Merge 576e61cea1 ("Merge tag 's390-6.1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux") into android-mainline

Steps on the way to 6.1-rc3 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I81d2cc862ba86b4859b2d1df225a3d76b7195a3e
2026-06-05 18:41:58 +09:00 · 2022-10-29 10:26:45 +02:00
parent 9ea9019770 576e61cea1
commit cdb76e3ee0
201 changed files with 2491 additions and 1005 deletions
--- a/Documentation/admin-guide/media/vivid.rst
+++ b/Documentation/admin-guide/media/vivid.rst
@@ -1318,7 +1318,7 @@ instance. This setup would require the following commands:
 	$ v4l2-ctl -d2 -i2
 	$ v4l2-ctl -d2 -c horizontal_movement=4
 	$ v4l2-ctl -d1 --overlay=1
-	$ v4l2-ctl -d1 -c loop_video=1
+	$ v4l2-ctl -d0 -c loop_video=1
 	$ v4l2-ctl -d2 --stream-mmap --overlay=1

 And from another console:
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -118,6 +118,12 @@ Text Searching
 CRC and Math Functions in Linux
 ===============================

+Arithmetic Overflow Checking
+----------------------------
+
+.. kernel-doc:: include/linux/overflow.h
+   :internal:
+
 CRC Functions
 -------------

--- a/Documentation/driver-api/basics.rst
+++ b/Documentation/driver-api/basics.rst
@@ -107,9 +107,6 @@ Kernel utility functions
 .. kernel-doc:: kernel/panic.c
   :export:

-.. kernel-doc:: include/linux/overflow.h
-   :internal:
-
 Device Resource Management
 --------------------------

--- a/15
+++ b/15
@@ -11265,7 +11265,6 @@ M:	Claudio Imbrenda <imbrenda@linux.ibm.com>
 R:	David Hildenbrand <david@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
 F:	Documentation/virt/kvm/s390*
 F:	arch/s390/include/asm/gmap.h
@@ -15443,6 +15442,7 @@ S:	Maintained
 W:	http://openvswitch.org
 F:	include/uapi/linux/openvswitch.h
 F:	net/openvswitch/
+F:	tools/testing/selftests/net/openvswitch/

 OPERATING PERFORMANCE POINTS (OPP)
 M:	Viresh Kumar <vireshk@kernel.org>
@@ -18004,7 +18004,6 @@ R:	Christian Borntraeger <borntraeger@linux.ibm.com>
 R:	Sven Schnelle <svens@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git
 F:	Documentation/driver-api/s390-drivers.rst
 F:	Documentation/s390/
@@ -18016,7 +18015,6 @@ M:	Vineeth Vijayan <vneethv@linux.ibm.com>
 M:	Peter Oberparleiter <oberpar@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/cio/

 S390 DASD DRIVER
@@ -18024,7 +18022,6 @@ M:	Stefan Haberland <sth@linux.ibm.com>
 M:	Jan Hoeppner <hoeppner@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	block/partitions/ibm.c
 F:	drivers/s390/block/dasd*
 F:	include/linux/dasd_mod.h
@@ -18034,7 +18031,6 @@ M:	Matthew Rosato <mjrosato@linux.ibm.com>
 M:	Gerald Schaefer <gerald.schaefer@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/iommu/s390-iommu.c

 S390 IUCV NETWORK LAYER
@@ -18043,7 +18039,6 @@ M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/net/*iucv*
 F:	include/net/iucv/
 F:	net/iucv/
@@ -18054,7 +18049,6 @@ M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/net/

 S390 PCI SUBSYSTEM
@@ -18062,7 +18056,6 @@ M:	Niklas Schnelle <schnelle@linux.ibm.com>
 M:	Gerald Schaefer <gerald.schaefer@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	arch/s390/pci/
 F:	drivers/pci/hotplug/s390_pci_hpc.c
 F:	Documentation/s390/pci.rst
@@ -18073,7 +18066,6 @@ M:	Halil Pasic <pasic@linux.ibm.com>
 M:	Jason Herne <jjherne@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	Documentation/s390/vfio-ap*
 F:	drivers/s390/crypto/vfio_ap*

@@ -18102,7 +18094,6 @@ S390 ZCRYPT DRIVER
 M:	Harald Freudenberger <freude@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/crypto/

 S390 ZFCP DRIVER
@@ -18110,7 +18101,6 @@ M:	Steffen Maier <maier@linux.ibm.com>
 M:	Benjamin Block <bblock@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/scsi/zfcp_*

 S3C ADC BATTERY DRIVER
@@ -18682,7 +18672,6 @@ M:	Wenjia Zhang <wenjia@linux.ibm.com>
 M:	Jan Karcher <jaka@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	net/smc/

 SHARP GP2AP002A00F/GP2AP002S00F SENSOR DRIVER
@@ -18793,7 +18782,7 @@ M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
-T:	git git://github.com/sifive/riscv-linux.git
+T:	git https://github.com/sifive/riscv-linux.git
 N:	sifive
 K:	[^@]sifive

--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -411,14 +411,16 @@ config RISCV_ISA_SVPBMT

 	   If you don't know what to do here, say Y.

-config CC_HAS_ZICBOM
+config TOOLCHAIN_HAS_ZICBOM
 	bool
-	default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
-	default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23800

 config RISCV_ISA_ZICBOM
 	bool "Zicbom extension support for non-coherent DMA operation"
-	depends on CC_HAS_ZICBOM
+	depends on TOOLCHAIN_HAS_ZICBOM
 	depends on !XIP_KERNEL && MMU
 	select RISCV_DMA_NONCOHERENT
 	select RISCV_ALTERNATIVE
@@ -433,6 +435,13 @@ config RISCV_ISA_ZICBOM

 	   If you don't know what to do here, say Y.

+config TOOLCHAIN_HAS_ZIHINTPAUSE
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zihintpause)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zihintpause)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23600
+
 config FPU
 	bool "FPU support"
 	default y
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -59,12 +59,10 @@ toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zi
 riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei

 # Check if the toolchain supports Zicbom extension
-toolchain-supports-zicbom := $(call cc-option-yn, -march=$(riscv-march-y)_zicbom)
-riscv-march-$(toolchain-supports-zicbom) := $(riscv-march-y)_zicbom
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZICBOM) := $(riscv-march-y)_zicbom

 # Check if the toolchain supports Zihintpause extension
-toolchain-supports-zihintpause := $(call cc-option-yn, -march=$(riscv-march-y)_zihintpause)
-riscv-march-$(toolchain-supports-zihintpause) := $(riscv-march-y)_zihintpause
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause

 KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
 KBUILD_AFLAGS += -march=$(riscv-march-y)
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -14,8 +14,8 @@

 #define JUMP_LABEL_NOP_SIZE 4

-static __always_inline bool arch_static_branch(struct static_key *key,
-					       bool branch)
+static __always_inline bool arch_static_branch(struct static_key * const key,
+					       const bool branch)
 {
 	asm_volatile_goto(
 		"	.option push				\n\t"
@@ -35,8 +35,8 @@ label:
 	return true;
 }

-static __always_inline bool arch_static_branch_jump(struct static_key *key,
-						    bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
+						    const bool branch)
 {
 	asm_volatile_goto(
 		"	.option push				\n\t"
--- a/arch/riscv/include/asm/vdso/processor.h
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -21,7 +21,7 @@ static inline void cpu_relax(void)
 		 * Reduce instruction retirement.
 		 * This assumes the PC changes.
 		 */
-#ifdef __riscv_zihintpause
+#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
 		__asm__ __volatile__ ("pause");
 #else
 		/* Encoding of the pause instruction */
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -213,6 +213,9 @@ static void print_mmu(struct seq_file *f)

 static void *c_start(struct seq_file *m, loff_t *pos)
 {
+	if (*pos == nr_cpu_ids)
+		return NULL;
+
 	*pos = cpumask_next(*pos - 1, cpu_online_mask);
 	if ((*pos) < nr_cpu_ids)
 		return (void *)(uintptr_t)(1 + *pos);
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -113,6 +113,8 @@ static void __init kasan_populate_pud(pgd_t *pgd,
 		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
 	} else if (pgd_none(*pgd)) {
 		base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+		memcpy(base_pud, (void *)kasan_early_shadow_pud,
+			sizeof(pud_t) * PTRS_PER_PUD);
 	} else {
 		base_pud = (pud_t *)pgd_page_vaddr(*pgd);
 		if (base_pud == lm_alias(kasan_early_shadow_pud)) {
@@ -173,8 +175,11 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd)));
 	} else {
 		base_p4d = (p4d_t *)pgd_page_vaddr(*pgd);
-		if (base_p4d == lm_alias(kasan_early_shadow_p4d))
+		if (base_p4d == lm_alias(kasan_early_shadow_p4d)) {
 			base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE);
+			memcpy(base_p4d, (void *)kasan_early_shadow_p4d,
+				sizeof(p4d_t) * PTRS_PER_P4D);
+		}
 	}

 	p4dp = base_p4d + p4d_index(vaddr);
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -102,8 +102,17 @@ SECTIONS
 		_compressed_start = .;
 		*(.vmlinux.bin.compressed)
 		_compressed_end = .;
-		FILL(0xff);
-		. = ALIGN(4096);
+	}
+
+#define SB_TRAILER_SIZE 32
+	/* Trailer needed for Secure Boot */
+	. += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */
+	. = ALIGN(4096) - SB_TRAILER_SIZE;
+	.sb.trailer : {
+		QUAD(0)
+		QUAD(0)
+		QUAD(0)
+		QUAD(0x000000207a49504c)
 	}
 	_end = .;

--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -17,7 +17,8 @@
 		"3: jl    1b\n"						\
 		"   lhi   %0,0\n"					\
 		"4: sacf  768\n"					\
-		EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b)		\
+		EX_TABLE(0b,4b) EX_TABLE(1b,4b)				\
+		EX_TABLE(2b,4b) EX_TABLE(3b,4b)				\
 		: "=d" (ret), "=&d" (oldval), "=&d" (newval),		\
 		  "=m" (*uaddr)						\
 		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -459,6 +459,7 @@ static int paiext_push_sample(void)
 		raw.frag.data = cpump->save;
 		raw.size = raw.frag.size;
 		data.raw = &raw;
+		data.sample_flags |= PERF_SAMPLE_RAW;
 	}

 	overflow = perf_event_overflow(event, &data, &regs);
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -157,7 +157,7 @@ unsigned long __clear_user(void __user *to, unsigned long size)
 	asm volatile(
 		"   lr	  0,%[spec]\n"
 		"0: mvcos 0(%1),0(%4),%0\n"
-		"   jz	  4f\n"
+		"6: jz	  4f\n"
 		"1: algr  %0,%2\n"
 		"   slgr  %1,%2\n"
 		"   j	  0b\n"
@@ -167,11 +167,11 @@ unsigned long __clear_user(void __user *to, unsigned long size)
 		"   clgr  %0,%3\n"	/* copy crosses next page boundary? */
 		"   jnh	  5f\n"
 		"3: mvcos 0(%1),0(%4),%3\n"
-		"   slgr  %0,%3\n"
+		"7: slgr  %0,%3\n"
 		"   j	  5f\n"
 		"4: slgr  %0,%0\n"
 		"5:\n"
-		EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+		EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b)
 		: "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
 		: "a" (empty_zero_page), [spec] "d" (spec.val)
 		: "cc", "memory", "0");
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -64,7 +64,7 @@ static inline int __pcistg_mio_inuser(
 	asm volatile (
 		"       sacf    256\n"
 		"0:     llgc    %[tmp],0(%[src])\n"
-		"       sllg    %[val],%[val],8\n"
+		"4:	sllg	%[val],%[val],8\n"
 		"       aghi    %[src],1\n"
 		"       ogr     %[val],%[tmp]\n"
 		"       brctg   %[cnt],0b\n"
@@ -72,7 +72,7 @@ static inline int __pcistg_mio_inuser(
 		"2:     ipm     %[cc]\n"
 		"       srl     %[cc],28\n"
 		"3:     sacf    768\n"
-		EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+		EX_TABLE(0b, 3b) EX_TABLE(4b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
 		:
 		[src] "+a" (src), [cnt] "+d" (cnt),
 		[val] "+d" (val), [tmp] "=d" (tmp),
@@ -215,10 +215,10 @@ static inline int __pcilg_mio_inuser(
 		"2:     ahi     %[shift],-8\n"
 		"       srlg    %[tmp],%[val],0(%[shift])\n"
 		"3:     stc     %[tmp],0(%[dst])\n"
-		"       aghi    %[dst],1\n"
+		"5:	aghi	%[dst],1\n"
 		"       brctg   %[cnt],2b\n"
 		"4:     sacf    768\n"
-		EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+		EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) EX_TABLE(5b, 4b)
 		:
 		[ioaddr_len] "+&d" (ioaddr_len.pair),
 		[cc] "+d" (cc), [val] "=d" (val),
--- a/arch/x86/crypto/polyval-clmulni_glue.c
+++ b/arch/x86/crypto/polyval-clmulni_glue.c
@@ -27,13 +27,17 @@
 #include <asm/cpu_device_id.h>
 #include <asm/simd.h>

+#define POLYVAL_ALIGN	16
+#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
+#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
+#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA)
 #define NUM_KEY_POWERS	8

 struct polyval_tfm_ctx {
 	/*
 	 * These powers must be in the order h^8, ..., h^1.
 	 */
-	u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE];
+	u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR;
 };

 struct polyval_desc_ctx {
@@ -45,6 +49,11 @@ asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator);
 asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2);

+static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
+{
+	return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN);
+}
+
 static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator)
 {
@@ -72,7 +81,7 @@ static void internal_polyval_mul(u8 *op1, const u8 *op2)
 static int polyval_x86_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
-	struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+	struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm);
 	int i;

 	if (keylen != POLYVAL_BLOCK_SIZE)
@@ -102,7 +111,7 @@ static int polyval_x86_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
-	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
 	u8 *pos;
 	unsigned int nblocks;
 	unsigned int n;
@@ -143,7 +152,7 @@ static int polyval_x86_update(struct shash_desc *desc,
 static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
-	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);

 	if (dctx->bytes) {
 		internal_polyval_mul(dctx->buffer,
@@ -167,7 +176,7 @@ static struct shash_alg polyval_alg = {
 		.cra_driver_name	= "polyval-clmulni",
 		.cra_priority		= 200,
 		.cra_blocksize		= POLYVAL_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct polyval_tfm_ctx),
+		.cra_ctxsize		= POLYVAL_CTX_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
 };
--- a/drivers/acpi/acpi_pcc.c
+++ b/drivers/acpi/acpi_pcc.c
@@ -27,7 +27,7 @@
 * Arbitrary retries in case the remote processor is slow to respond
 * to PCC commands
 */
-#define PCC_CMD_WAIT_RETRIES_NUM	500
+#define PCC_CMD_WAIT_RETRIES_NUM	500ULL

 struct pcc_data {
 	struct pcc_mbox_chan *pcc_chan;
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -425,6 +425,13 @@ static const struct dmi_system_id asus_laptop[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "S5402ZA"),
 		},
 	},
+	{
+		.ident = "Asus Vivobook S5602ZA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
+		},
+	},
 	{ }
 };

--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -789,6 +789,7 @@ static bool acpi_info_matches_ids(struct acpi_device_info *info,
 static const char * const acpi_ignore_dep_ids[] = {
 	"PNP0D80", /* Windows-compatible System Power Management Controller */
 	"INT33BD", /* Intel Baytrail Mailbox Device */
+	"LATT2021", /* Lattice FW Update Client Driver */
 	NULL
 };

--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2952,6 +2952,10 @@ static int genpd_iterate_idle_states(struct device_node *dn,
 		np = it.node;
 		if (!of_match_node(idle_state_match, np))
 			continue;
+
+		if (!of_device_is_available(np))
+			continue;
+
 		if (states) {
 			ret = genpd_parse_state(&states[i], np);
 			if (ret) {
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -229,7 +229,7 @@ EXPORT_SYMBOL_GPL(device_property_read_string);
 * Find a given string in a string array and if it is found return the
 * index back.
 *
- * Return: %0 if the property was found (success),
+ * Return: index, starting from %0, if the property was found (success),
 *	   %-EINVAL if given arguments are not valid,
 *	   %-ENODATA if the property does not have a value,
 *	   %-EPROTO if the property is not an array of strings,
@@ -450,7 +450,7 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_string);
 * Find a given string in a string array and if it is found return the
 * index back.
 *
- * Return: %0 if the property was found (success),
+ * Return: index, starting from %0, if the property was found (success),
 *	   %-EINVAL if given arguments are not valid,
 *	   %-ENODATA if the property does not have a value,
 *	   %-EPROTO if the property is not an array of strings,
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -27,6 +27,7 @@
 #include <linux/pm_qos.h>
 #include <trace/events/power.h>

+#include <asm/cpu.h>
 #include <asm/div64.h>
 #include <asm/msr.h>
 #include <asm/cpu_device_id.h>
@@ -280,10 +281,10 @@ static struct cpudata **all_cpu_data;
 * structure is used to store those callbacks.
 */
 struct pstate_funcs {
-	int (*get_max)(void);
-	int (*get_max_physical)(void);
-	int (*get_min)(void);
-	int (*get_turbo)(void);
+	int (*get_max)(int cpu);
+	int (*get_max_physical)(int cpu);
+	int (*get_min)(int cpu);
+	int (*get_turbo)(int cpu);
 	int (*get_scaling)(void);
 	int (*get_cpu_scaling)(int cpu);
 	int (*get_aperf_mperf_shift)(void);
@@ -398,16 +399,6 @@ static int intel_pstate_get_cppc_guaranteed(int cpu)

 	return cppc_perf.nominal_perf;
 }
-
-static u32 intel_pstate_cppc_nominal(int cpu)
-{
-	u64 nominal_perf;
-
-	if (cppc_get_nominal_perf(cpu, &nominal_perf))
-		return 0;
-
-	return nominal_perf;
-}
 #else /* CONFIG_ACPI_CPPC_LIB */
 static inline void intel_pstate_set_itmt_prio(int cpu)
 {
@@ -531,35 +522,18 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 {
 	int perf_ctl_max_phys = cpu->pstate.max_pstate_physical;
 	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
-	int perf_ctl_turbo = pstate_funcs.get_turbo();
-	int turbo_freq = perf_ctl_turbo * perf_ctl_scaling;
+	int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu);
 	int scaling = cpu->pstate.scaling;

 	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
-	pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, pstate_funcs.get_max());
 	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
 	pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling);
 	pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate);
 	pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate);
 	pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling);

-	/*
-	 * If the product of the HWP performance scaling factor and the HWP_CAP
-	 * highest performance is greater than the maximum turbo frequency
-	 * corresponding to the pstate_funcs.get_turbo() return value, the
-	 * scaling factor is too high, so recompute it to make the HWP_CAP
-	 * highest performance correspond to the maximum turbo frequency.
-	 */
-	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * scaling;
-	if (turbo_freq < cpu->pstate.turbo_freq) {
-		cpu->pstate.turbo_freq = turbo_freq;
-		scaling = DIV_ROUND_UP(turbo_freq, cpu->pstate.turbo_pstate);
-		cpu->pstate.scaling = scaling;
-
-		pr_debug("CPU%d: refined HWP-to-frequency scaling factor: %d\n",
-			 cpu->cpu, scaling);
-	}
-
+	cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling,
+					   perf_ctl_scaling);
 	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
 					 perf_ctl_scaling);

@@ -1740,7 +1714,7 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	intel_pstate_update_epp_defaults(cpudata);
 }

-static int atom_get_min_pstate(void)
+static int atom_get_min_pstate(int not_used)
 {
 	u64 value;

@@ -1748,7 +1722,7 @@ static int atom_get_min_pstate(void)
 	return (value >> 8) & 0x7F;
 }

-static int atom_get_max_pstate(void)
+static int atom_get_max_pstate(int not_used)
 {
 	u64 value;

@@ -1756,7 +1730,7 @@ static int atom_get_max_pstate(void)
 	return (value >> 16) & 0x7F;
 }

-static int atom_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(int not_used)
 {
 	u64 value;

@@ -1834,23 +1808,23 @@ static void atom_get_vid(struct cpudata *cpudata)
 	cpudata->vid.turbo = value & 0x7f;
 }

-static int core_get_min_pstate(void)
+static int core_get_min_pstate(int cpu)
 {
 	u64 value;

-	rdmsrl(MSR_PLATFORM_INFO, value);
+	rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &value);
 	return (value >> 40) & 0xFF;
 }

-static int core_get_max_pstate_physical(void)
+static int core_get_max_pstate_physical(int cpu)
 {
 	u64 value;

-	rdmsrl(MSR_PLATFORM_INFO, value);
+	rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &value);
 	return (value >> 8) & 0xFF;
 }

-static int core_get_tdp_ratio(u64 plat_info)
+static int core_get_tdp_ratio(int cpu, u64 plat_info)
 {
 	/* Check how many TDP levels present */
 	if (plat_info & 0x600000000) {
@@ -1860,13 +1834,13 @@ static int core_get_tdp_ratio(u64 plat_info)
 		int err;

 		/* Get the TDP level (0, 1, 2) to get ratios */
-		err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
+		err = rdmsrl_safe_on_cpu(cpu, MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
 		if (err)
 			return err;

 		/* TDP MSR are continuous starting at 0x648 */
 		tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
-		err = rdmsrl_safe(tdp_msr, &tdp_ratio);
+		err = rdmsrl_safe_on_cpu(cpu, tdp_msr, &tdp_ratio);
 		if (err)
 			return err;

@@ -1883,7 +1857,7 @@ static int core_get_tdp_ratio(u64 plat_info)
 	return -ENXIO;
 }

-static int core_get_max_pstate(void)
+static int core_get_max_pstate(int cpu)
 {
 	u64 tar;
 	u64 plat_info;
@@ -1891,10 +1865,10 @@ static int core_get_max_pstate(void)
 	int tdp_ratio;
 	int err;

-	rdmsrl(MSR_PLATFORM_INFO, plat_info);
+	rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &plat_info);
 	max_pstate = (plat_info >> 8) & 0xFF;

-	tdp_ratio = core_get_tdp_ratio(plat_info);
+	tdp_ratio = core_get_tdp_ratio(cpu, plat_info);
 	if (tdp_ratio <= 0)
 		return max_pstate;

@@ -1903,7 +1877,7 @@ static int core_get_max_pstate(void)
 		return tdp_ratio;
 	}

-	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
+	err = rdmsrl_safe_on_cpu(cpu, MSR_TURBO_ACTIVATION_RATIO, &tar);
 	if (!err) {
 		int tar_levels;

@@ -1918,13 +1892,13 @@ static int core_get_max_pstate(void)
 	return max_pstate;
 }

-static int core_get_turbo_pstate(void)
+static int core_get_turbo_pstate(int cpu)
 {
 	u64 value;
 	int nont, ret;

-	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
-	nont = core_get_max_pstate();
+	rdmsrl_on_cpu(cpu, MSR_TURBO_RATIO_LIMIT, &value);
+	nont = core_get_max_pstate(cpu);
 	ret = (value) & 255;
 	if (ret <= nont)
 		ret = nont;
@@ -1952,51 +1926,38 @@ static int knl_get_aperf_mperf_shift(void)
 	return 10;
 }

-static int knl_get_turbo_pstate(void)
+static int knl_get_turbo_pstate(int cpu)
 {
 	u64 value;
 	int nont, ret;

-	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
-	nont = core_get_max_pstate();
+	rdmsrl_on_cpu(cpu, MSR_TURBO_RATIO_LIMIT, &value);
+	nont = core_get_max_pstate(cpu);
 	ret = (((value) >> 8) & 0xFF);
 	if (ret <= nont)
 		ret = nont;
 	return ret;
 }

-#ifdef CONFIG_ACPI_CPPC_LIB
-static u32 hybrid_ref_perf;
+static void hybrid_get_type(void *data)
+{
+	u8 *cpu_type = data;
+
+	*cpu_type = get_this_hybrid_cpu_type();
+}

 static int hybrid_get_cpu_scaling(int cpu)
 {
-	return DIV_ROUND_UP(core_get_scaling() * hybrid_ref_perf,
-			    intel_pstate_cppc_nominal(cpu));
+	u8 cpu_type = 0;
+
+	smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
+	/* P-cores have a smaller perf level-to-freqency scaling factor. */
+	if (cpu_type == 0x40)
+		return 78741;
+
+	return core_get_scaling();
 }

-static void intel_pstate_cppc_set_cpu_scaling(void)
-{
-	u32 min_nominal_perf = U32_MAX;
-	int cpu;
-
-	for_each_present_cpu(cpu) {
-		u32 nominal_perf = intel_pstate_cppc_nominal(cpu);
-
-		if (nominal_perf && nominal_perf < min_nominal_perf)
-			min_nominal_perf = nominal_perf;
-	}
-
-	if (min_nominal_perf < U32_MAX) {
-		hybrid_ref_perf = min_nominal_perf;
-		pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;
-	}
-}
-#else
-static inline void intel_pstate_cppc_set_cpu_scaling(void)
-{
-}
-#endif /* CONFIG_ACPI_CPPC_LIB */
-
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
@@ -2025,10 +1986,10 @@ static void intel_pstate_max_within_limits(struct cpudata *cpu)

 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
-	int perf_ctl_max_phys = pstate_funcs.get_max_physical();
+	int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu);
 	int perf_ctl_scaling = pstate_funcs.get_scaling();

-	cpu->pstate.min_pstate = pstate_funcs.get_min();
+	cpu->pstate.min_pstate = pstate_funcs.get_min(cpu->cpu);
 	cpu->pstate.max_pstate_physical = perf_ctl_max_phys;
 	cpu->pstate.perf_ctl_scaling = perf_ctl_scaling;

@@ -2044,8 +2005,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 		}
 	} else {
 		cpu->pstate.scaling = perf_ctl_scaling;
-		cpu->pstate.max_pstate = pstate_funcs.get_max();
-		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
+		cpu->pstate.max_pstate = pstate_funcs.get_max(cpu->cpu);
+		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(cpu->cpu);
 	}

 	if (cpu->pstate.scaling == perf_ctl_scaling) {
@@ -3221,9 +3182,9 @@ static unsigned int force_load __initdata;

 static int __init intel_pstate_msrs_not_valid(void)
 {
-	if (!pstate_funcs.get_max() ||
-	    !pstate_funcs.get_min() ||
-	    !pstate_funcs.get_turbo())
+	if (!pstate_funcs.get_max(0) ||
+	    !pstate_funcs.get_min(0) ||
+	    !pstate_funcs.get_turbo(0))
 		return -ENODEV;

 	return 0;
@@ -3450,7 +3411,7 @@ static int __init intel_pstate_init(void)
 				default_driver = &intel_pstate;

 			if (boot_cpu_has(X86_FEATURE_HYBRID_CPU))
-				intel_pstate_cppc_set_cpu_scaling();
+				pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;

 			goto hwp_cpu_matched;
 		}
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -510,13 +510,13 @@ kfd_mem_dmamap_userptr(struct kgd_mem *mem,
 	struct ttm_tt *ttm = bo->tbo.ttm;
 	int ret;

+	if (WARN_ON(ttm->num_pages != src_ttm->num_pages))
+		return -EINVAL;
+
 	ttm->sg = kmalloc(sizeof(*ttm->sg), GFP_KERNEL);
 	if (unlikely(!ttm->sg))
 		return -ENOMEM;

-	if (WARN_ON(ttm->num_pages != src_ttm->num_pages))
-		return -EINVAL;
-
 	/* Same sequence as in amdgpu_ttm_tt_pin_userptr */
 	ret = sg_alloc_table_from_pages(ttm->sg, src_ttm->pages,
 					ttm->num_pages, 0,
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -326,7 +326,10 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority,
 	if (r)
 		return r;

-	ctx->stable_pstate = current_stable_pstate;
+	if (mgr->adev->pm.stable_pstate_ctx)
+		ctx->stable_pstate = mgr->adev->pm.stable_pstate_ctx->stable_pstate;
+	else
+		ctx->stable_pstate = current_stable_pstate;

 	return 0;
 }
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3210,6 +3210,15 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 			return r;
 		}
 		adev->ip_blocks[i].status.hw = true;
+
+		if (adev->in_s0ix && adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
+			/* disable gfxoff for IP resume. The gfxoff will be re-enabled in
+			 * amdgpu_device_resume() after IP resume.
+			 */
+			amdgpu_gfx_off_ctrl(adev, false);
+			DRM_DEBUG("will disable gfxoff for re-initializing other blocks\n");
+		}
+
 	}

 	return 0;
@@ -4185,6 +4194,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	/* Make sure IB tests flushed */
 	flush_delayed_work(&adev->delayed_init_work);

+	if (adev->in_s0ix) {
+		/* re-enable gfxoff after IP resume. This re-enables gfxoff after
+		 * it was disabled for IP resume in amdgpu_device_ip_resume_phase2().
+		 */
+		amdgpu_gfx_off_ctrl(adev, true);
+		DRM_DEBUG("will enable gfxoff for the mission mode\n");
+	}
 	if (fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false);

@@ -5381,7 +5397,7 @@ skip_hw_reset:
 			drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
 		}

-		if (adev->enable_mes)
+		if (adev->enable_mes && adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))
 			amdgpu_mes_self_test(tmp_adev);

 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) {
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -344,6 +344,10 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->ver = adev->mes.ucode_fw_version[1];
 		fw_info->feature = 0;
 		break;
+	case AMDGPU_INFO_FW_IMU:
+		fw_info->ver = adev->gfx.imu_fw_version;
+		fw_info->feature = 0;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1520,6 +1524,15 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 			   fw_info.feature, fw_info.ver);
 	}

+	/* IMU */
+	query_fw.fw_type = AMDGPU_INFO_FW_IMU;
+	query_fw.index = 0;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "IMU feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
 	/* PSP SOS */
 	query_fw.fw_type = AMDGPU_INFO_FW_SOS;
 	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -698,6 +698,7 @@ FW_VERSION_ATTR(rlc_srlg_fw_version, 0444, gfx.rlc_srlg_fw_version);
 FW_VERSION_ATTR(rlc_srls_fw_version, 0444, gfx.rlc_srls_fw_version);
 FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version);
 FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version);
+FW_VERSION_ATTR(imu_fw_version, 0444, gfx.imu_fw_version);
 FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version);
 FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_context.bin_desc.fw_version);
 FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.fw_version);
@@ -719,7 +720,8 @@ static struct attribute *fw_attrs[] = {
 	&dev_attr_ta_ras_fw_version.attr, &dev_attr_ta_xgmi_fw_version.attr,
 	&dev_attr_smc_fw_version.attr, &dev_attr_sdma_fw_version.attr,
 	&dev_attr_sdma2_fw_version.attr, &dev_attr_vcn_fw_version.attr,
-	&dev_attr_dmcu_fw_version.attr, NULL
+	&dev_attr_dmcu_fw_version.attr, &dev_attr_imu_fw_version.attr,
+	NULL
 };

 static const struct attribute_group fw_attr_group = {
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -547,6 +547,7 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev)
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC,      adev->gfx.mec_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2,     adev->gfx.mec2_fw_version);
+	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_IMU,      adev->gfx.imu_fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS,      adev->psp.sos.fw_version);
 	POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,
 			    adev->psp.asd_context.bin_desc.fw_version);
--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -70,6 +70,7 @@ enum amd_sriov_ucode_engine_id {
 	AMD_SRIOV_UCODE_ID_RLC_SRLS,
 	AMD_SRIOV_UCODE_ID_MEC,
 	AMD_SRIOV_UCODE_ID_MEC2,
+	AMD_SRIOV_UCODE_ID_IMU,
 	AMD_SRIOV_UCODE_ID_SOS,
 	AMD_SRIOV_UCODE_ID_ASD,
 	AMD_SRIOV_UCODE_ID_TA_RAS,
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -5051,6 +5051,7 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
 	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
 		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	case IP_VERSION(11, 0, 1):
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -98,7 +98,14 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	struct amdgpu_device *adev = mes->adev;
 	struct amdgpu_ring *ring = &mes->ring;
 	unsigned long flags;
+	signed long timeout = adev->usec_timeout;

+	if (amdgpu_emu_mode) {
+		timeout *= 100;
+	} else if (amdgpu_sriov_vf(adev)) {
+		/* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */
+		timeout = 15 * 600 * 1000;
+	}
 	BUG_ON(size % 4 != 0);

 	spin_lock_irqsave(&mes->ring_lock, flags);
@@ -118,7 +125,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	DRM_DEBUG("MES msg=%d was emitted\n", x_pkt->header.opcode);

 	r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq,
-		      adev->usec_timeout * (amdgpu_emu_mode ? 100 : 1));
+		      timeout);
 	if (r < 1) {
 		DRM_ERROR("MES failed to response msg=%d\n",
 			  x_pkt->header.opcode);
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -32,8 +32,6 @@
 #include "gc/gc_10_1_0_offset.h"
 #include "soc15_common.h"

-#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid                      0x064d
-#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid_BASE_IDX             0
 #define mmDAGB0_CNTL_MISC2_Sienna_Cichlid                       0x0070
 #define mmDAGB0_CNTL_MISC2_Sienna_Cichlid_BASE_IDX              0

@@ -574,7 +572,6 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
 		def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
 		break;
 	default:
@@ -608,8 +605,6 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		if (def != data)
-			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
 		if (def1 != data1)
 			WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid, data1);
 		break;
@@ -634,8 +629,8 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
-		break;
+		/* There is no ATCL2 in MMHUB for 2.1.x */
+		return;
 	default:
 		def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
 		break;
@@ -646,18 +641,8 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 	else
 		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;

-	if (def != data) {
-		switch (adev->ip_versions[MMHUB_HWIP][0]) {
-		case IP_VERSION(2, 1, 0):
-		case IP_VERSION(2, 1, 1):
-		case IP_VERSION(2, 1, 2):
-			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
-			break;
-		default:
-			WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
-			break;
-		}
-	}
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
 }

 static int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
@@ -695,7 +680,10 @@ static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
 	case IP_VERSION(2, 1, 2):
-		data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
+		/* There is no ATCL2 in MMHUB for 2.1.x. Keep the status
+		 * based on DAGB
+		 */
+		data = MM_ATC_L2_MISC_CG__ENABLE_MASK;
 		data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
 		break;
 	default:
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -795,6 +795,102 @@ static struct kfd_gpu_cache_info yellow_carp_cache_info[] = {
 	},
 };

+static struct kfd_gpu_cache_info gfx1037_cache_info[] = {
+	{
+		/* TCP L1 Cache per CU */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 1,
+	},
+	{
+		/* Scalar L1 Instruction Cache per SQC */
+		.cache_size = 32,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_INST_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* Scalar L1 Data Cache per SQC */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* GL1 Data Cache per SA */
+		.cache_size = 128,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* L2 Data Cache per GPU (Total Tex Cache) */
+		.cache_size = 256,
+		.cache_level = 2,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+				CRAT_CACHE_FLAGS_DATA_CACHE |
+				CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+};
+
+static struct kfd_gpu_cache_info gc_10_3_6_cache_info[] = {
+	{
+		/* TCP L1 Cache per CU */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+			  CRAT_CACHE_FLAGS_DATA_CACHE |
+			  CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 1,
+	},
+	{
+		/* Scalar L1 Instruction Cache per SQC */
+		.cache_size = 32,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+			  CRAT_CACHE_FLAGS_INST_CACHE |
+			  CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* Scalar L1 Data Cache per SQC */
+		.cache_size = 16,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+			  CRAT_CACHE_FLAGS_DATA_CACHE |
+			  CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* GL1 Data Cache per SA */
+		.cache_size = 128,
+		.cache_level = 1,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+			  CRAT_CACHE_FLAGS_DATA_CACHE |
+			  CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+	{
+		/* L2 Data Cache per GPU (Total Tex Cache) */
+		.cache_size = 256,
+		.cache_level = 2,
+		.flags = (CRAT_CACHE_FLAGS_ENABLED |
+			  CRAT_CACHE_FLAGS_DATA_CACHE |
+			  CRAT_CACHE_FLAGS_SIMD_CACHE),
+		.num_cu_shared = 2,
+	},
+};
+
 static void kfd_populated_cu_info_cpu(struct kfd_topology_device *dev,
 		struct crat_subtype_computeunit *cu)
 {
@@ -1514,11 +1610,17 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 			num_of_cache_types = ARRAY_SIZE(beige_goby_cache_info);
 			break;
 		case IP_VERSION(10, 3, 3):
-		case IP_VERSION(10, 3, 6): /* TODO: Double check these on production silicon */
-		case IP_VERSION(10, 3, 7): /* TODO: Double check these on production silicon */
 			pcache_info = yellow_carp_cache_info;
 			num_of_cache_types = ARRAY_SIZE(yellow_carp_cache_info);
 			break;
+		case IP_VERSION(10, 3, 6):
+			pcache_info = gc_10_3_6_cache_info;
+			num_of_cache_types = ARRAY_SIZE(gc_10_3_6_cache_info);
+			break;
+		case IP_VERSION(10, 3, 7):
+			pcache_info = gfx1037_cache_info;
+			num_of_cache_types = ARRAY_SIZE(gfx1037_cache_info);
+			break;
 		case IP_VERSION(11, 0, 0):
 		case IP_VERSION(11, 0, 1):
 		case IP_VERSION(11, 0, 2):
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1369,7 +1369,7 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
 {
 	struct amdgpu_device *adev = drm_to_adev(plane->dev);
 	const struct drm_format_info *info = drm_format_info(format);
-	struct hw_asic_id asic_id = adev->dm.dc->ctx->asic_id;
+	int i;

 	enum dm_micro_swizzle microtile = modifier_gfx9_swizzle_mode(modifier) & 3;

@@ -1386,49 +1386,13 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
 		return true;
 	}

-	/* check if swizzle mode is supported by this version of DCN */
-	switch (asic_id.chip_family) {
-	case FAMILY_SI:
-	case FAMILY_CI:
-	case FAMILY_KV:
-	case FAMILY_CZ:
-	case FAMILY_VI:
-		/* asics before AI does not have modifier support */
-		return false;
-	case FAMILY_AI:
-	case FAMILY_RV:
-	case FAMILY_NV:
-	case FAMILY_VGH:
-	case FAMILY_YELLOW_CARP:
-	case AMDGPU_FAMILY_GC_10_3_6:
-	case AMDGPU_FAMILY_GC_10_3_7:
-		switch (AMD_FMT_MOD_GET(TILE, modifier)) {
-		case AMD_FMT_MOD_TILE_GFX9_64K_R_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_D_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_S_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_D:
-			return true;
-		default:
-			return false;
-		}
-		break;
-	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_1:
-		switch (AMD_FMT_MOD_GET(TILE, modifier)) {
-		case AMD_FMT_MOD_TILE_GFX11_256K_R_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_R_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_D_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_S_X:
-		case AMD_FMT_MOD_TILE_GFX9_64K_D:
-			return true;
-		default:
-			return false;
-		}
-		break;
-	default:
-		ASSERT(0); /* Unknown asic */
-		break;
+	/* Check that the modifier is on the list of the plane's supported modifiers. */
+	for (i = 0; i < plane->modifier_count; i++) {
+		if (modifier == plane->modifiers[i])
+			break;
 	}
+	if (i == plane->modifier_count)
+		return false;

 	/*
 	 * For D swizzle the canonical modifier depends on the bpp, so check
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1270,16 +1270,6 @@ void dcn20_pipe_control_lock(
 					lock,
 					&hw_locks,
 					&inst_flags);
-	} else if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_MAIN) {
-		union dmub_inbox0_cmd_lock_hw hw_lock_cmd = { 0 };
-		hw_lock_cmd.bits.command_code = DMUB_INBOX0_CMD__HW_LOCK;
-		hw_lock_cmd.bits.hw_lock_client = HW_LOCK_CLIENT_DRIVER;
-		hw_lock_cmd.bits.lock_pipe = 1;
-		hw_lock_cmd.bits.otg_inst = pipe->stream_res.tg->inst;
-		hw_lock_cmd.bits.lock = lock;
-		if (!lock)
-			hw_lock_cmd.bits.should_release = 1;
-		dmub_hw_lock_mgr_inbox0_cmd(dc->ctx->dmub_srv, hw_lock_cmd);
 	} else if (pipe->plane_state != NULL && pipe->plane_state->triplebuffer_flips) {
 		if (lock)
 			pipe->stream_res.tg->funcs->triplebuffer_lock(pipe->stream_res.tg);
@@ -1856,7 +1846,7 @@ void dcn20_post_unlock_program_front_end(

 			for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS*1000
 					&& hubp->funcs->hubp_is_flip_pending(hubp); j++)
-				mdelay(1);
+				udelay(1);
 		}
 	}

--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -200,7 +200,7 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];

 		if (!pipe->stream)
-			return false;
+			continue;

 		if (!pipe->plane_state)
 			return false;
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
@@ -25,7 +25,7 @@
 #define SMU13_DRIVER_IF_V13_0_0_H

 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x24
+#define PPTABLE_VERSION 0x26

 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
@@ -109,6 +109,22 @@
 #define FEATURE_SPARE_63_BIT                  63
 #define NUM_FEATURES                          64

+#define ALLOWED_FEATURE_CTRL_DEFAULT 0xFFFFFFFFFFFFFFFFULL
+#define ALLOWED_FEATURE_CTRL_SCPM	((1 << FEATURE_DPM_GFXCLK_BIT) | \
+									(1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \
+									(1 << FEATURE_DPM_UCLK_BIT) | \
+									(1 << FEATURE_DPM_FCLK_BIT) | \
+									(1 << FEATURE_DPM_SOCCLK_BIT) | \
+									(1 << FEATURE_DPM_MP0CLK_BIT) | \
+									(1 << FEATURE_DPM_LINK_BIT) | \
+									(1 << FEATURE_DPM_DCN_BIT) | \
+									(1 << FEATURE_DS_GFXCLK_BIT) | \
+									(1 << FEATURE_DS_SOCCLK_BIT) | \
+									(1 << FEATURE_DS_FCLK_BIT) | \
+									(1 << FEATURE_DS_LCLK_BIT) | \
+									(1 << FEATURE_DS_DCFCLK_BIT) | \
+									(1 << FEATURE_DS_UCLK_BIT))
+
 //For use with feature control messages
 typedef enum {
  FEATURE_PWR_ALL,
@@ -133,6 +149,7 @@ typedef enum {
 #define DEBUG_OVERRIDE_DISABLE_DFLL                    0x00000200
 #define DEBUG_OVERRIDE_ENABLE_RLC_VF_BRINGUP_MODE      0x00000400
 #define DEBUG_OVERRIDE_DFLL_MASTER_MODE                0x00000800
+#define DEBUG_OVERRIDE_ENABLE_PROFILING_MODE           0x00001000

 // VR Mapping Bit Defines
 #define VR_MAPPING_VR_SELECT_MASK  0x01
@@ -262,15 +279,15 @@ typedef enum {
 } I2cControllerPort_e;

 typedef enum {
-  I2C_CONTROLLER_NAME_VR_GFX = 0,
-  I2C_CONTROLLER_NAME_VR_SOC,
-  I2C_CONTROLLER_NAME_VR_VMEMP,
-  I2C_CONTROLLER_NAME_VR_VDDIO,
-  I2C_CONTROLLER_NAME_LIQUID0,
-  I2C_CONTROLLER_NAME_LIQUID1,
-  I2C_CONTROLLER_NAME_PLX,
-  I2C_CONTROLLER_NAME_OTHER,
-  I2C_CONTROLLER_NAME_COUNT,
+	I2C_CONTROLLER_NAME_VR_GFX = 0,
+	I2C_CONTROLLER_NAME_VR_SOC,
+	I2C_CONTROLLER_NAME_VR_VMEMP,
+	I2C_CONTROLLER_NAME_VR_VDDIO,
+	I2C_CONTROLLER_NAME_LIQUID0,
+	I2C_CONTROLLER_NAME_LIQUID1,
+	I2C_CONTROLLER_NAME_PLX,
+	I2C_CONTROLLER_NAME_FAN_INTAKE,
+	I2C_CONTROLLER_NAME_COUNT,
 } I2cControllerName_e;

 typedef enum {
@@ -282,16 +299,17 @@ typedef enum {
  I2C_CONTROLLER_THROTTLER_LIQUID0,
  I2C_CONTROLLER_THROTTLER_LIQUID1,
  I2C_CONTROLLER_THROTTLER_PLX,
+  I2C_CONTROLLER_THROTTLER_FAN_INTAKE,
  I2C_CONTROLLER_THROTTLER_INA3221,
  I2C_CONTROLLER_THROTTLER_COUNT,
 } I2cControllerThrottler_e;

 typedef enum {
-  I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5,
-  I2C_CONTROLLER_PROTOCOL_VR_IR35217,
-  I2C_CONTROLLER_PROTOCOL_TMP_TMP102A,
-  I2C_CONTROLLER_PROTOCOL_INA3221,
-  I2C_CONTROLLER_PROTOCOL_COUNT,
+	I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5,
+	I2C_CONTROLLER_PROTOCOL_VR_IR35217,
+	I2C_CONTROLLER_PROTOCOL_TMP_MAX31875,
+	I2C_CONTROLLER_PROTOCOL_INA3221,
+	I2C_CONTROLLER_PROTOCOL_COUNT,
 } I2cControllerProtocol_e;

 typedef struct {
@@ -658,13 +676,20 @@ typedef struct {

 #define PP_NUM_OD_VF_CURVE_POINTS PP_NUM_RTAVFS_PWL_ZONES + 1

+typedef enum {
+	FAN_MODE_AUTO = 0,
+	FAN_MODE_MANUAL_LINEAR,
+} FanMode_e;

 typedef struct {
  uint32_t FeatureCtrlMask;

  //Voltage control
  int16_t                VoltageOffsetPerZoneBoundary[PP_NUM_OD_VF_CURVE_POINTS];
-  uint16_t               reserved[2];
+  uint16_t               VddGfxVmax;         // in mV
+
+  uint8_t                IdlePwrSavingFeaturesCtrl;
+  uint8_t                RuntimePwrSavingFeaturesCtrl;

  //Frequency changes
  int16_t                GfxclkFmin;           // MHz
@@ -674,7 +699,7 @@ typedef struct {

  //PPT
  int16_t                Ppt;         // %
-  int16_t                reserved1;
+  int16_t                Tdc;

  //Fan control
  uint8_t                FanLinearPwmPoints[NUM_OD_FAN_MAX_POINTS];
@@ -701,16 +726,19 @@ typedef struct {
  uint32_t FeatureCtrlMask;

  int16_t VoltageOffsetPerZoneBoundary;
-  uint16_t               reserved[2];
+  uint16_t               VddGfxVmax;         // in mV

-  uint16_t               GfxclkFmin;           // MHz
-  uint16_t               GfxclkFmax;           // MHz
+  uint8_t                IdlePwrSavingFeaturesCtrl;
+  uint8_t                RuntimePwrSavingFeaturesCtrl;
+
+  int16_t               GfxclkFmin;           // MHz
+  int16_t               GfxclkFmax;           // MHz
  uint16_t               UclkFmin;             // MHz
  uint16_t               UclkFmax;             // MHz

  //PPT
  int16_t                Ppt;         // %
-  int16_t                reserved1;
+  int16_t                Tdc;

  uint8_t                FanLinearPwmPoints;
  uint8_t                FanLinearTempPoints;
@@ -857,7 +885,8 @@ typedef struct {
  uint16_t  FanStartTempMin;
  uint16_t  FanStartTempMax;

-  uint32_t Spare[12];
+  uint16_t  PowerMinPpt0[POWER_SOURCE_COUNT];
+  uint32_t Spare[11];

 } MsgLimits_t;

@@ -1041,7 +1070,17 @@ typedef struct {
  uint32_t        GfxoffSpare[15];

  // GFX GPO
-  uint32_t        GfxGpoSpare[16];
+  uint32_t        DfllBtcMasterScalerM;
+  int32_t         DfllBtcMasterScalerB;
+  uint32_t        DfllBtcSlaveScalerM;
+  int32_t         DfllBtcSlaveScalerB;
+
+  uint32_t        DfllPccAsWaitCtrl; //GDFLL_AS_WAIT_CTRL_PCC register value to be passed to RLC msg
+  uint32_t        DfllPccAsStepCtrl; //GDFLL_AS_STEP_CTRL_PCC register value to be passed to RLC msg
+
+  uint32_t        DfllL2FrequencyBoostM; //Unitless (float)
+  uint32_t        DfllL2FrequencyBoostB; //In MHz (integer)
+  uint32_t        GfxGpoSpare[8];

  // GFX DCS

@@ -1114,12 +1153,14 @@ typedef struct {
  uint16_t IntakeTempHighIntakeAcousticLimit;
  uint16_t IntakeTempAcouticLimitReleaseRate;

-  uint16_t FanStalledTempLimitOffset;
+  int16_t FanAbnormalTempLimitOffset;
  uint16_t FanStalledTriggerRpm;
-  uint16_t FanAbnormalTriggerRpm;
-  uint16_t FanPadding;
+  uint16_t FanAbnormalTriggerRpmCoeff;
+  uint16_t FanAbnormalDetectionEnable;

-  uint32_t     FanSpare[14];
+  uint8_t      FanIntakeSensorSupport;
+  uint8_t      FanIntakePadding[3];
+  uint32_t     FanSpare[13];

  // SECTION: VDD_GFX AVFS

@@ -1198,8 +1239,13 @@ typedef struct {
  int16_t     TotalBoardPowerM;
  int16_t     TotalBoardPowerB;

+  //PMFW-11158
+  QuadraticInt_t qFeffCoeffGameClock[POWER_SOURCE_COUNT];
+  QuadraticInt_t qFeffCoeffBaseClock[POWER_SOURCE_COUNT];
+  QuadraticInt_t qFeffCoeffBoostClock[POWER_SOURCE_COUNT];
+
  // SECTION: Sku Reserved
-  uint32_t         Spare[61];
+  uint32_t         Spare[43];

  // Padding for MMHUB - do not modify this
  uint32_t     MmHubPadding[8];
@@ -1288,8 +1334,11 @@ typedef struct {
  uint32_t    PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued
  uint32_t    BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS

+  uint8_t     FuseWritePowerMuxPresent;
+  uint8_t     FuseWritePadding[3];
+
  // SECTION: Board Reserved
-  uint32_t     BoardSpare[64];
+  uint32_t     BoardSpare[63];

  // SECTION: Structure Padding

@@ -1381,7 +1430,7 @@ typedef struct {
  uint16_t AverageTotalBoardPower;

  uint16_t AvgTemperature[TEMP_COUNT];
-  uint16_t TempPadding;
+  uint16_t AvgTemperatureFanIntake;

  uint8_t  PcieRate               ;
  uint8_t  PcieWidth              ;
@@ -1550,5 +1599,7 @@ typedef struct {
 #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D0            0x5
 #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D3            0x6
 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING  0x7
+#define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
+#define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9

 #endif
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -30,7 +30,7 @@
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D

--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -289,7 +289,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
 		smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE;
 		break;
 	case IP_VERSION(13, 0, 0):
-		smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_0;
+	case IP_VERSION(13, 0, 10):
+		smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10;
 		break;
 	case IP_VERSION(13, 0, 7):
 		smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_7;
@@ -305,9 +306,6 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
 	case IP_VERSION(13, 0, 5):
 		smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_5;
 		break;
-	case IP_VERSION(13, 0, 10):
-		smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_10;
-		break;
 	default:
 		dev_err(adev->dev, "smu unsupported IP version: 0x%x.\n",
 			adev->ip_versions[MP1_HWIP][0]);
@@ -842,6 +840,7 @@ int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable)
 	case IP_VERSION(13, 0, 5):
 	case IP_VERSION(13, 0, 7):
 	case IP_VERSION(13, 0, 8):
+	case IP_VERSION(13, 0, 10):
 		if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 			return 0;
 		if (enable)
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -105,6 +105,7 @@ struct ps8640 {
 	struct gpio_desc *gpio_powerdown;
 	struct device_link *link;
 	bool pre_enabled;
+	bool need_post_hpd_delay;
 };

 static const struct regmap_config ps8640_regmap_config[] = {
@@ -173,14 +174,31 @@ static int _ps8640_wait_hpd_asserted(struct ps8640 *ps_bridge, unsigned long wai
 {
 	struct regmap *map = ps_bridge->regmap[PAGE2_TOP_CNTL];
 	int status;
+	int ret;

 	/*
 	 * Apparently something about the firmware in the chip signals that
 	 * HPD goes high by reporting GPIO9 as high (even though HPD isn't
 	 * actually connected to GPIO9).
 	 */
-	return regmap_read_poll_timeout(map, PAGE2_GPIO_H, status,
-					status & PS_GPIO9, wait_us / 10, wait_us);
+	ret = regmap_read_poll_timeout(map, PAGE2_GPIO_H, status,
+				       status & PS_GPIO9, wait_us / 10, wait_us);
+
+	/*
+	 * The first time we see HPD go high after a reset we delay an extra
+	 * 50 ms. The best guess is that the MCU is doing "stuff" during this
+	 * time (maybe talking to the panel) and we don't want to interrupt it.
+	 *
+	 * No locking is done around "need_post_hpd_delay". If we're here we
+	 * know we're holding a PM Runtime reference and the only other place
+	 * that touches this is PM Runtime resume.
+	 */
+	if (!ret && ps_bridge->need_post_hpd_delay) {
+		ps_bridge->need_post_hpd_delay = false;
+		msleep(50);
+	}
+
+	return ret;
 }

 static int ps8640_wait_hpd_asserted(struct drm_dp_aux *aux, unsigned long wait_us)
@@ -381,6 +399,9 @@ static int __maybe_unused ps8640_resume(struct device *dev)
 	msleep(50);
 	gpiod_set_value(ps_bridge->gpio_reset, 0);

+	/* We just reset things, so we need a delay after the first HPD */
+	ps_bridge->need_post_hpd_delay = true;
+
 	/*
 	 * Mystery 200 ms delay for the "MCU to be ready". It's unclear if
 	 * this is truly necessary since the MCU will already signal that
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -3957,6 +3957,8 @@ intel_dp_handle_hdmi_link_status_change(struct intel_dp *intel_dp)

 		drm_dp_pcon_hdmi_frl_link_error_count(&intel_dp->aux, &intel_dp->attached_connector->base);

+		intel_dp->frl.is_trained = false;
+
 		/* Restart FRL training or fall back to TMDS mode */
 		intel_dp_check_frl_training(intel_dp);
 	}
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -2293,11 +2293,11 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	}

 	if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
-	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
+	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_P(i915)) {
 		/*
 		 * Wa_1607030317:tgl
 		 * Wa_1607186500:tgl
-		 * Wa_1607297627:tgl,rkl,dg1[a0]
+		 * Wa_1607297627:tgl,rkl,dg1[a0],adlp
 		 *
 		 * On TGL and RKL there are multiple entries for this WA in the
 		 * BSpec; some indicate this is an A0-only WA, others indicate
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -591,8 +591,15 @@ void intel_runtime_pm_enable(struct intel_runtime_pm *rpm)
 		pm_runtime_use_autosuspend(kdev);
 	}

-	/* Enable by default */
-	pm_runtime_allow(kdev);
+	/*
+	 *  FIXME: Temp hammer to keep autosupend disable on lmem supported platforms.
+	 *  As per PCIe specs 5.3.1.4.1, all iomem read write request over a PCIe
+	 *  function will be unsupported in case PCIe endpoint function is in D3.
+	 *  Let's keep i915 autosuspend control 'on' till we fix all known issue
+	 *  with lmem access in D3.
+	 */
+	if (!IS_DGFX(i915))
+		pm_runtime_allow(kdev);

 	/*
 	 * The core calls the driver load handler with an RPM reference held.
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -155,7 +155,7 @@ config DRM_MSM_HDMI
 	  Compile in support for the HDMI output MSM DRM driver. It can
 	  be a primary or a secondary display on device. Note that this is used
 	  only for the direct HDMI output. If the device outputs HDMI data
-	  throught some kind of DSI-to-HDMI bridge, this option can be disabled.
+	  through some kind of DSI-to-HDMI bridge, this option can be disabled.

 config DRM_MSM_HDMI_HDCP
 	bool "Enable HDMI HDCP support in MSM DRM driver"
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -91,7 +91,7 @@ struct a6xx_state_memobj {
 static void *state_kcalloc(struct a6xx_gpu_state *a6xx_state, int nr, size_t objsize)
 {
 	struct a6xx_state_memobj *obj =
-		kzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL);
+		kvzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL);

 	if (!obj)
 		return NULL;
@@ -813,6 +813,9 @@ static struct msm_gpu_state_bo *a6xx_snapshot_gmu_bo(
 {
 	struct msm_gpu_state_bo *snapshot;

+	if (!bo->size)
+		return NULL;
+
 	snapshot = state_kcalloc(a6xx_state, 1, sizeof(*snapshot));
 	if (!snapshot)
 		return NULL;
@@ -1040,8 +1043,13 @@ static void a6xx_gpu_state_destroy(struct kref *kref)
 	if (a6xx_state->gmu_hfi)
 		kvfree(a6xx_state->gmu_hfi->data);

-	list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node)
-		kfree(obj);
+	if (a6xx_state->gmu_debug)
+		kvfree(a6xx_state->gmu_debug->data);
+
+	list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node) {
+		list_del(&obj->node);
+		kvfree(obj);
+	}

 	adreno_gpu_state_destroy(state);
 	kfree(a6xx_state);
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -679,6 +679,9 @@ static int adreno_system_suspend(struct device *dev)
 	struct msm_gpu *gpu = dev_to_gpu(dev);
 	int remaining, ret;

+	if (!gpu)
+		return 0;
+
 	suspend_scheduler(gpu);

 	remaining = wait_event_timeout(gpu->retire_event,
@@ -700,7 +703,12 @@ out:

 static int adreno_system_resume(struct device *dev)
 {
-	resume_scheduler(dev_to_gpu(dev));
+	struct msm_gpu *gpu = dev_to_gpu(dev);
+
+	if (!gpu)
+		return 0;
+
+	resume_scheduler(gpu);
 	return pm_runtime_force_resume(dev);
 }

--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -729,7 +729,12 @@ static char *adreno_gpu_ascii85_encode(u32 *src, size_t len)
 	return buf;
 }

-/* len is expected to be in bytes */
+/* len is expected to be in bytes
+ *
+ * WARNING: *ptr should be allocated with kvmalloc or friends.  It can be free'd
+ * with kvfree() and replaced with a newly kvmalloc'd buffer on the first call
+ * when the unencoded raw data is encoded
+ */
 void adreno_show_object(struct drm_printer *p, void **ptr, int len,
 		bool *encoded)
 {
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -56,8 +56,9 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector)
 	return ret;
 }

-static int mdp4_lvds_connector_mode_valid(struct drm_connector *connector,
-				 struct drm_display_mode *mode)
+static enum drm_mode_status
+mdp4_lvds_connector_mode_valid(struct drm_connector *connector,
+			       struct drm_display_mode *mode)
 {
 	struct mdp4_lvds_connector *mdp4_lvds_connector =
 			to_mdp4_lvds_connector(connector);
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1243,8 +1243,7 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
 {
 	int ret = 0;
 	const u8 *dpcd = ctrl->panel->dpcd;
-	u8 encoding = DP_SET_ANSI_8B10B;
-	u8 ssc;
+	u8 encoding[] = { 0, DP_SET_ANSI_8B10B };
 	u8 assr;
 	struct dp_link_info link_info = {0};

@@ -1256,13 +1255,11 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,

 	dp_aux_link_configure(ctrl->aux, &link_info);

-	if (drm_dp_max_downspread(dpcd)) {
-		ssc = DP_SPREAD_AMP_0_5;
-		drm_dp_dpcd_write(ctrl->aux, DP_DOWNSPREAD_CTRL, &ssc, 1);
-	}
+	if (drm_dp_max_downspread(dpcd))
+		encoding[0] |= DP_SPREAD_AMP_0_5;

-	drm_dp_dpcd_write(ctrl->aux, DP_MAIN_LINK_CHANNEL_CODING_SET,
-				&encoding, 1);
+	/* config DOWNSPREAD_CTRL and MAIN_LINK_CHANNEL_CODING_SET */
+	drm_dp_dpcd_write(ctrl->aux, DP_DOWNSPREAD_CTRL, encoding, 2);

 	if (drm_dp_alternate_scrambler_reset_cap(dpcd)) {
 		assr = DP_ALTERNATE_SCRAMBLER_RESET_ENABLE;
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -1249,7 +1249,7 @@ int dp_display_request_irq(struct msm_dp *dp_display)
 		return -EINVAL;
 	}

-	rc = devm_request_irq(&dp->pdev->dev, dp->irq,
+	rc = devm_request_irq(dp_display->drm_dev->dev, dp->irq,
 			dp_display_irq_handler,
 			IRQF_TRIGGER_HIGH, "dp_display_isr", dp);
 	if (rc < 0) {
@@ -1528,6 +1528,11 @@ void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor)
 	}
 }

+static void of_dp_aux_depopulate_bus_void(void *data)
+{
+	of_dp_aux_depopulate_bus(data);
+}
+
 static int dp_display_get_next_bridge(struct msm_dp *dp)
 {
 	int rc;
@@ -1552,10 +1557,16 @@ static int dp_display_get_next_bridge(struct msm_dp *dp)
 		 * panel driver is probed asynchronously but is the best we
 		 * can do without a bigger driver reorganization.
 		 */
-		rc = devm_of_dp_aux_populate_ep_devices(dp_priv->aux);
+		rc = of_dp_aux_populate_bus(dp_priv->aux, NULL);
 		of_node_put(aux_bus);
 		if (rc)
 			goto error;
+
+		rc = devm_add_action_or_reset(dp->drm_dev->dev,
+						of_dp_aux_depopulate_bus_void,
+						dp_priv->aux);
+		if (rc)
+			goto error;
 	} else if (dp->is_edp) {
 		DRM_ERROR("eDP aux_bus not found\n");
 		return -ENODEV;
@@ -1568,7 +1579,7 @@ static int dp_display_get_next_bridge(struct msm_dp *dp)
 	 * For DisplayPort interfaces external bridges are optional, so
 	 * silently ignore an error if one is not present (-ENODEV).
 	 */
-	rc = dp_parser_find_next_bridge(dp_priv->parser);
+	rc = devm_dp_parser_find_next_bridge(dp->drm_dev->dev, dp_priv->parser);
 	if (!dp->is_edp && rc == -ENODEV)
 		return 0;

@@ -1597,6 +1608,12 @@ int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev,
 		return -EINVAL;

 	priv = dev->dev_private;
+
+	if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
+		DRM_DEV_ERROR(dev->dev, "too many bridges\n");
+		return -ENOSPC;
+	}
+
 	dp_display->drm_dev = dev;

 	dp_priv = container_of(dp_display, struct dp_display_private, dp_display);
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -31,6 +31,36 @@ static enum drm_connector_status dp_bridge_detect(struct drm_bridge *bridge)
 					connector_status_disconnected;
 }

+static int dp_bridge_atomic_check(struct drm_bridge *bridge,
+			    struct drm_bridge_state *bridge_state,
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_connector_state *conn_state)
+{
+	struct msm_dp *dp;
+
+	dp = to_dp_bridge(bridge)->dp_display;
+
+	drm_dbg_dp(dp->drm_dev, "is_connected = %s\n",
+		(dp->is_connected) ? "true" : "false");
+
+	/*
+	 * There is no protection in the DRM framework to check if the display
+	 * pipeline has been already disabled before trying to disable it again.
+	 * Hence if the sink is unplugged, the pipeline gets disabled, but the
+	 * crtc->active is still true. Any attempt to set the mode or manually
+	 * disable this encoder will result in the crash.
+	 *
+	 * TODO: add support for telling the DRM subsystem that the pipeline is
+	 * disabled by the hardware and thus all access to it should be forbidden.
+	 * After that this piece of code can be removed.
+	 */
+	if (bridge->ops & DRM_BRIDGE_OP_HPD)
+		return (dp->is_connected) ? 0 : -ENOTCONN;
+
+	return 0;
+}
+
+
 /**
 * dp_bridge_get_modes - callback to add drm modes via drm_mode_probed_add()
 * @bridge: Poiner to drm bridge
@@ -61,6 +91,9 @@ static int dp_bridge_get_modes(struct drm_bridge *bridge, struct drm_connector *
 }

 static const struct drm_bridge_funcs dp_bridge_ops = {
+	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
+	.atomic_destroy_state   = drm_atomic_helper_bridge_destroy_state,
+	.atomic_reset           = drm_atomic_helper_bridge_reset,
 	.enable       = dp_bridge_enable,
 	.disable      = dp_bridge_disable,
 	.post_disable = dp_bridge_post_disable,
@@ -68,6 +101,7 @@ static const struct drm_bridge_funcs dp_bridge_ops = {
 	.mode_valid   = dp_bridge_mode_valid,
 	.get_modes    = dp_bridge_get_modes,
 	.detect       = dp_bridge_detect,
+	.atomic_check = dp_bridge_atomic_check,
 };

 struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev,
--- a/drivers/gpu/drm/msm/dp/dp_parser.c
+++ b/drivers/gpu/drm/msm/dp/dp_parser.c
@@ -240,12 +240,12 @@ static int dp_parser_clock(struct dp_parser *parser)
 	return 0;
 }

-int dp_parser_find_next_bridge(struct dp_parser *parser)
+int devm_dp_parser_find_next_bridge(struct device *dev, struct dp_parser *parser)
 {
-	struct device *dev = &parser->pdev->dev;
+	struct platform_device *pdev = parser->pdev;
 	struct drm_bridge *bridge;

-	bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0);
+	bridge = devm_drm_of_get_bridge(dev, pdev->dev.of_node, 1, 0);
 	if (IS_ERR(bridge))
 		return PTR_ERR(bridge);

--- a/drivers/gpu/drm/msm/dp/dp_parser.h
+++ b/drivers/gpu/drm/msm/dp/dp_parser.h
@@ -138,8 +138,9 @@ struct dp_parser {
 struct dp_parser *dp_parser_get(struct platform_device *pdev);

 /**
- * dp_parser_find_next_bridge() - find an additional bridge to DP
+ * devm_dp_parser_find_next_bridge() - find an additional bridge to DP
 *
+ * @dev: device to tie bridge lifetime to
 * @parser: dp_parser data from client
 *
 * This function is used to find any additional bridge attached to
@@ -147,6 +148,6 @@ struct dp_parser *dp_parser_get(struct platform_device *pdev);
 *
 * Return: 0 if able to get the bridge, otherwise negative errno for failure.
 */
-int dp_parser_find_next_bridge(struct dp_parser *parser);
+int devm_dp_parser_find_next_bridge(struct device *dev, struct dp_parser *parser);

 #endif
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -218,6 +218,12 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		return -EINVAL;

 	priv = dev->dev_private;
+
+	if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
+		DRM_DEV_ERROR(dev->dev, "too many bridges\n");
+		return -ENOSPC;
+	}
+
 	msm_dsi->dev = dev;

 	ret = msm_dsi_host_modeset_init(msm_dsi->host, dev);
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -300,6 +300,11 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 	struct platform_device *pdev = hdmi->pdev;
 	int ret;

+	if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
+		DRM_DEV_ERROR(dev->dev, "too many bridges\n");
+		return -ENOSPC;
+	}
+
 	hdmi->dev = dev;
 	hdmi->encoder = encoder;

@@ -339,7 +344,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
 		goto fail;
 	}

-	ret = devm_request_irq(&pdev->dev, hdmi->irq,
+	ret = devm_request_irq(dev->dev, hdmi->irq,
 			msm_hdmi_irq, IRQF_TRIGGER_HIGH,
 			"hdmi_isr", hdmi);
 	if (ret < 0) {
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -247,6 +247,7 @@ static int msm_drm_uninit(struct device *dev)

 	for (i = 0; i < priv->num_bridges; i++)
 		drm_bridge_remove(priv->bridges[i]);
+	priv->num_bridges = 0;

 	pm_runtime_get_sync(dev);
 	msm_irq_uninstall(ddev);
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -501,11 +501,11 @@ out:
 */
 static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 {
-	unsigned cleanup_flags = BO_LOCKED | BO_OBJ_PINNED;
+	unsigned cleanup_flags = BO_LOCKED;
 	unsigned i;

 	if (error)
-		cleanup_flags |= BO_VMA_PINNED;
+		cleanup_flags |= BO_VMA_PINNED | BO_OBJ_PINNED;

 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
@@ -706,7 +706,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_drm_private *priv = dev->dev_private;
 	struct drm_msm_gem_submit *args = data;
 	struct msm_file_private *ctx = file->driver_priv;
-	struct msm_gem_submit *submit = NULL;
+	struct msm_gem_submit *submit;
 	struct msm_gpu *gpu = priv->gpu;
 	struct msm_gpu_submitqueue *queue;
 	struct msm_ringbuffer *ring;
@@ -946,8 +946,7 @@ out_unlock:
 		put_unused_fd(out_fence_fd);
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (submit)
-		msm_gem_submit_put(submit);
+	msm_gem_submit_put(submit);
 	if (!IS_ERR_OR_NULL(post_deps)) {
 		for (i = 0; i < args->nr_out_syncobjs; ++i) {
 			kfree(post_deps[i].chain);
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -997,4 +997,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 	}

 	msm_devfreq_cleanup(gpu);
+
+	platform_set_drvdata(gpu->pdev, NULL);
 }
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -280,6 +280,10 @@ struct msm_gpu {
 static inline struct msm_gpu *dev_to_gpu(struct device *dev)
 {
 	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev);
+
+	if (!adreno_smmu)
+		return NULL;
+
 	return container_of(adreno_smmu, struct msm_gpu, adreno_smmu);
 }

--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -25,7 +25,8 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)

 		msm_gem_lock(obj);
 		msm_gem_unpin_vma_fenced(submit->bos[i].vma, fctx);
-		submit->bos[i].flags &= ~BO_VMA_PINNED;
+		msm_gem_unpin_locked(obj);
+		submit->bos[i].flags &= ~(BO_VMA_PINNED | BO_OBJ_PINNED);
 		msm_gem_unlock(obj);
 	}

--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -207,6 +207,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
 						 finish_cb);

+	dma_fence_put(f);
 	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
 	schedule_work(&job->work);
 }
@@ -234,8 +235,10 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
 		struct drm_sched_fence *s_fence = job->s_fence;

 		/* Wait for all dependencies to avoid data corruptions */
-		while ((f = drm_sched_job_dependency(job, entity)))
+		while ((f = drm_sched_job_dependency(job, entity))) {
 			dma_fence_wait(f, false);
+			dma_fence_put(f);
+		}

 		drm_sched_fence_scheduled(s_fence);
 		dma_fence_set_error(&s_fence->finished, -ESRCH);
@@ -250,6 +253,7 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
 			continue;
 		}

+		dma_fence_get(entity->last_scheduled);
 		r = dma_fence_add_callback(entity->last_scheduled,
 					   &job->finish_cb,
 					   drm_sched_entity_kill_jobs_cb);
--- a/drivers/media/test-drivers/vivid/vivid-core.c
+++ b/drivers/media/test-drivers/vivid/vivid-core.c
@@ -339,6 +339,28 @@ static int vidioc_g_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *a
 	return vivid_vid_out_g_fbuf(file, fh, a);
 }

+/*
+ * Only support the framebuffer of one of the vivid instances.
+ * Anything else is rejected.
+ */
+bool vivid_validate_fb(const struct v4l2_framebuffer *a)
+{
+	struct vivid_dev *dev;
+	int i;
+
+	for (i = 0; i < n_devs; i++) {
+		dev = vivid_devs[i];
+		if (!dev || !dev->video_pbase)
+			continue;
+		if ((unsigned long)a->base == dev->video_pbase &&
+		    a->fmt.width <= dev->display_width &&
+		    a->fmt.height <= dev->display_height &&
+		    a->fmt.bytesperline <= dev->display_byte_stride)
+			return true;
+	}
+	return false;
+}
+
 static int vidioc_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuffer *a)
 {
 	struct video_device *vdev = video_devdata(file);
@@ -920,8 +942,12 @@ static int vivid_detect_feature_set(struct vivid_dev *dev, int inst,

 	/* how many inputs do we have and of what type? */
 	dev->num_inputs = num_inputs[inst];
-	if (dev->num_inputs < 1)
-		dev->num_inputs = 1;
+	if (node_type & 0x20007) {
+		if (dev->num_inputs < 1)
+			dev->num_inputs = 1;
+	} else {
+		dev->num_inputs = 0;
+	}
 	if (dev->num_inputs >= MAX_INPUTS)
 		dev->num_inputs = MAX_INPUTS;
 	for (i = 0; i < dev->num_inputs; i++) {
@@ -938,8 +964,12 @@ static int vivid_detect_feature_set(struct vivid_dev *dev, int inst,

 	/* how many outputs do we have and of what type? */
 	dev->num_outputs = num_outputs[inst];
-	if (dev->num_outputs < 1)
-		dev->num_outputs = 1;
+	if (node_type & 0x40300) {
+		if (dev->num_outputs < 1)
+			dev->num_outputs = 1;
+	} else {
+		dev->num_outputs = 0;
+	}
 	if (dev->num_outputs >= MAX_OUTPUTS)
 		dev->num_outputs = MAX_OUTPUTS;
 	for (i = 0; i < dev->num_outputs; i++) {
--- a/drivers/media/test-drivers/vivid/vivid-core.h
+++ b/drivers/media/test-drivers/vivid/vivid-core.h
@@ -613,4 +613,6 @@ static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev)
 	return dev->output_type[dev->output] == HDMI;
 }

+bool vivid_validate_fb(const struct v4l2_framebuffer *a);
+
 #endif
--- a/drivers/media/test-drivers/vivid/vivid-osd.c
+++ b/drivers/media/test-drivers/vivid/vivid-osd.c
@@ -357,7 +357,7 @@ int vivid_fb_init(struct vivid_dev *dev)
 	int ret;

 	dev->video_buffer_size = MAX_OSD_HEIGHT * MAX_OSD_WIDTH * 2;
-	dev->video_vbase = kzalloc(dev->video_buffer_size, GFP_KERNEL | GFP_DMA32);
+	dev->video_vbase = kzalloc(dev->video_buffer_size, GFP_KERNEL);
 	if (dev->video_vbase == NULL)
 		return -ENOMEM;
 	dev->video_pbase = virt_to_phys(dev->video_vbase);
--- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c
+++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
@@ -453,6 +453,12 @@ void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls)
 	tpg_reset_source(&dev->tpg, dev->src_rect.width, dev->src_rect.height, dev->field_cap);
 	dev->crop_cap = dev->src_rect;
 	dev->crop_bounds_cap = dev->src_rect;
+	if (dev->bitmap_cap &&
+	    (dev->compose_cap.width != dev->crop_cap.width ||
+	     dev->compose_cap.height != dev->crop_cap.height)) {
+		vfree(dev->bitmap_cap);
+		dev->bitmap_cap = NULL;
+	}
 	dev->compose_cap = dev->crop_cap;
 	if (V4L2_FIELD_HAS_T_OR_B(dev->field_cap))
 		dev->compose_cap.height /= 2;
@@ -460,6 +466,14 @@ void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls)
 	tpg_s_video_aspect(&dev->tpg, vivid_get_video_aspect(dev));
 	tpg_s_pixel_aspect(&dev->tpg, vivid_get_pixel_aspect(dev));
 	tpg_update_mv_step(&dev->tpg);
+
+	/*
+	 * We can be called from within s_ctrl, in that case we can't
+	 * modify controls. Luckily we don't need to in that case.
+	 */
+	if (keep_controls)
+		return;
+
 	dims[0] = roundup(dev->src_rect.width, PIXEL_ARRAY_DIV);
 	dims[1] = roundup(dev->src_rect.height, PIXEL_ARRAY_DIV);
 	v4l2_ctrl_modify_dimensions(dev->pixel_array, dims);
@@ -913,6 +927,8 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection
 	struct vivid_dev *dev = video_drvdata(file);
 	struct v4l2_rect *crop = &dev->crop_cap;
 	struct v4l2_rect *compose = &dev->compose_cap;
+	unsigned orig_compose_w = compose->width;
+	unsigned orig_compose_h = compose->height;
 	unsigned factor = V4L2_FIELD_HAS_T_OR_B(dev->field_cap) ? 2 : 1;
 	int ret;

@@ -1029,17 +1045,17 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection
 			s->r.height /= factor;
 		}
 		v4l2_rect_map_inside(&s->r, &dev->fmt_cap_rect);
-		if (dev->bitmap_cap && (compose->width != s->r.width ||
-					compose->height != s->r.height)) {
-			vfree(dev->bitmap_cap);
-			dev->bitmap_cap = NULL;
-		}
 		*compose = s->r;
 		break;
 	default:
 		return -EINVAL;
 	}

+	if (dev->bitmap_cap && (compose->width != orig_compose_w ||
+				compose->height != orig_compose_h)) {
+		vfree(dev->bitmap_cap);
+		dev->bitmap_cap = NULL;
+	}
 	tpg_s_crop_compose(&dev->tpg, crop, compose);
 	return 0;
 }
@@ -1276,7 +1292,14 @@ int vivid_vid_cap_s_fbuf(struct file *file, void *fh,
 		return -EINVAL;
 	if (a->fmt.bytesperline < (a->fmt.width * fmt->bit_depth[0]) / 8)
 		return -EINVAL;
-	if (a->fmt.height * a->fmt.bytesperline < a->fmt.sizeimage)
+	if (a->fmt.bytesperline > a->fmt.sizeimage / a->fmt.height)
+		return -EINVAL;
+
+	/*
+	 * Only support the framebuffer of one of the vivid instances.
+	 * Anything else is rejected.
+	 */
+	if (!vivid_validate_fb(a))
 		return -EINVAL;

 	dev->fb_vbase_cap = phys_to_virt((unsigned long)a->base);
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -161,6 +161,20 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t,
 	    (bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) ||
 	    (!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE)))
 		return false;
+
+	/* sanity checks for the blanking timings */
+	if (!bt->interlaced &&
+	    (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch))
+		return false;
+	if (bt->hfrontporch > 2 * bt->width ||
+	    bt->hsync > 1024 || bt->hbackporch > 1024)
+		return false;
+	if (bt->vfrontporch > 4096 ||
+	    bt->vsync > 128 || bt->vbackporch > 4096)
+		return false;
+	if (bt->interlaced && (bt->il_vfrontporch > 4096 ||
+	    bt->il_vsync > 128 || bt->il_vbackporch > 4096))
+		return false;
 	return fnc == NULL || fnc(t, fnc_handle);
 }
 EXPORT_SYMBOL_GPL(v4l2_valid_dv_timings);
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -134,6 +134,7 @@ struct mmc_blk_data {
 	 * track of the current selected device partition.
 	 */
 	unsigned int	part_curr;
+#define MMC_BLK_PART_INVALID	UINT_MAX	/* Unknown partition active */
 	int	area_type;

 	/* debugfs files (only in main mmc_blk_data) */
@@ -987,33 +988,39 @@ static unsigned int mmc_blk_data_timeout_ms(struct mmc_host *host,
 	return ms;
 }

+/*
+ * Attempts to reset the card and get back to the requested partition.
+ * Therefore any error here must result in cancelling the block layer
+ * request, it must not be reattempted without going through the mmc_blk
+ * partition sanity checks.
+ */
 static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host,
 			 int type)
 {
 	int err;
+	struct mmc_blk_data *main_md = dev_get_drvdata(&host->card->dev);

 	if (md->reset_done & type)
 		return -EEXIST;

 	md->reset_done |= type;
 	err = mmc_hw_reset(host->card);
+	/*
+	 * A successful reset will leave the card in the main partition, but
+	 * upon failure it might not be, so set it to MMC_BLK_PART_INVALID
+	 * in that case.
+	 */
+	main_md->part_curr = err ? MMC_BLK_PART_INVALID : main_md->part_type;
+	if (err)
+		return err;
 	/* Ensure we switch back to the correct partition */
-	if (err) {
-		struct mmc_blk_data *main_md =
-			dev_get_drvdata(&host->card->dev);
-		int part_err;
-
-		main_md->part_curr = main_md->part_type;
-		part_err = mmc_blk_part_switch(host->card, md->part_type);
-		if (part_err) {
-			/*
-			 * We have failed to get back into the correct
-			 * partition, so we need to abort the whole request.
-			 */
-			return -ENODEV;
-		}
-	}
-	return err;
+	if (mmc_blk_part_switch(host->card, md->part_type))
+		/*
+		 * We have failed to get back into the correct
+		 * partition, so we need to abort the whole request.
+		 */
+		return -ENODEV;
+	return 0;
 }

 static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
@@ -1871,8 +1878,9 @@ static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req)
 		return;

 	/* Reset before last retry */
-	if (mqrq->retries + 1 == MMC_MAX_RETRIES)
-		mmc_blk_reset(md, card->host, type);
+	if (mqrq->retries + 1 == MMC_MAX_RETRIES &&
+	    mmc_blk_reset(md, card->host, type))
+		return;

 	/* Command errors fail fast, so use all MMC_MAX_RETRIES */
 	if (brq->sbc.error || brq->cmd.error)
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -48,6 +48,7 @@ static enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
 	case REQ_OP_DRV_OUT:
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
 		return MMC_ISSUE_SYNC;
 	case REQ_OP_FLUSH:
 		return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
@@ -493,6 +494,13 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 	if (blk_queue_quiesced(q))
 		blk_mq_unquiesce_queue(q);

+	/*
+	 * If the recovery completes the last (and only remaining) request in
+	 * the queue, and the card has been removed, we could end up here with
+	 * the recovery not quite finished yet, so cancel it.
+	 */
+	cancel_work_sync(&mq->recovery_work);
+
 	blk_mq_free_tag_set(&mq->tag_set);

 	/*
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -291,7 +291,8 @@ static void sdio_release_func(struct device *dev)
 {
 	struct sdio_func *func = dev_to_sdio_func(dev);

-	sdio_free_func_cis(func);
+	if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO))
+		sdio_free_func_cis(func);

 	kfree(func->info);
 	kfree(func->tmpbuf);
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -1075,9 +1075,10 @@ config MMC_SDHCI_OMAP

 config MMC_SDHCI_AM654
 	tristate "Support for the SDHCI Controller in TI's AM654 SOCs"
-	depends on MMC_SDHCI_PLTFM && OF && REGMAP_MMIO
+	depends on MMC_SDHCI_PLTFM && OF
 	select MMC_SDHCI_IO_ACCESSORS
 	select MMC_CQHCI
+	select REGMAP_MMIO
 	help
 	  This selects the Secure Digital Host Controller Interface (SDHCI)
 	  support present in TI's AM654 SOCs. The controller supports
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1660,6 +1660,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		host->mmc_host_ops.execute_tuning = usdhc_execute_tuning;
 	}

+	err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data);
+	if (err)
+		goto disable_ahb_clk;
+
 	if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING)
 		sdhci_esdhc_ops.platform_execute_tuning =
 					esdhc_executing_tuning;
@@ -1667,13 +1671,15 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 	if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536)
 		host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;

-	if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
+	if (host->caps & MMC_CAP_8_BIT_DATA &&
+	    imx_data->socdata->flags & ESDHC_FLAG_HS400)
 		host->mmc->caps2 |= MMC_CAP2_HS400;

 	if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23)
 		host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN;

-	if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) {
+	if (host->caps & MMC_CAP_8_BIT_DATA &&
+	    imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) {
 		host->mmc->caps2 |= MMC_CAP2_HS400_ES;
 		host->mmc_host_ops.hs400_enhanced_strobe =
 					esdhc_hs400_enhanced_strobe;
@@ -1695,10 +1701,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 			goto disable_ahb_clk;
 	}

-	err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data);
-	if (err)
-		goto disable_ahb_clk;
-
 	sdhci_esdhc_imx_hwinit(host);

 	err = sdhci_add_host(host);
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -914,6 +914,12 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot)
 		dmi_match(DMI_SYS_VENDOR, "IRBIS"));
 }

+static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot)
+{
+	return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_JSL_EMMC &&
+			dmi_match(DMI_BIOS_VENDOR, "ASUSTeK COMPUTER INC.");
+}
+
 static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	int ret = byt_emmc_probe_slot(slot);
@@ -922,9 +928,11 @@ static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot)
 		slot->host->mmc->caps2 |= MMC_CAP2_CQE;

 	if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) {
-		slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES;
-		slot->host->mmc_host_ops.hs400_enhanced_strobe =
-						intel_hs400_enhanced_strobe;
+		if (!jsl_broken_hs400es(slot)) {
+			slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES;
+			slot->host->mmc_host_ops.hs400_enhanced_strobe =
+							intel_hs400_enhanced_strobe;
+		}
 		slot->host->mmc->caps2 |= MMC_CAP2_CQE_DCMD;
 	}

--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -562,7 +562,7 @@ static void mtd_check_of_node(struct mtd_info *mtd)
 	if (!mtd_is_partition(mtd))
 		return;
 	parent = mtd->parent;
-	parent_dn = dev_of_node(&parent->dev);
+	parent_dn = of_node_get(dev_of_node(&parent->dev));
 	if (!parent_dn)
 		return;

--- a/drivers/mtd/nand/raw/intel-nand-controller.c
+++ b/drivers/mtd/nand/raw/intel-nand-controller.c
@@ -608,11 +608,12 @@ static int ebu_nand_probe(struct platform_device *pdev)
 	ret = of_property_read_u32(chip_np, "reg", &cs);
 	if (ret) {
 		dev_err(dev, "failed to get chip select: %d\n", ret);
-		return ret;
+		goto err_of_node_put;
 	}
 	if (cs >= MAX_CS) {
 		dev_err(dev, "got invalid chip select: %d\n", cs);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_of_node_put;
 	}

 	ebu_host->cs_num = cs;
@@ -620,18 +621,22 @@ static int ebu_nand_probe(struct platform_device *pdev)
 	resname = devm_kasprintf(dev, GFP_KERNEL, "nand_cs%d", cs);
 	ebu_host->cs[cs].chipaddr = devm_platform_ioremap_resource_byname(pdev,
 									  resname);
-	if (IS_ERR(ebu_host->cs[cs].chipaddr))
-		return PTR_ERR(ebu_host->cs[cs].chipaddr);
+	if (IS_ERR(ebu_host->cs[cs].chipaddr)) {
+		ret = PTR_ERR(ebu_host->cs[cs].chipaddr);
+		goto err_of_node_put;
+	}

 	ebu_host->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(ebu_host->clk))
-		return dev_err_probe(dev, PTR_ERR(ebu_host->clk),
-				     "failed to get clock\n");
+	if (IS_ERR(ebu_host->clk)) {
+		ret = dev_err_probe(dev, PTR_ERR(ebu_host->clk),
+				    "failed to get clock\n");
+		goto err_of_node_put;
+	}

 	ret = clk_prepare_enable(ebu_host->clk);
 	if (ret) {
 		dev_err(dev, "failed to enable clock: %d\n", ret);
-		return ret;
+		goto err_of_node_put;
 	}

 	ebu_host->dma_tx = dma_request_chan(dev, "tx");
@@ -695,6 +700,8 @@ err_cleanup_dma:
 	ebu_dma_cleanup(ebu_host);
 err_disable_unprepare_clk:
 	clk_disable_unprepare(ebu_host->clk);
+err_of_node_put:
+	of_node_put(chip_np);

 	return ret;
 }
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2678,7 +2678,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);

-	if (!of_property_read_bool(np, "marvell,nand-keep-config"))
+	if (of_property_read_bool(np, "marvell,nand-keep-config"))
 		chip->options |= NAND_KEEP_TIMINGS;

 	mtd = nand_to_mtd(chip);
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -1181,7 +1181,7 @@ static int tegra_nand_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	err = pm_runtime_resume_and_get(&pdev->dev);
 	if (err)
-		return err;
+		goto err_dis_pm;

 	err = reset_control_reset(rst);
 	if (err) {
@@ -1215,6 +1215,8 @@ static int tegra_nand_probe(struct platform_device *pdev)
 err_put_pm:
 	pm_runtime_put_sync_suspend(ctrl->dev);
 	pm_runtime_force_suspend(ctrl->dev);
+err_dis_pm:
+	pm_runtime_disable(&pdev->dev);
 	return err;
 }

--- a/drivers/mtd/parsers/bcm47xxpart.c
+++ b/drivers/mtd/parsers/bcm47xxpart.c
@@ -233,11 +233,11 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 		}

 		/* Read middle of the block */
-		err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read,
+		err = mtd_read(master, offset + (blocksize / 2), 0x4, &bytes_read,
 			       (uint8_t *)buf);
 		if (err && !mtd_is_bitflip(err)) {
 			pr_err("mtd_read error while parsing (offset: 0x%X): %d\n",
-			       offset + 0x8000, err);
+			       offset + (blocksize / 2), err);
 			continue;
 		}

--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -2724,7 +2724,9 @@ static int spi_nor_init(struct spi_nor *nor)
 		 */
 		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
 			  "enabling reset hack; may not recover from unexpected reboots\n");
-		return nor->params->set_4byte_addr_mode(nor, true);
+		err = nor->params->set_4byte_addr_mode(nor, true);
+		if (err && err != -ENOTSUPP)
+			return err;
 	}

 	return 0;
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -322,14 +322,14 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
 					       &mscan_clksrc);
 	if (!priv->can.clock.freq) {
 		dev_err(&ofdev->dev, "couldn't get MSCAN clock properties\n");
-		goto exit_free_mscan;
+		goto exit_put_clock;
 	}

 	err = register_mscandev(dev, mscan_clksrc);
 	if (err) {
 		dev_err(&ofdev->dev, "registering %s failed (err=%d)\n",
 			DRV_NAME, err);
-		goto exit_free_mscan;
+		goto exit_put_clock;
 	}

 	dev_info(&ofdev->dev, "MSCAN at 0x%p, irq %d, clock %d Hz\n",
@@ -337,7 +337,9 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)

 	return 0;

-exit_free_mscan:
+exit_put_clock:
+	if (data->put_clock)
+		data->put_clock(ofdev);
 	free_candev(dev);
 exit_dispose_irq:
 	irq_dispose_mapping(irq);
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1157,11 +1157,13 @@ static void rcar_canfd_handle_global_receive(struct rcar_canfd_global *gpriv, u3
 {
 	struct rcar_canfd_channel *priv = gpriv->ch[ch];
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
-	u32 sts;
+	u32 sts, cc;

 	/* Handle Rx interrupts */
 	sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(gpriv, ridx));
-	if (likely(sts & RCANFD_RFSTS_RFIF)) {
+	cc = rcar_canfd_read(priv->base, RCANFD_RFCC(gpriv, ridx));
+	if (likely(sts & RCANFD_RFSTS_RFIF &&
+		   cc & RCANFD_RFCC_RFIE)) {
 		if (napi_schedule_prep(&priv->napi)) {
 			/* Disable Rx FIFO interrupts */
 			rcar_canfd_clear_bit(priv->base,
@@ -1244,11 +1246,9 @@ static void rcar_canfd_handle_channel_tx(struct rcar_canfd_global *gpriv, u32 ch

 static irqreturn_t rcar_canfd_channel_tx_interrupt(int irq, void *dev_id)
 {
-	struct rcar_canfd_global *gpriv = dev_id;
-	u32 ch;
+	struct rcar_canfd_channel *priv = dev_id;

-	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels)
-		rcar_canfd_handle_channel_tx(gpriv, ch);
+	rcar_canfd_handle_channel_tx(priv->gpriv, priv->channel);

 	return IRQ_HANDLED;
 }
@@ -1276,11 +1276,9 @@ static void rcar_canfd_handle_channel_err(struct rcar_canfd_global *gpriv, u32 c

 static irqreturn_t rcar_canfd_channel_err_interrupt(int irq, void *dev_id)
 {
-	struct rcar_canfd_global *gpriv = dev_id;
-	u32 ch;
+	struct rcar_canfd_channel *priv = dev_id;

-	for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels)
-		rcar_canfd_handle_channel_err(gpriv, ch);
+	rcar_canfd_handle_channel_err(priv->gpriv, priv->channel);

 	return IRQ_HANDLED;
 }
@@ -1721,6 +1719,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 	priv->ndev = ndev;
 	priv->base = gpriv->base;
 	priv->channel = ch;
+	priv->gpriv = gpriv;
 	priv->can.clock.freq = fcan_freq;
 	dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq);

@@ -1749,7 +1748,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 		}
 		err = devm_request_irq(&pdev->dev, err_irq,
 				       rcar_canfd_channel_err_interrupt, 0,
-				       irq_name, gpriv);
+				       irq_name, priv);
 		if (err) {
 			dev_err(&pdev->dev, "devm_request_irq CH Err(%d) failed, error %d\n",
 				err_irq, err);
@@ -1763,7 +1762,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
 		}
 		err = devm_request_irq(&pdev->dev, tx_irq,
 				       rcar_canfd_channel_tx_interrupt, 0,
-				       irq_name, gpriv);
+				       irq_name, priv);
 		if (err) {
 			dev_err(&pdev->dev, "devm_request_irq Tx (%d) failed, error %d\n",
 				tx_irq, err);
@@ -1789,7 +1788,6 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,

 	priv->can.do_set_mode = rcar_canfd_do_set_mode;
 	priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter;
-	priv->gpriv = gpriv;
 	SET_NETDEV_DEV(ndev, &pdev->dev);

 	netif_napi_add_weight(ndev, &priv->napi, rcar_canfd_rx_poll,
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1415,11 +1415,14 @@ static int mcp251x_can_probe(struct spi_device *spi)

 	ret = mcp251x_gpio_setup(priv);
 	if (ret)
-		goto error_probe;
+		goto out_unregister_candev;

 	netdev_info(net, "MCP%x successfully initialized.\n", priv->model);
 	return 0;

+out_unregister_candev:
+	unregister_candev(net);
+
 error_probe:
 	destroy_workqueue(priv->wq);
 	priv->wq = NULL;
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1875,7 +1875,7 @@ static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv)
 {
 	int err;

-	init_completion(&priv->start_comp);
+	reinit_completion(&priv->start_comp);

 	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ,
 					       priv->channel);
@@ -1893,7 +1893,7 @@ static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv)
 {
 	int err;

-	init_completion(&priv->stop_comp);
+	reinit_completion(&priv->stop_comp);

 	/* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT
 	 * see comment in kvaser_usb_hydra_update_state()
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -1320,7 +1320,7 @@ static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv)
 {
 	int err;

-	init_completion(&priv->start_comp);
+	reinit_completion(&priv->start_comp);

 	err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP,
 					      priv->channel);
@@ -1338,7 +1338,7 @@ static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv)
 {
 	int err;

-	init_completion(&priv->stop_comp);
+	reinit_completion(&priv->stop_comp);

 	err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP,
 					      priv->channel);
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -561,8 +561,6 @@ static netdev_tx_t bcm4908_enet_start_xmit(struct sk_buff *skb, struct net_devic

 	if (++ring->write_idx == ring->length - 1)
 		ring->write_idx = 0;
-	enet->netdev->stats.tx_bytes += skb->len;
-	enet->netdev->stats.tx_packets++;

 	return NETDEV_TX_OK;
 }
@@ -635,6 +633,7 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight)
 	struct bcm4908_enet_dma_ring_bd *buf_desc;
 	struct bcm4908_enet_dma_ring_slot *slot;
 	struct device *dev = enet->dev;
+	unsigned int bytes = 0;
 	int handled = 0;

 	while (handled < weight && tx_ring->read_idx != tx_ring->write_idx) {
@@ -645,12 +644,17 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight)

 		dma_unmap_single(dev, slot->dma_addr, slot->len, DMA_TO_DEVICE);
 		dev_kfree_skb(slot->skb);
-		if (++tx_ring->read_idx == tx_ring->length)
-			tx_ring->read_idx = 0;

 		handled++;
+		bytes += slot->len;
+
+		if (++tx_ring->read_idx == tx_ring->length)
+			tx_ring->read_idx = 0;
 	}

+	enet->netdev->stats.tx_packets += handled;
+	enet->netdev->stats.tx_bytes += bytes;
+
 	if (handled < weight) {
 		napi_complete_done(napi, handled);
 		bcm4908_enet_dma_ring_intrs_on(enet, tx_ring);
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1991,6 +1991,9 @@ static int bcm_sysport_open(struct net_device *dev)
 		goto out_clk_disable;
 	}

+	/* Indicate that the MAC is responsible for PHY PM */
+	phydev->mac_managed_pm = true;
+
 	/* Reset house keeping link status */
 	priv->old_duplex = -1;
 	priv->old_link = -1;
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2090,7 +2090,12 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
 	else
 		enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE);

+	/* Also prepare the consumer index in case page allocation never
+	 * succeeds. In that case, hardware will never advance producer index
+	 * to match consumer index, and will drop all frames.
+	 */
 	enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0);
+	enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, 1);

 	/* enable Rx ints by setting pkt thr to 1 */
 	enetc_rxbdr_wr(hw, idx, ENETC_RBICR0, ENETC_RBICR0_ICEN | 0x1);
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2432,6 +2432,31 @@ static u32 fec_enet_register_offset[] = {
 	IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
 	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
 };
+/* for i.MX6ul */
+static u32 fec_enet_register_offset_6ul[] = {
+	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
+	FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
+	FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_RXIC0,
+	FEC_HASH_TABLE_HIGH, FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH,
+	FEC_GRP_HASH_TABLE_LOW, FEC_X_WMRK, FEC_R_DES_START_0,
+	FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM,
+	FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC,
+	RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT,
+	RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG,
+	RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255,
+	RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047,
+	RMON_T_P_GTE2048, RMON_T_OCTETS,
+	IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF,
+	IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE,
+	IEEE_T_FDXFC, IEEE_T_OCTETS_OK,
+	RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN,
+	RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB,
+	RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255,
+	RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047,
+	RMON_R_P_GTE2048, RMON_R_OCTETS,
+	IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
+	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
+};
 #else
 static __u32 fec_enet_register_version = 1;
 static u32 fec_enet_register_offset[] = {
@@ -2456,7 +2481,24 @@ static void fec_enet_get_regs(struct net_device *ndev,
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
 	int ret;
+#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
+	defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
+	defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+	u32 *reg_list;
+	u32 reg_cnt;

+	if (!of_machine_is_compatible("fsl,imx6ul")) {
+		reg_list = fec_enet_register_offset;
+		reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
+	} else {
+		reg_list = fec_enet_register_offset_6ul;
+		reg_cnt = ARRAY_SIZE(fec_enet_register_offset_6ul);
+	}
+#else
+	/* coldfire */
+	static u32 *reg_list = fec_enet_register_offset;
+	static const u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
+#endif
 	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0)
 		return;
@@ -2465,8 +2507,8 @@ static void fec_enet_get_regs(struct net_device *ndev,

 	memset(buf, 0, regs->len);

-	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
-		off = fec_enet_register_offset[i];
+	for (i = 0; i < reg_cnt; i++) {
+		off = reg_list[i];

 		if ((off == FEC_R_BOUND || off == FEC_R_FSTART) &&
 		    !(fep->quirks & FEC_QUIRK_HAS_FRREG))
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -2900,6 +2900,7 @@ static struct device *ehea_register_port(struct ehea_port *port,
 	ret = of_device_register(&port->ofdev);
 	if (ret) {
 		pr_err("failed to register device. ret=%d\n", ret);
+		put_device(&port->ofdev.dev);
 		goto out;
 	}

--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -3185,10 +3185,17 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)

 		if (cmd->flow_type == TCP_V4_FLOW ||
 		    cmd->flow_type == UDP_V4_FLOW) {
-			if (i_set & I40E_L3_SRC_MASK)
-				cmd->data |= RXH_IP_SRC;
-			if (i_set & I40E_L3_DST_MASK)
-				cmd->data |= RXH_IP_DST;
+			if (hw->mac.type == I40E_MAC_X722) {
+				if (i_set & I40E_X722_L3_SRC_MASK)
+					cmd->data |= RXH_IP_SRC;
+				if (i_set & I40E_X722_L3_DST_MASK)
+					cmd->data |= RXH_IP_DST;
+			} else {
+				if (i_set & I40E_L3_SRC_MASK)
+					cmd->data |= RXH_IP_SRC;
+				if (i_set & I40E_L3_DST_MASK)
+					cmd->data |= RXH_IP_DST;
+			}
 		} else if (cmd->flow_type == TCP_V6_FLOW ||
 			  cmd->flow_type == UDP_V6_FLOW) {
 			if (i_set & I40E_L3_V6_SRC_MASK)
@@ -3546,12 +3553,15 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,

 /**
 * i40e_get_rss_hash_bits - Read RSS Hash bits from register
+ * @hw: hw structure
 * @nfc: pointer to user request
 * @i_setc: bits currently set
 *
 * Returns value of bits to be set per user request
 **/
-static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc)
+static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw,
+				  struct ethtool_rxnfc *nfc,
+				  u64 i_setc)
 {
 	u64 i_set = i_setc;
 	u64 src_l3 = 0, dst_l3 = 0;
@@ -3570,8 +3580,13 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc)
 		dst_l3 = I40E_L3_V6_DST_MASK;
 	} else if (nfc->flow_type == TCP_V4_FLOW ||
 		  nfc->flow_type == UDP_V4_FLOW) {
-		src_l3 = I40E_L3_SRC_MASK;
-		dst_l3 = I40E_L3_DST_MASK;
+		if (hw->mac.type == I40E_MAC_X722) {
+			src_l3 = I40E_X722_L3_SRC_MASK;
+			dst_l3 = I40E_X722_L3_DST_MASK;
+		} else {
+			src_l3 = I40E_L3_SRC_MASK;
+			dst_l3 = I40E_L3_DST_MASK;
+		}
 	} else {
 		/* Any other flow type are not supported here */
 		return i_set;
@@ -3589,6 +3604,7 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc)
 	return i_set;
 }

+#define FLOW_PCTYPES_SIZE 64
 /**
 * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash
 * @pf: pointer to the physical function struct
@@ -3601,9 +3617,11 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	struct i40e_hw *hw = &pf->hw;
 	u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
 		   ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
-	u8 flow_pctype = 0;
+	DECLARE_BITMAP(flow_pctypes, FLOW_PCTYPES_SIZE);
 	u64 i_set, i_setc;

+	bitmap_zero(flow_pctypes, FLOW_PCTYPES_SIZE);
+
 	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
 		dev_err(&pf->pdev->dev,
 			"Change of RSS hash input set is not supported when MFP mode is enabled\n");
@@ -3619,36 +3637,35 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)

 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
 		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
-			hena |=
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
+			set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
+				flow_pctypes);
 		break;
 	case TCP_V6_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
 		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
-			hena |=
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
-			hena |=
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK);
+			set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
+				flow_pctypes);
 		break;
 	case UDP_V4_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
-			hena |=
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP);
-
+		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
+		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
+				flow_pctypes);
+			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
+				flow_pctypes);
+		}
 		hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4);
 		break;
 	case UDP_V6_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
-		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
-			hena |=
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
-			  BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP);
-
+		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
+		if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
+				flow_pctypes);
+			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
+				flow_pctypes);
+		}
 		hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6);
 		break;
 	case AH_ESP_V4_FLOW:
@@ -3681,17 +3698,20 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		return -EINVAL;
 	}

-	if (flow_pctype) {
-		i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0,
-					       flow_pctype)) |
-			((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1,
-					       flow_pctype)) << 32);
-		i_set = i40e_get_rss_hash_bits(nfc, i_setc);
-		i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_pctype),
-				  (u32)i_set);
-		i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_pctype),
-				  (u32)(i_set >> 32));
-		hena |= BIT_ULL(flow_pctype);
+	if (bitmap_weight(flow_pctypes, FLOW_PCTYPES_SIZE)) {
+		u8 flow_id;
+
+		for_each_set_bit(flow_id, flow_pctypes, FLOW_PCTYPES_SIZE) {
+			i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id)) |
+				 ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id)) << 32);
+			i_set = i40e_get_rss_hash_bits(&pf->hw, nfc, i_setc);
+
+			i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id),
+					  (u32)i_set);
+			i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id),
+					  (u32)(i_set >> 32));
+			hena |= BIT_ULL(flow_id);
+		}
 	}

 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena);
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1404,6 +1404,10 @@ struct i40e_lldp_variables {
 #define I40E_PFQF_CTL_0_HASHLUTSIZE_512	0x00010000

 /* INPUT SET MASK for RSS, flow director, and flexible payload */
+#define I40E_X722_L3_SRC_SHIFT		49
+#define I40E_X722_L3_SRC_MASK		(0x3ULL << I40E_X722_L3_SRC_SHIFT)
+#define I40E_X722_L3_DST_SHIFT		41
+#define I40E_X722_L3_DST_MASK		(0x3ULL << I40E_X722_L3_DST_SHIFT)
 #define I40E_L3_SRC_SHIFT		47
 #define I40E_L3_SRC_MASK		(0x3ULL << I40E_L3_SRC_SHIFT)
 #define I40E_L3_V6_SRC_SHIFT		43
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1536,10 +1536,12 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state))
 		return true;

-	/* If the VFs have been disabled, this means something else is
-	 * resetting the VF, so we shouldn't continue.
-	 */
-	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
+	/* Bail out if VFs are disabled. */
+	if (test_bit(__I40E_VF_DISABLE, pf->state))
+		return true;
+
+	/* If VF is being reset already we don't need to continue. */
+	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
 		return true;

 	i40e_trigger_vf_reset(vf, flr);
@@ -1576,7 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	i40e_cleanup_reset_vf(vf);

 	i40e_flush(hw);
-	clear_bit(__I40E_VF_DISABLE, pf->state);
+	clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states);

 	return true;
 }
@@ -1609,8 +1611,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		return false;

 	/* Begin reset on all VFs at once */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
-		i40e_trigger_vf_reset(&pf->vf[v], flr);
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		vf = &pf->vf[v];
+		/* If VF is being reset no need to trigger reset again */
+		if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			i40e_trigger_vf_reset(&pf->vf[v], flr);
+	}

 	/* HW requires some time to make sure it can flush the FIFO for a VF
 	 * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
@@ -1626,9 +1632,11 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		 */
 		while (v < pf->num_alloc_vfs) {
 			vf = &pf->vf[v];
-			reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
-			if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
-				break;
+			if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) {
+				reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
+				if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
+					break;
+			}

 			/* If the current VF has finished resetting, move on
 			 * to the next VF in sequence.
@@ -1656,6 +1664,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		if (pf->vf[v].lan_vsi_idx == 0)
 			continue;

+		/* If VF is reset in another thread just continue */
+		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			continue;
+
 		i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]);
 	}

@@ -1667,6 +1679,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		if (pf->vf[v].lan_vsi_idx == 0)
 			continue;

+		/* If VF is reset in another thread just continue */
+		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			continue;
+
 		i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]);
 	}

@@ -1676,8 +1692,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 	mdelay(50);

 	/* Finish the reset on each VF */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		/* If VF is reset in another thread just continue */
+		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			continue;
+
 		i40e_cleanup_reset_vf(&pf->vf[v]);
+	}

 	i40e_flush(hw);
 	clear_bit(__I40E_VF_DISABLE, pf->state);
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -39,6 +39,7 @@ enum i40e_vf_states {
 	I40E_VF_STATE_MC_PROMISC,
 	I40E_VF_STATE_UC_PROMISC,
 	I40E_VF_STATE_PRE_ENABLE,
+	I40E_VF_STATE_RESETTING
 };

 /* VF capabilities */
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -2004,7 +2004,7 @@ void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
 	ctx->dev = dev;
 	/* Starts at 1 to avoid doing wake_up if we are not cleaning up */
 	atomic_set(&ctx->num_inflight, 1);
-	init_waitqueue_head(&ctx->wait);
+	init_completion(&ctx->inflight_done);
 }
 EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);

@@ -2018,8 +2018,8 @@ EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);
 */
 void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx)
 {
-	atomic_dec(&ctx->num_inflight);
-	wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0);
+	if (!atomic_dec_and_test(&ctx->num_inflight))
+		wait_for_completion(&ctx->inflight_done);
 }
 EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx);

@@ -2032,7 +2032,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	status = cmd_status_err(ctx->dev, status, work->opcode, work->out);
 	work->user_callback(status, work);
 	if (atomic_dec_and_test(&ctx->num_inflight))
-		wake_up(&ctx->wait);
+		complete(&ctx->inflight_done);
 }

 int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
@@ -2050,7 +2050,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
 		       mlx5_cmd_exec_cb_handler, work, false);
 	if (ret && atomic_dec_and_test(&ctx->num_inflight))
-		wake_up(&ctx->wait);
+		complete(&ctx->inflight_done);

 	return ret;
 }
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -6,6 +6,7 @@

 #include "en.h"
 #include "en_stats.h"
+#include "en/txrx.h"
 #include <linux/ptp_classify.h>

 #define MLX5E_PTP_CHANNEL_IX 0
@@ -68,6 +69,14 @@ static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
 		fk.ports.dst == htons(PTP_EV_PORT));
 }

+static inline bool mlx5e_ptpsq_fifo_has_room(struct mlx5e_txqsq *sq)
+{
+	if (!sq->ptpsq)
+		return true;
+
+	return mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo);
+}
+
 int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 		   u8 lag_port, struct mlx5e_ptp **cp);
 void mlx5e_ptp_close(struct mlx5e_ptp *c);
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -96,6 +96,7 @@ struct mlx5e_tc_flow {
 	struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5e_tc_flow *peer_flow;
 	struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */
+	struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */
 	struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */
 	struct list_head hairpin; /* flows sharing the same hairpin */
 	struct list_head peer;    /* flows with peer flow */
@@ -111,6 +112,7 @@ struct mlx5e_tc_flow {
 	struct completion del_hw_done;
 	struct mlx5_flow_attr *attr;
 	struct list_head attrs;
+	u32 chain_mapping;
 };

 struct mlx5_flow_handle *
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -57,6 +57,12 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);

+static inline bool
+mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo)
+{
+	return (*fifo->pc - *fifo->cc) < fifo->mask;
+}
+
 static inline bool
 mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 {
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -101,7 +101,6 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct xfrm_replay_state_esn *replay_esn;
 	u32 seq_bottom = 0;
 	u8 overlap;
-	u32 *esn;

 	if (!(sa_entry->x->props.flags & XFRM_STATE_ESN)) {
 		sa_entry->esn_state.trigger = 0;
@@ -116,11 +115,9 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)

 	sa_entry->esn_state.esn = xfrm_replay_seqhi(sa_entry->x,
 						    htonl(seq_bottom));
-	esn = &sa_entry->esn_state.esn;

 	sa_entry->esn_state.trigger = 1;
 	if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) {
-		++(*esn);
 		sa_entry->esn_state.overlap = 0;
 		return true;
 	} else if (unlikely(!overlap &&
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -432,7 +432,7 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec,
 				     bool active)
 {
 	struct mlx5_core_dev *mdev = macsec->mdev;
-	struct mlx5_macsec_obj_attrs attrs;
+	struct mlx5_macsec_obj_attrs attrs = {};
 	int err = 0;

 	if (rx_sa->active != active)
@@ -444,7 +444,7 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec,
 		return 0;
 	}

-	attrs.sci = rx_sa->sci;
+	attrs.sci = cpu_to_be64((__force u64)rx_sa->sci);
 	attrs.enc_key_id = rx_sa->enc_key_id;
 	err = mlx5e_macsec_create_object(mdev, &attrs, false, &rx_sa->macsec_obj_id);
 	if (err)
@@ -999,11 +999,11 @@ static int mlx5e_macsec_upd_rxsa(struct macsec_context *ctx)
 	}

 	rx_sa = rx_sc->rx_sa[assoc_num];
-	if (rx_sa) {
+	if (!rx_sa) {
 		netdev_err(ctx->netdev,
-			   "MACsec offload rx_sc sci %lld rx_sa %d already exist\n",
+			   "MACsec offload rx_sc sci %lld rx_sa %d doesn't exist\n",
 			   sci, assoc_num);
-		err = -EEXIST;
+		err = -EINVAL;
 		goto out;
 	}

@@ -1055,11 +1055,11 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx)
 	}

 	rx_sa = rx_sc->rx_sa[assoc_num];
-	if (rx_sa) {
+	if (!rx_sa) {
 		netdev_err(ctx->netdev,
-			   "MACsec offload rx_sc sci %lld rx_sa %d already exist\n",
+			   "MACsec offload rx_sc sci %lld rx_sa %d doesn't exist\n",
 			   sci, assoc_num);
-		err = -EEXIST;
+		err = -EINVAL;
 		goto out;
 	}

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
@@ -1180,7 +1180,7 @@ macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs,
 	rx_rule->rule[0] = rule;

 	/* Rx crypto table without SCI rule */
-	if (cpu_to_be64((__force u64)attrs->sci) & ntohs(MACSEC_PORT_ES)) {
+	if ((cpu_to_be64((__force u64)attrs->sci) & 0xFFFF) == ntohs(MACSEC_PORT_ES)) {
 		memset(spec, 0, sizeof(struct mlx5_flow_spec));
 		memset(&dest, 0, sizeof(struct mlx5_flow_destination));
 		memset(&flow_act, 0, sizeof(flow_act));
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1405,8 +1405,13 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 			      struct mlx5e_tc_flow *flow,
 			      struct mlx5_flow_spec *spec)
 {
+	struct mlx5e_tc_mod_hdr_acts mod_acts = {};
+	struct mlx5e_mod_hdr_handle *mh = NULL;
 	struct mlx5_flow_attr *slow_attr;
 	struct mlx5_flow_handle *rule;
+	bool fwd_and_modify_cap;
+	u32 chain_mapping = 0;
+	int err;

 	slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
 	if (!slow_attr)
@@ -1417,13 +1422,56 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 	slow_attr->esw_attr->split_count = 0;
 	slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;

-	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
-	if (!IS_ERR(rule))
-		flow_flag_set(flow, SLOW);
+	fwd_and_modify_cap = MLX5_CAP_ESW_FLOWTABLE((esw)->dev, fdb_modify_header_fwd_to_table);
+	if (!fwd_and_modify_cap)
+		goto skip_restore;

+	err = mlx5_chains_get_chain_mapping(esw_chains(esw), flow->attr->chain, &chain_mapping);
+	if (err)
+		goto err_get_chain;
+
+	err = mlx5e_tc_match_to_reg_set(esw->dev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB,
+					CHAIN_TO_REG, chain_mapping);
+	if (err)
+		goto err_reg_set;
+
+	mh = mlx5e_mod_hdr_attach(esw->dev, get_mod_hdr_table(flow->priv, flow),
+				  MLX5_FLOW_NAMESPACE_FDB, &mod_acts);
+	if (IS_ERR(mh)) {
+		err = PTR_ERR(mh);
+		goto err_attach;
+	}
+
+	slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+	slow_attr->modify_hdr = mlx5e_mod_hdr_get(mh);
+
+skip_restore:
+	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_offload;
+	}
+
+	flow->slow_mh = mh;
+	flow->chain_mapping = chain_mapping;
+	flow_flag_set(flow, SLOW);
+
+	mlx5e_mod_hdr_dealloc(&mod_acts);
 	kfree(slow_attr);

 	return rule;
+
+err_offload:
+	if (fwd_and_modify_cap)
+		mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), mh);
+err_attach:
+err_reg_set:
+	if (fwd_and_modify_cap)
+		mlx5_chains_put_chain_mapping(esw_chains(esw), chain_mapping);
+err_get_chain:
+	mlx5e_mod_hdr_dealloc(&mod_acts);
+	kfree(slow_attr);
+	return ERR_PTR(err);
 }

 void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
@@ -1441,7 +1489,17 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	slow_attr->esw_attr->split_count = 0;
 	slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
+	if (flow->slow_mh) {
+		slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+		slow_attr->modify_hdr = mlx5e_mod_hdr_get(flow->slow_mh);
+	}
 	mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
+	if (flow->slow_mh) {
+		mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), flow->slow_mh);
+		mlx5_chains_put_chain_mapping(esw_chains(esw), flow->chain_mapping);
+		flow->chain_mapping = 0;
+		flow->slow_mh = NULL;
+	}
 	flow_flag_clear(flow, SLOW);
 	kfree(slow_attr);
 }
@@ -3575,6 +3633,10 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr,
 	attr2->action = 0;
 	attr2->flags = 0;
 	attr2->parse_attr = parse_attr;
+	attr2->esw_attr->out_count = 0;
+	attr2->esw_attr->split_count = 0;
+	attr2->dest_chain = 0;
+	attr2->dest_ft = NULL;
 	return attr2;
 }

@@ -4008,6 +4070,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv,
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5_flow_attr *attr = flow->attr;
 	struct mlx5_esw_flow_attr *esw_attr;
+	struct net_device *filter_dev;
 	int err;

 	err = flow_action_supported(flow_action, extack);
@@ -4016,6 +4079,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv,

 	esw_attr = attr->esw_attr;
 	parse_attr = attr->parse_attr;
+	filter_dev = parse_attr->filter_dev;
 	parse_state = &parse_attr->parse_state;
 	mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack);
 	parse_state->ct_priv = get_ct_priv(priv);
@@ -4025,13 +4089,21 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv,
 		return err;

 	/* Forward to/from internal port can only have 1 dest */
-	if ((netif_is_ovs_master(parse_attr->filter_dev) || esw_attr->dest_int_port) &&
+	if ((netif_is_ovs_master(filter_dev) || esw_attr->dest_int_port) &&
 	    esw_attr->out_count > 1) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Rules with internal port can have only one destination");
 		return -EOPNOTSUPP;
 	}

+	/* Forward from tunnel/internal port to internal port is not supported */
+	if ((mlx5e_get_tc_tun(filter_dev) || netif_is_ovs_master(filter_dev)) &&
+	    esw_attr->dest_int_port) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Forwarding from tunnel/internal port to internal port is not supported");
+		return -EOPNOTSUPP;
+	}
+
 	err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack);
 	if (err)
 		return err;
--- a/Show More
+++ b/Show More