Merge branch 'foreign/liubo/replace-lockup' into for-chris-4.6

Documentation/cgroup-v2.txt

@@ -7,7 +7,7 @@ This is the authoritative documentation on the design, interface and
 conventions of cgroup v2.  It describes all userland-visible aspects
 of cgroup including core and specific controller behaviors.  All
 future changes must be reflected in this document.  Documentation for
-v1 is available under Documentation/cgroup-legacy/.
+v1 is available under Documentation/cgroup-v1/.
 
 CONTENTS
 

Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt

@@ -8,6 +8,7 @@ OHCI and EHCI controllers.
 Required properties:
 - compatible: "renesas,pci-r8a7790" for the R8A7790 SoC;
 	      "renesas,pci-r8a7791" for the R8A7791 SoC;
+	      "renesas,pci-r8a7793" for the R8A7793 SoC;
 	      "renesas,pci-r8a7794" for the R8A7794 SoC;
 	      "renesas,pci-rcar-gen2" for a generic R-Car Gen2 compatible device
 

Documentation/devicetree/bindings/pci/rcar-pci.txt

@@ -4,6 +4,7 @@ Required properties:
 compatible: "renesas,pcie-r8a7779" for the R8A7779 SoC;
 	    "renesas,pcie-r8a7790" for the R8A7790 SoC;
 	    "renesas,pcie-r8a7791" for the R8A7791 SoC;
+	    "renesas,pcie-r8a7793" for the R8A7793 SoC;
 	    "renesas,pcie-r8a7795" for the R8A7795 SoC;
 	    "renesas,pcie-rcar-gen2" for a generic R-Car Gen2 compatible device.
 

Documentation/devicetree/bindings/sound/fsl-asoc-card.txt

@@ -30,6 +30,8 @@ The compatible list for this generic sound card currently:
  "fsl,imx-audio-sgtl5000"
  (compatible with Documentation/devicetree/bindings/sound/imx-audio-sgtl5000.txt)
 
+ "fsl,imx-audio-wm8960"
+
 Required properties:
 
   - compatible		: Contains one of entries in the compatible list.

Documentation/devicetree/bindings/thermal/rcar-thermal.txt

@@ -1,8 +1,9 @@
 * Renesas R-Car Thermal
 
 Required properties:
-- compatible		: "renesas,thermal-<soctype>", "renesas,rcar-thermal"
-			  as fallback.
+- compatible		: "renesas,thermal-<soctype>",
+			   "renesas,rcar-gen2-thermal" (with thermal-zone) or
+			   "renesas,rcar-thermal" (without thermal-zone) as fallback.
 			  Examples with soctypes are:
 			    - "renesas,thermal-r8a73a4" (R-Mobile APE6)
 			    - "renesas,thermal-r8a7779" (R-Car H1)
@@ -36,3 +37,35 @@ thermal@e61f0000 {
 		0xe61f0300 0x38>;
 	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+Example (with thermal-zone):
+
+thermal-zones {
+	cpu_thermal: cpu-thermal {
+		polling-delay-passive	= <1000>;
+		polling-delay		= <5000>;
+
+		thermal-sensors = <&thermal>;
+
+		trips {
+			cpu-crit {
+				temperature	= <115000>;
+				hysteresis	= <0>;
+				type		= "critical";
+			};
+		};
+		cooling-maps {
+		};
+	};
+};
+
+thermal: thermal@e61f0000 {
+	compatible =	"renesas,thermal-r8a7790",
+			"renesas,rcar-gen2-thermal",
+			"renesas,rcar-thermal";
+	reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
+	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+	power-domains = <&cpg_clocks>;
+	#thermal-sensor-cells = <0>;
+};

Documentation/kernel-parameters.txt

@@ -4235,6 +4235,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default value of this parameter is determined by
 			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
 
+	workqueue.debug_force_rr_cpu
+			Workqueue used to implicitly guarantee that work
+			items queued without explicit CPU specified are put
+			on the local CPU.  This guarantee is no longer true
+			and while local CPU is still preferred work items
+			may be put on foreign CPUs.  This debug option
+			forces round-robin CPU selection to flush out
+			usages which depend on the now broken guarantee.
+			When enabled, memory and cache locality will be
+			impacted.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.

MAINTAINERS

@@ -2362,14 +2362,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rpi/linux-rpi.git
 S:	Maintained
 N:	bcm2835
 
-BROADCOM BCM33XX MIPS ARCHITECTURE
-M:	Kevin Cernekee <cernekee@gmail.com>
-L:	linux-mips@linux-mips.org
-S:	Maintained
-F:	arch/mips/bcm3384/*
-F:	arch/mips/include/asm/mach-bcm3384/*
-F:	arch/mips/kernel/*bmips*
-
 BROADCOM BCM47XX MIPS ARCHITECTURE
 M:	Hauke Mehrtens <hauke@hauke-m.de>
 M:	Rafał Miłecki <zajec5@gmail.com>
@@ -9787,10 +9779,11 @@ S:	Supported
 F:	drivers/scsi/be2iscsi/
 
 Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
-M:	Sathya Perla <sathya.perla@avagotech.com>
-M:	Ajit Khaparde <ajit.khaparde@avagotech.com>
-M:	Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
-M:	Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
+M:	Sathya Perla <sathya.perla@broadcom.com>
+M:	Ajit Khaparde <ajit.khaparde@broadcom.com>
+M:	Padmanabh Ratnakar <padmanabh.ratnakar@broadcom.com>
+M:	Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
+M:	Somnath Kotur <somnath.kotur@broadcom.com>
 L:	netdev@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*

arch/arc/Kconfig

@@ -338,6 +338,19 @@ config ARC_PAGE_SIZE_4K
 
 endchoice
 
+choice
+	prompt "MMU Super Page Size"
+	depends on ISA_ARCV2 && TRANSPARENT_HUGEPAGE
+	default ARC_HUGEPAGE_2M
+
+config ARC_HUGEPAGE_2M
+	bool "2MB"
+
+config ARC_HUGEPAGE_16M
+	bool "16MB"
+
+endchoice
+
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
@@ -410,7 +423,7 @@ config ARC_HAS_RTC
 	default n
 	depends on !SMP
 
-config ARC_HAS_GRTC
+config ARC_HAS_GFRC
 	bool "SMP synchronized 64-bit cycle counter"
 	default y
 	depends on SMP
@@ -566,6 +579,12 @@ endmenu
 endmenu	 # "ARC Architecture Configuration"
 
 source "mm/Kconfig"
+
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	default "12" if ARC_HUGEPAGE_16M
+	default "11"
+
 source "net/Kconfig"
 source "drivers/Kconfig"
 source "fs/Kconfig"

arch/arc/configs/vdk_hs38_smp_defconfig

@@ -16,7 +16,7 @@ CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-# CONFIG_ARC_HAS_GRTC is not set
+# CONFIG_ARC_HAS_GFRC is not set
 CONFIG_ARC_UBOOT_SUPPORT=y
 CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp"
 CONFIG_PREEMPT=y

arch/arc/include/asm/arcregs.h

@@ -349,14 +349,13 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
-	struct bcr_timer timers;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
-			     pad4:8;
+			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;
 	struct bcr_extn_xymem extn_xymem;

arch/arc/include/asm/irqflags-arcv2.h

@@ -30,8 +30,11 @@
 /* Was Intr taken in User Mode */
 #define AUX_IRQ_ACT_BIT_U	31
 
-/* 0 is highest level, but taken by FIRQs, if present in design */
-#define ARCV2_IRQ_DEF_PRIO		0
+/*
+ * User space should be interruptable even by lowest prio interrupt
+ * Safe even if actual interrupt priorities is fewer or even one
+ */
+#define ARCV2_IRQ_DEF_PRIO	15
 
 /* seed value for status register */
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \

arch/arc/include/asm/mcip.h

@@ -39,8 +39,8 @@ struct mcip_cmd {
 #define CMD_DEBUG_SET_MASK		0x34
 #define CMD_DEBUG_SET_SELECT		0x36
 
-#define CMD_GRTC_READ_LO		0x42
-#define CMD_GRTC_READ_HI		0x43
+#define CMD_GFRC_READ_LO		0x42
+#define CMD_GFRC_READ_HI		0x43
 
 #define CMD_IDU_ENABLE			0x71
 #define CMD_IDU_DISABLE			0x72

arch/arc/include/asm/pgtable.h

@@ -179,37 +179,44 @@
 #define __S111  PAGE_U_X_W_R
 
 /****************************************************************
- * Page Table Lookup split
+ * 2 tier (PGD:PTE) software page walker
  *
- * We implement 2 tier paging and since this is all software, we are free
- * to customize the span of a PGD / PTE entry to suit us
- *
- *			32 bit virtual address
+ * [31]		    32 bit virtual address              [0]
  * -------------------------------------------------------
- * | BITS_FOR_PGD    |  BITS_FOR_PTE    |  BITS_IN_PAGE  |
+ * |               | <------------ PGDIR_SHIFT ----------> |
+ * |		   |					 |
+ * | BITS_FOR_PGD  |  BITS_FOR_PTE  | <-- PAGE_SHIFT --> |
  * -------------------------------------------------------
  *       |                  |                |
  *       |                  |                --> off in page frame
- *       |		    |
  *       |                  ---> index into Page Table
- *       |
  *       ----> index into Page Directory
+ *
+ * In a single page size configuration, only PAGE_SHIFT is fixed
+ * So both PGD and PTE sizing can be tweaked
+ *  e.g. 8K page (PAGE_SHIFT 13) can have
+ *  - PGDIR_SHIFT 21  -> 11:8:13 address split
+ *  - PGDIR_SHIFT 24  -> 8:11:13 address split
+ *
+ * If Super Page is configured, PGDIR_SHIFT becomes fixed too,
+ * so the sizing flexibility is gone.
  */
 
-#define BITS_IN_PAGE	PAGE_SHIFT
-
-/* Optimal Sizing of Pg Tbl - based on MMU page size */
-#if defined(CONFIG_ARC_PAGE_SIZE_8K)
-#define BITS_FOR_PTE	8		/* 11:8:13 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_16K)
-#define BITS_FOR_PTE	8		/* 10:8:14 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
-#define BITS_FOR_PTE	9		/* 11:9:12 */
+#if defined(CONFIG_ARC_HUGEPAGE_16M)
+#define PGDIR_SHIFT	24
+#elif defined(CONFIG_ARC_HUGEPAGE_2M)
+#define PGDIR_SHIFT	21
+#else
+/*
+ * Only Normal page support so "hackable" (see comment above)
+ * Default value provides 11:8:13 (8K), 11:9:12 (4K)
+ */
+#define PGDIR_SHIFT	21
 #endif
 
-#define BITS_FOR_PGD	(32 - BITS_FOR_PTE - BITS_IN_PAGE)
+#define BITS_FOR_PTE	(PGDIR_SHIFT - PAGE_SHIFT)
+#define BITS_FOR_PGD	(32 - PGDIR_SHIFT)
 
-#define PGDIR_SHIFT	(32 - BITS_FOR_PGD)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 

arch/arc/kernel/entry-arcv2.S

@@ -211,7 +211,11 @@ debug_marker_syscall:
 ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
 ; entry was via Exception in DS which got preempted in kernel).
 ;
-; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround
+;
+; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline
+; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly
+
 .Lintr_ret_to_delay_slot:
 debug_marker_ds:
 
@@ -222,18 +226,23 @@ debug_marker_ds:
 	ld	r2, [sp, PT_ret]
 	ld	r3, [sp, PT_status32]
 
+	; STAT32 for Int return created from scratch
+	; (No delay dlot, disable Further intr in trampoline)
+
 	bic  	r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK
 	st	r0, [sp, PT_status32]
 
 	mov	r1, .Lintr_ret_to_delay_slot_2
 	st	r1, [sp, PT_ret]
 
+	; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots
 	st	r2, [sp, 0]
 	st	r3, [sp, 4]
 
 	b	.Lisr_ret_fast_path
 
 .Lintr_ret_to_delay_slot_2:
+	; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP
 	sub	sp, sp, SZ_PT_REGS
 	st	r9, [sp, -4]
 
@@ -243,11 +252,19 @@ debug_marker_ds:
 	ld	r9, [sp, 4]
 	sr	r9, [erstatus]
 
+	; restore AUX_USER_SP if returning to U mode
+	bbit0	r9, STATUS_U_BIT, 1f
+	ld	r9, [sp, PT_sp]
+	sr	r9, [AUX_USER_SP]
+
+1:
 	ld	r9, [sp, 8]
 	sr	r9, [erbta]
 
 	ld	r9, [sp, -4]
 	add	sp, sp, SZ_PT_REGS
+
+	; return from pure kernel mode to delay slot
 	rtie
 
 END(ret_from_exception)

arch/arc/kernel/intc-arcv2.c

@@ -14,6 +14,8 @@
 #include <linux/irqchip.h>
 #include <asm/irq.h>
 
+static int irq_prio;
+
 /*
  * Early Hardware specific Interrupt setup
  * -Called very early (start_kernel -> setup_arch -> setup_processor)
@@ -24,6 +26,14 @@ void arc_init_IRQ(void)
 {
 	unsigned int tmp;
 
+	struct irq_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:3, firq:1, prio:4, exts:8, irqs:8, ver:8;
+#else
+		unsigned int ver:8, irqs:8, exts:8, prio:4, firq:1, pad:3;
+#endif
+	} irq_bcr;
+
 	struct aux_irq_ctrl {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int res3:18, save_idx_regs:1, res2:1,
@@ -46,28 +56,25 @@ void arc_init_IRQ(void)
 
 	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
 
-	/* setup status32, don't enable intr yet as kernel doesn't want */
-	tmp = read_aux_reg(0xa);
-	tmp |= ISA_INIT_STATUS_BITS;
-	tmp &= ~STATUS_IE_MASK;
-	asm volatile("flag %0	\n"::"r"(tmp));
-
 	/*
 	 * ARCv2 core intc provides multiple interrupt priorities (upto 16).
 	 * Typical builds though have only two levels (0-high, 1-low)
 	 * Linux by default uses lower prio 1 for most irqs, reserving 0 for
 	 * NMI style interrupts in future (say perf)
-	 *
-	 * Read the intc BCR to confirm that Linux default priority is avail
-	 * in h/w
-	 *
-	 * Note:
-	 *  IRQ_BCR[27..24] contains N-1 (for N priority levels) and prio level
-	 *  is 0 based.
 	 */
-	tmp = (read_aux_reg(ARC_REG_IRQ_BCR) >> 24 ) & 0xF;
-	if (ARCV2_IRQ_DEF_PRIO > tmp)
-		panic("Linux default irq prio incorrect\n");
+
+	READ_BCR(ARC_REG_IRQ_BCR, irq_bcr);
+
+	irq_prio = irq_bcr.prio;	/* Encoded as N-1 for N levels */
+	pr_info("archs-intc\t: %d priority levels (default %d)%s\n",
+		irq_prio + 1, irq_prio,
+		irq_bcr.firq ? " FIRQ (not used)":"");
+
+	/* setup status32, don't enable intr yet as kernel doesn't want */
+	tmp = read_aux_reg(0xa);
+	tmp |= STATUS_AD_MASK | (irq_prio << 1);
+	tmp &= ~STATUS_IE_MASK;
+	asm volatile("flag %0	\n"::"r"(tmp));
 }
 
 static void arcv2_irq_mask(struct irq_data *data)
@@ -86,7 +93,7 @@ void arcv2_irq_enable(struct irq_data *data)
 {
 	/* set default priority */
 	write_aux_reg(AUX_IRQ_SELECT, data->irq);
-	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+	write_aux_reg(AUX_IRQ_PRIORITY, irq_prio);
 
 	/*
 	 * hw auto enables (linux unmask) all by default

arch/arc/kernel/mcip.c

@@ -96,13 +96,13 @@ static void mcip_probe_n_setup(void)
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int pad3:8,
 			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  grtc:1, dbg:1, pad2:1,
+			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
 			     msg:1, sem:1, ipi:1, pad:1,
 			     ver:8;
 #else
 		unsigned int ver:8,
 			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, grtc:1, iocoh:1,
+			     pad2:1, dbg:1, gfrc:1, iocoh:1,
 			     num_cores:6, llm:1, idu:1,
 			     pad3:8;
 #endif
@@ -116,7 +116,7 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
-		IS_AVAIL1(mp.grtc, "GRTC"));
+		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	idu_detected = mp.idu;
 
@@ -125,8 +125,8 @@ static void mcip_probe_n_setup(void)
 		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
 	}
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_GRTC) && !mp.grtc)
-		panic("kernel trying to use non-existent GRTC\n");
+	if (IS_ENABLED(CONFIG_ARC_HAS_GFRC) && !mp.gfrc)
+		panic("kernel trying to use non-existent GFRC\n");
 }
 
 struct plat_smp_ops plat_smp_ops = {

arch/arc/kernel/setup.c

@@ -45,6 +45,7 @@ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 static void read_arc_build_cfg_regs(void)
 {
 	struct bcr_perip uncached_space;
+	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	unsigned long perip_space;
@@ -53,7 +54,11 @@ static void read_arc_build_cfg_regs(void)
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
-	READ_BCR(ARC_REG_TIMERS_BCR, cpu->timers);
+	READ_BCR(ARC_REG_TIMERS_BCR, timer);
+	cpu->extn.timer0 = timer.t0;
+	cpu->extn.timer1 = timer.t1;
+	cpu->extn.rtc = timer.rtc;
+
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
@@ -208,9 +213,9 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       (unsigned int)(arc_get_core_freq() / 10000) % 100);
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
-		       IS_AVAIL1(cpu->timers.t0, "Timer0 "),
-		       IS_AVAIL1(cpu->timers.t1, "Timer1 "),
-		       IS_AVAIL2(cpu->timers.rtc, "64-bit RTC ",
+		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
+		       IS_AVAIL1(cpu->extn.timer1, "Timer1 "),
+		       IS_AVAIL2(cpu->extn.rtc, "Local-64-bit-Ctr ",
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
@@ -293,13 +298,13 @@ static void arc_chk_core_config(void)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	int fpu_enabled;
 
-	if (!cpu->timers.t0)
+	if (!cpu->extn.timer0)
 		panic("Timer0 is not present!\n");
 
-	if (!cpu->timers.t1)
+	if (!cpu->extn.timer1)
 		panic("Timer1 is not present!\n");
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->timers.rtc)
+	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->extn.rtc)
 		panic("RTC is not present\n");
 
 #ifdef CONFIG_ARC_HAS_DCCM
@@ -334,6 +339,7 @@ static void arc_chk_core_config(void)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
 
 	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    IS_ENABLED(CONFIG_ARC_HAS_LLSC) &&
 	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
 		panic("llock/scond livelock workaround missing\n");
 }

arch/arc/kernel/time.c

@@ -62,7 +62,7 @@
 
 /********** Clock Source Device *********/
 
-#ifdef CONFIG_ARC_HAS_GRTC
+#ifdef CONFIG_ARC_HAS_GFRC
 
 static int arc_counter_setup(void)
 {
@@ -83,10 +83,10 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 
 	local_irq_save(flags);
 
-	__mcip_cmd(CMD_GRTC_READ_LO, 0);
+	__mcip_cmd(CMD_GFRC_READ_LO, 0);
 	stamp.l = read_aux_reg(ARC_REG_MCIP_READBACK);
 
-	__mcip_cmd(CMD_GRTC_READ_HI, 0);
+	__mcip_cmd(CMD_GFRC_READ_HI, 0);
 	stamp.h = read_aux_reg(ARC_REG_MCIP_READBACK);
 
 	local_irq_restore(flags);
@@ -95,7 +95,7 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 }
 
 static struct clocksource arc_counter = {
-	.name   = "ARConnect GRTC",
+	.name   = "ARConnect GFRC",
 	.rating = 400,
 	.read   = arc_counter_read,
 	.mask   = CLOCKSOURCE_MASK(64),

arch/arm/common/icst.c

@@ -16,7 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-
+#include <asm/div64.h>
 #include <asm/hardware/icst.h>
 
 /*
@@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div);
 
 unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco)
 {
-	return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]);
+	u64 dividend = p->ref * 2 * (u64)(vco.v + 8);
+	u32 divisor = (vco.r + 2) * p->s2div[vco.s];
+
+	do_div(dividend, divisor);
+	return (unsigned long)dividend;
 }
 
 EXPORT_SYMBOL(icst_hz);
@@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq)
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)

arch/arm/configs/omap2plus_defconfig

@@ -292,24 +292,23 @@ CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
-CONFIG_OMAP2_DSS=m
-CONFIG_OMAP5_DSS_HDMI=y
-CONFIG_OMAP2_DSS_SDI=y
-CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP5_DSS_HDMI=y
+CONFIG_FB_OMAP2_DSS_SDI=y
+CONFIG_FB_OMAP2_DSS_DSI=y
 CONFIG_FB_OMAP2=m
-CONFIG_DISPLAY_ENCODER_TFP410=m
-CONFIG_DISPLAY_ENCODER_TPD12S015=m
-CONFIG_DISPLAY_CONNECTOR_DVI=m
-CONFIG_DISPLAY_CONNECTOR_HDMI=m
-CONFIG_DISPLAY_CONNECTOR_ANALOG_TV=m
-CONFIG_DISPLAY_PANEL_DPI=m
-CONFIG_DISPLAY_PANEL_DSI_CM=m
-CONFIG_DISPLAY_PANEL_SONY_ACX565AKM=m
-CONFIG_DISPLAY_PANEL_LGPHILIPS_LB035Q02=m
-CONFIG_DISPLAY_PANEL_SHARP_LS037V7DW01=m
-CONFIG_DISPLAY_PANEL_TPO_TD028TTEC1=m
-CONFIG_DISPLAY_PANEL_TPO_TD043MTEA1=m
-CONFIG_DISPLAY_PANEL_NEC_NL8048HL11=m
+CONFIG_FB_OMAP2_ENCODER_TFP410=m
+CONFIG_FB_OMAP2_ENCODER_TPD12S015=m
+CONFIG_FB_OMAP2_CONNECTOR_DVI=m
+CONFIG_FB_OMAP2_CONNECTOR_HDMI=m
+CONFIG_FB_OMAP2_CONNECTOR_ANALOG_TV=m
+CONFIG_FB_OMAP2_PANEL_DPI=m
+CONFIG_FB_OMAP2_PANEL_DSI_CM=m
+CONFIG_FB_OMAP2_PANEL_SONY_ACX565AKM=m
+CONFIG_FB_OMAP2_PANEL_LGPHILIPS_LB035Q02=m
+CONFIG_FB_OMAP2_PANEL_SHARP_LS037V7DW01=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD028TTEC1=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD043MTEA1=m
+CONFIG_FB_OMAP2_PANEL_NEC_NL8048HL11=m
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=y

arch/arm64/include/asm/arch_gicv3.h

@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 

arch/arm64/include/asm/kvm_arm.h

@@ -182,6 +182,7 @@
 #define CPTR_EL2_TCPAC	(1 << 31)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
+#define CPTR_EL2_DEFAULT	0x000033ff
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TDRA		(1 << 11)

arch/arm64/include/asm/kvm_emulate.h

@@ -127,10 +127,14 @@ static inline unsigned long *vcpu_spsr(const struct kvm_vcpu *vcpu)
 
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
-	u32 mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
+	u32 mode;
 
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
+		mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
 		return mode > COMPAT_PSR_MODE_USR;
+	}
+
+	mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
 
 	return mode != PSR_MODE_EL0t;
 }

arch/arm64/kvm/hyp/switch.c

@@ -36,7 +36,11 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(val, hcr_el2);
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
-	write_sysreg(CPTR_EL2_TTA | CPTR_EL2_TFP, cptr_el2);
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
+	write_sysreg(val, cptr_el2);
+
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
@@ -45,7 +49,7 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(HCR_RW, hcr_el2);
 	write_sysreg(0, hstr_el2);
 	write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
-	write_sysreg(0, cptr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
 static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)

arch/arm64/kvm/inject_fault.c

@@ -27,7 +27,11 @@
 
 #define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
 				 PSR_I_BIT | PSR_D_BIT)
-#define EL1_EXCEPT_SYNC_OFFSET	0x200
+
+#define CURRENT_EL_SP_EL0_VECTOR	0x0
+#define CURRENT_EL_SP_ELx_VECTOR	0x200
+#define LOWER_EL_AArch64_VECTOR		0x400
+#define LOWER_EL_AArch32_VECTOR		0x600
 
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
@@ -97,6 +101,34 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		*fsr = 0x14;
 }
 
+enum exception_type {
+	except_type_sync	= 0,
+	except_type_irq		= 0x80,
+	except_type_fiq		= 0x100,
+	except_type_serror	= 0x180,
+};
+
+static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
+{
+	u64 exc_offset;
+
+	switch (*vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT)) {
+	case PSR_MODE_EL1t:
+		exc_offset = CURRENT_EL_SP_EL0_VECTOR;
+		break;
+	case PSR_MODE_EL1h:
+		exc_offset = CURRENT_EL_SP_ELx_VECTOR;
+		break;
+	case PSR_MODE_EL0t:
+		exc_offset = LOWER_EL_AArch64_VECTOR;
+		break;
+	default:
+		exc_offset = LOWER_EL_AArch32_VECTOR;
+	}
+
+	return vcpu_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -108,8 +140,8 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
 
+	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
 
 	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
 
@@ -143,8 +175,8 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
 
+	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
 
 	/*
 	 * Build an unknown exception, depending on the instruction

arch/arm64/kvm/sys_regs.c

@@ -1007,10 +1007,9 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			/* Handled */
+			return 0;
 		}
-
-		/* Handled */
-		return 0;
 	}
 
 	/* Not handled */
@@ -1043,7 +1042,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 }
 
 /**
- * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP14/CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
@@ -1095,7 +1094,7 @@ out:
 }
 
 /**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */

arch/mips/Kconfig

@@ -2085,7 +2085,7 @@ config PAGE_SIZE_32KB
 
 config PAGE_SIZE_64KB
 	bool "64kB"
-	depends on !CPU_R3000 && !CPU_TX39XX
+	depends on !CPU_R3000 && !CPU_TX39XX && !CPU_R6000
 	help
 	  Using 64kB page size will result in higher performance kernel at
 	  the price of higher memory consumption.  This option is available on

arch/mips/boot/dts/brcm/bcm6328.dtsi

@@ -74,6 +74,7 @@
 		timer: timer@10000040 {
 			compatible = "syscon";
 			reg = <0x10000040 0x2c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7125.dtsi

@@ -98,6 +98,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7125-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7346.dtsi

@@ -118,6 +118,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7346-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7358.dtsi

@@ -112,6 +112,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7358-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7360.dtsi

@@ -112,6 +112,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7360-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7362.dtsi

@@ -118,6 +118,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7362-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7420.dtsi

@@ -99,6 +99,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7420-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7425.dtsi

@@ -100,6 +100,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/boot/dts/brcm/bcm7435.dtsi

@@ -114,6 +114,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {

arch/mips/include/asm/elf.h

@@ -227,7 +227,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
@@ -258,7 +258,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS64)			\
 		__res = 0;						\
@@ -285,6 +285,11 @@ struct mips_elf_abiflags_v0 {
 
 #endif /* !defined(ELF_ARCH) */
 
+#define mips_elf_check_machine(x) ((x)->e_machine == EM_MIPS)
+
+#define vmcore_elf32_check_arch mips_elf_check_machine
+#define vmcore_elf64_check_arch mips_elf_check_machine
+
 struct mips_abi;
 
 extern struct mips_abi mips_abi;

arch/mips/include/asm/fpu.h

@@ -179,6 +179,10 @@ static inline void lose_fpu_inatomic(int save, struct task_struct *tsk)
 		if (save)
 			_save_fp(tsk);
 		__disable_fpu();
+	} else {
+		/* FPU should not have been left enabled with no owner */
+		WARN(read_c0_status() & ST0_CU1,
+		     "Orphaned FPU left enabled");
 	}
 	KSTK_STATUS(tsk) &= ~ST0_CU1;
 	clear_tsk_thread_flag(tsk, TIF_USEDFPU);

arch/mips/include/asm/octeon/octeon-feature.h

@@ -128,7 +128,8 @@ static inline int octeon_has_feature(enum octeon_feature feature)
 	case OCTEON_FEATURE_PCIE:
 		return OCTEON_IS_MODEL(OCTEON_CN56XX)
 			|| OCTEON_IS_MODEL(OCTEON_CN52XX)
-			|| OCTEON_IS_MODEL(OCTEON_CN6XXX);
+			|| OCTEON_IS_MODEL(OCTEON_CN6XXX)
+			|| OCTEON_IS_MODEL(OCTEON_CN7XXX);
 
 	case OCTEON_FEATURE_SRIO:
 		return OCTEON_IS_MODEL(OCTEON_CN63XX)

arch/mips/include/asm/processor.h

@@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
  * User space process size: 2GB. This is hardcoded into a few places,
  * so don't change it unless you know what you are doing.
  */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif
 
 #define STACK_TOP_MAX	TASK_SIZE

arch/mips/include/asm/stackframe.h

@@ -289,7 +289,7 @@
 		.set	reorder
 		.set	noat
 		mfc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_IM
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
@@ -330,7 +330,7 @@
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_FR | ST0_IM
 		and	a0, v1
 		LONG_L	v0, PT_STATUS(sp)
 		nor	v1, $0, v1

arch/mips/include/asm/syscall.h

@@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
 	if ((config_enabled(CONFIG_32BIT) ||
 	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall)) {
+	    (regs->regs[2] == __NR_syscall))
 		i++;
-		n++;
-	}
 
 	while (n--)
 		ret |= mips_get_syscall_arg(args++, task, regs, i++);

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

@@ -380,16 +380,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 357)
 #define __NR_membarrier			(__NR_Linux + 358)
 #define __NR_mlock2			(__NR_Linux + 359)
+#define __NR_copy_file_range		(__NR_Linux + 360)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		359
+#define __NR_Linux_syscalls		360
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		359
+#define __NR_O32_Linux_syscalls		360
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -717,16 +718,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 317)
 #define __NR_membarrier			(__NR_Linux + 318)
 #define __NR_mlock2			(__NR_Linux + 319)
+#define __NR_copy_file_range		(__NR_Linux + 320)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		319
+#define __NR_Linux_syscalls		320
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		319
+#define __NR_64_Linux_syscalls		320
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1058,15 +1060,16 @@
 #define __NR_userfaultfd		(__NR_Linux + 321)
 #define __NR_membarrier			(__NR_Linux + 322)
 #define __NR_mlock2			(__NR_Linux + 323)
+#define __NR_copy_file_range		(__NR_Linux + 324)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		323
+#define __NR_Linux_syscalls		324
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		323
+#define __NR_N32_Linux_syscalls		324
 
 #endif /* _UAPI_ASM_UNISTD_H */

arch/mips/kernel/binfmt_elfn32.c

@@ -35,7 +35,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\

arch/mips/kernel/binfmt_elfo32.c

@@ -47,7 +47,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\

arch/mips/kernel/process.c

@@ -65,12 +65,10 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
 	status |= KU_USER;
 	regs->cp0_status = status;
+	lose_fpu(0);
+	clear_thread_flag(TIF_MSA_CTX_LIVE);
 	clear_used_math();
-	clear_fpu_owner();
 	init_dsp();
-	clear_thread_flag(TIF_USEDMSA);
-	clear_thread_flag(TIF_MSA_CTX_LIVE);
-	disable_msa();
 	regs->cp0_epc = pc;
 	regs->regs[29] = sp;
 }

arch/mips/kernel/scall32-o32.S

@@ -595,3 +595,4 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */

arch/mips/kernel/scall64-64.S

@@ -433,4 +433,5 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 5320 */
 	.size	sys_call_table,.-sys_call_table

arch/mips/kernel/scall64-n32.S

@@ -423,4 +423,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range
 	.size	sysn32_call_table,.-sysn32_call_table

arch/mips/kernel/scall64-o32.S

@@ -578,4 +578,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
 	.size	sys32_call_table,.-sys32_call_table

arch/mips/kernel/setup.c

@@ -782,6 +782,7 @@ static inline void prefill_possible_map(void) {}
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
+	mips_cm_probe();
 	prom_init();
 
 	setup_early_fdc_console();

arch/mips/kernel/traps.c

@@ -663,7 +663,7 @@ static int simulate_rdhwr_normal(struct pt_regs *regs, unsigned int opcode)
 	return -1;
 }
 
-static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned short opcode)
+static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned int opcode)
 {
 	if ((opcode & MM_POOL32A_FUNC) == MM_RDHWR) {
 		int rd = (opcode & MM_RS) >> 16;
@@ -1119,11 +1119,12 @@ no_r2_instr:
 	if (get_isa16_mode(regs->cp0_epc)) {
 		unsigned short mmop[2] = { 0 };
 
-		if (unlikely(get_user(mmop[0], epc) < 0))
+		if (unlikely(get_user(mmop[0], (u16 __user *)epc + 0) < 0))
 			status = SIGSEGV;
-		if (unlikely(get_user(mmop[1], epc) < 0))
+		if (unlikely(get_user(mmop[1], (u16 __user *)epc + 1) < 0))
 			status = SIGSEGV;
-		opcode = (mmop[0] << 16) | mmop[1];
+		opcode = mmop[0];
+		opcode = (opcode << 16) | mmop[1];
 
 		if (status < 0)
 			status = simulate_rdhwr_mm(regs, opcode);
@@ -1369,26 +1370,12 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 		if (unlikely(compute_return_epc(regs) < 0))
 			break;
 
-		if (get_isa16_mode(regs->cp0_epc)) {
-			unsigned short mmop[2] = { 0 };
-
-			if (unlikely(get_user(mmop[0], epc) < 0))
-				status = SIGSEGV;
-			if (unlikely(get_user(mmop[1], epc) < 0))
-				status = SIGSEGV;
-			opcode = (mmop[0] << 16) | mmop[1];
-
-			if (status < 0)
-				status = simulate_rdhwr_mm(regs, opcode);
-		} else {
+		if (!get_isa16_mode(regs->cp0_epc)) {
 			if (unlikely(get_user(opcode, epc) < 0))
 				status = SIGSEGV;
 
 			if (!cpu_has_llsc && status < 0)
 				status = simulate_llsc(regs, opcode);
-
-			if (status < 0)
-				status = simulate_rdhwr_normal(regs, opcode);
 		}
 
 		if (status < 0)

arch/mips/mm/sc-mips.c

@@ -181,10 +181,6 @@ static int __init mips_sc_probe_cm3(void)
 	return 1;
 }
 
-void __weak platform_early_l2_init(void)
-{
-}
-
 static inline int __init mips_sc_probe(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
@@ -194,12 +190,6 @@ static inline int __init mips_sc_probe(void)
 	/* Mark as not present until probe completed */
 	c->scache.flags |= MIPS_CACHE_NOT_PRESENT;
 
-	/*
-	 * Do we need some platform specific probing before
-	 * we configure L2?
-	 */
-	platform_early_l2_init();
-
 	if (mips_cm_revision() >= CM_REV_CM3)
 		return mips_sc_probe_cm3();
 

arch/mips/mti-malta/malta-init.c

@@ -293,7 +293,6 @@ mips_pci_controller:
 	console_config();
 #endif
 	/* Early detection of CMP support */
-	mips_cm_probe();
 	mips_cpc_probe();
 
 	if (!register_cps_smp_ops())
@@ -304,10 +303,3 @@ mips_pci_controller:
 		return;
 	register_up_smp_ops();
 }
-
-void platform_early_l2_init(void)
-{
-	/* L2 configuration lives in the CM3 */
-	if (mips_cm_revision() >= CM_REV_CM3)
-		mips_cm_probe();
-}

arch/mips/pci/pci-mt7620.c

@@ -297,12 +297,12 @@ static int mt7620_pci_probe(struct platform_device *pdev)
 		return PTR_ERR(rstpcie0);
 
 	bridge_base = devm_ioremap_resource(&pdev->dev, bridge_res);
-	if (!bridge_base)
-		return -ENOMEM;
+	if (IS_ERR(bridge_base))
+		return PTR_ERR(bridge_base);
 
 	pcie_base = devm_ioremap_resource(&pdev->dev, pcie_res);
-	if (!pcie_base)
-		return -ENOMEM;
+	if (IS_ERR(pcie_base))
+		return PTR_ERR(pcie_base);
 
 	iomem_resource.start = 0;
 	iomem_resource.end = ~0;

arch/x86/Kconfig

@@ -475,6 +475,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---

arch/x86/include/asm/processor.h

@@ -766,7 +766,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
  * Return saved PC of a blocked thread.
  * What is this good for? it will be always the scheduler or ret_from_fork.
  */
-#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
+#define thread_saved_pc(t)	READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);

arch/x86/mm/numa.c

@@ -469,7 +469,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
 	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
+	phys_addr_t start, end;
 	struct memblock_region *r;
 
 	/*

block/blk-core.c

@@ -2455,14 +2455,16 @@ struct request *blk_peek_request(struct request_queue *q)
 
 			rq = NULL;
 			break;
-		} else if (ret == BLKPREP_KILL) {
+		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
+			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
+
 			rq->cmd_flags |= REQ_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, -EIO);
+			__blk_end_request_all(rq, err);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;

crypto/algif_skcipher.c

@@ -65,18 +65,10 @@ struct skcipher_async_req {
 	struct skcipher_async_rsgl first_sgl;
 	struct list_head list;
 	struct scatterlist *tsg;
-	char iv[];
+	atomic_t *inflight;
+	struct skcipher_request req;
 };
 
-#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)))
-
-#define GET_REQ_SIZE(ctx) \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))
-
-#define GET_IV_SIZE(ctx) \
-	crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req))
-
 #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
 		      sizeof(struct scatterlist) - 1)
 
@@ -102,15 +94,12 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq)
 
 static void skcipher_async_cb(struct crypto_async_request *req, int err)
 {
-	struct sock *sk = req->data;
-	struct alg_sock *ask = alg_sk(sk);
-	struct skcipher_ctx *ctx = ask->private;
-	struct skcipher_async_req *sreq = GET_SREQ(req, ctx);
+	struct skcipher_async_req *sreq = req->data;
 	struct kiocb *iocb = sreq->iocb;
 
-	atomic_dec(&ctx->inflight);
+	atomic_dec(sreq->inflight);
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
+	kzfree(sreq);
 	iocb->ki_complete(iocb, err, err);
 }
 
@@ -306,8 +295,11 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req);
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	unsigned ivsize = crypto_skcipher_ivsize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct af_alg_control con = {};
@@ -509,37 +501,43 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	struct skcipher_async_req *sreq;
 	struct skcipher_request *req;
 	struct skcipher_async_rsgl *last_rsgl = NULL;
-	unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx);
-	unsigned int reqlen = sizeof(struct skcipher_async_req) +
-				GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx);
+	unsigned int txbufs = 0, len = 0, tx_nents;
+	unsigned int reqsize = crypto_skcipher_reqsize(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	int err = -ENOMEM;
 	bool mark = false;
+	char *iv;
 
-	lock_sock(sk);
-	req = kmalloc(reqlen, GFP_KERNEL);
-	if (unlikely(!req))
-		goto unlock;
+	sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL);
+	if (unlikely(!sreq))
+		goto out;
 
-	sreq = GET_SREQ(req, ctx);
+	req = &sreq->req;
+	iv = (char *)(req + 1) + reqsize;
 	sreq->iocb = msg->msg_iocb;
-	memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl));
 	INIT_LIST_HEAD(&sreq->list);
+	sreq->inflight = &ctx->inflight;
+
+	lock_sock(sk);
+	tx_nents = skcipher_all_sg_nents(ctx);
 	sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL);
-	if (unlikely(!sreq->tsg)) {
-		kfree(req);
+	if (unlikely(!sreq->tsg))
 		goto unlock;
-	}
 	sg_init_table(sreq->tsg, tx_nents);
-	memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx));
-	skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req));
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				      skcipher_async_cb, sk);
+	memcpy(iv, ctx->iv, ivsize);
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      skcipher_async_cb, sreq);
 
 	while (iov_iter_count(&msg->msg_iter)) {
 		struct skcipher_async_rsgl *rsgl;
@@ -615,20 +613,22 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg,
 		sg_mark_end(sreq->tsg + txbufs - 1);
 
 	skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg,
-				   len, sreq->iv);
+				   len, iv);
 	err = ctx->enc ? crypto_skcipher_encrypt(req) :
 			 crypto_skcipher_decrypt(req);
 	if (err == -EINPROGRESS) {
 		atomic_inc(&ctx->inflight);
 		err = -EIOCBQUEUED;
+		sreq = NULL;
 		goto unlock;
 	}
 free:
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
 unlock:
 	skcipher_wmem_wakeup(sk);
 	release_sock(sk);
+	kzfree(sreq);
+out:
 	return err;
 }
 
@@ -637,9 +637,12 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm(
-		&ctx->req));
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
+	unsigned bs = crypto_skcipher_blocksize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	int err = -EAGAIN;
@@ -947,7 +950,8 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 	ask->private = ctx;
 
 	skcipher_request_set_tfm(&ctx->req, skcipher);
-	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+						 CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      af_alg_complete, &ctx->completion);
 
 	sk->sk_destruct = skcipher_sock_destruct;

crypto/crypto_user.c

@@ -499,6 +499,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (link->dump == NULL)
 			return -EINVAL;
 
+		down_read(&crypto_alg_sem);
 		list_for_each_entry(alg, &crypto_alg_list, cra_list)
 			dump_alloc += CRYPTO_REPORT_MAXSIZE;
 
@@ -508,8 +509,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				.done = link->done,
 				.min_dump_alloc = dump_alloc,
 			};
-			return netlink_dump_start(crypto_nlsk, skb, nlh, &c);
+			err = netlink_dump_start(crypto_nlsk, skb, nlh, &c);
 		}
+		up_read(&crypto_alg_sem);
+
+		return err;
 	}
 
 	err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX,

drivers/ata/ahci.c

@@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */

drivers/ata/ahci.h

@@ -250,6 +250,7 @@ enum {
 	AHCI_HFLAG_MULTI_MSI		= 0,
 	AHCI_HFLAG_MULTI_MSIX		= 0,
 #endif
+	AHCI_HFLAG_WAKE_BEFORE_STOP	= (1 << 22), /* wake before DMA stop */
 
 	/* ap->flags bits */
 

drivers/ata/ahci_brcmstb.c

@@ -317,6 +317,7 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
 	hpriv->plat_data = priv;
+	hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP;
 
 	brcm_sata_alpm_init(hpriv);
 

drivers/ata/libahci.c

@@ -496,8 +496,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		}
 	}
 
-	/* fabricate port_map from cap.nr_ports */
-	if (!port_map) {
+	/* fabricate port_map from cap.nr_ports for < AHCI 1.3 */
+	if (!port_map && vers < 0x10300) {
 		port_map = (1 << ahci_nr_ports(cap)) - 1;
 		dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map);
 
@@ -593,8 +593,22 @@ EXPORT_SYMBOL_GPL(ahci_start_engine);
 int ahci_stop_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u32 tmp;
 
+	/*
+	 * On some controllers, stopping a port's DMA engine while the port
+	 * is in ALPM state (partial or slumber) results in failures on
+	 * subsequent DMA engine starts.  For those controllers, put the
+	 * port back in active state before stopping its DMA engine.
+	 */
+	if ((hpriv->flags & AHCI_HFLAG_WAKE_BEFORE_STOP) &&
+	    (ap->link.lpm_policy > ATA_LPM_MAX_POWER) &&
+	    ahci_set_lpm(&ap->link, ATA_LPM_MAX_POWER, ATA_LPM_WAKE_ONLY)) {
+		dev_err(ap->host->dev, "Failed to wake up port before engine stop\n");
+		return -EIO;
+	}
+
 	tmp = readl(port_mmio + PORT_CMD);
 
 	/* check if the HBA is idle */
@@ -689,6 +703,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	void __iomem *port_mmio = ahci_port_base(ap);
 
 	if (policy != ATA_LPM_MAX_POWER) {
+		/* wakeup flag only applies to the max power policy */
+		hints &= ~ATA_LPM_WAKE_ONLY;
+
 		/*
 		 * Disable interrupts on Phy Ready. This keeps us from
 		 * getting woken up due to spurious phy ready
@@ -704,7 +721,8 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 		u32 cmd = readl(port_mmio + PORT_CMD);
 
 		if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) {
-			cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
+			if (!(hints & ATA_LPM_WAKE_ONLY))
+				cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
 			cmd |= PORT_CMD_ICC_ACTIVE;
 
 			writel(cmd, port_mmio + PORT_CMD);
@@ -712,6 +730,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 
 			/* wait 10ms to be sure we've come out of LPM state */
 			ata_msleep(ap, 10);
+
+			if (hints & ATA_LPM_WAKE_ONLY)
+				return 0;
 		} else {
 			cmd |= PORT_CMD_ALPE;
 			if (policy == ATA_LPM_MIN_POWER)

drivers/ata/libata-core.c

@@ -4125,6 +4125,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "SAMSUNG CD-ROM SN-124", "N001",	ATA_HORKAGE_NODMA },
 	{ "Seagate STT20000A", NULL,		ATA_HORKAGE_NODMA },
 	{ " 2GB ATA Flash Disk", "ADMA428M",	ATA_HORKAGE_NODMA },
+	{ "VRFDFC22048UCHC-TE*", NULL,		ATA_HORKAGE_NODMA },
 	/* Odd clown on sil3726/4726 PMPs */
 	{ "Config  Disk",	NULL,		ATA_HORKAGE_DISABLE },
 

drivers/ata/libata-sff.c

@@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap,
 static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 {
 	struct ata_port *ap = qc->ap;
-	unsigned long flags;
 
 	if (ap->ops->error_handler) {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
-
 			/* EH might have kicked in while host lock is
 			 * released.
 			 */
@@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 				} else
 					ata_port_freeze(ap);
 			}
-
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else {
 			if (likely(!(qc->err_mask & AC_ERR_HSM)))
 				ata_qc_complete(qc);
@@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 		}
 	} else {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
 			ata_sff_irq_on(ap);
 			ata_qc_complete(qc);
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else
 			ata_qc_complete(qc);
 	}
@@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 {
 	struct ata_link *link = qc->dev->link;
 	struct ata_eh_info *ehi = &link->eh_info;
-	unsigned long flags = 0;
 	int poll_next;
 
+	lockdep_assert_held(ap->lock);
+
 	WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0);
 
 	/* Make sure ata_sff_qc_issue() does not throw things
@@ -1112,14 +1106,6 @@ fsm_start:
 			}
 		}
 
-		/* Send the CDB (atapi) or the first data block (ata pio out).
-		 * During the state transition, interrupt handler shouldn't
-		 * be invoked before the data transfer is complete and
-		 * hsm_task_state is changed. Hence, the following locking.
-		 */
-		if (in_wq)
-			spin_lock_irqsave(ap->lock, flags);
-
 		if (qc->tf.protocol == ATA_PROT_PIO) {
 			/* PIO data out protocol.
 			 * send first data block.
@@ -1135,9 +1121,6 @@ fsm_start:
 			/* send CDB */
 			atapi_send_cdb(ap, qc);
 
-		if (in_wq)
-			spin_unlock_irqrestore(ap->lock, flags);
-
 		/* if polling, ata_sff_pio_task() handles the rest.
 		 * otherwise, interrupt handler takes over from here.
 		 */
@@ -1296,7 +1279,8 @@ fsm_start:
 		break;
 	default:
 		poll_next = 0;
-		BUG();
+		WARN(true, "ata%d: SFF host state machine in invalid state %d",
+		     ap->print_id, ap->hsm_task_state);
 	}
 
 	return poll_next;
@@ -1361,12 +1345,14 @@ static void ata_sff_pio_task(struct work_struct *work)
 	u8 status;
 	int poll_next;
 
+	spin_lock_irq(ap->lock);
+
 	BUG_ON(ap->sff_pio_task_link == NULL);
 	/* qc can be NULL if timeout occurred */
 	qc = ata_qc_from_tag(ap, link->active_tag);
 	if (!qc) {
 		ap->sff_pio_task_link = NULL;
-		return;
+		goto out_unlock;
 	}
 
 fsm_start:
@@ -1381,11 +1367,14 @@ fsm_start:
 	 */
 	status = ata_sff_busy_wait(ap, ATA_BUSY, 5);
 	if (status & ATA_BUSY) {
+		spin_unlock_irq(ap->lock);
 		ata_msleep(ap, 2);
+		spin_lock_irq(ap->lock);
+
 		status = ata_sff_busy_wait(ap, ATA_BUSY, 10);
 		if (status & ATA_BUSY) {
 			ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE);
-			return;
+			goto out_unlock;
 		}
 	}
 
@@ -1402,6 +1391,8 @@ fsm_start:
 	 */
 	if (poll_next)
 		goto fsm_start;
+out_unlock:
+	spin_unlock_irq(ap->lock);
 }
 
 /**

drivers/base/component.c

@@ -206,6 +206,8 @@ static void component_match_release(struct device *master,
 		if (mc->release)
 			mc->release(master, mc->data);
 	}
+
+	kfree(match->compare);
 }
 
 static void devm_component_match_release(struct device *dev, void *res)
@@ -221,14 +223,14 @@ static int component_match_realloc(struct device *dev,
 	if (match->alloc == num)
 		return 0;
 
-	new = devm_kmalloc_array(dev, num, sizeof(*new), GFP_KERNEL);
+	new = kmalloc_array(num, sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
 	if (match->compare) {
 		memcpy(new, match->compare, sizeof(*new) *
 					    min(match->num, num));
-		devm_kfree(dev, match->compare);
+		kfree(match->compare);
 	}
 	match->compare = new;
 	match->alloc = num;
@@ -283,6 +285,24 @@ void component_match_add_release(struct device *master,
 }
 EXPORT_SYMBOL(component_match_add_release);
 
+static void free_master(struct master *master)
+{
+	struct component_match *match = master->match;
+	int i;
+
+	list_del(&master->node);
+
+	if (match) {
+		for (i = 0; i < match->num; i++) {
+			struct component *c = match->compare[i].component;
+			if (c)
+				c->master = NULL;
+		}
+	}
+
+	kfree(master);
+}
+
 int component_master_add_with_match(struct device *dev,
 	const struct component_master_ops *ops,
 	struct component_match *match)
@@ -309,11 +329,9 @@ int component_master_add_with_match(struct device *dev,
 
 	ret = try_to_bring_up_master(master, NULL);
 
-	if (ret < 0) {
-		/* Delete off the list if we weren't successful */
-		list_del(&master->node);
-		kfree(master);
-	}
+	if (ret < 0)
+		free_master(master);
+
 	mutex_unlock(&component_mutex);
 
 	return ret < 0 ? ret : 0;
@@ -324,25 +342,12 @@ void component_master_del(struct device *dev,
 	const struct component_master_ops *ops)
 {
 	struct master *master;
-	int i;
 
 	mutex_lock(&component_mutex);
 	master = __master_find(dev, ops);
 	if (master) {
-		struct component_match *match = master->match;
-
 		take_down_master(master);
-
-		list_del(&master->node);
-
-		if (match) {
-			for (i = 0; i < match->num; i++) {
-				struct component *c = match->compare[i].component;
-				if (c)
-					c->master = NULL;
-			}
-		}
-		kfree(master);
+		free_master(master);
 	}
 	mutex_unlock(&component_mutex);
 }
@@ -486,6 +491,8 @@ int component_add(struct device *dev, const struct component_ops *ops)
 
 	ret = try_to_bring_up_masters(component);
 	if (ret < 0) {
+		if (component->master)
+			remove_component(component->master, component);
 		list_del(&component->node);
 
 		kfree(component);

drivers/base/regmap/regmap-mmio.c

@@ -133,17 +133,17 @@ static int regmap_mmio_gather_write(void *context,
 	while (val_size) {
 		switch (ctx->val_bytes) {
 		case 1:
-			__raw_writeb(*(u8 *)val, ctx->regs + offset);
+			writeb(*(u8 *)val, ctx->regs + offset);
 			break;
 		case 2:
-			__raw_writew(*(u16 *)val, ctx->regs + offset);
+			writew(*(u16 *)val, ctx->regs + offset);
 			break;
 		case 4:
-			__raw_writel(*(u32 *)val, ctx->regs + offset);
+			writel(*(u32 *)val, ctx->regs + offset);
 			break;
 #ifdef CONFIG_64BIT
 		case 8:
-			__raw_writeq(*(u64 *)val, ctx->regs + offset);
+			writeq(*(u64 *)val, ctx->regs + offset);
 			break;
 #endif
 		default:
@@ -193,17 +193,17 @@ static int regmap_mmio_read(void *context,
 	while (val_size) {
 		switch (ctx->val_bytes) {
 		case 1:
-			*(u8 *)val = __raw_readb(ctx->regs + offset);
+			*(u8 *)val = readb(ctx->regs + offset);
 			break;
 		case 2:
-			*(u16 *)val = __raw_readw(ctx->regs + offset);
+			*(u16 *)val = readw(ctx->regs + offset);
 			break;
 		case 4:
-			*(u32 *)val = __raw_readl(ctx->regs + offset);
+			*(u32 *)val = readl(ctx->regs + offset);
 			break;
 #ifdef CONFIG_64BIT
 		case 8:
-			*(u64 *)val = __raw_readq(ctx->regs + offset);
+			*(u64 *)val = readq(ctx->regs + offset);
 			break;
 #endif
 		default:

drivers/crypto/atmel-sha.c

@@ -782,7 +782,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err)
 	dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU |
 			SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 
 	if (req->base.complete)
 		req->base.complete(&req->base, err);
@@ -795,7 +795,7 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd)
 {
 	int err;
 
-	err = clk_prepare_enable(dd->iclk);
+	err = clk_enable(dd->iclk);
 	if (err)
 		return err;
 
@@ -822,7 +822,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd)
 	dev_info(dd->dev,
 			"version: 0x%x\n", dd->hw_version);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 }
 
 static int atmel_sha_handle_queue(struct atmel_sha_dev *dd,
@@ -1410,6 +1410,10 @@ static int atmel_sha_probe(struct platform_device *pdev)
 		goto res_err;
 	}
 
+	err = clk_prepare(sha_dd->iclk);
+	if (err)
+		goto res_err;
+
 	atmel_sha_hw_version_init(sha_dd);
 
 	atmel_sha_get_cap(sha_dd);
@@ -1421,12 +1425,12 @@ static int atmel_sha_probe(struct platform_device *pdev)
 			if (IS_ERR(pdata)) {
 				dev_err(&pdev->dev, "platform data not available\n");
 				err = PTR_ERR(pdata);
-				goto res_err;
+				goto iclk_unprepare;
 			}
 		}
 		if (!pdata->dma_slave) {
 			err = -ENXIO;
-			goto res_err;
+			goto iclk_unprepare;
 		}
 		err = atmel_sha_dma_init(sha_dd, pdata);
 		if (err)
@@ -1457,6 +1461,8 @@ err_algs:
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 err_sha_dma:
+iclk_unprepare:
+	clk_unprepare(sha_dd->iclk);
 res_err:
 	tasklet_kill(&sha_dd->done_task);
 sha_dd_err:
@@ -1483,12 +1489,7 @@ static int atmel_sha_remove(struct platform_device *pdev)
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 
-	iounmap(sha_dd->io_base);
-
-	clk_put(sha_dd->iclk);
-
-	if (sha_dd->irq >= 0)
-		free_irq(sha_dd->irq, sha_dd);
+	clk_unprepare(sha_dd->iclk);
 
 	return 0;
 }

drivers/crypto/marvell/cesa.c

@@ -306,7 +306,7 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
 		return -ENOMEM;
 
 	dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0);
-	if (!dma->cache_pool)
+	if (!dma->padding_pool)
 		return -ENOMEM;
 
 	cesa->dma = dma;

drivers/gpio/gpio-altera.c

@@ -312,8 +312,8 @@ static int altera_gpio_probe(struct platform_device *pdev)
 		handle_simple_irq, IRQ_TYPE_NONE);
 
 	if (ret) {
-		dev_info(&pdev->dev, "could not add irqchip\n");
-		return ret;
+		dev_err(&pdev->dev, "could not add irqchip\n");
+		goto teardown;
 	}
 
 	gpiochip_set_chained_irqchip(&altera_gc->mmchip.gc,
@@ -326,6 +326,7 @@ static int altera_gpio_probe(struct platform_device *pdev)
 skip_irq:
 	return 0;
 teardown:
+	of_mm_gpiochip_remove(&altera_gc->mmchip);
 	pr_err("%s: registration failed with status %d\n",
 		node->full_name, ret);
 

drivers/gpio/gpio-davinci.c

@@ -195,7 +195,7 @@ static int davinci_gpio_of_xlate(struct gpio_chip *gc,
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	int i, base;
-	unsigned ngpio;
+	unsigned ngpio, nbank;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
 	struct davinci_gpio_regs __iomem *regs;
@@ -224,8 +224,9 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (WARN_ON(ARCH_NR_GPIOS < ngpio))
 		ngpio = ARCH_NR_GPIOS;
 
+	nbank = DIV_ROUND_UP(ngpio, 32);
 	chips = devm_kzalloc(dev,
-			     ngpio * sizeof(struct davinci_gpio_controller),
+			     nbank * sizeof(struct davinci_gpio_controller),
 			     GFP_KERNEL);
 	if (!chips)
 		return -ENOMEM;
@@ -511,7 +512,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 			return irq;
 		}
 
-		irq_domain = irq_domain_add_legacy(NULL, ngpio, irq, 0,
+		irq_domain = irq_domain_add_legacy(dev->of_node, ngpio, irq, 0,
 							&davinci_gpio_irq_ops,
 							chips);
 		if (!irq_domain) {

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -87,6 +87,8 @@ extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
 extern int amdgpu_enable_semaphores;
 extern int amdgpu_powerplay;
+extern unsigned amdgpu_pcie_gen_cap;
+extern unsigned amdgpu_pcie_lane_cap;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -132,47 +134,6 @@ extern int amdgpu_powerplay;
 #define AMDGPU_RESET_VCE			(1 << 13)
 #define AMDGPU_RESET_VCE1			(1 << 14)
 
-/* CG block flags */
-#define AMDGPU_CG_BLOCK_GFX			(1 << 0)
-#define AMDGPU_CG_BLOCK_MC			(1 << 1)
-#define AMDGPU_CG_BLOCK_SDMA			(1 << 2)
-#define AMDGPU_CG_BLOCK_UVD			(1 << 3)
-#define AMDGPU_CG_BLOCK_VCE			(1 << 4)
-#define AMDGPU_CG_BLOCK_HDP			(1 << 5)
-#define AMDGPU_CG_BLOCK_BIF			(1 << 6)
-
-/* CG flags */
-#define AMDGPU_CG_SUPPORT_GFX_MGCG		(1 << 0)
-#define AMDGPU_CG_SUPPORT_GFX_MGLS		(1 << 1)
-#define AMDGPU_CG_SUPPORT_GFX_CGCG		(1 << 2)
-#define AMDGPU_CG_SUPPORT_GFX_CGLS		(1 << 3)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS		(1 << 4)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
-#define AMDGPU_CG_SUPPORT_GFX_CP_LS		(1 << 6)
-#define AMDGPU_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
-#define AMDGPU_CG_SUPPORT_MC_LS			(1 << 8)
-#define AMDGPU_CG_SUPPORT_MC_MGCG		(1 << 9)
-#define AMDGPU_CG_SUPPORT_SDMA_LS		(1 << 10)
-#define AMDGPU_CG_SUPPORT_SDMA_MGCG		(1 << 11)
-#define AMDGPU_CG_SUPPORT_BIF_LS		(1 << 12)
-#define AMDGPU_CG_SUPPORT_UVD_MGCG		(1 << 13)
-#define AMDGPU_CG_SUPPORT_VCE_MGCG		(1 << 14)
-#define AMDGPU_CG_SUPPORT_HDP_LS		(1 << 15)
-#define AMDGPU_CG_SUPPORT_HDP_MGCG		(1 << 16)
-
-/* PG flags */
-#define AMDGPU_PG_SUPPORT_GFX_PG		(1 << 0)
-#define AMDGPU_PG_SUPPORT_GFX_SMG		(1 << 1)
-#define AMDGPU_PG_SUPPORT_GFX_DMG		(1 << 2)
-#define AMDGPU_PG_SUPPORT_UVD			(1 << 3)
-#define AMDGPU_PG_SUPPORT_VCE			(1 << 4)
-#define AMDGPU_PG_SUPPORT_CP			(1 << 5)
-#define AMDGPU_PG_SUPPORT_GDS			(1 << 6)
-#define AMDGPU_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
-#define AMDGPU_PG_SUPPORT_SDMA			(1 << 8)
-#define AMDGPU_PG_SUPPORT_ACP			(1 << 9)
-#define AMDGPU_PG_SUPPORT_SAMU			(1 << 10)
-
 /* GFX current status */
 #define AMDGPU_GFX_NORMAL_MODE			0x00000000L
 #define AMDGPU_GFX_SAFE_MODE			0x00000001L
@@ -606,8 +567,6 @@ struct amdgpu_sa_manager {
 	uint32_t		align;
 };
 
-struct amdgpu_sa_bo;
-
 /* sub-allocation buffer */
 struct amdgpu_sa_bo {
 	struct list_head		olist;
@@ -2360,6 +2319,8 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 				     uint32_t flags);
 bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end);
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm);
 uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 				 struct ttm_mem_reg *mem);

drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c

@@ -795,6 +795,12 @@ static int amdgpu_cgs_query_system_info(void *cgs_device,
 	case CGS_SYSTEM_INFO_PCIE_MLW:
 		sys_info->value = adev->pm.pcie_mlw_mask;
 		break;
+	case CGS_SYSTEM_INFO_CG_FLAGS:
+		sys_info->value = adev->cg_flags;
+		break;
+	case CGS_SYSTEM_INFO_PG_FLAGS:
+		sys_info->value = adev->pg_flags;
+		break;
 	default:
 		return -ENODEV;
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -1795,15 +1795,20 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	/* post card */
-	amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	if (!amdgpu_card_posted(adev))
+		amdgpu_atom_asic_init(adev->mode_info.atom_context);
 
 	r = amdgpu_resume(adev);
+	if (r)
+		DRM_ERROR("amdgpu_resume failed (%d).\n", r);
 
 	amdgpu_fence_driver_resume(adev);
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
+	if (resume) {
+		r = amdgpu_ib_ring_tests(adev);
+		if (r)
+			DRM_ERROR("ib ring test failed (%d).\n", r);
+	}
 
 	r = amdgpu_late_init(adev);
 	if (r)
@@ -1933,80 +1938,97 @@ retry:
 	return r;
 }
 
+#define AMDGPU_DEFAULT_PCIE_GEN_MASK 0x30007  /* gen: chipset 1/2, asic 1/2/3 */
+#define AMDGPU_DEFAULT_PCIE_MLW_MASK 0x2f0000 /* 1/2/4/8/16 lanes */
+
 void amdgpu_get_pcie_info(struct amdgpu_device *adev)
 {
 	u32 mask;
 	int ret;
 
-	if (pci_is_root_bus(adev->pdev->bus))
-		return;
+	if (amdgpu_pcie_gen_cap)
+		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
 
-	if (amdgpu_pcie_gen2 == 0)
-		return;
+	if (amdgpu_pcie_lane_cap)
+		adev->pm.pcie_mlw_mask = amdgpu_pcie_lane_cap;
 
-	if (adev->flags & AMD_IS_APU)
+	/* covers APUs as well */
+	if (pci_is_root_bus(adev->pdev->bus)) {
+		if (adev->pm.pcie_gen_mask == 0)
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		if (adev->pm.pcie_mlw_mask == 0)
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		return;
+	}
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (!ret) {
-		adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-		if (mask & DRM_PCIE_SPEED_25)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-		if (mask & DRM_PCIE_SPEED_50)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-		if (mask & DRM_PCIE_SPEED_80)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
-	}
-	ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-	if (!ret) {
-		switch (mask) {
-		case 32:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 16:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 12:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 8:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 4:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 2:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 1:
-			adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
-			break;
-		default:
-			break;
+	if (adev->pm.pcie_gen_mask == 0) {
+		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
+		if (!ret) {
+			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+
+			if (mask & DRM_PCIE_SPEED_25)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+			if (mask & DRM_PCIE_SPEED_50)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
+			if (mask & DRM_PCIE_SPEED_80)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
+		} else {
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		}
+	}
+	if (adev->pm.pcie_mlw_mask == 0) {
+		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
+		if (!ret) {
+			switch (mask) {
+			case 32:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 16:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 12:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 8:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 4:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 2:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 1:
+				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
+				break;
+			default:
+				break;
+			}
+		} else {
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -83,6 +83,8 @@ int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
 int amdgpu_enable_semaphores = 0;
 int amdgpu_powerplay = -1;
+unsigned amdgpu_pcie_gen_cap = 0;
+unsigned amdgpu_pcie_lane_cap = 0;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -170,6 +172,12 @@ MODULE_PARM_DESC(powerplay, "Powerplay component (1 = enable, 0 = disable, -1 =
 module_param_named(powerplay, amdgpu_powerplay, int, 0444);
 #endif
 
+MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
+module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
+
+MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
+module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
+
 static struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c

@@ -142,7 +142,8 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
 
 		list_for_each_entry(bo, &node->bos, mn_list) {
 
-			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+			if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start,
+							  end))
 				continue;
 
 			r = amdgpu_bo_reserve(bo, true);

drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c

@@ -354,12 +354,15 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 
 		for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i)
 			if (fences[i])
-				fences[count++] = fences[i];
+				fences[count++] = fence_get(fences[i]);
 
 		if (count) {
 			spin_unlock(&sa_manager->wq.lock);
 			t = fence_wait_any_timeout(fences, count, false,
 						   MAX_SCHEDULE_TIMEOUT);
+			for (i = 0; i < count; ++i)
+				fence_put(fences[i]);
+
 			r = (t > 0) ? 0 : t;
 			spin_lock(&sa_manager->wq.lock);
 		} else {

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

@@ -783,6 +783,25 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm)
 	return !!gtt->userptr;
 }
 
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end)
+{
+	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	unsigned long size;
+
+	if (gtt == NULL)
+		return false;
+
+	if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr)
+		return false;
+
+	size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE;
+	if (gtt->userptr > end || gtt->userptr + size <= start)
+		return false;
+
+	return true;
+}
+
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;

drivers/gpu/drm/amd/amdgpu/ci_dpm.c

@@ -31,6 +31,7 @@
 #include "ci_dpm.h"
 #include "gfx_v7_0.h"
 #include "atom.h"
+#include "amd_pcie.h"
 #include <linux/seq_file.h>
 
 #include "smu/smu_7_0_1_d.h"
@@ -5835,18 +5836,16 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	u8 frev, crev;
 	struct ci_power_info *pi;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	adev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (ret)
-		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	pi->sys_pcie_mask =
+		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
+		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = AMDGPU_PCIE_GEN1;

drivers/gpu/drm/amd/amdgpu/cik.c

@@ -1762,6 +1762,9 @@ static void cik_program_aspm(struct amdgpu_device *adev)
 	if (amdgpu_aspm == 0)
 		return;
 
+	if (pci_is_root_bus(adev->pdev->bus))
+		return;
+
 	/* XXX double check APUs */
 	if (adev->flags & AMD_IS_APU)
 		return;
@@ -2332,72 +2335,72 @@ static int cik_common_early_init(void *handle)
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x14;
 		break;
 	case CHIP_HAWAII:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = 0x28;
 		break;
 	case CHIP_KAVERI:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG |
-			  AMDGPU_PG_SUPPORT_GFX_DMG |*/
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_ACP |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG |
+			  AMD_PG_SUPPORT_GFX_DMG |*/
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_ACP |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->pdev->device == 0x1312 ||
 			adev->pdev->device == 0x1316 ||
@@ -2409,29 +2412,29 @@ static int cik_common_early_init(void *handle)
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG | */
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG | */
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->asic_type == CHIP_KABINI) {
 			if (adev->rev_id == 0)

drivers/gpu/drm/amd/amdgpu/cik_sdma.c

@@ -885,7 +885,7 @@ static void cik_enable_sdma_mgcg(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG)) {
 		WREG32(mmSDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET, 0x00000100);
 		WREG32(mmSDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET, 0x00000100);
 	} else {
@@ -906,7 +906,7 @@ static void cik_enable_sdma_mgls(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS)) {
 		orig = data = RREG32(mmSDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET);
 		data |= 0x100;
 		if (orig != data)

drivers/gpu/drm/amd/amdgpu/cz_dpm.c

@@ -445,13 +445,13 @@ static int cz_dpm_init(struct amdgpu_device *adev)
 	pi->gfx_pg_threshold = 500;
 	pi->caps_fps = true;
 	/* uvd */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
 	/* vce */
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
 	pi->caps_vce_dpm = true;
 	/* acp */
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_acp_dpm = true;
 
 	pi->caps_stable_power_state = false;

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c

@@ -4109,7 +4109,7 @@ static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
 
 	orig = data = RREG32(mmRLC_CGCG_CGLS_CTRL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) {
 		gfx_v7_0_enable_gui_idle_interrupt(adev, true);
 
 		tmp = gfx_v7_0_halt_rlc(adev);
@@ -4147,9 +4147,9 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 {
 	u32 data, orig, tmp = 0;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGCG)) {
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) {
-			if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CP_LS) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) {
+			if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
 				orig = data = RREG32(mmCP_MEM_SLP_CNTL);
 				data |= CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
 				if (orig != data)
@@ -4176,14 +4176,14 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 
 		gfx_v7_0_update_rlc(adev, tmp);
 
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS) {
 			orig = data = RREG32(mmCGTS_SM_CTRL_REG);
 			data &= ~CGTS_SM_CTRL_REG__SM_MODE_MASK;
 			data |= (0x2 << CGTS_SM_CTRL_REG__SM_MODE__SHIFT);
 			data |= CGTS_SM_CTRL_REG__SM_MODE_ENABLE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__OVERRIDE_MASK;
-			if ((adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) &&
-			    (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS_LS))
+			if ((adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) &&
+			    (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS_LS))
 				data &= ~CGTS_SM_CTRL_REG__LS_OVERRIDE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__ON_MONITOR_ADD_MASK;
 			data |= CGTS_SM_CTRL_REG__ON_MONITOR_ADD_EN_MASK;
@@ -4249,7 +4249,7 @@ static void gfx_v7_0_enable_sclk_slowdown_on_pu(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
@@ -4263,7 +4263,7 @@ static void gfx_v7_0_enable_sclk_slowdown_on_pd(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
@@ -4276,7 +4276,7 @@ static void gfx_v7_0_enable_cp_pg(struct amdgpu_device *adev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_CP))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_CP))
 		data &= ~0x8000;
 	else
 		data |= 0x8000;
@@ -4289,7 +4289,7 @@ static void gfx_v7_0_enable_gds_pg(struct amdgpu_device *adev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GDS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GDS))
 		data &= ~0x2000;
 	else
 		data |= 0x2000;
@@ -4370,7 +4370,7 @@ static void gfx_v7_0_enable_gfx_cgpg(struct amdgpu_device *adev,
 {
 	u32 data, orig;
 
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG)) {
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		orig = data = RREG32(mmRLC_PG_CNTL);
 		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
 		if (orig != data)
@@ -4442,7 +4442,7 @@ static void gfx_v7_0_enable_gfx_static_mgpg(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_SMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG))
 		data |= RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
@@ -4456,7 +4456,7 @@ static void gfx_v7_0_enable_gfx_dynamic_mgpg(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_DMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG))
 		data |= RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
@@ -4623,15 +4623,15 @@ static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev,
 
 static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_enable_sclk_slowdown_on_pu(adev, true);
 		gfx_v7_0_enable_sclk_slowdown_on_pd(adev, true);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_init_gfx_cgpg(adev);
 			gfx_v7_0_enable_cp_pg(adev, true);
 			gfx_v7_0_enable_gds_pg(adev, true);
@@ -4643,14 +4643,14 @@ static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 
 static void gfx_v7_0_fini_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, false);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, false);
 			gfx_v7_0_enable_gds_pg(adev, false);
 		}
@@ -5527,14 +5527,14 @@ static int gfx_v7_0_set_powergating_state(void *handle,
 	if (state == AMD_PG_STATE_GATE)
 		gate = true;
 
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, gate);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, gate);
 			gfx_v7_0_enable_gds_pg(adev, gate);
 		}

drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c

@@ -792,7 +792,7 @@ static void gmc_v7_0_enable_mc_ls(struct amdgpu_device *adev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_LS))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
 			data |= mc_cg_ls_en[i];
 		else
 			data &= ~mc_cg_ls_en[i];
@@ -809,7 +809,7 @@ static void gmc_v7_0_enable_mc_mgcg(struct amdgpu_device *adev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_MGCG))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
 			data |= mc_cg_en[i];
 		else
 			data &= ~mc_cg_en[i];
@@ -825,7 +825,7 @@ static void gmc_v7_0_enable_bif_mgls(struct amdgpu_device *adev,
 
 	orig = data = RREG32_PCIE(ixPCIE_CNTL2);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_BIF_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
 		data = REG_SET_FIELD(data, PCIE_CNTL2, SLV_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, MST_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, REPLAY_MEM_LS_EN, 1);
@@ -848,7 +848,7 @@ static void gmc_v7_0_enable_hdp_mgcg(struct amdgpu_device *adev,
 
 	orig = data = RREG32(mmHDP_HOST_PATH_CNTL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_MGCG))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 0);
 	else
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 1);
@@ -864,7 +864,7 @@ static void gmc_v7_0_enable_hdp_ls(struct amdgpu_device *adev,
 
 	orig = data = RREG32(mmHDP_MEM_POWER_LS);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_LS))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 1);
 	else
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 0);

drivers/gpu/drm/amd/amdgpu/kv_dpm.c

@@ -2859,11 +2859,11 @@ static int kv_dpm_init(struct amdgpu_device *adev)
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
-	pi->caps_samu_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_SAMU) ? true : false;
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_samu_pg = (adev->pg_flags & AMD_PG_SUPPORT_SAMU) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_stable_p_state = false;
 
 	ret = kv_parse_sys_info_table(adev);

drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c

@@ -611,7 +611,7 @@ static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) {
 		data = RREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL);
 		data = 0xfff;
 		WREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL, data);
@@ -830,6 +830,9 @@ static int uvd_v4_2_set_clockgating_state(void *handle,
 	bool gate = false;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	if (state == AMD_CG_STATE_GATE)
 		gate = true;
 
@@ -848,7 +851,10 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 	 * revisit this when there is a cleaner line between
 	 * the smc and the hw blocks
 	 */
-	 struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
 
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v4_2_stop(adev);

drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c

@@ -774,6 +774,11 @@ static int uvd_v5_0_process_interrupt(struct amdgpu_device *adev,
 static int uvd_v5_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	return 0;
 }
 
@@ -789,6 +794,9 @@ static int uvd_v5_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v5_0_stop(adev);
 		return 0;

drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c

@@ -532,7 +532,7 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	uvd_v6_0_mc_resume(adev);
 
 	/* Set dynamic clock gating in S/W control mode */
-	if (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG) {
+	if (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG) {
 		if (adev->flags & AMD_IS_APU)
 			cz_set_uvd_clock_gating_branches(adev, false);
 		else
@@ -1000,7 +1000,7 @@ static int uvd_v6_0_set_clockgating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
 		return 0;
 
 	if (enable) {
@@ -1030,6 +1030,9 @@ static int uvd_v6_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v6_0_stop(adev);
 		return 0;

drivers/gpu/drm/amd/amdgpu/vce_v2_0.c

@@ -373,7 +373,7 @@ static void vce_v2_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 {
 	bool sw_cg = false;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) {
 		if (sw_cg)
 			vce_v2_0_set_sw_cg(adev, true);
 		else
@@ -608,6 +608,9 @@ static int vce_v2_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v2_0_stop()? */
 		return 0;

drivers/gpu/drm/amd/amdgpu/vce_v3_0.c

@@ -277,7 +277,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		WREG32_P(mmVCE_STATUS, 0, ~1);
 
 		/* Set Clock-Gating off */
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)
+		if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 
 		if (r) {
@@ -676,7 +676,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 	int i;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG))
 		return 0;
 
 	mutex_lock(&adev->grbm_idx_mutex);
@@ -728,6 +728,9 @@ static int vce_v3_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v3_0_stop()? */
 		return 0;

drivers/gpu/drm/amd/amdgpu/vi.c

@@ -1457,8 +1457,7 @@ static int vi_common_early_init(void *handle)
 	case CHIP_STONEY:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		/* Disable UVD pg */
-		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
+		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
 	default:

drivers/gpu/drm/amd/include/amd_shared.h

@@ -85,6 +85,38 @@ enum amd_powergating_state {
 	AMD_PG_STATE_UNGATE,
 };
 
+/* CG flags */
+#define AMD_CG_SUPPORT_GFX_MGCG			(1 << 0)
+#define AMD_CG_SUPPORT_GFX_MGLS			(1 << 1)
+#define AMD_CG_SUPPORT_GFX_CGCG			(1 << 2)
+#define AMD_CG_SUPPORT_GFX_CGLS			(1 << 3)
+#define AMD_CG_SUPPORT_GFX_CGTS			(1 << 4)
+#define AMD_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
+#define AMD_CG_SUPPORT_GFX_CP_LS		(1 << 6)
+#define AMD_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
+#define AMD_CG_SUPPORT_MC_LS			(1 << 8)
+#define AMD_CG_SUPPORT_MC_MGCG			(1 << 9)
+#define AMD_CG_SUPPORT_SDMA_LS			(1 << 10)
+#define AMD_CG_SUPPORT_SDMA_MGCG		(1 << 11)
+#define AMD_CG_SUPPORT_BIF_LS			(1 << 12)
+#define AMD_CG_SUPPORT_UVD_MGCG			(1 << 13)
+#define AMD_CG_SUPPORT_VCE_MGCG			(1 << 14)
+#define AMD_CG_SUPPORT_HDP_LS			(1 << 15)
+#define AMD_CG_SUPPORT_HDP_MGCG			(1 << 16)
+
+/* PG flags */
+#define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
+#define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
+#define AMD_PG_SUPPORT_GFX_DMG			(1 << 2)
+#define AMD_PG_SUPPORT_UVD			(1 << 3)
+#define AMD_PG_SUPPORT_VCE			(1 << 4)
+#define AMD_PG_SUPPORT_CP			(1 << 5)
+#define AMD_PG_SUPPORT_GDS			(1 << 6)
+#define AMD_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
+#define AMD_PG_SUPPORT_SDMA			(1 << 8)
+#define AMD_PG_SUPPORT_ACP			(1 << 9)
+#define AMD_PG_SUPPORT_SAMU			(1 << 10)
+
 enum amd_pm_state_type {
 	/* not used for dpm */
 	POWER_STATE_TYPE_DEFAULT,

drivers/gpu/drm/amd/include/cgs_common.h

@@ -109,6 +109,8 @@ enum cgs_system_info_id {
 	CGS_SYSTEM_INFO_ADAPTER_BDF_ID = 1,
 	CGS_SYSTEM_INFO_PCIE_GEN_INFO,
 	CGS_SYSTEM_INFO_PCIE_MLW,
+	CGS_SYSTEM_INFO_CG_FLAGS,
+	CGS_SYSTEM_INFO_PG_FLAGS,
 	CGS_SYSTEM_INFO_ID_MAXIMUM,
 };
 

drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c

@@ -174,6 +174,8 @@ static int cz_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 {
 	struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend);
 	uint32_t i;
+	struct cgs_system_info sys_info = {0};
+	int result;
 
 	cz_hwmgr->gfx_ramp_step = 256*25/100;
 
@@ -247,6 +249,22 @@ static int cz_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 				   PHM_PlatformCaps_DisableVoltageIsland);
 
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c

@@ -4451,6 +4451,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	pp_atomctrl_gpio_pin_assignment gpio_pin_assignment;
 	struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable);
 	phw_tonga_ulv_parm *ulv;
+	struct cgs_system_info sys_info = {0};
 
 	PP_ASSERT_WITH_CODE((NULL != hwmgr),
 		"Invalid Parameter!", return -1;);
@@ -4615,9 +4616,23 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	data->vddc_phase_shed_control = 0;
 
-	if (0 == result) {
-		struct cgs_system_info sys_info = {0};
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
 
+	if (0 == result) {
 		data->is_tlu_enabled = 0;
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 			TONGA_MAX_HARDWARE_POWERLEVELS;

drivers/gpu/drm/radeon/radeon_sa.c

@@ -349,8 +349,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 			/* see if we can skip over some allocations */
 		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
 
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_ref(fences[i]);
+
 		spin_unlock(&sa_manager->wq.lock);
 		r = radeon_fence_wait_any(rdev, fences, false);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_unref(&fences[i]);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
 		if (r == -ENOENT) {

drivers/infiniband/core/sysfs.c

@@ -336,7 +336,6 @@ static ssize_t _show_port_gid_attr(struct ib_port *p,
 	union ib_gid gid;
 	struct ib_gid_attr gid_attr = {};
 	ssize_t ret;
-	va_list args;
 
 	ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid,
 			   &gid_attr);
@@ -348,7 +347,6 @@ static ssize_t _show_port_gid_attr(struct ib_port *p,
 err:
 	if (gid_attr.ndev)
 		dev_put(gid_attr.ndev);
-	va_end(args);
 	return ret;
 }
 
@@ -722,12 +720,11 @@ static struct attribute_group *get_counter_table(struct ib_device *dev,
 
 	if (get_perf_mad(dev, port_num, IB_PMA_CLASS_PORT_INFO,
 				&cpi, 40, sizeof(cpi)) >= 0) {
-
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH)
 			/* We have extended counters */
 			return &pma_group_ext;
 
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
 			/* But not the IETF ones */
 			return &pma_group_noietf;
 	}