Merge branch 'x86/urgent' into x86/cache, to pick up dependent fix

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/devicetree/bindings/input/gpio-keys.txt

@@ -1,4 +1,4 @@
-Device-Tree bindings for input/gpio_keys.c keyboard driver
+Device-Tree bindings for input/keyboard/gpio_keys.c keyboard driver
 
 Required properties:
 	- compatible = "gpio-keys";

Documentation/driver-api/fpga/fpga-mgr.rst

@@ -184,6 +184,11 @@ API for implementing a new FPGA Manager driver
 API for programming an FPGA
 ---------------------------
 
+FPGA Manager flags
+
+.. kernel-doc:: include/linux/fpga/fpga-mgr.h
+   :doc: FPGA Manager flags
+
 .. kernel-doc:: include/linux/fpga/fpga-mgr.h
    :functions: fpga_image_info
 

Documentation/fb/uvesafb.txt

@@ -15,7 +15,8 @@ than x86.  Check the v86d documentation for a list of currently supported
 arches.
 
 v86d source code can be downloaded from the following website:
-  http://dev.gentoo.org/~spock/projects/uvesafb
+
+  https://github.com/mjanusz/v86d
 
 Please refer to the v86d documentation for detailed configuration and
 installation instructions.
@@ -177,7 +178,7 @@ from the Video BIOS if you set pixclock to 0 in fb_var_screeninfo.
 
 --
  Michal Januszewski <spock@gentoo.org>
- Last updated: 2009-03-30
+ Last updated: 2017-10-10
 
  Documentation of the uvesafb options is loosely based on vesafb.txt.
 

Documentation/networking/ip-sysctl.txt

@@ -425,7 +425,7 @@ tcp_mtu_probing - INTEGER
 	  1 - Disabled by default, enabled when an ICMP black hole detected
 	  2 - Always enabled, use initial MSS of tcp_base_mss.
 
-tcp_probe_interval - INTEGER
+tcp_probe_interval - UNSIGNED INTEGER
 	Controls how often to start TCP Packetization-Layer Path MTU
 	Discovery reprobe. The default is reprobing every 10 minutes as
 	per RFC4821.

MAINTAINERS

@@ -324,7 +324,6 @@ F:	Documentation/ABI/testing/sysfs-bus-acpi
 F:	Documentation/ABI/testing/configfs-acpi
 F:	drivers/pci/*acpi*
 F:	drivers/pci/*/*acpi*
-F:	drivers/pci/*/*/*acpi*
 F:	tools/power/acpi/
 
 ACPI APEI
@@ -1251,7 +1250,7 @@ N:	meson
 
 ARM/Annapurna Labs ALPINE ARCHITECTURE
 M:	Tsahee Zidenberg <tsahee@annapurnalabs.com>
-M:	Antoine Tenart <antoine.tenart@free-electrons.com>
+M:	Antoine Tenart <antoine.tenart@bootlin.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-alpine/
@@ -2956,7 +2955,6 @@ F:	include/linux/bcm963xx_tag.h
 
 BROADCOM BNX2 GIGABIT ETHERNET DRIVER
 M:	Rasesh Mody <rasesh.mody@cavium.com>
-M:	Harish Patil <harish.patil@cavium.com>
 M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -2977,6 +2975,7 @@ F:	drivers/scsi/bnx2i/
 
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
 M:	Ariel Elior <ariel.elior@cavium.com>
+M:	Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
 M:	everest-linux-l2@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -5470,7 +5469,8 @@ S:	Odd Fixes
 F:	drivers/net/ethernet/agere/
 
 ETHERNET BRIDGE
-M:	Stephen Hemminger <stephen@networkplumber.org>
+M:	Roopa Prabhu <roopa@cumulusnetworks.com>
+M:	Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
 L:	bridge@lists.linux-foundation.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net:Bridge
@@ -8598,7 +8598,6 @@ F:	include/linux/spinlock*.h
 F:	arch/*/include/asm/spinlock*.h
 F:	include/linux/rwlock*.h
 F:	include/linux/mutex*.h
-F:	arch/*/include/asm/mutex*.h
 F:	include/linux/rwsem*.h
 F:	arch/*/include/asm/rwsem.h
 F:	include/linux/seqlock.h
@@ -9716,13 +9715,6 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/mn88473*
 
-PCI DRIVER FOR MOBIVEIL PCIE IP
-M:	Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
-L:	linux-pci@vger.kernel.org
-S:	Supported
-F:	Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
-F:	drivers/pci/controller/pcie-mobiveil.c
-
 MODULE SUPPORT
 M:	Jessica Yu <jeyu@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux.git modules-next
@@ -10949,7 +10941,7 @@ M:	Willy Tarreau <willy@haproxy.com>
 M:	Ksenija Stanojevic <ksenija.stanojevic@gmail.com>
 S:	Odd Fixes
 F:	Documentation/auxdisplay/lcd-panel-cgram.txt
-F:	drivers/misc/panel.c
+F:	drivers/auxdisplay/panel.c
 
 PARALLEL PORT SUBSYSTEM
 M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
@@ -11137,6 +11129,13 @@ F:	include/uapi/linux/switchtec_ioctl.h
 F:	include/linux/switchtec.h
 F:	drivers/ntb/hw/mscc/
 
+PCI DRIVER FOR MOBIVEIL PCIE IP
+M:	Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
+L:	linux-pci@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
+F:	drivers/pci/controller/pcie-mobiveil.c
+
 PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support)
 M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
 M:	Jason Cooper <jason@lakedaemon.net>
@@ -11203,8 +11202,14 @@ F:	tools/pci/
 
 PCI ENHANCED ERROR HANDLING (EEH) FOR POWERPC
 M:	Russell Currey <ruscur@russell.cc>
+M:	Sam Bobroff <sbobroff@linux.ibm.com>
+M:	Oliver O'Halloran <oohall@gmail.com>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
+F:	Documentation/PCI/pci-error-recovery.txt
+F:	drivers/pci/pcie/aer.c
+F:	drivers/pci/pcie/dpc.c
+F:	drivers/pci/pcie/err.c
 F:	Documentation/powerpc/eeh-pci-error-recovery.txt
 F:	arch/powerpc/kernel/eeh*.c
 F:	arch/powerpc/platforms/*/eeh*.c
@@ -11973,7 +11978,7 @@ F:	Documentation/scsi/LICENSE.qla4xxx
 F:	drivers/scsi/qla4xxx/
 
 QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M:	Harish Patil <harish.patil@cavium.com>
+M:	Shahed Shaikh <Shahed.Shaikh@cavium.com>
 M:	Manish Chopra <manish.chopra@cavium.com>
 M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
@@ -11981,7 +11986,6 @@ S:	Supported
 F:	drivers/net/ethernet/qlogic/qlcnic/
 
 QLOGIC QLGE 10Gb ETHERNET DRIVER
-M:	Harish Patil <harish.patil@cavium.com>
 M:	Manish Chopra <manish.chopra@cavium.com>
 M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
@@ -15389,7 +15393,7 @@ S:	Maintained
 UVESAFB DRIVER
 M:	Michal Januszewski <spock@gentoo.org>
 L:	linux-fbdev@vger.kernel.org
-W:	http://dev.gentoo.org/~spock/projects/uvesafb/
+W:	https://github.com/mjanusz/v86d
 S:	Maintained
 F:	Documentation/fb/uvesafb.txt
 F:	drivers/video/fbdev/uvesafb.*

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc7
 NAME = Merciless Moray
 
 # *DOCUMENTATION*

arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts

@@ -11,6 +11,7 @@
 #include "sama5d2-pinfunc.h"
 #include <dt-bindings/mfd/atmel-flexcom.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/at91.h>
 
 / {
 	model = "Atmel SAMA5D2 PTC EK";
@@ -299,6 +300,7 @@
 							 <PIN_PA30__NWE_NANDWE>,
 							 <PIN_PB2__NRD_NANDOE>;
 						bias-pull-up;
+						atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>;
 					};
 
 					ale_cle_rdy_cs {

arch/arm/boot/dts/bcm63138.dtsi

@@ -106,21 +106,23 @@
 		global_timer: timer@1e200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x1e200 0x20>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&axi_clk>;
 		};
 
 		local_timer: local-timer@1e600 {
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x1e600 0x20>;
-			interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&axi_clk>;
 		};
 
 		twd_watchdog: watchdog@1e620 {
 			compatible = "arm,cortex-a9-twd-wdt";
 			reg = <0x1e620 0x20>;
-			interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
+						  IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
 		armpll: armpll {
@@ -158,7 +160,7 @@
 		serial0: serial@600 {
 			compatible = "brcm,bcm6345-uart";
 			reg = <0x600 0x1b>;
-			interrupts = <GIC_SPI 32 0>;
+			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&periph_clk>;
 			clock-names = "periph";
 			status = "disabled";
@@ -167,7 +169,7 @@
 		serial1: serial@620 {
 			compatible = "brcm,bcm6345-uart";
 			reg = <0x620 0x1b>;
-			interrupts = <GIC_SPI 33 0>;
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&periph_clk>;
 			clock-names = "periph";
 			status = "disabled";
@@ -180,7 +182,7 @@
 			reg = <0x2000 0x600>, <0xf0 0x10>;
 			reg-names = "nand", "nand-int-base";
 			status = "disabled";
-			interrupts = <GIC_SPI 38 0>;
+			interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "nand";
 		};
 

arch/arm/boot/dts/stm32mp157c.dtsi

@@ -1078,8 +1078,8 @@
 			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&rcc SPI6_K>;
 			resets = <&rcc SPI6_R>;
-			dmas = <&mdma1 34 0x0 0x40008 0x0 0x0 0>,
+			dmas = <&mdma1 34 0x0 0x40008 0x0 0x0>,
-			       <&mdma1 35 0x0 0x40002 0x0 0x0 0>;
+			       <&mdma1 35 0x0 0x40002 0x0 0x0>;
 			dma-names = "rx", "tx";
 			status = "disabled";
 		};

arch/arm/boot/dts/sun8i-r40.dtsi

@@ -800,8 +800,7 @@
 		};
 
 		hdmi_phy: hdmi-phy@1ef0000 {
-			compatible = "allwinner,sun8i-r40-hdmi-phy",
+			compatible = "allwinner,sun8i-r40-hdmi-phy";
-				     "allwinner,sun50i-a64-hdmi-phy";
 			reg = <0x01ef0000 0x10000>;
 			clocks = <&ccu CLK_BUS_HDMI1>, <&ccu CLK_HDMI_SLOW>,
 				 <&ccu 7>, <&ccu 16>;

arch/arm/mm/ioremap.c

@@ -473,7 +473,7 @@ void pci_ioremap_set_mem_type(int mem_type)
 
 int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 {
-	BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT);
+	BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT);
 
 	return ioremap_page_range(PCI_IO_VIRT_BASE + offset,
 				  PCI_IO_VIRT_BASE + offset + SZ_64K,

arch/arm/tools/syscall.tbl

@@ -413,3 +413,4 @@
 396	common	pkey_free		sys_pkey_free
 397	common	statx			sys_statx
 398	common	rseq			sys_rseq
+399	common	io_pgetevents		sys_io_pgetevents

arch/arm64/kvm/guest.c

@@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id)
 	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
 }
 
+static int validate_core_offset(const struct kvm_one_reg *reg)
+{
+	u64 off = core_reg_offset_from_id(reg->id);
+	int size;
+
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		size = sizeof(__u64);
+		break;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		size = sizeof(__uint128_t);
+		break;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		size = sizeof(__u32);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (KVM_REG_SIZE(reg->id) == size &&
+	    IS_ALIGNED(off, size / sizeof(__u32)))
+		return 0;
+
+	return -EINVAL;
+}
+
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	/*
@@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
+	if (validate_core_offset(reg))
+		return -EINVAL;
+
 	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
@@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
+	if (validate_core_offset(reg))
+		return -EINVAL;
+
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
 		return -EINVAL;
 
@@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
-		u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
+		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
+			if (!system_supports_32bit_el0())
+				return -EINVAL;
+			break;
 		case PSR_AA32_MODE_FIQ:
 		case PSR_AA32_MODE_IRQ:
 		case PSR_AA32_MODE_SVC:
 		case PSR_AA32_MODE_ABT:
 		case PSR_AA32_MODE_UND:
+			if (!vcpu_el1_is_32bit(vcpu))
+				return -EINVAL;
+			break;
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:
+			if (vcpu_el1_is_32bit(vcpu))
+				return -EINVAL;
 			break;
 		default:
 			err = -EINVAL;

arch/arm64/mm/hugetlbpage.c

@@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 
 		/*
 		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty bit for any page in the set, so check
+		 * the dirty or accessed bit for any page in the set,
-		 * them all.  All hugetlb entries are already young.
+		 * so check them all.
 		 */
 		if (pte_dirty(pte))
 			orig_pte = pte_mkdirty(orig_pte);
+
+		if (pte_young(pte))
+			orig_pte = pte_mkyoung(orig_pte);
 	}
 
 	if (valid) {
@@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+	int i;
+
+	if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
+		return 1;
+
+	for (i = 0; i < ncontig; i++) {
+		pte_t orig_pte = huge_ptep_get(ptep + i);
+
+		if (pte_dirty(pte) != pte_dirty(orig_pte))
+			return 1;
+
+		if (pte_young(pte) != pte_young(orig_pte))
+			return 1;
+	}
+
+	return 0;
+}
+
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       unsigned long addr, pte_t *ptep,
 			       pte_t pte, int dirty)
 {
-	int ncontig, i, changed = 0;
+	int ncontig, i;
 	size_t pgsize = 0;
 	unsigned long pfn = pte_pfn(pte), dpfn;
 	pgprot_t hugeprot;
@@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
 
-	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	if (!__cont_access_flags_changed(ptep, pte, ncontig))
-	if (!pte_same(orig_pte, pte))
+		return 0;
-		changed = 1;
 
-	/* Make sure we don't lose the dirty state */
+	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+
+	/* Make sure we don't lose the dirty or young state */
 	if (pte_dirty(orig_pte))
 		pte = pte_mkdirty(pte);
 
+	if (pte_young(orig_pte))
+		pte = pte_mkyoung(pte);
+
 	hugeprot = pte_pgprot(pte);
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
 		set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
 
-	return changed;
+	return 1;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,

arch/powerpc/include/asm/setup.h

@@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex);
 
 extern unsigned int rtas_data;
 extern unsigned long long memory_limit;
+extern bool init_mem_is_free;
 extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 

arch/powerpc/kernel/exceptions-64s.S

@@ -1314,9 +1314,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
 
 #ifdef CONFIG_PPC_DENORMALISATION
 	mfspr	r10,SPRN_HSRR1
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
 	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
-	addi	r11,r11,-4		/* HSRR0 is next instruction */
 	bne+	denorm_assist
 #endif
 
@@ -1382,6 +1380,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
  */
 	XVCPSGNDP32(32)
 denorm_done:
+	mfspr	r11,SPRN_HSRR0
+	subi	r11,r11,4
 	mtspr	SPRN_HSRR0,r11
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)

arch/powerpc/kernel/process.c

@@ -1306,6 +1306,16 @@ void show_user_instructions(struct pt_regs *regs)
 
 	pc = regs->nip - (instructions_to_print * 3 / 4 * sizeof(int));
 
+	/*
+	 * Make sure the NIP points at userspace, not kernel text/data or
+	 * elsewhere.
+	 */
+	if (!__access_ok(pc, instructions_to_print * sizeof(int), USER_DS)) {
+		pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
+			current->comm, current->pid);
+		return;
+	}
+
 	pr_info("%s[%d]: code: ", current->comm, current->pid);
 
 	for (i = 0; i < instructions_to_print; i++) {

arch/powerpc/kernel/tm.S

@@ -176,13 +176,27 @@ _GLOBAL(tm_reclaim)
 	std	r1, PACATMSCRATCH(r13)
 	ld	r1, PACAR1(r13)
 
-	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
 
+	/*
+	 * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is
+	 * clobbered by an exception once we turn on MSR_RI below.
+	 */
+	ld	r11, PACATMSCRATCH(r13)
+	std	r11, GPR1(r1)
+
+	/*
+	 * Store r13 away so we can free up the scratch SPR for the SLB fault
+	 * handler (needed once we start accessing the thread_struct).
+	 */
+	GET_SCRATCH0(r11)
+	std	r11, GPR13(r1)
+
 	/* Reset MSR RI so we can take SLB faults again */
 	li	r11, MSR_RI
 	mtmsrd	r11, 1
 
+	/* Store the PPR in r11 and reset to decent value */
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -207,11 +221,11 @@ _GLOBAL(tm_reclaim)
 	SAVE_GPR(8, r7)				/* user r8 */
 	SAVE_GPR(9, r7)				/* user r9 */
 	SAVE_GPR(10, r7)			/* user r10 */
-	ld	r3, PACATMSCRATCH(r13)		/* user r1 */
+	ld	r3, GPR1(r1)			/* user r1 */
 	ld	r4, GPR7(r1)			/* user r7 */
 	ld	r5, GPR11(r1)			/* user r11 */
 	ld	r6, GPR12(r1)			/* user r12 */
-	GET_SCRATCH0(8)				/* user r13 */
+	ld	r8, GPR13(r1)			/* user r13 */
 	std	r3, GPR1(r7)
 	std	r4, GPR7(r7)
 	std	r5, GPR11(r7)

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -646,6 +646,16 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	local_irq_disable();
 	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	/*
+	 * If the PTE disappeared temporarily due to a THP
+	 * collapse, just return and let the guest try again.
+	 */
+	if (!ptep) {
+		local_irq_enable();
+		if (page)
+			put_page(page);
+		return RESUME_GUEST;
+	}
 	pte = *ptep;
 	local_irq_enable();
 

arch/powerpc/lib/checksum_64.S

@@ -443,6 +443,9 @@ _GLOBAL(csum_ipv6_magic)
 	addc	r0, r8, r9
 	ld	r10, 0(r4)
 	ld	r11, 8(r4)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	rotldi	r5, r5, 8
+#endif
 	adde	r0, r0, r10
 	add	r5, r5, r7
 	adde	r0, r0, r11

arch/powerpc/lib/code-patching.c

@@ -142,7 +142,7 @@ static inline int unmap_patch_area(unsigned long addr)
 	return 0;
 }
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 	unsigned int *patch_addr = NULL;
@@ -182,12 +182,22 @@ out:
 }
 #else /* !CONFIG_STRICT_KERNEL_RWX */
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	return raw_patch_instruction(addr, instr);
 }
 
 #endif /* CONFIG_STRICT_KERNEL_RWX */
+
+int patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", addr);
+		return 0;
+	}
+	return do_patch_instruction(addr, instr);
+}
 NOKPROBE_SYMBOL(patch_instruction);
 
 int patch_branch(unsigned int *addr, unsigned long target, int flags)

arch/powerpc/mm/mem.c

@@ -63,6 +63,7 @@
 #endif
 
 unsigned long long memory_limit;
+bool init_mem_is_free;
 
 #ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
@@ -396,6 +397,7 @@ void free_initmem(void)
 {
 	ppc_md.progress = ppc_printk_progress;
 	mark_initmem_nx();
+	init_mem_is_free = true;
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 

arch/powerpc/mm/numa.c

@@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu)
 	int new_nid;
 
 	/* Use associativity from first thread for all siblings */
-	vphn_get_associativity(cpu, associativity);
+	if (vphn_get_associativity(cpu, associativity))
+		return cpu_to_node(cpu);
+
 	new_nid = associativity_to_nid(associativity);
 	if (new_nid < 0 || !node_possible(new_nid))
 		new_nid = first_online_node;
@@ -1215,9 +1217,10 @@ int find_and_online_cpu_nid(int cpu)
 		 * Need to ensure that NODE_DATA is initialized for a node from
 		 * available memory (see memblock_alloc_try_nid). If unable to
 		 * init the node, then default to nearest node that has memory
-		 * installed.
+		 * installed. Skip onlining a node if the subsystems are not
+		 * yet initialized.
 		 */
-		if (try_online_node(new_nid))
+		if (!topology_inited || try_online_node(new_nid))
 			new_nid = first_online_node;
 #else
 		/*
@@ -1452,7 +1455,8 @@ static struct timer_list topology_timer;
 
 static void reset_topology_timer(void)
 {
-	mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
+	if (vphn_enabled)
+		mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
 }
 
 #ifdef CONFIG_SMP

arch/powerpc/mm/pkeys.c

@@ -45,7 +45,7 @@ static void scan_pkey_feature(void)
 	 * Since any pkey can be used for data or execute, we will just treat
 	 * all keys as equal and track them as one entity.
 	 */
-	pkeys_total = be32_to_cpu(vals[0]);
+	pkeys_total = vals[0];
 	pkeys_devtree_defined = true;
 }
 

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

@@ -276,7 +276,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 	level_shift = entries_shift + 3;
 	level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT);
 
-	if ((level_shift - 3) * levels + page_shift >= 60)
+	if ((level_shift - 3) * levels + page_shift >= 55)
 		return -EINVAL;
 
 	/* Allocate TCE table */

arch/riscv/include/asm/asm-prototypes.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PROTOTYPES_H
+
+#include <linux/ftrace.h>
+#include <asm-generic/asm-prototypes.h>
+
+#endif /* _ASM_RISCV_PROTOTYPES_H */

arch/riscv/kernel/setup.c

@@ -186,7 +186,7 @@ static void __init setup_bootmem(void)
 	BUG_ON(mem_size == 0);
 
 	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = pfn_base + PFN_DOWN(mem_size);
+	max_low_pfn = memblock_end_of_DRAM();
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();

arch/x86/boot/compressed/mem_encrypt.S

@@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit)
 	push	%ebx
 	push	%ecx
 	push	%edx
-	push	%edi
-
-	/*
-	 * RIP-relative addressing is needed to access the encryption bit
-	 * variable. Since we are running in 32-bit mode we need this call/pop
-	 * sequence to get the proper relative addressing.
-	 */
-	call	1f
-1:	popl	%edi
-	subl	$1b, %edi
-
-	movl	enc_bit(%edi), %eax
-	cmpl	$0, %eax
-	jge	.Lsev_exit
 
 	/* Check if running under a hypervisor */
 	movl	$1, %eax
@@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit)
 
 	movl	%ebx, %eax
 	andl	$0x3f, %eax		/* Return the encryption bit location */
-	movl	%eax, enc_bit(%edi)
 	jmp	.Lsev_exit
 
 .Lno_sev:
 	xor	%eax, %eax
-	movl	%eax, enc_bit(%edi)
 
 .Lsev_exit:
-	pop	%edi
 	pop	%edx
 	pop	%ecx
 	pop	%ebx
@@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask)
 ENDPROC(set_sev_encryption_mask)
 
 	.data
-enc_bit:
-	.int	0xffffffff
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	.balign	8

arch/x86/entry/vdso/Makefile

@@ -68,7 +68,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
-       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS)
+       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+  CFL += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
@@ -138,7 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+  KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
 $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 
 $(obj)/vdso32.so.dbg: FORCE \

arch/x86/entry/vdso/vclock_gettime.c

@@ -43,8 +43,9 @@ extern u8 hvclock_page
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;
-	asm("syscall" : "=a" (ret) :
+	asm ("syscall" : "=a" (ret), "=m" (*ts) :
-	    "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+	     "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
+	     "memory", "rcx", "r11");
 	return ret;
 }
 
@@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
+	asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) :
-	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	     "0" (__NR_gettimeofday), "D" (tv), "S" (tz) :
+	     "memory", "rcx", "r11");
 	return ret;
 }
 
@@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;
 
-	asm(
+	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[clock], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
-		: "=a" (ret)
+		: "=a" (ret), "=m" (*ts)
-		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+		: "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
 		: "memory", "edx");
 	return ret;
 }
@@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 
-	asm(
+	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[tv], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
-		: "=a" (ret)
+		: "=a" (ret), "=m" (*tv), "=m" (*tz)
-		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+		: "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
 		: "memory", "edx");
 	return ret;
 }

arch/x86/events/amd/uncore.c

@@ -36,6 +36,7 @@
 
 static int num_counters_llc;
 static int num_counters_nb;
+static bool l3_mask;
 
 static HLIST_HEAD(uncore_unused_list);
 
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events in
+	 * Family 17h. For other events, the two fields do not affect the count.
+	 */
+	if (l3_mask)
+		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l3";
 		format_attr_event_df.show = &event_show_df;
 		format_attr_event_l3.show = &event_show_l3;
+		l3_mask			  = true;
 	} else {
 		num_counters_nb		  = NUM_COUNTERS_NB;
 		num_counters_llc	  = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l2";
 		format_attr_event_df	  = format_attr_event;
 		format_attr_event_l3	  = format_attr_event;
+		l3_mask			  = false;
 	}
 
 	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;

arch/x86/events/intel/uncore_snbep.c

@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
 
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
 		.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
 	},
 	{ /* M3UPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
 	},
 	{ /* M3UPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
 	},
 	{ /* M3UPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
-		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+		.driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
 	},
 	{ /* end: all zeroes */ }
 };

arch/x86/include/asm/perf_event.h

@@ -46,6 +46,14 @@
 #define INTEL_ARCH_EVENT_MASK	\
 	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
+#define AMD64_L3_SLICE_SHIFT				48
+#define AMD64_L3_SLICE_MASK				\
+	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT				56
+#define AMD64_L3_THREAD_MASK				\
+	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
 	 ARCH_PERFMON_EVENTSEL_UMASK |	\

arch/x86/include/asm/uv/uv.h

@@ -10,8 +10,13 @@ struct cpumask;
 struct mm_struct;
 
 #ifdef CONFIG_X86_UV
+#include <linux/efi.h>
 
 extern enum uv_system_type get_uv_system_type(void);
+static inline bool is_early_uv_system(void)
+{
+	return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab);
+}
 extern int is_uv_system(void);
 extern int is_uv_hubless(void);
 extern void uv_cpu_init(void);
@@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 #else	/* X86_UV */
 
 static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline bool is_early_uv_system(void)	{ return 0; }
 static inline int is_uv_system(void)	{ return 0; }
 static inline int is_uv_hubless(void)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }

arch/x86/kernel/cpu/amd.c

@@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 {
 	/* AMD errata T13 (order #21922) */
-	if ((c->x86 == 6)) {
+	if (c->x86 == 6) {
 		/* Duron Rev A0 */
 		if (c->x86_model == 3 && c->x86_stepping == 0)
 			size = 64;

arch/x86/kernel/cpu/intel_rdt.h

@@ -529,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
 bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 _cbm, int closid, bool exclusive);
+			   unsigned long cbm, int closid, bool exclusive);
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
-				  u32 cbm);
+				  unsigned long cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm);
 bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
 int rdt_pseudo_lock_init(void);
 void rdt_pseudo_lock_release(void);

arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c

@@ -789,25 +789,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 /**
  * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
  * @d: RDT domain
- * @_cbm: CBM to test
+ * @cbm: CBM to test
  *
- * @d represents a cache instance and @_cbm a capacity bitmask that is
+ * @d represents a cache instance and @cbm a capacity bitmask that is
- * considered for it. Determine if @_cbm overlaps with any existing
+ * considered for it. Determine if @cbm overlaps with any existing
  * pseudo-locked region on @d.
  *
- * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
+ * Return: true if @cbm overlaps with pseudo-locked region on @d, false
  * otherwise.
  */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
 {
-	unsigned long *cbm = (unsigned long *)&_cbm;
-	unsigned long *cbm_b;
 	unsigned int cbm_len;
+	unsigned long cbm_b;
 
 	if (d->plr) {
 		cbm_len = d->plr->r->cache.cbm_len;
-		cbm_b = (unsigned long *)&d->plr->cbm;
+		cbm_b = d->plr->cbm;
-		if (bitmap_intersects(cbm, cbm_b, cbm_len))
+		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
 			return true;
 	}
 	return false;

arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

@@ -975,33 +975,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
  * is false then overlaps with any resource group or hardware entities
  * will be considered.
  *
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
  * Return: false if CBM does not overlap, true if it does.
  */
 bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 _cbm, int closid, bool exclusive)
+			   unsigned long cbm, int closid, bool exclusive)
 {
-	unsigned long *cbm = (unsigned long *)&_cbm;
-	unsigned long *ctrl_b;
 	enum rdtgrp_mode mode;
+	unsigned long ctrl_b;
 	u32 *ctrl;
 	int i;
 
 	/* Check for any overlap with regions used by hardware directly */
 	if (!exclusive) {
-		if (bitmap_intersects(cbm,
+		ctrl_b = r->cache.shareable_bits;
-				      (unsigned long *)&r->cache.shareable_bits,
+		if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
-				      r->cache.cbm_len))
 			return true;
 	}
 
 	/* Check for overlap with other resource groups */
 	ctrl = d->ctrl_val;
 	for (i = 0; i < closids_supported(); i++, ctrl++) {
-		ctrl_b = (unsigned long *)ctrl;
+		ctrl_b = *ctrl;
 		mode = rdtgroup_mode_by_closid(i);
 		if (closid_allocated(i) && i != closid &&
 		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
-			if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+			if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
 				if (exclusive) {
 					if (mode == RDT_MODE_EXCLUSIVE)
 						return true;
@@ -1138,15 +1139,18 @@ out:
  * computed by first dividing the total cache size by the CBM length to
  * determine how many bytes each bit in the bitmask represents. The result
  * is multiplied with the number of bits set in the bitmask.
+ *
+ * @cbm is unsigned long, even if only 32 bits are used to make the
+ * bitmap functions work correctly.
  */
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
-				  struct rdt_domain *d, u32 cbm)
+				  struct rdt_domain *d, unsigned long cbm)
 {
 	struct cpu_cacheinfo *ci;
 	unsigned int size = 0;
 	int num_b, i;
 
-	num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
 		if (ci->info_list[i].level == r->cache_level) {
@@ -2353,6 +2357,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 	u32 used_b = 0, unused_b = 0;
 	u32 closid = rdtgrp->closid;
 	struct rdt_resource *r;
+	unsigned long tmp_cbm;
 	enum rdtgrp_mode mode;
 	struct rdt_domain *d;
 	int i, ret;
@@ -2390,9 +2395,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			 * modify the CBM based on system availability.
 			 */
 			cbm_ensure_valid(&d->new_ctrl, r);
-			if (bitmap_weight((unsigned long *) &d->new_ctrl,
+			/*
-					  r->cache.cbm_len) <
+			 * Assign the u32 CBM to an unsigned long to ensure
-					r->cache.min_cbm_bits) {
+			 * that bitmap_weight() does not access out-of-bound
+			 * memory.
+			 */
+			tmp_cbm = d->new_ctrl;
+			if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
+			    r->cache.min_cbm_bits) {
 				rdt_last_cmd_printf("no space on %s:%d\n",
 						    r->name, d->id);
 				return -ENOSPC;

arch/x86/kernel/tsc.c

@@ -26,6 +26,7 @@
 #include <asm/apic.h>
 #include <asm/intel-family.h>
 #include <asm/i8259.h>
+#include <asm/uv/uv.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -1433,6 +1434,9 @@ void __init tsc_early_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return;
+	/* Don't change UV TSC multi-chassis synchronization */
+	if (is_early_uv_system())
+		return;
 	if (!determine_cpu_tsc_frequencies(true))
 		return;
 	loops_per_jiffy = get_loops_per_jiffy();

arch/x86/kvm/mmu.c

@@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
  */
 static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
 
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs.  To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts.  This mask covers the lower bits of the GFN.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static union kvm_mmu_page_role
 kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
@@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte)
 
 static gfn_t get_mmio_spte_gfn(u64 spte)
 {
-	u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask |
+	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
-		   shadow_nonpresent_or_rsvd_mask;
-	u64 gpa = spte & ~mask;
 
 	gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
 	       & shadow_nonpresent_or_rsvd_mask;
@@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
 static void kvm_mmu_reset_all_pte_masks(void)
 {
+	u8 low_phys_bits;
+
 	shadow_user_mask = 0;
 	shadow_accessed_mask = 0;
 	shadow_dirty_mask = 0;
@@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void)
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
 	 * assumed that the CPU is not vulnerable to L1TF.
 	 */
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
 	if (boot_cpu_data.x86_phys_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len)
+	    52 - shadow_nonpresent_or_rsvd_mask_len) {
 		shadow_nonpresent_or_rsvd_mask =
 			rsvd_bits(boot_cpu_data.x86_phys_bits -
 				  shadow_nonpresent_or_rsvd_mask_len,
 				  boot_cpu_data.x86_phys_bits - 1);
+		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+	}
+	shadow_nonpresent_or_rsvd_lower_gfn_mask =
+		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
 }
 
 static int is_cpuid_PSE36(void)

arch/x86/kvm/vmx.c

@@ -121,7 +121,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
 
 #define MSR_BITMAP_MODE_X2APIC		1
 #define MSR_BITMAP_MODE_X2APIC_APICV	2
-#define MSR_BITMAP_MODE_LM		4
 
 #define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
 
@@ -857,6 +856,7 @@ struct nested_vmx {
 
 	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
 	u64 vmcs01_debugctl;
+	u64 vmcs01_guest_bndcfgs;
 
 	u16 vpid02;
 	u16 last_vpid;
@@ -2899,8 +2899,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
 	}
 
-	if (is_long_mode(&vmx->vcpu))
+	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #else
 	savesegment(fs, fs_sel);
 	savesegment(gs, gs_sel);
@@ -2951,8 +2950,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 	vmx->loaded_cpu_state = NULL;
 
 #ifdef CONFIG_X86_64
-	if (is_long_mode(&vmx->vcpu))
+	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #endif
 	if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
 		kvm_load_ldt(host_state->ldt_sel);
@@ -2980,24 +2978,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
 {
-	if (is_long_mode(&vmx->vcpu)) {
+	preempt_disable();
-		preempt_disable();
+	if (vmx->loaded_cpu_state)
-		if (vmx->loaded_cpu_state)
+		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-			rdmsrl(MSR_KERNEL_GS_BASE,
+	preempt_enable();
-			       vmx->msr_guest_kernel_gs_base);
-		preempt_enable();
-	}
 	return vmx->msr_guest_kernel_gs_base;
 }
 
 static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
 {
-	if (is_long_mode(&vmx->vcpu)) {
+	preempt_disable();
-		preempt_disable();
+	if (vmx->loaded_cpu_state)
-		if (vmx->loaded_cpu_state)
+		wrmsrl(MSR_KERNEL_GS_BASE, data);
-			wrmsrl(MSR_KERNEL_GS_BASE, data);
+	preempt_enable();
-		preempt_enable();
-	}
 	vmx->msr_guest_kernel_gs_base = data;
 }
 #endif
@@ -3533,9 +3526,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
 
-	if (kvm_mpx_supported())
-		msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
-
 	/* We support free control of debug control saving. */
 	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
 
@@ -3552,8 +3542,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		VM_ENTRY_LOAD_IA32_PAT;
 	msrs->entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
-	if (kvm_mpx_supported())
-		msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* We support free control of debug control loading. */
 	msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
@@ -3601,12 +3589,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		msrs->secondary_ctls_high);
 	msrs->secondary_ctls_low = 0;
 	msrs->secondary_ctls_high &=
-		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING;
+
 	/*
 	 * We can emulate "VMCS shadowing," even if the hardware
 	 * doesn't support it.
@@ -3663,6 +3651,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		msrs->secondary_ctls_high |=
 			SECONDARY_EXEC_UNRESTRICTED_GUEST;
 
+	if (flexpriority_enabled)
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC,
 		msrs->misc_low,
@@ -5073,19 +5065,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	if (!msr)
 		return;
 
-	/*
-	 * MSR_KERNEL_GS_BASE is not intercepted when the guest is in
-	 * 64-bit mode as a 64-bit kernel may frequently access the
-	 * MSR.  This means we need to manually save/restore the MSR
-	 * when switching between guest and host state, but only if
-	 * the guest is in 64-bit mode.  Sync our cached value if the
-	 * guest is transitioning to 32-bit mode and the CPU contains
-	 * guest state, i.e. the cache is stale.
-	 */
-#ifdef CONFIG_X86_64
-	if (!(efer & EFER_LMA))
-		(void)vmx_read_guest_kernel_gs_base(vmx);
-#endif
 	vcpu->arch.efer = efer;
 	if (efer & EFER_LMA) {
 		vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
@@ -6078,9 +6057,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
 	}
 
-	if (is_long_mode(vcpu))
-		mode |= MSR_BITMAP_MODE_LM;
-
 	return mode;
 }
 
@@ -6121,9 +6097,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 	if (!changed)
 		return;
 
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
-				  !(mode & MSR_BITMAP_MODE_LM));
-
 	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
 		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
 
@@ -6189,6 +6162,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
+static u8 vmx_get_rvi(void)
+{
+	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+}
+
 static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6201,7 +6179,7 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 		WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
 		return false;
 
-	rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+	rvi = vmx_get_rvi();
 
 	vapic_page = kmap(vmx->nested.virtual_apic_page);
 	vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
@@ -10245,15 +10223,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	if (!lapic_in_kernel(vcpu))
 		return;
 
+	if (!flexpriority_enabled &&
+	    !cpu_has_vmx_virtualize_x2apic_mode())
+		return;
+
 	/* Postpone execution until vmcs01 is the current VMCS. */
 	if (is_guest_mode(vcpu)) {
 		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
 		return;
 	}
 
-	if (!cpu_need_tpr_shadow(vcpu))
-		return;
-
 	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -10375,6 +10354,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	return max_irr;
 }
 
+static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
+{
+	u8 rvi = vmx_get_rvi();
+	u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);
+
+	return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -11264,6 +11251,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 #undef cr4_fixed1_update
 }
 
+static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (kvm_mpx_supported()) {
+		bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);
+
+		if (mpx_enabled) {
+			vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
+			vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
+		} else {
+			vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
+			vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
+		}
+	}
+}
+
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -11280,8 +11284,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
 			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 
-	if (nested_vmx_allowed(vcpu))
+	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
+		nested_vmx_entry_exit_ctls_update(vcpu);
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -12049,8 +12055,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	set_cr4_guest_host_mask(vmx);
 
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported()) {
-		vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+		if (vmx->nested.nested_run_pending &&
+			(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+			vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+		else
+			vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+	}
 
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
@@ -12595,15 +12606,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	bool from_vmentry = !!exit_qual;
 	u32 dummy_exit_qual;
-	u32 vmcs01_cpu_exec_ctrl;
+	bool evaluate_pending_interrupts;
 	int r = 0;
 
-	vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
+		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
+		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
 
 	enter_guest_mode(vcpu);
 
 	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	if (kvm_mpx_supported() &&
+		!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+		vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
 	vmx_segment_cache_clear(vmx);
@@ -12643,16 +12660,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
 	 * to L1 or delivered directly to L2 (e.g. In case L1 don't
 	 * intercept EXTERNAL_INTERRUPT).
 	 *
-	 * Usually this would be handled by L0 requesting a
+	 * Usually this would be handled by the processor noticing an
-	 * IRQ/NMI window by setting VMCS accordingly. However,
+	 * IRQ/NMI window request, or checking RVI during evaluation of
-	 * this setting was done on VMCS01 and now VMCS02 is active
+	 * pending virtual interrupts.  However, this setting was done
-	 * instead. Thus, we force L0 to perform pending event
+	 * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
-	 * evaluation by requesting a KVM_REQ_EVENT.
+	 * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
 	 */
-	if (vmcs01_cpu_exec_ctrl &
+	if (unlikely(evaluate_pending_interrupts))
-		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) {
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
-	}
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point

arch/x86/kvm/x86.c

@@ -4698,7 +4698,7 @@ static void kvm_init_msr_list(void)
 		 */
 		switch (msrs_to_save[i]) {
 		case MSR_IA32_BNDCFGS:
-			if (!kvm_x86_ops->mpx_supported())
+			if (!kvm_mpx_supported())
 				continue;
 			break;
 		case MSR_TSC_AUX:

block/blk-mq-tag.c

@@ -322,16 +322,11 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 
 	/*
 	 * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
-	 * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
+	 * queue_hw_ctx after freeze the queue, so we use q_usage_counter
-	 * to avoid race with it. __blk_mq_update_nr_hw_queues will users
+	 * to avoid race with it.
-	 * synchronize_rcu to ensure all of the users go out of the critical
-	 * section below and see zeroed q_usage_counter.
 	 */
-	rcu_read_lock();
+	if (!percpu_ref_tryget(&q->q_usage_counter))
-	if (percpu_ref_is_zero(&q->q_usage_counter)) {
-		rcu_read_unlock();
 		return;
-	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_tags *tags = hctx->tags;
@@ -347,7 +342,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
 		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
 	}
-	rcu_read_unlock();
+	blk_queue_exit(q);
 }
 
 static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,

block/blk-mq.c

@@ -1628,7 +1628,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		BUG_ON(!rq->q);
 		if (rq->mq_ctx != this_ctx) {
 			if (this_ctx) {
-				trace_block_unplug(this_q, depth, from_schedule);
+				trace_block_unplug(this_q, depth, !from_schedule);
 				blk_mq_sched_insert_requests(this_q, this_ctx,
 								&ctx_list,
 								from_schedule);
@@ -1648,7 +1648,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 * on 'ctx_list'. Do those.
 	 */
 	if (this_ctx) {
-		trace_block_unplug(this_q, depth, from_schedule);
+		trace_block_unplug(this_q, depth, !from_schedule);
 		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
 						from_schedule);
 	}

block/elevator.c

@@ -609,7 +609,7 @@ void elv_drain_elevator(struct request_queue *q)
 
 	while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
 		;
-	if (q->nr_sorted && printed++ < 10) {
+	if (q->nr_sorted && !blk_queue_is_zoned(q) && printed++ < 10 ) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
 		       "(nr_sorted=%u), please report this\n",
 		       q->elevator->type->elevator_name, q->nr_sorted);

drivers/base/firmware_loader/main.c

@@ -226,8 +226,11 @@ static int alloc_lookup_fw_priv(const char *fw_name,
 	}
 
 	tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size);
-	if (tmp && !(opt_flags & FW_OPT_NOCACHE))
+	if (tmp) {
-		list_add(&tmp->list, &fwc->head);
+		INIT_LIST_HEAD(&tmp->list);
+		if (!(opt_flags & FW_OPT_NOCACHE))
+			list_add(&tmp->list, &fwc->head);
+	}
 	spin_unlock(&fwc->lock);
 
 	*fw_priv = tmp;

drivers/base/power/main.c

@@ -1713,8 +1713,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 
 	dpm_wait_for_subordinate(dev, async);
 
-	if (async_error)
+	if (async_error) {
+		dev->power.direct_complete = false;
 		goto Complete;
+	}
 
 	/*
 	 * If a device configured to wake up the system from sleep states
@@ -1726,6 +1728,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		pm_wakeup_event(dev, 0);
 
 	if (pm_wakeup_pending()) {
+		dev->power.direct_complete = false;
 		async_error = -EBUSY;
 		goto Complete;
 	}

drivers/block/xen-blkfront.c

@@ -2670,8 +2670,8 @@ static void purge_persistent_grants(struct blkfront_info *info)
 			list_del(&gnt_list_entry->node);
 			gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL);
 			rinfo->persistent_gnts_c--;
-			__free_page(gnt_list_entry->page);
+			gnt_list_entry->gref = GRANT_INVALID_REF;
-			kfree(gnt_list_entry);
+			list_add_tail(&gnt_list_entry->node, &rinfo->grants);
 		}
 
 		spin_unlock_irqrestore(&rinfo->ring_lock, flags);

drivers/clocksource/timer-atmel-pit.c

@@ -180,26 +180,29 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
 	data->base = of_iomap(node, 0);
 	if (!data->base) {
 		pr_err("Could not map PIT address\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto exit;
 	}
 
 	data->mck = of_clk_get(node, 0);
 	if (IS_ERR(data->mck)) {
 		pr_err("Unable to get mck clk\n");
-		return PTR_ERR(data->mck);
+		ret = PTR_ERR(data->mck);
+		goto exit;
 	}
 
 	ret = clk_prepare_enable(data->mck);
 	if (ret) {
 		pr_err("Unable to enable mck\n");
-		return ret;
+		goto exit;
 	}
 
 	/* Get the interrupts property */
 	data->irq = irq_of_parse_and_map(node, 0);
 	if (!data->irq) {
 		pr_err("Unable to get IRQ from DT\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	/*
@@ -227,7 +230,7 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
 	ret = clocksource_register_hz(&data->clksrc, pit_rate);
 	if (ret) {
 		pr_err("Failed to register clocksource\n");
-		return ret;
+		goto exit;
 	}
 
 	/* Set up irq handler */
@@ -236,7 +239,8 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
 			  "at91_tick", data);
 	if (ret) {
 		pr_err("Unable to setup IRQ\n");
-		return ret;
+		clocksource_unregister(&data->clksrc);
+		goto exit;
 	}
 
 	/* Set up and register clockevents */
@@ -254,6 +258,10 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
 	clockevents_register_device(&data->clkevt);
 
 	return 0;
+
+exit:
+	kfree(data);
+	return ret;
 }
 TIMER_OF_DECLARE(at91sam926x_pit, "atmel,at91sam9260-pit",
 		       at91sam926x_pit_dt_init);

drivers/clocksource/timer-fttmr010.c

@@ -130,13 +130,17 @@ static int fttmr010_timer_set_next_event(unsigned long cycles,
 	cr &= ~fttmr010->t1_enable_val;
 	writel(cr, fttmr010->base + TIMER_CR);
 
-	/* Setup the match register forward/backward in time */
+	if (fttmr010->count_down) {
-	cr = readl(fttmr010->base + TIMER1_COUNT);
+		/*
-	if (fttmr010->count_down)
+		 * ASPEED Timer Controller will load TIMER1_LOAD register
-		cr -= cycles;
+		 * into TIMER1_COUNT register when the timer is re-enabled.
-	else
+		 */
-		cr += cycles;
+		writel(cycles, fttmr010->base + TIMER1_LOAD);
-	writel(cr, fttmr010->base + TIMER1_MATCH1);
+	} else {
+		/* Setup the match register forward in time */
+		cr = readl(fttmr010->base + TIMER1_COUNT);
+		writel(cr + cycles, fttmr010->base + TIMER1_MATCH1);
+	}
 
 	/* Start */
 	cr = readl(fttmr010->base + TIMER_CR);

drivers/clocksource/timer-ti-32k.c

@@ -97,6 +97,9 @@ static int __init ti_32k_timer_init(struct device_node *np)
 		return -ENXIO;
 	}
 
+	if (!of_machine_is_compatible("ti,am43"))
+		ti_32k_timer.cs.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
+
 	ti_32k_timer.counter = ti_32k_timer.base;
 
 	/*

drivers/cpufreq/qcom-cpufreq-kryo.c

@@ -44,7 +44,7 @@ enum _msm8996_version {
 
 struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
 
-static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
+static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void)
 {
 	size_t len;
 	u32 *msm_id;
@@ -222,7 +222,7 @@ static int __init qcom_cpufreq_kryo_init(void)
 }
 module_init(qcom_cpufreq_kryo_init);
 
-static void __init qcom_cpufreq_kryo_exit(void)
+static void __exit qcom_cpufreq_kryo_exit(void)
 {
 	platform_device_unregister(kryo_cpufreq_pdev);
 	platform_driver_unregister(&qcom_cpufreq_kryo_driver);

drivers/crypto/caam/caamalg.c

@@ -1553,8 +1553,8 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	edesc->src_nents = src_nents;
 	edesc->dst_nents = dst_nents;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
-	edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
+	edesc->sec4_sg = (struct sec4_sg_entry *)((u8 *)edesc->hw_desc +
-			 desc_bytes;
+						  desc_bytes);
 	edesc->iv_dir = DMA_TO_DEVICE;
 
 	/* Make sure IV is located in a DMAable area */
@@ -1757,8 +1757,8 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
 	edesc->src_nents = src_nents;
 	edesc->dst_nents = dst_nents;
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
-	edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
+	edesc->sec4_sg = (struct sec4_sg_entry *)((u8 *)edesc->hw_desc +
-			 desc_bytes;
+						  desc_bytes);
 	edesc->iv_dir = DMA_FROM_DEVICE;
 
 	/* Make sure IV is located in a DMAable area */

drivers/crypto/chelsio/chcr_algo.c

@@ -367,7 +367,8 @@ static inline void dsgl_walk_init(struct dsgl_walk *walk,
 	walk->to = (struct phys_sge_pairs *)(dsgl + 1);
 }
 
-static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid)
+static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid,
+				 int pci_chan_id)
 {
 	struct cpl_rx_phys_dsgl *phys_cpl;
 
@@ -385,6 +386,7 @@ static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid)
 	phys_cpl->rss_hdr_int.opcode = CPL_RX_PHYS_ADDR;
 	phys_cpl->rss_hdr_int.qid = htons(qid);
 	phys_cpl->rss_hdr_int.hash_val = 0;
+	phys_cpl->rss_hdr_int.channel = pci_chan_id;
 }
 
 static inline void dsgl_walk_add_page(struct dsgl_walk *walk,
@@ -718,7 +720,7 @@ static inline void create_wreq(struct chcr_context *ctx,
 		FILL_WR_RX_Q_ID(ctx->dev->rx_channel_id, qid,
 				!!lcb, ctx->tx_qidx);
 
-	chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->dev->tx_channel_id,
+	chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->tx_chan_id,
 						       qid);
 	chcr_req->ulptx.len = htonl((DIV_ROUND_UP(len16, 16) -
 				     ((sizeof(chcr_req->wreq)) >> 4)));
@@ -1339,16 +1341,23 @@ static int chcr_device_init(struct chcr_context *ctx)
 				    adap->vres.ncrypto_fc);
 		rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan;
 		txq_perchan = ntxq / u_ctx->lldi.nchan;
-		rxq_idx = ctx->dev->tx_channel_id * rxq_perchan;
-		rxq_idx += id % rxq_perchan;
-		txq_idx = ctx->dev->tx_channel_id * txq_perchan;
-		txq_idx += id % txq_perchan;
 		spin_lock(&ctx->dev->lock_chcr_dev);
-		ctx->rx_qidx = rxq_idx;
+		ctx->tx_chan_id = ctx->dev->tx_channel_id;
-		ctx->tx_qidx = txq_idx;
 		ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id;
 		ctx->dev->rx_channel_id = 0;
 		spin_unlock(&ctx->dev->lock_chcr_dev);
+		rxq_idx = ctx->tx_chan_id * rxq_perchan;
+		rxq_idx += id % rxq_perchan;
+		txq_idx = ctx->tx_chan_id * txq_perchan;
+		txq_idx += id % txq_perchan;
+		ctx->rx_qidx = rxq_idx;
+		ctx->tx_qidx = txq_idx;
+		/* Channel Id used by SGE to forward packet to Host.
+		 * Same value should be used in cpl_fw6_pld RSS_CH field
+		 * by FW. Driver programs PCI channel ID to be used in fw
+		 * at the time of queue allocation with value "pi->tx_chan"
+		 */
+		ctx->pci_chan_id = txq_idx / txq_perchan;
 	}
 out:
 	return err;
@@ -2503,6 +2512,7 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct dsgl_walk dsgl_walk;
 	unsigned int authsize = crypto_aead_authsize(tfm);
+	struct chcr_context *ctx = a_ctx(tfm);
 	u32 temp;
 
 	dsgl_walk_init(&dsgl_walk, phys_cpl);
@@ -2512,7 +2522,7 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
 	dsgl_walk_add_page(&dsgl_walk, IV, &reqctx->iv_dma);
 	temp = req->cryptlen + (reqctx->op ? -authsize : authsize);
 	dsgl_walk_add_sg(&dsgl_walk, req->dst, temp, req->assoclen);
-	dsgl_walk_end(&dsgl_walk, qid);
+	dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id);
 }
 
 void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
@@ -2544,6 +2554,8 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
 			     unsigned short qid)
 {
 	struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req);
+	struct chcr_context *ctx = c_ctx(tfm);
 	struct dsgl_walk dsgl_walk;
 
 	dsgl_walk_init(&dsgl_walk, phys_cpl);
@@ -2552,7 +2564,7 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
 	reqctx->dstsg = dsgl_walk.last_sg;
 	reqctx->dst_ofst = dsgl_walk.last_sg_len;
 
-	dsgl_walk_end(&dsgl_walk, qid);
+	dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id);
 }
 
 void chcr_add_hash_src_ent(struct ahash_request *req,

drivers/crypto/chelsio/chcr_crypto.h

@@ -255,6 +255,8 @@ struct chcr_context {
 	struct chcr_dev *dev;
 	unsigned char tx_qidx;
 	unsigned char rx_qidx;
+	unsigned char tx_chan_id;
+	unsigned char pci_chan_id;
 	struct __crypto_ctx crypto_ctx[0];
 };
 

drivers/crypto/mxs-dcp.c

@@ -63,7 +63,7 @@ struct dcp {
 	struct dcp_coherent_block	*coh;
 
 	struct completion		completion[DCP_MAX_CHANS];
-	struct mutex			mutex[DCP_MAX_CHANS];
+	spinlock_t			lock[DCP_MAX_CHANS];
 	struct task_struct		*thread[DCP_MAX_CHANS];
 	struct crypto_queue		queue[DCP_MAX_CHANS];
 };
@@ -349,13 +349,20 @@ static int dcp_chan_thread_aes(void *data)
 
 	int ret;
 
-	do {
+	while (!kthread_should_stop()) {
-		__set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 
-		mutex_lock(&sdcp->mutex[chan]);
+		spin_lock(&sdcp->lock[chan]);
 		backlog = crypto_get_backlog(&sdcp->queue[chan]);
 		arq = crypto_dequeue_request(&sdcp->queue[chan]);
-		mutex_unlock(&sdcp->mutex[chan]);
+		spin_unlock(&sdcp->lock[chan]);
+
+		if (!backlog && !arq) {
+			schedule();
+			continue;
+		}
+
+		set_current_state(TASK_RUNNING);
 
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
@@ -363,11 +370,8 @@ static int dcp_chan_thread_aes(void *data)
 		if (arq) {
 			ret = mxs_dcp_aes_block_crypt(arq);
 			arq->complete(arq, ret);
-			continue;
 		}
-
+	}
-		schedule();
-	} while (!kthread_should_stop());
 
 	return 0;
 }
@@ -409,9 +413,9 @@ static int mxs_dcp_aes_enqueue(struct ablkcipher_request *req, int enc, int ecb)
 	rctx->ecb = ecb;
 	actx->chan = DCP_CHAN_CRYPTO;
 
-	mutex_lock(&sdcp->mutex[actx->chan]);
+	spin_lock(&sdcp->lock[actx->chan]);
 	ret = crypto_enqueue_request(&sdcp->queue[actx->chan], &req->base);
-	mutex_unlock(&sdcp->mutex[actx->chan]);
+	spin_unlock(&sdcp->lock[actx->chan]);
 
 	wake_up_process(sdcp->thread[actx->chan]);
 
@@ -640,13 +644,20 @@ static int dcp_chan_thread_sha(void *data)
 	struct ahash_request *req;
 	int ret, fini;
 
-	do {
+	while (!kthread_should_stop()) {
-		__set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 
-		mutex_lock(&sdcp->mutex[chan]);
+		spin_lock(&sdcp->lock[chan]);
 		backlog = crypto_get_backlog(&sdcp->queue[chan]);
 		arq = crypto_dequeue_request(&sdcp->queue[chan]);
-		mutex_unlock(&sdcp->mutex[chan]);
+		spin_unlock(&sdcp->lock[chan]);
+
+		if (!backlog && !arq) {
+			schedule();
+			continue;
+		}
+
+		set_current_state(TASK_RUNNING);
 
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
@@ -658,12 +669,8 @@ static int dcp_chan_thread_sha(void *data)
 			ret = dcp_sha_req_to_buf(arq);
 			fini = rctx->fini;
 			arq->complete(arq, ret);
-			if (!fini)
-				continue;
 		}
-
+	}
-		schedule();
-	} while (!kthread_should_stop());
 
 	return 0;
 }
@@ -721,9 +728,9 @@ static int dcp_sha_update_fx(struct ahash_request *req, int fini)
 		rctx->init = 1;
 	}
 
-	mutex_lock(&sdcp->mutex[actx->chan]);
+	spin_lock(&sdcp->lock[actx->chan]);
 	ret = crypto_enqueue_request(&sdcp->queue[actx->chan], &req->base);
-	mutex_unlock(&sdcp->mutex[actx->chan]);
+	spin_unlock(&sdcp->lock[actx->chan]);
 
 	wake_up_process(sdcp->thread[actx->chan]);
 	mutex_unlock(&actx->mutex);
@@ -997,7 +1004,7 @@ static int mxs_dcp_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, sdcp);
 
 	for (i = 0; i < DCP_MAX_CHANS; i++) {
-		mutex_init(&sdcp->mutex[i]);
+		spin_lock_init(&sdcp->lock[i]);
 		init_completion(&sdcp->completion[i]);
 		crypto_init_queue(&sdcp->queue[i], 50);
 	}

drivers/crypto/qat/qat_c3xxx/adf_drv.c

@@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret, bar_mask;
+	unsigned long bar_mask;
+	int ret;
 
 	switch (ent->device) {
 	case ADF_C3XXX_PCI_DEVICE_ID:
@@ -235,8 +236,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	i = 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
-	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+	for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
-			 ADF_PCI_MAX_BARS * 2) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
 		bar->base_addr = pci_resource_start(pdev, bar_nr);

drivers/crypto/qat/qat_c3xxxvf/adf_drv.c

@@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret, bar_mask;
+	unsigned long bar_mask;
+	int ret;
 
 	switch (ent->device) {
 	case ADF_C3XXXIOV_PCI_DEVICE_ID:
@@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	i = 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
-	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+	for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
-			 ADF_PCI_MAX_BARS * 2) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
 		bar->base_addr = pci_resource_start(pdev, bar_nr);

drivers/crypto/qat/qat_c62x/adf_drv.c

@@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret, bar_mask;
+	unsigned long bar_mask;
+	int ret;
 
 	switch (ent->device) {
 	case ADF_C62X_PCI_DEVICE_ID:
@@ -235,8 +236,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
-	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+	for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
-			 ADF_PCI_MAX_BARS * 2) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
 		bar->base_addr = pci_resource_start(pdev, bar_nr);

drivers/crypto/qat/qat_c62xvf/adf_drv.c

@@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret, bar_mask;
+	unsigned long bar_mask;
+	int ret;
 
 	switch (ent->device) {
 	case ADF_C62XIOV_PCI_DEVICE_ID:
@@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	i = 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
-	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+	for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
-			 ADF_PCI_MAX_BARS * 2) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
 		bar->base_addr = pci_resource_start(pdev, bar_nr);

drivers/crypto/qat/qat_dh895xcc/adf_drv.c

@@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret, bar_mask;
+	unsigned long bar_mask;
+	int ret;
 
 	switch (ent->device) {
 	case ADF_DH895XCC_PCI_DEVICE_ID:
@@ -237,8 +238,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	i = 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
-	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+	for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
-			 ADF_PCI_MAX_BARS * 2) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
 		bar->base_addr = pci_resource_start(pdev, bar_nr);

drivers/crypto/qat/qat_dh895xccvf/adf_drv.c

@@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct adf_hw_device_data *hw_data;
 	char name[ADF_DEVICE_NAME_LENGTH];
 	unsigned int i, bar_nr;
-	int ret, bar_mask;
+	unsigned long bar_mask;
+	int ret;
 
 	switch (ent->device) {
 	case ADF_DH895XCCIOV_PCI_DEVICE_ID:
@@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Find and map all the device's BARS */
 	i = 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
-	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
+	for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
-			 ADF_PCI_MAX_BARS * 2) {
 		struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
 
 		bar->base_addr = pci_resource_start(pdev, bar_nr);

drivers/fpga/dfl-fme-region.c

@@ -14,6 +14,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/fpga/fpga-mgr.h>
 #include <linux/fpga/fpga-region.h>
 
 #include "dfl-fme-pr.h"
@@ -66,9 +67,10 @@ eprobe_mgr_put:
 static int fme_region_remove(struct platform_device *pdev)
 {
 	struct fpga_region *region = dev_get_drvdata(&pdev->dev);
+	struct fpga_manager *mgr = region->mgr;
 
 	fpga_region_unregister(region);
-	fpga_mgr_put(region->mgr);
+	fpga_mgr_put(mgr);
 
 	return 0;
 }

drivers/fpga/fpga-bridge.c

@@ -125,7 +125,7 @@ static int fpga_bridge_dev_match(struct device *dev, const void *data)
  *
  * Given a device, get an exclusive reference to a fpga bridge.
  *
- * Return: fpga manager struct or IS_ERR() condition containing error code.
+ * Return: fpga bridge struct or IS_ERR() condition containing error code.
  */
 struct fpga_bridge *fpga_bridge_get(struct device *dev,
 				    struct fpga_image_info *info)

drivers/fpga/of-fpga-region.c

@@ -437,9 +437,10 @@ eprobe_mgr_put:
 static int of_fpga_region_remove(struct platform_device *pdev)
 {
 	struct fpga_region *region = platform_get_drvdata(pdev);
+	struct fpga_manager *mgr = region->mgr;
 
 	fpga_region_unregister(region);
-	fpga_mgr_put(region->mgr);
+	fpga_mgr_put(mgr);
 
 	return 0;
 }

drivers/gpio/gpiolib.c

@@ -571,7 +571,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 		if (ret)
 			goto out_free_descs;
 		lh->descs[i] = desc;
-		count = i;
+		count = i + 1;
 
 		if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
 			set_bit(FLAG_ACTIVE_LOW, &desc->flags);

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

@@ -258,6 +258,8 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev)
 {
 	int i;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
@@ -268,7 +270,6 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev)
 	if (i == AMDGPU_MAX_VCE_HANDLES)
 		return 0;
 
-	cancel_delayed_work_sync(&adev->vce.idle_work);
 	/* TODO: suspending running encoding sessions isn't supported */
 	return -EINVAL;
 }

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

@@ -153,11 +153,11 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev)
 	unsigned size;
 	void *ptr;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	if (adev->vcn.vcpu_bo == NULL)
 		return 0;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	size = amdgpu_bo_size(adev->vcn.vcpu_bo);
 	ptr = adev->vcn.cpu_addr;
 

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -358,8 +358,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
 					struct qcm_process_device *qpd)
 {
-	int retval;
 	struct mqd_manager *mqd_mgr;
+	int retval;
 
 	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
 	if (!mqd_mgr)
@@ -387,8 +387,12 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (!q->properties.is_active)
 		return 0;
 
-	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+	if (WARN(q->process->mm != current->mm,
-			&q->properties, q->process->mm);
+		 "should only run in user thread"))
+		retval = -EFAULT;
+	else
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+					   &q->properties, current->mm);
 	if (retval)
 		goto out_uninit_mqd;
 
@@ -545,9 +549,15 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		retval = map_queues_cpsch(dqm);
 	else if (q->properties.is_active &&
 		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
-		  q->properties.type == KFD_QUEUE_TYPE_SDMA))
+		  q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
-		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+		if (WARN(q->process->mm != current->mm,
-				       &q->properties, q->process->mm);
+			 "should only run in user thread"))
+			retval = -EFAULT;
+		else
+			retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd,
+						   q->pipe, q->queue,
+						   &q->properties, current->mm);
+	}
 
 out_unlock:
 	dqm_unlock(dqm);
@@ -653,6 +663,7 @@ out:
 static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 					  struct qcm_process_device *qpd)
 {
+	struct mm_struct *mm = NULL;
 	struct queue *q;
 	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
@@ -686,6 +697,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		kfd_flush_tlb(pdd);
 	}
 
+	/* Take a safe reference to the mm_struct, which may otherwise
+	 * disappear even while the kfd_process is still referenced.
+	 */
+	mm = get_task_mm(pdd->process->lead_thread);
+	if (!mm) {
+		retval = -EFAULT;
+		goto out;
+	}
+
 	/* activate all active queues on the qpd */
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_evicted)
@@ -700,14 +720,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		q->properties.is_evicted = false;
 		q->properties.is_active = true;
 		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
-				       q->queue, &q->properties,
+				       q->queue, &q->properties, mm);
-				       q->process->mm);
 		if (retval)
 			goto out;
 		dqm->queue_count++;
 	}
 	qpd->evicted = 0;
 out:
+	if (mm)
+		mmput(mm);
 	dqm_unlock(dqm);
 	return retval;
 }

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -641,6 +641,87 @@ amdgpu_dm_find_first_crtc_matching_connector(struct drm_atomic_state *state,
 	return NULL;
 }
 
+static void emulated_link_detect(struct dc_link *link)
+{
+	struct dc_sink_init_data sink_init_data = { 0 };
+	struct display_sink_capability sink_caps = { 0 };
+	enum dc_edid_status edid_status;
+	struct dc_context *dc_ctx = link->ctx;
+	struct dc_sink *sink = NULL;
+	struct dc_sink *prev_sink = NULL;
+
+	link->type = dc_connection_none;
+	prev_sink = link->local_sink;
+
+	if (prev_sink != NULL)
+		dc_sink_retain(prev_sink);
+
+	switch (link->connector_signal) {
+	case SIGNAL_TYPE_HDMI_TYPE_A: {
+		sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C;
+		sink_caps.signal = SIGNAL_TYPE_HDMI_TYPE_A;
+		break;
+	}
+
+	case SIGNAL_TYPE_DVI_SINGLE_LINK: {
+		sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C;
+		sink_caps.signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+		break;
+	}
+
+	case SIGNAL_TYPE_DVI_DUAL_LINK: {
+		sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C;
+		sink_caps.signal = SIGNAL_TYPE_DVI_DUAL_LINK;
+		break;
+	}
+
+	case SIGNAL_TYPE_LVDS: {
+		sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C;
+		sink_caps.signal = SIGNAL_TYPE_LVDS;
+		break;
+	}
+
+	case SIGNAL_TYPE_EDP: {
+		sink_caps.transaction_type =
+			DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
+		sink_caps.signal = SIGNAL_TYPE_EDP;
+		break;
+	}
+
+	case SIGNAL_TYPE_DISPLAY_PORT: {
+		sink_caps.transaction_type =
+			DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
+		sink_caps.signal = SIGNAL_TYPE_VIRTUAL;
+		break;
+	}
+
+	default:
+		DC_ERROR("Invalid connector type! signal:%d\n",
+			link->connector_signal);
+		return;
+	}
+
+	sink_init_data.link = link;
+	sink_init_data.sink_signal = sink_caps.signal;
+
+	sink = dc_sink_create(&sink_init_data);
+	if (!sink) {
+		DC_ERROR("Failed to create sink!\n");
+		return;
+	}
+
+	link->local_sink = sink;
+
+	edid_status = dm_helpers_read_local_edid(
+			link->ctx,
+			link,
+			sink);
+
+	if (edid_status != EDID_OK)
+		DC_ERROR("Failed to read EDID");
+
+}
+
 static int dm_resume(void *handle)
 {
 	struct amdgpu_device *adev = handle;
@@ -654,6 +735,7 @@ static int dm_resume(void *handle)
 	struct drm_plane *plane;
 	struct drm_plane_state *new_plane_state;
 	struct dm_plane_state *dm_new_plane_state;
+	enum dc_connection_type new_connection_type = dc_connection_none;
 	int ret;
 	int i;
 
@@ -684,7 +766,13 @@ static int dm_resume(void *handle)
 			continue;
 
 		mutex_lock(&aconnector->hpd_lock);
-		dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD);
+		if (!dc_link_detect_sink(aconnector->dc_link, &new_connection_type))
+			DRM_ERROR("KMS: Failed to detect connector\n");
+
+		if (aconnector->base.force && new_connection_type == dc_connection_none)
+			emulated_link_detect(aconnector->dc_link);
+		else
+			dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD);
 
 		if (aconnector->fake_enable && aconnector->dc_link->local_sink)
 			aconnector->fake_enable = false;
@@ -922,6 +1010,7 @@ static void handle_hpd_irq(void *param)
 	struct amdgpu_dm_connector *aconnector = (struct amdgpu_dm_connector *)param;
 	struct drm_connector *connector = &aconnector->base;
 	struct drm_device *dev = connector->dev;
+	enum dc_connection_type new_connection_type = dc_connection_none;
 
 	/* In case of failure or MST no need to update connector status or notify the OS
 	 * since (for MST case) MST does this in it's own context.
@@ -931,7 +1020,21 @@ static void handle_hpd_irq(void *param)
 	if (aconnector->fake_enable)
 		aconnector->fake_enable = false;
 
-	if (dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD)) {
+	if (!dc_link_detect_sink(aconnector->dc_link, &new_connection_type))
+		DRM_ERROR("KMS: Failed to detect connector\n");
+
+	if (aconnector->base.force && new_connection_type == dc_connection_none) {
+		emulated_link_detect(aconnector->dc_link);
+
+
+		drm_modeset_lock_all(dev);
+		dm_restore_drm_connector_state(dev, connector);
+		drm_modeset_unlock_all(dev);
+
+		if (aconnector->base.force == DRM_FORCE_UNSPECIFIED)
+			drm_kms_helper_hotplug_event(dev);
+
+	} else if (dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD)) {
 		amdgpu_dm_update_connector_after_detect(aconnector);
 
 
@@ -1031,6 +1134,7 @@ static void handle_hpd_rx_irq(void *param)
 	struct drm_device *dev = connector->dev;
 	struct dc_link *dc_link = aconnector->dc_link;
 	bool is_mst_root_connector = aconnector->mst_mgr.mst_state;
+	enum dc_connection_type new_connection_type = dc_connection_none;
 
 	/* TODO:Temporary add mutex to protect hpd interrupt not have a gpio
 	 * conflict, after implement i2c helper, this mutex should be
@@ -1042,7 +1146,24 @@ static void handle_hpd_rx_irq(void *param)
 	if (dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL) &&
 			!is_mst_root_connector) {
 		/* Downstream Port status changed. */
-		if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) {
+		if (!dc_link_detect_sink(dc_link, &new_connection_type))
+			DRM_ERROR("KMS: Failed to detect connector\n");
+
+		if (aconnector->base.force && new_connection_type == dc_connection_none) {
+			emulated_link_detect(dc_link);
+
+			if (aconnector->fake_enable)
+				aconnector->fake_enable = false;
+
+			amdgpu_dm_update_connector_after_detect(aconnector);
+
+
+			drm_modeset_lock_all(dev);
+			dm_restore_drm_connector_state(dev, connector);
+			drm_modeset_unlock_all(dev);
+
+			drm_kms_helper_hotplug_event(dev);
+		} else if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) {
 
 			if (aconnector->fake_enable)
 				aconnector->fake_enable = false;
@@ -1433,6 +1554,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	struct amdgpu_mode_info *mode_info = &adev->mode_info;
 	uint32_t link_cnt;
 	int32_t total_overlay_planes, total_primary_planes;
+	enum dc_connection_type new_connection_type = dc_connection_none;
 
 	link_cnt = dm->dc->caps.max_links;
 	if (amdgpu_dm_mode_config_init(dm->adev)) {
@@ -1499,7 +1621,14 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 
 		link = dc_get_link_at_index(dm->dc, i);
 
-		if (dc_link_detect(link, DETECT_REASON_BOOT)) {
+		if (!dc_link_detect_sink(link, &new_connection_type))
+			DRM_ERROR("KMS: Failed to detect connector\n");
+
+		if (aconnector->base.force && new_connection_type == dc_connection_none) {
+			emulated_link_detect(link);
+			amdgpu_dm_update_connector_after_detect(aconnector);
+
+		} else if (dc_link_detect(link, DETECT_REASON_BOOT)) {
 			amdgpu_dm_update_connector_after_detect(aconnector);
 			register_backlight_device(dm, link);
 		}
@@ -2494,7 +2623,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	if (dm_state && dm_state->freesync_capable)
 		stream->ignore_msa_timing_param = true;
 finish:
-	if (sink && sink->sink_signal == SIGNAL_TYPE_VIRTUAL)
+	if (sink && sink->sink_signal == SIGNAL_TYPE_VIRTUAL && aconnector->base.force != DRM_FORCE_ON)
 		dc_sink_release(sink);
 
 	return stream;
@@ -4504,12 +4633,18 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	}
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 
-	/* Signal HW programming completion */
-	drm_atomic_helper_commit_hw_done(state);
 
 	if (wait_for_vblank)
 		drm_atomic_helper_wait_for_flip_done(dev, state);
 
+	/*
+	 * FIXME:
+	 * Delay hw_done() until flip_done() is signaled. This is to block
+	 * another commit from freeing the CRTC state while we're still
+	 * waiting on flip_done.
+	 */
+	drm_atomic_helper_commit_hw_done(state);
+
 	drm_atomic_helper_cleanup_planes(dev, state);
 
 	/* Finally, drop a runtime PM reference for each newly disabled CRTC,

drivers/gpu/drm/amd/display/dc/core/dc_link.c

@@ -195,7 +195,7 @@ static bool program_hpd_filter(
 	return result;
 }
 
-static bool detect_sink(struct dc_link *link, enum dc_connection_type *type)
+bool dc_link_detect_sink(struct dc_link *link, enum dc_connection_type *type)
 {
 	uint32_t is_hpd_high = 0;
 	struct gpio *hpd_pin;
@@ -604,7 +604,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 	if (link->connector_signal == SIGNAL_TYPE_VIRTUAL)
 		return false;
 
-	if (false == detect_sink(link, &new_connection_type)) {
+	if (false == dc_link_detect_sink(link, &new_connection_type)) {
 		BREAK_TO_DEBUGGER();
 		return false;
 	}

drivers/gpu/drm/amd/display/dc/dc_link.h

@@ -215,6 +215,7 @@ void dc_link_enable_hpd_filter(struct dc_link *link, bool enable);
 
 bool dc_link_is_dp_sink_present(struct dc_link *link);
 
+bool dc_link_detect_sink(struct dc_link *link, enum dc_connection_type *type);
 /*
  * DPCD access interfaces
  */

drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c

@@ -2560,7 +2560,7 @@ static void pplib_apply_display_requirements(
 	dc->prev_display_config = *pp_display_cfg;
 }
 
-void dce110_set_bandwidth(
+static void dce110_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)

drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h

@@ -68,11 +68,6 @@ void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg);
 
-void dce110_set_bandwidth(
-		struct dc *dc,
-		struct dc_state *context,
-		bool decrease_allowed);
-
 uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context);
 
 void dp_receiver_power_ctrl(struct dc_link *link, bool on);

drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c

@@ -244,17 +244,6 @@ static void dce120_update_dchub(
 	dh_data->dchub_info_valid = false;
 }
 
-static void dce120_set_bandwidth(
-		struct dc *dc,
-		struct dc_state *context,
-		bool decrease_allowed)
-{
-	if (context->stream_count <= 0)
-		return;
-
-	dce110_set_bandwidth(dc, context, decrease_allowed);
-}
-
 void dce120_hw_sequencer_construct(struct dc *dc)
 {
 	/* All registers used by dce11.2 match those in dce11 in offset and
@@ -263,6 +252,5 @@ void dce120_hw_sequencer_construct(struct dc *dc)
 	dce110_hw_sequencer_construct(dc);
 	dc->hwss.enable_display_power_gating = dce120_enable_display_power_gating;
 	dc->hwss.update_dchub = dce120_update_dchub;
-	dc->hwss.set_bandwidth = dce120_set_bandwidth;
 }
 

drivers/gpu/drm/arm/malidp_drv.c

@@ -754,6 +754,7 @@ static int malidp_bind(struct device *dev)
 	drm->irq_enabled = true;
 
 	ret = drm_vblank_init(drm, drm->mode_config.num_crtc);
+	drm_crtc_vblank_reset(&malidp->crtc);
 	if (ret < 0) {
 		DRM_ERROR("failed to initialise vblank\n");
 		goto vblank_fail;

drivers/gpu/drm/arm/malidp_hw.c

@@ -384,7 +384,8 @@ static long malidp500_se_calc_mclk(struct malidp_hw_device *hwdev,
 
 static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev,
 				     dma_addr_t *addrs, s32 *pitches,
-				     int num_planes, u16 w, u16 h, u32 fmt_id)
+				     int num_planes, u16 w, u16 h, u32 fmt_id,
+				     const s16 *rgb2yuv_coeffs)
 {
 	u32 base = MALIDP500_SE_MEMWRITE_BASE;
 	u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
@@ -416,6 +417,16 @@ static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev,
 
 	malidp_hw_write(hwdev, MALIDP_DE_H_ACTIVE(w) | MALIDP_DE_V_ACTIVE(h),
 			MALIDP500_SE_MEMWRITE_OUT_SIZE);
+
+	if (rgb2yuv_coeffs) {
+		int i;
+
+		for (i = 0; i < MALIDP_COLORADJ_NUM_COEFFS; i++) {
+			malidp_hw_write(hwdev, rgb2yuv_coeffs[i],
+					MALIDP500_SE_RGB_YUV_COEFFS + i * 4);
+		}
+	}
+
 	malidp_hw_setbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL);
 
 	return 0;
@@ -658,7 +669,8 @@ static long malidp550_se_calc_mclk(struct malidp_hw_device *hwdev,
 
 static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev,
 				     dma_addr_t *addrs, s32 *pitches,
-				     int num_planes, u16 w, u16 h, u32 fmt_id)
+				     int num_planes, u16 w, u16 h, u32 fmt_id,
+				     const s16 *rgb2yuv_coeffs)
 {
 	u32 base = MALIDP550_SE_MEMWRITE_BASE;
 	u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
@@ -689,6 +701,15 @@ static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev,
 	malidp_hw_setbits(hwdev, MALIDP550_SE_MEMWRITE_ONESHOT | MALIDP_SE_MEMWRITE_EN,
 			  MALIDP550_SE_CONTROL);
 
+	if (rgb2yuv_coeffs) {
+		int i;
+
+		for (i = 0; i < MALIDP_COLORADJ_NUM_COEFFS; i++) {
+			malidp_hw_write(hwdev, rgb2yuv_coeffs[i],
+					MALIDP550_SE_RGB_YUV_COEFFS + i * 4);
+		}
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/arm/malidp_hw.h

@@ -191,7 +191,8 @@ struct malidp_hw {
 	 * @param fmt_id - internal format ID of output buffer
 	 */
 	int (*enable_memwrite)(struct malidp_hw_device *hwdev, dma_addr_t *addrs,
-			       s32 *pitches, int num_planes, u16 w, u16 h, u32 fmt_id);
+			       s32 *pitches, int num_planes, u16 w, u16 h, u32 fmt_id,
+			       const s16 *rgb2yuv_coeffs);
 
 	/*
 	 * Disable the writing to memory of the next frame's content.

drivers/gpu/drm/arm/malidp_mw.c

@@ -26,6 +26,8 @@ struct malidp_mw_connector_state {
 	s32 pitches[2];
 	u8 format;
 	u8 n_planes;
+	bool rgb2yuv_initialized;
+	const s16 *rgb2yuv_coeffs;
 };
 
 static int malidp_mw_connector_get_modes(struct drm_connector *connector)
@@ -84,7 +86,7 @@ static void malidp_mw_connector_destroy(struct drm_connector *connector)
 static struct drm_connector_state *
 malidp_mw_connector_duplicate_state(struct drm_connector *connector)
 {
-	struct malidp_mw_connector_state *mw_state;
+	struct malidp_mw_connector_state *mw_state, *mw_current_state;
 
 	if (WARN_ON(!connector->state))
 		return NULL;
@@ -93,7 +95,10 @@ malidp_mw_connector_duplicate_state(struct drm_connector *connector)
 	if (!mw_state)
 		return NULL;
 
-	/* No need to preserve any of our driver-local data */
+	mw_current_state = to_mw_state(connector->state);
+	mw_state->rgb2yuv_coeffs = mw_current_state->rgb2yuv_coeffs;
+	mw_state->rgb2yuv_initialized = mw_current_state->rgb2yuv_initialized;
+
 	__drm_atomic_helper_connector_duplicate_state(connector, &mw_state->base);
 
 	return &mw_state->base;
@@ -108,6 +113,13 @@ static const struct drm_connector_funcs malidp_mw_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
+static const s16 rgb2yuv_coeffs_bt709_limited[MALIDP_COLORADJ_NUM_COEFFS] = {
+	47,  157,   16,
+	-26,  -87,  112,
+	112, -102,  -10,
+	16,  128,  128
+};
+
 static int
 malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
 			       struct drm_crtc_state *crtc_state,
@@ -157,6 +169,9 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
 	}
 	mw_state->n_planes = n_planes;
 
+	if (fb->format->is_yuv)
+		mw_state->rgb2yuv_coeffs = rgb2yuv_coeffs_bt709_limited;
+
 	return 0;
 }
 
@@ -239,10 +254,12 @@ void malidp_mw_atomic_commit(struct drm_device *drm,
 
 		drm_writeback_queue_job(mw_conn, conn_state->writeback_job);
 		conn_state->writeback_job = NULL;
-
 		hwdev->hw->enable_memwrite(hwdev, mw_state->addrs,
 					   mw_state->pitches, mw_state->n_planes,
-					   fb->width, fb->height, mw_state->format);
+					   fb->width, fb->height, mw_state->format,
+					   !mw_state->rgb2yuv_initialized ?
+					   mw_state->rgb2yuv_coeffs : NULL);
+		mw_state->rgb2yuv_initialized = !!mw_state->rgb2yuv_coeffs;
 	} else {
 		DRM_DEV_DEBUG_DRIVER(drm->dev, "Disable memwrite\n");
 		hwdev->hw->disable_memwrite(hwdev);

drivers/gpu/drm/arm/malidp_regs.h

@@ -205,6 +205,7 @@
 #define MALIDP500_SE_BASE		0x00c00
 #define MALIDP500_SE_CONTROL		0x00c0c
 #define MALIDP500_SE_MEMWRITE_OUT_SIZE	0x00c2c
+#define MALIDP500_SE_RGB_YUV_COEFFS	0x00C74
 #define MALIDP500_SE_MEMWRITE_BASE	0x00e00
 #define MALIDP500_DC_IRQ_BASE		0x00f00
 #define MALIDP500_CONFIG_VALID		0x00f00
@@ -238,6 +239,7 @@
 #define MALIDP550_SE_CONTROL		0x08010
 #define   MALIDP550_SE_MEMWRITE_ONESHOT	(1 << 7)
 #define MALIDP550_SE_MEMWRITE_OUT_SIZE	0x08030
+#define MALIDP550_SE_RGB_YUV_COEFFS	0x08078
 #define MALIDP550_SE_MEMWRITE_BASE	0x08100
 #define MALIDP550_DC_BASE		0x0c000
 #define MALIDP550_DC_CONTROL		0x0c010

drivers/gpu/drm/drm_client.c

@@ -63,20 +63,21 @@ static void drm_client_close(struct drm_client_dev *client)
 EXPORT_SYMBOL(drm_client_close);
 
 /**
- * drm_client_new - Create a DRM client
+ * drm_client_init - Initialise a DRM client
  * @dev: DRM device
  * @client: DRM client
  * @name: Client name
  * @funcs: DRM client functions (optional)
  *
+ * This initialises the client and opens a &drm_file. Use drm_client_add() to complete the process.
  * The caller needs to hold a reference on @dev before calling this function.
  * The client is freed when the &drm_device is unregistered. See drm_client_release().
  *
  * Returns:
  * Zero on success or negative error code on failure.
  */
-int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
+int drm_client_init(struct drm_device *dev, struct drm_client_dev *client,
-		   const char *name, const struct drm_client_funcs *funcs)
+		    const char *name, const struct drm_client_funcs *funcs)
 {
 	int ret;
 
@@ -95,10 +96,6 @@ int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
 	if (ret)
 		goto err_put_module;
 
-	mutex_lock(&dev->clientlist_mutex);
-	list_add(&client->list, &dev->clientlist);
-	mutex_unlock(&dev->clientlist_mutex);
-
 	drm_dev_get(dev);
 
 	return 0;
@@ -109,13 +106,33 @@ err_put_module:
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_client_new);
+EXPORT_SYMBOL(drm_client_init);
+
+/**
+ * drm_client_add - Add client to the device list
+ * @client: DRM client
+ *
+ * Add the client to the &drm_device client list to activate its callbacks.
+ * @client must be initialized by a call to drm_client_init(). After
+ * drm_client_add() it is no longer permissible to call drm_client_release()
+ * directly (outside the unregister callback), instead cleanup will happen
+ * automatically on driver unload.
+ */
+void drm_client_add(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_add(&client->list, &dev->clientlist);
+	mutex_unlock(&dev->clientlist_mutex);
+}
+EXPORT_SYMBOL(drm_client_add);
 
 /**
  * drm_client_release - Release DRM client resources
  * @client: DRM client
  *
- * Releases resources by closing the &drm_file that was opened by drm_client_new().
+ * Releases resources by closing the &drm_file that was opened by drm_client_init().
  * It is called automatically if the &drm_client_funcs.unregister callback is _not_ set.
  *
  * This function should only be called from the unregister callback. An exception

drivers/gpu/drm/drm_fb_cma_helper.c

@@ -160,7 +160,7 @@ struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
 
 	fb_helper = &fbdev_cma->fb_helper;
 
-	ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL);
+	ret = drm_client_init(dev, &fb_helper->client, "fbdev", NULL);
 	if (ret)
 		goto err_free;
 
@@ -169,6 +169,8 @@ struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
 	if (ret)
 		goto err_client_put;
 
+	drm_client_add(&fb_helper->client);
+
 	return fbdev_cma;
 
 err_client_put:

drivers/gpu/drm/drm_fb_helper.c

@@ -3218,12 +3218,14 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
 	if (!fb_helper)
 		return -ENOMEM;
 
-	ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
+	ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
 	if (ret) {
 		kfree(fb_helper);
 		return ret;
 	}
 
+	drm_client_add(&fb_helper->client);
+
 	fb_helper->preferred_bpp = preferred_bpp;
 
 	drm_fbdev_client_hotplug(&fb_helper->client);

drivers/gpu/drm/drm_lease.c

@@ -566,14 +566,14 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	lessee_priv->is_master = 1;
 	lessee_priv->authenticated = 1;
 
-	/* Hook up the fd */
-	fd_install(fd, lessee_file);
-
 	/* Pass fd back to userspace */
 	DRM_DEBUG_LEASE("Returning fd %d id %d\n", fd, lessee->lessee_id);
 	cl->fd = fd;
 	cl->lessee_id = lessee->lessee_id;
 
+	/* Hook up the fd */
+	fd_install(fd, lessee_file);
+
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
 	return 0;
 

drivers/gpu/drm/drm_panel.c

@@ -24,7 +24,6 @@
 #include <linux/err.h>
 #include <linux/module.h>
 
-#include <drm/drm_device.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_panel.h>
 
@@ -105,13 +104,6 @@ int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
 	if (panel->connector)
 		return -EBUSY;
 
-	panel->link = device_link_add(connector->dev->dev, panel->dev, 0);
-	if (!panel->link) {
-		dev_err(panel->dev, "failed to link panel to %s\n",
-			dev_name(connector->dev->dev));
-		return -EINVAL;
-	}
-
 	panel->connector = connector;
 	panel->drm = connector->dev;
 
@@ -133,8 +125,6 @@ EXPORT_SYMBOL(drm_panel_attach);
  */
 int drm_panel_detach(struct drm_panel *panel)
 {
-	device_link_del(panel->link);
-
 	panel->connector = NULL;
 	panel->drm = NULL;
 

drivers/gpu/drm/drm_syncobj.c

@@ -97,6 +97,8 @@ static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj,
 {
 	int ret;
 
+	WARN_ON(*fence);
+
 	*fence = drm_syncobj_fence_get(syncobj);
 	if (*fence)
 		return 1;
@@ -743,6 +745,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 
 	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
 		for (i = 0; i < count; ++i) {
+			if (entries[i].fence)
+				continue;
+
 			drm_syncobj_fence_get_or_add_callback(syncobjs[i],
 							      &entries[i].fence,
 							      &entries[i].syncobj_cb,

drivers/gpu/drm/etnaviv/etnaviv_drv.c

@@ -592,8 +592,6 @@ static int etnaviv_pdev_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct component_match *match = NULL;
 
-	dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
-
 	if (!dev->platform_data) {
 		struct device_node *core_node;
 
@@ -655,13 +653,30 @@ static int __init etnaviv_init(void)
 	for_each_compatible_node(np, NULL, "vivante,gc") {
 		if (!of_device_is_available(np))
 			continue;
-		pdev = platform_device_register_simple("etnaviv", -1,
+
-						       NULL, 0);
+		pdev = platform_device_alloc("etnaviv", -1);
-		if (IS_ERR(pdev)) {
+		if (!pdev) {
-			ret = PTR_ERR(pdev);
+			ret = -ENOMEM;
 			of_node_put(np);
 			goto unregister_platform_driver;
 		}
+		pdev->dev.coherent_dma_mask = DMA_BIT_MASK(40);
+		pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+
+		/*
+		 * Apply the same DMA configuration to the virtual etnaviv
+		 * device as the GPU we found. This assumes that all Vivante
+		 * GPUs in the system share the same DMA constraints.
+		 */
+		of_dma_configure(&pdev->dev, np, true);
+
+		ret = platform_device_add(pdev);
+		if (ret) {
+			platform_device_put(pdev);
+			of_node_put(np);
+			goto unregister_platform_driver;
+		}
+
 		etnaviv_drm = pdev;
 		of_node_put(np);
 		break;

drivers/gpu/drm/exynos/exynos_drm_iommu.h

@@ -55,37 +55,12 @@ static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
 static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv,
 					unsigned long start, unsigned long size)
 {
-	struct iommu_domain *domain;
+	priv->mapping = iommu_get_domain_for_dev(priv->dma_dev);
-	int ret;
-
-	domain = iommu_domain_alloc(priv->dma_dev->bus);
-	if (!domain)
-		return -ENOMEM;
-
-	ret = iommu_get_dma_cookie(domain);
-	if (ret)
-		goto free_domain;
-
-	ret = iommu_dma_init_domain(domain, start, size, NULL);
-	if (ret)
-		goto put_cookie;
-
-	priv->mapping = domain;
 	return 0;
-
-put_cookie:
-	iommu_put_dma_cookie(domain);
-free_domain:
-	iommu_domain_free(domain);
-	return ret;
 }
 
 static inline void __exynos_iommu_release_mapping(struct exynos_drm_private *priv)
 {
-	struct iommu_domain *domain = priv->mapping;
-
-	iommu_put_dma_cookie(domain);
-	iommu_domain_free(domain);
 	priv->mapping = NULL;
 }
 
@@ -94,7 +69,9 @@ static inline int __exynos_iommu_attach(struct exynos_drm_private *priv,
 {
 	struct iommu_domain *domain = priv->mapping;
 
-	return iommu_attach_device(domain, dev);
+	if (dev != priv->dma_dev)
+		return iommu_attach_device(domain, dev);
+	return 0;
 }
 
 static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
@@ -102,7 +79,8 @@ static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
 {
 	struct iommu_domain *domain = priv->mapping;
 
-	iommu_detach_device(domain, dev);
+	if (dev != priv->dma_dev)
+		iommu_detach_device(domain, dev);
 }
 #else
 #error Unsupported architecture and IOMMU/DMA-mapping glue code

drivers/gpu/drm/i2c/tda9950.c

@@ -191,7 +191,8 @@ static irqreturn_t tda9950_irq(int irq, void *data)
 			break;
 		}
 		/* TDA9950 executes all retries for us */
-		tx_status |= CEC_TX_STATUS_MAX_RETRIES;
+		if (tx_status != CEC_TX_STATUS_OK)
+			tx_status |= CEC_TX_STATUS_MAX_RETRIES;
 		cec_transmit_done(priv->adap, tx_status, arb_lost_cnt,
 				  nack_cnt, 0, err_cnt);
 		break;
@@ -310,7 +311,7 @@ static void tda9950_release(struct tda9950_priv *priv)
 	/* Wait up to .5s for it to signal non-busy */
 	do {
 		csr = tda9950_read(client, REG_CSR);
-		if (!(csr & CSR_BUSY) || --timeout)
+		if (!(csr & CSR_BUSY) || !--timeout)
 			break;
 		msleep(10);
 	} while (1);

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -232,6 +232,20 @@ static bool compress_init(struct compress *c)
 	return true;
 }
 
+static void *compress_next_page(struct drm_i915_error_object *dst)
+{
+	unsigned long page;
+
+	if (dst->page_count >= dst->num_pages)
+		return ERR_PTR(-ENOSPC);
+
+	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	return dst->pages[dst->page_count++] = (void *)page;
+}
+
 static int compress_page(struct compress *c,
 			 void *src,
 			 struct drm_i915_error_object *dst)
@@ -245,19 +259,14 @@ static int compress_page(struct compress *c,
 
 	do {
 		if (zstream->avail_out == 0) {
-			unsigned long page;
+			zstream->next_out = compress_next_page(dst);
+			if (IS_ERR(zstream->next_out))
+				return PTR_ERR(zstream->next_out);
 
-			page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
-			if (!page)
-				return -ENOMEM;
-
-			dst->pages[dst->page_count++] = (void *)page;
-
-			zstream->next_out = (void *)page;
 			zstream->avail_out = PAGE_SIZE;
 		}
 
-		if (zlib_deflate(zstream, Z_SYNC_FLUSH) != Z_OK)
+		if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK)
 			return -EIO;
 	} while (zstream->avail_in);
 
@@ -268,19 +277,42 @@ static int compress_page(struct compress *c,
 	return 0;
 }
 
+static int compress_flush(struct compress *c,
+			  struct drm_i915_error_object *dst)
+{
+	struct z_stream_s *zstream = &c->zstream;
+
+	do {
+		switch (zlib_deflate(zstream, Z_FINISH)) {
+		case Z_OK: /* more space requested */
+			zstream->next_out = compress_next_page(dst);
+			if (IS_ERR(zstream->next_out))
+				return PTR_ERR(zstream->next_out);
+
+			zstream->avail_out = PAGE_SIZE;
+			break;
+
+		case Z_STREAM_END:
+			goto end;
+
+		default: /* any error */
+			return -EIO;
+		}
+	} while (1);
+
+end:
+	memset(zstream->next_out, 0, zstream->avail_out);
+	dst->unused = zstream->avail_out;
+	return 0;
+}
+
 static void compress_fini(struct compress *c,
 			  struct drm_i915_error_object *dst)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
-	if (dst) {
-		zlib_deflate(zstream, Z_FINISH);
-		dst->unused = zstream->avail_out;
-	}
-
 	zlib_deflateEnd(zstream);
 	kfree(zstream->workspace);
-
 	if (c->tmp)
 		free_page((unsigned long)c->tmp);
 }
@@ -319,6 +351,12 @@ static int compress_page(struct compress *c,
 	return 0;
 }
 
+static int compress_flush(struct compress *c,
+			  struct drm_i915_error_object *dst)
+{
+	return 0;
+}
+
 static void compress_fini(struct compress *c,
 			  struct drm_i915_error_object *dst)
 {
@@ -917,6 +955,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 	unsigned long num_pages;
 	struct sgt_iter iter;
 	dma_addr_t dma;
+	int ret;
 
 	if (!vma)
 		return NULL;
@@ -930,6 +969,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 
 	dst->gtt_offset = vma->node.start;
 	dst->gtt_size = vma->node.size;
+	dst->num_pages = num_pages;
 	dst->page_count = 0;
 	dst->unused = 0;
 
@@ -938,28 +978,26 @@ i915_error_object_create(struct drm_i915_private *i915,
 		return NULL;
 	}
 
+	ret = -EINVAL;
 	for_each_sgt_dma(dma, iter, vma->pages) {
 		void __iomem *s;
-		int ret;
 
 		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
 
 		s = io_mapping_map_atomic_wc(&ggtt->iomap, slot);
 		ret = compress_page(&compress, (void  __force *)s, dst);
 		io_mapping_unmap_atomic(s);
-
 		if (ret)
-			goto unwind;
+			break;
 	}
-	goto out;
 
-unwind:
+	if (ret || compress_flush(&compress, dst)) {
-	while (dst->page_count--)
+		while (dst->page_count--)
-		free_page((unsigned long)dst->pages[dst->page_count]);
+			free_page((unsigned long)dst->pages[dst->page_count]);
-	kfree(dst);
+		kfree(dst);
-	dst = NULL;
+		dst = NULL;
+	}
 
-out:
 	compress_fini(&compress, dst);
 	ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
 	return dst;

drivers/gpu/drm/i915/i915_gpu_error.h

@@ -135,6 +135,7 @@ struct i915_gpu_state {
 		struct drm_i915_error_object {
 			u64 gtt_offset;
 			u64 gtt_size;
+			int num_pages;
 			int page_count;
 			int unused;
 			u32 *pages[0];

drivers/gpu/drm/i915/i915_irq.c

@@ -3091,36 +3091,27 @@ gen11_gt_irq_handler(struct drm_i915_private * const i915,
 	spin_unlock(&i915->irq_lock);
 }
 
-static void
+static u32
-gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl,
+gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl)
-		      u32 *iir)
 {
 	void __iomem * const regs = dev_priv->regs;
+	u32 iir;
 
 	if (!(master_ctl & GEN11_GU_MISC_IRQ))
-		return;
+		return 0;
 
-	*iir = raw_reg_read(regs, GEN11_GU_MISC_IIR);
+	iir = raw_reg_read(regs, GEN11_GU_MISC_IIR);
-	if (likely(*iir))
+	if (likely(iir))
-		raw_reg_write(regs, GEN11_GU_MISC_IIR, *iir);
+		raw_reg_write(regs, GEN11_GU_MISC_IIR, iir);
+
+	return iir;
 }
 
 static void
-gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv,
+gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv, const u32 iir)
-			  const u32 master_ctl, const u32 iir)
 {
-	if (!(master_ctl & GEN11_GU_MISC_IRQ))
-		return;
-
-	if (unlikely(!iir)) {
-		DRM_ERROR("GU_MISC iir blank!\n");
-		return;
-	}
-
 	if (iir & GEN11_GU_MISC_GSE)
 		intel_opregion_asle_intr(dev_priv);
-	else
-		DRM_ERROR("Unexpected GU_MISC interrupt 0x%x\n", iir);
 }
 
 static irqreturn_t gen11_irq_handler(int irq, void *arg)
@@ -3157,12 +3148,12 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
 		enable_rpm_wakeref_asserts(i915);
 	}
 
-	gen11_gu_misc_irq_ack(i915, master_ctl, &gu_misc_iir);
+	gu_misc_iir = gen11_gu_misc_irq_ack(i915, master_ctl);
 
 	/* Acknowledge and enable interrupts. */
 	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ | master_ctl);
 
-	gen11_gu_misc_irq_handler(i915, master_ctl, gu_misc_iir);
+	gen11_gu_misc_irq_handler(i915, gu_misc_iir);
 
 	return IRQ_HANDLED;
 }

drivers/gpu/drm/i915/i915_pci.c

@@ -592,7 +592,6 @@ static const struct intel_device_info intel_cannonlake_info = {
 	GEN10_FEATURES, \
 	GEN(11), \
 	.ddb_size = 2048, \
-	.has_csr = 0, \
 	.has_logical_ring_elsq = 1
 
 static const struct intel_device_info intel_icelake_11_info = {

drivers/hid/hid-ids.h

@@ -976,7 +976,6 @@
 #define USB_DEVICE_ID_SIS817_TOUCH	0x0817
 #define USB_DEVICE_ID_SIS_TS		0x1013
 #define USB_DEVICE_ID_SIS1030_TOUCH	0x1030
-#define USB_DEVICE_ID_SIS10FB_TOUCH	0x10fb
 
 #define USB_VENDOR_ID_SKYCABLE			0x1223
 #define	USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER	0x3F07

drivers/hid/i2c-hid/i2c-hid.c

@@ -47,7 +47,7 @@
 /* quirks to control the device */
 #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV	BIT(0)
 #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET	BIT(1)
-#define I2C_HID_QUIRK_RESEND_REPORT_DESCR	BIT(2)
+#define I2C_HID_QUIRK_NO_RUNTIME_PM		BIT(2)
 
 /* flags */
 #define I2C_HID_STARTED		0
@@ -169,9 +169,8 @@ static const struct i2c_hid_quirks {
 	{ USB_VENDOR_ID_WEIDA, USB_DEVICE_ID_WEIDA_8755,
 		I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV },
 	{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
-		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
+		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET |
-	{ USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH,
+		I2C_HID_QUIRK_NO_RUNTIME_PM },
-		I2C_HID_QUIRK_RESEND_REPORT_DESCR },
 	{ 0, 0 }
 };
 
@@ -1105,7 +1104,9 @@ static int i2c_hid_probe(struct i2c_client *client,
 		goto err_mem_free;
 	}
 
-	pm_runtime_put(&client->dev);
+	if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
+		pm_runtime_put(&client->dev);
+
 	return 0;
 
 err_mem_free:
@@ -1130,7 +1131,8 @@ static int i2c_hid_remove(struct i2c_client *client)
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 	struct hid_device *hid;
 
-	pm_runtime_get_sync(&client->dev);
+	if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
+		pm_runtime_get_sync(&client->dev);
 	pm_runtime_disable(&client->dev);
 	pm_runtime_set_suspended(&client->dev);
 	pm_runtime_put_noidle(&client->dev);
@@ -1236,22 +1238,13 @@ static int i2c_hid_resume(struct device *dev)
 
 	/* Instead of resetting device, simply powers the device on. This
 	 * solves "incomplete reports" on Raydium devices 2386:3118 and
-	 * 2386:4B33
+	 * 2386:4B33 and fixes various SIS touchscreens no longer sending
+	 * data after a suspend/resume.
 	 */
 	ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
 	if (ret)
 		return ret;
 
-	/* Some devices need to re-send report descr cmd
-	 * after resume, after this it will be back normal.
-	 * otherwise it issues too many incomplete reports.
-	 */
-	if (ihid->quirks & I2C_HID_QUIRK_RESEND_REPORT_DESCR) {
-		ret = i2c_hid_command(client, &hid_report_descr_cmd, NULL, 0);
-		if (ret)
-			return ret;
-	}
-
 	if (hid->driver && hid->driver->reset_resume) {
 		ret = hid->driver->reset_resume(hid);
 		return ret;

drivers/hid/intel-ish-hid/ipc/hw-ish.h

@@ -29,6 +29,7 @@
 #define CNL_Ax_DEVICE_ID	0x9DFC
 #define GLK_Ax_DEVICE_ID	0x31A2
 #define CNL_H_DEVICE_ID		0xA37C
+#define ICL_MOBILE_DEVICE_ID	0x34FC
 #define SPT_H_DEVICE_ID		0xA135
 
 #define	REVISION_ID_CHT_A0	0x6

drivers/hid/intel-ish-hid/ipc/pci-ish.c

@@ -38,6 +38,7 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_Ax_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, GLK_Ax_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_H_DEVICE_ID)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, ICL_MOBILE_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)},
 	{0, }
 };

drivers/hv/connection.c

@@ -76,6 +76,7 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 					__u32 version)
 {
 	int ret = 0;
+	unsigned int cur_cpu;
 	struct vmbus_channel_initiate_contact *msg;
 	unsigned long flags;
 
@@ -118,9 +119,10 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	 * the CPU attempting to connect may not be CPU 0.
 	 */
 	if (version >= VERSION_WIN8_1) {
-		msg->target_vcpu =
+		cur_cpu = get_cpu();
-			hv_cpu_number_to_vp_number(smp_processor_id());
+		msg->target_vcpu = hv_cpu_number_to_vp_number(cur_cpu);
-		vmbus_connection.connect_cpu = smp_processor_id();
+		vmbus_connection.connect_cpu = cur_cpu;
+		put_cpu();
 	} else {
 		msg->target_vcpu = 0;
 		vmbus_connection.connect_cpu = 0;

drivers/i2c/busses/i2c-designware-master.c

@@ -34,11 +34,11 @@ static void i2c_dw_configure_fifo_master(struct dw_i2c_dev *dev)
 
 static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev)
 {
-	u32 ic_clk = i2c_dw_clk_rate(dev);
 	const char *mode_str, *fp_str = "";
 	u32 comp_param1;
 	u32 sda_falling_time, scl_falling_time;
 	struct i2c_timings *t = &dev->timings;
+	u32 ic_clk;
 	int ret;
 
 	ret = i2c_dw_acquire_lock(dev);
@@ -53,6 +53,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev)
 
 	/* Calculate SCL timing parameters for standard mode if not set */
 	if (!dev->ss_hcnt || !dev->ss_lcnt) {
+		ic_clk = i2c_dw_clk_rate(dev);
 		dev->ss_hcnt =
 			i2c_dw_scl_hcnt(ic_clk,
 					4000,	/* tHD;STA = tHIGH = 4.0 us */
@@ -89,6 +90,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev)
 	 * needed also in high speed mode.
 	 */
 	if (!dev->fs_hcnt || !dev->fs_lcnt) {
+		ic_clk = i2c_dw_clk_rate(dev);
 		dev->fs_hcnt =
 			i2c_dw_scl_hcnt(ic_clk,
 					600,	/* tHD;STA = tHIGH = 0.6 us */

drivers/i2c/busses/i2c-isch.c

@@ -164,7 +164,7 @@ static s32 sch_access(struct i2c_adapter *adap, u16 addr,
 		 * run ~75 kHz instead which should do no harm.
 		 */
 		dev_notice(&sch_adapter.dev,
-			"Clock divider unitialized. Setting defaults\n");
+			"Clock divider uninitialized. Setting defaults\n");
 		outw(backbone_speed / (4 * 100), SMBHSTCLK);
 	}