Merge back thermal control material for v6.1.

Documentation/atomic_bitops.txt

@@ -59,7 +59,7 @@ Like with atomic_t, the rule of thumb is:
  - RMW operations that have a return value are fully ordered.
 
  - RMW operations that are conditional are unordered on FAILURE,
-   otherwise the above rules apply. In the case of test_and_{}_bit() operations,
+   otherwise the above rules apply. In the case of test_and_set_bit_lock(),
    if the bit in memory is unchanged by the operation then it is deemed to have
    failed.
 

Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml

@@ -233,6 +233,7 @@ allOf:
               - allwinner,sun8i-a83t-tcon-lcd
               - allwinner,sun8i-v3s-tcon
               - allwinner,sun9i-a80-tcon-lcd
+              - allwinner,sun20i-d1-tcon-lcd
 
     then:
       properties:
@@ -252,6 +253,7 @@ allOf:
               - allwinner,sun8i-a83t-tcon-tv
               - allwinner,sun8i-r40-tcon-tv
               - allwinner,sun9i-a80-tcon-tv
+              - allwinner,sun20i-d1-tcon-tv
 
     then:
       properties:
@@ -278,6 +280,7 @@ allOf:
               - allwinner,sun9i-a80-tcon-lcd
               - allwinner,sun4i-a10-tcon
               - allwinner,sun8i-a83t-tcon-lcd
+              - allwinner,sun20i-d1-tcon-lcd
 
     then:
       required:
@@ -294,6 +297,7 @@ allOf:
               - allwinner,sun8i-a23-tcon
               - allwinner,sun8i-a33-tcon
               - allwinner,sun8i-a83t-tcon-lcd
+              - allwinner,sun20i-d1-tcon-lcd
 
     then:
       properties:

Documentation/devicetree/bindings/net/qcom-emac.txt

@@ -14,7 +14,7 @@ MAC node:
 - mac-address : The 6-byte MAC address. If present, it is the default
 	MAC address.
 - internal-phy : phandle to the internal PHY node
-- phy-handle : phandle the external PHY node
+- phy-handle : phandle to the external PHY node
 
 Internal PHY node:
 - compatible : Should be "qcom,fsm9900-emac-sgmii" or "qcom,qdf2432-emac-sgmii".

Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml

@@ -47,12 +47,6 @@ properties:
         description:
           Properties for single LDO regulator.
 
-        properties:
-          regulator-name:
-            pattern: "^LDO[1-5]$"
-            description:
-              should be "LDO1", ..., "LDO5"
-
         unevaluatedProperties: false
 
       "^BUCK[1-6]$":
@@ -62,11 +56,6 @@ properties:
           Properties for single BUCK regulator.
 
         properties:
-          regulator-name:
-            pattern: "^BUCK[1-6]$"
-            description:
-              should be "BUCK1", ..., "BUCK6"
-
           nxp,dvs-run-voltage:
             $ref: "/schemas/types.yaml#/definitions/uint32"
             minimum: 600000

Documentation/devicetree/bindings/spi/cdns,qspi-nor-peripheral-props.yaml

@@ -10,7 +10,7 @@ description:
   See spi-peripheral-props.yaml for more info.
 
 maintainers:
-  - Pratyush Yadav <p.yadav@ti.com>
+  - Vaishnav Achath <vaishnav.a@ti.com>
 
 properties:
   # cdns,qspi-nor.yaml

Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml

@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Cadence Quad SPI controller
 
 maintainers:
-  - Pratyush Yadav <p.yadav@ti.com>
+  - Vaishnav Achath <vaishnav.a@ti.com>
 
 allOf:
   - $ref: spi-controller.yaml#

Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml

@@ -16,7 +16,7 @@ description:
   their own separate schema that should be referenced from here.
 
 maintainers:
-  - Pratyush Yadav <p.yadav@ti.com>
+  - Mark Brown <broonie@kernel.org>
 
 properties:
   reg:

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

@@ -42,7 +42,7 @@ properties:
     description:
       Address ranges of the thermal registers. If more then one range is given
       the first one must be the common registers followed by each sensor
-      according the datasheet.
+      according to the datasheet.
     minItems: 1
     maxItems: 4
 

Documentation/kbuild/kconfig-language.rst

@@ -525,8 +525,8 @@ followed by a test macro::
 If you need to expose a compiler capability to makefiles and/or C source files,
 `CC_HAS_` is the recommended prefix for the config option::
 
-  config CC_HAS_ASM_GOTO
+  config CC_HAS_FOO
-	def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC))
+	def_bool $(success,$(srctree)/scripts/cc-check-foo.sh $(CC))
 
 Build as module only
 ~~~~~~~~~~~~~~~~~~~~

Documentation/tools/rtla/rtla-timerlat-hist.rst

@@ -33,7 +33,7 @@ EXAMPLE
 =======
 In the example below, **rtla timerlat hist** is set to run for *10* minutes,
 in the cpus *0-4*, *skipping zero* only lines. Moreover, **rtla timerlat
-hist** will change the priority of the *timelat* threads to run under
+hist** will change the priority of the *timerlat* threads to run under
 *SCHED_DEADLINE* priority, with a *10us* runtime every *1ms* period. The
 *1ms* period is also passed to the *timerlat* tracer::
 

MAINTAINERS

@@ -2178,7 +2178,7 @@ M:	Jean-Marie Verdun <verdun@hpe.com>
 M:	Nick Hawkins <nick.hawkins@hpe.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/hpe,gxp.yaml
-F:	Documentation/devicetree/bindings/spi/hpe,gxp-spi.yaml
+F:	Documentation/devicetree/bindings/spi/hpe,gxp-spifi.yaml
 F:	Documentation/devicetree/bindings/timer/hpe,gxp-timer.yaml
 F:	arch/arm/boot/dts/hpe-bmc*
 F:	arch/arm/boot/dts/hpe-gxp*
@@ -5145,6 +5145,7 @@ T:	git git://git.samba.org/sfrench/cifs-2.6.git
 F:	Documentation/admin-guide/cifs/
 F:	fs/cifs/
 F:	fs/smbfs_common/
+F:	include/uapi/linux/cifs
 
 COMPACTPCI HOTPLUG CORE
 M:	Scott Murray <scott@spiteful.org>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
@@ -1113,13 +1113,11 @@ vmlinux-alldirs	:= $(sort $(vmlinux-dirs) Documentation \
 		     $(patsubst %/,%,$(filter %/, $(core-) \
 			$(drivers-) $(libs-))))
 
-subdir-modorder := $(addsuffix modules.order,$(filter %/, \
-			$(core-y) $(core-m) $(libs-y) $(libs-m) \
-			$(drivers-y) $(drivers-m)))
-
 build-dirs	:= $(vmlinux-dirs)
 clean-dirs	:= $(vmlinux-alldirs)
 
+subdir-modorder := $(addsuffix /modules.order, $(build-dirs))
+
 # Externally visible symbols (used by link-vmlinux.sh)
 KBUILD_VMLINUX_OBJS := $(head-y) $(patsubst %/,%/built-in.a, $(core-y))
 KBUILD_VMLINUX_OBJS += $(addsuffix built-in.a, $(filter %/, $(libs-y)))

arch/Kconfig

@@ -53,7 +53,6 @@ config KPROBES
 config JUMP_LABEL
 	bool "Optimize very unlikely/likely branches"
 	depends on HAVE_ARCH_JUMP_LABEL
-	depends on CC_HAS_ASM_GOTO
 	select OBJTOOL if HAVE_JUMP_LABEL_HACK
 	help
 	 This option enables a transparent branch optimization that
@@ -1361,7 +1360,7 @@ config HAVE_PREEMPT_DYNAMIC_CALL
 
 config HAVE_PREEMPT_DYNAMIC_KEY
 	bool
-	depends on HAVE_ARCH_JUMP_LABEL && CC_HAS_ASM_GOTO
+	depends on HAVE_ARCH_JUMP_LABEL
 	select HAVE_PREEMPT_DYNAMIC
 	help
 	   An architecture should select this if it can handle the preemption

arch/arm64/include/asm/kvm_host.h

@@ -929,6 +929,10 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 	(system_supports_mte() &&				\
 	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))
 
+#define kvm_supports_32bit_el0()				\
+	(system_supports_32bit_el0() &&				\
+	 !static_branch_unlikely(&arm64_mismatched_32bit_el0))
+
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 extern phys_addr_t hyp_mem_base;

arch/arm64/include/uapi/asm/kvm.h

@@ -75,9 +75,11 @@ struct kvm_regs {
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
-#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK	GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+						KVM_ARM_DEVICE_TYPE_SHIFT)
 #define KVM_ARM_DEVICE_ID_SHIFT		16
-#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK		GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+						KVM_ARM_DEVICE_ID_SHIFT)
 
 /* Supported device IDs */
 #define KVM_ARM_DEVICE_VGIC_V2		0

arch/arm64/kvm/arm.c

@@ -757,8 +757,7 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
 	if (likely(!vcpu_mode_is_32bit(vcpu)))
 		return false;
 
-	return !system_supports_32bit_el0() ||
+	return !kvm_supports_32bit_el0();
-		static_branch_unlikely(&arm64_mismatched_32bit_el0);
 }
 
 /**

arch/arm64/kvm/guest.c

@@ -242,7 +242,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
-			if (!system_supports_32bit_el0())
+			if (!kvm_supports_32bit_el0())
 				return -EINVAL;
 			break;
 		case PSR_AA32_MODE_FIQ:

arch/arm64/kvm/mmu.c

@@ -993,7 +993,7 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 * THP doesn't start to split while we are adjusting the
 		 * refcounts.
 		 *
-		 * We are sure this doesn't happen, because mmu_notifier_retry
+		 * We are sure this doesn't happen, because mmu_invalidate_retry
 		 * was successful and we are holding the mmu_lock, so if this
 		 * THP is trying to split, it will be blocked in the mmu
 		 * notifier before touching any of the pages, specifically
@@ -1188,9 +1188,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			return ret;
 	}
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_notifier_seq happens before we call
+	 * Ensure the read of mmu_invalidate_seq happens before we call
 	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
 	 * the page we just got a reference to gets unmapped before we have a
 	 * chance to grab the mmu_lock, which ensure that if the page gets
@@ -1246,7 +1246,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	else
 		write_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/*

arch/arm64/kvm/sys_regs.c

@@ -652,7 +652,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
-	if (!system_supports_32bit_el0())
+	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
@@ -701,7 +701,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
-		if (!system_supports_32bit_el0())
+		if (!kvm_supports_32bit_el0())
 			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);

arch/loongarch/include/asm/irq.h

@@ -81,7 +81,6 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS];
 #define GSI_MIN_PCH_IRQ		LOONGSON_PCH_IRQ_BASE
 #define GSI_MAX_PCH_IRQ		(LOONGSON_PCH_IRQ_BASE + 256 - 1)
 
-extern int find_pch_pic(u32 gsi);
 struct acpi_madt_lio_pic;
 struct acpi_madt_eio_pic;
 struct acpi_madt_ht_pic;

arch/mips/include/asm/kvm_host.h

@@ -84,8 +84,6 @@
 
 
 #define KVM_MAX_VCPUS		16
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS	0
 
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 

arch/mips/kvm/mmu.c

@@ -615,17 +615,17 @@ retry:
 	 * Used to check for invalidations in progress, of the pfn that is
 	 * returned by pfn_to_pfn_prot below.
 	 */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_notifier_seq isn't reordered with PTE reads in
+	 * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads
-	 * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
+	 * in gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
 	 * risk the page we get a reference to getting unmapped before we have a
-	 * chance to grab the mmu_lock without mmu_notifier_retry() noticing.
+	 * chance to grab the mmu_lock without mmu_invalidate_retry() noticing.
 	 *
 	 * This smp_rmb() pairs with the effective smp_wmb() of the combination
 	 * of the pte_unmap_unlock() after the PTE is zapped, and the
 	 * spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before
-	 * mmu_notifier_seq is incremented.
+	 * mmu_invalidate_seq is incremented.
 	 */
 	smp_rmb();
 
@@ -638,7 +638,7 @@ retry:
 
 	spin_lock(&kvm->mmu_lock);
 	/* Check if an invalidation has taken place since we got pfn */
-	if (mmu_notifier_retry(kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		/*
 		 * This can happen when mappings are changed asynchronously, but
 		 * also synchronously if a COW is triggered by

arch/nios2/include/asm/entry.h

@@ -50,7 +50,8 @@
 	stw	r13, PT_R13(sp)
 	stw	r14, PT_R14(sp)
 	stw	r15, PT_R15(sp)
-	stw	r2, PT_ORIG_R2(sp)
+	movi	r24, -1
+	stw	r24, PT_ORIG_R2(sp)
 	stw	r7, PT_ORIG_R7(sp)
 
 	stw	ra, PT_RA(sp)

arch/nios2/include/asm/ptrace.h

@@ -74,6 +74,8 @@ extern void show_regs(struct pt_regs *);
 	((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE)\
 		- 1)
 
+#define force_successful_syscall_return() (current_pt_regs()->orig_r2 = -1)
+
 int do_syscall_trace_enter(void);
 void do_syscall_trace_exit(void);
 #endif /* __ASSEMBLY__ */

arch/nios2/kernel/entry.S

@@ -185,6 +185,7 @@ ENTRY(handle_system_call)
 	ldw	r5, PT_R5(sp)
 
 local_restart:
+	stw	r2, PT_ORIG_R2(sp)
 	/* Check that the requested system call is within limits */
 	movui	r1, __NR_syscalls
 	bgeu	r2, r1, ret_invsyscall
@@ -192,7 +193,6 @@ local_restart:
 	movhi	r11, %hiadj(sys_call_table)
 	add	r1, r1, r11
 	ldw	r1, %lo(sys_call_table)(r1)
-	beq	r1, r0, ret_invsyscall
 
 	/* Check if we are being traced */
 	GET_THREAD_INFO r11
@@ -213,6 +213,9 @@ local_restart:
 translate_rc_and_ret:
 	movi	r1, 0
 	bge	r2, zero, 3f
+	ldw	r1, PT_ORIG_R2(sp)
+	addi	r1, r1, 1
+	beq	r1, zero, 3f
 	sub	r2, zero, r2
 	movi	r1, 1
 3:
@@ -255,9 +258,9 @@ traced_system_call:
 	ldw	r6, PT_R6(sp)
 	ldw	r7, PT_R7(sp)
 
-	/* Fetch the syscall function, we don't need to check the boundaries
+	/* Fetch the syscall function. */
-	 * since this is already done.
+	movui	r1, __NR_syscalls
-	 */
+	bgeu	r2, r1, traced_invsyscall
 	slli	r1, r2, 2
 	movhi	r11,%hiadj(sys_call_table)
 	add	r1, r1, r11
@@ -276,6 +279,9 @@ traced_system_call:
 translate_rc_and_ret2:
 	movi	r1, 0
 	bge	r2, zero, 4f
+	ldw	r1, PT_ORIG_R2(sp)
+	addi	r1, r1, 1
+	beq	r1, zero, 4f
 	sub	r2, zero, r2
 	movi	r1, 1
 4:
@@ -287,6 +293,11 @@ end_translate_rc_and_ret2:
 	RESTORE_SWITCH_STACK
 	br	ret_from_exception
 
+	/* If the syscall number was invalid return ENOSYS */
+traced_invsyscall:
+	movi	r2, -ENOSYS
+	br	translate_rc_and_ret2
+
 Luser_return:
 	GET_THREAD_INFO	r11			/* get thread_info pointer */
 	ldw	r10, TI_FLAGS(r11)		/* get thread_info->flags */
@@ -336,9 +347,6 @@ external_interrupt:
 	/* skip if no interrupt is pending */
 	beq	r12, r0, ret_from_interrupt
 
-	movi	r24, -1
-	stw	r24, PT_ORIG_R2(sp)
-
 	/*
 	 * Process an external hardware interrupt.
 	 */

arch/nios2/kernel/signal.c

@@ -242,7 +242,7 @@ static int do_signal(struct pt_regs *regs)
 	/*
 	 * If we were from a system call, check for system call restarting...
 	 */
-	if (regs->orig_r2 >= 0) {
+	if (regs->orig_r2 >= 0 && regs->r1) {
 		continue_addr = regs->ea;
 		restart_addr = continue_addr - 4;
 		retval = regs->r2;
@@ -264,6 +264,7 @@ static int do_signal(struct pt_regs *regs)
 			regs->ea = restart_addr;
 			break;
 		}
+		regs->orig_r2 = -1;
 	}
 
 	if (get_signal(&ksig)) {

arch/nios2/kernel/syscall_table.c

@@ -13,5 +13,6 @@
 #define __SYSCALL(nr, call) [nr] = (call),
 
 void *sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls-1] = sys_ni_syscall,
 #include <asm/unistd.h>
 };

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -666,7 +666,7 @@ static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq,
 	VM_WARN(!spin_is_locked(&kvm->mmu_lock),
 		"%s called with kvm mmu_lock not held \n", __func__);
 
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		return NULL;
 
 	pte = __find_linux_pte(kvm->mm->pgd, ea, NULL, hshift);

arch/powerpc/kernel/pci-common.c

@@ -68,10 +68,6 @@ void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops)
 	pci_dma_ops = dma_ops;
 }
 
-/*
- * This function should run under locking protection, specifically
- * hose_spinlock.
- */
 static int get_phb_number(struct device_node *dn)
 {
 	int ret, phb_id = -1;
@@ -108,15 +104,20 @@ static int get_phb_number(struct device_node *dn)
 	if (!ret)
 		phb_id = (int)(prop & (MAX_PHBS - 1));
 
+	spin_lock(&hose_spinlock);
+
 	/* We need to be sure to not use the same PHB number twice. */
 	if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
-		return phb_id;
+		goto out_unlock;
 
 	/* If everything fails then fallback to dynamic PHB numbering. */
 	phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
 	BUG_ON(phb_id >= MAX_PHBS);
 	set_bit(phb_id, phb_bitmap);
 
+out_unlock:
+	spin_unlock(&hose_spinlock);
+
 	return phb_id;
 }
 
@@ -127,10 +128,13 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL);
 	if (phb == NULL)
 		return NULL;
-	spin_lock(&hose_spinlock);
+
 	phb->global_number = get_phb_number(dev);
+
+	spin_lock(&hose_spinlock);
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
+
 	phb->dn = dev;
 	phb->is_dynamic = slab_is_available();
 #ifdef CONFIG_PPC64

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -90,7 +90,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	unsigned long pfn;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Get host physical address for gpa */
@@ -151,7 +151,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	cpte = kvmppc_mmu_hpte_cache_next(vcpu);
 
 	spin_lock(&kvm->mmu_lock);
-	if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
+	if (!cpte || mmu_invalidate_retry(kvm, mmu_seq)) {
 		r = -EAGAIN;
 		goto out_unlock;
 	}

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -578,7 +578,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 		return -EFAULT;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	ret = -EFAULT;
@@ -693,7 +693,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 
 	/* Check if we might have been invalidated; let the guest retry if so */
 	ret = RESUME_GUEST;
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) {
 		unlock_rmap(rmap);
 		goto out_unlock;
 	}

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -640,7 +640,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 	/* Check if we might have been invalidated; let the guest retry if so */
 	spin_lock(&kvm->mmu_lock);
 	ret = -EAGAIN;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/* Now traverse again under the lock and change the tree */
@@ -830,7 +830,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	bool large_enable;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
@@ -1191,7 +1191,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	 * Increase the mmu notifier sequence number to prevent any page
 	 * fault that read the memslot earlier from writing a PTE.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	spin_unlock(&kvm->mmu_lock);
 }
 

arch/powerpc/kvm/book3s_hv_nested.c

@@ -1580,7 +1580,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 	/* 2. Find the host pte for this L1 guest real address */
 
 	/* Used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* See if can find translation in our partition scoped tables for L1 */

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -219,7 +219,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	g_ptel = ptel;
 
 	/* used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Find the memslot (if any) for this address */
@@ -366,7 +366,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 			rmap = real_vmalloc_addr(rmap);
 		lock_rmap(rmap);
 		/* Check for pending invalidations under the rmap chain lock */
-		if (mmu_notifier_retry(kvm, mmu_seq)) {
+		if (mmu_invalidate_retry(kvm, mmu_seq)) {
 			/* inval in progress, write a non-present HPTE */
 			pteh |= HPTE_V_ABSENT;
 			pteh &= ~HPTE_V_VALID;
@@ -932,7 +932,7 @@ static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
 	int i;
 
 	/* Used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
@@ -960,7 +960,7 @@ static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
 	long ret = H_SUCCESS;
 
 	/* Used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);

arch/powerpc/kvm/e500_mmu_host.c

@@ -339,7 +339,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	unsigned long flags;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
@@ -460,7 +460,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	spin_lock(&kvm->mmu_lock);
-	if (mmu_notifier_retry(kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		ret = -EAGAIN;
 		goto out;
 	}

arch/riscv/kernel/cpufeature.c

@@ -28,7 +28,7 @@ unsigned long elf_hwcap __read_mostly;
 /* Host ISA bitmap */
 static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 
-__ro_after_init DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX);
+DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX);
 EXPORT_SYMBOL(riscv_isa_ext_keys);
 
 /**

arch/riscv/kvm/mmu.c

@@ -666,7 +666,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 		return ret;
 	}
 
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 
 	hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable);
 	if (hfn == KVM_PFN_ERR_HWPOISON) {
@@ -686,7 +686,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 
 	spin_lock(&kvm->mmu_lock);
 
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	if (writable) {

arch/s390/hypfs/hypfs_diag.c

@@ -437,7 +437,7 @@ __init int hypfs_diag_init(void)
 	int rc;
 
 	if (diag204_probe()) {
-		pr_err("The hardware system does not support hypfs\n");
+		pr_info("The hardware system does not support hypfs\n");
 		return -ENODATA;
 	}
 

arch/s390/hypfs/inode.c

@@ -496,9 +496,9 @@ fail_hypfs_sprp_exit:
 	hypfs_vm_exit();
 fail_hypfs_diag_exit:
 	hypfs_diag_exit();
+	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 fail_dbfs_exit:
 	hypfs_dbfs_exit();
-	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 	return rc;
 }
 device_initcall(hypfs_init)

arch/um/drivers/virtio_uml.c

@@ -1011,7 +1011,7 @@ error_kzalloc:
 
 static int vu_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		       const char * const names[], u32 sizes[], const bool *ctx,
+		       const char * const names[], const bool *ctx,
 		       struct irq_affinity *desc)
 {
 	struct virtio_uml_device *vu_dev = to_virtio_uml_device(vdev);

arch/um/include/asm/cpufeature.h

@@ -65,20 +65,6 @@ extern void setup_clear_cpu_cap(unsigned int bit);
 
 #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
 
-#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
-
-/*
- * Workaround for the sake of BPF compilation which utilizes kernel
- * headers, but clang does not support ASM GOTO and fails the build.
- */
-#ifndef __BPF_TRACING__
-#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
-#endif
-
-#define static_cpu_has(bit)            boot_cpu_has(bit)
-
-#else
-
 /*
  * Static testing of CPU features. Used the same as boot_cpu_has(). It
  * statically patches the target code for additional performance. Use
@@ -137,7 +123,6 @@ t_no:
 		boot_cpu_has(bit) :				\
 		_static_cpu_has(bit)				\
 )
-#endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
 #define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))

arch/x86/Makefile

@@ -286,10 +286,6 @@ vdso_install:
 
 archprepare: checkbin
 checkbin:
-ifndef CONFIG_CC_HAS_ASM_GOTO
-	@echo Compiler lacks asm-goto support.
-	@exit 1
-endif
 ifdef CONFIG_RETPOLINE
 ifeq ($(RETPOLINE_CFLAGS),)
 	@echo "You are building kernel with non-retpoline compiler." >&2

arch/x86/include/asm/cpufeature.h

@@ -155,20 +155,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 
 #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
 
-#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
-
-/*
- * Workaround for the sake of BPF compilation which utilizes kernel
- * headers, but clang does not support ASM GOTO and fails the build.
- */
-#ifndef __BPF_TRACING__
-#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
-#endif
-
-#define static_cpu_has(bit)            boot_cpu_has(bit)
-
-#else
-
 /*
  * Static testing of CPU features. Used the same as boot_cpu_has(). It
  * statically patches the target code for additional performance. Use
@@ -208,7 +194,6 @@ t_no:
 		boot_cpu_has(bit) :				\
 		_static_cpu_has(bit)				\
 )
-#endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
 #define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))

arch/x86/include/asm/extable_fixup_types.h

@@ -64,4 +64,6 @@
 #define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
 #define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
+#define EX_TYPE_ZEROPAD			20 /* longword load with zeropad on fault */
+
 #endif

arch/x86/include/asm/ibt.h

@@ -31,6 +31,16 @@
 
 #define __noendbr	__attribute__((nocf_check))
 
+/*
+ * Create a dummy function pointer reference to prevent objtool from marking
+ * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by
+ * apply_ibt_endbr()).
+ */
+#define IBT_NOSEAL(fname)				\
+	".pushsection .discard.ibt_endbr_noseal\n\t"	\
+	_ASM_PTR fname "\n\t"				\
+	".popsection\n\t"
+
 static inline __attribute_const__ u32 gen_endbr(void)
 {
 	u32 endbr;
@@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save);
 #ifndef __ASSEMBLY__
 
 #define ASM_ENDBR
+#define IBT_NOSEAL(name)
 
 #define __noendbr
 

arch/x86/include/asm/kvm_host.h

@@ -53,7 +53,7 @@
 #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO)
 
 /* memory slots that are not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 3
+#define KVM_INTERNAL_MEM_SLOTS 3
 
 #define KVM_HALT_POLL_NS_DEFAULT 200000
 

arch/x86/include/asm/rmwcc.h

@@ -11,7 +11,7 @@
 
 #define __CLOBBERS_MEM(clb...)	"memory", ## clb
 
-#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO)
+#ifndef __GCC_ASM_FLAG_OUTPUTS__
 
 /* Use asm goto */
 
@@ -27,7 +27,7 @@ cc_label:	c = true;						\
 	c;								\
 })
 
-#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
 
 /* Use flags output or a set instruction */
 
@@ -40,7 +40,7 @@ cc_label:	c = true;						\
 	c;								\
 })
 
-#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
 
 #define GEN_UNARY_RMWcc_4(op, var, cc, arg0)				\
 	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())

arch/x86/include/asm/word-at-a-time.h

@@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask)
  * and the next page not being mapped, take the exception and
  * return zeroes in the non-existing part.
  */
-#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
-
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long offset, data;
 	unsigned long ret;
 
-	asm_volatile_goto(
+	asm volatile(
 		"1:	mov %[mem], %[ret]\n"
-
-		_ASM_EXTABLE(1b, %l[do_exception])
-
-		: [ret] "=r" (ret)
-		: [mem] "m" (*(unsigned long *)addr)
-		: : do_exception);
-
-	return ret;
-
-do_exception:
-	offset = (unsigned long)addr & (sizeof(long) - 1);
-	addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
-	data = *(unsigned long *)addr;
-	ret = data >> offset * 8;
-
-	return ret;
-}
-
-#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
-static inline unsigned long load_unaligned_zeropad(const void *addr)
-{
-	unsigned long offset, data;
-	unsigned long ret, err = 0;
-
-	asm(	"1:	mov %[mem], %[ret]\n"
 		"2:\n"
-
+		_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD)
-		_ASM_EXTABLE_FAULT(1b, 2b)
+		: [ret] "=r" (ret)
-
-		: [ret] "=&r" (ret), "+a" (err)
 		: [mem] "m" (*(unsigned long *)addr));
 
-	if (unlikely(err)) {
-		offset = (unsigned long)addr & (sizeof(long) - 1);
-		addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
-		data = *(unsigned long *)addr;
-		ret = data >> offset * 8;
-	}
-
 	return ret;
 }
 
-#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
 #endif /* _ASM_WORD_AT_A_TIME_H */

arch/x86/kernel/kprobes/core.c

@@ -505,7 +505,7 @@ static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
 		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
 			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
 		if (p->ainsn.jcc.type >= 0xe)
-			match = match && (regs->flags & X86_EFLAGS_ZF);
+			match = match || (regs->flags & X86_EFLAGS_ZF);
 	}
 	__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
 }

arch/x86/kvm/emulate.c

@@ -326,7 +326,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
 	name ":\n\t" \
-	ASM_ENDBR
+	ASM_ENDBR \
+	IBT_NOSEAL(name)
 
 #define FOP_FUNC(name) \
 	__FOP_FUNC(#name)
@@ -446,27 +447,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	FOP_END
 
 /* Special case for SETcc - 1 instruction per cc */
-
-/*
- * Depending on .config the SETcc functions look like:
- *
- * ENDBR			[4 bytes; CONFIG_X86_KERNEL_IBT]
- * SETcc %al			[3 bytes]
- * RET | JMP __x86_return_thunk	[1,5 bytes; CONFIG_RETHUNK]
- * INT3				[1 byte; CONFIG_SLS]
- */
-#define SETCC_ALIGN	16
-
 #define FOP_SETCC(op) \
-	".align " __stringify(SETCC_ALIGN) " \n\t" \
+	FOP_FUNC(op) \
-	".type " #op ", @function \n\t" \
-	#op ": \n\t" \
-	ASM_ENDBR \
 	#op " %al \n\t" \
-	__FOP_RET(#op) \
+	FOP_RET(op)
-	".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t"
 
-__FOP_START(setcc, SETCC_ALIGN)
+FOP_START(setcc)
 FOP_SETCC(seto)
 FOP_SETCC(setno)
 FOP_SETCC(setc)
@@ -493,7 +479,7 @@ FOP_END;
 
 /*
  * XXX: inoutclob user must know where the argument is being expanded.
- *      Relying on CONFIG_CC_HAS_ASM_GOTO would allow us to remove _fault.
+ *      Using asm goto would allow us to remove _fault.
  */
 #define asm_safe(insn, inoutclob...) \
 ({ \
@@ -1079,7 +1065,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
 static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 {
 	u8 rc;
-	void (*fop)(void) = (void *)em_setcc + SETCC_ALIGN * (condition & 0xf);
+	void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf);
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
 	asm("push %[flags]; popf; " CALL_NOSPEC

arch/x86/kvm/mmu/mmu.c

@@ -2914,7 +2914,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	 * If addresses are being invalidated, skip prefetching to avoid
 	 * accidentally prefetching those addresses.
 	 */
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
 		return;
 
 	__direct_pte_prefetch(vcpu, sp, sptep);
@@ -2928,7 +2928,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -3056,7 +3056,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 		return;
 
 	/*
-	 * mmu_notifier_retry() was successful and mmu_lock is held, so
+	 * mmu_invalidate_retry() was successful and mmu_lock is held, so
 	 * the pmd can't be split from under us.
 	 */
 	fault->goal_level = fault->req_level;
@@ -4203,7 +4203,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 		return true;
 
 	return fault->slot &&
-	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+	       mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -4227,7 +4227,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (r)
 		return r;
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	r = kvm_faultin_pfn(vcpu, fault);
@@ -6055,7 +6055,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	write_lock(&kvm->mmu_lock);
 
-	kvm_inc_notifier_count(kvm, gfn_start, gfn_end);
+	kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end);
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
@@ -6069,7 +6069,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 		kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
 						   gfn_end - gfn_start);
 
-	kvm_dec_notifier_count(kvm, gfn_start, gfn_end);
+	kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end);
 
 	write_unlock(&kvm->mmu_lock);
 }

arch/x86/kvm/mmu/paging_tmpl.h

@@ -589,7 +589,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	 * If addresses are being invalidated, skip prefetching to avoid
 	 * accidentally prefetching those addresses.
 	 */
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
 		return;
 
 	if (sp->role.direct)
@@ -838,7 +838,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		fault->max_level = walker.level;
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	r = kvm_faultin_pfn(vcpu, fault);

arch/x86/mm/extable.c

@@ -41,6 +41,59 @@ static bool ex_handler_default(const struct exception_table_entry *e,
 	return true;
 }
 
+/*
+ * This is the *very* rare case where we do a "load_unaligned_zeropad()"
+ * and it's a page crosser into a non-existent page.
+ *
+ * This happens when we optimistically load a pathname a word-at-a-time
+ * and the name is less than the full word and the  next page is not
+ * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC.
+ *
+ * NOTE! The faulting address is always a 'mov mem,reg' type instruction
+ * of size 'long', and the exception fixup must always point to right
+ * after the instruction.
+ */
+static bool ex_handler_zeropad(const struct exception_table_entry *e,
+			       struct pt_regs *regs,
+			       unsigned long fault_addr)
+{
+	struct insn insn;
+	const unsigned long mask = sizeof(long) - 1;
+	unsigned long offset, addr, next_ip, len;
+	unsigned long *reg;
+
+	next_ip = ex_fixup_addr(e);
+	len = next_ip - regs->ip;
+	if (len > MAX_INSN_SIZE)
+		return false;
+
+	if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN))
+		return false;
+	if (insn.length != len)
+		return false;
+
+	if (insn.opcode.bytes[0] != 0x8b)
+		return false;
+	if (insn.opnd_bytes != sizeof(long))
+		return false;
+
+	addr = (unsigned long) insn_get_addr_ref(&insn, regs);
+	if (addr == ~0ul)
+		return false;
+
+	offset = addr & mask;
+	addr = addr & ~mask;
+	if (fault_addr != addr + sizeof(long))
+		return false;
+
+	reg = insn_get_modrm_reg_ptr(&insn, regs);
+	if (!reg)
+		return false;
+
+	*reg = *(unsigned long *)addr >> (offset * 8);
+	return ex_handler_default(e, regs);
+}
+
 static bool ex_handler_fault(const struct exception_table_entry *fixup,
 			     struct pt_regs *regs, int trapnr)
 {
@@ -217,6 +270,8 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		return ex_handler_sgx(e, regs, trapnr);
 	case EX_TYPE_UCOPY_LEN:
 		return ex_handler_ucopy_len(e, regs, trapnr, reg, imm);
+	case EX_TYPE_ZEROPAD:
+		return ex_handler_zeropad(e, regs, fault_addr);
 	}
 	BUG();
 }

arch/x86/mm/init_64.c

@@ -645,7 +645,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
 
-			prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE);
+			prot = __pgprot(pgprot_val(prot) | _PAGE_PSE);
 
 			set_pte_init((pte_t *)pud,
 				     pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,

block/blk-mq.c

@@ -2229,26 +2229,6 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
 
-/**
- * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
- * @q: request queue.
- *
- * The caller is responsible for serializing this function against
- * blk_mq_{start,stop}_hw_queue().
- */
-bool blk_mq_queue_stopped(struct request_queue *q)
-{
-	struct blk_mq_hw_ctx *hctx;
-	unsigned long i;
-
-	queue_for_each_hw_ctx(q, hctx, i)
-		if (blk_mq_hctx_stopped(hctx))
-			return true;
-
-	return false;
-}
-EXPORT_SYMBOL(blk_mq_queue_stopped);
-
 /*
  * This function is often used for pausing .queue_rq() by driver when
  * there isn't enough resource or some conditions aren't satisfied, and
@@ -2570,7 +2550,7 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule)
 			break;
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
-			blk_mq_request_bypass_insert(rq, false, last);
+			blk_mq_request_bypass_insert(rq, false, true);
 			blk_mq_commit_rqs(hctx, &queued, from_schedule);
 			return;
 		default:

drivers/ata/ahci_imx.c

@@ -327,7 +327,7 @@ static int read_adc_sum(void *dev, u16 rtune_ctl_reg, void __iomem * mmio)
 }
 
 /* SATA AHCI temperature monitor */
-static int sata_ahci_read_temperature(void *dev, int *temp)
+static int __sata_ahci_read_temperature(void *dev, int *temp)
 {
 	u16 mpll_test_reg, rtune_ctl_reg, dac_ctl_reg, read_sum;
 	u32 str1, str2, str3, str4;
@@ -416,6 +416,11 @@ static int sata_ahci_read_temperature(void *dev, int *temp)
 	return 0;
 }
 
+static int sata_ahci_read_temperature(struct thermal_zone_device *tz, int *temp)
+{
+	return __sata_ahci_read_temperature(tz->devdata, temp);
+}
+
 static ssize_t sata_ahci_show_temp(struct device *dev,
 				   struct device_attribute *da,
 				   char *buf)
@@ -423,14 +428,14 @@ static ssize_t sata_ahci_show_temp(struct device *dev,
 	unsigned int temp = 0;
 	int err;
 
-	err = sata_ahci_read_temperature(dev, &temp);
+	err = __sata_ahci_read_temperature(dev, &temp);
 	if (err < 0)
 		return err;
 
 	return sprintf(buf, "%u\n", temp);
 }
 
-static const struct thermal_zone_of_device_ops fsl_sata_ahci_of_thermal_ops = {
+static const struct thermal_zone_device_ops fsl_sata_ahci_of_thermal_ops = {
 	.get_temp = sata_ahci_read_temperature,
 };
 
@@ -1131,8 +1136,8 @@ static int imx_ahci_probe(struct platform_device *pdev)
 			ret = PTR_ERR(hwmon_dev);
 			goto disable_clk;
 		}
-		devm_thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
+		devm_thermal_of_zone_register(hwmon_dev, 0, hwmon_dev,
-					     &fsl_sata_ahci_of_thermal_ops);
+					      &fsl_sata_ahci_of_thermal_ops);
 		dev_info(dev, "%s: sensor 'sata_ahci'\n", dev_name(hwmon_dev));
 	}
 

drivers/ata/libata-eh.c

@@ -2122,6 +2122,7 @@ const char *ata_get_cmd_name(u8 command)
 		{ ATA_CMD_WRITE_QUEUED_FUA_EXT, "WRITE DMA QUEUED FUA EXT" },
 		{ ATA_CMD_FPDMA_READ,		"READ FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_WRITE,		"WRITE FPDMA QUEUED" },
+		{ ATA_CMD_NCQ_NON_DATA,		"NCQ NON-DATA" },
 		{ ATA_CMD_FPDMA_SEND,		"SEND FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_RECV,		"RECEIVE FPDMA QUEUED" },
 		{ ATA_CMD_PIO_READ,		"READ SECTOR(S)" },

drivers/block/ublk_drv.c

@@ -555,7 +555,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
 	return (struct ublk_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static bool ubq_daemon_is_dying(struct ublk_queue *ubq)
+static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 {
 	return ubq->ubq_daemon->flags & PF_EXITING;
 }
@@ -605,8 +605,9 @@ static void ublk_complete_rq(struct request *req)
 }
 
 /*
- * __ublk_fail_req() may be called from abort context or ->ubq_daemon
+ * Since __ublk_rq_task_work always fails requests immediately during
- * context during exiting, so lock is required.
+ * exiting, __ublk_fail_req() is only called from abort context during
+ * exiting. So lock is unnecessary.
  *
  * Also aborting may not be started yet, keep in mind that one failed
  * request may be issued by block layer again.
@@ -644,8 +645,7 @@ static inline void __ublk_rq_task_work(struct request *req)
 	struct ublk_device *ub = ubq->dev;
 	int tag = req->tag;
 	struct ublk_io *io = &ubq->ios[tag];
-	bool task_exiting = current != ubq->ubq_daemon ||
+	bool task_exiting = current != ubq->ubq_daemon || ubq_daemon_is_dying(ubq);
-		(current->flags & PF_EXITING);
 	unsigned int mapped_bytes;
 
 	pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n",
@@ -680,6 +680,11 @@ static inline void __ublk_rq_task_work(struct request *req)
 		 * do the copy work.
 		 */
 		io->flags &= ~UBLK_IO_FLAG_NEED_GET_DATA;
+		/* update iod->addr because ublksrv may have passed a new io buffer */
+		ublk_get_iod(ubq, req->tag)->addr = io->addr;
+		pr_devel("%s: update iod->addr: op %d, qid %d tag %d io_flags %x addr %llx\n",
+				__func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags,
+				ublk_get_iod(ubq, req->tag)->addr);
 	}
 
 	mapped_bytes = ublk_map_io(ubq, req, io);
@@ -751,9 +756,25 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode))
 			goto fail;
 	} else {
-		struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd;
+		struct ublk_io *io = &ubq->ios[rq->tag];
+		struct io_uring_cmd *cmd = io->cmd;
 		struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 
+		/*
+		 * If the check pass, we know that this is a re-issued request aborted
+		 * previously in monitor_work because the ubq_daemon(cmd's task) is
+		 * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore
+		 * because this ioucmd's io_uring context may be freed now if no inflight
+		 * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work.
+		 *
+		 * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing
+		 * the tag). Then the request is re-started(allocating the tag) and we are here.
+		 * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED
+		 * guarantees that here is a re-issued request aborted previously.
+		 */
+		if ((io->flags & UBLK_IO_FLAG_ABORTED))
+			goto fail;
+
 		pdu->req = rq;
 		io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
 	}

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

@@ -148,30 +148,22 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 			      struct amdgpu_reset_context *reset_context)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle;
+	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head reset_device_list;
 	int r = 0;
 
 	dev_dbg(adev->dev, "aldebaran perform hw reset\n");
+
+	if (reset_device_list == NULL)
+		return -EINVAL;
+
 	if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) &&
 	    reset_context->hive == NULL) {
 		/* Wrong context, return error */
 		return -EINVAL;
 	}
 
-	INIT_LIST_HEAD(&reset_device_list);
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
-	if (reset_context->hive) {
-		list_for_each_entry (tmp_adev,
-				     &reset_context->hive->device_list,
-				     gmc.xgmi.head)
-			list_add_tail(&tmp_adev->reset_list,
-				      &reset_device_list);
-	} else {
-		list_add_tail(&reset_context->reset_req_dev->reset_list,
-			      &reset_device_list);
-	}
-
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
 		mutex_lock(&tmp_adev->reset_cntl->reset_lock);
 		tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_MODE2;
 	}
@@ -179,7 +171,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 	 * Mode2 reset doesn't need any sync between nodes in XGMI hive, instead launch
 	 * them together so that they can be completed asynchronously on multiple nodes
 	 */
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		/* For XGMI run all resets in parallel to speed up the process */
 		if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
 			if (!queue_work(system_unbound_wq,
@@ -197,7 +189,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 
 	/* For XGMI wait for all resets to complete before proceed */
 	if (!r) {
-		list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+		list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 			if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
 				flush_work(&tmp_adev->reset_cntl->reset_work);
 				r = tmp_adev->asic_reset_res;
@@ -207,7 +199,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 		}
 	}
 
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		mutex_unlock(&tmp_adev->reset_cntl->reset_lock);
 		tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_NONE;
 	}
@@ -339,10 +331,13 @@ static int
 aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 				  struct amdgpu_reset_context *reset_context)
 {
+	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head reset_device_list;
 	int r;
 
+	if (reset_device_list == NULL)
+		return -EINVAL;
+
 	if (reset_context->reset_req_dev->ip_versions[MP1_HWIP][0] ==
 		    IP_VERSION(13, 0, 2) &&
 	    reset_context->hive == NULL) {
@@ -350,19 +345,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		return -EINVAL;
 	}
 
-	INIT_LIST_HEAD(&reset_device_list);
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
-	if (reset_context->hive) {
-		list_for_each_entry (tmp_adev,
-				     &reset_context->hive->device_list,
-				     gmc.xgmi.head)
-			list_add_tail(&tmp_adev->reset_list,
-				      &reset_device_list);
-	} else {
-		list_add_tail(&reset_context->reset_req_dev->reset_list,
-			      &reset_device_list);
-	}
-
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
 		dev_info(tmp_adev->dev,
 			 "GPU reset succeeded, trying to resume\n");
 		r = aldebaran_mode2_restore_ip(tmp_adev);

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

@@ -317,7 +317,7 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-
+#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000

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

@@ -96,6 +96,7 @@ struct amdgpu_amdkfd_fence {
 struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
 	uint64_t vram_used;
+	uint64_t vram_used_aligned;
 	bool init_complete;
 	struct work_struct reset_work;
 };

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

@@ -40,10 +40,10 @@
 #define AMDGPU_USERPTR_RESTORE_DELAY_MS 1
 
 /*
- * Align VRAM allocations to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
+ * Align VRAM availability to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
  * BO chunk
  */
-#define VRAM_ALLOCATION_ALIGN (1 << 21)
+#define VRAM_AVAILABLITY_ALIGN (1 << 21)
 
 /* Impose limit on how much memory KFD can use */
 static struct {
@@ -149,7 +149,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 		 * to avoid fragmentation caused by 4K allocations in the tail
 		 * 2M BO chunk.
 		 */
-		vram_needed = ALIGN(size, VRAM_ALLOCATION_ALIGN);
+		vram_needed = size;
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
 		system_mem_needed = size;
 	} else if (!(alloc_flag &
@@ -182,8 +182,10 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	 */
 	WARN_ONCE(vram_needed && !adev,
 		  "adev reference can't be null when vram is used");
-	if (adev)
+	if (adev) {
 		adev->kfd.vram_used += vram_needed;
+		adev->kfd.vram_used_aligned += ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
+	}
 	kfd_mem_limit.system_mem_used += system_mem_needed;
 	kfd_mem_limit.ttm_mem_used += ttm_mem_needed;
 
@@ -203,8 +205,10 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		WARN_ONCE(!adev,
 			  "adev reference can't be null when alloc mem flags vram is set");
-		if (adev)
+		if (adev) {
-			adev->kfd.vram_used -= ALIGN(size, VRAM_ALLOCATION_ALIGN);
+			adev->kfd.vram_used -= size;
+			adev->kfd.vram_used_aligned -= ALIGN(size, VRAM_AVAILABLITY_ALIGN);
+		}
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
 		kfd_mem_limit.system_mem_used -= size;
 	} else if (!(alloc_flag &
@@ -1608,15 +1612,14 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev)
 	uint64_t reserved_for_pt =
 		ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size);
 	size_t available;
-
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 	available = adev->gmc.real_vram_size
-		- adev->kfd.vram_used
+		- adev->kfd.vram_used_aligned
 		- atomic64_read(&adev->vram_pin_size)
 		- reserved_for_pt;
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 
-	return ALIGN_DOWN(available, VRAM_ALLOCATION_ALIGN);
+	return ALIGN_DOWN(available, VRAM_AVAILABLITY_ALIGN);
 }
 
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(

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

@@ -314,7 +314,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = vram_info->v30.channel_num;
 					mem_channel_width = vram_info->v30.channel_width;
 					if (vram_width)
-						*vram_width = mem_channel_number * mem_channel_width;
+						*vram_width = mem_channel_number * (1 << mem_channel_width);
 					break;
 				default:
 					return -EINVAL;

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

@@ -837,16 +837,12 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			continue;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
-		if (r) {
+		if (r)
-			mutex_unlock(&p->bo_list->bo_list_mutex);
 			return r;
-		}
 
 		r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update);
-		if (r) {
+		if (r)
-			mutex_unlock(&p->bo_list->bo_list_mutex);
 			return r;
-		}
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);

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

@@ -1705,7 +1705,7 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
 	char reg_offset[11];
-	uint32_t *new, *tmp = NULL;
+	uint32_t *new = NULL, *tmp = NULL;
 	int ret, i = 0, len = 0;
 
 	do {
@@ -1747,7 +1747,8 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
 	ret = size;
 
 error_free:
-	kfree(tmp);
+	if (tmp != new)
+		kfree(tmp);
 	kfree(new);
 	return ret;
 }

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

@@ -4742,6 +4742,8 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 				    reset_list);
 	amdgpu_reset_reg_dumps(tmp_adev);
+
+	reset_context->reset_device_list = device_list_handle;
 	r = amdgpu_reset_perform_reset(tmp_adev, reset_context);
 	/* If reset handler not implemented, continue; otherwise return */
 	if (r == -ENOSYS)

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

@@ -272,10 +272,6 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	/* Signal all jobs not yet scheduled */
 	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		struct drm_sched_rq *rq = &sched->sched_rq[i];
-
-		if (!rq)
-			continue;
-
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list) {
 			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {

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

@@ -37,6 +37,7 @@ struct amdgpu_reset_context {
 	struct amdgpu_device *reset_req_dev;
 	struct amdgpu_job *job;
 	struct amdgpu_hive_info *hive;
+	struct list_head *reset_device_list;
 	unsigned long flags;
 };
 

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

@@ -637,6 +637,8 @@ struct amdgpu_ttm_tt {
 #endif
 };
 
+#define ttm_to_amdgpu_ttm_tt(ptr)	container_of(ptr, struct amdgpu_ttm_tt, ttm)
+
 #ifdef CONFIG_DRM_AMDGPU_USERPTR
 /*
  * amdgpu_ttm_tt_get_user_pages - get device accessible pages that back user
@@ -648,7 +650,7 @@ struct amdgpu_ttm_tt {
 int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 {
 	struct ttm_tt *ttm = bo->tbo.ttm;
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	unsigned long start = gtt->userptr;
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
@@ -702,7 +704,7 @@ out_unlock:
  */
 bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	bool r = false;
 
 	if (!gtt || !gtt->userptr)
@@ -751,7 +753,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_device *bdev,
 				     struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
@@ -788,7 +790,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev,
 					struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
@@ -822,7 +824,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
 {
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(tbo);
 	struct ttm_tt *ttm = tbo->ttm;
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (amdgpu_bo_encrypted(abo))
 		flags |= AMDGPU_PTE_TMZ;
@@ -860,7 +862,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev,
 				   struct ttm_resource *bo_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void*)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	uint64_t flags;
 	int r;
 
@@ -927,7 +929,7 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_ttm_tt *gtt = (void *)bo->ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(bo->ttm);
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	struct ttm_resource *tmp;
@@ -998,7 +1000,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev,
 				      struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	/* if the pages have userptr pinning then clear that first */
 	if (gtt->userptr) {
@@ -1025,7 +1027,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev,
 static void amdgpu_ttm_backend_destroy(struct ttm_device *bdev,
 				       struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt->usertask)
 		put_task_struct(gtt->usertask);
@@ -1079,7 +1081,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	pgoff_t i;
 	int ret;
 
@@ -1113,7 +1115,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 				     struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	struct amdgpu_device *adev;
 	pgoff_t i;
 
@@ -1182,7 +1184,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
 	/* Set TTM_TT_FLAG_EXTERNAL before populate but after create. */
 	bo->ttm->page_flags |= TTM_TT_FLAG_EXTERNAL;
 
-	gtt = (void *)bo->ttm;
+	gtt = ttm_to_amdgpu_ttm_tt(bo->ttm);
 	gtt->userptr = addr;
 	gtt->userflags = flags;
 
@@ -1199,7 +1201,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
  */
 struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL)
 		return NULL;
@@ -1218,7 +1220,7 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 				  unsigned long end, unsigned long *userptr)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	unsigned long size;
 
 	if (gtt == NULL || !gtt->userptr)
@@ -1241,7 +1243,7 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
  */
 bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL || !gtt->userptr)
 		return false;
@@ -1254,7 +1256,7 @@ bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm)
  */
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL)
 		return false;

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

@@ -496,8 +496,7 @@ static int amdgpu_vkms_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = YRES_MAX;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
 
 	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 

drivers/gpu/drm/amd/amdgpu/athub_v3_0.c

@@ -28,13 +28,44 @@
 #include "navi10_enum.h"
 #include "soc15_common.h"
 
+#define regATHUB_MISC_CNTL_V3_0_1			0x00d7
+#define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX		0
+
+
+static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
+{
+	uint32_t data;
+
+	switch (adev->ip_versions[ATHUB_HWIP][0]) {
+	case IP_VERSION(3, 0, 1):
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1);
+		break;
+	default:
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+		break;
+	}
+	return data;
+}
+
+static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data)
+{
+	switch (adev->ip_versions[ATHUB_HWIP][0]) {
+	case IP_VERSION(3, 0, 1):
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data);
+		break;
+	default:
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		break;
+	}
+}
+
 static void
 athub_v3_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 					    bool enable)
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	def = data = athub_v3_0_get_cg_cntl(adev);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ATHUB_MGCG))
 		data |= ATHUB_MISC_CNTL__CG_ENABLE_MASK;
@@ -42,7 +73,7 @@ athub_v3_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		data &= ~ATHUB_MISC_CNTL__CG_ENABLE_MASK;
 
 	if (def != data)
-		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		athub_v3_0_set_cg_cntl(adev, data);
 }
 
 static void
@@ -51,7 +82,7 @@ athub_v3_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	def = data = athub_v3_0_get_cg_cntl(adev);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ATHUB_LS))
 		data |= ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
@@ -59,7 +90,7 @@ athub_v3_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 		data &= ~ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
 
 	if (def != data)
-		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		athub_v3_0_set_cg_cntl(adev, data);
 }
 
 int athub_v3_0_set_clockgating(struct amdgpu_device *adev,
@@ -70,6 +101,7 @@ int athub_v3_0_set_clockgating(struct amdgpu_device *adev,
 
 	switch (adev->ip_versions[ATHUB_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 1):
 	case IP_VERSION(3, 0, 2):
 		athub_v3_0_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
@@ -88,7 +120,7 @@ void athub_v3_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 	int data;
 
 	/* AMD_CG_SUPPORT_ATHUB_MGCG */
-	data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	data = athub_v3_0_get_cg_cntl(adev);
 	if (data & ATHUB_MISC_CNTL__CG_ENABLE_MASK)
 		*flags |= AMD_CG_SUPPORT_ATHUB_MGCG;
 

drivers/gpu/drm/amd/amdgpu/dce_v10_0.c

@@ -2796,8 +2796,7 @@ static int dce_v10_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 

drivers/gpu/drm/amd/amdgpu/dce_v11_0.c

@@ -2914,8 +2914,7 @@ static int dce_v11_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 

drivers/gpu/drm/amd/amdgpu/dce_v6_0.c

@@ -2673,8 +2673,7 @@ static int dce_v6_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_width = 16384;
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 

drivers/gpu/drm/amd/amdgpu/dce_v8_0.c

@@ -2693,8 +2693,11 @@ static int dce_v8_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
+	if (adev->asic_type == CHIP_HAWAII)
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+		/* disable prefer shadow for now due to hibernation issues */
+		adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	else
+		adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -4846,7 +4846,7 @@ static int gfx_v10_0_sw_init(void *handle)
 	case IP_VERSION(10, 3, 3):
 	case IP_VERSION(10, 3, 7):
 		adev->gfx.me.num_me = 1;
-		adev->gfx.me.num_pipe_per_me = 2;
+		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
 		adev->gfx.mec.num_mec = 2;
 		adev->gfx.mec.num_pipe_per_mec = 4;

drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c

@@ -53,6 +53,7 @@
 #define GFX11_MEC_HPD_SIZE	2048
 
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
+#define RLC_PG_DELAY_3_DEFAULT_GC_11_0_1	0x1388
 
 #define regCGTT_WD_CLK_CTRL		0x5086
 #define regCGTT_WD_CLK_CTRL_BASE_IDX	1
@@ -5279,6 +5280,38 @@ static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = {
 	.update_spm_vmid = gfx_v11_0_update_spm_vmid,
 };
 
+static void gfx_v11_cntl_power_gating(struct amdgpu_device *adev, bool enable)
+{
+	u32 data = RREG32_SOC15(GC, 0, regRLC_PG_CNTL);
+
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
+		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+
+	WREG32_SOC15(GC, 0, regRLC_PG_CNTL, data);
+
+	// Program RLC_PG_DELAY3 for CGPG hysteresis
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
+		switch (adev->ip_versions[GC_HWIP][0]) {
+		case IP_VERSION(11, 0, 1):
+			WREG32_SOC15(GC, 0, regRLC_PG_DELAY_3, RLC_PG_DELAY_3_DEFAULT_GC_11_0_1);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void gfx_v11_cntl_pg(struct amdgpu_device *adev, bool enable)
+{
+	amdgpu_gfx_rlc_enter_safe_mode(adev);
+
+	gfx_v11_cntl_power_gating(adev, enable);
+
+	amdgpu_gfx_rlc_exit_safe_mode(adev);
+}
+
 static int gfx_v11_0_set_powergating_state(void *handle,
 					   enum amd_powergating_state state)
 {
@@ -5293,6 +5326,11 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 	case IP_VERSION(11, 0, 2):
 		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
+	case IP_VERSION(11, 0, 1):
+		gfx_v11_cntl_pg(adev, enable);
+		/* TODO: Enable this when GFXOFF is ready */
+		// amdgpu_gfx_off_ctrl(adev, enable);
+		break;
 	default:
 		break;
 	}
@@ -5310,6 +5348,7 @@ static int gfx_v11_0_set_clockgating_state(void *handle,
 
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 2):
 	        gfx_v11_0_update_gfx_clock_gating(adev,
 	                        state ==  AMD_CG_STATE_GATE);

drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c

@@ -419,6 +419,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -437,7 +438,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			return -ETIME;

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -896,6 +896,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -935,7 +936,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			up_read(&adev->reset_domain->sem);
@@ -1624,12 +1625,15 @@ static int gmc_v9_0_sw_init(void *handle)
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 47);
 		else
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
+		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
+			adev->gmc.translate_further = adev->vm_manager.num_level > 1;
 		break;
 	case IP_VERSION(9, 4, 1):
 		adev->num_vmhubs = 3;
 
 		/* Keep the vm size same with Vega20 */
 		amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
+		adev->gmc.translate_further = adev->vm_manager.num_level > 1;
 		break;
 	default:
 		break;

drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c

@@ -40,6 +40,156 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
 			0);
 }
 
+static void hdp_v5_2_update_mem_power_gating(struct amdgpu_device *adev,
+					     bool enable)
+{
+	uint32_t hdp_clk_cntl;
+	uint32_t hdp_mem_pwr_cntl;
+
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS |
+				AMD_CG_SUPPORT_HDP_DS |
+				AMD_CG_SUPPORT_HDP_SD)))
+		return;
+
+	hdp_clk_cntl = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+	hdp_mem_pwr_cntl = RREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL);
+
+	/* Before doing clock/power mode switch, forced on MEM clock */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     ATOMIC_MEM_CLK_SOFT_OVERRIDE, 1);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 1);
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+
+	/* disable clock and power gating before any changing */
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_CTRL_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_LS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_DS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_SD_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_CTRL_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_LS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_DS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_SD_EN, 0);
+	WREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+
+	/* Already disabled above. The actions below are for "enabled" only */
+	if (enable) {
+		/* only one clock gating mode (LS/DS/SD) can be enabled */
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_SD_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_SD_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_LS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_LS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_DS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_DS_EN, 1);
+		}
+
+		/* confirmed that ATOMIC/RC_MEM_POWER_CTRL_EN have to be set for SRAM LS/DS/SD */
+		if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
+				      AMD_CG_SUPPORT_HDP_SD)) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_CTRL_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_CTRL_EN, 1);
+			WREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+		}
+	}
+
+	/* disable MEM clock override after clock/power mode changing */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     ATOMIC_MEM_CLK_SOFT_OVERRIDE, 0);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 0);
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+}
+
+static void hdp_v5_2_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t hdp_clk_cntl;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
+		return;
+
+	hdp_clk_cntl = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+
+	if (enable) {
+		hdp_clk_cntl &=
+			~(uint32_t)
+			(HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK);
+	} else {
+		hdp_clk_cntl |= HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK;
+	}
+
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+}
+
+static void hdp_v5_2_get_clockgating_state(struct amdgpu_device *adev,
+					   u64 *flags)
+{
+	uint32_t tmp;
+
+	/* AMD_CG_SUPPORT_HDP_MGCG */
+	tmp = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+	if (!(tmp & (HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK)))
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+
+	/* AMD_CG_SUPPORT_HDP_LS/DS/SD */
+	tmp = RREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL);
+	if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_LS;
+	else if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_DS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_DS;
+	else if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_SD_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_SD;
+}
+
+static void hdp_v5_2_update_clock_gating(struct amdgpu_device *adev,
+					      bool enable)
+{
+	hdp_v5_2_update_mem_power_gating(adev, enable);
+	hdp_v5_2_update_medium_grain_clock_gating(adev, enable);
+}
+
 const struct amdgpu_hdp_funcs hdp_v5_2_funcs = {
 	.flush_hdp = hdp_v5_2_flush_hdp,
+	.update_clock_gating = hdp_v5_2_update_clock_gating,
+	.get_clock_gating_state = hdp_v5_2_get_clockgating_state,
 };

drivers/gpu/drm/amd/amdgpu/ih_v6_0.c

@@ -727,6 +727,7 @@ static const struct amd_ip_funcs ih_v6_0_ip_funcs = {
 static const struct amdgpu_ih_funcs ih_v6_0_funcs = {
 	.get_wptr = ih_v6_0_get_wptr,
 	.decode_iv = amdgpu_ih_decode_iv_helper,
+	.decode_iv_ts = amdgpu_ih_decode_iv_ts_helper,
 	.set_rptr = ih_v6_0_set_rptr
 };
 

drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c

@@ -518,18 +518,41 @@ static u64 mmhub_v3_0_1_get_mc_fb_offset(struct amdgpu_device *adev)
 static void mmhub_v3_0_1_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 							  bool enable)
 {
-	//TODO
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	if (enable)
+		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
+	else
+		data &= ~MM_ATC_L2_MISC_CG__ENABLE_MASK;
+
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG, data);
 }
 
 static void mmhub_v3_0_1_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 							 bool enable)
 {
-	//TODO
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	if (enable)
+		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+	else
+		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG, data);
 }
 
 static int mmhub_v3_0_1_set_clockgating(struct amdgpu_device *adev,
 					enum amd_clockgating_state state)
 {
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	mmhub_v3_0_1_update_medium_grain_clock_gating(adev,
 			state == AMD_CG_STATE_GATE);
 	mmhub_v3_0_1_update_medium_grain_light_sleep(adev,
@@ -539,7 +562,20 @@ static int mmhub_v3_0_1_set_clockgating(struct amdgpu_device *adev,
 
 static void mmhub_v3_0_1_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 {
-	//TODO
+	int data;
+
+	if (amdgpu_sriov_vf(adev))
+		*flags = 0;
+
+	data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	/* AMD_CG_SUPPORT_MC_MGCG */
+	if (data & MM_ATC_L2_MISC_CG__ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_MC_MGCG;
+
+	/* AMD_CG_SUPPORT_MC_LS */
+	if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
 
 const struct amdgpu_mmhub_funcs mmhub_v3_0_1_funcs = {

drivers/gpu/drm/amd/amdgpu/navi10_ih.c

@@ -409,9 +409,11 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -483,6 +485,9 @@ static void navi10_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;

drivers/gpu/drm/amd/amdgpu/psp_v12_0.c

@@ -101,6 +101,16 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 		adev->psp.dtm_context.context.bin_desc.start_addr =
 			(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
 			le32_to_cpu(ta_hdr->dtm.offset_bytes);
+
+		if (adev->apu_flags & AMD_APU_IS_RENOIR) {
+			adev->psp.securedisplay_context.context.bin_desc.fw_version =
+				le32_to_cpu(ta_hdr->securedisplay.fw_version);
+			adev->psp.securedisplay_context.context.bin_desc.size_bytes =
+				le32_to_cpu(ta_hdr->securedisplay.size_bytes);
+			adev->psp.securedisplay_context.context.bin_desc.start_addr =
+				(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
+				le32_to_cpu(ta_hdr->securedisplay.offset_bytes);
+		}
 	}
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/psp_v13_0.c

@@ -20,7 +20,6 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
-#include <linux/dev_printk.h>
 #include <drm/drm_drv.h>
 #include <linux/vmalloc.h>
 #include "amdgpu.h"

drivers/gpu/drm/amd/amdgpu/soc21.c

@@ -546,8 +546,10 @@ static int soc21_common_early_init(void *handle)
 	case IP_VERSION(11, 0, 0):
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_CGCG |
 			AMD_CG_SUPPORT_GFX_CGLS |
+#if 0
 			AMD_CG_SUPPORT_GFX_3D_CGCG |
 			AMD_CG_SUPPORT_GFX_3D_CGLS |
+#endif
 			AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_REPEATER_FGCG |
 			AMD_CG_SUPPORT_GFX_FGCG |
@@ -575,7 +577,9 @@ static int soc21_common_early_init(void *handle)
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_ATHUB_MGCG |
-			AMD_CG_SUPPORT_ATHUB_LS;
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_HDP_SD;
 		adev->pg_flags =
 			AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
@@ -586,9 +590,23 @@ static int soc21_common_early_init(void *handle)
 		break;
 	case IP_VERSION(11, 0, 1):
 		adev->cg_flags =
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_FGCG |
+			AMD_CG_SUPPORT_REPEATER_FGCG |
+			AMD_CG_SUPPORT_GFX_PERF_CLK |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags =
+			AMD_PG_SUPPORT_GFX_PG |
 			AMD_PG_SUPPORT_JPEG;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
@@ -683,6 +701,7 @@ static int soc21_common_set_clockgating_state(void *handle,
 
 	switch (adev->ip_versions[NBIO_HWIP][0]) {
 	case IP_VERSION(4, 3, 0):
+	case IP_VERSION(4, 3, 1):
 		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
@@ -690,6 +709,10 @@ static int soc21_common_set_clockgating_state(void *handle,
 		adev->hdp.funcs->update_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		break;
+	case IP_VERSION(7, 7, 0):
+		adev->hdp.funcs->update_clock_gating(adev,
+				state == AMD_CG_STATE_GATE);
+		break;
 	default:
 		break;
 	}

drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c

@@ -1115,7 +1115,7 @@ static int vcn_v4_0_start(struct amdgpu_device *adev)
  *
  * Stop VCN block with dpg mode
  */
-static int vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 {
 	uint32_t tmp;
 
@@ -1133,7 +1133,6 @@ static int vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	/* disable dynamic power gating mode */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 0,
 		~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
-	return 0;
 }
 
 /**
@@ -1154,7 +1153,7 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev)
 		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_stop_dpg_mode(adev, i);
+			vcn_v4_0_stop_dpg_mode(adev, i);
 			continue;
 		}
 

drivers/gpu/drm/amd/amdgpu/vega10_ih.c

@@ -334,9 +334,11 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -409,6 +411,9 @@ static void vega10_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;

drivers/gpu/drm/amd/amdgpu/vega20_ih.c

@@ -385,9 +385,11 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -461,6 +463,9 @@ static void vega20_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;

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

@@ -874,7 +874,7 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
 	err = kfd_wait_on_events(p, args->num_events,
 			(void __user *)args->events_ptr,
 			(args->wait_for_all != 0),
-			args->timeout, &args->wait_result);
+			&args->timeout, &args->wait_result);
 
 	return err;
 }

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

@@ -102,13 +102,18 @@ static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
 
 	switch (sdma_version) {
 	case IP_VERSION(6, 0, 0):
-	case IP_VERSION(6, 0, 1):
 	case IP_VERSION(6, 0, 2):
 		/* Reserve 1 for paging and 1 for gfx */
 		kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
 		/* BIT(0)=engine-0 queue-0; BIT(1)=engine-1 queue-0; BIT(2)=engine-0 queue-1; ... */
 		kfd->device_info.reserved_sdma_queues_bitmap = 0xFULL;
 		break;
+	case IP_VERSION(6, 0, 1):
+		/* Reserve 1 for paging and 1 for gfx */
+		kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
+		/* BIT(0)=engine-0 queue-0; BIT(1)=engine-0 queue-1; ... */
+		kfd->device_info.reserved_sdma_queues_bitmap = 0x3ULL;
+		break;
 	default:
 		break;
 	}

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

@@ -894,7 +894,8 @@ static long user_timeout_to_jiffies(uint32_t user_timeout_ms)
 	return msecs_to_jiffies(user_timeout_ms) + 1;
 }
 
-static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
+static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters,
+			 bool undo_auto_reset)
 {
 	uint32_t i;
 
@@ -903,6 +904,9 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
 			spin_lock(&waiters[i].event->lock);
 			remove_wait_queue(&waiters[i].event->wq,
 					  &waiters[i].wait);
+			if (undo_auto_reset && waiters[i].activated &&
+			    waiters[i].event && waiters[i].event->auto_reset)
+				set_event(waiters[i].event);
 			spin_unlock(&waiters[i].event->lock);
 		}
 
@@ -911,7 +915,7 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
 
 int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
-		       bool all, uint32_t user_timeout_ms,
+		       bool all, uint32_t *user_timeout_ms,
 		       uint32_t *wait_result)
 {
 	struct kfd_event_data __user *events =
@@ -920,7 +924,7 @@ int kfd_wait_on_events(struct kfd_process *p,
 	int ret = 0;
 
 	struct kfd_event_waiter *event_waiters = NULL;
-	long timeout = user_timeout_to_jiffies(user_timeout_ms);
+	long timeout = user_timeout_to_jiffies(*user_timeout_ms);
 
 	event_waiters = alloc_event_waiters(num_events);
 	if (!event_waiters) {
@@ -970,15 +974,11 @@ int kfd_wait_on_events(struct kfd_process *p,
 		}
 
 		if (signal_pending(current)) {
-			/*
-			 * This is wrong when a nonzero, non-infinite timeout
-			 * is specified. We need to use
-			 * ERESTARTSYS_RESTARTBLOCK, but struct restart_block
-			 * contains a union with data for each user and it's
-			 * in generic kernel code that I don't want to
-			 * touch yet.
-			 */
 			ret = -ERESTARTSYS;
+			if (*user_timeout_ms != KFD_EVENT_TIMEOUT_IMMEDIATE &&
+			    *user_timeout_ms != KFD_EVENT_TIMEOUT_INFINITE)
+				*user_timeout_ms = jiffies_to_msecs(
+					max(0l, timeout-1));
 			break;
 		}
 
@@ -1019,7 +1019,7 @@ int kfd_wait_on_events(struct kfd_process *p,
 					       event_waiters, events);
 
 out_unlock:
-	free_waiters(num_events, event_waiters);
+	free_waiters(num_events, event_waiters, ret == -ERESTARTSYS);
 	mutex_unlock(&p->event_mutex);
 out:
 	if (ret)

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -1317,7 +1317,7 @@ void kfd_event_free_process(struct kfd_process *p);
 int kfd_event_mmap(struct kfd_process *process, struct vm_area_struct *vma);
 int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
-		       bool all, uint32_t user_timeout_ms,
+		       bool all, uint32_t *user_timeout_ms,
 		       uint32_t *wait_result);
 void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits);

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

@@ -541,7 +541,6 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
 		kfree(svm_bo);
 		return -ESRCH;
 	}
-	svm_bo->svms = prange->svms;
 	svm_bo->eviction_fence =
 		amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
 					   mm,
@@ -3273,7 +3272,6 @@ int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 {
 	struct svm_range_bo *svm_bo;
-	struct kfd_process *p;
 	struct mm_struct *mm;
 	int r = 0;
 
@@ -3281,13 +3279,12 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	if (!svm_bo_ref_unless_zero(svm_bo))
 		return; /* svm_bo was freed while eviction was pending */
 
-	/* svm_range_bo_release destroys this worker thread. So during
+	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
-	 * the lifetime of this thread, kfd_process and mm will be valid.
+		mm = svm_bo->eviction_fence->mm;
-	 */
+	} else {
-	p = container_of(svm_bo->svms, struct kfd_process, svms);
+		svm_range_bo_unref(svm_bo);
-	mm = p->mm;
-	if (!mm)
 		return;
+	}
 
 	mmap_read_lock(mm);
 	spin_lock(&svm_bo->list_lock);
@@ -3305,8 +3302,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 
 		mutex_lock(&prange->migrate_mutex);
 		do {
-			r = svm_migrate_vram_to_ram(prange,
+			r = svm_migrate_vram_to_ram(prange, mm,
-						svm_bo->eviction_fence->mm,
 						KFD_MIGRATE_TRIGGER_TTM_EVICTION);
 		} while (!r && prange->actual_loc && --retries);
 
@@ -3324,6 +3320,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	}
 	spin_unlock(&svm_bo->list_lock);
 	mmap_read_unlock(mm);
+	mmput(mm);
 
 	dma_fence_signal(&svm_bo->eviction_fence->base);
 

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

@@ -46,7 +46,6 @@ struct svm_range_bo {
 	spinlock_t			list_lock;
 	struct amdgpu_amdkfd_fence	*eviction_fence;
 	struct work_struct		eviction_work;
-	struct svm_range_list		*svms;
 	uint32_t			evicting;
 	struct work_struct		release_work;
 };

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

@@ -1392,8 +1392,8 @@ static int kfd_build_p2p_node_entry(struct kfd_topology_device *dev,
 
 static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int gpu_node)
 {
+	struct kfd_iolink_properties *gpu_link, *tmp_link, *cpu_link;
 	struct kfd_iolink_properties *props = NULL, *props2 = NULL;
-	struct kfd_iolink_properties *gpu_link, *cpu_link;
 	struct kfd_topology_device *cpu_dev;
 	int ret = 0;
 	int i, num_cpu;
@@ -1416,16 +1416,19 @@ static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int g
 			continue;
 
 		/* find CPU <-->  CPU links */
+		cpu_link = NULL;
 		cpu_dev = kfd_topology_device_by_proximity_domain(i);
 		if (cpu_dev) {
-			list_for_each_entry(cpu_link,
+			list_for_each_entry(tmp_link,
 					&cpu_dev->io_link_props, list) {
-				if (cpu_link->node_to == gpu_link->node_to)
+				if (tmp_link->node_to == gpu_link->node_to) {
+					cpu_link = tmp_link;
 					break;
+				}
 			}
 		}
 
-		if (cpu_link->node_to != gpu_link->node_to)
+		if (!cpu_link)
 			return -ENOMEM;
 
 		/* CPU <--> CPU <--> GPU, GPU node*/

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

@@ -3825,8 +3825,11 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
+	if (adev->asic_type == CHIP_HAWAII)
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+		/* disable prefer shadow for now due to hibernation issues */
+		adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	else
+		adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 	/* indicates support for immediate flip */
 	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
@@ -4135,6 +4138,7 @@ static void register_backlight_device(struct amdgpu_display_manager *dm,
 	}
 }
 
+static void amdgpu_set_panel_orientation(struct drm_connector *connector);
 
 /*
  * In this architecture, the association
@@ -4326,6 +4330,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 					adev_to_drm(adev)->vblank_disable_immediate = false;
 			}
 		}
+		amdgpu_set_panel_orientation(&aconnector->base);
 	}
 
 	/* Software is initialized. Now we can register interrupt handlers. */
@@ -6684,6 +6689,10 @@ static void amdgpu_set_panel_orientation(struct drm_connector *connector)
 	    connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
 		return;
 
+	mutex_lock(&connector->dev->mode_config.mutex);
+	amdgpu_dm_connector_get_modes(connector);
+	mutex_unlock(&connector->dev->mode_config.mutex);
+
 	encoder = amdgpu_dm_connector_to_encoder(connector);
 	if (!encoder)
 		return;
@@ -6728,8 +6737,6 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 		 * restored here.
 		 */
 		amdgpu_dm_update_freesync_caps(connector, edid);
-
-		amdgpu_set_panel_orientation(connector);
 	} else {
 		amdgpu_dm_connector->num_modes = 0;
 	}

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

@@ -660,7 +660,7 @@ static int get_plane_modifiers(struct amdgpu_device *adev, unsigned int plane_ty
 			add_gfx10_1_modifiers(adev, mods, &size, &capacity);
 		break;
 	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		add_gfx11_modifiers(adev, mods, &size, &capacity);
 		break;
 	}
@@ -1412,7 +1412,7 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
 		}
 		break;
 	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_2:
+	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:

drivers/gpu/drm/amd/display/dc/basics/conversion.c

@@ -100,3 +100,24 @@ void convert_float_matrix(
 		matrix[i] = (uint16_t)reg_value;
 	}
 }
+
+static uint32_t find_gcd(uint32_t a, uint32_t b)
+{
+	uint32_t remainder = 0;
+	while (b != 0) {
+		remainder = a % b;
+		a = b;
+		b = remainder;
+	}
+	return a;
+}
+
+void reduce_fraction(uint32_t num, uint32_t den,
+		uint32_t *out_num, uint32_t *out_den)
+{
+	uint32_t gcd = 0;
+
+	gcd = find_gcd(num, den);
+	*out_num = num / gcd;
+	*out_den = den / gcd;
+}

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

@@ -38,6 +38,9 @@ void convert_float_matrix(
 	struct fixed31_32 *flt,
 	uint32_t buffer_size);
 
+void reduce_fraction(uint32_t num, uint32_t den,
+		uint32_t *out_num, uint32_t *out_den);
+
 static inline unsigned int log_2(unsigned int num)
 {
 	return ilog2(num);