 * this clock
@@ -1979,6 +1973,9 @@ int __clk_init(struct device *dev, struc
 out:
 	clk_prepare_unlock();
 
+	if (!ret)
+		clk_debug_register(clk);
+
 	return ret;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/clk/rockchip/clk-rk3188.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/rockchip/clk-rk3188.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/rockchip/clk-rk3188.c
@@ -210,6 +210,17 @@ PNAME(mux_sclk_hsadc_p)		= { "hsadc_src"
 PNAME(mux_mac_p)		= { "gpll", "dpll" };
 PNAME(mux_sclk_macref_p)	= { "mac_src", "ext_rmii" };
 
+static struct rockchip_pll_clock rk3066_pll_clks[] __initdata = {
+	[apll] = PLL(pll_rk3066, PLL_APLL, "apll", mux_pll_p, 0, RK2928_PLL_CON(0),
+		     RK2928_MODE_CON, 0, 5, rk3188_pll_rates),
+	[dpll] = PLL(pll_rk3066, PLL_DPLL, "dpll", mux_pll_p, 0, RK2928_PLL_CON(4),
+		     RK2928_MODE_CON, 4, 4, NULL),
+	[cpll] = PLL(pll_rk3066, PLL_CPLL, "cpll", mux_pll_p, 0, RK2928_PLL_CON(8),
+		     RK2928_MODE_CON, 8, 6, rk3188_pll_rates),
+	[gpll] = PLL(pll_rk3066, PLL_GPLL, "gpll", mux_pll_p, 0, RK2928_PLL_CON(12),
+		     RK2928_MODE_CON, 12, 7, rk3188_pll_rates),
+};
+
 static struct rockchip_pll_clock rk3188_pll_clks[] __initdata = {
 	[apll] = PLL(pll_rk3066, PLL_APLL, "apll", mux_pll_p, 0, RK2928_PLL_CON(0),
 		     RK2928_MODE_CON, 0, 6, rk3188_pll_rates),
@@ -742,8 +753,8 @@ static void __init rk3188_common_clk_ini
 static void __init rk3066a_clk_init(struct device_node *np)
 {
 	rk3188_common_clk_init(np);
-	rockchip_clk_register_plls(rk3188_pll_clks,
-				   ARRAY_SIZE(rk3188_pll_clks),
+	rockchip_clk_register_plls(rk3066_pll_clks,
+				   ARRAY_SIZE(rk3066_pll_clks),
 				   RK3066_GRF_SOC_STATUS);
 	rockchip_clk_register_branches(rk3066a_clk_branches,
 				  ARRAY_SIZE(rk3066a_clk_branches));
Index: linux-3.18.13-rt10-r7s4/drivers/clk/rockchip/clk-rk3288.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/rockchip/clk-rk3288.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/rockchip/clk-rk3288.c
@@ -142,20 +142,20 @@ struct rockchip_pll_rate_table rk3288_pl
 	}
 
 static struct rockchip_cpuclk_rate_table rk3288_cpuclk_rates[] __initdata = {
-	RK3288_CPUCLK_RATE(1800000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1704000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1608000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1512000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1416000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1200000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE(1008000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 816000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 696000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 600000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 408000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 312000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 216000000, 2, 4, 2, 4, 4),
-	RK3288_CPUCLK_RATE( 126000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1800000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1704000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1608000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1512000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1416000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1200000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE(1008000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 816000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 696000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 600000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 408000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 312000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 216000000, 1, 3, 1, 3, 3),
+	RK3288_CPUCLK_RATE( 126000000, 1, 3, 1, 3, 3),
 };
 
 static const struct rockchip_cpuclk_reg_data rk3288_cpuclk_data = {
Index: linux-3.18.13-rt10-r7s4/drivers/clk/samsung/clk-exynos-audss.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/samsung/clk-exynos-audss.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/samsung/clk-exynos-audss.c
@@ -210,6 +210,10 @@ static int exynos_audss_clk_remove(struc
 {
 	int i;
 
+#ifdef CONFIG_PM_SLEEP
+	unregister_syscore_ops(&exynos_audss_clk_syscore_ops);
+#endif
+
 	of_clk_del_provider(pdev->dev.of_node);
 
 	for (i = 0; i < clk_data.clk_num; i++) {
Index: linux-3.18.13-rt10-r7s4/drivers/clk/sunxi/clk-sunxi.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/sunxi/clk-sunxi.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/sunxi/clk-sunxi.c
@@ -419,6 +419,7 @@ static struct clk_factors_config sun6i_a
 	.kwidth = 2,
 	.mshift = 0,
 	.mwidth = 2,
+	.n_start = 1,
 };
 
 static struct clk_factors_config sun8i_a23_pll1_config = {
Index: linux-3.18.13-rt10-r7s4/drivers/clk/zynq/clkc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clk/zynq/clkc.c
+++ linux-3.18.13-rt10-r7s4/drivers/clk/zynq/clkc.c
@@ -303,6 +303,7 @@ static void __init zynq_clk_setup(struct
 	clks[cpu_2x] = clk_register_gate(NULL, clk_output_name[cpu_2x],
 			"cpu_2x_div", CLK_IGNORE_UNUSED, SLCR_ARM_CLK_CTRL,
 			26, 0, &armclk_lock);
+	clk_prepare_enable(clks[cpu_2x]);
 
 	clk = clk_register_fixed_factor(NULL, "cpu_1x_div", "cpu_div", 0, 1,
 			4 + 2 * tmp);
Index: linux-3.18.13-rt10-r7s4/drivers/clocksource/arm_arch_timer.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clocksource/arm_arch_timer.c
+++ linux-3.18.13-rt10-r7s4/drivers/clocksource/arm_arch_timer.c
@@ -462,7 +462,10 @@ static void __init arch_counter_register
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_CP15_TIMER) {
-		arch_timer_read_counter = arch_counter_get_cntvct;
+		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_use_virtual)
+			arch_timer_read_counter = arch_counter_get_cntvct;
+		else
+			arch_timer_read_counter = arch_counter_get_cntpct;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 
Index: linux-3.18.13-rt10-r7s4/drivers/clocksource/exynos_mct.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clocksource/exynos_mct.c
+++ linux-3.18.13-rt10-r7s4/drivers/clocksource/exynos_mct.c
@@ -97,8 +97,8 @@ static void exynos4_mct_write(unsigned i
 	writel_relaxed(value, reg_base + offset);
 
 	if (likely(offset >= EXYNOS4_MCT_L_BASE(0))) {
-		stat_addr = (offset & ~EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET;
-		switch (offset & EXYNOS4_MCT_L_MASK) {
+		stat_addr = (offset & EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET;
+		switch (offset & ~EXYNOS4_MCT_L_MASK) {
 		case MCT_L_TCON_OFFSET:
 			mask = 1 << 3;		/* L_TCON write status */
 			break;
Index: linux-3.18.13-rt10-r7s4/drivers/clocksource/mtk_timer.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clocksource/mtk_timer.c
+++ linux-3.18.13-rt10-r7s4/drivers/clocksource/mtk_timer.c
@@ -224,6 +224,8 @@ static void __init mtk_timer_init(struct
 	}
 	rate = clk_get_rate(clk);
 
+	mtk_timer_global_reset(evt);
+
 	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
 			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
 		pr_warn("failed to setup irq %d\n", evt->dev.irq);
@@ -232,8 +234,6 @@ static void __init mtk_timer_init(struct
 
 	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	mtk_timer_global_reset(evt);
-
 	/* Configure clock source */
 	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
 	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
@@ -241,10 +241,11 @@ static void __init mtk_timer_init(struct
 
 	/* Configure clock event */
 	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
 	clockevents_config_and_register(&evt->dev, rate, 0x3,
 					0xffffffff);
+
+	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
+
 	return;
 
 err_clk_disable:
Index: linux-3.18.13-rt10-r7s4/drivers/clocksource/time-efm32.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clocksource/time-efm32.c
+++ linux-3.18.13-rt10-r7s4/drivers/clocksource/time-efm32.c
@@ -225,12 +225,12 @@ static int __init efm32_clockevent_init(
 	clock_event_ddata.base = base;
 	clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ);
 
-	setup_irq(irq, &efm32_clock_event_irq);
-
 	clockevents_config_and_register(&clock_event_ddata.evtdev,
 					DIV_ROUND_CLOSEST(rate, 1024),
 					0xf, 0xffff);
 
+	setup_irq(irq, &efm32_clock_event_irq);
+
 	return 0;
 
 err_get_irq:
Index: linux-3.18.13-rt10-r7s4/drivers/clocksource/timer-sun5i.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/clocksource/timer-sun5i.c
+++ linux-3.18.13-rt10-r7s4/drivers/clocksource/timer-sun5i.c
@@ -178,10 +178,6 @@ static void __init sun5i_timer_init(stru
 
 	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	ret = setup_irq(irq, &sun5i_timer_irq);
-	if (ret)
-		pr_warn("failed to setup irq %d\n", irq);
-
 	/* Enable timer0 interrupt */
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
@@ -191,6 +187,10 @@ static void __init sun5i_timer_init(stru
 
 	clockevents_config_and_register(&sun5i_clockevent, rate,
 					TIMER_SYNC_TICKS, 0xffffffff);
+
+	ret = setup_irq(irq, &sun5i_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
 }
 CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
 		       sun5i_timer_init);
Index: linux-3.18.13-rt10-r7s4/drivers/cpufreq/cpufreq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpufreq/cpufreq.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpufreq/cpufreq.c
@@ -1409,9 +1409,10 @@ static int __cpufreq_remove_dev_finish(s
 	unsigned long flags;
 	struct cpufreq_policy *policy;
 
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	policy = per_cpu(cpufreq_cpu_data, cpu);
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
@@ -1466,7 +1467,6 @@ static int __cpufreq_remove_dev_finish(s
 		}
 	}
 
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	return 0;
 }
 
@@ -1717,15 +1717,18 @@ void cpufreq_resume(void)
 		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
 			pr_err("%s: Failed to start governor for policy: %p\n",
 				__func__, policy);
-
-		/*
-		 * schedule call cpufreq_update_policy() for boot CPU, i.e. last
-		 * policy in list. It will verify that the current freq is in
-		 * sync with what we believe it to be.
-		 */
-		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
-			schedule_work(&policy->update);
 	}
+
+	/*
+	 * schedule call cpufreq_update_policy() for first-online CPU, as that
+	 * wouldn't be hotplugged-out on suspend. It will verify that the
+	 * current freq is in sync with what we believe it to be.
+	 */
+	policy = cpufreq_cpu_get_raw(cpumask_first(cpu_online_mask));
+	if (WARN_ON(!policy))
+		return;
+
+	schedule_work(&policy->update);
 }
 
 /**
Index: linux-3.18.13-rt10-r7s4/drivers/cpufreq/s3c2416-cpufreq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpufreq/s3c2416-cpufreq.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpufreq/s3c2416-cpufreq.c
@@ -263,7 +263,7 @@ out:
 }
 
 #ifdef CONFIG_ARM_S3C2416_CPUFREQ_VCORESCALE
-static void __init s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq)
+static void s3c2416_cpufreq_cfg_regulator(struct s3c2416_data *s3c_freq)
 {
 	int count, v, i, found;
 	struct cpufreq_frequency_table *pos;
@@ -333,7 +333,7 @@ static struct notifier_block s3c2416_cpu
 	.notifier_call = s3c2416_cpufreq_reboot_notifier_evt,
 };
 
-static int __init s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
+static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
 {
 	struct s3c2416_data *s3c_freq = &s3c2416_cpufreq;
 	struct cpufreq_frequency_table *pos;
Index: linux-3.18.13-rt10-r7s4/drivers/cpufreq/s3c24xx-cpufreq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpufreq/s3c24xx-cpufreq.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -144,11 +144,6 @@ static void s3c_cpufreq_setfvco(struct s
 	(cfg->info->set_fvco)(cfg);
 }
 
-static inline void s3c_cpufreq_resume_clocks(void)
-{
-	cpu_cur.info->resume_clocks();
-}
-
 static inline void s3c_cpufreq_updateclk(struct clk *clk,
 					 unsigned int freq)
 {
@@ -417,9 +412,6 @@ static int s3c_cpufreq_resume(struct cpu
 
 	last_target = ~0;	/* invalidate last_target setting */
 
-	/* first, find out what speed we resumed at. */
-	s3c_cpufreq_resume_clocks();
-
 	/* whilst we will be called later on, we try and re-set the
 	 * cpu frequencies as soon as possible so that we do not end
 	 * up resuming devices and then immediately having to re-set
@@ -454,7 +446,7 @@ static struct cpufreq_driver s3c24xx_dri
 };
 
 
-int __init s3c_cpufreq_register(struct s3c_cpufreq_info *info)
+int s3c_cpufreq_register(struct s3c_cpufreq_info *info)
 {
 	if (!info || !info->name) {
 		printk(KERN_ERR "%s: failed to pass valid information\n",
Index: linux-3.18.13-rt10-r7s4/drivers/cpufreq/speedstep-lib.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpufreq/speedstep-lib.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpufreq/speedstep-lib.c
@@ -400,6 +400,7 @@ unsigned int speedstep_get_freqs(enum sp
 
 	pr_debug("previous speed is %u\n", prev_speed);
 
+	preempt_disable();
 	local_irq_save(flags);
 
 	/* switch to low state */
@@ -464,6 +465,8 @@ unsigned int speedstep_get_freqs(enum sp
 
 out:
 	local_irq_restore(flags);
+	preempt_enable();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(speedstep_get_freqs);
Index: linux-3.18.13-rt10-r7s4/drivers/cpufreq/speedstep-smi.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpufreq/speedstep-smi.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpufreq/speedstep-smi.c
@@ -156,6 +156,7 @@ static void speedstep_set_state(unsigned
 		return;
 
 	/* Disable IRQs */
+	preempt_disable();
 	local_irq_save(flags);
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
@@ -166,9 +167,19 @@ static void speedstep_set_state(unsigned
 
 	do {
 		if (retry) {
+			/*
+			 * We need to enable interrupts, otherwise the blockage
+			 * won't resolve.
+			 *
+			 * We disable preemption so that other processes don't
+			 * run. If other processes were running, they could
+			 * submit more DMA requests, making the blockage worse.
+			 */
 			pr_debug("retry %u, previous result %u, waiting...\n",
 					retry, result);
+			local_irq_enable();
 			mdelay(retry * 50);
+			local_irq_disable();
 		}
 		retry++;
 		__asm__ __volatile__(
@@ -185,6 +196,7 @@ static void speedstep_set_state(unsigned
 
 	/* enable IRQs */
 	local_irq_restore(flags);
+	preempt_enable();
 
 	if (new_state == state)
 		pr_debug("change to %u MHz succeeded after %u tries "
Index: linux-3.18.13-rt10-r7s4/drivers/cpuidle/cpuidle-mvebu-v7.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpuidle/cpuidle-mvebu-v7.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpuidle/cpuidle-mvebu-v7.c
@@ -37,11 +37,11 @@ static int mvebu_v7_enter_idle(struct cp
 		deepidle = true;
 
 	ret = mvebu_v7_cpu_suspend(deepidle);
+	cpu_pm_exit();
+
 	if (ret)
 		return ret;
 
-	cpu_pm_exit();
-
 	return index;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/cpuidle/cpuidle.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpuidle/cpuidle.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpuidle/cpuidle.c
@@ -297,9 +297,6 @@ int cpuidle_enable_device(struct cpuidle
 	if (!dev->registered)
 		return -EINVAL;
 
-	if (!dev->state_count)
-		dev->state_count = drv->state_count;
-
 	ret = cpuidle_add_device_sysfs(dev);
 	if (ret)
 		return ret;
Index: linux-3.18.13-rt10-r7s4/drivers/cpuidle/sysfs.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/cpuidle/sysfs.c
+++ linux-3.18.13-rt10-r7s4/drivers/cpuidle/sysfs.c
@@ -401,7 +401,7 @@ static int cpuidle_add_state_sysfs(struc
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device);
 
 	/* state statistics */
-	for (i = 0; i < device->state_count; i++) {
+	for (i = 0; i < drv->state_count; i++) {
 		kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL);
 		if (!kobj)
 			goto error_state;
@@ -433,9 +433,10 @@ error_state:
  */
 static void cpuidle_remove_state_sysfs(struct cpuidle_device *device)
 {
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device);
 	int i;
 
-	for (i = 0; i < device->state_count; i++)
+	for (i = 0; i < drv->state_count; i++)
 		cpuidle_free_state_kobj(device, i);
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/crypto/padlock-aes.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/crypto/padlock-aes.c
+++ linux-3.18.13-rt10-r7s4/drivers/crypto/padlock-aes.c
@@ -563,4 +563,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algo
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
Index: linux-3.18.13-rt10-r7s4/drivers/crypto/padlock-sha.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/crypto/padlock-sha.c
+++ linux-3.18.13-rt10-r7s4/drivers/crypto/padlock-sha.c
@@ -593,7 +593,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("sha1-padlock");
-MODULE_ALIAS("sha256-padlock");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-padlock");
+MODULE_ALIAS_CRYPTO("sha256-padlock");
Index: linux-3.18.13-rt10-r7s4/drivers/crypto/qat/qat_common/adf_ctl_drv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ linux-3.18.13-rt10-r7s4/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -52,6 +52,7 @@
 #include <linux/pci.h>
 #include <linux/cdev.h>
 #include <linux/uaccess.h>
+#include <linux/crypto.h>
 
 #include "adf_accel_devices.h"
 #include "adf_common_drv.h"
@@ -487,4 +488,4 @@ module_exit(adf_unregister_ctl_device_dr
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
-MODULE_ALIAS("intel_qat");
+MODULE_ALIAS_CRYPTO("intel_qat");
Index: linux-3.18.13-rt10-r7s4/drivers/crypto/ux500/cryp/cryp_core.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/crypto/ux500/cryp/cryp_core.c
+++ linux-3.18.13-rt10-r7s4/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1810,7 +1810,7 @@ module_exit(ux500_cryp_mod_fini);
 module_param(cryp_mode, int, 0);
 
 MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 CRYP crypto engine.");
-MODULE_ALIAS("aes-all");
-MODULE_ALIAS("des-all");
+MODULE_ALIAS_CRYPTO("aes-all");
+MODULE_ALIAS_CRYPTO("des-all");
 
 MODULE_LICENSE("GPL");
Index: linux-3.18.13-rt10-r7s4/drivers/crypto/ux500/hash/hash_core.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/crypto/ux500/hash/hash_core.c
+++ linux-3.18.13-rt10-r7s4/drivers/crypto/ux500/hash/hash_core.c
@@ -1995,7 +1995,7 @@ module_exit(ux500_hash_mod_fini);
 MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 HASH engine.");
 MODULE_LICENSE("GPL");
 
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("hmac-sha1-all");
-MODULE_ALIAS("hmac-sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("hmac-sha1-all");
+MODULE_ALIAS_CRYPTO("hmac-sha256-all");
Index: linux-3.18.13-rt10-r7s4/drivers/dma-buf/reservation.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/dma-buf/reservation.c
+++ linux-3.18.13-rt10-r7s4/drivers/dma-buf/reservation.c
@@ -402,8 +402,6 @@ reservation_object_test_signaled_single(
 	int ret = 1;
 
 	if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) {
-		int ret;
-
 		fence = fence_get_rcu(lfence);
 		if (!fence)
 			return -1;
Index: linux-3.18.13-rt10-r7s4/drivers/dma/dw/platform.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/dma/dw/platform.c
+++ linux-3.18.13-rt10-r7s4/drivers/dma/dw/platform.c
@@ -25,6 +25,8 @@
 
 #include "internal.h"
 
+#define DRV_NAME	"dw_dmac"
+
 static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 					struct of_dma *ofdma)
 {
@@ -279,7 +281,7 @@ static struct platform_driver dw_driver
 	.remove		= dw_remove,
 	.shutdown       = dw_shutdown,
 	.driver = {
-		.name	= "dw_dmac",
+		.name	= DRV_NAME,
 		.pm	= &dw_dev_pm_ops,
 		.of_match_table = of_match_ptr(dw_dma_of_id_table),
 		.acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table),
@@ -300,3 +302,4 @@ module_exit(dw_exit);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver");
+MODULE_ALIAS("platform:" DRV_NAME);
Index: linux-3.18.13-rt10-r7s4/drivers/dma/edma.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/dma/edma.c
+++ linux-3.18.13-rt10-r7s4/drivers/dma/edma.c
@@ -258,6 +258,13 @@ static int edma_terminate_all(struct edm
 	 */
 	if (echan->edesc) {
 		int cyclic = echan->edesc->cyclic;
+
+		/*
+		 * free the running request descriptor
+		 * since it is not in any of the vdesc lists
+		 */
+		edma_desc_free(&echan->edesc->vdesc);
+
 		echan->edesc = NULL;
 		edma_stop(echan->ch_num);
 		/* Move the cyclic channel back to default queue */
Index: linux-3.18.13-rt10-r7s4/drivers/dma/omap-dma.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/dma/omap-dma.c
+++ linux-3.18.13-rt10-r7s4/drivers/dma/omap-dma.c
@@ -978,6 +978,7 @@ static int omap_dma_terminate_all(struct
 	 * c->desc is NULL and exit.)
 	 */
 	if (c->desc) {
+		omap_dma_desc_free(&c->desc->vd);
 		c->desc = NULL;
 		/* Avoid stopping the dma twice */
 		if (!c->paused)
Index: linux-3.18.13-rt10-r7s4/drivers/edac/amd64_edac.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/edac/amd64_edac.c
+++ linux-3.18.13-rt10-r7s4/drivers/edac/amd64_edac.c
@@ -2039,14 +2039,20 @@ static void __log_bus_error(struct mem_c
 
 static inline void decode_bus_error(int node_id, struct mce *m)
 {
-	struct mem_ctl_info *mci = mcis[node_id];
-	struct amd64_pvt *pvt = mci->pvt_info;
+	struct mem_ctl_info *mci;
+	struct amd64_pvt *pvt;
 	u8 ecc_type = (m->status >> 45) & 0x3;
 	u8 xec = XEC(m->status, 0x1f);
 	u16 ec = EC(m->status);
 	u64 sys_addr;
 	struct err_info err;
 
+	mci = edac_mc_find(node_id);
+	if (!mci)
+		return;
+
+	pvt = mci->pvt_info;
+
 	/* Bail out early if this was an 'observed' error */
 	if (PP(ec) == NBSL_PP_OBS)
 		return;
Index: linux-3.18.13-rt10-r7s4/drivers/edac/sb_edac.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/edac/sb_edac.c
+++ linux-3.18.13-rt10-r7s4/drivers/edac/sb_edac.c
@@ -135,6 +135,7 @@ static inline int sad_pkg(const struct i
 
 #define TOLM		0x80
 #define	TOHM		0x84
+#define HASWELL_TOLM	0xd0
 #define HASWELL_TOHM_0	0xd4
 #define HASWELL_TOHM_1	0xd8
 
@@ -706,8 +707,8 @@ static u64 haswell_get_tolm(struct sbrid
 {
 	u32 reg;
 
-	pci_read_config_dword(pvt->info.pci_vtd, TOLM, &reg);
-	return (GET_BITFIELD(reg, 26, 31) << 26) | 0x1ffffff;
+	pci_read_config_dword(pvt->info.pci_vtd, HASWELL_TOLM, &reg);
+	return (GET_BITFIELD(reg, 26, 31) << 26) | 0x3ffffff;
 }
 
 static u64 haswell_get_tohm(struct sbridge_pvt *pvt)
@@ -848,7 +849,7 @@ static int get_dimm_config(struct mem_ct
 	else
 		edac_dbg(0, "Memory is unregistered\n");
 
-	if (mtype == MEM_DDR4 || MEM_RDDR4)
+	if (mtype == MEM_DDR4 || mtype == MEM_RDDR4)
 		banks = 16;
 	else
 		banks = 8;
@@ -2297,7 +2298,7 @@ static int sbridge_probe(struct pci_dev
 		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_ibridge_table);
 		type = IVY_BRIDGE;
 		break;
-	case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA:
+	case PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0:
 		rc = sbridge_get_all_devices(&num_mc, pci_dev_descr_sbridge_table);
 		type = SANDY_BRIDGE;
 		break;
@@ -2306,8 +2307,11 @@ static int sbridge_probe(struct pci_dev
 		type = HASWELL;
 		break;
 	}
-	if (unlikely(rc < 0))
+	if (unlikely(rc < 0)) {
+		edac_dbg(0, "couldn't get all devices for 0x%x\n", pdev->device);
 		goto fail0;
+	}
+
 	mc = 0;
 
 	list_for_each_entry(sbridge_dev, &sbridge_edac_list, list) {
@@ -2320,7 +2324,7 @@ static int sbridge_probe(struct pci_dev
 			goto fail1;
 	}
 
-	sbridge_printk(KERN_INFO, "Driver loaded.\n");
+	sbridge_printk(KERN_INFO, "%s\n", SBRIDGE_REVISION);
 
 	mutex_unlock(&sbridge_edac_lock);
 	return 0;
Index: linux-3.18.13-rt10-r7s4/drivers/firmware/efi/libstub/efi-stub-helper.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ linux-3.18.13-rt10-r7s4/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -170,12 +170,12 @@ again:
 		start = desc->phys_addr;
 		end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
 
-		if ((start + size) > end || (start + size) > max)
-			continue;
-
-		if (end - size > max)
+		if (end > max)
 			end = max;
 
+		if ((start + size) > end)
+			continue;
+
 		if (round_down(end - size, align) < start)
 			continue;
 
Index: linux-3.18.13-rt10-r7s4/drivers/firmware/efi/runtime-map.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/firmware/efi/runtime-map.c
+++ linux-3.18.13-rt10-r7s4/drivers/firmware/efi/runtime-map.c
@@ -191,7 +191,7 @@ int __init efi_runtime_map_init(struct k
 
 	return 0;
 out_add_entry:
-	for (j = i - 1; j > 0; j--) {
+	for (j = i - 1; j >= 0; j--) {
 		entry = *(map_entries + j);
 		kobject_put(&entry->kobj);
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/gpio/gpio-crystalcove.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpio/gpio-crystalcove.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpio/gpio-crystalcove.c
@@ -272,7 +272,7 @@ static irqreturn_t crystalcove_gpio_irq_
 	for (gpio = 0; gpio < CRYSTALCOVE_GPIO_NUM; gpio++) {
 		if (pending & BIT(gpio)) {
 			virq = irq_find_mapping(cg->chip.irqdomain, gpio);
-			generic_handle_irq(virq);
+			handle_nested_irq(virq);
 		}
 	}
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpio/gpio-mcp23s08.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpio/gpio-mcp23s08.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpio/gpio-mcp23s08.c
@@ -785,9 +785,11 @@ static int mcp230xx_probe(struct i2c_cli
 		client->irq = irq_of_parse_and_map(client->dev.of_node, 0);
 	} else {
 		pdata = dev_get_platdata(&client->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&client->dev, "invalid platform data\n");
-			return -EINVAL;
+		if (!pdata) {
+			pdata = devm_kzalloc(&client->dev,
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 	}
 
@@ -908,10 +910,11 @@ static int mcp23s08_probe(struct spi_dev
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
-			dev_dbg(&spi->dev,
-					"invalid or missing platform data\n");
-			return -EINVAL;
+		if (!pdata) {
+			pdata = devm_kzalloc(&spi->dev,
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 
 		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
Index: linux-3.18.13-rt10-r7s4/drivers/gpio/gpio-tps65912.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpio/gpio-tps65912.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpio/gpio-tps65912.c
@@ -26,9 +26,12 @@ struct tps65912_gpio_data {
 	struct gpio_chip gpio_chip;
 };
 
+#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip)
+
 static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 	int val;
 
 	val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset);
@@ -42,7 +45,8 @@ static int tps65912_gpio_get(struct gpio
 static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset,
 			      int value)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	if (value)
 		tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset,
@@ -55,7 +59,8 @@ static void tps65912_gpio_set(struct gpi
 static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset,
 				int value)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	/* Set the initial value */
 	tps65912_gpio_set(gc, offset, value);
@@ -66,7 +71,8 @@ static int tps65912_gpio_output(struct g
 
 static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+	struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+	struct tps65912 *tps65912 = tps65912_gpio->tps65912;
 
 	return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset,
 								GPIO_CFG_MASK);
Index: linux-3.18.13-rt10-r7s4/drivers/gpio/gpiolib-of.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpio/gpiolib-of.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpio/gpiolib-of.c
@@ -45,8 +45,15 @@ static int of_gpiochip_find_and_xlate(st
 		return false;
 
 	ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags);
-	if (ret < 0)
+	if (ret < 0) {
+		/* We've found a gpio chip, but the translation failed.
+		 * Store translation error in out_gpio.
+		 * Return false to keep looking, as more than one gpio chip
+		 * could be registered per of-node.
+		 */
+		gg_data->out_gpio = ERR_PTR(ret);
 		return false;
+	 }
 
 	gg_data->out_gpio = gpiochip_get_desc(gc, ret);
 	return true;
Index: linux-3.18.13-rt10-r7s4/drivers/gpio/gpiolib-sysfs.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpio/gpiolib-sysfs.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpio/gpiolib-sysfs.c
@@ -128,7 +128,7 @@ static ssize_t gpio_value_store(struct d
 	return status;
 }
 
-static const DEVICE_ATTR(value, 0644,
+static DEVICE_ATTR(value, 0644,
 		gpio_value_show, gpio_value_store);
 
 static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
@@ -353,18 +353,15 @@ static ssize_t gpio_active_low_store(str
 	return status ? : size;
 }
 
-static const DEVICE_ATTR(active_low, 0644,
+static DEVICE_ATTR(active_low, 0644,
 		gpio_active_low_show, gpio_active_low_store);
 
-static const struct attribute *gpio_attrs[] = {
+static struct attribute *gpio_attrs[] = {
 	&dev_attr_value.attr,
 	&dev_attr_active_low.attr,
 	NULL,
 };
-
-static const struct attribute_group gpio_attr_group = {
-	.attrs = (struct attribute **) gpio_attrs,
-};
+ATTRIBUTE_GROUPS(gpio);
 
 /*
  * /sys/class/gpio/gpiochipN/
@@ -400,16 +397,13 @@ static ssize_t chip_ngpio_show(struct de
 }
 static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL);
 
-static const struct attribute *gpiochip_attrs[] = {
+static struct attribute *gpiochip_attrs[] = {
 	&dev_attr_base.attr,
 	&dev_attr_label.attr,
 	&dev_attr_ngpio.attr,
 	NULL,
 };
-
-static const struct attribute_group gpiochip_attr_group = {
-	.attrs = (struct attribute **) gpiochip_attrs,
-};
+ATTRIBUTE_GROUPS(gpiochip);
 
 /*
  * /sys/class/gpio/export ... write-only
@@ -564,18 +558,15 @@ int gpiod_export(struct gpio_desc *desc,
 	if (desc->chip->names && desc->chip->names[offset])
 		ioname = desc->chip->names[offset];
 
-	dev = device_create(&gpio_class, desc->chip->dev, MKDEV(0, 0),
-			    desc, ioname ? ioname : "gpio%u",
-			    desc_to_gpio(desc));
+	dev = device_create_with_groups(&gpio_class, desc->chip->dev,
+					MKDEV(0, 0), desc, gpio_groups,
+					ioname ? ioname : "gpio%u",
+					desc_to_gpio(desc));
 	if (IS_ERR(dev)) {
 		status = PTR_ERR(dev);
 		goto fail_unlock;
 	}
 
-	status = sysfs_create_group(&dev->kobj, &gpio_attr_group);
-	if (status)
-		goto fail_unregister_device;
-
 	if (direction_may_change) {
 		status = device_create_file(dev, &dev_attr_direction);
 		if (status)
@@ -586,13 +577,15 @@ int gpiod_export(struct gpio_desc *desc,
 				       !test_bit(FLAG_IS_OUT, &desc->flags))) {
 		status = device_create_file(dev, &dev_attr_edge);
 		if (status)
-			goto fail_unregister_device;
+			goto fail_remove_attr_direction;
 	}
 
 	set_bit(FLAG_EXPORT, &desc->flags);
 	mutex_unlock(&sysfs_lock);
 	return 0;
 
+fail_remove_attr_direction:
+	device_remove_file(dev, &dev_attr_direction);
 fail_unregister_device:
 	device_unregister(dev);
 fail_unlock:
@@ -637,6 +630,7 @@ int gpiod_export_link(struct device *dev
 		if (tdev != NULL) {
 			status = sysfs_create_link(&dev->kobj, &tdev->kobj,
 						name);
+			put_device(tdev);
 		} else {
 			status = -ENODEV;
 		}
@@ -684,7 +678,7 @@ int gpiod_sysfs_set_active_low(struct gp
 	}
 
 	status = sysfs_set_active_low(desc, dev, value);
-
+	put_device(dev);
 unlock:
 	mutex_unlock(&sysfs_lock);
 
@@ -726,6 +720,8 @@ void gpiod_unexport(struct gpio_desc *de
 	mutex_unlock(&sysfs_lock);
 
 	if (dev) {
+		device_remove_file(dev, &dev_attr_edge);
+		device_remove_file(dev, &dev_attr_direction);
 		device_unregister(dev);
 		put_device(dev);
 	}
@@ -750,13 +746,13 @@ int gpiochip_export(struct gpio_chip *ch
 
 	/* use chip->base for the ID; it's already known to be unique */
 	mutex_lock(&sysfs_lock);
-	dev = device_create(&gpio_class, chip->dev, MKDEV(0, 0), chip,
-				"gpiochip%d", chip->base);
-	if (!IS_ERR(dev)) {
-		status = sysfs_create_group(&dev->kobj,
-				&gpiochip_attr_group);
-	} else
+	dev = device_create_with_groups(&gpio_class, chip->dev, MKDEV(0, 0),
+					chip, gpiochip_groups,
+					"gpiochip%d", chip->base);
+	if (IS_ERR(dev))
 		status = PTR_ERR(dev);
+	else
+		status = 0;
 	chip->exported = (status == 0);
 	mutex_unlock(&sysfs_lock);
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpio/gpiolib.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpio/gpiolib.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpio/gpiolib.c
@@ -268,6 +268,9 @@ int gpiochip_add(struct gpio_chip *chip)
 
 	spin_unlock_irqrestore(&gpio_lock, flags);
 
+	if (status)
+		goto fail;
+
 #ifdef CONFIG_PINCTRL
 	INIT_LIST_HEAD(&chip->pin_ranges);
 #endif
@@ -275,12 +278,12 @@ int gpiochip_add(struct gpio_chip *chip)
 	of_gpiochip_add(chip);
 	acpi_gpiochip_add(chip);
 
-	if (status)
-		goto fail;
-
 	status = gpiochip_export(chip);
-	if (status)
+	if (status) {
+		acpi_gpiochip_remove(chip);
+		of_gpiochip_remove(chip);
 		goto fail;
+	}
 
 	pr_debug("%s: registered GPIOs %d to %d on device: %s\n", __func__,
 		chip->base, chip->base + chip->ngpio - 1,
@@ -313,14 +316,13 @@ void gpiochip_remove(struct gpio_chip *c
 	unsigned long	flags;
 	unsigned	id;
 
-	acpi_gpiochip_remove(chip);
-
-	spin_lock_irqsave(&gpio_lock, flags);
-
 	gpiochip_irqchip_remove(chip);
+
+	acpi_gpiochip_remove(chip);
 	gpiochip_remove_pin_ranges(chip);
 	of_gpiochip_remove(chip);
 
+	spin_lock_irqsave(&gpio_lock, flags);
 	for (id = 0; id < chip->ngpio; id++) {
 		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags))
 			dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_crtc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_crtc.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_crtc.c
@@ -42,9 +42,10 @@
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
 
-static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
-							struct drm_mode_fb_cmd2 *r,
-							struct drm_file *file_priv);
+static struct drm_framebuffer *
+internal_framebuffer_create(struct drm_device *dev,
+			    struct drm_mode_fb_cmd2 *r,
+			    struct drm_file *file_priv);
 
 /* Avoid boilerplate.  I'm tired of typing. */
 #define DRM_ENUM_NAME_FN(fnname, list)				\
@@ -530,17 +531,6 @@ void drm_framebuffer_reference(struct dr
 }
 EXPORT_SYMBOL(drm_framebuffer_reference);
 
-static void drm_framebuffer_free_bug(struct kref *kref)
-{
-	BUG();
-}
-
-static void __drm_framebuffer_unreference(struct drm_framebuffer *fb)
-{
-	DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
-	kref_put(&fb->refcount, drm_framebuffer_free_bug);
-}
-
 /**
  * drm_framebuffer_unregister_private - unregister a private fb from the lookup idr
  * @fb: fb to unregister
@@ -1331,7 +1321,7 @@ void drm_plane_force_disable(struct drm_
 		return;
 	}
 	/* disconnect the plane from the fb and crtc: */
-	__drm_framebuffer_unreference(plane->old_fb);
+	drm_framebuffer_unreference(plane->old_fb);
 	plane->old_fb = NULL;
 	plane->fb = NULL;
 	plane->crtc = NULL;
@@ -2774,13 +2764,11 @@ static int drm_mode_cursor_universal(str
 	 */
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (req->handle) {
-			fb = add_framebuffer_internal(dev, &fbreq, file_priv);
+			fb = internal_framebuffer_create(dev, &fbreq, file_priv);
 			if (IS_ERR(fb)) {
 				DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n");
 				return PTR_ERR(fb);
 			}
-
-			drm_framebuffer_reference(fb);
 		} else {
 			fb = NULL;
 		}
@@ -3149,9 +3137,10 @@ static int framebuffer_check(const struc
 	return 0;
 }
 
-static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
-							struct drm_mode_fb_cmd2 *r,
-							struct drm_file *file_priv)
+static struct drm_framebuffer *
+internal_framebuffer_create(struct drm_device *dev,
+			    struct drm_mode_fb_cmd2 *r,
+			    struct drm_file *file_priv)
 {
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_framebuffer *fb;
@@ -3183,12 +3172,6 @@ static struct drm_framebuffer *add_frame
 		return fb;
 	}
 
-	mutex_lock(&file_priv->fbs_lock);
-	r->fb_id = fb->base.id;
-	list_add(&fb->filp_head, &file_priv->fbs);
-	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
-	mutex_unlock(&file_priv->fbs_lock);
-
 	return fb;
 }
 
@@ -3210,15 +3193,24 @@ static struct drm_framebuffer *add_frame
 int drm_mode_addfb2(struct drm_device *dev,
 		    void *data, struct drm_file *file_priv)
 {
+	struct drm_mode_fb_cmd2 *r = data;
 	struct drm_framebuffer *fb;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	fb = add_framebuffer_internal(dev, data, file_priv);
+	fb = internal_framebuffer_create(dev, r, file_priv);
 	if (IS_ERR(fb))
 		return PTR_ERR(fb);
 
+	/* Transfer ownership to the filp for reaping on close */
+
+	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
+	mutex_lock(&file_priv->fbs_lock);
+	r->fb_id = fb->base.id;
+	list_add(&fb->filp_head, &file_priv->fbs);
+	mutex_unlock(&file_priv->fbs_lock);
+
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_dp_helper.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_dp_helper.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_dp_helper.c
@@ -378,10 +378,11 @@ static int drm_dp_dpcd_access(struct drm
 
 	/*
 	 * The specification doesn't give any recommendation on how often to
-	 * retry native transactions, so retry 7 times like for I2C-over-AUX
-	 * transactions.
+	 * retry native transactions. We used to retry 7 times like for
+	 * aux i2c transactions but real world devices this wasn't
+	 * sufficient, bump to 32 which makes Dell 4k monitors happier.
 	 */
-	for (retry = 0; retry < 7; retry++) {
+	for (retry = 0; retry < 32; retry++) {
 
 		mutex_lock(&aux->hw_mutex);
 		err = aux->transfer(aux, &msg);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_dp_mst_topology.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_dp_mst_topology.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -839,6 +839,8 @@ static void drm_dp_put_mst_branch_device
 
 static void drm_dp_port_teardown_pdt(struct drm_dp_mst_port *port, int old_pdt)
 {
+	struct drm_dp_mst_branch *mstb;
+
 	switch (old_pdt) {
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 	case DP_PEER_DEVICE_SST_SINK:
@@ -846,8 +848,9 @@ static void drm_dp_port_teardown_pdt(str
 		drm_dp_mst_unregister_i2c_bus(&port->aux);
 		break;
 	case DP_PEER_DEVICE_MST_BRANCHING:
-		drm_dp_put_mst_branch_device(port->mstb);
+		mstb = port->mstb;
 		port->mstb = NULL;
+		drm_dp_put_mst_branch_device(mstb);
 		break;
 	}
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_edid_load.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_edid_load.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_edid_load.c
@@ -288,6 +288,7 @@ int drm_load_edid_firmware(struct drm_co
 
 	drm_mode_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
+	drm_edid_to_eld(connector, edid);
 	kfree(edid);
 
 	return ret;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_fb_helper.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_fb_helper.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_fb_helper.c
@@ -145,6 +145,31 @@ int drm_fb_helper_add_one_connector(stru
 }
 EXPORT_SYMBOL(drm_fb_helper_add_one_connector);
 
+static void remove_from_modeset(struct drm_mode_set *set,
+		struct drm_connector *connector)
+{
+	int i, j;
+
+	for (i = 0; i < set->num_connectors; i++) {
+		if (set->connectors[i] == connector)
+			break;
+	}
+
+	if (i == set->num_connectors)
+		return;
+
+	for (j = i + 1; j < set->num_connectors; j++) {
+		set->connectors[j - 1] = set->connectors[j];
+	}
+	set->num_connectors--;
+
+	/* because i915 is pissy about this..
+	 * TODO maybe need to makes sure we set it back to !=NULL somewhere?
+	 */
+	if (set->num_connectors == 0)
+		set->fb = NULL;
+}
+
 int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 				       struct drm_connector *connector)
 {
@@ -167,6 +192,11 @@ int drm_fb_helper_remove_one_connector(s
 	}
 	fb_helper->connector_count--;
 	kfree(fb_helper_connector);
+
+	/* also cleanup dangling references to the connector: */
+	for (i = 0; i < fb_helper->crtc_count; i++)
+		remove_from_modeset(&fb_helper->crtc_info[i].mode_set, connector);
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_remove_one_connector);
@@ -347,9 +377,18 @@ bool drm_fb_helper_restore_fbdev_mode_un
 {
 	struct drm_device *dev = fb_helper->dev;
 	bool ret;
+	bool do_delayed = false;
+
 	drm_modeset_lock_all(dev);
 	ret = restore_fbdev_mode(fb_helper);
+
+	do_delayed = fb_helper->delayed_hotplug;
+	if (do_delayed)
+		fb_helper->delayed_hotplug = false;
 	drm_modeset_unlock_all(dev);
+
+	if (do_delayed)
+		drm_fb_helper_hotplug_event(fb_helper);
 	return ret;
 }
 EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked);
@@ -888,10 +927,6 @@ int drm_fb_helper_set_par(struct fb_info
 
 	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
 
-	if (fb_helper->delayed_hotplug) {
-		fb_helper->delayed_hotplug = false;
-		drm_fb_helper_hotplug_event(fb_helper);
-	}
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_set_par);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_irq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_irq.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_irq.c
@@ -1029,7 +1029,8 @@ void drm_vblank_put(struct drm_device *d
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 
-	BUG_ON(atomic_read(&vblank->refcount) == 0);
+	if (WARN_ON(atomic_read(&vblank->refcount) == 0))
+		return;
 
 	if (WARN_ON(crtc >= dev->num_crtcs))
 		return;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_probe_helper.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/drm_probe_helper.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/drm_probe_helper.c
@@ -151,6 +151,7 @@ static int drm_helper_probe_single_conne
 			struct edid *edid = (struct edid *) connector->edid_blob_ptr->data;
 
 			count = drm_add_edid_modes(connector, edid);
+			drm_edid_to_eld(connector, edid);
 		} else
 			count = (*connector_funcs->get_modes)(connector);
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_drv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_drv.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_drv.c
@@ -692,11 +692,12 @@ static int __i915_drm_thaw(struct drm_de
 			spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 		}
 
-		intel_dp_mst_resume(dev);
 		drm_modeset_lock_all(dev);
 		intel_modeset_setup_hw_state(dev, true);
 		drm_modeset_unlock_all(dev);
 
+		intel_dp_mst_resume(dev);
+
 		/*
 		 * ... but also need to make sure that hotplug processing
 		 * doesn't cause havoc. Like in the driver load code we don't
@@ -1140,6 +1141,7 @@ static void vlv_save_gunit_s0ix_state(st
 	/* Gunit-Display CZ domain, 0x182028-0x1821CF */
 	s->gu_ctl0		= I915_READ(VLV_GU_CTL0);
 	s->gu_ctl1		= I915_READ(VLV_GU_CTL1);
+	s->pcbr			= I915_READ(VLV_PCBR);
 	s->clock_gate_dis2	= I915_READ(VLV_GUNIT_CLOCK_GATE2);
 
 	/*
@@ -1234,6 +1236,7 @@ static void vlv_restore_gunit_s0ix_state
 	/* Gunit-Display CZ domain, 0x182028-0x1821CF */
 	I915_WRITE(VLV_GU_CTL0,			s->gu_ctl0);
 	I915_WRITE(VLV_GU_CTL1,			s->gu_ctl1);
+	I915_WRITE(VLV_PCBR,			s->pcbr);
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE2,	s->clock_gate_dis2);
 }
 
@@ -1242,19 +1245,7 @@ int vlv_force_gfx_clock(struct drm_i915_
 	u32 val;
 	int err;
 
-	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
-	WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on);
-
 #define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT)
-	/* Wait for a previous force-off to settle */
-	if (force_on) {
-		err = wait_for(!COND, 20);
-		if (err) {
-			DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n",
-				  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
-			return err;
-		}
-	}
 
 	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
 	val &= ~VLV_GFX_CLK_FORCE_ON_BIT;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_drv.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_drv.h
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_drv.h
@@ -877,6 +877,7 @@ struct i915_suspend_saved_registers {
 	u32 savePIPEB_LINK_N1;
 	u32 saveMCHBAR_RENDER_STANDBY;
 	u32 savePCH_PORT_HOTPLUG;
+	u16 saveGCDGMBUS;
 };
 
 struct vlv_s0ix_state {
@@ -937,6 +938,7 @@ struct vlv_s0ix_state {
 	/* Display 2 CZ domain */
 	u32 gu_ctl0;
 	u32 gu_ctl1;
+	u32 pcbr;
 	u32 clock_gate_dis2;
 };
 
@@ -1665,8 +1667,6 @@ struct drm_i915_private {
 	 */
 	struct workqueue_struct *dp_wq;
 
-	uint32_t bios_vgacntr;
-
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
@@ -2077,8 +2077,8 @@ struct drm_i915_cmd_table {
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
-				 ((INTEL_DEVID(dev) & 0xf) == 0x2  || \
-				 (INTEL_DEVID(dev) & 0xf) == 0x6 || \
+				 ((INTEL_DEVID(dev) & 0xf) == 0x6 ||	\
+				 (INTEL_DEVID(dev) & 0xf) == 0xb ||	\
 				 (INTEL_DEVID(dev) & 0xf) == 0xe))
 #define IS_HSW_ULT(dev)		(IS_HASWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0A00)
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_gem.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem.c
@@ -3050,6 +3050,13 @@ static void i965_write_fence_reg(struct
 		u32 size = i915_gem_obj_ggtt_size(obj);
 		uint64_t val;
 
+		/* Adjust fence size to match tiled area */
+		if (obj->tiling_mode != I915_TILING_NONE) {
+			uint32_t row_size = obj->stride *
+				(obj->tiling_mode == I915_TILING_Y ? 32 : 8);
+			size = (size / row_size) * row_size;
+		}
+
 		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
 				 0xfffff000) << 32;
 		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
@@ -4193,7 +4200,7 @@ i915_gem_pin_ioctl(struct drm_device *de
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	if (INTEL_INFO(dev)->gen >= 6)
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
 	ret = i915_mutex_lock_interruptible(dev);
@@ -4249,6 +4256,9 @@ i915_gem_unpin_ioctl(struct drm_device *
 	struct drm_i915_gem_object *obj;
 	int ret;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -ENODEV;
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
@@ -4808,25 +4818,18 @@ i915_gem_init_hw(struct drm_device *dev)
 	for (i = 0; i < NUM_L3_SLICES(dev); i++)
 		i915_gem_l3_remap(&dev_priv->ring[RCS], i);
 
-	/*
-	 * XXX: Contexts should only be initialized once. Doing a switch to the
-	 * default context switch however is something we'd like to do after
-	 * reset or thaw (the latter may not actually be necessary for HW, but
-	 * goes with our code better). Context switching requires rings (for
-	 * the do_switch), but before enabling PPGTT. So don't move this.
-	 */
-	ret = i915_gem_context_enable(dev_priv);
+	ret = i915_ppgtt_init_hw(dev);
 	if (ret && ret != -EIO) {
-		DRM_ERROR("Context enable failed %d\n", ret);
+		DRM_ERROR("PPGTT enable failed %d\n", ret);
 		i915_gem_cleanup_ringbuffer(dev);
-
-		return ret;
 	}
 
-	ret = i915_ppgtt_init_hw(dev);
+	ret = i915_gem_context_enable(dev_priv);
 	if (ret && ret != -EIO) {
-		DRM_ERROR("PPGTT enable failed %d\n", ret);
+		DRM_ERROR("Context enable failed %d\n", ret);
 		i915_gem_cleanup_ringbuffer(dev);
+
+		return ret;
 	}
 
 	return ret;
@@ -5141,7 +5144,7 @@ static bool mutex_is_locked_by(struct mu
 	if (!mutex_is_locked(mutex))
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
 	return mutex->owner == task;
 #else
 	/* Since UP may be pre-empted, we cannot assume that we own the lock */
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_context.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_gem_context.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_context.c
@@ -468,7 +468,12 @@ mi_set_context(struct intel_engine_cs *r
 	       u32 hw_flags)
 {
 	u32 flags = hw_flags | MI_MM_SPACE_GTT;
-	int ret;
+	const int num_rings =
+		/* Use an extended w/a on ivb+ if signalling from other rings */
+		i915_semaphore_is_enabled(ring->dev) ?
+		hweight32(INTEL_INFO(ring->dev)->ring_mask) - 1 :
+		0;
+	int len, i, ret;
 
 	/* w/a: If Flush TLB Invalidation Mode is enabled, driver must do a TLB
 	 * invalidation prior to MI_SET_CONTEXT. On GEN6 we don't set the value
@@ -485,15 +490,31 @@ mi_set_context(struct intel_engine_cs *r
 	if (!IS_HASWELL(ring->dev) && INTEL_INFO(ring->dev)->gen < 8)
 		flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
 
-	ret = intel_ring_begin(ring, 6);
+
+	len = 4;
+	if (INTEL_INFO(ring->dev)->gen >= 7)
+		len += 2 + (num_rings ? 4*num_rings + 2 : 0);
+
+	ret = intel_ring_begin(ring, len);
 	if (ret)
 		return ret;
 
 	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */
-	if (INTEL_INFO(ring->dev)->gen >= 7)
+	if (INTEL_INFO(ring->dev)->gen >= 7) {
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_DISABLE);
-	else
-		intel_ring_emit(ring, MI_NOOP);
+		if (num_rings) {
+			struct intel_engine_cs *signaller;
+
+			intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(num_rings));
+			for_each_ring(signaller, to_i915(ring->dev), i) {
+				if (signaller == ring)
+					continue;
+
+				intel_ring_emit(ring, RING_PSMI_CTL(signaller->mmio_base));
+				intel_ring_emit(ring, _MASKED_BIT_ENABLE(GEN6_PSMI_SLEEP_MSG_DISABLE));
+			}
+		}
+	}
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
@@ -505,10 +526,21 @@ mi_set_context(struct intel_engine_cs *r
 	 */
 	intel_ring_emit(ring, MI_NOOP);
 
-	if (INTEL_INFO(ring->dev)->gen >= 7)
+	if (INTEL_INFO(ring->dev)->gen >= 7) {
+		if (num_rings) {
+			struct intel_engine_cs *signaller;
+
+			intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(num_rings));
+			for_each_ring(signaller, to_i915(ring->dev), i) {
+				if (signaller == ring)
+					continue;
+
+				intel_ring_emit(ring, RING_PSMI_CTL(signaller->mmio_base));
+				intel_ring_emit(ring, _MASKED_BIT_DISABLE(GEN6_PSMI_SLEEP_MSG_DISABLE));
+			}
+		}
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
-	else
-		intel_ring_emit(ring, MI_NOOP);
+	}
 
 	intel_ring_advance(ring);
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_stolen.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -137,7 +137,11 @@ static unsigned long i915_stolen_to_phys
 		r = devm_request_mem_region(dev->dev, base + 1,
 					    dev_priv->gtt.stolen_size - 1,
 					    "Graphics Stolen Memory");
-		if (r == NULL) {
+		/*
+		 * GEN3 firmware likes to smash pci bridges into the stolen
+		 * range. Apparently this works.
+		 */
+		if (r == NULL && !IS_GEN3(dev)) {
 			DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
 				  base, base + (uint32_t)dev_priv->gtt.stolen_size);
 			base = 0;
@@ -481,10 +485,7 @@ i915_gem_object_create_stolen_for_preall
 			stolen_offset, gtt_offset, size);
 
 	/* KISS and expect everything to be page-aligned */
-	BUG_ON(stolen_offset & 4095);
-	BUG_ON(size & 4095);
-
-	if (WARN_ON(size == 0))
+	if (WARN_ON(size == 0 || stolen_offset & 4095 || size & 4095))
 		return NULL;
 
 	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_tiling.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -315,9 +315,10 @@ i915_gem_set_tiling(struct drm_device *d
 		return -EINVAL;
 	}
 
+	mutex_lock(&dev->struct_mutex);
 	if (i915_gem_obj_is_pinned(obj) || obj->framebuffer_references) {
-		drm_gem_object_unreference_unlocked(&obj->base);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto err;
 	}
 
 	if (args->tiling_mode == I915_TILING_NONE) {
@@ -349,7 +350,6 @@ i915_gem_set_tiling(struct drm_device *d
 		}
 	}
 
-	mutex_lock(&dev->struct_mutex);
 	if (args->tiling_mode != obj->tiling_mode ||
 	    args->stride != obj->stride) {
 		/* We need to rebind the object if its current allocation
@@ -395,6 +395,7 @@ i915_gem_set_tiling(struct drm_device *d
 		obj->bit_17 = NULL;
 	}
 
+err:
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_userptr.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -113,7 +113,10 @@ restart:
 			continue;
 
 		obj = mo->obj;
-		drm_gem_object_reference(&obj->base);
+
+		if (!kref_get_unless_zero(&obj->base.refcount))
+			continue;
+
 		spin_unlock(&mn->lock);
 
 		cancel_userptr(obj);
@@ -149,7 +152,20 @@ static void i915_gem_userptr_mn_invalida
 			it = interval_tree_iter_first(&mn->objects, start, end);
 		if (it != NULL) {
 			obj = container_of(it, struct i915_mmu_object, it)->obj;
-			drm_gem_object_reference(&obj->base);
+
+			/* The mmu_object is released late when destroying the
+			 * GEM object so it is entirely possible to gain a
+			 * reference on an object in the process of being freed
+			 * since our serialisation is via the spinlock and not
+			 * the struct_mutex - and consequently use it after it
+			 * is freed and then double free it.
+			 */
+			if (!kref_get_unless_zero(&obj->base.refcount)) {
+				spin_unlock(&mn->lock);
+				serial = 0;
+				continue;
+			}
+
 			serial = mn->serial;
 		}
 		spin_unlock(&mn->lock);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_irq.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_irq.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_irq.c
@@ -2123,6 +2123,9 @@ static irqreturn_t valleyview_irq_handle
 	u32 iir, gt_iir, pm_iir;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	while (true) {
 		/* Find, clear, then process each source of interrupt */
 
@@ -2167,6 +2170,9 @@ static irqreturn_t cherryview_irq_handle
 	u32 master_ctl, iir;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	for (;;) {
 		master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL;
 		iir = I915_READ(VLV_IIR);
@@ -2455,6 +2461,9 @@ static irqreturn_t ironlake_irq_handler(
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	/* We get interrupts on unclaimed registers, so check for this before we
 	 * do any I915_{READ,WRITE}. */
 	intel_uncore_check_errors(dev);
@@ -2525,6 +2534,9 @@ static irqreturn_t gen8_irq_handler(int
 	uint32_t tmp = 0;
 	enum pipe pipe;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	master_ctl = I915_READ(GEN8_MASTER_IRQ);
 	master_ctl &= ~GEN8_MASTER_IRQ_CONTROL;
 	if (!master_ctl)
@@ -4022,8 +4034,6 @@ static bool i8xx_handle_vblank(struct dr
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -4033,6 +4043,7 @@ static bool i8xx_handle_vblank(struct dr
 	if (I915_READ16(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
@@ -4053,6 +4064,9 @@ static irqreturn_t i8xx_irq_handler(int
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ16(IIR);
 	if (iir == 0)
 		return IRQ_NONE;
@@ -4210,8 +4224,6 @@ static bool i915_handle_vblank(struct dr
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -4221,6 +4233,7 @@ static bool i915_handle_vblank(struct dr
 	if (I915_READ(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
@@ -4240,6 +4253,9 @@ static irqreturn_t i915_irq_handler(int
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 	int pipe, ret = IRQ_NONE;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ(IIR);
 	do {
 		bool irq_received = (iir & ~flip_mask) != 0;
@@ -4468,6 +4484,9 @@ static irqreturn_t i965_irq_handler(int
 		I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT |
 		I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	iir = I915_READ(IIR);
 
 	for (;;) {
@@ -4779,4 +4798,5 @@ void intel_runtime_pm_restore_interrupts
 	dev_priv->pm._irqs_disabled = false;
 	dev->driver->irq_preinstall(dev);
 	dev->driver->irq_postinstall(dev);
+	synchronize_irq(dev_priv->dev->irq);
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_reg.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_reg.h
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_reg.h
@@ -74,6 +74,7 @@
 #define   I915_GC_RENDER_CLOCK_166_MHZ	(0 << 0)
 #define   I915_GC_RENDER_CLOCK_200_MHZ	(1 << 0)
 #define   I915_GC_RENDER_CLOCK_333_MHZ	(4 << 0)
+#define GCDGMBUS 0xcc
 #define PCI_LBPC 0xf4 /* legacy/combination backlight modes, also called LBB */
 
 
@@ -370,6 +371,7 @@
 #define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
 #define   PIPE_CONTROL_CS_STALL				(1<<20)
 #define   PIPE_CONTROL_TLB_INVALIDATE			(1<<18)
+#define   PIPE_CONTROL_MEDIA_STATE_CLEAR		(1<<16)
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
 #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
@@ -1071,6 +1073,7 @@ enum punit_power_well {
 #define GEN6_VERSYNC	(RING_SYNC_1(VEBOX_RING_BASE))
 #define GEN6_VEVSYNC	(RING_SYNC_2(VEBOX_RING_BASE))
 #define GEN6_NOSYNC 0
+#define RING_PSMI_CTL(base)	((base)+0x50)
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
@@ -1401,6 +1404,7 @@ enum punit_power_well {
 #define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
 
 #define GEN6_RC_SLEEP_PSMI_CONTROL	0x2050
+#define   GEN6_PSMI_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
 #define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1<<10)
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_suspend.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/i915_suspend.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/i915_suspend.c
@@ -328,6 +328,10 @@ int i915_save_state(struct drm_device *d
 		}
 	}
 
+	if (IS_GEN4(dev))
+		pci_read_config_word(dev->pdev, GCDGMBUS,
+				     &dev_priv->regfile.saveGCDGMBUS);
+
 	/* Cache mode state */
 	if (INTEL_INFO(dev)->gen < 7)
 		dev_priv->regfile.saveCACHE_MODE_0 = I915_READ(CACHE_MODE_0);
@@ -356,6 +360,10 @@ int i915_restore_state(struct drm_device
 	mutex_lock(&dev->struct_mutex);
 
 	i915_gem_restore_fences(dev);
+
+	if (IS_GEN4(dev))
+		pci_write_config_word(dev->pdev, GCDGMBUS,
+				      dev_priv->regfile.saveGCDGMBUS);
 	i915_restore_display(dev);
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET)) {
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_display.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_display.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_display.c
@@ -2358,13 +2358,19 @@ static bool intel_alloc_plane_obj(struct
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_gem_object *obj = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = { 0 };
-	u32 base = plane_config->base;
+	u32 base_aligned = round_down(plane_config->base, PAGE_SIZE);
+	u32 size_aligned = round_up(plane_config->base + plane_config->size,
+				    PAGE_SIZE);
+
+	size_aligned -= base_aligned;
 
 	if (plane_config->size == 0)
 		return false;
 
-	obj = i915_gem_object_create_stolen_for_preallocated(dev, base, base,
-							     plane_config->size);
+	obj = i915_gem_object_create_stolen_for_preallocated(dev,
+							     base_aligned,
+							     base_aligned,
+							     size_aligned);
 	if (!obj)
 		return false;
 
@@ -6383,8 +6389,7 @@ static void i9xx_get_plane_config(struct
 	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
 					    plane_config->tiled);
 
-	plane_config->size = PAGE_ALIGN(crtc->base.primary->fb->pitches[0] *
-					aligned_height);
+	plane_config->size = crtc->base.primary->fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe/plane %d/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe, plane, crtc->base.primary->fb->width,
@@ -7424,8 +7429,7 @@ static void ironlake_get_plane_config(st
 	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
 					    plane_config->tiled);
 
-	plane_config->size = PAGE_ALIGN(crtc->base.primary->fb->pitches[0] *
-					aligned_height);
+	plane_config->size = crtc->base.primary->fb->pitches[0] * aligned_height;
 
 	DRM_DEBUG_KMS("pipe/plane %d/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n",
 		      pipe, plane, crtc->base.primary->fb->width,
@@ -10019,7 +10023,7 @@ static int intel_crtc_page_flip(struct d
 		if (obj->tiling_mode != work->old_fb_obj->tiling_mode)
 			/* vlv: DISPLAY_FLIP fails to change tiling */
 			ring = NULL;
-	} else if (IS_IVYBRIDGE(dev)) {
+	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
 		ring = &dev_priv->ring[BCS];
 	} else if (INTEL_INFO(dev)->gen >= 7) {
 		ring = obj->ring;
@@ -12895,6 +12899,9 @@ static struct intel_quirk intel_quirks[]
 
 	/* HP Chromebook 14 (Celeron 2955U) */
 	{ 0x0a06, 0x103c, 0x21ed, quirk_backlight_present },
+
+	/* Dell Chromebook 11 */
+	{ 0x0a06, 0x1028, 0x0a35, quirk_backlight_present },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -12933,11 +12940,7 @@ static void i915_disable_vga(struct drm_
 	vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
 	udelay(300);
 
-	/*
-	 * Fujitsu-Siemens Lifebook S6010 (830) has problems resuming
-	 * from S3 without preserving (some of?) the other bits.
-	 */
-	I915_WRITE(vga_reg, dev_priv->bios_vgacntr | VGA_DISP_DISABLE);
+	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
 	POSTING_READ(vga_reg);
 }
 
@@ -13026,8 +13029,6 @@ void intel_modeset_init(struct drm_devic
 
 	intel_shared_dpll_init(dev);
 
-	/* save the BIOS value before clobbering it */
-	dev_priv->bios_vgacntr = I915_READ(i915_vgacntrl_reg(dev));
 	/* Just disable it once at startup */
 	i915_disable_vga(dev);
 	intel_setup_outputs(dev);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_dp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_dp.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_dp.c
@@ -3645,8 +3645,6 @@ intel_dp_link_down(struct intel_dp *inte
 	enum port port = intel_dig_port->port;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(intel_dig_port->base.base.crtc);
 	uint32_t DP = intel_dp->DP;
 
 	if (WARN_ON(HAS_DDI(dev)))
@@ -3671,8 +3669,6 @@ intel_dp_link_down(struct intel_dp *inte
 
 	if (HAS_PCH_IBX(dev) &&
 	    I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
-		struct drm_crtc *crtc = intel_dig_port->base.base.crtc;
-
 		/* Hardware workaround: leaving our transcoder select
 		 * set to transcoder B while it's off will prevent the
 		 * corresponding HDMI output on transcoder A.
@@ -3683,18 +3679,7 @@ intel_dp_link_down(struct intel_dp *inte
 		 */
 		DP &= ~DP_PIPEB_SELECT;
 		I915_WRITE(intel_dp->output_reg, DP);
-
-		/* Changes to enable or select take place the vblank
-		 * after being written.
-		 */
-		if (WARN_ON(crtc == NULL)) {
-			/* We should never try to disable a port without a crtc
-			 * attached. For paranoia keep the code around for a
-			 * bit. */
-			POSTING_READ(intel_dp->output_reg);
-			msleep(50);
-		} else
-			intel_wait_for_vblank(dev, intel_crtc->pipe);
+		POSTING_READ(intel_dp->output_reg);
 	}
 
 	DP &= ~DP_AUDIO_OUTPUT_ENABLE;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_lrc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_lrc.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_lrc.c
@@ -1106,15 +1106,17 @@ static int gen8_emit_flush(struct intel_
 
 	cmd = MI_FLUSH_DW + 1;
 
-	if (ring == &dev_priv->ring[VCS]) {
-		if (invalidate_domains & I915_GEM_GPU_DOMAINS)
-			cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-				MI_FLUSH_DW_STORE_INDEX |
-				MI_FLUSH_DW_OP_STOREDW;
-	} else {
-		if (invalidate_domains & I915_GEM_DOMAIN_RENDER)
-			cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-				MI_FLUSH_DW_OP_STOREDW;
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
+	if (invalidate_domains & I915_GEM_GPU_DOMAINS) {
+		cmd |= MI_INVALIDATE_TLB;
+		if (ring == &dev_priv->ring[VCS])
+			cmd |= MI_INVALIDATE_BSD;
 	}
 
 	intel_logical_ring_emit(ringbuf, cmd);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_panel.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_panel.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_panel.c
@@ -947,7 +947,7 @@ void intel_panel_enable_backlight(struct
 
 	WARN_ON(panel->backlight.max == 0);
 
-	if (panel->backlight.level == 0) {
+	if (panel->backlight.level <= panel->backlight.min) {
 		panel->backlight.level = panel->backlight.max;
 		if (panel->backlight.device)
 			panel->backlight.device->props.brightness =
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_pm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_pm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_pm.c
@@ -6520,29 +6520,6 @@ static void chv_pipe_power_well_disable(
 	chv_set_pipe_power_well(dev_priv, power_well, false);
 }
 
-static void check_power_well_state(struct drm_i915_private *dev_priv,
-				   struct i915_power_well *power_well)
-{
-	bool enabled = power_well->ops->is_enabled(dev_priv, power_well);
-
-	if (power_well->always_on || !i915.disable_power_well) {
-		if (!enabled)
-			goto mismatch;
-
-		return;
-	}
-
-	if (enabled != (power_well->count > 0))
-		goto mismatch;
-
-	return;
-
-mismatch:
-	WARN(1, "state mismatch for '%s' (always_on %d hw state %d use-count %d disable_power_well %d\n",
-		  power_well->name, power_well->always_on, enabled,
-		  power_well->count, i915.disable_power_well);
-}
-
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain)
 {
@@ -6562,8 +6539,6 @@ void intel_display_power_get(struct drm_
 			power_well->ops->enable(dev_priv, power_well);
 			power_well->hw_enabled = true;
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	power_domains->domain_use_count[domain]++;
@@ -6593,8 +6568,6 @@ void intel_display_power_put(struct drm_
 			power_well->hw_enabled = false;
 			power_well->ops->disable(dev_priv, power_well);
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	mutex_unlock(&power_domains->lock);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_ringbuffer.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -362,12 +362,15 @@ gen7_render_ring_flush(struct intel_engi
 		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR;
 		/*
 		 * TLB invalidate requires a post-sync write.
 		 */
 		flags |= PIPE_CONTROL_QW_WRITE;
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
 
+		flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD;
+
 		/* Workaround: we must issue a pipe_control with CS-stall bit
 		 * set before a pipe_control command that has the state cache
 		 * invalidate bit set. */
@@ -2136,6 +2139,14 @@ static int gen6_bsd_ring_flush(struct in
 	cmd = MI_FLUSH_DW;
 	if (INTEL_INFO(ring->dev)->gen >= 8)
 		cmd += 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
 	/*
 	 * Bspec vol 1c.5 - video engine command streamer:
 	 * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2143,8 +2154,8 @@ static int gen6_bsd_ring_flush(struct in
 	 * Post-Sync Operation field is a value of 1h or 3h."
 	 */
 	if (invalidate & I915_GEM_GPU_DOMAINS)
-		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-			MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+		cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	if (INTEL_INFO(ring->dev)->gen >= 8) {
@@ -2239,6 +2250,14 @@ static int gen6_ring_flush(struct intel_
 	cmd = MI_FLUSH_DW;
 	if (INTEL_INFO(ring->dev)->gen >= 8)
 		cmd += 1;
+
+	/* We always require a command barrier so that subsequent
+	 * commands, such as breadcrumb interrupts, are strictly ordered
+	 * wrt the contents of the write cache being flushed to memory
+	 * (and thus being coherent from the CPU).
+	 */
+	cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
 	/*
 	 * Bspec vol 1c.3 - blitter engine command streamer:
 	 * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2246,8 +2265,7 @@ static int gen6_ring_flush(struct intel_
 	 * Post-Sync Operation field is a value of 1h or 3h."
 	 */
 	if (invalidate & I915_GEM_DOMAIN_RENDER)
-		cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-			MI_FLUSH_DW_OP_STOREDW;
+		cmd |= MI_INVALIDATE_TLB;
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
 	if (INTEL_INFO(ring->dev)->gen >= 8) {
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_sideband.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_sideband.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_sideband.c
@@ -82,7 +82,7 @@ u32 vlv_punit_read(struct drm_i915_priva
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT,
 			SB_CRRDDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
@@ -94,7 +94,7 @@ void vlv_punit_write(struct drm_i915_pri
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT,
 			SB_CRWRDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
@@ -103,7 +103,7 @@ u32 vlv_bunit_read(struct drm_i915_priva
 {
 	u32 val = 0;
 
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT,
 			SB_CRRDDA_NP, reg, &val);
 
 	return val;
@@ -111,7 +111,7 @@ u32 vlv_bunit_read(struct drm_i915_priva
 
 void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT,
 			SB_CRWRDA_NP, reg, &val);
 }
 
@@ -122,7 +122,7 @@ u32 vlv_nc_read(struct drm_i915_private
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_NC,
 			SB_CRRDDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
@@ -132,56 +132,56 @@ u32 vlv_nc_read(struct drm_i915_private
 u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPIO_NC,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPIO_NC,
 			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCK,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCK,
 			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCU,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_CCU,
 			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPS_CORE,
 			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE,
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(0, 0), IOSF_PORT_GPS_CORE,
 			SB_CRWRDA_NP, reg, &val);
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_sprite.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_sprite.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_sprite.c
@@ -1178,7 +1178,7 @@ int intel_sprite_set_colorkey(struct drm
 	drm_modeset_lock_all(dev);
 
 	plane = drm_plane_find(dev, set->plane_id);
-	if (!plane) {
+	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY) {
 		ret = -ENOENT;
 		goto out_unlock;
 	}
@@ -1205,7 +1205,7 @@ int intel_sprite_get_colorkey(struct drm
 	drm_modeset_lock_all(dev);
 
 	plane = drm_plane_find(dev, get->plane_id);
-	if (!plane) {
+	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY) {
 		ret = -ENOENT;
 		goto out_unlock;
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_uncore.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/i915/intel_uncore.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/i915/intel_uncore.c
@@ -43,8 +43,8 @@
 static void
 assert_device_not_suspended(struct drm_i915_private *dev_priv)
 {
-	WARN(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
-	     "Device suspended\n");
+	WARN_ONCE(HAS_RUNTIME_PM(dev_priv->dev) && dev_priv->pm.suspended,
+		  "Device suspended\n");
 }
 
 static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/core/core/event.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/nouveau/core/core/event.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/core/core/event.c
@@ -26,7 +26,7 @@
 void
 nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (--event->refs[index * event->types_nr + type] == 0) {
@@ -39,7 +39,7 @@ nvkm_event_put(struct nvkm_event *event,
 void
 nvkm_event_get(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (++event->refs[index * event->types_nr + type] == 1) {
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/core/core/notify.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/nouveau/core/core/notify.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/core/core/notify.c
@@ -98,7 +98,7 @@ nvkm_notify_send(struct nvkm_notify *not
 	struct nvkm_event *event = notify->event;
 	unsigned long flags;
 
-	BUG_ON(!spin_is_locked(&event->list_lock));
+	assert_spin_locked(&event->list_lock);
 	BUG_ON(size != notify->size);
 
 	spin_lock_irqsave(&event->refs_lock, flags);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
@@ -24,13 +24,6 @@
 
 #include "nv04.h"
 
-static void
-nv4c_mc_msi_rearm(struct nouveau_mc *pmc)
-{
-	struct nv04_mc_priv *priv = (void *)pmc;
-	nv_wr08(priv, 0x088050, 0xff);
-}
-
 struct nouveau_oclass *
 nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 	.base.handle = NV_SUBDEV(MC, 0x4c),
@@ -41,5 +34,4 @@ nv4c_mc_oclass = &(struct nouveau_mc_ocl
 		.fini = _nouveau_mc_fini,
 	},
 	.intr = nv04_mc_intr,
-	.msi_rearm = nv4c_mc_msi_rearm,
 }.base;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/nouveau_ttm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -28,6 +28,7 @@
 #include "nouveau_ttm.h"
 #include "nouveau_gem.h"
 
+#include "drm_legacy.h"
 static int
 nouveau_vram_manager_init(struct ttm_mem_type_manager *man, unsigned long psize)
 {
@@ -281,7 +282,7 @@ nouveau_ttm_mmap(struct file *filp, stru
 	struct nouveau_drm *drm = nouveau_drm(file_priv->minor->dev);
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return -EINVAL;
+		return drm_legacy_mmap(filp, vma);
 
 	return ttm_bo_mmap(filp, vma, &drm->ttm.bdev);
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/atombios_crtc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/atombios_crtc.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1405,6 +1405,9 @@ static int dce4_crtc_do_set_base(struct
 	       (x << 16) | y);
 	viewport_w = crtc->mode.hdisplay;
 	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
+	if ((rdev->family >= CHIP_BONAIRE) &&
+	    (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE))
+		viewport_h *= 2;
 	WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
 	       (viewport_w << 16) | viewport_h);
 
@@ -1851,10 +1854,9 @@ static int radeon_atom_pick_pll(struct d
 				return pll;
 		}
 		/* otherwise, pick one of the plls */
-		if ((rdev->family == CHIP_KAVERI) ||
-		    (rdev->family == CHIP_KABINI) ||
+		if ((rdev->family == CHIP_KABINI) ||
 		    (rdev->family == CHIP_MULLINS)) {
-			/* KB/KV/ML has PPLL1 and PPLL2 */
+			/* KB/ML has PPLL1 and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -1863,7 +1865,7 @@ static int radeon_atom_pick_pll(struct d
 			DRM_ERROR("unable to allocate a PPLL\n");
 			return ATOM_PPLL_INVALID;
 		} else {
-			/* CI has PPLL0, PPLL1, and PPLL2 */
+			/* CI/KV has PPLL0, PPLL1, and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -2154,6 +2156,7 @@ static void atombios_crtc_disable(struct
 	case ATOM_PPLL0:
 		/* disable the ppll */
 		if ((rdev->family == CHIP_ARUBA) ||
+		    (rdev->family == CHIP_KAVERI) ||
 		    (rdev->family == CHIP_BONAIRE) ||
 		    (rdev->family == CHIP_HAWAII))
 			atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/atombios_dp.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/atombios_dp.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/atombios_dp.c
@@ -492,6 +492,10 @@ int radeon_dp_mode_valid_helper(struct d
 	struct radeon_connector_atom_dig *dig_connector;
 	int dp_clock;
 
+	if ((mode->clock > 340000) &&
+	    (!radeon_connector_is_dp12_capable(connector)))
+		return MODE_CLOCK_HIGH;
+
 	if (!radeon_connector->con_priv)
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
@@ -619,10 +623,8 @@ static int radeon_dp_link_train_init(str
 		drm_dp_dpcd_writeb(dp_info->aux,
 				   DP_DOWNSPREAD_CTRL, 0);
 
-	if ((dp_info->connector->connector_type == DRM_MODE_CONNECTOR_eDP) &&
-	    (dig->panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)) {
+	if (dig->panel_mode == DP_PANEL_MODE_INTERNAL_DP2_MODE)
 		drm_dp_dpcd_writeb(dp_info->aux, DP_EDP_CONFIGURATION_SET, 1);
-	}
 
 	/* set the lane count on the sink */
 	tmp = dp_info->dp_lane_count;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/ci_dpm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/ci_dpm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/ci_dpm.c
@@ -4729,7 +4729,7 @@ void ci_dpm_disable(struct radeon_device
 	ci_enable_spread_spectrum(rdev, false);
 	ci_enable_auto_throttle_source(rdev, RADEON_DPM_AUTO_THROTTLE_SRC_THERMAL, false);
 	ci_stop_dpm(rdev);
-	ci_enable_ds_master_switch(rdev, true);
+	ci_enable_ds_master_switch(rdev, false);
 	ci_enable_ulv(rdev, false);
 	ci_clear_vc(rdev);
 	ci_reset_to_default(rdev);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/cik.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/cik.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/cik.c
@@ -3880,7 +3880,21 @@ void cik_fence_gfx_ring_emit(struct rade
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
 	u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
 
-	/* EVENT_WRITE_EOP - flush caches, send int */
+	/* Workaround for cache flush problems. First send a dummy EOP
+	 * event down the pipe with seq one below.
+	 */
+	radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
+	radeon_ring_write(ring, (EOP_TCL1_ACTION_EN |
+				 EOP_TC_ACTION_EN |
+				 EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) |
+				 EVENT_INDEX(5)));
+	radeon_ring_write(ring, addr & 0xfffffffc);
+	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
+				DATA_SEL(1) | INT_SEL(0));
+	radeon_ring_write(ring, fence->seq - 1);
+	radeon_ring_write(ring, 0);
+
+	/* Then send the real EOP event down the pipe. */
 	radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 	radeon_ring_write(ring, (EOP_TCL1_ACTION_EN |
 				 EOP_TC_ACTION_EN |
@@ -6314,6 +6328,7 @@ static void cik_enable_mgcg(struct radeo
 		}
 
 		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
+		data |= 0x00000001;
 		data &= 0xfffffffd;
 		if (orig != data)
 			WREG32(RLC_CGTT_MGCG_OVERRIDE, data);
@@ -6345,7 +6360,7 @@ static void cik_enable_mgcg(struct radeo
 		}
 	} else {
 		orig = data = RREG32(RLC_CGTT_MGCG_OVERRIDE);
-		data |= 0x00000002;
+		data |= 0x00000003;
 		if (orig != data)
 			WREG32(RLC_CGTT_MGCG_OVERRIDE, data);
 
@@ -7294,7 +7309,6 @@ int cik_irq_set(struct radeon_device *rd
 	u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6;
 	u32 grbm_int_cntl = 0;
 	u32 dma_cntl, dma_cntl1;
-	u32 thermal_int;
 
 	if (!rdev->irq.installed) {
 		WARN(1, "Can't enable IRQ/MSI because no handler is installed\n");
@@ -7331,13 +7345,6 @@ int cik_irq_set(struct radeon_device *rd
 	cp_m2p2 = RREG32(CP_ME2_PIPE2_INT_CNTL) & ~TIME_STAMP_INT_ENABLE;
 	cp_m2p3 = RREG32(CP_ME2_PIPE3_INT_CNTL) & ~TIME_STAMP_INT_ENABLE;
 
-	if (rdev->flags & RADEON_IS_IGP)
-		thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL) &
-			~(THERM_INTH_MASK | THERM_INTL_MASK);
-	else
-		thermal_int = RREG32_SMC(CG_THERMAL_INT) &
-			~(THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW);
-
 	/* enable CP interrupts on all rings */
 	if (atomic_read(&rdev->irq.ring_int[RADEON_RING_TYPE_GFX_INDEX])) {
 		DRM_DEBUG("cik_irq_set: sw int gfx\n");
@@ -7495,14 +7502,6 @@ int cik_irq_set(struct radeon_device *rd
 		hpd6 |= DC_HPDx_INT_EN;
 	}
 
-	if (rdev->irq.dpm_thermal) {
-		DRM_DEBUG("dpm thermal\n");
-		if (rdev->flags & RADEON_IS_IGP)
-			thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK;
-		else
-			thermal_int |= THERM_INT_MASK_HIGH | THERM_INT_MASK_LOW;
-	}
-
 	WREG32(CP_INT_CNTL_RING0, cp_int_cntl);
 
 	WREG32(SDMA0_CNTL + SDMA0_REGISTER_OFFSET, dma_cntl);
@@ -7556,10 +7555,8 @@ int cik_irq_set(struct radeon_device *rd
 	WREG32(DC_HPD5_INT_CONTROL, hpd5);
 	WREG32(DC_HPD6_INT_CONTROL, hpd6);
 
-	if (rdev->flags & RADEON_IS_IGP)
-		WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int);
-	else
-		WREG32_SMC(CG_THERMAL_INT, thermal_int);
+	/* posting read */
+	RREG32(SRBM_STATUS);
 
 	return 0;
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/dce3_1_afmt.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -103,7 +103,7 @@ static void dce3_2_afmt_write_sad_regs(s
 	}
 
 	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 		return;
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/evergreen.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/evergreen.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/evergreen.c
@@ -4589,6 +4589,9 @@ int evergreen_irq_set(struct radeon_devi
 	WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, afmt5);
 	WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, afmt6);
 
+	/* posting read */
+	RREG32(SRBM_STATUS);
+
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/kv_dpm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/kv_dpm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/kv_dpm.c
@@ -1169,6 +1169,19 @@ void kv_dpm_enable_bapm(struct radeon_de
 	}
 }
 
+static void kv_enable_thermal_int(struct radeon_device *rdev, bool enable)
+{
+	u32 thermal_int;
+
+	thermal_int = RREG32_SMC(CG_THERMAL_INT_CTRL);
+	if (enable)
+		thermal_int |= THERM_INTH_MASK | THERM_INTL_MASK;
+	else
+		thermal_int &= ~(THERM_INTH_MASK | THERM_INTL_MASK);
+	WREG32_SMC(CG_THERMAL_INT_CTRL, thermal_int);
+
+}
+
 int kv_dpm_enable(struct radeon_device *rdev)
 {
 	struct kv_power_info *pi = kv_get_pi(rdev);
@@ -1280,8 +1293,7 @@ int kv_dpm_late_enable(struct radeon_dev
 			DRM_ERROR("kv_set_thermal_temperature_range failed\n");
 			return ret;
 		}
-		rdev->irq.dpm_thermal = true;
-		radeon_irq_set(rdev);
+		kv_enable_thermal_int(rdev, true);
 	}
 
 	/* powerdown unused blocks for now */
@@ -1312,6 +1324,7 @@ void kv_dpm_disable(struct radeon_device
 	kv_stop_dpm(rdev);
 	kv_enable_ulv(rdev, false);
 	kv_reset_am(rdev);
+	kv_enable_thermal_int(rdev, false);
 
 	kv_update_current_ps(rdev, rdev->pm.dpm.boot_ps);
 }
@@ -2745,13 +2758,11 @@ int kv_dpm_init(struct radeon_device *rd
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
 	if (radeon_bapm == -1) {
-		/* There are stability issues reported on with
-		 * bapm enabled on an asrock system.
-		 */
-		if (rdev->pdev->subsystem_vendor == 0x1849)
-			pi->bapm_enable = false;
-		else
+		/* only enable bapm on KB, ML by default */
+		if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 			pi->bapm_enable = true;
+		else
+			pi->bapm_enable = false;
 	} else if (radeon_bapm == 0) {
 		pi->bapm_enable = false;
 	} else {
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/ni.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/ni.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/ni.c
@@ -1085,12 +1085,12 @@ static void cayman_gpu_init(struct radeo
 
 	if ((rdev->config.cayman.max_backends_per_se == 1) &&
 	    (rdev->flags & RADEON_IS_IGP)) {
-		if ((disabled_rb_mask & 3) == 1) {
-			/* RB0 disabled, RB1 enabled */
-			tmp = 0x11111111;
-		} else {
+		if ((disabled_rb_mask & 3) == 2) {
 			/* RB1 disabled, RB0 enabled */
 			tmp = 0x00000000;
+		} else {
+			/* RB0 disabled, RB1 enabled */
+			tmp = 0x11111111;
 		}
 	} else {
 		tmp = gb_addr_config & NUM_PIPES_MASK;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r100.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/r100.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r100.c
@@ -644,6 +644,7 @@ int r100_pci_gart_init(struct radeon_dev
 		return r;
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+	rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
 	rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	return radeon_gart_table_ram_alloc(rdev);
 }
@@ -681,11 +682,16 @@ void r100_pci_gart_disable(struct radeon
 	WREG32(RADEON_AIC_HI_ADDR, 0);
 }
 
+uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags)
+{
+	return addr;
+}
+
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr, uint32_t flags)
+			    uint64_t entry)
 {
 	u32 *gtt = rdev->gart.ptr;
-	gtt[i] = cpu_to_le32(lower_32_bits(addr));
+	gtt[i] = cpu_to_le32(lower_32_bits(entry));
 }
 
 void r100_pci_gart_fini(struct radeon_device *rdev)
@@ -722,6 +728,10 @@ int r100_irq_set(struct radeon_device *r
 		tmp |= RADEON_FP2_DETECT_MASK;
 	}
 	WREG32(RADEON_GEN_INT_CNTL, tmp);
+
+	/* read back to post the write */
+	RREG32(RADEON_GEN_INT_CNTL);
+
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r300.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/r300.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r300.c
@@ -73,11 +73,8 @@ void rv370_pcie_gart_tlb_flush(struct ra
 #define R300_PTE_WRITEABLE (1 << 2)
 #define R300_PTE_READABLE  (1 << 3)
 
-void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-			      uint64_t addr, uint32_t flags)
+uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
-	void __iomem *ptr = rdev->gart.ptr;
-
 	addr = (lower_32_bits(addr) >> 8) |
 		((upper_32_bits(addr) & 0xff) << 24);
 	if (flags & RADEON_GART_PAGE_READ)
@@ -86,10 +83,18 @@ void rv370_pcie_gart_set_page(struct rad
 		addr |= R300_PTE_WRITEABLE;
 	if (!(flags & RADEON_GART_PAGE_SNOOP))
 		addr |= R300_PTE_UNSNOOPED;
+	return addr;
+}
+
+void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
+			      uint64_t entry)
+{
+	void __iomem *ptr = rdev->gart.ptr;
+
 	/* on x86 we want this to be CPU endian, on powerpc
 	 * on powerpc without HW swappers, it'll get swapped on way
 	 * into VRAM - so no need for cpu_to_le32 on VRAM tables */
-	writel(addr, ((void __iomem *)ptr) + (i * 4));
+	writel(entry, ((void __iomem *)ptr) + (i * 4));
 }
 
 int rv370_pcie_gart_init(struct radeon_device *rdev)
@@ -109,6 +114,7 @@ int rv370_pcie_gart_init(struct radeon_d
 		DRM_ERROR("Failed to register debugfs file for PCIE gart !\n");
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
+	rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
 	rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
 	return radeon_gart_table_vram_alloc(rdev);
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r600.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/r600.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r600.c
@@ -3787,6 +3787,9 @@ int r600_irq_set(struct radeon_device *r
 		WREG32(RV770_CG_THERMAL_INT, thermal_int);
 	}
 
+	/* posting read */
+	RREG32(R_000E50_SRBM_STATUS);
+
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r600_dpm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/r600_dpm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/r600_dpm.c
@@ -188,7 +188,7 @@ u32 r600_dpm_get_vrefresh(struct radeon_
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			radeon_crtc = to_radeon_crtc(crtc);
 			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-				vrefresh = radeon_crtc->hw_mode.vrefresh;
+				vrefresh = drm_mode_vrefresh(&radeon_crtc->hw_mode);
 				break;
 			}
 		}
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon.h
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon.h
@@ -245,6 +245,7 @@ bool radeon_get_bios(struct radeon_devic
  * Dummy page
  */
 struct radeon_dummy_page {
+	uint64_t	entry;
 	struct page	*page;
 	dma_addr_t	addr;
 };
@@ -626,6 +627,7 @@ struct radeon_gart {
 	unsigned			table_size;
 	struct page			**pages;
 	dma_addr_t			*pages_addr;
+	uint64_t			*pages_entry;
 	bool				ready;
 };
 
@@ -1542,6 +1544,7 @@ struct radeon_dpm {
 	int			new_active_crtc_count;
 	u32			current_active_crtcs;
 	int			current_active_crtc_count;
+	bool single_display;
 	struct radeon_dpm_dynamic_state dyn_state;
 	struct radeon_dpm_fan fan;
 	u32 tdp_limit;
@@ -1819,8 +1822,9 @@ struct radeon_asic {
 	/* gart */
 	struct {
 		void (*tlb_flush)(struct radeon_device *rdev);
+		uint64_t (*get_page_entry)(uint64_t addr, uint32_t flags);
 		void (*set_page)(struct radeon_device *rdev, unsigned i,
-				 uint64_t addr, uint32_t flags);
+				 uint64_t entry);
 	} gart;
 	struct {
 		int (*init)(struct radeon_device *rdev);
@@ -2818,7 +2822,8 @@ static inline void radeon_ring_write(str
 #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
-#define radeon_gart_set_page(rdev, i, p, f) (rdev)->asic->gart.set_page((rdev), (i), (p), (f))
+#define radeon_gart_get_page_entry(a, f) (rdev)->asic->gart.get_page_entry((a), (f))
+#define radeon_gart_set_page(rdev, i, e) (rdev)->asic->gart.set_page((rdev), (i), (e))
 #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
 #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
 #define radeon_asic_vm_copy_pages(rdev, ib, pe, src, count) ((rdev)->asic->vm.copy_pages((rdev), (ib), (pe), (src), (count)))
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_asic.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_asic.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_asic.c
@@ -159,11 +159,13 @@ void radeon_agp_disable(struct radeon_de
 		DRM_INFO("Forcing AGP to PCIE mode\n");
 		rdev->flags |= RADEON_IS_PCIE;
 		rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
+		rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
 		rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
 	} else {
 		DRM_INFO("Forcing AGP to PCI mode\n");
 		rdev->flags |= RADEON_IS_PCI;
 		rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+		rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
 		rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	}
 	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
@@ -199,6 +201,7 @@ static struct radeon_asic r100_asic = {
 	.mc_wait_for_idle = &r100_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -265,6 +268,7 @@ static struct radeon_asic r200_asic = {
 	.mc_wait_for_idle = &r100_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -333,6 +337,20 @@ static struct radeon_asic_ring r300_gfx_
 	.set_wptr = &r100_gfx_set_wptr,
 };
 
+static struct radeon_asic_ring rv515_gfx_ring = {
+	.ib_execute = &r100_ring_ib_execute,
+	.emit_fence = &r300_fence_ring_emit,
+	.emit_semaphore = &r100_semaphore_ring_emit,
+	.cs_parse = &r300_cs_parse,
+	.ring_start = &rv515_ring_start,
+	.ring_test = &r100_ring_test,
+	.ib_test = &r100_ib_test,
+	.is_lockup = &r100_gpu_is_lockup,
+	.get_rptr = &r100_gfx_get_rptr,
+	.get_wptr = &r100_gfx_get_wptr,
+	.set_wptr = &r100_gfx_set_wptr,
+};
+
 static struct radeon_asic r300_asic = {
 	.init = &r300_init,
 	.fini = &r300_fini,
@@ -345,6 +363,7 @@ static struct radeon_asic r300_asic = {
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -411,6 +430,7 @@ static struct radeon_asic r300_asic_pcie
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -477,6 +497,7 @@ static struct radeon_asic r420_asic = {
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -543,6 +564,7 @@ static struct radeon_asic rs400_asic = {
 	.mc_wait_for_idle = &rs400_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs400_gart_tlb_flush,
+		.get_page_entry = &rs400_gart_get_page_entry,
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
@@ -609,6 +631,7 @@ static struct radeon_asic rs600_asic = {
 	.mc_wait_for_idle = &rs600_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs600_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -677,6 +700,7 @@ static struct radeon_asic rs690_asic = {
 	.mc_wait_for_idle = &rs690_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs400_gart_tlb_flush,
+		.get_page_entry = &rs400_gart_get_page_entry,
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
@@ -745,10 +769,11 @@ static struct radeon_asic rv515_asic = {
 	.mc_wait_for_idle = &rv515_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
+		[RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -811,10 +836,11 @@ static struct radeon_asic r520_asic = {
 	.mc_wait_for_idle = &r520_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
-		[RADEON_RING_TYPE_GFX_INDEX] = &r300_gfx_ring
+		[RADEON_RING_TYPE_GFX_INDEX] = &rv515_gfx_ring
 	},
 	.irq = {
 		.set = &rs600_irq_set,
@@ -905,6 +931,7 @@ static struct radeon_asic r600_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -990,6 +1017,7 @@ static struct radeon_asic rv6xx_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1081,6 +1109,7 @@ static struct radeon_asic rs780_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1185,6 +1214,7 @@ static struct radeon_asic rv770_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1303,6 +1333,7 @@ static struct radeon_asic evergreen_asic
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1395,6 +1426,7 @@ static struct radeon_asic sumo_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1486,6 +1518,7 @@ static struct radeon_asic btc_asic = {
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1621,6 +1654,7 @@ static struct radeon_asic cayman_asic =
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -1724,6 +1758,7 @@ static struct radeon_asic trinity_asic =
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -1857,6 +1892,7 @@ static struct radeon_asic si_asic = {
 	.get_gpu_clock_counter = &si_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &si_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -2018,6 +2054,7 @@ static struct radeon_asic ci_asic = {
 	.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cik_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -2125,6 +2162,7 @@ static struct radeon_asic kv_asic = {
 	.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cik_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_asic.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_asic.h
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_asic.h
@@ -67,8 +67,9 @@ bool r100_gpu_is_lockup(struct radeon_de
 int r100_asic_reset(struct radeon_device *rdev);
 u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void r100_pci_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr, uint32_t flags);
+			    uint64_t entry);
 void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
 int r100_irq_set(struct radeon_device *rdev);
 int r100_irq_process(struct radeon_device *rdev);
@@ -172,8 +173,9 @@ extern void r300_fence_ring_emit(struct
 				struct radeon_fence *fence);
 extern int r300_cs_parse(struct radeon_cs_parser *p);
 extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
+extern uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags);
 extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-				     uint64_t addr, uint32_t flags);
+				     uint64_t entry);
 extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
 extern void r300_set_reg_safe(struct radeon_device *rdev);
@@ -208,8 +210,9 @@ extern void rs400_fini(struct radeon_dev
 extern int rs400_suspend(struct radeon_device *rdev);
 extern int rs400_resume(struct radeon_device *rdev);
 void rs400_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags);
+			 uint64_t entry);
 uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int rs400_gart_init(struct radeon_device *rdev);
@@ -232,8 +235,9 @@ int rs600_irq_process(struct radeon_devi
 void rs600_irq_disable(struct radeon_device *rdev);
 u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void rs600_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags);
+			 uint64_t entry);
 uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rs600_bandwidth_update(struct radeon_device *rdev);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_atombios.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_atombios.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -3280,6 +3280,7 @@ int radeon_atom_get_voltage_evv(struct r
 
 	args.in.ucVoltageType = VOLTAGE_TYPE_VDDC;
 	args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
+	args.in.usVoltageLevel = cpu_to_le16(virtual_voltage_id);
 	args.in.ulSCLKFreq =
 		cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk);
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_benchmark.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -34,7 +34,8 @@
 
 static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 				    uint64_t saddr, uint64_t daddr,
-				    int flag, int n)
+				    int flag, int n,
+				    struct reservation_object *resv)
 {
 	unsigned long start_jiffies;
 	unsigned long end_jiffies;
@@ -47,12 +48,12 @@ static int radeon_benchmark_do_move(stru
 		case RADEON_BENCHMARK_COPY_DMA:
 			fence = radeon_copy_dma(rdev, saddr, daddr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						resv);
 			break;
 		case RADEON_BENCHMARK_COPY_BLIT:
 			fence = radeon_copy_blit(rdev, saddr, daddr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 resv);
 			break;
 		default:
 			DRM_ERROR("Unknown copy method\n");
@@ -120,7 +121,8 @@ static void radeon_benchmark_move(struct
 
 	if (rdev->asic->copy.dma) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_DMA, n);
+						RADEON_BENCHMARK_COPY_DMA, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
@@ -130,7 +132,8 @@ static void radeon_benchmark_move(struct
 
 	if (rdev->asic->copy.blit) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_BLIT, n);
+						RADEON_BENCHMARK_COPY_BLIT, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_bios.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_bios.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_bios.c
@@ -76,7 +76,7 @@ static bool igp_read_bios_from_vram(stru
 
 static bool radeon_read_bios(struct radeon_device *rdev)
 {
-	uint8_t __iomem *bios;
+	uint8_t __iomem *bios, val1, val2;
 	size_t size;
 
 	rdev->bios = NULL;
@@ -86,15 +86,19 @@ static bool radeon_read_bios(struct rade
 		return false;
 	}
 
-	if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) {
+	val1 = readb(&bios[0]);
+	val2 = readb(&bios[1]);
+
+	if (size == 0 || val1 != 0x55 || val2 != 0xaa) {
 		pci_unmap_rom(rdev->pdev, bios);
 		return false;
 	}
-	rdev->bios = kmemdup(bios, size, GFP_KERNEL);
+	rdev->bios = kzalloc(size, GFP_KERNEL);
 	if (rdev->bios == NULL) {
 		pci_unmap_rom(rdev->pdev, bios);
 		return false;
 	}
+	memcpy_fromio(rdev->bios, bios, size);
 	pci_unmap_rom(rdev->pdev, bios);
 	return true;
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_cs.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_cs.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_cs.c
@@ -275,11 +275,13 @@ int radeon_cs_parser_init(struct radeon_
 	u32 ring = RADEON_CS_RING_GFX;
 	s32 priority = 0;
 
+	INIT_LIST_HEAD(&p->validated);
+
 	if (!cs->num_chunks) {
 		return 0;
 	}
+
 	/* get chunks */
-	INIT_LIST_HEAD(&p->validated);
 	p->idx = 0;
 	p->ib.sa_bo = NULL;
 	p->ib.semaphore = NULL;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_device.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_device.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_device.c
@@ -743,6 +743,8 @@ int radeon_dummy_page_init(struct radeon
 		rdev->dummy_page.page = NULL;
 		return -ENOMEM;
 	}
+	rdev->dummy_page.entry = radeon_gart_get_page_entry(rdev->dummy_page.addr,
+							    RADEON_GART_PAGE_DUMMY);
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_display.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_display.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_display.c
@@ -959,6 +959,9 @@ void radeon_compute_pll_avivo(struct rad
 	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV &&
 	    pll->flags & RADEON_PLL_USE_REF_DIV)
 		ref_div_max = pll->reference_div;
+	else if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP)
+		/* fix for problems on RS880 */
+		ref_div_max = min(pll->max_ref_div, 7u);
 	else
 		ref_div_max = pll->max_ref_div;
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_encoders.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_encoders.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -179,9 +179,12 @@ static void radeon_encoder_add_backlight
 		    (rdev->pdev->subsystem_vendor == 0x1734) &&
 		    (rdev->pdev->subsystem_device == 0x1107))
 			use_bl = false;
+/* Older PPC macs use on-GPU backlight controller */
+#ifndef CONFIG_PPC_PMAC
 		/* disable native backlight control on older asics */
 		else if (rdev->family < CHIP_R600)
 			use_bl = false;
+#endif
 		else
 			use_bl = true;
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_fence.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_fence.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_fence.c
@@ -1029,37 +1029,59 @@ static inline bool radeon_test_signaled(
 	return test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags);
 }
 
+struct radeon_wait_cb {
+	struct fence_cb base;
+	struct task_struct *task;
+};
+
+static void
+radeon_fence_wait_cb(struct fence *fence, struct fence_cb *cb)
+{
+	struct radeon_wait_cb *wait =
+		container_of(cb, struct radeon_wait_cb, base);
+
+	wake_up_process(wait->task);
+}
+
 static signed long radeon_fence_default_wait(struct fence *f, bool intr,
 					     signed long t)
 {
 	struct radeon_fence *fence = to_radeon_fence(f);
 	struct radeon_device *rdev = fence->rdev;
-	bool signaled;
+	struct radeon_wait_cb cb;
+
+	cb.task = current;
+
+	if (fence_add_callback(f, &cb.base, radeon_fence_wait_cb))
+		return t;
 
-	fence_enable_sw_signaling(&fence->base);
+	while (t > 0) {
+		if (intr)
+			set_current_state(TASK_INTERRUPTIBLE);
+		else
+			set_current_state(TASK_UNINTERRUPTIBLE);
+
+		/*
+		 * radeon_test_signaled must be called after
+		 * set_current_state to prevent a race with wake_up_process
+		 */
+		if (radeon_test_signaled(fence))
+			break;
+
+		if (rdev->needs_reset) {
+			t = -EDEADLK;
+			break;
+		}
+
+		t = schedule_timeout(t);
+
+		if (t > 0 && intr && signal_pending(current))
+			t = -ERESTARTSYS;
+	}
 
-	/*
-	 * This function has to return -EDEADLK, but cannot hold
-	 * exclusive_lock during the wait because some callers
-	 * may already hold it. This means checking needs_reset without
-	 * lock, and not fiddling with any gpu internals.
-	 *
-	 * The callback installed with fence_enable_sw_signaling will
-	 * run before our wait_event_*timeout call, so we will see
-	 * both the signaled fence and the changes to needs_reset.
-	 */
-
-	if (intr)
-		t = wait_event_interruptible_timeout(rdev->fence_queue,
-			((signaled = radeon_test_signaled(fence)) ||
-			 rdev->needs_reset), t);
-	else
-		t = wait_event_timeout(rdev->fence_queue,
-			((signaled = radeon_test_signaled(fence)) ||
-			 rdev->needs_reset), t);
+	__set_current_state(TASK_RUNNING);
+	fence_remove_callback(f, &cb.base);
 
-	if (t > 0 && !signaled)
-		return -EDEADLK;
 	return t;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_gart.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_gart.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_gart.c
@@ -165,6 +165,19 @@ int radeon_gart_table_vram_pin(struct ra
 		radeon_bo_unpin(rdev->gart.robj);
 	radeon_bo_unreserve(rdev->gart.robj);
 	rdev->gart.table_addr = gpu_addr;
+
+	if (!r) {
+		int i;
+
+		/* We might have dropped some GART table updates while it wasn't
+		 * mapped, restore all entries
+		 */
+		for (i = 0; i < rdev->gart.num_gpu_pages; i++)
+			radeon_gart_set_page(rdev, i, rdev->gart.pages_entry[i]);
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
+
 	return r;
 }
 
@@ -228,7 +241,6 @@ void radeon_gart_unbind(struct radeon_de
 	unsigned t;
 	unsigned p;
 	int i, j;
-	u64 page_base;
 
 	if (!rdev->gart.ready) {
 		WARN(1, "trying to unbind memory from uninitialized GART !\n");
@@ -240,13 +252,12 @@ void radeon_gart_unbind(struct radeon_de
 		if (rdev->gart.pages[p]) {
 			rdev->gart.pages[p] = NULL;
 			rdev->gart.pages_addr[p] = rdev->dummy_page.addr;
-			page_base = rdev->gart.pages_addr[p];
 			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
+				rdev->gart.pages_entry[t] = rdev->dummy_page.entry;
 				if (rdev->gart.ptr) {
-					radeon_gart_set_page(rdev, t, page_base,
-							     RADEON_GART_PAGE_DUMMY);
+					radeon_gart_set_page(rdev, t,
+							     rdev->dummy_page.entry);
 				}
-				page_base += RADEON_GPU_PAGE_SIZE;
 			}
 		}
 	}
@@ -274,7 +285,7 @@ int radeon_gart_bind(struct radeon_devic
 {
 	unsigned t;
 	unsigned p;
-	uint64_t page_base;
+	uint64_t page_base, page_entry;
 	int i, j;
 
 	if (!rdev->gart.ready) {
@@ -287,12 +298,14 @@ int radeon_gart_bind(struct radeon_devic
 	for (i = 0; i < pages; i++, p++) {
 		rdev->gart.pages_addr[p] = dma_addr[i];
 		rdev->gart.pages[p] = pagelist[i];
-		if (rdev->gart.ptr) {
-			page_base = rdev->gart.pages_addr[p];
-			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
-				radeon_gart_set_page(rdev, t, page_base, flags);
-				page_base += RADEON_GPU_PAGE_SIZE;
+		page_base = dma_addr[i];
+		for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
+			page_entry = radeon_gart_get_page_entry(page_base, flags);
+			rdev->gart.pages_entry[t] = page_entry;
+			if (rdev->gart.ptr) {
+				radeon_gart_set_page(rdev, t, page_entry);
 			}
+			page_base += RADEON_GPU_PAGE_SIZE;
 		}
 	}
 	mb();
@@ -340,10 +353,17 @@ int radeon_gart_init(struct radeon_devic
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
+	rdev->gart.pages_entry = vmalloc(sizeof(uint64_t) *
+					 rdev->gart.num_gpu_pages);
+	if (rdev->gart.pages_entry == NULL) {
+		radeon_gart_fini(rdev);
+		return -ENOMEM;
+	}
 	/* set GART entry to point to the dummy page by default */
-	for (i = 0; i < rdev->gart.num_cpu_pages; i++) {
+	for (i = 0; i < rdev->gart.num_cpu_pages; i++)
 		rdev->gart.pages_addr[i] = rdev->dummy_page.addr;
-	}
+	for (i = 0; i < rdev->gart.num_gpu_pages; i++)
+		rdev->gart.pages_entry[i] = rdev->dummy_page.entry;
 	return 0;
 }
 
@@ -356,15 +376,17 @@ int radeon_gart_init(struct radeon_devic
  */
 void radeon_gart_fini(struct radeon_device *rdev)
 {
-	if (rdev->gart.pages && rdev->gart.pages_addr && rdev->gart.ready) {
+	if (rdev->gart.ready) {
 		/* unbind pages */
 		radeon_gart_unbind(rdev, 0, rdev->gart.num_cpu_pages);
 	}
 	rdev->gart.ready = false;
 	vfree(rdev->gart.pages);
 	vfree(rdev->gart.pages_addr);
+	vfree(rdev->gart.pages_entry);
 	rdev->gart.pages = NULL;
 	rdev->gart.pages_addr = NULL;
+	rdev->gart.pages_entry = NULL;
 
 	radeon_dummy_page_fini(rdev);
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_gem.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_gem.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_gem.c
@@ -146,7 +146,8 @@ int radeon_gem_object_open(struct drm_ge
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return 0;
 	}
 
@@ -176,7 +177,8 @@ void radeon_gem_object_close(struct drm_
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return;
 	}
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_kms.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_kms.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_kms.c
@@ -598,14 +598,14 @@ int radeon_driver_open_kms(struct drm_de
 			return -ENOMEM;
 		}
 
-		vm = &fpriv->vm;
-		r = radeon_vm_init(rdev, vm);
-		if (r) {
-			kfree(fpriv);
-			return r;
-		}
-
 		if (rdev->accel_working) {
+			vm = &fpriv->vm;
+			r = radeon_vm_init(rdev, vm);
+			if (r) {
+				kfree(fpriv);
+				return r;
+			}
+
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r) {
 				radeon_vm_fini(rdev, vm);
@@ -663,9 +663,9 @@ void radeon_driver_postclose_kms(struct
 					radeon_vm_bo_rmv(rdev, vm->ib_bo_va);
 				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			}
+			radeon_vm_fini(rdev, vm);
 		}
 
-		radeon_vm_fini(rdev, vm);
 		kfree(fpriv);
 		file_priv->driver_priv = NULL;
 	}
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_mn.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_mn.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_mn.c
@@ -122,7 +122,6 @@ static void radeon_mn_invalidate_range_s
 	it = interval_tree_iter_first(&rmn->objects, start, end);
 	while (it) {
 		struct radeon_bo *bo;
-		struct fence *fence;
 		int r;
 
 		bo = container_of(it, struct radeon_bo, mn_it);
@@ -134,12 +133,10 @@ static void radeon_mn_invalidate_range_s
 			continue;
 		}
 
-		fence = reservation_object_get_excl(bo->tbo.resv);
-		if (fence) {
-			r = radeon_fence_wait((struct radeon_fence *)fence, false);
-			if (r)
-				DRM_ERROR("(%d) failed to wait for user bo\n", r);
-		}
+		r = reservation_object_wait_timeout_rcu(bo->tbo.resv, true,
+			false, MAX_SCHEDULE_TIMEOUT);
+		if (r)
+			DRM_ERROR("(%d) failed to wait for user bo\n", r);
 
 		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_object.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_object.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_object.c
@@ -151,19 +151,6 @@ void radeon_ttm_placement_from_domain(st
 		else
 			rbo->placements[i].lpfn = 0;
 	}
-
-	/*
-	 * Use two-ended allocation depending on the buffer size to
-	 * improve fragmentation quality.
-	 * 512kb was measured as the most optimal number.
-	 */
-	if (!((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
-	      (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) &&
-	    rbo->tbo.mem.size > 512 * 1024) {
-		for (i = 0; i < c; i++) {
-			rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
-		}
-	}
 }
 
 int radeon_bo_create(struct radeon_device *rdev,
@@ -218,6 +205,18 @@ int radeon_bo_create(struct radeon_devic
 	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
 	bo->flags &= ~RADEON_GEM_GTT_WC;
+#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
+	/* Don't try to enable write-combining when it can't work, or things
+	 * may be slow
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
+	 */
+
+#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
+	 thanks to write-combining
+
+	DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+		      "better performance thanks to write-combining\n");
+	bo->flags &= ~RADEON_GEM_GTT_WC;
 #endif
 
 	radeon_ttm_placement_from_domain(bo, domain);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_pm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_pm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_pm.c
@@ -704,12 +704,8 @@ static void radeon_dpm_thermal_work_hand
 	radeon_pm_compute_clocks(rdev);
 }
 
-static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
-						     enum radeon_pm_state_type dpm_state)
+static bool radeon_dpm_single_display(struct radeon_device *rdev)
 {
-	int i;
-	struct radeon_ps *ps;
-	u32 ui_class;
 	bool single_display = (rdev->pm.dpm.new_active_crtc_count < 2) ?
 		true : false;
 
@@ -719,6 +715,17 @@ static struct radeon_ps *radeon_dpm_pick
 			single_display = false;
 	}
 
+	return single_display;
+}
+
+static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
+						     enum radeon_pm_state_type dpm_state)
+{
+	int i;
+	struct radeon_ps *ps;
+	u32 ui_class;
+	bool single_display = radeon_dpm_single_display(rdev);
+
 	/* certain older asics have a separare 3D performance state,
 	 * so try that first if the user selected performance
 	 */
@@ -844,6 +851,7 @@ static void radeon_dpm_change_power_stat
 	struct radeon_ps *ps;
 	enum radeon_pm_state_type dpm_state;
 	int ret;
+	bool single_display = radeon_dpm_single_display(rdev);
 
 	/* if dpm init failed */
 	if (!rdev->pm.dpm_enabled)
@@ -868,6 +876,9 @@ static void radeon_dpm_change_power_stat
 		/* vce just modifies an existing state so force a change */
 		if (ps->vce_active != rdev->pm.dpm.vce_active)
 			goto force;
+		/* user has made a display change (such as timing) */
+		if (rdev->pm.dpm.single_display != single_display)
+			goto force;
 		if ((rdev->family < CHIP_BARTS) || (rdev->flags & RADEON_IS_IGP)) {
 			/* for pre-BTC and APUs if the num crtcs changed but state is the same,
 			 * all we need to do is update the display configuration.
@@ -930,6 +941,7 @@ force:
 
 	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
 	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
+	rdev->pm.dpm.single_display = single_display;
 
 	/* wait for the rings to drain */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
@@ -1287,8 +1299,39 @@ dpm_failed:
 	return ret;
 }
 
+struct radeon_dpm_quirk {
+	u32 chip_vendor;
+	u32 chip_device;
+	u32 subsys_vendor;
+	u32 subsys_device;
+};
+
+/* cards with dpm stability problems */
+static struct radeon_dpm_quirk radeon_dpm_quirk_list[] = {
+	/* TURKS - https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1386534 */
+	{ PCI_VENDOR_ID_ATI, 0x6759, 0x1682, 0x3195 },
+	/* TURKS - https://bugzilla.kernel.org/show_bug.cgi?id=83731 */
+	{ PCI_VENDOR_ID_ATI, 0x6840, 0x1179, 0xfb81 },
+	{ 0, 0, 0, 0 },
+};
+
 int radeon_pm_init(struct radeon_device *rdev)
 {
+	struct radeon_dpm_quirk *p = radeon_dpm_quirk_list;
+	bool disable_dpm = false;
+
+	/* Apply dpm quirks */
+	while (p && p->chip_device != 0) {
+		if (rdev->pdev->vendor == p->chip_vendor &&
+		    rdev->pdev->device == p->chip_device &&
+		    rdev->pdev->subsystem_vendor == p->subsys_vendor &&
+		    rdev->pdev->subsystem_device == p->subsys_device) {
+			disable_dpm = true;
+			break;
+		}
+		++p;
+	}
+
 	/* enable dpm on rv6xx+ */
 	switch (rdev->family) {
 	case CHIP_RV610:
@@ -1344,6 +1387,8 @@ int radeon_pm_init(struct radeon_device
 			 (!(rdev->flags & RADEON_IS_IGP)) &&
 			 (!rdev->smc_fw))
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
+		else if (disable_dpm && (radeon_dpm == -1))
+			rdev->pm.pm_method = PM_METHOD_PROFILE;
 		else if (radeon_dpm == 0)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
 		else
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_test.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_test.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_test.c
@@ -119,11 +119,11 @@ static void radeon_do_test_moves(struct
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, gtt_addr, vram_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, gtt_addr, vram_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
 			r = PTR_ERR(fence);
@@ -170,11 +170,11 @@ static void radeon_do_test_moves(struct
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, vram_addr, gtt_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, vram_addr, gtt_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
 			r = PTR_ERR(fence);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_ttm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_ttm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -196,7 +196,7 @@ static void radeon_evict_flags(struct tt
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	switch (bo->mem.mem_type) {
 	case TTM_PL_VRAM:
-		if (rbo->rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready == false)
+		if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false)
 			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU);
 		else
 			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
@@ -575,6 +575,10 @@ static void radeon_ttm_tt_unpin_userptr(
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
 
+	/* double check that we don't free the table twice */
+	if (!ttm->sg->sgl)
+		return;
+
 	/* free the sg table and pages again */
 	dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_vm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/radeon_vm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/radeon_vm.c
@@ -753,9 +753,11 @@ static void radeon_vm_frag_ptes(struct r
 	 */
 
 	/* NI is optimized for 256KB fragments, SI and newer for 64KB */
-	uint64_t frag_flags = rdev->family == CHIP_CAYMAN ?
+	uint64_t frag_flags = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ?
 			R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB;
-	uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80;
+	uint64_t frag_align = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ? 0x200 : 0x80;
 
 	uint64_t frag_start = ALIGN(pe_start, frag_align);
 	uint64_t frag_end = pe_end & ~(frag_align - 1);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/rs400.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/rs400.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/rs400.c
@@ -212,11 +212,9 @@ void rs400_gart_fini(struct radeon_devic
 #define RS400_PTE_WRITEABLE (1 << 2)
 #define RS400_PTE_READABLE  (1 << 3)
 
-void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags)
+uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
 	uint32_t entry;
-	u32 *gtt = rdev->gart.ptr;
 
 	entry = (lower_32_bits(addr) & PAGE_MASK) |
 		((upper_32_bits(addr) & 0xff) << 4);
@@ -226,8 +224,14 @@ void rs400_gart_set_page(struct radeon_d
 		entry |= RS400_PTE_WRITEABLE;
 	if (!(flags & RADEON_GART_PAGE_SNOOP))
 		entry |= RS400_PTE_UNSNOOPED;
-	entry = cpu_to_le32(entry);
-	gtt[i] = entry;
+	return entry;
+}
+
+void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t entry)
+{
+	u32 *gtt = rdev->gart.ptr;
+	gtt[i] = cpu_to_le32(lower_32_bits(entry));
 }
 
 int rs400_mc_wait_for_idle(struct radeon_device *rdev)
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/rs600.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/rs600.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/rs600.c
@@ -625,11 +625,8 @@ static void rs600_gart_fini(struct radeo
 	radeon_gart_table_vram_free(rdev);
 }
 
-void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags)
+uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
-	void __iomem *ptr = (void *)rdev->gart.ptr;
-
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
 	addr |= R600_PTE_SYSTEM;
 	if (flags & RADEON_GART_PAGE_VALID)
@@ -640,7 +637,14 @@ void rs600_gart_set_page(struct radeon_d
 		addr |= R600_PTE_WRITEABLE;
 	if (flags & RADEON_GART_PAGE_SNOOP)
 		addr |= R600_PTE_SNOOPED;
-	writeq(addr, ptr + (i * 8));
+	return addr;
+}
+
+void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t entry)
+{
+	void __iomem *ptr = (void *)rdev->gart.ptr;
+	writeq(entry, ptr + (i * 8));
 }
 
 int rs600_irq_set(struct radeon_device *rdev)
@@ -689,6 +693,10 @@ int rs600_irq_set(struct radeon_device *
 	WREG32(R_007D18_DC_HOT_PLUG_DETECT2_INT_CONTROL, hpd2);
 	if (ASIC_IS_DCE2(rdev))
 		WREG32(R_007408_HDMI0_AUDIO_PACKET_CONTROL, hdmi0);
+
+	/* posting read */
+	RREG32(R_000040_GEN_INT_CNTL);
+
 	return 0;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/si.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/si.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/si.c
@@ -6192,6 +6192,9 @@ int si_irq_set(struct radeon_device *rde
 
 	WREG32(CG_THERMAL_INT, thermal_int);
 
+	/* posting read */
+	RREG32(SRBM_STATUS);
+
 	return 0;
 }
 
@@ -7112,8 +7115,7 @@ int si_set_uvd_clocks(struct radeon_devi
 	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK);
 
 	if (!vclk || !dclk) {
-		/* keep the Bypass mode, put PLL to sleep */
-		WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+		/* keep the Bypass mode */
 		return 0;
 	}
 
@@ -7129,8 +7131,7 @@ int si_set_uvd_clocks(struct radeon_devi
 	/* set VCO_MODE to 1 */
 	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK);
 
-	/* toggle UPLL_SLEEP to 1 then back to 0 */
-	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+	/* disable sleep mode */
 	WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK);
 
 	/* deassert UPLL_RESET */
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/si_dpm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/radeon/si_dpm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/radeon/si_dpm.c
@@ -2908,6 +2908,22 @@ static int si_init_smc_spll_table(struct
 	return ret;
 }
 
+struct si_dpm_quirk {
+	u32 chip_vendor;
+	u32 chip_device;
+	u32 subsys_vendor;
+	u32 subsys_device;
+	u32 max_sclk;
+	u32 max_mclk;
+};
+
+/* cards with dpm stability problems */
+static struct si_dpm_quirk si_dpm_quirk_list[] = {
+	/* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */
+	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
+	{ 0, 0, 0, 0 },
+};
+
 static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 					struct radeon_ps *rps)
 {
@@ -2918,7 +2934,22 @@ static void si_apply_state_adjust_rules(
 	u32 mclk, sclk;
 	u16 vddc, vddci;
 	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
+	u32 max_sclk = 0, max_mclk = 0;
 	int i;
+	struct si_dpm_quirk *p = si_dpm_quirk_list;
+
+	/* Apply dpm quirks */
+	while (p && p->chip_device != 0) {
+		if (rdev->pdev->vendor == p->chip_vendor &&
+		    rdev->pdev->device == p->chip_device &&
+		    rdev->pdev->subsystem_vendor == p->subsys_vendor &&
+		    rdev->pdev->subsystem_device == p->subsys_device) {
+			max_sclk = p->max_sclk;
+			max_mclk = p->max_mclk;
+			break;
+		}
+		++p;
+	}
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    ni_dpm_vblank_too_short(rdev))
@@ -2972,6 +3003,14 @@ static void si_apply_state_adjust_rules(
 			if (ps->performance_levels[i].mclk > max_mclk_vddc)
 				ps->performance_levels[i].mclk = max_mclk_vddc;
 		}
+		if (max_mclk) {
+			if (ps->performance_levels[i].mclk > max_mclk)
+				ps->performance_levels[i].mclk = max_mclk;
+		}
+		if (max_sclk) {
+			if (ps->performance_levels[i].sclk > max_sclk)
+				ps->performance_levels[i].sclk = max_sclk;
+		}
 	}
 
 	/* XXX validate the min clocks required for display */
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/tegra/drm.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/tegra/drm.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/tegra/drm.c
@@ -152,7 +152,7 @@ static int host1x_reloc_copy_from_user(s
 	if (err < 0)
 		return err;
 
-	err = get_user(dest->target.offset, &src->cmdbuf.offset);
+	err = get_user(dest->target.offset, &src->target.offset);
 	if (err < 0)
 		return err;
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/tegra/gem.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/tegra/gem.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/tegra/gem.c
@@ -259,16 +259,12 @@ void tegra_bo_free_object(struct drm_gem
 int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm,
 			 struct drm_mode_create_dumb *args)
 {
-	int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+	unsigned int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
 	struct tegra_drm *tegra = drm->dev_private;
 	struct tegra_bo *bo;
 
-	min_pitch = round_up(min_pitch, tegra->pitch_align);
-	if (args->pitch < min_pitch)
-		args->pitch = min_pitch;
-
-	if (args->size < args->pitch * args->height)
-		args->size = args->pitch * args->height;
+	args->pitch = round_up(min_pitch, tegra->pitch_align);
+	args->size = args->pitch * args->height;
 
 	bo = tegra_bo_create_with_handle(file, drm, args->size, 0,
 					 &args->handle);
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/ttm/ttm_page_alloc.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -297,11 +297,12 @@ static void ttm_pool_update_free_locked(
  *
  * @pool: to free the pages from
  * @free_all: If set to true will free all pages in pool
- * @gfp: GFP flags.
+ * @use_static: Safe to use static buffer
  **/
 static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
-			      gfp_t gfp)
+			      bool use_static)
 {
+	static struct page *static_buf[NUM_PAGES_TO_ALLOC];
 	unsigned long irq_flags;
 	struct page *p;
 	struct page **pages_to_free;
@@ -311,7 +312,11 @@ static int ttm_page_pool_free(struct ttm
 	if (NUM_PAGES_TO_ALLOC < nr_free)
 		npages_to_free = NUM_PAGES_TO_ALLOC;
 
-	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
+	if (use_static)
+		pages_to_free = static_buf;
+	else
+		pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
+					GFP_KERNEL);
 	if (!pages_to_free) {
 		pr_err("Failed to allocate memory for pool free operation\n");
 		return 0;
@@ -374,7 +379,8 @@ restart:
 	if (freed_pages)
 		ttm_pages_put(pages_to_free, freed_pages);
 out:
-	kfree(pages_to_free);
+	if (pages_to_free != static_buf)
+		kfree(pages_to_free);
 	return nr_free;
 }
 
@@ -383,8 +389,6 @@ out:
  *
  * XXX: (dchinner) Deadlock warning!
  *
- * We need to pass sc->gfp_mask to ttm_page_pool_free().
- *
  * This code is crying out for a shrinker per pool....
  */
 static unsigned long
@@ -407,8 +411,8 @@ ttm_pool_shrink_scan(struct shrinker *sh
 		if (shrink_pages == 0)
 			break;
 		pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
-		shrink_pages = ttm_page_pool_free(pool, nr_free,
-						  sc->gfp_mask);
+		/* OK to use static buffer since global mutex is held. */
+		shrink_pages = ttm_page_pool_free(pool, nr_free, true);
 		freed += nr_free - shrink_pages;
 	}
 	mutex_unlock(&lock);
@@ -710,7 +714,7 @@ static void ttm_put_pages(struct page **
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
 	if (npages)
-		ttm_page_pool_free(pool, npages, GFP_KERNEL);
+		ttm_page_pool_free(pool, npages, false);
 }
 
 /*
@@ -849,9 +853,9 @@ void ttm_page_alloc_fini(void)
 	pr_info("Finalizing pool allocator\n");
 	ttm_pool_mm_shrink_fini(_manager);
 
+	/* OK to use static buffer since global mutex is no longer used. */
 	for (i = 0; i < NUM_POOLS; ++i)
-		ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES,
-				   GFP_KERNEL);
+		ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES, true);
 
 	kobject_put(&_manager->kobj);
 	_manager = NULL;
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -411,11 +411,12 @@ static void ttm_dma_page_put(struct dma_
  *
  * @pool: to free the pages from
  * @nr_free: If set to true will free all pages in pool
- * @gfp: GFP flags.
+ * @use_static: Safe to use static buffer
  **/
 static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free,
-				       gfp_t gfp)
+				       bool use_static)
 {
+	static struct page *static_buf[NUM_PAGES_TO_ALLOC];
 	unsigned long irq_flags;
 	struct dma_page *dma_p, *tmp;
 	struct page **pages_to_free;
@@ -432,7 +433,11 @@ static unsigned ttm_dma_page_pool_free(s
 			 npages_to_free, nr_free);
 	}
 #endif
-	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
+	if (use_static)
+		pages_to_free = static_buf;
+	else
+		pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
+					GFP_KERNEL);
 
 	if (!pages_to_free) {
 		pr_err("%s: Failed to allocate memory for pool free operation\n",
@@ -502,7 +507,8 @@ restart:
 	if (freed_pages)
 		ttm_dma_pages_put(pool, &d_pages, pages_to_free, freed_pages);
 out:
-	kfree(pages_to_free);
+	if (pages_to_free != static_buf)
+		kfree(pages_to_free);
 	return nr_free;
 }
 
@@ -531,7 +537,8 @@ static void ttm_dma_free_pool(struct dev
 		if (pool->type != type)
 			continue;
 		/* Takes a spinlock.. */
-		ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, GFP_KERNEL);
+		/* OK to use static buffer since global mutex is held. */
+		ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, true);
 		WARN_ON(((pool->npages_in_use + pool->npages_free) != 0));
 		/* This code path is called after _all_ references to the
 		 * struct device has been dropped - so nobody should be
@@ -986,7 +993,7 @@ void ttm_dma_unpopulate(struct ttm_dma_t
 
 	/* shrink pool if necessary (only on !is_cached pools)*/
 	if (npages)
-		ttm_dma_page_pool_free(pool, npages, GFP_KERNEL);
+		ttm_dma_page_pool_free(pool, npages, false);
 	ttm->state = tt_unpopulated;
 }
 EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
@@ -996,8 +1003,6 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
  *
  * XXX: (dchinner) Deadlock warning!
  *
- * We need to pass sc->gfp_mask to ttm_dma_page_pool_free().
- *
  * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
  * shrinkers
  */
@@ -1030,8 +1035,8 @@ ttm_dma_pool_shrink_scan(struct shrinker
 		if (++idx < pool_offset)
 			continue;
 		nr_free = shrink_pages;
-		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free,
-						      sc->gfp_mask);
+		/* OK to use static buffer since global mutex is held. */
+		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free, true);
 		freed += nr_free - shrink_pages;
 
 		pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -406,11 +406,9 @@ int vmw_3d_resource_inc(struct vmw_priva
 		if (unlikely(ret != 0))
 			--dev_priv->num_3d_resources;
 	} else if (unhide_svga) {
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  vmw_read(dev_priv, SVGA_REG_ENABLE) &
 			  ~SVGA_REG_ENABLE_HIDE);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	mutex_unlock(&dev_priv->release_mutex);
@@ -433,13 +431,10 @@ void vmw_3d_resource_dec(struct vmw_priv
 	mutex_lock(&dev_priv->release_mutex);
 	if (unlikely(--dev_priv->num_3d_resources == 0))
 		vmw_release_device(dev_priv);
-	else if (hide_svga) {
-		mutex_lock(&dev_priv->hw_mutex);
+	else if (hide_svga)
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  vmw_read(dev_priv, SVGA_REG_ENABLE) |
 			  SVGA_REG_ENABLE_HIDE);
-		mutex_unlock(&dev_priv->hw_mutex);
-	}
 
 	n3d = (int32_t) dev_priv->num_3d_resources;
 	mutex_unlock(&dev_priv->release_mutex);
@@ -600,12 +595,14 @@ static int vmw_driver_load(struct drm_de
 	dev_priv->dev = dev;
 	dev_priv->vmw_chipset = chipset;
 	dev_priv->last_read_seqno = (uint32_t) -100;
-	mutex_init(&dev_priv->hw_mutex);
 	mutex_init(&dev_priv->cmdbuf_mutex);
 	mutex_init(&dev_priv->release_mutex);
 	mutex_init(&dev_priv->binding_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	ttm_lock_init(&dev_priv->reservation_sem);
+	spin_lock_init(&dev_priv->hw_lock);
+	spin_lock_init(&dev_priv->waiter_lock);
+	spin_lock_init(&dev_priv->cap_lock);
 
 	for (i = vmw_res_context; i < vmw_res_max; ++i) {
 		idr_init(&dev_priv->res_idr[i]);
@@ -626,14 +623,11 @@ static int vmw_driver_load(struct drm_de
 
 	dev_priv->enable_fb = enable_fbdev;
 
-	mutex_lock(&dev_priv->hw_mutex);
-
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
 	svga_id = vmw_read(dev_priv, SVGA_REG_ID);
 	if (svga_id != SVGA_ID_2) {
 		ret = -ENOSYS;
 		DRM_ERROR("Unsupported SVGA ID 0x%x\n", svga_id);
-		mutex_unlock(&dev_priv->hw_mutex);
 		goto out_err0;
 	}
 
@@ -683,10 +677,8 @@ static int vmw_driver_load(struct drm_de
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
 	ret = vmw_dma_masks(dev_priv);
-	if (unlikely(ret != 0)) {
-		mutex_unlock(&dev_priv->hw_mutex);
+	if (unlikely(ret != 0))
 		goto out_err0;
-	}
 
 	/*
 	 * Limit back buffer size to VRAM size.  Remove this once
@@ -695,8 +687,6 @@ static int vmw_driver_load(struct drm_de
 	if (dev_priv->prim_bb_mem > dev_priv->vram_size)
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
-	mutex_unlock(&dev_priv->hw_mutex);
-
 	vmw_print_capabilities(dev_priv->capabilities);
 
 	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
@@ -735,32 +725,6 @@ static int vmw_driver_load(struct drm_de
 		goto out_err1;
 	}
 
-	ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM,
-			     (dev_priv->vram_size >> PAGE_SHIFT));
-	if (unlikely(ret != 0)) {
-		DRM_ERROR("Failed initializing memory manager for VRAM.\n");
-		goto out_err2;
-	}
-
-	dev_priv->has_gmr = true;
-	if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) ||
-	    refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR,
-					 VMW_PL_GMR) != 0) {
-		DRM_INFO("No GMR memory available. "
-			 "Graphics memory resources are very limited.\n");
-		dev_priv->has_gmr = false;
-	}
-
-	if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
-		dev_priv->has_mob = true;
-		if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB,
-				   VMW_PL_MOB) != 0) {
-			DRM_INFO("No MOB memory available. "
-				 "3D will be disabled.\n");
-			dev_priv->has_mob = false;
-		}
-	}
-
 	dev_priv->mmio_mtrr = arch_phys_wc_add(dev_priv->mmio_start,
 					       dev_priv->mmio_size);
 
@@ -823,6 +787,33 @@ static int vmw_driver_load(struct drm_de
 		goto out_no_fman;
 	}
 
+
+	ret = ttm_bo_init_mm(&dev_priv->bdev, TTM_PL_VRAM,
+			     (dev_priv->vram_size >> PAGE_SHIFT));
+	if (unlikely(ret != 0)) {
+		DRM_ERROR("Failed initializing memory manager for VRAM.\n");
+		goto out_no_vram;
+	}
+
+	dev_priv->has_gmr = true;
+	if (((dev_priv->capabilities & (SVGA_CAP_GMR | SVGA_CAP_GMR2)) == 0) ||
+	    refuse_dma || ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_GMR,
+					 VMW_PL_GMR) != 0) {
+		DRM_INFO("No GMR memory available. "
+			 "Graphics memory resources are very limited.\n");
+		dev_priv->has_gmr = false;
+	}
+
+	if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
+		dev_priv->has_mob = true;
+		if (ttm_bo_init_mm(&dev_priv->bdev, VMW_PL_MOB,
+				   VMW_PL_MOB) != 0) {
+			DRM_INFO("No MOB memory available. "
+				 "3D will be disabled.\n");
+			dev_priv->has_mob = false;
+		}
+	}
+
 	vmw_kms_save_vga(dev_priv);
 
 	/* Start kms and overlay systems, needs fifo. */
@@ -848,6 +839,12 @@ out_no_fifo:
 	vmw_kms_close(dev_priv);
 out_no_kms:
 	vmw_kms_restore_vga(dev_priv);
+	if (dev_priv->has_mob)
+		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
+	if (dev_priv->has_gmr)
+		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
+	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
+out_no_vram:
 	vmw_fence_manager_takedown(dev_priv->fman);
 out_no_fman:
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
@@ -863,12 +860,6 @@ out_err4:
 	iounmap(dev_priv->mmio_virt);
 out_err3:
 	arch_phys_wc_del(dev_priv->mmio_mtrr);
-	if (dev_priv->has_mob)
-		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
-	if (dev_priv->has_gmr)
-		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
-	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
-out_err2:
 	(void)ttm_bo_device_release(&dev_priv->bdev);
 out_err1:
 	vmw_ttm_global_release(dev_priv);
@@ -898,6 +889,13 @@ static int vmw_driver_unload(struct drm_
 	}
 	vmw_kms_close(dev_priv);
 	vmw_overlay_close(dev_priv);
+
+	if (dev_priv->has_mob)
+		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
+	if (dev_priv->has_gmr)
+		(void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
+	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
+
 	vmw_fence_manager_takedown(dev_priv->fman);
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
 		drm_irq_uninstall(dev_priv->dev);
@@ -909,11 +907,6 @@ static int vmw_driver_unload(struct drm_
 	ttm_object_device_release(&dev_priv->tdev);
 	iounmap(dev_priv->mmio_virt);
 	arch_phys_wc_del(dev_priv->mmio_mtrr);
-	if (dev_priv->has_mob)
-		(void) ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_MOB);
-	if (dev_priv->has_gmr)
-		(void)ttm_bo_clean_mm(&dev_priv->bdev, VMW_PL_GMR);
-	(void)ttm_bo_clean_mm(&dev_priv->bdev, TTM_PL_VRAM);
 	(void)ttm_bo_device_release(&dev_priv->bdev);
 	vmw_ttm_global_release(dev_priv);
 
@@ -1063,8 +1056,12 @@ static long vmw_generic_ioctl(struct fil
 
 	vmaster = vmw_master_check(dev, file_priv, flags);
 	if (unlikely(IS_ERR(vmaster))) {
-		DRM_INFO("IOCTL ERROR %d\n", nr);
-		return PTR_ERR(vmaster);
+		ret = PTR_ERR(vmaster);
+
+		if (ret != -ERESTARTSYS)
+			DRM_INFO("IOCTL ERROR Command %d, Error %ld.\n",
+				 nr, ret);
+		return ret;
 	}
 
 	ret = ioctl_func(filp, cmd, arg);
@@ -1157,9 +1154,7 @@ static int vmw_master_set(struct drm_dev
 		if (unlikely(ret != 0))
 			return ret;
 		vmw_kms_save_vga(dev_priv);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 0);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	if (active) {
@@ -1193,9 +1188,7 @@ out_no_active_lock:
 	if (!dev_priv->enable_fb) {
 		vmw_kms_restore_vga(dev_priv);
 		vmw_3d_resource_dec(dev_priv, true);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 	return ret;
 }
@@ -1230,9 +1223,7 @@ static void vmw_master_drop(struct drm_d
 			DRM_ERROR("Unable to clean VRAM on master drop.\n");
 		vmw_kms_restore_vga(dev_priv);
 		vmw_3d_resource_dec(dev_priv, true);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	dev_priv->active_master = &dev_priv->fbdev_master;
@@ -1364,10 +1355,8 @@ static void vmw_pm_complete(struct devic
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct vmw_private *dev_priv = vmw_priv(dev);
 
-	mutex_lock(&dev_priv->hw_mutex);
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
 	(void) vmw_read(dev_priv, SVGA_REG_ID);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	/**
 	 * Reclaim 3d reference held by fbdev and potentially
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -399,7 +399,8 @@ struct vmw_private {
 	uint32_t memory_size;
 	bool has_gmr;
 	bool has_mob;
-	struct mutex hw_mutex;
+	spinlock_t hw_lock;
+	spinlock_t cap_lock;
 
 	/*
 	 * VGA registers.
@@ -449,8 +450,9 @@ struct vmw_private {
 	atomic_t marker_seq;
 	wait_queue_head_t fence_queue;
 	wait_queue_head_t fifo_queue;
-	int fence_queue_waiters; /* Protected by hw_mutex */
-	int goal_queue_waiters; /* Protected by hw_mutex */
+	spinlock_t waiter_lock;
+	int fence_queue_waiters; /* Protected by waiter_lock */
+	int goal_queue_waiters; /* Protected by waiter_lock */
 	atomic_t fifo_queue_waiters;
 	uint32_t last_read_seqno;
 	spinlock_t irq_lock;
@@ -553,20 +555,35 @@ static inline struct vmw_master *vmw_mas
 	return (struct vmw_master *) master->driver_priv;
 }
 
+/*
+ * The locking here is fine-grained, so that it is performed once
+ * for every read- and write operation. This is of course costly, but we
+ * don't perform much register access in the timing critical paths anyway.
+ * Instead we have the extra benefit of being sure that we don't forget
+ * the hw lock around register accesses.
+ */
 static inline void vmw_write(struct vmw_private *dev_priv,
 			     unsigned int offset, uint32_t value)
 {
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&dev_priv->hw_lock, irq_flags);
 	outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT);
 	outl(value, dev_priv->io_start + VMWGFX_VALUE_PORT);
+	spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags);
 }
 
 static inline uint32_t vmw_read(struct vmw_private *dev_priv,
 				unsigned int offset)
 {
-	uint32_t val;
+	unsigned long irq_flags;
+	u32 val;
 
+	spin_lock_irqsave(&dev_priv->hw_lock, irq_flags);
 	outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT);
 	val = inl(dev_priv->io_start + VMWGFX_VALUE_PORT);
+	spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags);
+
 	return val;
 }
 
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2778,13 +2778,11 @@ int vmw_execbuf_ioctl(struct drm_device
 				  NULL, arg->command_size, arg->throttle_us,
 				  (void __user *)(unsigned long)arg->fence_rep,
 				  NULL);
-
+	ttm_read_unlock(&dev_priv->reservation_sem);
 	if (unlikely(ret != 0))
-		goto out_unlock;
+		return ret;
 
 	vmw_kms_cursor_post_execbuf(dev_priv);
 
-out_unlock:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
+	return 0;
 }
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -35,7 +35,7 @@ struct vmw_fence_manager {
 	struct vmw_private *dev_priv;
 	spinlock_t lock;
 	struct list_head fence_list;
-	struct work_struct work, ping_work;
+	struct work_struct work;
 	u32 user_fence_size;
 	u32 fence_size;
 	u32 event_fence_action_size;
@@ -134,14 +134,6 @@ static const char *vmw_fence_get_timelin
 	return "svga";
 }
 
-static void vmw_fence_ping_func(struct work_struct *work)
-{
-	struct vmw_fence_manager *fman =
-		container_of(work, struct vmw_fence_manager, ping_work);
-
-	vmw_fifo_ping_host(fman->dev_priv, SVGA_SYNC_GENERIC);
-}
-
 static bool vmw_fence_enable_signaling(struct fence *f)
 {
 	struct vmw_fence_obj *fence =
@@ -155,11 +147,7 @@ static bool vmw_fence_enable_signaling(s
 	if (seqno - fence->base.seqno < VMW_FENCE_WRAP)
 		return false;
 
-	if (mutex_trylock(&dev_priv->hw_mutex)) {
-		vmw_fifo_ping_host_locked(dev_priv, SVGA_SYNC_GENERIC);
-		mutex_unlock(&dev_priv->hw_mutex);
-	} else
-		schedule_work(&fman->ping_work);
+	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 
 	return true;
 }
@@ -305,7 +293,6 @@ struct vmw_fence_manager *vmw_fence_mana
 	INIT_LIST_HEAD(&fman->fence_list);
 	INIT_LIST_HEAD(&fman->cleanup_list);
 	INIT_WORK(&fman->work, &vmw_fence_work_func);
-	INIT_WORK(&fman->ping_work, &vmw_fence_ping_func);
 	fman->fifo_down = true;
 	fman->user_fence_size = ttm_round_pot(sizeof(struct vmw_user_fence));
 	fman->fence_size = ttm_round_pot(sizeof(struct vmw_fence_obj));
@@ -323,7 +310,6 @@ void vmw_fence_manager_takedown(struct v
 	bool lists_empty;
 
 	(void) cancel_work_sync(&fman->work);
-	(void) cancel_work_sync(&fman->ping_work);
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
 	lists_empty = list_empty(&fman->fence_list) &&
@@ -545,35 +531,19 @@ void vmw_fence_obj_flush(struct vmw_fenc
 
 static void vmw_fence_destroy(struct vmw_fence_obj *fence)
 {
-	struct vmw_fence_manager *fman = fman_from_fence(fence);
-
 	fence_free(&fence->base);
-
-	/*
-	 * Free kernel space accounting.
-	 */
-	ttm_mem_global_free(vmw_mem_glob(fman->dev_priv),
-			    fman->fence_size);
 }
 
 int vmw_fence_create(struct vmw_fence_manager *fman,
 		     uint32_t seqno,
 		     struct vmw_fence_obj **p_fence)
 {
-	struct ttm_mem_global *mem_glob = vmw_mem_glob(fman->dev_priv);
 	struct vmw_fence_obj *fence;
 	int ret;
 
-	ret = ttm_mem_global_alloc(mem_glob, fman->fence_size,
-				   false, false);
-	if (unlikely(ret != 0))
-		return ret;
-
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
-	if (unlikely(fence == NULL)) {
-		ret = -ENOMEM;
-		goto out_no_object;
-	}
+	if (unlikely(fence == NULL))
+		return -ENOMEM;
 
 	ret = vmw_fence_obj_init(fman, fence, seqno,
 				 vmw_fence_destroy);
@@ -585,8 +555,6 @@ int vmw_fence_create(struct vmw_fence_ma
 
 out_err_init:
 	kfree(fence);
-out_no_object:
-	ttm_mem_global_free(mem_glob, fman->fence_size);
 	return ret;
 }
 
@@ -1105,6 +1073,8 @@ static int vmw_event_fence_action_create
 	if (ret != 0)
 		goto out_no_queue;
 
+	return 0;
+
 out_no_queue:
 	event->base.destroy(&event->base);
 out_no_event:
@@ -1180,17 +1150,10 @@ int vmw_fence_event_ioctl(struct drm_dev
 
 	BUG_ON(fence == NULL);
 
-	if (arg->flags & DRM_VMW_FE_FLAG_REQ_TIME)
-		ret = vmw_event_fence_action_create(file_priv, fence,
-						    arg->flags,
-						    arg->user_data,
-						    true);
-	else
-		ret = vmw_event_fence_action_create(file_priv, fence,
-						    arg->flags,
-						    arg->user_data,
-						    true);
-
+	ret = vmw_event_fence_action_create(file_priv, fence,
+					    arg->flags,
+					    arg->user_data,
+					    true);
 	if (unlikely(ret != 0)) {
 		if (ret != -ERESTARTSYS)
 			DRM_ERROR("Failed to attach event to fence.\n");
Index: linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
===================================================================
--- linux-3.18.13-rt10-r7s4.orig/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ linux-3.18.13-rt10-r7s4/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -44,10 +44,10 @@ bool vmw_fifo_have_3d(struct vmw_private
 		if (!dev_priv->has_mob)
 			return false;
 
-		mutex_lock(&dev_priv->hw_mutex);
+		spin_lock(&dev_priv->cap_lock);
 		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_3D);
 		result = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
-		mutex_unlock(&dev_priv->hw_mutex);
+		spin_unlock(&dev_priv->cap_lock);
 
 		return (result != 0);
 	}
@@ -120,7 +120,6 @@ int vmw_fifo_init(struct vmw_private *de
 	DRM_INFO("height %d\n", vmw_read(dev_priv, SVGA_REG_HEIGHT));
 	DRM_INFO("bpp %d\n", vmw_read(dev_priv, SVGA_REG_BITS_PER_PIXEL));
 
-	mutex_lock(&dev_priv->hw_mutex);
 	dev_priv->enable_state = vmw_read(dev_priv, SVGA_REG_ENABLE);
 	dev_priv->config_done_state = vmw_read(dev_priv, SVGA_REG_CONFIG_DONE);
 	dev_priv->traces_state = vmw_read(dev_priv, SVGA_REG_TRACES);
@@ -143,7 +142,6 @@ int vmw_fifo_init(struct vmw_private *de
 	mb();
 
 	vmw_write(dev_priv, SVGA_REG_CONFIG_DONE, 1);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	max = ioread32(fifo_mem + SVGA_FIFO_MAX);
 	min = ioread32(fifo_mem  + SVGA_FIFO_MIN);
@@ -160,31 +158,28 @@ int vmw_fifo_init(struct vmw_private *de
 	return vmw_fifo_send_fence(dev_priv, &dummy);
 }
 
-void vmw_fifo_ping_host_locked(struct vmw_private *dev_priv, uint32_t reason)
+void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
 {
 	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
+	static DEFINE_SPINLOCK(ping_lock);
+	unsigned long irq_flags;
 
+	/*
+	 * The ping_lock is needed because we don't have an atomic
+	 * test-and-set of