Linux 5.14

Pull clk fix from Stephen Boyd:
 "One hotfix for a NULL pointer deref in the Renesas usb clk driver"

* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
  clk: renesas: rcar-usb2-clock-sel: Fix kernel NULL pointer dereference

Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml

@@ -24,10 +24,10 @@ allOf:
 select:
   properties:
     compatible:
-      items:
-        - enum:
-            - sifive,fu540-c000-ccache
-            - sifive,fu740-c000-ccache
+      contains:
+        enum:
+          - sifive,fu540-c000-ccache
+          - sifive,fu740-c000-ccache
 
   required:
     - compatible

MAINTAINERS

@@ -3866,6 +3866,16 @@ L:	bcm-kernel-feedback-list@broadcom.com
 S:	Maintained
 F:	drivers/mtd/nand/raw/brcmnand/
 
+BROADCOM STB PCIE DRIVER
+M:	Jim Quinlan <jim2101024@gmail.com>
+M:	Nicolas Saenz Julienne <nsaenz@kernel.org>
+M:	Florian Fainelli <f.fainelli@gmail.com>
+M:	bcm-kernel-feedback-list@broadcom.com
+L:	linux-pci@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
+F:	drivers/pci/controller/pcie-brcmstb.c
+
 BROADCOM SYSTEMPORT ETHERNET DRIVER
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	bcm-kernel-feedback-list@broadcom.com
@@ -4498,7 +4508,7 @@ L:	clang-built-linux@googlegroups.com
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
 B:	https://github.com/ClangBuiltLinux/linux/issues
-C:	irc://chat.freenode.net/clangbuiltlinux
+C:	irc://irc.libera.chat/clangbuiltlinux
 F:	Documentation/kbuild/llvm.rst
 F:	include/linux/compiler-clang.h
 F:	scripts/clang-tools/
@@ -6945,7 +6955,7 @@ F:	include/uapi/linux/mdio.h
 F:	include/uapi/linux/mii.h
 
 EXFAT FILE SYSTEM
-M:	Namjae Jeon <namjae.jeon@samsung.com>
+M:	Namjae Jeon <linkinjeon@kernel.org>
 M:	Sungjong Seo <sj1557.seo@samsung.com>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
@@ -14430,6 +14440,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/pci/hisilicon-histb-pcie.txt
 F:	drivers/pci/controller/dwc/pcie-histb.c
 
+PCIE DRIVER FOR INTEL LGM GW SOC
+M:	Rahul Tanwar <rtanwar@maxlinear.com>
+L:	linux-pci@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
+F:	drivers/pci/controller/dwc/pcie-intel-gw.c
+
 PCIE DRIVER FOR MEDIATEK
 M:	Ryder Lee <ryder.lee@mediatek.com>
 M:	Jianjun Wang <jianjun.wang@mediatek.com>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION =
 NAME = Opossums on Parade
 
 # *DOCUMENTATION*

arch/arm/configs/nhk8815_defconfig

@@ -15,8 +15,6 @@ CONFIG_SLAB=y
 CONFIG_ARCH_NOMADIK=y
 CONFIG_MACH_NOMADIK_8815NHK=y
 CONFIG_AEABI=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -52,9 +50,9 @@ CONFIG_MTD_BLOCK=y
 CONFIG_MTD_ONENAND=y
 CONFIG_MTD_ONENAND_VERIFY_WRITE=y
 CONFIG_MTD_ONENAND_GENERIC=y
-CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
 CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_FSMC=y
+CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=y
 CONFIG_BLK_DEV_RAM=y
@@ -97,6 +95,7 @@ CONFIG_REGULATOR=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_TPO_TPG110=y
 CONFIG_DRM_PL111=y
+CONFIG_FB=y
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -136,9 +135,8 @@ CONFIG_NLS_ISO8859_15=y
 CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_SHA1=y
 CONFIG_CRYPTO_DES=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_FS=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set

arch/arm/include/asm/memory.h

@@ -160,10 +160,11 @@ extern unsigned long vectors_base;
 
 /*
  * Physical start and end address of the kernel sections. These addresses are
- * 2MB-aligned to match the section mappings placed over the kernel.
+ * 2MB-aligned to match the section mappings placed over the kernel. We use
+ * u64 so that LPAE mappings beyond the 32bit limit will work out as well.
  */
-extern u32 kernel_sec_start;
-extern u32 kernel_sec_end;
+extern u64 kernel_sec_start;
+extern u64 kernel_sec_end;
 
 /*
  * Physical vs virtual RAM address space conversion.  These are

arch/arm/kernel/head.S

@@ -49,7 +49,8 @@
 
 	/*
 	 * This needs to be assigned at runtime when the linker symbols are
-	 * resolved.
+	 * resolved. These are unsigned 64bit really, but in this assembly code
+	 * We store them as 32bit.
 	 */
 	.pushsection .data
 	.align	2
@@ -57,7 +58,9 @@
 	.globl	kernel_sec_end
 kernel_sec_start:
 	.long	0
+	.long	0
 kernel_sec_end:
+	.long	0
 	.long	0
 	.popsection
 
@@ -250,7 +253,11 @@ __create_page_tables:
 	add	r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
 	ldr	r6, =(_end - 1)
 	adr_l	r5, kernel_sec_start		@ _pa(kernel_sec_start)
-	str	r8, [r5]			@ Save physical start of kernel
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	str	r8, [r5, #4]			@ Save physical start of kernel (BE)
+#else
+	str	r8, [r5]			@ Save physical start of kernel (LE)
+#endif
 	orr	r3, r8, r7			@ Add the MMU flags
 	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
 1:	str	r3, [r0], #1 << PMD_ORDER
@@ -259,7 +266,11 @@ __create_page_tables:
 	bls	1b
 	eor	r3, r3, r7			@ Remove the MMU flags
 	adr_l	r5, kernel_sec_end		@ _pa(kernel_sec_end)
-	str	r3, [r5]			@ Save physical end of kernel
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	str	r3, [r5, #4]			@ Save physical end of kernel (BE)
+#else
+	str	r3, [r5]			@ Save physical end of kernel (LE)
+#endif
 
 #ifdef CONFIG_XIP_KERNEL
 	/*

arch/arm/mach-ixp4xx/include/mach/ixp4xx-regs.h

@@ -218,30 +218,30 @@
 /*
  * PCI Control/Status Registers
  */
-#define IXP4XX_PCI_CSR(x) ((volatile u32 *)(IXP4XX_PCI_CFG_BASE_VIRT+(x)))
+#define _IXP4XX_PCI_CSR(x) ((volatile u32 *)(IXP4XX_PCI_CFG_BASE_VIRT+(x)))
 
-#define PCI_NP_AD               IXP4XX_PCI_CSR(PCI_NP_AD_OFFSET)
-#define PCI_NP_CBE              IXP4XX_PCI_CSR(PCI_NP_CBE_OFFSET)
-#define PCI_NP_WDATA            IXP4XX_PCI_CSR(PCI_NP_WDATA_OFFSET)
-#define PCI_NP_RDATA            IXP4XX_PCI_CSR(PCI_NP_RDATA_OFFSET)
-#define PCI_CRP_AD_CBE          IXP4XX_PCI_CSR(PCI_CRP_AD_CBE_OFFSET)
-#define PCI_CRP_WDATA           IXP4XX_PCI_CSR(PCI_CRP_WDATA_OFFSET)
-#define PCI_CRP_RDATA           IXP4XX_PCI_CSR(PCI_CRP_RDATA_OFFSET)
-#define PCI_CSR                 IXP4XX_PCI_CSR(PCI_CSR_OFFSET) 
-#define PCI_ISR                 IXP4XX_PCI_CSR(PCI_ISR_OFFSET)
-#define PCI_INTEN               IXP4XX_PCI_CSR(PCI_INTEN_OFFSET)
-#define PCI_DMACTRL             IXP4XX_PCI_CSR(PCI_DMACTRL_OFFSET)
-#define PCI_AHBMEMBASE          IXP4XX_PCI_CSR(PCI_AHBMEMBASE_OFFSET)
-#define PCI_AHBIOBASE           IXP4XX_PCI_CSR(PCI_AHBIOBASE_OFFSET)
-#define PCI_PCIMEMBASE          IXP4XX_PCI_CSR(PCI_PCIMEMBASE_OFFSET)
-#define PCI_AHBDOORBELL         IXP4XX_PCI_CSR(PCI_AHBDOORBELL_OFFSET)
-#define PCI_PCIDOORBELL         IXP4XX_PCI_CSR(PCI_PCIDOORBELL_OFFSET)
-#define PCI_ATPDMA0_AHBADDR     IXP4XX_PCI_CSR(PCI_ATPDMA0_AHBADDR_OFFSET)
-#define PCI_ATPDMA0_PCIADDR     IXP4XX_PCI_CSR(PCI_ATPDMA0_PCIADDR_OFFSET)
-#define PCI_ATPDMA0_LENADDR     IXP4XX_PCI_CSR(PCI_ATPDMA0_LENADDR_OFFSET)
-#define PCI_ATPDMA1_AHBADDR     IXP4XX_PCI_CSR(PCI_ATPDMA1_AHBADDR_OFFSET)
-#define PCI_ATPDMA1_PCIADDR     IXP4XX_PCI_CSR(PCI_ATPDMA1_PCIADDR_OFFSET)
-#define PCI_ATPDMA1_LENADDR     IXP4XX_PCI_CSR(PCI_ATPDMA1_LENADDR_OFFSET)
+#define PCI_NP_AD               _IXP4XX_PCI_CSR(PCI_NP_AD_OFFSET)
+#define PCI_NP_CBE              _IXP4XX_PCI_CSR(PCI_NP_CBE_OFFSET)
+#define PCI_NP_WDATA            _IXP4XX_PCI_CSR(PCI_NP_WDATA_OFFSET)
+#define PCI_NP_RDATA            _IXP4XX_PCI_CSR(PCI_NP_RDATA_OFFSET)
+#define PCI_CRP_AD_CBE          _IXP4XX_PCI_CSR(PCI_CRP_AD_CBE_OFFSET)
+#define PCI_CRP_WDATA           _IXP4XX_PCI_CSR(PCI_CRP_WDATA_OFFSET)
+#define PCI_CRP_RDATA           _IXP4XX_PCI_CSR(PCI_CRP_RDATA_OFFSET)
+#define PCI_CSR                 _IXP4XX_PCI_CSR(PCI_CSR_OFFSET) 
+#define PCI_ISR                 _IXP4XX_PCI_CSR(PCI_ISR_OFFSET)
+#define PCI_INTEN               _IXP4XX_PCI_CSR(PCI_INTEN_OFFSET)
+#define PCI_DMACTRL             _IXP4XX_PCI_CSR(PCI_DMACTRL_OFFSET)
+#define PCI_AHBMEMBASE          _IXP4XX_PCI_CSR(PCI_AHBMEMBASE_OFFSET)
+#define PCI_AHBIOBASE           _IXP4XX_PCI_CSR(PCI_AHBIOBASE_OFFSET)
+#define PCI_PCIMEMBASE          _IXP4XX_PCI_CSR(PCI_PCIMEMBASE_OFFSET)
+#define PCI_AHBDOORBELL         _IXP4XX_PCI_CSR(PCI_AHBDOORBELL_OFFSET)
+#define PCI_PCIDOORBELL         _IXP4XX_PCI_CSR(PCI_PCIDOORBELL_OFFSET)
+#define PCI_ATPDMA0_AHBADDR     _IXP4XX_PCI_CSR(PCI_ATPDMA0_AHBADDR_OFFSET)
+#define PCI_ATPDMA0_PCIADDR     _IXP4XX_PCI_CSR(PCI_ATPDMA0_PCIADDR_OFFSET)
+#define PCI_ATPDMA0_LENADDR     _IXP4XX_PCI_CSR(PCI_ATPDMA0_LENADDR_OFFSET)
+#define PCI_ATPDMA1_AHBADDR     _IXP4XX_PCI_CSR(PCI_ATPDMA1_AHBADDR_OFFSET)
+#define PCI_ATPDMA1_PCIADDR     _IXP4XX_PCI_CSR(PCI_ATPDMA1_PCIADDR_OFFSET)
+#define PCI_ATPDMA1_LENADDR     _IXP4XX_PCI_CSR(PCI_ATPDMA1_LENADDR_OFFSET)
 
 /*
  * PCI register values and bit definitions 

arch/arm/mm/mmu.c

@@ -1608,6 +1608,13 @@ static void __init early_paging_init(const struct machine_desc *mdesc)
 	if (offset == 0)
 		return;
 
+	/*
+	 * Offset the kernel section physical offsets so that the kernel
+	 * mapping will work out later on.
+	 */
+	kernel_sec_start += offset;
+	kernel_sec_end += offset;
+
 	/*
 	 * Get the address of the remap function in the 1:1 identity
 	 * mapping setup by the early page table assembly code.  We
@@ -1716,7 +1723,7 @@ void __init paging_init(const struct machine_desc *mdesc)
 {
 	void *zero_page;
 
-	pr_debug("physical kernel sections: 0x%08x-0x%08x\n",
+	pr_debug("physical kernel sections: 0x%08llx-0x%08llx\n",
 		 kernel_sec_start, kernel_sec_end);
 
 	prepare_page_table();

arch/arm/mm/pv-fixup-asm.S

@@ -29,7 +29,7 @@ ENTRY(lpae_pgtables_remap_asm)
 	ldr	r6, =(_end - 1)
 	add	r7, r2, #0x1000
 	add	r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER
-	add	r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER)
+	add	r7, r7, #KERNEL_OFFSET >> (SECTION_SHIFT - L2_ORDER)
 1:	ldrd	r4, r5, [r7]
 	adds	r4, r4, r0
 	adc	r5, r5, r1

arch/arm64/Kconfig

@@ -156,6 +156,7 @@ config ARM64
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
+	select HAVE_ARCH_PFN_VALID
 	select HAVE_ARCH_PREL32_RELOCATIONS
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER

arch/arm64/Makefile

@@ -183,6 +183,8 @@ endif
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
+	$(Q)$(MAKE) $(clean)=arch/arm64/kernel/vdso
+	$(Q)$(MAKE) $(clean)=arch/arm64/kernel/vdso32
 
 ifeq ($(KBUILD_EXTMOD),)
 # We need to generate vdso-offsets.h before compiling certain files in kernel/.

arch/arm64/boot/dts/qcom/msm8992-bullhead-rev-101.dts

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2015, LGE Inc. All rights reserved.
  * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com>
  */
 
 /dts-v1/;
@@ -9,6 +10,9 @@
 #include "pm8994.dtsi"
 #include "pmi8994.dtsi"
 
+/* cont_splash_mem has different memory mapping */
+/delete-node/ &cont_splash_mem;
+
 / {
 	model = "LG Nexus 5X";
 	compatible = "lg,bullhead", "qcom,msm8992";
@@ -17,6 +21,9 @@
 	qcom,board-id = <0xb64 0>;
 	qcom,pmic-id = <0x10009 0x1000A 0x0 0x0>;
 
+	/* Bullhead firmware doesn't support PSCI */
+	/delete-node/ psci;
+
 	aliases {
 		serial0 = &blsp1_uart2;
 	};
@@ -38,6 +45,11 @@
 			ftrace-size = <0x10000>;
 			pmsg-size = <0x20000>;
 		};
+
+		cont_splash_mem: memory@3400000 {
+			reg = <0 0x03400000 0 0x1200000>;
+			no-map;
+		};
 	};
 };
 

arch/arm64/boot/dts/qcom/msm8994-angler-rev-101.dts

@@ -1,12 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2015, Huawei Inc. All rights reserved.
  * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com>
  */
 
 /dts-v1/;
 
 #include "msm8994.dtsi"
 
+/* Angler's firmware does not report where the memory is allocated */
+/delete-node/ &cont_splash_mem;
+
 / {
 	model = "Huawei Nexus 6P";
 	compatible = "huawei,angler", "qcom,msm8994";

arch/arm64/boot/dts/qcom/sc7280.dtsi

@@ -200,7 +200,7 @@
 					   &BIG_CPU_SLEEP_1
 					   &CLUSTER_SLEEP_0>;
 			next-level-cache = <&L2_700>;
-			qcom,freq-domain = <&cpufreq_hw 1>;
+			qcom,freq-domain = <&cpufreq_hw 2>;
 			#cooling-cells = <2>;
 			L2_700: l2-cache {
 				compatible = "cache";

arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi

@@ -69,7 +69,7 @@
 		};
 		rmtfs_upper_guard: memory@f5d01000 {
 			no-map;
-			reg = <0 0xf5d01000 0 0x2000>;
+			reg = <0 0xf5d01000 0 0x1000>;
 		};
 
 		/*
@@ -78,7 +78,7 @@
 		 */
 		removed_region: memory@88f00000 {
 			no-map;
-			reg = <0 0x88f00000 0 0x200000>;
+			reg = <0 0x88f00000 0 0x1c00000>;
 		};
 
 		ramoops: ramoops@ac300000 {

arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts

@@ -700,7 +700,7 @@
 		left_spkr: wsa8810-left{
 			compatible = "sdw10217211000";
 			reg = <0 3>;
-			powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_HIGH>;
+			powerdown-gpios = <&wcdgpio 1 GPIO_ACTIVE_HIGH>;
 			#thermal-sensor-cells = <0>;
 			sound-name-prefix = "SpkrLeft";
 			#sound-dai-cells = <0>;
@@ -708,7 +708,7 @@
 
 		right_spkr: wsa8810-right{
 			compatible = "sdw10217211000";
-			powerdown-gpios = <&wcdgpio 3 GPIO_ACTIVE_HIGH>;
+			powerdown-gpios = <&wcdgpio 2 GPIO_ACTIVE_HIGH>;
 			reg = <0 4>;
 			#thermal-sensor-cells = <0>;
 			sound-name-prefix = "SpkrRight";

arch/arm64/include/asm/el2_setup.h

@@ -33,8 +33,7 @@
  * EL2.
  */
 .macro __init_el2_timers
-	mrs	x0, cnthctl_el2
-	orr	x0, x0, #3			// Enable EL1 physical timers
+	mov	x0, #3				// Enable EL1 physical timers
 	msr	cnthctl_el2, x0
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 .endm

arch/arm64/include/asm/page.h

@@ -41,6 +41,7 @@ void tag_clear_highpage(struct page *to);
 
 typedef struct page *pgtable_t;
 
+int pfn_valid(unsigned long pfn);
 int pfn_is_map_memory(unsigned long pfn);
 
 #include <asm/memory.h>

arch/arm64/mm/init.c

@@ -219,6 +219,43 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	free_area_init(max_zone_pfns);
 }
 
+int pfn_valid(unsigned long pfn)
+{
+	phys_addr_t addr = PFN_PHYS(pfn);
+	struct mem_section *ms;
+
+	/*
+	 * Ensure the upper PAGE_SHIFT bits are clear in the
+	 * pfn. Else it might lead to false positives when
+	 * some of the upper bits are set, but the lower bits
+	 * match a valid pfn.
+	 */
+	if (PHYS_PFN(addr) != pfn)
+		return 0;
+
+	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
+		return 0;
+
+	ms = __pfn_to_section(pfn);
+	if (!valid_section(ms))
+		return 0;
+
+	/*
+	 * ZONE_DEVICE memory does not have the memblock entries.
+	 * memblock_is_map_memory() check for ZONE_DEVICE based
+	 * addresses will always fail. Even the normal hotplugged
+	 * memory will never have MEMBLOCK_NOMAP flag set in their
+	 * memblock entries. Skip memblock search for all non early
+	 * memory sections covering all of hotplug memory including
+	 * both normal and ZONE_DEVICE based.
+	 */
+	if (!early_section(ms))
+		return pfn_section_valid(ms, pfn);
+
+	return memblock_is_memory(addr);
+}
+EXPORT_SYMBOL(pfn_valid);
+
 int pfn_is_map_memory(unsigned long pfn)
 {
 	phys_addr_t addr = PFN_PHYS(pfn);

arch/parisc/include/asm/string.h

@@ -8,19 +8,4 @@ extern void * memset(void *, int, size_t);
 #define __HAVE_ARCH_MEMCPY
 void * memcpy(void * dest,const void *src,size_t count);
 
-#define __HAVE_ARCH_STRLEN
-extern size_t strlen(const char *s);
-
-#define __HAVE_ARCH_STRCPY
-extern char *strcpy(char *dest, const char *src);
-
-#define __HAVE_ARCH_STRNCPY
-extern char *strncpy(char *dest, const char *src, size_t count);
-
-#define __HAVE_ARCH_STRCAT
-extern char *strcat(char *dest, const char *src);
-
-#define __HAVE_ARCH_MEMSET
-extern void *memset(void *, int, size_t);
-
 #endif

arch/parisc/kernel/parisc_ksyms.c

@@ -17,10 +17,6 @@
 
 #include <linux/string.h>
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strcpy);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strcat);
 
 #include <linux/atomic.h>
 EXPORT_SYMBOL(__xchg8);

arch/parisc/lib/Makefile

@@ -3,7 +3,7 @@
 # Makefile for parisc-specific library files
 #
 
-lib-y	:= lusercopy.o bitops.o checksum.o io.o memcpy.o \
-	   ucmpdi2.o delay.o string.o
+lib-y	:= lusercopy.o bitops.o checksum.o io.o memset.o memcpy.o \
+	   ucmpdi2.o delay.o
 
 obj-y	:= iomap.o

arch/parisc/lib/memset.c

@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <linux/types.h>
+#include <asm/string.h>
+
+#define OPSIZ (BITS_PER_LONG/8)
+typedef unsigned long op_t;
+
+void *
+memset (void *dstpp, int sc, size_t len)
+{
+  unsigned int c = sc;
+  long int dstp = (long int) dstpp;
+
+  if (len >= 8)
+    {
+      size_t xlen;
+      op_t cccc;
+
+      cccc = (unsigned char) c;
+      cccc |= cccc << 8;
+      cccc |= cccc << 16;
+      if (OPSIZ > 4)
+	/* Do the shift in two steps to avoid warning if long has 32 bits.  */
+	cccc |= (cccc << 16) << 16;
+
+      /* There are at least some bytes to set.
+	 No need to test for LEN == 0 in this alignment loop.  */
+      while (dstp % OPSIZ != 0)
+	{
+	  ((unsigned char *) dstp)[0] = c;
+	  dstp += 1;
+	  len -= 1;
+	}
+
+      /* Write 8 `op_t' per iteration until less than 8 `op_t' remain.  */
+      xlen = len / (OPSIZ * 8);
+      while (xlen > 0)
+	{
+	  ((op_t *) dstp)[0] = cccc;
+	  ((op_t *) dstp)[1] = cccc;
+	  ((op_t *) dstp)[2] = cccc;
+	  ((op_t *) dstp)[3] = cccc;
+	  ((op_t *) dstp)[4] = cccc;
+	  ((op_t *) dstp)[5] = cccc;
+	  ((op_t *) dstp)[6] = cccc;
+	  ((op_t *) dstp)[7] = cccc;
+	  dstp += 8 * OPSIZ;
+	  xlen -= 1;
+	}
+      len %= OPSIZ * 8;
+
+      /* Write 1 `op_t' per iteration until less than OPSIZ bytes remain.  */
+      xlen = len / OPSIZ;
+      while (xlen > 0)
+	{
+	  ((op_t *) dstp)[0] = cccc;
+	  dstp += OPSIZ;
+	  xlen -= 1;
+	}
+      len %= OPSIZ;
+    }
+
+  /* Write the last few bytes.  */
+  while (len > 0)
+    {
+      ((unsigned char *) dstp)[0] = c;
+      dstp += 1;
+      len -= 1;
+    }
+
+  return dstpp;
+}

arch/parisc/lib/string.S

@@ -1,136 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *    PA-RISC assembly string functions
- *
- *    Copyright (C) 2019 Helge Deller <deller@gmx.de>
- */
-
-#include <asm/assembly.h>
-#include <linux/linkage.h>
-
-	.section .text.hot
-	.level PA_ASM_LEVEL
-
-	t0 = r20
-	t1 = r21
-	t2 = r22
-
-ENTRY_CFI(strlen, frame=0,no_calls)
-	or,COND(<>) arg0,r0,ret0
-	b,l,n	.Lstrlen_null_ptr,r0
-	depwi	0,31,2,ret0
-	cmpb,COND(<>) arg0,ret0,.Lstrlen_not_aligned
-	ldw,ma	4(ret0),t0
-	cmpib,tr 0,r0,.Lstrlen_loop
-	uxor,nbz r0,t0,r0
-.Lstrlen_not_aligned:
-	uaddcm	arg0,ret0,t1
-	shladd	t1,3,r0,t1
-	mtsar	t1
-	depwi	-1,%sar,32,t0
-	uxor,nbz r0,t0,r0
-.Lstrlen_loop:
-	b,l,n	.Lstrlen_end_loop,r0
-	ldw,ma	4(ret0),t0
-	cmpib,tr 0,r0,.Lstrlen_loop
-	uxor,nbz r0,t0,r0
-.Lstrlen_end_loop:
-	extrw,u,<> t0,7,8,r0
-	addib,tr,n -3,ret0,.Lstrlen_out
-	extrw,u,<> t0,15,8,r0
-	addib,tr,n -2,ret0,.Lstrlen_out
-	extrw,u,<> t0,23,8,r0
-	addi	-1,ret0,ret0
-.Lstrlen_out:
-	bv r0(rp)
-	uaddcm ret0,arg0,ret0
-.Lstrlen_null_ptr:
-	bv,n r0(rp)
-ENDPROC_CFI(strlen)
-
-
-ENTRY_CFI(strcpy, frame=0,no_calls)
-	ldb	0(arg1),t0
-	stb	t0,0(arg0)
-	ldo	0(arg0),ret0
-	ldo	1(arg1),t1
-	cmpb,=	r0,t0,2f
-	ldo	1(arg0),t2
-1:	ldb	0(t1),arg1
-	stb	arg1,0(t2)
-	ldo	1(t1),t1
-	cmpb,<> r0,arg1,1b
-	ldo	1(t2),t2
-2:	bv,n	r0(rp)
-ENDPROC_CFI(strcpy)
-
-
-ENTRY_CFI(strncpy, frame=0,no_calls)
-	ldb	0(arg1),t0
-	stb	t0,0(arg0)
-	ldo	1(arg1),t1
-	ldo	0(arg0),ret0
-	cmpb,=	r0,t0,2f
-	ldo	1(arg0),arg1
-1:	ldo	-1(arg2),arg2
-	cmpb,COND(=),n r0,arg2,2f
-	ldb	0(t1),arg0
-	stb	arg0,0(arg1)
-	ldo	1(t1),t1
-	cmpb,<> r0,arg0,1b
-	ldo	1(arg1),arg1
-2:	bv,n	r0(rp)
-ENDPROC_CFI(strncpy)
-
-
-ENTRY_CFI(strcat, frame=0,no_calls)
-	ldb	0(arg0),t0
-	cmpb,=	t0,r0,2f
-	ldo	0(arg0),ret0
-	ldo	1(arg0),arg0
-1:	ldb	0(arg0),t1
-	cmpb,<>,n r0,t1,1b
-	ldo	1(arg0),arg0
-2:	ldb	0(arg1),t2
-	stb	t2,0(arg0)
-	ldo	1(arg0),arg0
-	ldb	0(arg1),t0
-	cmpb,<>	r0,t0,2b
-	ldo	1(arg1),arg1
-	bv,n	r0(rp)
-ENDPROC_CFI(strcat)
-
-
-ENTRY_CFI(memset, frame=0,no_calls)
-	copy	arg0,ret0
-	cmpb,COND(=) r0,arg0,4f
-	copy	arg0,t2
-	cmpb,COND(=) r0,arg2,4f
-	ldo	-1(arg2),arg3
-	subi	-1,arg3,t0
-	subi	0,t0,t1
-	cmpiclr,COND(>=) 0,t1,arg2
-	ldo	-1(t1),arg2
-	extru arg2,31,2,arg0
-2:	stb	arg1,0(t2)
-	ldo	1(t2),t2
-	addib,>= -1,arg0,2b
-	ldo	-1(arg3),arg3
-	cmpiclr,COND(<=) 4,arg2,r0
-	b,l,n	4f,r0
-#ifdef CONFIG_64BIT
-	depd,*	r0,63,2,arg2
-#else
-	depw	r0,31,2,arg2
-#endif
-	ldo	1(t2),t2
-3:	stb	arg1,-1(t2)
-	stb	arg1,0(t2)
-	stb	arg1,1(t2)
-	stb	arg1,2(t2)
-	addib,COND(>) -4,arg2,3b
-	ldo	4(t2),t2
-4:	bv,n	r0(rp)
-ENDPROC_CFI(memset)
-
-	.end

arch/powerpc/include/asm/book3s/32/kup.h

@@ -4,6 +4,8 @@
 
 #include <asm/bug.h>
 #include <asm/book3s/32/mmu-hash.h>
+#include <asm/mmu.h>
+#include <asm/synch.h>
 
 #ifndef __ASSEMBLY__
 
@@ -28,6 +30,15 @@ static inline void kuep_lock(void)
 		return;
 
 	update_user_segments(mfsr(0) | SR_NX);
+	/*
+	 * This isync() shouldn't be necessary as the kernel is not excepted to
+	 * run any instruction in userspace soon after the update of segments,
+	 * but hash based cores (at least G3) seem to exhibit a random
+	 * behaviour when the 'isync' is not there. 603 cores don't have this
+	 * behaviour so don't do the 'isync' as it saves several CPU cycles.
+	 */
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		isync();	/* Context sync required after mtsr() */
 }
 
 static inline void kuep_unlock(void)
@@ -36,6 +47,15 @@ static inline void kuep_unlock(void)
 		return;
 
 	update_user_segments(mfsr(0) & ~SR_NX);
+	/*
+	 * This isync() shouldn't be necessary as a 'rfi' will soon be executed
+	 * to return to userspace, but hash based cores (at least G3) seem to
+	 * exhibit a random behaviour when the 'isync' is not there. 603 cores
+	 * don't have this behaviour so don't do the 'isync' as it saves several
+	 * CPU cycles.
+	 */
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		isync();	/* Context sync required after mtsr() */
 }
 
 #ifdef CONFIG_PPC_KUAP

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

@@ -812,7 +812,6 @@ __start_interrupts:
  * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
  */
 EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
-1:
 	/* SCV 0 */
 	mr	r9,r13
 	GET_PACA(r13)
@@ -842,10 +841,12 @@ EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
 	b	system_call_vectored_sigill
 #endif
 	.endr
-2:
 EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
 
-SOFT_MASK_TABLE(1b, 2b) // Treat scv vectors as soft-masked, see comment above.
+// Treat scv vectors as soft-masked, see comment above.
+// Use absolute values rather than labels here, so they don't get relocated,
+// because this code runs unrelocated.
+SOFT_MASK_TABLE(0xc000000000003000, 0xc000000000004000)
 
 #ifdef CONFIG_RELOCATABLE
 TRAMP_VIRT_BEGIN(system_call_vectored_tramp)

arch/powerpc/mm/pageattr.c

@@ -18,16 +18,12 @@
 /*
  * Updates the attributes of a page in three steps:
  *
- * 1. invalidate the page table entry
- * 2. flush the TLB
- * 3. install the new entry with the updated attributes
- *
- * Invalidating the pte means there are situations where this will not work
- * when in theory it should.
- * For example:
- * - removing write from page whilst it is being executed
- * - setting a page read-only whilst it is being read by another CPU
+ * 1. take the page_table_lock
+ * 2. install the new entry with the updated attributes
+ * 3. flush the TLB
  *
+ * This sequence is safe against concurrent updates, and also allows updating the
+ * attributes of a page currently being executed or accessed.
  */
 static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 {
@@ -36,9 +32,7 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 
 	spin_lock(&init_mm.page_table_lock);
 
-	/* invalidate the PTE so it's safe to modify */
-	pte = ptep_get_and_clear(&init_mm, addr, ptep);
-	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	pte = ptep_get(ptep);
 
 	/* modify the PTE bits as desired, then apply */
 	switch (action) {
@@ -59,11 +53,14 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 		break;
 	}
 
-	set_pte_at(&init_mm, addr, ptep, pte);
+	pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0);
 
 	/* See ptesync comment in radix__set_pte_at() */
 	if (radix_enabled())
 		asm volatile("ptesync": : :"memory");
+
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
 	spin_unlock(&init_mm.page_table_lock);
 
 	return 0;

arch/powerpc/platforms/Kconfig.cputype

@@ -98,7 +98,7 @@ config PPC_BOOK3S_64
 	select PPC_HAVE_PMU_SUPPORT
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
-	select ARCH_ENABLE_PMD_SPLIT_PTLOCK
+	select ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_SUPPORTS_NUMA_BALANCING

arch/powerpc/sysdev/xive/common.c

@@ -1170,7 +1170,7 @@ out:
 	return ret;
 }
 
-static int __init xive_request_ipi(unsigned int cpu)
+static int xive_request_ipi(unsigned int cpu)
 {
 	struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)];
 	int ret;

arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts

@@ -14,6 +14,10 @@
 	model = "Microchip PolarFire-SoC Icicle Kit";
 	compatible = "microchip,mpfs-icicle-kit";
 
+	aliases {
+		ethernet0 = &emac1;
+	};
+
 	chosen {
 		stdout-path = &serial0;
 	};

arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi

@@ -317,7 +317,7 @@
 			reg = <0x0 0x20112000 0x0 0x2000>;
 			interrupt-parent = <&plic>;
 			interrupts = <70 71 72 73>;
-			mac-address = [00 00 00 00 00 00];
+			local-mac-address = [00 00 00 00 00 00];
 			clocks = <&clkcfg 5>, <&clkcfg 2>;
 			status = "disabled";
 			clock-names = "pclk", "hclk";

arch/riscv/kernel/ptrace.c

@@ -10,6 +10,7 @@
 #include <asm/ptrace.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
+#include <asm/switch_to.h>
 #include <linux/audit.h>
 #include <linux/ptrace.h>
 #include <linux/elf.h>
@@ -56,6 +57,9 @@ static int riscv_fpr_get(struct task_struct *target,
 {
 	struct __riscv_d_ext_state *fstate = &target->thread.fstate;
 
+	if (target == current)
+		fstate_save(current, task_pt_regs(current));
+
 	membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr));
 	membuf_store(&to, fstate->fcsr);
 	return membuf_zero(&to, 4);	// explicitly pad

arch/riscv/kernel/setup.c

@@ -229,8 +229,8 @@ static void __init init_resources(void)
 	}
 
 	/* Clean-up any unused pre-allocated resources */
-	mem_res_sz = (num_resources - res_idx + 1) * sizeof(*mem_res);
-	memblock_free(__pa(mem_res), mem_res_sz);
+	if (res_idx >= 0)
+		memblock_free(__pa(mem_res), (res_idx + 1) * sizeof(*mem_res));
 	return;
 
  error:

arch/s390/pci/pci.c

@@ -560,9 +560,12 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
 
 int pcibios_add_device(struct pci_dev *pdev)
 {
+	struct zpci_dev *zdev = to_zpci(pdev);
 	struct resource *res;
 	int i;
 
+	/* The pdev has a reference to the zdev via its bus */
+	zpci_zdev_get(zdev);
 	if (pdev->is_physfn)
 		pdev->no_vf_scan = 1;
 
@@ -582,7 +585,10 @@ int pcibios_add_device(struct pci_dev *pdev)
 
 void pcibios_release_device(struct pci_dev *pdev)
 {
+	struct zpci_dev *zdev = to_zpci(pdev);
+
 	zpci_unmap_resources(pdev);
+	zpci_zdev_put(zdev);
 }
 
 int pcibios_enable_device(struct pci_dev *pdev, int mask)

arch/s390/pci/pci_bus.h

@@ -22,6 +22,11 @@ static inline void zpci_zdev_put(struct zpci_dev *zdev)
 	kref_put(&zdev->kref, zpci_release_device);
 }
 
+static inline void zpci_zdev_get(struct zpci_dev *zdev)
+{
+	kref_get(&zdev->kref);
+}
+
 int zpci_alloc_domain(int domain);
 void zpci_free_domain(int domain);
 int zpci_setup_bus_resources(struct zpci_dev *zdev,

arch/x86/boot/compressed/efi_thunk_64.S

@@ -5,9 +5,8 @@
  * Early support for invoking 32-bit EFI services from a 64-bit kernel.
  *
  * Because this thunking occurs before ExitBootServices() we have to
- * restore the firmware's 32-bit GDT before we make EFI service calls,
- * since the firmware's 32-bit IDT is still currently installed and it
- * needs to be able to service interrupts.
+ * restore the firmware's 32-bit GDT and IDT before we make EFI service
+ * calls.
  *
  * On the plus side, we don't have to worry about mangling 64-bit
  * addresses into 32-bits because we're executing with an identity
@@ -39,7 +38,7 @@ SYM_FUNC_START(__efi64_thunk)
 	/*
 	 * Convert x86-64 ABI params to i386 ABI
 	 */
-	subq	$32, %rsp
+	subq	$64, %rsp
 	movl	%esi, 0x0(%rsp)
 	movl	%edx, 0x4(%rsp)
 	movl	%ecx, 0x8(%rsp)
@@ -49,14 +48,19 @@ SYM_FUNC_START(__efi64_thunk)
 	leaq	0x14(%rsp), %rbx
 	sgdt	(%rbx)
 
+	addq	$16, %rbx
+	sidt	(%rbx)
+
 	/*
-	 * Switch to gdt with 32-bit segments. This is the firmware GDT
-	 * that was installed when the kernel started executing. This
-	 * pointer was saved at the EFI stub entry point in head_64.S.
+	 * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT
+	 * and IDT that was installed when the kernel started executing. The
+	 * pointers were saved at the EFI stub entry point in head_64.S.
 	 *
 	 * Pass the saved DS selector to the 32-bit code, and use far return to
 	 * restore the saved CS selector.
 	 */
+	leaq	efi32_boot_idt(%rip), %rax
+	lidt	(%rax)
 	leaq	efi32_boot_gdt(%rip), %rax
 	lgdt	(%rax)
 
@@ -67,7 +71,7 @@ SYM_FUNC_START(__efi64_thunk)
 	pushq	%rax
 	lretq
 
-1:	addq	$32, %rsp
+1:	addq	$64, %rsp
 	movq	%rdi, %rax
 
 	pop	%rbx
@@ -128,10 +132,13 @@ SYM_FUNC_START_LOCAL(efi_enter32)
 
 	/*
 	 * Some firmware will return with interrupts enabled. Be sure to
-	 * disable them before we switch GDTs.
+	 * disable them before we switch GDTs and IDTs.
 	 */
 	cli
 
+	lidtl	(%ebx)
+	subl	$16, %ebx
+
 	lgdtl	(%ebx)
 
 	movl	%cr4, %eax
@@ -166,6 +173,11 @@ SYM_DATA_START(efi32_boot_gdt)
 	.quad	0
 SYM_DATA_END(efi32_boot_gdt)
 
+SYM_DATA_START(efi32_boot_idt)
+	.word	0
+	.quad	0
+SYM_DATA_END(efi32_boot_idt)
+
 SYM_DATA_START(efi32_boot_cs)
 	.word	0
 SYM_DATA_END(efi32_boot_cs)

arch/x86/boot/compressed/head_64.S

@@ -319,6 +319,9 @@ SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL)
 	movw	%cs, rva(efi32_boot_cs)(%ebp)
 	movw	%ds, rva(efi32_boot_ds)(%ebp)
 
+	/* Store firmware IDT descriptor */
+	sidtl	rva(efi32_boot_idt)(%ebp)
+
 	/* Disable paging */
 	movl	%cr0, %eax
 	btrl	$X86_CR0_PG_BIT, %eax

arch/x86/events/amd/ibs.c

@@ -90,6 +90,7 @@ struct perf_ibs {
 	unsigned long			offset_mask[1];
 	int				offset_max;
 	unsigned int			fetch_count_reset_broken : 1;
+	unsigned int			fetch_ignore_if_zero_rip : 1;
 	struct cpu_perf_ibs __percpu	*pcpu;
 
 	struct attribute		**format_attrs;
@@ -570,6 +571,7 @@ static struct perf_ibs perf_ibs_op = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
@@ -672,6 +674,10 @@ fail:
 	if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 	} else {
+		/* Workaround for erratum #1197 */
+		if (perf_ibs->fetch_ignore_if_zero_rip && !(ibs_data.regs[1]))
+			goto out;
+
 		set_linear_ip(&regs, ibs_data.regs[1]);
 		regs.flags |= PERF_EFLAGS_EXACT;
 	}
@@ -769,6 +775,9 @@ static __init void perf_event_ibs_init(void)
 	if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18)
 		perf_ibs_fetch.fetch_count_reset_broken = 1;
 
+	if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10)
+		perf_ibs_fetch.fetch_ignore_if_zero_rip = 1;
+
 	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
 
 	if (ibs_caps & IBS_CAPS_OPCNT) {

arch/x86/events/amd/power.c

@@ -213,6 +213,7 @@ static struct pmu pmu_class = {
 	.stop		= pmu_event_stop,
 	.read		= pmu_event_read,
 	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	.module		= THIS_MODULE,
 };
 
 static int power_cpu_exit(unsigned int cpu)

arch/x86/events/intel/pt.c

@@ -62,7 +62,7 @@ static struct pt_cap_desc {
 	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
 	PT_CAP(output_subsys,		0, CPUID_ECX, BIT(3)),
 	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
-	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
+	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x7),
 	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
 	PT_CAP(cycle_thresholds,	1, CPUID_EBX, 0xffff),
 	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),

arch/x86/events/intel/uncore_snbep.c

@@ -4811,7 +4811,7 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
 		return;
 
 	pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
-	addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
+	addr = ((resource_size_t)pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
 
 	pci_read_config_dword(pdev, mem_offset, &pci_dword);
 	addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;

arch/x86/include/asm/svm.h

@@ -184,6 +184,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define V_IGN_TPR_SHIFT 20
 #define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
 
+#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK)
+
 #define V_INTR_MASKING_SHIFT 24
 #define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
 

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -304,6 +304,12 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
 		m = &rr->d->mbm_local[rmid];
 		break;
+	default:
+		/*
+		 * Code would never reach here because an invalid
+		 * event id would fail the __rmid_read.
+		 */
+		return RMID_VAL_ERROR;
 	}
 
 	if (rr->first) {

arch/x86/kvm/svm/nested.c

@@ -158,6 +158,9 @@ void recalc_intercepts(struct vcpu_svm *svm)
 	/* If SMI is not intercepted, ignore guest SMI intercept as well  */
 	if (!intercept_smi)
 		vmcb_clr_intercept(c, INTERCEPT_SMI);
+
+	vmcb_set_intercept(c, INTERCEPT_VMLOAD);
+	vmcb_set_intercept(c, INTERCEPT_VMSAVE);
 }
 
 static void copy_vmcb_control_area(struct vmcb_control_area *dst,
@@ -503,7 +506,11 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 
 static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 {
-	const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
+	const u32 int_ctl_vmcb01_bits =
+		V_INTR_MASKING_MASK | V_GIF_MASK | V_GIF_ENABLE_MASK;
+
+	const u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK;
+
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	/*
@@ -535,8 +542,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 		vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;
 
 	svm->vmcb->control.int_ctl             =
-		(svm->nested.ctl.int_ctl & ~mask) |
-		(svm->vmcb01.ptr->control.int_ctl & mask);
+		(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
+		(svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
 
 	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
 	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;

arch/x86/kvm/svm/svm.c

@@ -1589,17 +1589,18 @@ static void svm_set_vintr(struct vcpu_svm *svm)
 
 static void svm_clear_vintr(struct vcpu_svm *svm)
 {
-	const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK;
 	svm_clr_intercept(svm, INTERCEPT_VINTR);
 
 	/* Drop int_ctl fields related to VINTR injection.  */
-	svm->vmcb->control.int_ctl &= mask;
+	svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
 	if (is_guest_mode(&svm->vcpu)) {
-		svm->vmcb01.ptr->control.int_ctl &= mask;
+		svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
 
 		WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) !=
 			(svm->nested.ctl.int_ctl & V_TPR_MASK));
-		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask;
+
+		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
+			V_IRQ_INJECTION_BITS_MASK;
 	}
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);

block/blk-core.c

@@ -122,7 +122,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->internal_tag = BLK_MQ_NO_TAG;
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
-	refcount_set(&rq->ref, 1);
 	blk_crypto_rq_set_defaults(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);

block/blk-flush.c

@@ -262,6 +262,11 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
+bool is_flush_rq(struct request *rq)
+{
+	return rq->end_io == flush_end_io;
+}
+
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
@@ -329,6 +334,14 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
+	/*
+	 * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one
+	 * implied in refcount_inc_not_zero() called from
+	 * blk_mq_find_and_get_req(), which orders WRITE/READ flush_rq->ref
+	 * and READ flush_rq->end_io
+	 */
+	smp_wmb();
+	refcount_set(&flush_rq->ref, 1);
 
 	blk_flush_queue_rq(flush_rq, false);
 }

block/blk-mq.c

@@ -911,7 +911,7 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 
 void blk_mq_put_rq_ref(struct request *rq)
 {
-	if (is_flush_rq(rq, rq->mq_hctx))
+	if (is_flush_rq(rq))
 		rq->end_io(rq, 0);
 	else if (refcount_dec_and_test(&rq->ref))
 		__blk_mq_free_request(rq);
@@ -923,34 +923,14 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	unsigned long *next = priv;
 
 	/*
-	 * Just do a quick check if it is expired before locking the request in
-	 * so we're not unnecessarilly synchronizing across CPUs.
-	 */
-	if (!blk_mq_req_expired(rq, next))
-		return true;
-
-	/*
-	 * We have reason to believe the request may be expired. Take a
-	 * reference on the request to lock this request lifetime into its
-	 * currently allocated context to prevent it from being reallocated in
-	 * the event the completion by-passes this timeout handler.
-	 *
-	 * If the reference was already released, then the driver beat the
-	 * timeout handler to posting a natural completion.
-	 */
-	if (!refcount_inc_not_zero(&rq->ref))
-		return true;
-
-	/*
-	 * The request is now locked and cannot be reallocated underneath the
-	 * timeout handler's processing. Re-verify this exact request is truly
-	 * expired; if it is not expired, then the request was completed and
-	 * reallocated as a new request.
+	 * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot
+	 * be reallocated underneath the timeout handler's processing, then
+	 * the expire check is reliable. If the request is not expired, then
+	 * it was completed and reallocated as a new request after returning
+	 * from blk_mq_check_expired().
 	 */
 	if (blk_mq_req_expired(rq, next))
 		blk_mq_rq_timed_out(rq, reserved);
-
-	blk_mq_put_rq_ref(rq);
 	return true;
 }
 

block/blk.h

@@ -44,11 +44,7 @@ static inline void __blk_get_queue(struct request_queue *q)
 	kobject_get(&q->kobj);
 }
 
-static inline bool
-is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
-{
-	return hctx->fq->flush_rq == req;
-}
+bool is_flush_rq(struct request *req);
 
 struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
 					      gfp_t flags);

block/mq-deadline.c

@@ -31,11 +31,6 @@
  */
 static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
 static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
-/*
- * Time after which to dispatch lower priority requests even if higher
- * priority requests are pending.
- */
-static const int aging_expire = 10 * HZ;
 static const int writes_starved = 2;    /* max times reads can starve a write */
 static const int fifo_batch = 16;       /* # of sequential requests treated as one
 				     by the above parameters. For throughput. */
@@ -103,7 +98,6 @@ struct deadline_data {
 	int writes_starved;
 	int front_merges;
 	u32 async_depth;
-	int aging_expire;
 
 	spinlock_t lock;
 	spinlock_t zone_lock;
@@ -369,11 +363,10 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 
 /*
  * deadline_dispatch_requests selects the best request according to
- * read/write expire, fifo_batch, etc and with a start time <= @latest.
+ * read/write expire, fifo_batch, etc
  */
 static struct request *__dd_dispatch_request(struct deadline_data *dd,
-					     struct dd_per_prio *per_prio,
-					     u64 latest_start_ns)
+					     struct dd_per_prio *per_prio)
 {
 	struct request *rq, *next_rq;
 	enum dd_data_dir data_dir;
@@ -385,8 +378,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 	if (!list_empty(&per_prio->dispatch)) {
 		rq = list_first_entry(&per_prio->dispatch, struct request,
 				      queuelist);
-		if (rq->start_time_ns > latest_start_ns)
-			return NULL;
 		list_del_init(&rq->queuelist);
 		goto done;
 	}
@@ -464,8 +455,6 @@ dispatch_find_request:
 	dd->batching = 0;
 
 dispatch_request:
-	if (rq->start_time_ns > latest_start_ns)
-		return NULL;
 	/*
 	 * rq is the selected appropriate request.
 	 */
@@ -494,32 +483,15 @@ done:
 static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
-	const u64 now_ns = ktime_get_ns();
-	struct request *rq = NULL;
+	struct request *rq;
 	enum dd_prio prio;
 
 	spin_lock(&dd->lock);
-	/*
-	 * Start with dispatching requests whose deadline expired more than
-	 * aging_expire jiffies ago.
-	 */
-	for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) {
-		rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns -
-					   jiffies_to_nsecs(dd->aging_expire));
-		if (rq)
-			goto unlock;
-	}
-	/*
-	 * Next, dispatch requests in priority order. Ignore lower priority
-	 * requests if any higher priority requests are pending.
-	 */
 	for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
-		rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns);
-		if (rq || dd_queued(dd, prio))
+		rq = __dd_dispatch_request(dd, &dd->per_prio[prio]);
+		if (rq)
 			break;
 	}
-
-unlock:
 	spin_unlock(&dd->lock);
 
 	return rq;
@@ -620,7 +592,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
 	dd->front_merges = 1;
 	dd->last_dir = DD_WRITE;
 	dd->fifo_batch = fifo_batch;
-	dd->aging_expire = aging_expire;
 	spin_lock_init(&dd->lock);
 	spin_lock_init(&dd->zone_lock);
 
@@ -711,6 +682,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	prio = ioprio_class_to_prio[ioprio_class];
 	dd_count(dd, inserted, prio);
+	rq->elv.priv[0] = (void *)(uintptr_t)1;
 
 	if (blk_mq_sched_try_insert_merge(q, rq, &free)) {
 		blk_mq_free_requests(&free);
@@ -759,12 +731,10 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 	spin_unlock(&dd->lock);
 }
 
-/*
- * Nothing to do here. This is defined only to ensure that .finish_request
- * method is called upon request completion.
- */
+/* Callback from inside blk_mq_rq_ctx_init(). */
 static void dd_prepare_request(struct request *rq)
 {
+	rq->elv.priv[0] = NULL;
 }
 
 /*
@@ -791,7 +761,14 @@ static void dd_finish_request(struct request *rq)
 	const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
 	struct dd_per_prio *per_prio = &dd->per_prio[prio];
 
-	dd_count(dd, completed, prio);
+	/*
+	 * The block layer core may call dd_finish_request() without having
+	 * called dd_insert_requests(). Hence only update statistics for
+	 * requests for which dd_insert_requests() has been called. See also
+	 * blk_mq_request_bypass_insert().
+	 */
+	if (rq->elv.priv[0])
+		dd_count(dd, completed, prio);
 
 	if (blk_queue_is_zoned(q)) {
 		unsigned long flags;
@@ -836,7 +813,6 @@ static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 #define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR))
 SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]);
 SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]);
-SHOW_JIFFIES(deadline_aging_expire_show, dd->aging_expire);
 SHOW_INT(deadline_writes_starved_show, dd->writes_starved);
 SHOW_INT(deadline_front_merges_show, dd->front_merges);
 SHOW_INT(deadline_async_depth_show, dd->front_merges);
@@ -866,7 +842,6 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
 	STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies)
 STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX);
 STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX);
-STORE_JIFFIES(deadline_aging_expire_store, &dd->aging_expire, 0, INT_MAX);
 STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX);
 STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1);
 STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX);
@@ -885,7 +860,6 @@ static struct elv_fs_entry deadline_attrs[] = {
 	DD_ATTR(front_merges),
 	DD_ATTR(async_depth),
 	DD_ATTR(fifo_batch),
-	DD_ATTR(aging_expire),
 	__ATTR_NULL
 };
 

crypto/Kconfig

@@ -1768,7 +1768,7 @@ config CRYPTO_DRBG_HMAC
 	bool
 	default y
 	select CRYPTO_HMAC
-	select CRYPTO_SHA256
+	select CRYPTO_SHA512
 
 config CRYPTO_DRBG_HASH
 	bool "Enable Hash DRBG"

drivers/acpi/prmt.c

@@ -292,6 +292,12 @@ void __init init_prmt(void)
 	int mc = acpi_table_parse_entries(ACPI_SIG_PRMT, sizeof(struct acpi_table_prmt) +
 					  sizeof (struct acpi_table_prmt_header),
 					  0, acpi_parse_prmt, 0);
+	/*
+	 * Return immediately if PRMT table is not present or no PRM module found.
+	 */
+	if (mc <= 0)
+		return;
+
 	pr_info("PRM: found %u modules\n", mc);
 
 	status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT,

drivers/acpi/x86/s2idle.c

@@ -452,7 +452,7 @@ int acpi_s2idle_prepare_late(void)
 	if (lps0_dsm_func_mask_microsoft > 0) {
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
-		acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_EXIT,
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_ENTRY,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
@@ -479,7 +479,7 @@ void acpi_s2idle_restore_early(void)
 	if (lps0_dsm_func_mask_microsoft > 0) {
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
-		acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_ENTRY,
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_EXIT,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);
 		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON,
 				lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft);

drivers/base/power/domain.c

@@ -435,7 +435,7 @@ static void genpd_restore_performance_state(struct device *dev,
 int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 {
 	struct generic_pm_domain *genpd;
-	int ret;
+	int ret = 0;
 
 	genpd = dev_to_genpd_safe(dev);
 	if (!genpd)
@@ -446,7 +446,13 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 		return -EINVAL;
 
 	genpd_lock(genpd);
-	ret = genpd_set_performance_state(dev, state);
+	if (pm_runtime_suspended(dev)) {
+		dev_gpd_data(dev)->rpm_pstate = state;
+	} else {
+		ret = genpd_set_performance_state(dev, state);
+		if (!ret)
+			dev_gpd_data(dev)->rpm_pstate = 0;
+	}
 	genpd_unlock(genpd);
 
 	return ret;

drivers/block/Kconfig

@@ -213,7 +213,7 @@ config BLK_DEV_LOOP_MIN_COUNT
 	  dynamically allocated with the /dev/loop-control interface.
 
 config BLK_DEV_CRYPTOLOOP
-	tristate "Cryptoloop Support"
+	tristate "Cryptoloop Support (DEPRECATED)"
 	select CRYPTO
 	select CRYPTO_CBC
 	depends on BLK_DEV_LOOP
@@ -225,7 +225,7 @@ config BLK_DEV_CRYPTOLOOP
 	  WARNING: This device is not safe for journaled file systems like
 	  ext3 or Reiserfs. Please use the Device Mapper crypto module
 	  instead, which can be configured to be on-disk compatible with the
-	  cryptoloop device.
+	  cryptoloop device.  cryptoloop support will be removed in Linux 5.16.
 
 source "drivers/block/drbd/Kconfig"
 

drivers/block/cryptoloop.c

@@ -189,6 +189,8 @@ init_cryptoloop(void)
 
 	if (rc)
 		printk(KERN_ERR "cryptoloop: loop_register_transfer failed\n");
+	else
+		pr_warn("the cryptoloop driver has been deprecated and will be removed in in Linux 5.16\n");
 	return rc;
 }
 

drivers/block/paride/pd.c

@@ -892,7 +892,7 @@ static void pd_probe_drive(struct pd_unit *disk)
 		return;
 
 	p = blk_mq_alloc_disk(&disk->tag_set, disk);
-	if (!p) {
+	if (IS_ERR(p)) {
 		blk_mq_free_tag_set(&disk->tag_set);
 		return;
 	}

drivers/block/virtio_blk.c

@@ -692,6 +692,28 @@ static const struct blk_mq_ops virtio_mq_ops = {
 static unsigned int virtblk_queue_depth;
 module_param_named(queue_depth, virtblk_queue_depth, uint, 0444);
 
+static int virtblk_validate(struct virtio_device *vdev)
+{
+	u32 blk_size;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	if (!virtio_has_feature(vdev, VIRTIO_BLK_F_BLK_SIZE))
+		return 0;
+
+	blk_size = virtio_cread32(vdev,
+			offsetof(struct virtio_blk_config, blk_size));
+
+	if (blk_size < SECTOR_SIZE || blk_size > PAGE_SIZE)
+		__virtio_clear_bit(vdev, VIRTIO_BLK_F_BLK_SIZE);
+
+	return 0;
+}
+
 static int virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
@@ -703,12 +725,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	u8 physical_block_exp, alignment_offset;
 	unsigned int queue_depth;
 
-	if (!vdev->config->get) {
-		dev_err(&vdev->dev, "%s failure: config access disabled\n",
-			__func__);
-		return -EINVAL;
-	}
-
 	err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
 			     GFP_KERNEL);
 	if (err < 0)
@@ -823,6 +839,14 @@ static int virtblk_probe(struct virtio_device *vdev)
 	else
 		blk_size = queue_logical_block_size(q);
 
+	if (unlikely(blk_size < SECTOR_SIZE || blk_size > PAGE_SIZE)) {
+		dev_err(&vdev->dev,
+			"block size is changed unexpectedly, now is %u\n",
+			blk_size);
+		err = -EINVAL;
+		goto err_cleanup_disk;
+	}
+
 	/* Use topology information if available */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, physical_block_exp,
@@ -881,6 +905,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 	device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);
 	return 0;
 
+err_cleanup_disk:
+	blk_cleanup_disk(vblk->disk);
 out_free_tags:
 	blk_mq_free_tag_set(&vblk->tag_set);
 out_free_vq:
@@ -983,6 +1009,7 @@ static struct virtio_driver virtio_blk = {
 	.driver.name			= KBUILD_MODNAME,
 	.driver.owner			= THIS_MODULE,
 	.id_table			= id_table,
+	.validate			= virtblk_validate,
 	.probe				= virtblk_probe,
 	.remove				= virtblk_remove,
 	.config_changed			= virtblk_config_changed,

drivers/bus/mhi/core/internal.h

@@ -682,7 +682,7 @@ void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl,
 		      struct image_info *img_info);
 void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl);
 int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
-			struct mhi_chan *mhi_chan, unsigned int flags);
+			struct mhi_chan *mhi_chan);
 int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl,
 		       struct mhi_chan *mhi_chan);
 void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl,

drivers/bus/mhi/core/main.c

@@ -1430,7 +1430,7 @@ exit_unprepare_channel:
 }
 
 int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
-			struct mhi_chan *mhi_chan, unsigned int flags)
+			struct mhi_chan *mhi_chan)
 {
 	int ret = 0;
 	struct device *dev = &mhi_chan->mhi_dev->dev;
@@ -1455,9 +1455,6 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
 	if (ret)
 		goto error_pm_state;
 
-	if (mhi_chan->dir == DMA_FROM_DEVICE)
-		mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS);
-	
 	/* Pre-allocate buffer for xfer ring */
 	if (mhi_chan->pre_alloc) {
 		int nr_el = get_nr_avail_ring_elements(mhi_cntrl,
@@ -1613,7 +1610,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan)
 }
 
 /* Move channel to start state */
-int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags)
+int mhi_prepare_for_transfer(struct mhi_device *mhi_dev)
 {
 	int ret, dir;
 	struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl;
@@ -1624,7 +1621,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags)
 		if (!mhi_chan)
 			continue;
 
-		ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags);
+		ret = mhi_prepare_channel(mhi_cntrl, mhi_chan);
 		if (ret)
 			goto error_open_chan;
 	}

drivers/bus/ti-sysc.c

@@ -3097,8 +3097,10 @@ static int sysc_probe(struct platform_device *pdev)
 		return error;
 
 	error = sysc_check_active_timer(ddata);
-	if (error == -EBUSY)
+	if (error == -ENXIO)
 		ddata->reserved = true;
+	else if (error)
+		return error;
 
 	error = sysc_get_clocks(ddata);
 	if (error)

drivers/clk/imx/clk-imx6q.c

@@ -974,6 +974,6 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 			       hws[IMX6QDL_CLK_PLL3_USB_OTG]->clk);
 	}
 
-	imx_register_uart_clocks(1);
+	imx_register_uart_clocks(2);
 }
 CLK_OF_DECLARE(imx6q, "fsl,imx6q-ccm", imx6q_clocks_init);

drivers/clk/qcom/gdsc.c

@@ -357,27 +357,43 @@ static int gdsc_init(struct gdsc *sc)
 	if (on < 0)
 		return on;
 
-	/*
-	 * Votable GDSCs can be ON due to Vote from other masters.
-	 * If a Votable GDSC is ON, make sure we have a Vote.
-	 */
-	if ((sc->flags & VOTABLE) && on)
+	if (on) {
+		/* The regulator must be on, sync the kernel state */
+		if (sc->rsupply) {
+			ret = regulator_enable(sc->rsupply);
+			if (ret < 0)
+				return ret;
+		}
+
+		/*
+		 * Votable GDSCs can be ON due to Vote from other masters.
+		 * If a Votable GDSC is ON, make sure we have a Vote.
+		 */
+		if (sc->flags & VOTABLE) {
+			ret = regmap_update_bits(sc->regmap, sc->gdscr,
+						 SW_COLLAPSE_MASK, val);
+			if (ret)
+				return ret;
+		}
+
+		/* Turn on HW trigger mode if supported */
+		if (sc->flags & HW_CTRL) {
+			ret = gdsc_hwctrl(sc, true);
+			if (ret < 0)
+				return ret;
+		}
+
+		/*
+		 * Make sure the retain bit is set if the GDSC is already on,
+		 * otherwise we end up turning off the GDSC and destroying all
+		 * the register contents that we thought we were saving.
+		 */
+		if (sc->flags & RETAIN_FF_ENABLE)
+			gdsc_retain_ff_on(sc);
+	} else if (sc->flags & ALWAYS_ON) {
+		/* If ALWAYS_ON GDSCs are not ON, turn them ON */
 		gdsc_enable(&sc->pd);
-
-	/*
-	 * Make sure the retain bit is set if the GDSC is already on, otherwise
-	 * we end up turning off the GDSC and destroying all the register
-	 * contents that we thought we were saving.
-	 */
-	if ((sc->flags & RETAIN_FF_ENABLE) && on)
-		gdsc_retain_ff_on(sc);
-
-	/* If ALWAYS_ON GDSCs are not ON, turn them ON */
-	if (sc->flags & ALWAYS_ON) {
-		if (!on)
-			gdsc_enable(&sc->pd);
 		on = true;
-		sc->pd.flags |= GENPD_FLAG_ALWAYS_ON;
 	}
 
 	if (on || (sc->pwrsts & PWRSTS_RET))
@@ -385,6 +401,8 @@ static int gdsc_init(struct gdsc *sc)
 	else
 		gdsc_clear_mem_on(sc);
 
+	if (sc->flags & ALWAYS_ON)
+		sc->pd.flags |= GENPD_FLAG_ALWAYS_ON;
 	if (!sc->pd.power_off)
 		sc->pd.power_off = gdsc_disable;
 	if (!sc->pd.power_on)

drivers/clk/renesas/rcar-usb2-clock-sel.c

@@ -187,7 +187,7 @@ static int rcar_usb2_clock_sel_probe(struct platform_device *pdev)
 	init.ops = &usb2_clock_sel_clock_ops;
 	priv->hw.init = &init;
 
-	ret = devm_clk_hw_register(NULL, &priv->hw);
+	ret = devm_clk_hw_register(dev, &priv->hw);
 	if (ret)
 		goto pm_put;
 

drivers/cpufreq/armada-37xx-cpufreq.c

@@ -104,7 +104,11 @@ struct armada_37xx_dvfs {
 };
 
 static struct armada_37xx_dvfs armada_37xx_dvfs[] = {
-	{.cpu_freq_max = 1200*1000*1000, .divider = {1, 2, 4, 6} },
+	/*
+	 * The cpufreq scaling for 1.2 GHz variant of the SOC is currently
+	 * unstable because we do not know how to configure it properly.
+	 */
+	/* {.cpu_freq_max = 1200*1000*1000, .divider = {1, 2, 4, 6} }, */
 	{.cpu_freq_max = 1000*1000*1000, .divider = {1, 2, 4, 5} },
 	{.cpu_freq_max = 800*1000*1000,  .divider = {1, 2, 3, 4} },
 	{.cpu_freq_max = 600*1000*1000,  .divider = {2, 4, 5, 6} },

drivers/cpufreq/cpufreq-dt-platdev.c

@@ -139,7 +139,9 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,qcs404", },
 	{ .compatible = "qcom,sc7180", },
 	{ .compatible = "qcom,sc7280", },
+	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sdm845", },
+	{ .compatible = "qcom,sm8150", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },

drivers/cpufreq/scmi-cpufreq.c

@@ -134,7 +134,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	}
 
 	if (!zalloc_cpumask_var(&opp_shared_cpus, GFP_KERNEL))
-		ret = -ENOMEM;
+		return -ENOMEM;
 
 	/* Obtain CPUs that share SCMI performance controls */
 	ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus);

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

@@ -1040,7 +1040,7 @@ void amdgpu_acpi_detect(void)
  */
 bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
 {
-#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_PM_SLEEP)
+#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_SUSPEND)
 	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
 		if (adev->flags & AMD_IS_APU)
 			return pm_suspend_target_state == PM_SUSPEND_TO_IDLE;

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

@@ -2777,12 +2777,11 @@ static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, gfx.gfx_off_delay_work.work);
 
-	mutex_lock(&adev->gfx.gfx_off_mutex);
-	if (!adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true))
-			adev->gfx.gfx_off_state = true;
-	}
-	mutex_unlock(&adev->gfx.gfx_off_mutex);
+	WARN_ON_ONCE(adev->gfx.gfx_off_state);
+	WARN_ON_ONCE(adev->gfx.gfx_off_req_count);
+
+	if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true))
+		adev->gfx.gfx_off_state = true;
 }
 
 /**

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

@@ -563,24 +563,38 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 	mutex_lock(&adev->gfx.gfx_off_mutex);
 
-	if (!enable)
-		adev->gfx.gfx_off_req_count++;
-	else if (adev->gfx.gfx_off_req_count > 0)
+	if (enable) {
+		/* If the count is already 0, it means there's an imbalance bug somewhere.
+		 * Note that the bug may be in a different caller than the one which triggers the
+		 * WARN_ON_ONCE.
+		 */
+		if (WARN_ON_ONCE(adev->gfx.gfx_off_req_count == 0))
+			goto unlock;
+
 		adev->gfx.gfx_off_req_count--;
 
-	if (enable && !adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
-	} else if (!enable && adev->gfx.gfx_off_state) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
-			adev->gfx.gfx_off_state = false;
+		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+	} else {
+		if (adev->gfx.gfx_off_req_count == 0) {
+			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
 
-			if (adev->gfx.funcs->init_spm_golden) {
-				dev_dbg(adev->dev, "GFXOFF is disabled, re-init SPM golden settings\n");
-				amdgpu_gfx_init_spm_golden(adev);
+			if (adev->gfx.gfx_off_state &&
+			    !amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
+				adev->gfx.gfx_off_state = false;
+
+				if (adev->gfx.funcs->init_spm_golden) {
+					dev_dbg(adev->dev,
+						"GFXOFF is disabled, re-init SPM golden settings\n");
+					amdgpu_gfx_init_spm_golden(adev);
+				}
 			}
 		}
+
+		adev->gfx.gfx_off_req_count++;
 	}
 
+unlock:
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
 

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

@@ -920,11 +920,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			return -EINVAL;
 	}
 
-	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
-	 * See function amdgpu_display_supported_domains()
-	 */
-	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
-
 	if (bo->tbo.pin_count) {
 		uint32_t mem_type = bo->tbo.resource->mem_type;
 		uint32_t mem_flags = bo->tbo.resource->placement;
@@ -949,6 +944,11 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return 0;
 	}
 
+	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
+	 * See function amdgpu_display_supported_domains()
+	 */
+	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
+
 	if (bo->tbo.base.import_attach)
 		dma_buf_pin(bo->tbo.base.import_attach);
 

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

@@ -3026,6 +3026,14 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 	pr_debug("svms 0x%p [0x%llx 0x%llx] nattr 0x%x\n", &p->svms, start,
 		 start + size - 1, nattr);
 
+	/* Flush pending deferred work to avoid racing with deferred actions from
+	 * previous memory map changes (e.g. munmap). Concurrent memory map changes
+	 * can still race with get_attr because we don't hold the mmap lock. But that
+	 * would be a race condition in the application anyway, and undefined
+	 * behaviour is acceptable in that case.
+	 */
+	flush_work(&p->svms.deferred_list_work);
+
 	mmap_read_lock(mm);
 	if (!svm_range_is_valid(mm, start, size)) {
 		pr_debug("invalid range\n");

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

@@ -1530,6 +1530,12 @@ void dc_z10_restore(struct dc *dc)
 	if (dc->hwss.z10_restore)
 		dc->hwss.z10_restore(dc);
 }
+
+void dc_z10_save_init(struct dc *dc)
+{
+	if (dc->hwss.z10_save_init)
+		dc->hwss.z10_save_init(dc);
+}
 #endif
 /*
  * Applies given context to HW and copy it into current context.

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

@@ -47,6 +47,9 @@ int dc_setup_system_context(struct dc *dc, struct dc_phy_addr_space_config *pa_c
 		 */
 		memcpy(&dc->vm_pa_config, pa_config, sizeof(struct dc_phy_addr_space_config));
 		dc->vm_pa_config.valid = true;
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		dc_z10_save_init(dc);
+#endif
 	}
 
 	return num_vmids;

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

@@ -1338,6 +1338,7 @@ void dc_hardware_release(struct dc *dc);
 bool dc_set_psr_allow_active(struct dc *dc, bool enable);
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 void dc_z10_restore(struct dc *dc);
+void dc_z10_save_init(struct dc *dc);
 #endif
 
 bool dc_enable_dmub_notifications(struct dc *dc);

drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c

@@ -1622,106 +1622,12 @@ static void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b
 	dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30);
 }
 
-static void calculate_wm_set_for_vlevel(
-		int vlevel,
-		struct wm_range_table_entry *table_entry,
-		struct dcn_watermarks *wm_set,
-		struct display_mode_lib *dml,
-		display_e2e_pipe_params_st *pipes,
-		int pipe_cnt)
-{
-	double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us;
-
-	ASSERT(vlevel < dml->soc.num_states);
-	/* only pipe 0 is read for voltage and dcf/soc clocks */
-	pipes[0].clks_cfg.voltage = vlevel;
-	pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz;
-	pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz;
-
-	dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us;
-	dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us;
-	dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us;
-
-	wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000;
-	wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000;
-	wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000;
-	wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000;
-	wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000;
-	wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000;
-	wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000;
-	wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000;
-	dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached;
-
-}
-
-static void dcn301_calculate_wm_and_dlg(
-		struct dc *dc, struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		int pipe_cnt,
-		int vlevel_req)
-{
-	int i, pipe_idx;
-	int vlevel, vlevel_max;
-	struct wm_range_table_entry *table_entry;
-	struct clk_bw_params *bw_params = dc->clk_mgr->bw_params;
-
-	ASSERT(bw_params);
-
-	vlevel_max = bw_params->clk_table.num_entries - 1;
-
-	/* WM Set D */
-	table_entry = &bw_params->wm_table.entries[WM_D];
-	if (table_entry->wm_type == WM_TYPE_RETRAINING)
-		vlevel = 0;
-	else
-		vlevel = vlevel_max;
-	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d,
-						&context->bw_ctx.dml, pipes, pipe_cnt);
-	/* WM Set C */
-	table_entry = &bw_params->wm_table.entries[WM_C];
-	vlevel = min(max(vlevel_req, 2), vlevel_max);
-	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c,
-						&context->bw_ctx.dml, pipes, pipe_cnt);
-	/* WM Set B */
-	table_entry = &bw_params->wm_table.entries[WM_B];
-	vlevel = min(max(vlevel_req, 1), vlevel_max);
-	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b,
-						&context->bw_ctx.dml, pipes, pipe_cnt);
-
-	/* WM Set A */
-	table_entry = &bw_params->wm_table.entries[WM_A];
-	vlevel = min(vlevel_req, vlevel_max);
-	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a,
-						&context->bw_ctx.dml, pipes, pipe_cnt);
-
-	for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
-		if (!context->res_ctx.pipe_ctx[i].stream)
-			continue;
-
-		pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt);
-		pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
-
-		if (dc->config.forced_clocks) {
-			pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz;
-			pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz;
-		}
-		if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000)
-			pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0;
-		if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000)
-			pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0;
-
-		pipe_idx++;
-	}
-
-	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
-}
-
 static struct resource_funcs dcn301_res_pool_funcs = {
 	.destroy = dcn301_destroy_resource_pool,
 	.link_enc_create = dcn301_link_encoder_create,
 	.panel_cntl_create = dcn301_panel_cntl_create,
 	.validate_bandwidth = dcn30_validate_bandwidth,
-	.calculate_wm_and_dlg = dcn301_calculate_wm_and_dlg,
+	.calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg,
 	.update_soc_for_wm_a = dcn30_update_soc_for_wm_a,
 	.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,

drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c

@@ -404,6 +404,18 @@ void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx)
 			&pipe_ctx->stream_res.encoder_info_frame);
 	}
 }
+void dcn31_z10_save_init(struct dc *dc)
+{
+	union dmub_rb_cmd cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.dcn_restore.header.type = DMUB_CMD__IDLE_OPT;
+	cmd.dcn_restore.header.sub_type = DMUB_CMD__IDLE_OPT_DCN_SAVE_INIT;
+
+	dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
+	dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
+}
 
 void dcn31_z10_restore(struct dc *dc)
 {

drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h

@@ -44,6 +44,7 @@ void dcn31_enable_power_gating_plane(
 void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx);
 
 void dcn31_z10_restore(struct dc *dc);
+void dcn31_z10_save_init(struct dc *dc);
 
 void dcn31_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on);
 int dcn31_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config);

drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c

@@ -97,6 +97,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 	.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
 	.set_pipe = dcn21_set_pipe,
 	.z10_restore = dcn31_z10_restore,
+	.z10_save_init = dcn31_z10_save_init,
 	.is_abm_supported = dcn31_is_abm_supported,
 	.set_disp_pattern_generator = dcn30_set_disp_pattern_generator,
 	.update_visual_confirm_color = dcn20_update_visual_confirm_color,

drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h

@@ -237,6 +237,7 @@ struct hw_sequencer_funcs {
 			int width, int height, int offset);
 
 	void (*z10_restore)(struct dc *dc);
+	void (*z10_save_init)(struct dc *dc);
 
 	void (*update_visual_confirm_color)(struct dc *dc,
 			struct pipe_ctx *pipe_ctx,

drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h

@@ -856,6 +856,11 @@ enum dmub_cmd_idle_opt_type {
 	 * DCN hardware restore.
 	 */
 	DMUB_CMD__IDLE_OPT_DCN_RESTORE = 0,
+
+	/**
+	 * DCN hardware save.
+	 */
+	DMUB_CMD__IDLE_OPT_DCN_SAVE_INIT = 1
 };
 
 /**

drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c

@@ -5127,6 +5127,13 @@ static int vega10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	return size;
 }
 
+static bool vega10_get_power_profile_mode_quirks(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (adev->pdev->device == 0x6860);
+}
+
 static int vega10_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint32_t size)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
@@ -5163,9 +5170,15 @@ static int vega10_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui
 	}
 
 out:
-	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
+	if (vega10_get_power_profile_mode_quirks(hwmgr))
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
+						1 << power_profile_mode,
+						NULL);
+	else
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
 						(!power_profile_mode) ? 0 : 1 << (power_profile_mode - 1),
 						NULL);
+
 	hwmgr->power_profile_mode = power_profile_mode;
 
 	return 0;

drivers/gpu/drm/drm_ioc32.c

@@ -855,8 +855,6 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	req.request.sequence = req32.request.sequence;
 	req.request.signal = req32.request.signal;
 	err = drm_ioctl_kernel(file, drm_wait_vblank_ioctl, &req, DRM_UNLOCKED);
-	if (err)
-		return err;
 
 	req32.reply.type = req.reply.type;
 	req32.reply.sequence = req.reply.sequence;
@@ -865,7 +863,7 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	if (copy_to_user(argp, &req32, sizeof(req32)))
 		return -EFAULT;
 
-	return 0;
+	return err;
 }
 
 #if defined(CONFIG_X86)

drivers/gpu/drm/i915/display/intel_ddi.c

@@ -2463,6 +2463,15 @@ static void intel_ddi_power_up_lanes(struct intel_encoder *encoder,
 	}
 }
 
+/* Splitter enable for eDP MSO is limited to certain pipes. */
+static u8 intel_ddi_splitter_pipe_mask(struct drm_i915_private *i915)
+{
+	if (IS_ALDERLAKE_P(i915))
+		return BIT(PIPE_A) | BIT(PIPE_B);
+	else
+		return BIT(PIPE_A);
+}
+
 static void intel_ddi_mso_get_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config)
 {
@@ -2480,8 +2489,7 @@ static void intel_ddi_mso_get_config(struct intel_encoder *encoder,
 	if (!pipe_config->splitter.enable)
 		return;
 
-	/* Splitter enable is supported for pipe A only. */
-	if (drm_WARN_ON(&i915->drm, pipe != PIPE_A)) {
+	if (drm_WARN_ON(&i915->drm, !(intel_ddi_splitter_pipe_mask(i915) & BIT(pipe)))) {
 		pipe_config->splitter.enable = false;
 		return;
 	}
@@ -2513,10 +2521,6 @@ static void intel_ddi_mso_configure(const struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->splitter.enable) {
-		/* Splitter enable is supported for pipe A only. */
-		if (drm_WARN_ON(&i915->drm, pipe != PIPE_A))
-			return;
-
 		dss1 |= SPLITTER_ENABLE;
 		dss1 |= OVERLAP_PIXELS(crtc_state->splitter.pixel_overlap);
 		if (crtc_state->splitter.link_count == 2)
@@ -4743,12 +4747,8 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 
 		dig_port->hpd_pulse = intel_dp_hpd_pulse;
 
-		/* Splitter enable for eDP MSO is limited to certain pipes. */
-		if (dig_port->dp.mso_link_count) {
-			encoder->pipe_mask = BIT(PIPE_A);
-			if (IS_ALDERLAKE_P(dev_priv))
-				encoder->pipe_mask |= BIT(PIPE_B);
-		}
+		if (dig_port->dp.mso_link_count)
+			encoder->pipe_mask = intel_ddi_splitter_pipe_mask(dev_priv);
 	}
 
 	/* In theory we don't need the encoder->type check, but leave it just in

drivers/gpu/drm/i915/display/intel_display_power.c

@@ -6387,13 +6387,13 @@ void intel_display_power_suspend_late(struct drm_i915_private *i915)
 	if (DISPLAY_VER(i915) >= 11 || IS_GEMINILAKE(i915) ||
 	    IS_BROXTON(i915)) {
 		bxt_enable_dc9(i915);
-		/* Tweaked Wa_14010685332:icp,jsp,mcc */
-		if (INTEL_PCH_TYPE(i915) >= PCH_ICP && INTEL_PCH_TYPE(i915) <= PCH_MCC)
-			intel_de_rmw(i915, SOUTH_CHICKEN1,
-				     SBCLK_RUN_REFCLK_DIS, SBCLK_RUN_REFCLK_DIS);
 	} else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) {
 		hsw_enable_pc8(i915);
 	}
+
+	/* Tweaked Wa_14010685332:cnp,icp,jsp,mcc,tgp,adp */
+	if (INTEL_PCH_TYPE(i915) >= PCH_CNP && INTEL_PCH_TYPE(i915) < PCH_DG1)
+		intel_de_rmw(i915, SOUTH_CHICKEN1, SBCLK_RUN_REFCLK_DIS, SBCLK_RUN_REFCLK_DIS);
 }
 
 void intel_display_power_resume_early(struct drm_i915_private *i915)
@@ -6402,13 +6402,13 @@ void intel_display_power_resume_early(struct drm_i915_private *i915)
 	    IS_BROXTON(i915)) {
 		gen9_sanitize_dc_state(i915);
 		bxt_disable_dc9(i915);
-		/* Tweaked Wa_14010685332:icp,jsp,mcc */
-		if (INTEL_PCH_TYPE(i915) >= PCH_ICP && INTEL_PCH_TYPE(i915) <= PCH_MCC)
-			intel_de_rmw(i915, SOUTH_CHICKEN1, SBCLK_RUN_REFCLK_DIS, 0);
-
 	} else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) {
 		hsw_disable_pc8(i915);
 	}
+
+	/* Tweaked Wa_14010685332:cnp,icp,jsp,mcc,tgp,adp */
+	if (INTEL_PCH_TYPE(i915) >= PCH_CNP && INTEL_PCH_TYPE(i915) < PCH_DG1)
+		intel_de_rmw(i915, SOUTH_CHICKEN1, SBCLK_RUN_REFCLK_DIS, 0);
 }
 
 void intel_display_power_suspend(struct drm_i915_private *i915)

drivers/gpu/drm/i915/display/intel_dp.c

@@ -3850,23 +3850,18 @@ static void intel_dp_check_device_service_irq(struct intel_dp *intel_dp)
 
 static void intel_dp_check_link_service_irq(struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 val;
 
 	if (intel_dp->dpcd[DP_DPCD_REV] < 0x11)
 		return;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
-			      DP_LINK_SERVICE_IRQ_VECTOR_ESI0, &val) != 1 || !val) {
-		drm_dbg_kms(&i915->drm, "Error in reading link service irq vector\n");
+			      DP_LINK_SERVICE_IRQ_VECTOR_ESI0, &val) != 1 || !val)
 		return;
-	}
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux,
-			       DP_LINK_SERVICE_IRQ_VECTOR_ESI0, val) != 1) {
-		drm_dbg_kms(&i915->drm, "Error in writing link service irq vector\n");
+			       DP_LINK_SERVICE_IRQ_VECTOR_ESI0, val) != 1)
 		return;
-	}
 
 	if (val & HDMI_LINK_STATUS_CHANGED)
 		intel_dp_handle_hdmi_link_status_change(intel_dp);

drivers/gpu/drm/i915/display/intel_dp_link_training.c

@@ -206,7 +206,6 @@ int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp)
 
 	return lttpr_count;
 }
-EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps);
 
 static u8 dp_voltage_max(u8 preemph)
 {

drivers/gpu/drm/i915/gt/intel_timeline.c

@@ -127,6 +127,15 @@ static void intel_timeline_fini(struct rcu_head *rcu)
 
 	i915_vma_put(timeline->hwsp_ggtt);
 	i915_active_fini(&timeline->active);
+
+	/*
+	 * A small race exists between intel_gt_retire_requests_timeout and
+	 * intel_timeline_exit which could result in the syncmap not getting
+	 * free'd. Rather than work to hard to seal this race, simply cleanup
+	 * the syncmap on fini.
+	 */
+	i915_syncmap_free(&timeline->sync);
+
 	kfree(timeline);
 }
 

drivers/gpu/drm/i915/i915_irq.c

@@ -3064,24 +3064,6 @@ static void valleyview_irq_reset(struct drm_i915_private *dev_priv)
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
-static void cnp_display_clock_wa(struct drm_i915_private *dev_priv)
-{
-	struct intel_uncore *uncore = &dev_priv->uncore;
-
-	/*
-	 * Wa_14010685332:cnp/cmp,tgp,adp
-	 * TODO: Clarify which platforms this applies to
-	 * TODO: Figure out if this workaround can be applied in the s0ix suspend/resume handlers as
-	 * on earlier platforms and whether the workaround is also needed for runtime suspend/resume
-	 */
-	if (INTEL_PCH_TYPE(dev_priv) == PCH_CNP ||
-	    (INTEL_PCH_TYPE(dev_priv) >= PCH_TGP && INTEL_PCH_TYPE(dev_priv) < PCH_DG1)) {
-		intel_uncore_rmw(uncore, SOUTH_CHICKEN1, SBCLK_RUN_REFCLK_DIS,
-				 SBCLK_RUN_REFCLK_DIS);
-		intel_uncore_rmw(uncore, SOUTH_CHICKEN1, SBCLK_RUN_REFCLK_DIS, 0);
-	}
-}
-
 static void gen8_display_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
@@ -3115,7 +3097,6 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv)
 	if (HAS_PCH_SPLIT(dev_priv))
 		ibx_irq_reset(dev_priv);
 
-	cnp_display_clock_wa(dev_priv);
 }
 
 static void gen11_display_irq_reset(struct drm_i915_private *dev_priv)
@@ -3159,8 +3140,6 @@ static void gen11_display_irq_reset(struct drm_i915_private *dev_priv)
 
 	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		GEN3_IRQ_RESET(uncore, SDE);
-
-	cnp_display_clock_wa(dev_priv);
 }
 
 static void gen11_irq_reset(struct drm_i915_private *dev_priv)

drivers/gpu/drm/imx/ipuv3-plane.c

@@ -683,7 +683,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
 		break;
 	}
 
-	ipu_dmfc_config_wait4eot(ipu_plane->dmfc, drm_rect_width(dst));
+	ipu_dmfc_config_wait4eot(ipu_plane->dmfc, ALIGN(drm_rect_width(dst), 8));
 
 	width = ipu_src_rect_width(new_state);
 	height = drm_rect_height(&new_state->src) >> 16;

drivers/gpu/drm/mediatek/mtk_disp_color.c

@@ -133,6 +133,8 @@ static int mtk_disp_color_probe(struct platform_device *pdev)
 
 static int mtk_disp_color_remove(struct platform_device *pdev)
 {
+	component_del(&pdev->dev, &mtk_disp_color_component_ops);
+
 	return 0;
 }
 

drivers/gpu/drm/mediatek/mtk_disp_ovl.c

@@ -423,6 +423,8 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev)
 
 static int mtk_disp_ovl_remove(struct platform_device *pdev)
 {
+	component_del(&pdev->dev, &mtk_disp_ovl_component_ops);
+
 	return 0;
 }
 

drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c

@@ -34,6 +34,7 @@
 
 #define DISP_AAL_EN				0x0000
 #define DISP_AAL_SIZE				0x0030
+#define DISP_AAL_OUTPUT_SIZE			0x04d8
 
 #define DISP_DITHER_EN				0x0000
 #define DITHER_EN				BIT(0)
@@ -197,6 +198,7 @@ static void mtk_aal_config(struct device *dev, unsigned int w,
 	struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev);
 
 	mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_AAL_OUTPUT_SIZE);
 }
 
 static void mtk_aal_gamma_set(struct device *dev, struct drm_crtc_state *state)

drivers/gpu/drm/nouveau/dispnv50/disp.c

@@ -2237,6 +2237,33 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 		interlock[NV50_DISP_INTERLOCK_CORE] = 0;
 	}
 
+	/* Finish updating head(s)...
+	 *
+	 * NVD is rather picky about both where window assignments can change,
+	 * *and* about certain core and window channel states matching.
+	 *
+	 * The EFI GOP driver on newer GPUs configures window channels with a
+	 * different output format to what we do, and the core channel update
+	 * in the assign_windows case above would result in a state mismatch.
+	 *
+	 * Delay some of the head update until after that point to workaround
+	 * the issue.  This only affects the initial modeset.
+	 *
+	 * TODO: handle this better when adding flexible window mapping
+	 */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state);
+		struct nv50_head *head = nv50_head(crtc);
+
+		NV_ATOMIC(drm, "%s: set %04x (clr %04x)\n", crtc->name,
+			  asyh->set.mask, asyh->clr.mask);
+
+		if (asyh->set.mask) {
+			nv50_head_flush_set_wndw(head, asyh);
+			interlock[NV50_DISP_INTERLOCK_CORE] = 1;
+		}
+	}
+
 	/* Update plane(s). */
 	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
 		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);

drivers/gpu/drm/nouveau/dispnv50/head.c

@@ -50,11 +50,8 @@ nv50_head_flush_clr(struct nv50_head *head,
 }
 
 void
-nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh)
 {
-	if (asyh->set.view   ) head->func->view    (head, asyh);
-	if (asyh->set.mode   ) head->func->mode    (head, asyh);
-	if (asyh->set.core   ) head->func->core_set(head, asyh);
 	if (asyh->set.olut   ) {
 		asyh->olut.offset = nv50_lut_load(&head->olut,
 						  asyh->olut.buffer,
@@ -62,6 +59,14 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 						  asyh->olut.load);
 		head->func->olut_set(head, asyh);
 	}
+}
+
+void
+nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	if (asyh->set.view   ) head->func->view    (head, asyh);
+	if (asyh->set.mode   ) head->func->mode    (head, asyh);
+	if (asyh->set.core   ) head->func->core_set(head, asyh);
 	if (asyh->set.curs   ) head->func->curs_set(head, asyh);
 	if (asyh->set.base   ) head->func->base    (head, asyh);
 	if (asyh->set.ovly   ) head->func->ovly    (head, asyh);

drivers/gpu/drm/nouveau/dispnv50/head.h

@@ -21,6 +21,7 @@ struct nv50_head {
 
 struct nv50_head *nv50_head_create(struct drm_device *, int index);
 void nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh);
+void nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh);
 void nv50_head_flush_clr(struct nv50_head *head,
 			 struct nv50_head_atom *asyh, bool flush);
 

drivers/gpu/drm/nouveau/include/nvif/cl0080.h

@@ -4,7 +4,8 @@
 
 struct nv_device_v0 {
 	__u8  version;
-	__u8  pad01[7];
+	__u8  priv;
+	__u8  pad02[6];
 	__u64 device;	/* device identifier, ~0 for client default */
 };
 

drivers/gpu/drm/nouveau/include/nvif/class.h

@@ -61,8 +61,6 @@
 #define NV10_CHANNEL_DMA                              /* cl506b.h */ 0x0000006e
 #define NV17_CHANNEL_DMA                              /* cl506b.h */ 0x0000176e
 #define NV40_CHANNEL_DMA                              /* cl506b.h */ 0x0000406e
-#define NV50_CHANNEL_DMA                              /* cl506e.h */ 0x0000506e
-#define G82_CHANNEL_DMA                               /* cl826e.h */ 0x0000826e
 
 #define NV50_CHANNEL_GPFIFO                           /* cl506f.h */ 0x0000506f
 #define G82_CHANNEL_GPFIFO                            /* cl826f.h */ 0x0000826f

drivers/gpu/drm/nouveau/include/nvif/client.h

@@ -9,7 +9,6 @@ struct nvif_client {
 	const struct nvif_driver *driver;
 	u64 version;
 	u8 route;
-	bool super;
 };
 
 int  nvif_client_ctor(struct nvif_client *parent, const char *name, u64 device,

drivers/gpu/drm/nouveau/include/nvif/driver.h

@@ -11,7 +11,7 @@ struct nvif_driver {
 	void (*fini)(void *priv);
 	int (*suspend)(void *priv);
 	int (*resume)(void *priv);
-	int (*ioctl)(void *priv, bool super, void *data, u32 size, void **hack);
+	int (*ioctl)(void *priv, void *data, u32 size, void **hack);
 	void __iomem *(*map)(void *priv, u64 handle, u32 size);
 	void (*unmap)(void *priv, void __iomem *ptr, u32 size);
 	bool keep;