Linux 3.19.2

This reverts commit abc86d0f99 as it is
broken in 3.19 and is easier to revert here than try to fix it.

Reported-by: Florian Westphal <fw@strlen.de
Reported-by: David Miller <davem@redhat.com>
Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

Documentation/stable_kernel_rules.txt

@@ -32,18 +32,42 @@ Procedure for submitting patches to the -stable tree:
  - 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 -stable tree:
      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:

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 19
-SUBLEVEL = 0
+SUBLEVEL = 2
 EXTRAVERSION =
 NAME = Diseased Newt
 

arch/arc/include/asm/pgtable.h

@@ -259,7 +259,8 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 #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)						\
 ({									\

arch/arc/include/asm/processor.h

@@ -75,18 +75,19 @@ unsigned long thread_saved_pc(struct task_struct *t);
 #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);

arch/arc/kernel/stacktrace.c

@@ -64,9 +64,9 @@ static void seed_unwind_frame_info(struct task_struct *tsk,
 
 		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

arch/arm/boot/dts/am335x-bone-common.dtsi

@@ -195,6 +195,7 @@
 
 &usb0 {
 	status = "okay";
+	dr_mode = "peripheral";
 };
 
 &usb1 {

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>;
 		};
 

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";

arch/arm/mach-bcm/Kconfig

@@ -68,7 +68,7 @@ config ARCH_BCM_MOBILE
 	  This enables support for systems based on Broadcom mobile SoCs.
 
 config ARCH_BCM_281XX
-	bool "Broadcom BCM281XX SoC family"
+	bool "Broadcom BCM281XX SoC family" if ARCH_MULTI_V7
 	select ARCH_BCM_MOBILE
 	select HAVE_SMP
 	help
@@ -77,7 +77,7 @@ config ARCH_BCM_281XX
 	  variants.
 
 config ARCH_BCM_21664
-	bool "Broadcom BCM21664 SoC family"
+	bool "Broadcom BCM21664 SoC family" if ARCH_MULTI_V7
 	select ARCH_BCM_MOBILE
 	select HAVE_SMP
 	help

arch/arm/mach-bcm/platsmp-brcmstb.c

@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/jiffies.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/printk.h>
@@ -94,10 +95,35 @@ static u32 pwr_ctrl_rd(u32 cpu)
 	return readl_relaxed(base);
 }
 
-static void pwr_ctrl_wr(u32 cpu, u32 val)
+static void pwr_ctrl_set(unsigned int cpu, u32 val, u32 mask)
 {
 	void __iomem *base = pwr_ctrl_get_base(cpu);
-	writel(val, base);
+	writel((readl(base) & mask) | val, base);
+}
+
+static void pwr_ctrl_clr(unsigned int cpu, u32 val, u32 mask)
+{
+	void __iomem *base = pwr_ctrl_get_base(cpu);
+	writel((readl(base) & mask) & ~val, base);
+}
+
+#define POLL_TMOUT_MS 500
+static int pwr_ctrl_wait_tmout(unsigned int cpu, u32 set, u32 mask)
+{
+	const unsigned long timeo = jiffies + msecs_to_jiffies(POLL_TMOUT_MS);
+	u32 tmp;
+
+	do {
+		tmp = pwr_ctrl_rd(cpu) & mask;
+		if (!set == !tmp)
+			return 0;
+	} while (time_before(jiffies, timeo));
+
+	tmp = pwr_ctrl_rd(cpu) & mask;
+	if (!set == !tmp)
+		return 0;
+
+	return -ETIMEDOUT;
 }
 
 static void cpu_rst_cfg_set(u32 cpu, int set)
@@ -139,15 +165,22 @@ static void brcmstb_cpu_power_on(u32 cpu)
 	 * The secondary cores power was cut, so we must go through
 	 * power-on initialization.
 	 */
-	u32 tmp;
+	pwr_ctrl_set(cpu, ZONE_MAN_ISO_CNTL_MASK, 0xffffff00);
+	pwr_ctrl_set(cpu, ZONE_MANUAL_CONTROL_MASK, -1);
+	pwr_ctrl_set(cpu, ZONE_RESERVED_1_MASK, -1);
 
-	/* Request zone power up */
-	pwr_ctrl_wr(cpu, ZONE_PWR_UP_REQ_MASK);
+	pwr_ctrl_set(cpu, ZONE_MAN_MEM_PWR_MASK, -1);
 
-	/* Wait for the power up FSM to complete */
-	do {
-		tmp = pwr_ctrl_rd(cpu);
-	} while (!(tmp & ZONE_PWR_ON_STATE_MASK));
+	if (pwr_ctrl_wait_tmout(cpu, 1, ZONE_MEM_PWR_STATE_MASK))
+		panic("ZONE_MEM_PWR_STATE_MASK set timeout");
+
+	pwr_ctrl_set(cpu, ZONE_MAN_CLKEN_MASK, -1);
+
+	if (pwr_ctrl_wait_tmout(cpu, 1, ZONE_DPG_PWR_STATE_MASK))
+		panic("ZONE_DPG_PWR_STATE_MASK set timeout");
+
+	pwr_ctrl_clr(cpu, ZONE_MAN_ISO_CNTL_MASK, -1);
+	pwr_ctrl_set(cpu, ZONE_MAN_RESET_CNTL_MASK, -1);
 }
 
 static int brcmstb_cpu_get_power_state(u32 cpu)
@@ -174,25 +207,33 @@ static void brcmstb_cpu_die(u32 cpu)
 
 static int brcmstb_cpu_kill(u32 cpu)
 {
-	u32 tmp;
+	/*
+	 * Ordinarily, the hardware forbids power-down of CPU0 (which is good
+	 * because it is the boot CPU), but this is not true when using BPCM
+	 * manual mode.  Consequently, we must avoid turning off CPU0 here to
+	 * ensure that TI2C master reset will work.
+	 */
+	if (cpu == 0) {
+		pr_warn("SMP: refusing to power off CPU0\n");
+		return 1;
+	}
 
 	while (per_cpu_sw_state_rd(cpu))
 		;
 
-	/* Program zone reset */
-	pwr_ctrl_wr(cpu, ZONE_RESET_STATE_MASK | ZONE_BLK_RST_ASSERT_MASK |
-			      ZONE_PWR_DN_REQ_MASK);
+	pwr_ctrl_set(cpu, ZONE_MANUAL_CONTROL_MASK, -1);
+	pwr_ctrl_clr(cpu, ZONE_MAN_RESET_CNTL_MASK, -1);
+	pwr_ctrl_clr(cpu, ZONE_MAN_CLKEN_MASK, -1);
+	pwr_ctrl_set(cpu, ZONE_MAN_ISO_CNTL_MASK, -1);
+	pwr_ctrl_clr(cpu, ZONE_MAN_MEM_PWR_MASK, -1);
 
-	/* Verify zone reset */
-	tmp = pwr_ctrl_rd(cpu);
-	if (!(tmp & ZONE_RESET_STATE_MASK))
-		pr_err("%s: Zone reset bit for CPU %d not asserted!\n",
-			__func__, cpu);
+	if (pwr_ctrl_wait_tmout(cpu, 0, ZONE_MEM_PWR_STATE_MASK))
+		panic("ZONE_MEM_PWR_STATE_MASK clear timeout");
 
-	/* Wait for power down */
-	do {
-		tmp = pwr_ctrl_rd(cpu);
-	} while (!(tmp & ZONE_PWR_OFF_STATE_MASK));
+	pwr_ctrl_clr(cpu, ZONE_RESERVED_1_MASK, -1);
+
+	if (pwr_ctrl_wait_tmout(cpu, 0, ZONE_DPG_PWR_STATE_MASK))
+		panic("ZONE_DPG_PWR_STATE_MASK clear timeout");
 
 	/* Flush pipeline before resetting CPU */
 	mb();

arch/arm/mach-mvebu/system-controller.c

@@ -126,7 +126,7 @@ int mvebu_system_controller_get_soc_id(u32 *dev, u32 *rev)
 		return -ENODEV;
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_MACH_MVEBU_V7)
 void mvebu_armada375_smp_wa_init(void)
 {
 	u32 dev, rev;

arch/arm/mach-omap2/omap_hwmod_7xx_data.c

@@ -2017,7 +2017,7 @@ static struct omap_hwmod dra7xx_uart3_hwmod = {
 	.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,

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)

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")

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)

arch/arm/mach-pxa/spitz.c

@@ -979,6 +979,8 @@ static void __init spitz_init(void)
 	spitz_nand_init();
 	spitz_i2c_init();
 	spitz_audio_init();
+
+	regulator_has_full_constraints();
 }
 
 static void __init spitz_fixup(struct tag *tags, char **cmdline)

arch/arm/mach-sa1100/pm.c

@@ -81,6 +81,7 @@ static int sa11x0_pm_enter(suspend_state_t state)
 	/*
 	 * Ensure not to come back here if it wasn't intended
 	 */
+	RCSR = RCSR_SMR;
 	PSPR = 0;
 
 	/*

arch/arm/mach-vexpress/Kconfig

@@ -73,6 +73,7 @@ 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.

arch/arm64/kernel/signal32.c

@@ -154,8 +154,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 	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_siginfo_t __user *to, const siginfo_t *from)
 	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;
 	case __SI_SYS:
 		err |= __put_user((compat_uptr_t)(unsigned long)

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)
 

arch/mips/alchemy/common/clock.c

@@ -127,6 +127,8 @@ static unsigned long alchemy_clk_cpu_recalc(struct clk_hw *hw,
 		t = 396000000;
 	else {
 		t = alchemy_rdsys(AU1000_SYS_CPUPLL) & 0x7f;
+		if (alchemy_get_cputype() < ALCHEMY_CPU_AU1300)
+			t &= 0x3f;
 		t *= parent_rate;
 	}
 

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

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[];

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_struct *prev, struct mm_struct *next,
 	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_struct *prev, struct mm_struct *next,
 	 */
 	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, struct mm_struct *next)
 
 	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, struct mm_struct *next)
 	/* 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, unsigned cpu)
 	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, unsigned cpu)
 		/* will get a new context next time */
 		cpu_context(cpu, mm) = 0;
 	}
+	htw_start();
 	local_irq_restore(flags);
 }
 

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_struct *mm, unsigned long addr, pte_t *pt
 {
 	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, pte_t pteval)
 
 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_struct *mm, unsigned long addr, pte_t *pt
 	else
 #endif
 		set_pte_at(mm, addr, ptep, __pte(0));
-	htw_reset();
+	htw_start();
 }
 #endif
 

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
 

arch/mips/kernel/cpu-probe.c

@@ -424,8 +424,10 @@ static inline unsigned int decode_config3(struct cpuinfo_mips *c)
 	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;
 }

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,
@@ -31,6 +33,14 @@ extern long __strnlen_kernel_asm(const char *s);
 extern long __strnlen_user_nocheck_asm(const char *s);
 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
  */

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

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_vcpu *vcpu, struct kvm_run *run)
 		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_vcpu *vcpu, struct kvm_run *run)
 
 	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 *run, struct kvm_vcpu *vcpu)
 	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;
 }
 

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 */

arch/powerpc/include/asm/pnv-pci.h

@@ -19,7 +19,7 @@ int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
 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,

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -152,7 +152,7 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 	 * in virtual mode.
 	 */
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		/* Down_CPPR */
 		new_state.cppr = new_cppr;
@@ -211,7 +211,7 @@ unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
 	 * pending priority
 	 */
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		xirr = old_state.xisr | (((u32)old_state.cppr) << 24);
 		if (!old_state.xisr)
@@ -277,7 +277,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
 	 * whenever the MFRR is made less favored.
 	 */
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		/* Set_MFRR */
 		new_state.mfrr = mfrr;
@@ -352,7 +352,7 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
 	icp_rm_clr_vcpu_irq(icp->vcpu);
 
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		reject = 0;
 		new_state.cppr = cppr;

arch/powerpc/kvm/book3s_xics.c

@@ -327,7 +327,7 @@ static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority,
 		 icp->server_num);
 
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		*reject = 0;
 
@@ -512,7 +512,7 @@ static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 	 * in virtual mode.
 	 */
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		/* Down_CPPR */
 		new_state.cppr = new_cppr;
@@ -567,7 +567,7 @@ static noinline unsigned long kvmppc_h_xirr(struct kvm_vcpu *vcpu)
 	 * pending priority
 	 */
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		xirr = old_state.xisr | (((u32)old_state.cppr) << 24);
 		if (!old_state.xisr)
@@ -634,7 +634,7 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
 	 * whenever the MFRR is made less favored.
 	 */
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		/* Set_MFRR */
 		new_state.mfrr = mfrr;
@@ -679,7 +679,7 @@ static int kvmppc_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
 		if (!icp)
 			return H_PARAMETER;
 	}
-	state = ACCESS_ONCE(icp->state);
+	state = READ_ONCE(icp->state);
 	kvmppc_set_gpr(vcpu, 4, ((u32)state.cppr << 24) | state.xisr);
 	kvmppc_set_gpr(vcpu, 5, state.mfrr);
 	return H_SUCCESS;
@@ -721,7 +721,7 @@ static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
 				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
 
 	do {
-		old_state = new_state = ACCESS_ONCE(icp->state);
+		old_state = new_state = READ_ONCE(icp->state);
 
 		reject = 0;
 		new_state.cppr = cppr;
@@ -885,7 +885,7 @@ static int xics_debug_show(struct seq_file *m, void *private)
 		if (!icp)
 			continue;
 
-		state.raw = ACCESS_ONCE(icp->state.raw);
+		state.raw = READ_ONCE(icp->state.raw);
 		seq_printf(m, "cpu server %#lx XIRR:%#x PPRI:%#x CPPR:%#x MFRR:%#x OUT:%d NR:%d\n",
 			   icp->server_num, state.xisr,
 			   state.pending_pri, state.cppr, state.mfrr,
@@ -1082,7 +1082,7 @@ int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
 	 * the ICS states before the ICP states.
 	 */
 	do {
-		old_state = ACCESS_ONCE(icp->state);
+		old_state = READ_ONCE(icp->state);
 
 		if (new_state.mfrr <= old_state.mfrr) {
 			resend = false;

arch/powerpc/mm/hugetlbpage.c

@@ -978,7 +978,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 		 */
 		pdshift = PUD_SHIFT;
 		pudp = pud_offset(&pgd, ea);
-		pud  = ACCESS_ONCE(*pudp);
+		pud  = READ_ONCE(*pudp);
 
 		if (pud_none(pud))
 			return NULL;
@@ -990,7 +990,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 		else {
 			pdshift = PMD_SHIFT;
 			pmdp = pmd_offset(&pud, ea);
-			pmd  = ACCESS_ONCE(*pmdp);
+			pmd  = READ_ONCE(*pmdp);
 			/*
 			 * A hugepage collapse is captured by pmd_none, because
 			 * it mark the pmd none and do a hpte invalidate.

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1460,13 +1460,13 @@ static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 
 #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)
 {

arch/powerpc/sysdev/axonram.c

@@ -156,7 +156,7 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
 	}
 
 	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
 
 	return 0;
 }

arch/s390/kvm/interrupt.c

@@ -820,7 +820,7 @@ 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;
 }
 
@@ -840,10 +840,20 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 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;
 }
 
@@ -1187,6 +1197,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 		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 {
@@ -1221,6 +1233,7 @@ 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)
@@ -1268,7 +1281,10 @@ 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,

arch/s390/kvm/kvm-s390.c

@@ -670,7 +670,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *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;

arch/sh/mm/gup.c

@@ -17,7 +17,7 @@
 static inline pte_t gup_get_pte(pte_t *ptep)
 {
 #ifndef CONFIG_X2TLB
-	return ACCESS_ONCE(*ptep);
+	return READ_ONCE(*ptep);
 #else
 	/*
 	 * With get_user_pages_fast, we walk down the pagetables without

arch/x86/boot/compressed/Makefile

@@ -49,6 +49,7 @@ $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
 vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
 	$(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
 	$(call if_changed,ld)

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 */

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:

arch/x86/include/asm/spinlock.h

@@ -46,7 +46,7 @@ static __always_inline bool static_key_false(struct static_key *key);
 
 static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
 {
-	set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
+	set_bit(0, (volatile unsigned long *)&lock->tickets.head);
 }
 
 #else  /* !CONFIG_PARAVIRT_SPINLOCKS */
@@ -60,10 +60,30 @@ static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
 }
 
 #endif /* CONFIG_PARAVIRT_SPINLOCKS */
+static inline int  __tickets_equal(__ticket_t one, __ticket_t two)
+{
+	return !((one ^ two) & ~TICKET_SLOWPATH_FLAG);
+}
+
+static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock,
+							__ticket_t head)
+{
+	if (head & TICKET_SLOWPATH_FLAG) {
+		arch_spinlock_t old, new;
+
+		old.tickets.head = head;
+		new.tickets.head = head & ~TICKET_SLOWPATH_FLAG;
+		old.tickets.tail = new.tickets.head + TICKET_LOCK_INC;
+		new.tickets.tail = old.tickets.tail;
+
+		/* try to clear slowpath flag when there are no contenders */
+		cmpxchg(&lock->head_tail, old.head_tail, new.head_tail);
+	}
+}
 
 static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
-	return lock.tickets.head == lock.tickets.tail;
+	return __tickets_equal(lock.tickets.head, lock.tickets.tail);
 }
 
 /*
@@ -87,18 +107,21 @@ static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 	if (likely(inc.head == inc.tail))
 		goto out;
 
-	inc.tail &= ~TICKET_SLOWPATH_FLAG;
 	for (;;) {
 		unsigned count = SPIN_THRESHOLD;
 
 		do {
-			if (READ_ONCE(lock->tickets.head) == inc.tail)
-				goto out;
+			inc.head = READ_ONCE(lock->tickets.head);
+			if (__tickets_equal(inc.head, inc.tail))
+				goto clear_slowpath;
 			cpu_relax();
 		} while (--count);
 		__ticket_lock_spinning(lock, inc.tail);
 	}
-out:	barrier();	/* make sure nothing creeps before the lock is taken */
+clear_slowpath:
+	__ticket_check_and_clear_slowpath(lock, inc.head);
+out:
+	barrier();	/* make sure nothing creeps before the lock is taken */
 }
 
 static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -106,56 +129,30 @@ static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
 	arch_spinlock_t old, new;
 
 	old.tickets = READ_ONCE(lock->tickets);
-	if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
+	if (!__tickets_equal(old.tickets.head, old.tickets.tail))
 		return 0;
 
 	new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
+	new.head_tail &= ~TICKET_SLOWPATH_FLAG;
 
 	/* cmpxchg is a full barrier, so nothing can move before it */
 	return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
 }
 
-static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
-					    arch_spinlock_t old)
-{
-	arch_spinlock_t new;
-
-	BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
-
-	/* Perform the unlock on the "before" copy */
-	old.tickets.head += TICKET_LOCK_INC;
-
-	/* Clear the slowpath flag */
-	new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);
-
-	/*
-	 * If the lock is uncontended, clear the flag - use cmpxchg in
-	 * case it changes behind our back though.
-	 */
-	if (new.tickets.head != new.tickets.tail ||
-	    cmpxchg(&lock->head_tail, old.head_tail,
-					new.head_tail) != old.head_tail) {
-		/*
-		 * Lock still has someone queued for it, so wake up an
-		 * appropriate waiter.
-		 */
-		__ticket_unlock_kick(lock, old.tickets.head);
-	}
-}
-
 static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	if (TICKET_SLOWPATH_FLAG &&
-	    static_key_false(&paravirt_ticketlocks_enabled)) {
-		arch_spinlock_t prev;
+		static_key_false(&paravirt_ticketlocks_enabled)) {
+		__ticket_t head;
 
-		prev = *lock;
-		add_smp(&lock->tickets.head, TICKET_LOCK_INC);
+		BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
 
-		/* add_smp() is a full mb() */
+		head = xadd(&lock->tickets.head, TICKET_LOCK_INC);
 
-		if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
-			__ticket_unlock_slowpath(lock, prev);
+		if (unlikely(head & TICKET_SLOWPATH_FLAG)) {
+			head &= ~TICKET_SLOWPATH_FLAG;
+			__ticket_unlock_kick(lock, (head + TICKET_LOCK_INC));
+		}
 	} else
 		__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
 }
@@ -164,14 +161,15 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
 	struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 
-	return tmp.tail != tmp.head;
+	return !__tickets_equal(tmp.tail, tmp.head);
 }
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
 	struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 
-	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
+	tmp.head &= ~TICKET_SLOWPATH_FLAG;
+	return (tmp.tail - tmp.head) > TICKET_LOCK_INC;
 }
 #define arch_spin_is_contended	arch_spin_is_contended
 
@@ -183,16 +181,16 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
-	__ticket_t head = ACCESS_ONCE(lock->tickets.head);
+	__ticket_t head = READ_ONCE(lock->tickets.head);
 
 	for (;;) {
-		struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+		struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 		/*
 		 * We need to check "unlocked" in a loop, tmp.head == head
 		 * can be false positive because of overflow.
 		 */
-		if (tmp.head == (tmp.tail & ~TICKET_SLOWPATH_FLAG) ||
-		    tmp.head != head)
+		if (__tickets_equal(tmp.head, tmp.tail) ||
+				!__tickets_equal(tmp.head, head))
 			break;
 
 		cpu_relax();

arch/x86/include/asm/xsave.h

@@ -82,18 +82,15 @@ static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
 	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;
 }
 
@@ -112,18 +109,15 @@ static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
 	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;
 }
 
@@ -149,9 +143,9 @@ static inline int xsave_state(struct xsave_struct *fx, u64 mask)
 	 */
 	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");
@@ -178,7 +172,7 @@ static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
 	 */
 	alternative_input(
 		"1: " XRSTOR,
-		"1: " XRSTORS,
+		XRSTORS,
 		X86_FEATURE_XSAVES,
 		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 		: "memory");

arch/x86/kernel/acpi/boot.c

@@ -613,6 +613,11 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
 	int rc, irq, trigger, polarity;
 
+	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
+		*irqp = gsi;
+		return 0;
+	}
+
 	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
 	if (rc == 0) {
 		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;

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

arch/x86/kernel/kvm.c

@@ -609,7 +609,7 @@ static inline void check_zero(void)
 	u8 ret;
 	u8 old;
 
-	old = ACCESS_ONCE(zero_stats);
+	old = READ_ONCE(zero_stats);
 	if (unlikely(old)) {
 		ret = cmpxchg(&zero_stats, old, 0);
 		/* This ensures only one fellow resets the stat */
@@ -727,6 +727,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	int cpu;
 	u64 start;
 	unsigned long flags;
+	__ticket_t head;
 
 	if (in_nmi())
 		return;
@@ -768,11 +769,15 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	 */
 	__ticket_enter_slowpath(lock);
 
+	/* make sure enter_slowpath, which is atomic does not cross the read */
+	smp_mb__after_atomic();
+
 	/*
 	 * check again make sure it didn't become free while
 	 * we weren't looking.
 	 */
-	if (ACCESS_ONCE(lock->tickets.head) == want) {
+	head = READ_ONCE(lock->tickets.head);
+	if (__tickets_equal(head, want)) {
 		add_stats(TAKEN_SLOW_PICKUP, 1);
 		goto out;
 	}
@@ -803,8 +808,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
 	add_stats(RELEASED_SLOW, 1);
 	for_each_cpu(cpu, &waiting_cpus) {
 		const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
-		if (ACCESS_ONCE(w->lock) == lock &&
-		    ACCESS_ONCE(w->want) == ticket) {
+		if (READ_ONCE(w->lock) == lock &&
+		    READ_ONCE(w->want) == ticket) {
 			add_stats(RELEASED_SLOW_KICKED, 1);
 			kvm_kick_cpu(cpu);
 			break;

arch/x86/kernel/pmc_atom.c

@@ -217,6 +217,8 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
 	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 *pmc, struct pci_dev *pdev)
 		dev_err(&pdev->dev, "sleep_state register failed\n");
 		goto err;
 	}
-	pmc->dbgfs_dir = dir;
+
 	return 0;
 err:
 	pmc_dbgfs_unregister(pmc);

arch/x86/kvm/emulate.c

@@ -4863,7 +4863,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		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:
 

arch/x86/mm/gup.c

@@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		 */
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (unlikely(pmd_large(pmd))) {
+		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

arch/x86/mm/hugetlbpage.c

@@ -66,9 +66,15 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 	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)

arch/x86/mm/mmap.c

@@ -35,12 +35,12 @@ struct va_alignment __read_mostly va_align = {
 	.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;

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

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

arch/x86/xen/p2m.c

@@ -554,7 +554,7 @@ static bool alloc_p2m(unsigned long pfn)
 		mid_mfn = NULL;
 	}
 
-	p2m_pfn = pte_pfn(ACCESS_ONCE(*ptep));
+	p2m_pfn = pte_pfn(READ_ONCE(*ptep));
 	if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) ||
 	    p2m_pfn == PFN_DOWN(__pa(p2m_missing))) {
 		/* p2m leaf page is missing */

arch/x86/xen/spinlock.c

@@ -41,7 +41,7 @@ static u8 zero_stats;
 static inline void check_zero(void)
 {
 	u8 ret;
-	u8 old = ACCESS_ONCE(zero_stats);
+	u8 old = READ_ONCE(zero_stats);
 	if (unlikely(old)) {
 		ret = cmpxchg(&zero_stats, old, 0);
 		/* This ensures only one fellow resets the stat */
@@ -112,6 +112,7 @@ __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
 	int cpu = smp_processor_id();
 	u64 start;
+	__ticket_t head;
 	unsigned long flags;
 
 	/* If kicker interrupts not initialized yet, just spin */
@@ -159,11 +160,15 @@ __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	 */
 	__ticket_enter_slowpath(lock);
 
+	/* make sure enter_slowpath, which is atomic does not cross the read */
+	smp_mb__after_atomic();
+
 	/*
 	 * check again make sure it didn't become free while
 	 * we weren't looking
 	 */
-	if (ACCESS_ONCE(lock->tickets.head) == want) {
+	head = READ_ONCE(lock->tickets.head);
+	if (__tickets_equal(head, want)) {
 		add_stats(TAKEN_SLOW_PICKUP, 1);
 		goto out;
 	}
@@ -204,8 +209,8 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
 		const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
 
 		/* Make sure we read lock before want */
-		if (ACCESS_ONCE(w->lock) == lock &&
-		    ACCESS_ONCE(w->want) == next) {
+		if (READ_ONCE(w->lock) == lock &&
+		    READ_ONCE(w->want) == next) {
 			add_stats(RELEASED_SLOW_KICKED, 1);
 			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
 			break;

block/blk-mq-tag.c

@@ -509,6 +509,7 @@ static int bt_alloc(struct blk_mq_bitmap_tags *bt, unsigned int depth,
 	bt->bs = kzalloc(BT_WAIT_QUEUES * sizeof(*bt->bs), GFP_KERNEL);
 	if (!bt->bs) {
 		kfree(bt->map);
+		bt->map = NULL;
 		return -ENOMEM;
 	}
 

block/blk-throttle.c

@@ -1292,6 +1292,9 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf,
 	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);
 

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;
 	}

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_private_data *pdata)
 	}
 }
 
-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_private_data *pdata)
 	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_dev_desc = {
 
 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_dev_desc = {
 
 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_dev_desc = {
 	.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_lpss_device_ids[] = {
 	/* 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;
 }
 

drivers/acpi/video.c

@@ -2149,6 +2149,17 @@ EXPORT_SYMBOL(acpi_video_unregister_backlight);
 
 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())

drivers/bluetooth/ath3k.c

@@ -108,6 +108,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ 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 */
@@ -162,6 +163,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ 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 */
@@ -174,6 +176,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 #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)
@@ -205,6 +209,9 @@ static int ath3k_load_firmware(struct usb_device *udev,
 	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);
 
@@ -302,6 +309,9 @@ static int ath3k_load_fwfile(struct usb_device *udev,
 	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);
 

drivers/bluetooth/btusb.c

@@ -109,16 +109,24 @@ static const struct usb_device_id btusb_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3404),
 	  .driver_info = BTUSB_BCM_PATCHRAM },
 
+	/* 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),
 	  .driver_info = BTUSB_BCM_PATCHRAM },
 
+	/* 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) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x0b05, 0xff, 0x01, 0x01),
+	  .driver_info = BTUSB_BCM_PATCHRAM },
 
 	/* Belkin F8065bf - Broadcom based */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x050d, 0xff, 0x01, 0x01) },
@@ -188,6 +196,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ 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 */

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;

drivers/char/tpm/tpm-interface.c

@@ -1122,7 +1122,7 @@ struct tpm_chip *tpm_register_hardware(struct device *dev,
 
 	/* 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;

drivers/char/tpm/tpm_i2c_atmel.c

@@ -168,6 +168,10 @@ static int i2c_atmel_probe(struct i2c_client *client,
 
 	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);

drivers/char/tpm/tpm_i2c_nuvoton.c

@@ -538,6 +538,11 @@ static int i2c_nuvoton_probe(struct i2c_client *client,
 
 	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);
 

drivers/char/tpm/tpm_i2c_stm_st33.c

@@ -487,7 +487,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 		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;
 

drivers/char/tpm/tpm_ibmvtpm.c

@@ -148,7 +148,8 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 	crq.len = (u16)count;
 	crq.data = ibmvtpm->rtce_dma_handle;
 
-	rc = ibmvtpm_send_crq(ibmvtpm->vdev, word[0], word[1]);
+	rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(word[0]),
+			      cpu_to_be64(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(struct ibmvtpm_dev *ibmvtpm)
 	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(struct ibmvtpm_dev *ibmvtpm)
 	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_dev *vdev)
 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 device *dev)
 	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 ibmvtpm_crq *crq,
 	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 ibmvtpm_crq *crq,
 
 			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:

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 dummy, void *dev_id)
 	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 *dev, resource_size_t start,
 	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 *dev, resource_size_t start,
 	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 *dev, resource_size_t start,
 		}
 	}
 
+	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);

drivers/clk/clk-gate.c

@@ -128,7 +128,7 @@ struct clk *clk_register_gate(struct device *dev, const char *name,
 	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);
 		}

drivers/clk/clk.c

@@ -343,13 +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);
 }
 

drivers/clk/sunxi/clk-sunxi.c

@@ -413,6 +413,7 @@ static struct clk_factors_config sun6i_a31_pll1_config = {
 	.kwidth = 2,
 	.mshift = 0,
 	.mwidth = 2,
+	.n_start = 1,
 };
 
 static struct clk_factors_config sun8i_a23_pll1_config = {

drivers/clk/zynq/clkc.c

@@ -303,6 +303,7 @@ static void __init zynq_clk_setup(struct device_node *np)
 	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);

drivers/clocksource/mtk_timer.c

@@ -224,6 +224,8 @@ static void __init mtk_timer_init(struct device_node *node)
 	}
 	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 device_node *node)
 
 	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 device_node *node)
 
 	/* 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:

drivers/coresight/coresight-etm3x.c

@@ -573,7 +573,8 @@ static ssize_t mode_store(struct device *dev,
 	if (drvdata->mode & ETM_MODE_STALL) {
 		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
 			dev_warn(drvdata->dev, "stall mode not supported\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_unlock;
 		}
 		drvdata->ctrl |= ETMCR_STALL_MODE;
 	 } else
@@ -582,7 +583,8 @@ static ssize_t mode_store(struct device *dev,
 	if (drvdata->mode & ETM_MODE_TIMESTAMP) {
 		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
 			dev_warn(drvdata->dev, "timestamp not supported\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_unlock;
 		}
 		drvdata->ctrl |= ETMCR_TIMESTAMP_EN;
 	} else
@@ -595,6 +597,10 @@ static ssize_t mode_store(struct device *dev,
 	spin_unlock(&drvdata->spinlock);
 
 	return size;
+
+err_unlock:
+	spin_unlock(&drvdata->spinlock);
+	return ret;
 }
 static DEVICE_ATTR_RW(mode);
 

drivers/cpufreq/cpufreq.c

@@ -1416,9 +1416,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 	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__);
@@ -1473,7 +1474,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 		}
 	}
 
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	return 0;
 }
 

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_cpufreq_reboot_notifier = {
 	.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;

drivers/cpufreq/s3c24xx-cpufreq.c

@@ -144,11 +144,6 @@ static void s3c_cpufreq_setfvco(struct s3c_cpufreq_config *cfg)
 	(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 cpufreq_policy *policy)
 
 	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_driver = {
 };
 
 
-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",

drivers/cpufreq/speedstep-lib.c

@@ -400,6 +400,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 	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 speedstep_processor processor,
 
 out:
 	local_irq_restore(flags);
+	preempt_enable();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(speedstep_get_freqs);

drivers/cpufreq/speedstep-smi.c

@@ -156,6 +156,7 @@ static void speedstep_set_state(unsigned int state)
 		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 int state)
 
 	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 int state)
 
 	/* enable IRQs */
 	local_irq_restore(flags);
+	preempt_enable();
 
 	if (new_state == state)
 		pr_debug("change to %u MHz succeeded after %u tries "

drivers/dma-buf/reservation.c

@@ -402,8 +402,6 @@ reservation_object_test_signaled_single(struct fence *passed_fence)
 	int ret = 1;
 
 	if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) {
-		int ret;
-
 		fence = fence_get_rcu(lfence);
 		if (!fence)
 			return -1;

drivers/edac/amd64_edac.c

@@ -2174,14 +2174,20 @@ static void __log_bus_error(struct mem_ctl_info *mci, struct err_info *err,
 
 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;

drivers/edac/sb_edac.c

@@ -2447,7 +2447,7 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		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;
@@ -2460,8 +2460,11 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		type = BROADWELL;
 		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) {
@@ -2474,7 +2477,7 @@ static int sbridge_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			goto fail1;
 	}
 
-	sbridge_printk(KERN_INFO, "Driver loaded.\n");
+	sbridge_printk(KERN_INFO, "%s\n", SBRIDGE_REVISION);
 
 	mutex_unlock(&sbridge_edac_lock);
 	return 0;

drivers/firmware/dmi_scan.c

@@ -78,7 +78,7 @@ static const char * __init dmi_string(const struct dmi_header *dm, u8 s)
  *	We have to be cautious here. We have seen BIOSes with DMI pointers
  *	pointing to completely the wrong place for example
  */
-static void dmi_table(u8 *buf, int len, int num,
+static void dmi_table(u8 *buf, u32 len, int num,
 		      void (*decode)(const struct dmi_header *, void *),
 		      void *private_data)
 {
@@ -92,12 +92,6 @@ static void dmi_table(u8 *buf, int len, int num,
 	while ((i < num) && (data - buf + sizeof(struct dmi_header)) <= len) {
 		const struct dmi_header *dm = (const struct dmi_header *)data;
 
-		/*
-		 * 7.45 End-of-Table (Type 127) [SMBIOS reference spec v3.0.0]
-		 */
-		if (dm->type == DMI_ENTRY_END_OF_TABLE)
-			break;
-
 		/*
 		 *  We want to know the total length (formatted area and
 		 *  strings) before decoding to make sure we won't run off the
@@ -108,13 +102,20 @@ static void dmi_table(u8 *buf, int len, int num,
 			data++;
 		if (data - buf < len - 1)
 			decode(dm, private_data);
+
+		/*
+		 * 7.45 End-of-Table (Type 127) [SMBIOS reference spec v3.0.0]
+		 */
+		if (dm->type == DMI_ENTRY_END_OF_TABLE)
+			break;
+
 		data += 2;
 		i++;
 	}
 }
 
 static phys_addr_t dmi_base;
-static u16 dmi_len;
+static u32 dmi_len;
 static u16 dmi_num;
 
 static int __init dmi_walk_early(void (*decode)(const struct dmi_header *,

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;
 

drivers/firmware/efi/runtime-map.c

@@ -191,7 +191,7 @@ int __init efi_runtime_map_init(struct kobject *efi_kobj)
 
 	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);
 	}

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_chip *gc, unsigned offset)
 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 gpio_chip *gc, unsigned offset,
 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 gpio_chip *gc, unsigned offset,
 
 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);

drivers/gpio/gpiolib-of.c

@@ -46,12 +46,13 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data)
 
 	ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags);
 	if (ret < 0) {
-		/* We've found the gpio chip, but the translation failed.
-		 * Return true to stop looking and return the translation
-		 * error via out_gpio
+		/* 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 true;
+		return false;
 	 }
 
 	gg_data->out_gpio = gpiochip_get_desc(gc, ret);

drivers/gpu/drm/i915/i915_drv.h

@@ -2160,6 +2160,7 @@ struct drm_i915_cmd_table {
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
 				 ((INTEL_DEVID(dev) & 0xf) == 0x6 ||	\
+				 (INTEL_DEVID(dev) & 0xf) == 0xb ||	\
 				 (INTEL_DEVID(dev) & 0xf) == 0xe))
 #define IS_BDW_GT3(dev)		(IS_BROADWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0x00F0) == 0x0020)

drivers/gpu/drm/i915/i915_gem_tiling.c

@@ -335,9 +335,10 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		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) {
@@ -369,7 +370,6 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		}
 	}
 
-	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
@@ -424,6 +424,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		obj->bit_17 = NULL;
 	}
 
+err:
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
 

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_invalidate_range_start(struct mmu_notifier *_mn,
 			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);

drivers/gpu/drm/i915/i915_irq.c

@@ -1884,6 +1884,9 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 	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 */
 
@@ -1928,6 +1931,9 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 	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);
@@ -2200,6 +2206,9 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	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);
@@ -2271,6 +2280,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	enum pipe pipe;
 	u32 aux_mask = GEN8_AUX_CHANNEL_A;
 
+	if (!intel_irqs_enabled(dev_priv))
+		return IRQ_NONE;
+
 	if (IS_GEN9(dev))
 		aux_mask |=  GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
 			GEN9_AUX_CHANNEL_D;
@@ -3770,6 +3782,9 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		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;
@@ -3950,6 +3965,9 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		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;
@@ -4172,6 +4190,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		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 (;;) {
@@ -4523,6 +4544,7 @@ void intel_runtime_pm_disable_interrupts(struct drm_i915_private *dev_priv)
 {
 	dev_priv->dev->driver->irq_uninstall(dev_priv->dev);
 	dev_priv->pm.irqs_enabled = false;
+	synchronize_irq(dev_priv->dev->irq);
 }
 
 /**

drivers/gpu/drm/i915/intel_display.c

@@ -13019,6 +13019,9 @@ 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)

drivers/gpu/drm/i915/intel_dp.c

@@ -3515,8 +3515,6 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 	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)))
@@ -3541,8 +3539,6 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 
 	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.
@@ -3553,18 +3549,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 		 */
 		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;

drivers/gpu/drm/i915/intel_fifo_underrun.c

@@ -282,16 +282,6 @@ bool intel_set_cpu_fifo_underrun_reporting(struct drm_i915_private *dev_priv,
 	return ret;
 }
 
-static bool
-__cpu_fifo_underrun_reporting_enabled(struct drm_i915_private *dev_priv,
-				      enum pipe pipe)
-{
-	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
-	return !intel_crtc->cpu_fifo_underrun_disabled;
-}
-
 /**
  * intel_set_pch_fifo_underrun_reporting - set PCH fifo underrun reporting state
  * @dev_priv: i915 device instance
@@ -352,9 +342,15 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_i915_private *dev_priv,
 void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv,
 					 enum pipe pipe)
 {
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+
+	/* We may be called too early in init, thanks BIOS! */
+	if (crtc == NULL)
+		return;
+
 	/* GMCH can't disable fifo underruns, filter them. */
 	if (HAS_GMCH_DISPLAY(dev_priv->dev) &&
-	    !__cpu_fifo_underrun_reporting_enabled(dev_priv, pipe))
+	    to_intel_crtc(crtc)->cpu_fifo_underrun_disabled)
 		return;
 
 	if (intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false))

drivers/gpu/drm/i915/intel_lrc.c

@@ -1237,15 +1237,17 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
 
 	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);

drivers/gpu/drm/i915/intel_pm.c

@@ -4625,7 +4625,10 @@ static void gen6_init_rps_frequencies(struct drm_device *dev)
 					&ddcc_status);
 		if (0 == ret)
 			dev_priv->rps.efficient_freq =
-				(ddcc_status >> 8) & 0xff;
+				clamp_t(u8,
+					((ddcc_status >> 8) & 0xff),
+					dev_priv->rps.min_freq,
+					dev_priv->rps.max_freq);
 	}
 
 	/* Preserve min/max settings in case of re-init */

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -2178,6 +2178,14 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 	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
@@ -2185,8 +2193,8 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 	 * 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) {
@@ -2282,6 +2290,14 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	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
@@ -2289,8 +2305,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	 * 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) {