Merge 4.19-rc6 into usb-next

We want the USB fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

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

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

Documentation/devicetree/bindings/net/macb.txt

@@ -10,6 +10,7 @@ Required properties:
   Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on
   the Cadence GEM, or the generic form: "cdns,gem".
   Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs.
+  Use "atmel,sama5d3-macb" for the 10/100Mbit IP available on Atmel sama5d3 SoCs.
   Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs.
   Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs.
   Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC.

Documentation/media/uapi/dvb/video_function_calls.rst

@@ -33,4 +33,3 @@ Video Function Calls
     video-clear-buffer
     video-set-streamtype
     video-set-format
-    video-set-attributes

Documentation/virtual/kvm/api.txt

@@ -4510,7 +4510,8 @@ Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 Architectures: s390
 Parameters: none
 Returns: 0 on success, -EINVAL if hpage module parameter was not set
-	 or cmma is enabled
+	 or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL
+	 flag set
 
 With this capability the KVM support for memory backing with 1m pages
 through hugetlbfs can be enabled for a VM. After the capability is
@@ -4521,6 +4522,15 @@ hpage module parameter is not set to 1, -EINVAL is returned.
 While it is generally possible to create a huge page backed VM without
 this capability, the VM will not be able to run.
 
+7.14 KVM_CAP_MSR_PLATFORM_INFO
+
+Architectures: x86
+Parameters: args[0] whether feature should be enabled or not
+
+With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
+a #GP would be raised when the guest tries to access. Currently, this
+capability does not enable write permissions of this MSR for the guest.
+
 8. Other capabilities.
 ----------------------
 

MAINTAINERS

@@ -9716,13 +9716,6 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/mn88473*
 
-PCI DRIVER FOR MOBIVEIL PCIE IP
-M:	Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
-L:	linux-pci@vger.kernel.org
-S:	Supported
-F:	Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
-F:	drivers/pci/controller/pcie-mobiveil.c
-
 MODULE SUPPORT
 M:	Jessica Yu <jeyu@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux.git modules-next
@@ -10949,7 +10942,7 @@ M:	Willy Tarreau <willy@haproxy.com>
 M:	Ksenija Stanojevic <ksenija.stanojevic@gmail.com>
 S:	Odd Fixes
 F:	Documentation/auxdisplay/lcd-panel-cgram.txt
-F:	drivers/misc/panel.c
+F:	drivers/auxdisplay/panel.c
 
 PARALLEL PORT SUBSYSTEM
 M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
@@ -11137,6 +11130,13 @@ F:	include/uapi/linux/switchtec_ioctl.h
 F:	include/linux/switchtec.h
 F:	drivers/ntb/hw/mscc/
 
+PCI DRIVER FOR MOBIVEIL PCIE IP
+M:	Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
+L:	linux-pci@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
+F:	drivers/pci/controller/pcie-mobiveil.c
+
 PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support)
 M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
 M:	Jason Cooper <jason@lakedaemon.net>
@@ -11203,8 +11203,14 @@ F:	tools/pci/
 
 PCI ENHANCED ERROR HANDLING (EEH) FOR POWERPC
 M:	Russell Currey <ruscur@russell.cc>
+M:	Sam Bobroff <sbobroff@linux.ibm.com>
+M:	Oliver O'Halloran <oohall@gmail.com>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
+F:	Documentation/PCI/pci-error-recovery.txt
+F:	drivers/pci/pcie/aer.c
+F:	drivers/pci/pcie/dpc.c
+F:	drivers/pci/pcie/err.c
 F:	Documentation/powerpc/eeh-pci-error-recovery.txt
 F:	arch/powerpc/kernel/eeh*.c
 F:	arch/powerpc/platforms/*/eeh*.c
@@ -12260,6 +12266,7 @@ F:	Documentation/networking/rds.txt
 
 RDT - RESOURCE ALLOCATION
 M:	Fenghua Yu <fenghua.yu@intel.com>
+M:	Reinette Chatre <reinette.chatre@intel.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	arch/x86/kernel/cpu/intel_rdt*
@@ -13449,9 +13456,8 @@ F:	drivers/i2c/busses/i2c-synquacer.c
 F:	Documentation/devicetree/bindings/i2c/i2c-synquacer.txt
 
 SOCIONEXT UNIPHIER SOUND DRIVER
-M:	Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
-S:	Maintained
+S:	Orphan
 F:	sound/soc/uniphier/
 
 SOEKRIS NET48XX LED SUPPORT
@@ -15919,6 +15925,7 @@ F:	net/x25/
 X86 ARCHITECTURE (32-BIT AND 64-BIT)
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Ingo Molnar <mingo@redhat.com>
+M:	Borislav Petkov <bp@alien8.de>
 R:	"H. Peter Anvin" <hpa@zytor.com>
 M:	x86@kernel.org
 L:	linux-kernel@vger.kernel.org
@@ -15947,6 +15954,15 @@ M:	Borislav Petkov <bp@alien8.de>
 S:	Maintained
 F:	arch/x86/kernel/cpu/microcode/*
 
+X86 MM
+M:	Dave Hansen <dave.hansen@linux.intel.com>
+M:	Andy Lutomirski <luto@kernel.org>
+M:	Peter Zijlstra <peterz@infradead.org>
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm
+S:	Maintained
+F:	arch/x86/mm/
+
 X86 PLATFORM DRIVERS
 M:	Darren Hart <dvhart@infradead.org>
 M:	Andy Shevchenko <andy@infradead.org>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Merciless Moray
 
 # *DOCUMENTATION*
@@ -299,19 +299,7 @@ KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null)
 KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION)
 export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION
 
-# SUBARCH tells the usermode build what the underlying arch is.  That is set
+include scripts/subarch.include
-# first, and if a usermode build is happening, the "ARCH=um" on the command
-# line overrides the setting of ARCH below.  If a native build is happening,
-# then ARCH is assigned, getting whatever value it gets normally, and
-# SUBARCH is subsequently ignored.
-
-SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
-				  -e s/sun4u/sparc64/ \
-				  -e s/arm.*/arm/ -e s/sa110/arm/ \
-				  -e s/s390x/s390/ -e s/parisc64/parisc/ \
-				  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-				  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
-				  -e s/riscv.*/riscv/)
 
 # Cross compiling and selecting different set of gcc/bin-utils
 # ---------------------------------------------------------------------------

arch/arm/boot/dts/sama5d3_emac.dtsi

@@ -41,7 +41,7 @@ macb1_clk: macb1_clk {
 			};
 
 			macb1: ethernet@f802c000 {
-				compatible = "cdns,at91sam9260-macb", "cdns,macb";
+				compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb";
 				reg = <0xf802c000 0x100>;
 				interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>;
 				pinctrl-names = "default";

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1051,7 +1051,6 @@ static inline void vmemmap_remove_mapping(unsigned long start,
 	return hash__vmemmap_remove_mapping(start, page_size);
 }
 #endif
-struct page *realmode_pfn_to_page(unsigned long pfn);
 
 static inline pte_t pmd_pte(pmd_t pmd)
 {

arch/powerpc/include/asm/iommu.h

@@ -220,8 +220,6 @@ extern void iommu_del_device(struct device *dev);
 extern int __init tce_iommu_bus_notifier_init(void);
 extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction);
-extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
-		unsigned long *hpa, enum dma_data_direction *direction);
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,

arch/powerpc/include/asm/mmu_context.h

@@ -38,6 +38,7 @@ extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
+extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif

arch/powerpc/include/asm/setup.h

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

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

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

arch/powerpc/kernel/iommu.c

@@ -1013,31 +1013,6 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_xchg);
 
-#ifdef CONFIG_PPC_BOOK3S_64
-long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret;
-
-	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
-
-	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
-			(*direction == DMA_BIDIRECTIONAL))) {
-		struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
-
-		if (likely(pg)) {
-			SetPageDirty(pg);
-		} else {
-			tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
-			ret = -EFAULT;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
-#endif
-
 int iommu_take_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;

arch/powerpc/kernel/tm.S

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

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -525,8 +525,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				   unsigned long ea, unsigned long dsisr)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long mmu_seq, pte_size;
+	unsigned long mmu_seq;
-	unsigned long gpa, gfn, hva, pfn;
+	unsigned long gpa, gfn, hva;
 	struct kvm_memory_slot *memslot;
 	struct page *page = NULL;
 	long ret;
@@ -623,9 +623,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	hva = gfn_to_hva_memslot(memslot, gfn);
 	if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
-		pfn = page_to_pfn(page);
 		upgrade_write = true;
 	} else {
+		unsigned long pfn;
+
 		/* Call KVM generic code to do the slow-path check */
 		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
 					   writing, upgrade_p);
@@ -639,61 +640,43 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		}
 	}
 
-	/* See if we can insert a 1GB or 2MB large PTE here */
+	/*
-	level = 0;
+	 * Read the PTE from the process' radix tree and use that
-	if (page && PageCompound(page)) {
+	 * so we get the shift and attribute bits.
-		pte_size = PAGE_SIZE << compound_order(compound_head(page));
+	 */
-		if (pte_size >= PUD_SIZE &&
+	local_irq_disable();
-		    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
-		    (hva & (PUD_SIZE - PAGE_SIZE))) {
+	pte = *ptep;
-			level = 2;
+	local_irq_enable();
-			pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1);
+
-		} else if (pte_size >= PMD_SIZE &&
+	/* Get pte level from shift/size */
-			   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+	if (shift == PUD_SHIFT &&
-			   (hva & (PMD_SIZE - PAGE_SIZE))) {
+	    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
-			level = 1;
+	    (hva & (PUD_SIZE - PAGE_SIZE))) {
-			pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
+		level = 2;
+	} else if (shift == PMD_SHIFT &&
+		   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+		   (hva & (PMD_SIZE - PAGE_SIZE))) {
+		level = 1;
+	} else {
+		level = 0;
+		if (shift > PAGE_SHIFT) {
+			/*
+			 * If the pte maps more than one page, bring over
+			 * bits from the virtual address to get the real
+			 * address of the specific single page we want.
+			 */
+			unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+			pte = __pte(pte_val(pte) | (hva & rpnmask));
 		}
 	}
 
-	/*
+	pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
-	 * Compute the PTE value that we need to insert.
+	if (writing || upgrade_write) {
-	 */
+		if (pte_val(pte) & _PAGE_WRITE)
-	if (page) {
+			pte = __pte(pte_val(pte) | _PAGE_DIRTY);
-		pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE |
-			_PAGE_ACCESSED;
-		if (writing || upgrade_write)
-			pgflags |= _PAGE_WRITE | _PAGE_DIRTY;
-		pte = pfn_pte(pfn, __pgprot(pgflags));
 	} else {
-		/*
+		pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
-		 * Read the PTE from the process' radix tree and use that
-		 * so we get the attribute bits.
-		 */
-		local_irq_disable();
-		ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
-		pte = *ptep;
-		local_irq_enable();
-		if (shift == PUD_SHIFT &&
-		    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
-		    (hva & (PUD_SIZE - PAGE_SIZE))) {
-			level = 2;
-		} else if (shift == PMD_SHIFT &&
-			   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
-			   (hva & (PMD_SIZE - PAGE_SIZE))) {
-			level = 1;
-		} else if (shift && shift != PAGE_SHIFT) {
-			/* Adjust PFN */
-			unsigned long mask = (1ul << shift) - PAGE_SIZE;
-			pte = __pte(pte_val(pte) | (hva & mask));
-		}
-		pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
-		if (writing || upgrade_write) {
-			if (pte_val(pte) & _PAGE_WRITE)
-				pte = __pte(pte_val(pte) | _PAGE_DIRTY);
-		} else {
-			pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
-		}
 	}
 
 	/* Allocate space in the tree and write the PTE */

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -187,12 +187,35 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
 EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long *hpa,
+		enum dma_data_direction *direction)
+{
+	long ret;
+
+	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+				(*direction == DMA_BIDIRECTIONAL))) {
+		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+		/*
+		 * kvmppc_rm_tce_iommu_do_map() updates the UA cache after
+		 * calling this so we still get here a valid UA.
+		 */
+		if (pua && *pua)
+			mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua));
+	}
+
+	return ret;
+}
+
+static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry)
 {
 	unsigned long hpa = 0;
 	enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+	iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
 }
 
 static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -224,7 +247,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
 	unsigned long hpa = 0;
 	long ret;
 
-	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+	if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir))
 		/*
 		 * real mode xchg can fail if struct page crosses
 		 * a page boundary
@@ -236,7 +259,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
 
 	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
 	if (ret)
-		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
 
 	return ret;
 }
@@ -282,7 +305,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
 		return H_CLOSED;
 
-	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+	ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
 	if (ret) {
 		mm_iommu_mapped_dec(mem);
 		/*
@@ -371,7 +394,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			return ret;
 
 		WARN_ON_ONCE_RM(1);
-		kvmppc_rm_clear_tce(stit->tbl, entry);
+		kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
 	}
 
 	kvmppc_tce_put(stt, entry, tce);
@@ -520,7 +543,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 				goto unlock_exit;
 
 			WARN_ON_ONCE_RM(1);
-			kvmppc_rm_clear_tce(stit->tbl, entry);
+			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
 		}
 
 		kvmppc_tce_put(stt, entry + i, tce);
@@ -571,7 +594,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 				return ret;
 
 			WARN_ON_ONCE_RM(1);
-			kvmppc_rm_clear_tce(stit->tbl, entry);
+			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
 		}
 	}
 

arch/powerpc/lib/checksum_64.S

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

arch/powerpc/lib/code-patching.c

@@ -28,6 +28,12 @@ static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
 {
 	int err;
 
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(exec_addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr);
+		return 0;
+	}
+
 	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;

arch/powerpc/mm/init_64.c

@@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 {
 }
 
-/*
- * We do not have access to the sparsemem vmemmap, so we fallback to
- * walking the list of sparsemem blocks which we already maintain for
- * the sake of crashdump. In the long run, we might want to maintain
- * a tree if performance of that linear walk becomes a problem.
- *
- * realmode_pfn_to_page functions can fail due to:
- * 1) As real sparsemem blocks do not lay in RAM continously (they
- * are in virtual address space which is not available in the real mode),
- * the requested page struct can be split between blocks so get_page/put_page
- * may fail.
- * 2) When huge pages are used, the get_page/put_page API will fail
- * in real mode as the linked addresses in the page struct are virtual
- * too.
- */
-struct page *realmode_pfn_to_page(unsigned long pfn)
-{
-	struct vmemmap_backing *vmem_back;
-	struct page *page;
-	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
-	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
-
-	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
-		if (pg_va < vmem_back->virt_addr)
-			continue;
-
-		/* After vmemmap_list entry free is possible, need check all */
-		if ((pg_va + sizeof(struct page)) <=
-				(vmem_back->virt_addr + page_size)) {
-			page = (struct page *) (vmem_back->phys + pg_va -
-				vmem_back->virt_addr);
-			return page;
-		}
-	}
-
-	/* Probably that page struct is split between real pages */
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
-
-#else
-
-struct page *realmode_pfn_to_page(unsigned long pfn)
-{
-	struct page *page = pfn_to_page(pfn);
-	return page;
-}
-EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
-
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 #ifdef CONFIG_PPC_BOOK3S_64

arch/powerpc/mm/mem.c

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

arch/powerpc/mm/mmu_context_iommu.c

@@ -18,11 +18,15 @@
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
+#include <linux/sizes.h>
 #include <asm/mmu_context.h>
 #include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
+#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY	0x1
+#define MM_IOMMU_TABLE_GROUP_PAGE_MASK	~(SZ_4K - 1)
+
 struct mm_iommu_table_group_mem_t {
 	struct list_head next;
 	struct rcu_head rcu;
@@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 		if (!page)
 			continue;
 
+		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
+			SetPageDirty(page);
+
 		put_page(page);
 		mem->hpas[i] = 0;
 	}
@@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
 
 struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
@@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (pageshift > mem->pageshift)
 		return -EFAULT;
 
-	*hpa = *va | (ua & ~PAGE_MASK);
+	*hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
 
 	return 0;
 }
@@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (!pa)
 		return -EFAULT;
 
-	*hpa = *pa | (ua & ~PAGE_MASK);
+	*hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
+extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+	long entry;
+	void *va;
+	unsigned long *pa;
+
+	mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
+	if (!mem)
+		return;
+
+	entry = (ua - mem->ua) >> PAGE_SHIFT;
+	va = &mem->hpas[entry];
+
+	pa = (void *) vmalloc_to_phys(va);
+	if (!pa)
+		return;
+
+	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
+}
 
 long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
 {

arch/powerpc/mm/numa.c

@@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu)
 	int new_nid;
 
 	/* Use associativity from first thread for all siblings */
-	vphn_get_associativity(cpu, associativity);
+	if (vphn_get_associativity(cpu, associativity))
+		return cpu_to_node(cpu);
+
 	new_nid = associativity_to_nid(associativity);
 	if (new_nid < 0 || !node_possible(new_nid))
 		new_nid = first_online_node;
@@ -1452,7 +1454,8 @@ static struct timer_list topology_timer;
 
 static void reset_topology_timer(void)
 {
-	mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
+	if (vphn_enabled)
+		mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
 }
 
 #ifdef CONFIG_SMP

arch/powerpc/mm/pkeys.c

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

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

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

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

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

arch/s390/kvm/kvm-s390.c

@@ -481,7 +481,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_S390_HPAGE_1M:
 		r = 0;
-		if (hpage)
+		if (hpage && !kvm_is_ucontrol(kvm))
 			r = 1;
 		break;
 	case KVM_CAP_S390_MEM_OP:
@@ -691,7 +691,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		mutex_lock(&kvm->lock);
 		if (kvm->created_vcpus)
 			r = -EBUSY;
-		else if (!hpage || kvm->arch.use_cmma)
+		else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm))
 			r = -EINVAL;
 		else {
 			r = 0;

arch/s390/mm/gmap.c

@@ -708,11 +708,13 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		vmaddr |= gaddr & ~PMD_MASK;
 		/* Find vma in the parent mm */
 		vma = find_vma(gmap->mm, vmaddr);
+		if (!vma)
+			continue;
 		/*
 		 * We do not discard pages that are backed by
 		 * hugetlbfs, so we don't have to refault them.
 		 */
-		if (vma && is_vm_hugetlb_page(vma))
+		if (is_vm_hugetlb_page(vma))
 			continue;
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
 		zap_page_range(vma, vmaddr, size);

arch/x86/boot/compressed/mem_encrypt.S

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

arch/x86/crypto/aegis128-aesni-glue.c

@@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
 	    !boot_cpu_has(X86_FEATURE_AES) ||
-	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 

arch/x86/crypto/aegis128l-aesni-glue.c

@@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
 	    !boot_cpu_has(X86_FEATURE_AES) ||
-	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 

arch/x86/crypto/aegis256-aesni-glue.c

@@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
 	    !boot_cpu_has(X86_FEATURE_AES) ||
-	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 

arch/x86/crypto/morus1280-sse2-glue.c

@@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
 static int __init crypto_morus1280_sse2_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
-	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 

arch/x86/crypto/morus640-sse2-glue.c

@@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
 static int __init crypto_morus640_sse2_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
-	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 

arch/x86/hyperv/hv_apic.c

@@ -95,8 +95,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val)
  */
 static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 {
-	struct ipi_arg_ex **arg;
+	struct hv_send_ipi_ex **arg;
-	struct ipi_arg_ex *ipi_arg;
+	struct hv_send_ipi_ex *ipi_arg;
 	unsigned long flags;
 	int nr_bank = 0;
 	int ret = 1;
@@ -105,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 		return false;
 
 	local_irq_save(flags);
-	arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+	arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	ipi_arg = *arg;
 	if (unlikely(!ipi_arg))
@@ -135,7 +135,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 {
 	int cur_cpu, vcpu;
-	struct ipi_arg_non_ex ipi_arg;
+	struct hv_send_ipi ipi_arg;
 	int ret = 1;
 
 	trace_hyperv_send_ipi_mask(mask, vector);

arch/x86/include/asm/fixmap.h

@@ -14,6 +14,16 @@
 #ifndef _ASM_X86_FIXMAP_H
 #define _ASM_X86_FIXMAP_H
 
+/*
+ * Exposed to assembly code for setting up initial page tables. Cannot be
+ * calculated in assembly code (fixmap entries are an enum), but is sanity
+ * checked in the actual fixmap C code to make sure that the fixmap is
+ * covered fully.
+ */
+#define FIXMAP_PMD_NUM	2
+/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
+#define FIXMAP_PMD_TOP	507
+
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
 #include <asm/acpi.h>

arch/x86/include/asm/hyperv-tlfs.h

@@ -726,19 +726,21 @@ struct hv_enlightened_vmcs {
 #define HV_STIMER_AUTOENABLE		(1ULL << 3)
 #define HV_STIMER_SINT(config)		(__u8)(((config) >> 16) & 0x0F)
 
-struct ipi_arg_non_ex {
-	u32 vector;
-	u32 reserved;
-	u64 cpu_mask;
-};
-
 struct hv_vpset {
 	u64 format;
 	u64 valid_bank_mask;
 	u64 bank_contents[];
 };
 
-struct ipi_arg_ex {
+/* HvCallSendSyntheticClusterIpi hypercall */
+struct hv_send_ipi {
+	u32 vector;
+	u32 reserved;
+	u64 cpu_mask;
+};
+
+/* HvCallSendSyntheticClusterIpiEx hypercall */
+struct hv_send_ipi_ex {
 	u32 vector;
 	u32 reserved;
 	struct hv_vpset vp_set;

arch/x86/include/asm/kvm_host.h

@@ -869,6 +869,8 @@ struct kvm_arch {
 
 	bool x2apic_format;
 	bool x2apic_broadcast_quirk_disabled;
+
+	bool guest_can_read_msr_platform_info;
 };
 
 struct kvm_vm_stat {
@@ -1022,6 +1024,7 @@ struct kvm_x86_ops {
 	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
+	bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
@@ -1055,6 +1058,7 @@ struct kvm_x86_ops {
 	bool (*umip_emulated)(void);
 
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
+	void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
 
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
 
@@ -1482,6 +1486,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 
 int kvm_is_in_guest(void);
 

arch/x86/include/asm/mem_encrypt.h

@@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
 
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_init(void);
+void __init mem_encrypt_free_decrypted_mem(void);
 
 bool sme_active(void);
 bool sev_active(void);
 
+#define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
+
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define sme_me_mask	0ULL
@@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0;
 static inline int __init
 early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
 
+#define __bss_decrypted
+
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
 /*
@@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0;
 #define __sme_pa(x)		(__pa(x) | sme_me_mask)
 #define __sme_pa_nodebug(x)	(__pa_nodebug(x) | sme_me_mask)
 
+extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __X86_MEM_ENCRYPT_H__ */

arch/x86/include/asm/pgtable_64.h

@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <linux/bitops.h>
 #include <linux/threads.h>
+#include <asm/fixmap.h>
 
 extern p4d_t level4_kernel_pgt[512];
 extern p4d_t level4_ident_pgt[512];
@@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
-extern pte_t level1_fixmap_pgt[512];
+extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
 extern pgd_t init_top_pgt[];
 
 #define swapper_pg_dir init_top_pgt

arch/x86/include/uapi/asm/kvm.h

@@ -377,6 +377,7 @@ struct kvm_sync_regs {
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002

arch/x86/kernel/cpu/intel_rdt.h

@@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e)
 		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
+struct rdt_parse_data {
+	struct rdtgroup		*rdtgrp;
+	char			*buf;
+};
+
 /**
  * struct rdt_resource - attributes of an RDT resource
  * @rid:		The index of the resource
@@ -423,16 +428,19 @@ struct rdt_resource {
 	struct rdt_cache	cache;
 	struct rdt_membw	membw;
 	const char		*format_str;
-	int (*parse_ctrlval)	(void *data, struct rdt_resource *r,
+	int (*parse_ctrlval)(struct rdt_parse_data *data,
-				 struct rdt_domain *d);
+			     struct rdt_resource *r,
+			     struct rdt_domain *d);
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
 	unsigned long		fflags;
 };
 
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
-int parse_bw(void *_buf, struct rdt_resource *r,  struct rdt_domain *d);
+	      struct rdt_domain *d);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+	     struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
 void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
+int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(void);
 void free_rmid(u32 rmid);

arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c

@@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+	     struct rdt_domain *d)
 {
-	unsigned long data;
+	unsigned long bw_val;
-	char *buf = _buf;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
-	if (!bw_validate(buf, &data, r))
+	if (!bw_validate(data->buf, &bw_val, r))
 		return -EINVAL;
-	d->new_ctrl = data;
+	d->new_ctrl = bw_val;
 	d->have_new_ctrl = true;
 
 	return 0;
@@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 	return true;
 }
 
-struct rdt_cbm_parse_data {
-	struct rdtgroup		*rdtgrp;
-	char			*buf;
-};
-
 /*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+	      struct rdt_domain *d)
 {
-	struct rdt_cbm_parse_data *data = _data;
 	struct rdtgroup *rdtgrp = data->rdtgrp;
 	u32 cbm_val;
 
@@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 static int parse_line(char *line, struct rdt_resource *r,
 		      struct rdtgroup *rdtgrp)
 {
-	struct rdt_cbm_parse_data data;
+	struct rdt_parse_data data;
 	char *dom = NULL, *id;
 	struct rdt_domain *d;
 	unsigned long dom_id;
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	    r->rid == RDT_RESOURCE_MBA) {
+		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
+		return -EINVAL;
+	}
+
 next:
 	if (!line || line[0] == '\0')
 		return 0;

arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

@@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...)
  *   limited as the number of resources grows.
  */
 static int closid_free_map;
+static int closid_free_map_len;
+
+int closids_supported(void)
+{
+	return closid_free_map_len;
+}
 
 static void closid_init(void)
 {
@@ -111,6 +117,7 @@ static void closid_init(void)
 
 	/* CLOSID 0 is always reserved for the default group */
 	closid_free_map &= ~1;
+	closid_free_map_len = rdt_min_closid;
 }
 
 static int closid_alloc(void)
@@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 		sw_shareable = 0;
 		exclusive = 0;
 		seq_printf(seq, "%d=", dom->id);
-		for (i = 0; i < r->num_closid; i++, ctrl++) {
+		for (i = 0; i < closids_supported(); i++, ctrl++) {
 			if (!closid_allocated(i))
 				continue;
 			mode = rdtgroup_mode_by_closid(i);
@@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
 
 	/* Check for overlap with other resource groups */
 	ctrl = d->ctrl_val;
-	for (i = 0; i < r->num_closid; i++, ctrl++) {
+	for (i = 0; i < closids_supported(); i++, ctrl++) {
 		ctrl_b = (unsigned long *)ctrl;
 		mode = rdtgroup_mode_by_closid(i);
 		if (closid_allocated(i) && i != closid &&
@@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 {
 	int closid = rdtgrp->closid;
 	struct rdt_resource *r;
+	bool has_cache = false;
 	struct rdt_domain *d;
 
 	for_each_alloc_enabled_rdt_resource(r) {
+		if (r->rid == RDT_RESOURCE_MBA)
+			continue;
+		has_cache = true;
 		list_for_each_entry(d, &r->domains, list) {
 			if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
-						  rdtgrp->closid, false))
+						  rdtgrp->closid, false)) {
+				rdt_last_cmd_puts("schemata overlaps\n");
 				return false;
+			}
 		}
 	}
 
+	if (!has_cache) {
+		rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n");
+		return false;
+	}
+
 	return true;
 }
 
@@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 		rdtgrp->mode = RDT_MODE_SHAREABLE;
 	} else if (!strcmp(buf, "exclusive")) {
 		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
-			rdt_last_cmd_printf("schemata overlaps\n");
 			ret = -EINVAL;
 			goto out;
 		}
@@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 	unsigned int size;
-	bool sep = false;
+	bool sep;
-	u32 cbm;
+	u32 ctrl;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
+		sep = false;
 		seq_printf(s, "%*s:", max_name_width, r->name);
 		list_for_each_entry(d, &r->domains, list) {
 			if (sep)
@@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 				size = 0;
 			} else {
-				cbm = d->ctrl_val[rdtgrp->closid];
+				ctrl = (!is_mba_sc(r) ?
-				size = rdtgroup_cbm_to_size(r, d, cbm);
+						d->ctrl_val[rdtgrp->closid] :
+						d->mbps_val[rdtgrp->closid]);
+				if (r->rid == RDT_RESOURCE_MBA)
+					size = ctrl;
+				else
+					size = rdtgroup_cbm_to_size(r, d, ctrl);
 			}
 			seq_printf(s, "%d=%u", d->id, size);
 			sep = true;
@@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 	u32 *ctrl;
 
 	for_each_alloc_enabled_rdt_resource(r) {
+		/*
+		 * Only initialize default allocations for CBM cache
+		 * resources
+		 */
+		if (r->rid == RDT_RESOURCE_MBA)
+			continue;
 		list_for_each_entry(d, &r->domains, list) {
 			d->have_new_ctrl = false;
 			d->new_ctrl = r->cache.shareable_bits;
 			used_b = r->cache.shareable_bits;
 			ctrl = d->ctrl_val;
-			for (i = 0; i < r->num_closid; i++, ctrl++) {
+			for (i = 0; i < closids_supported(); i++, ctrl++) {
 				if (closid_allocated(i) && i != closid) {
 					mode = rdtgroup_mode_by_closid(i);
 					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
@@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
+		/*
+		 * Only initialize default allocations for CBM cache
+		 * resources
+		 */
+		if (r->rid == RDT_RESOURCE_MBA)
+			continue;
 		ret = update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("failed to initialize allocations\n");

arch/x86/kernel/head64.c

@@ -35,6 +35,7 @@
 #include <asm/bootparam_utils.h>
 #include <asm/microcode.h>
 #include <asm/kasan.h>
+#include <asm/fixmap.h>
 
 /*
  * Manage page tables very early on.
@@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr)
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
+	unsigned long vaddr, vaddr_end;
 	unsigned long load_delta, *p;
 	unsigned long pgtable_flags;
 	pgdval_t *pgd;
@@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	pud[511] += load_delta;
 
 	pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
-	pmd[506] += load_delta;
+	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+		pmd[i] += load_delta;
 
 	/*
 	 * Set up the identity mapping for the switchover.  These
@@ -234,6 +237,21 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	/* Encrypt the kernel and related (if SME is active) */
 	sme_encrypt_kernel(bp);
 
+	/*
+	 * Clear the memory encryption mask from the .bss..decrypted section.
+	 * The bss section will be memset to zero later in the initialization so
+	 * there is no need to zero it after changing the memory encryption
+	 * attribute.
+	 */
+	if (mem_encrypt_active()) {
+		vaddr = (unsigned long)__start_bss_decrypted;
+		vaddr_end = (unsigned long)__end_bss_decrypted;
+		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+			i = pmd_index(vaddr);
+			pmd[i] -= sme_get_me_mask();
+		}
+	}
+
 	/*
 	 * Return the SME encryption mask (if SME is active) to be used as a
 	 * modifier for the initial pgdir entry programmed into CR3.

arch/x86/kernel/head_64.S

@@ -24,6 +24,7 @@
 #include "../entry/calling.h"
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
+#include <asm/fixmap.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt)
 		KERNEL_IMAGE_SIZE/PMD_SIZE)
 
 NEXT_PAGE(level2_fixmap_pgt)
-	.fill	506,8,0
+	.fill	(512 - 4 - FIXMAP_PMD_NUM),8,0
-	.quad	level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+	pgtno = 0
-	/* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
+	.rept (FIXMAP_PMD_NUM)
-	.fill	5,8,0
+	.quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \
+		+ _PAGE_TABLE_NOENC;
+	pgtno = pgtno + 1
+	.endr
+	/* 6 MB reserved space + a 2MB hole */
+	.fill	4,8,0
 
 NEXT_PAGE(level1_fixmap_pgt)
+	.rept (FIXMAP_PMD_NUM)
 	.fill	512,8,0
+	.endr
 
 #undef PMDS
 

arch/x86/kernel/kvmclock.c

@@ -28,6 +28,7 @@
 #include <linux/sched/clock.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/set_memory.h>
 
 #include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
@@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
 
 static struct pvclock_vsyscall_time_info
-			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
+			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
-static struct pvclock_wall_clock wall_clock;
+static struct pvclock_wall_clock wall_clock __bss_decrypted;
 static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+static struct pvclock_vsyscall_time_info *hvclock_mem;
 
 static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
 {
@@ -236,6 +238,45 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
+static void __init kvmclock_init_mem(void)
+{
+	unsigned long ncpus;
+	unsigned int order;
+	struct page *p;
+	int r;
+
+	if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus())
+		return;
+
+	ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE;
+	order = get_order(ncpus * sizeof(*hvclock_mem));
+
+	p = alloc_pages(GFP_KERNEL, order);
+	if (!p) {
+		pr_warn("%s: failed to alloc %d pages", __func__, (1U << order));
+		return;
+	}
+
+	hvclock_mem = page_address(p);
+
+	/*
+	 * hvclock is shared between the guest and the hypervisor, must
+	 * be mapped decrypted.
+	 */
+	if (sev_active()) {
+		r = set_memory_decrypted((unsigned long) hvclock_mem,
+					 1UL << order);
+		if (r) {
+			__free_pages(p, order);
+			hvclock_mem = NULL;
+			pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n");
+			return;
+		}
+	}
+
+	memset(hvclock_mem, 0, PAGE_SIZE << order);
+}
+
 static int __init kvm_setup_vsyscall_timeinfo(void)
 {
 #ifdef CONFIG_X86_64
@@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void)
 
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
 #endif
+
+	kvmclock_init_mem();
+
 	return 0;
 }
 early_initcall(kvm_setup_vsyscall_timeinfo);
@@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu)
 	/* Use the static page for the first CPUs, allocate otherwise */
 	if (cpu < HVC_BOOT_ARRAY_SIZE)
 		p = &hv_clock_boot[cpu];
+	else if (hvclock_mem)
+		p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE;
 	else
-		p = kzalloc(sizeof(*p), GFP_KERNEL);
+		return -ENOMEM;
 
 	per_cpu(hv_clock_per_cpu, cpu) = p;
 	return p ? 0 : -ENOMEM;

arch/x86/kernel/paravirt.c

@@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf,
 
 	if (len < 5) {
 #ifdef CONFIG_RETPOLINE
-		WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+		WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr);
 #endif
 		return len;	/* call too long for patch site */
 	}
@@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 
 	if (len < 5) {
 #ifdef CONFIG_RETPOLINE
-		WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+		WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
 #endif
 		return len;	/* call too long for patch site */
 	}

arch/x86/kernel/vmlinux.lds.S

@@ -65,6 +65,23 @@ jiffies_64 = jiffies;
 #define ALIGN_ENTRY_TEXT_BEGIN	. = ALIGN(PMD_SIZE);
 #define ALIGN_ENTRY_TEXT_END	. = ALIGN(PMD_SIZE);
 
+/*
+ * This section contains data which will be mapped as decrypted. Memory
+ * encryption operates on a page basis. Make this section PMD-aligned
+ * to avoid splitting the pages while mapping the section early.
+ *
+ * Note: We use a separate section so that only this section gets
+ * decrypted to avoid exposing more than we wish.
+ */
+#define BSS_DECRYPTED						\
+	. = ALIGN(PMD_SIZE);					\
+	__start_bss_decrypted = .;				\
+	*(.bss..decrypted);					\
+	. = ALIGN(PAGE_SIZE);					\
+	__start_bss_decrypted_unused = .;			\
+	. = ALIGN(PMD_SIZE);					\
+	__end_bss_decrypted = .;				\
+
 #else
 
 #define X86_ALIGN_RODATA_BEGIN
@@ -74,6 +91,7 @@ jiffies_64 = jiffies;
 
 #define ALIGN_ENTRY_TEXT_BEGIN
 #define ALIGN_ENTRY_TEXT_END
+#define BSS_DECRYPTED
 
 #endif
 
@@ -355,6 +373,7 @@ SECTIONS
 		__bss_start = .;
 		*(.bss..page_aligned)
 		*(.bss)
+		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
 		__bss_stop = .;
 	}

arch/x86/kvm/lapic.c

@@ -1344,9 +1344,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read);
 
 static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
 {
-	return kvm_apic_hw_enabled(apic) &&
+	return addr >= apic->base_address &&
-	    addr >= apic->base_address &&
+		addr < apic->base_address + LAPIC_MMIO_LENGTH;
-	    addr < apic->base_address + LAPIC_MMIO_LENGTH;
 }
 
 static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
@@ -1358,6 +1357,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!apic_mmio_in_range(apic, address))
 		return -EOPNOTSUPP;
 
+	if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) {
+		if (!kvm_check_has_quirk(vcpu->kvm,
+					 KVM_X86_QUIRK_LAPIC_MMIO_HOLE))
+			return -EOPNOTSUPP;
+
+		memset(data, 0xff, len);
+		return 0;
+	}
+
 	kvm_lapic_reg_read(apic, offset, len, data);
 
 	return 0;
@@ -1917,6 +1925,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 	if (!apic_mmio_in_range(apic, address))
 		return -EOPNOTSUPP;
 
+	if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) {
+		if (!kvm_check_has_quirk(vcpu->kvm,
+					 KVM_X86_QUIRK_LAPIC_MMIO_HOLE))
+			return -EOPNOTSUPP;
+
+		return 0;
+	}
+
 	/*
 	 * APIC register must be aligned on 128-bits boundary.
 	 * 32/64/128 bits registers must be accessed thru 32 bits.

arch/x86/kvm/mmu.c

@@ -899,7 +899,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * Make sure the write to vcpu->mode is not reordered in front of
-	 * reads to sptes.  If it does, kvm_commit_zap_page() can see us
+	 * reads to sptes.  If it does, kvm_mmu_commit_zap_page() can see us
 	 * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
 	 */
 	smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
@@ -5417,7 +5417,12 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 {
 	MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
-	kvm_init_mmu(vcpu, true);
+	/*
+	 * kvm_mmu_setup() is called only on vCPU initialization.  
+	 * Therefore, no need to reset mmu roots as they are not yet
+	 * initialized.
+	 */
+	kvm_init_mmu(vcpu, false);
 }
 
 static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,

arch/x86/kvm/svm.c

@@ -1226,8 +1226,7 @@ static __init int sev_hardware_setup(void)
 	min_sev_asid = cpuid_edx(0x8000001F);
 
 	/* Initialize SEV ASID bitmap */
-	sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid),
+	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
-				sizeof(unsigned long), GFP_KERNEL);
 	if (!sev_asid_bitmap)
 		return 1;
 
@@ -1405,7 +1404,7 @@ static __exit void svm_hardware_unsetup(void)
 	int cpu;
 
 	if (svm_sev_enabled())
-		kfree(sev_asid_bitmap);
+		bitmap_free(sev_asid_bitmap);
 
 	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
@@ -7149,6 +7148,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.check_intercept = svm_check_intercept,
 	.handle_external_intr = svm_handle_external_intr,
 
+	.request_immediate_exit = __kvm_request_immediate_exit,
+
 	.sched_in = svm_sched_in,
 
 	.pmu_ops = &amd_pmu_ops,

arch/x86/kvm/vmx.c

@@ -397,6 +397,7 @@ struct loaded_vmcs {
 	int cpu;
 	bool launched;
 	bool nmi_known_unmasked;
+	bool hv_timer_armed;
 	/* Support for vnmi-less CPUs */
 	int soft_vnmi_blocked;
 	ktime_t entry_time;
@@ -1019,6 +1020,8 @@ struct vcpu_vmx {
 	int ple_window;
 	bool ple_window_dirty;
 
+	bool req_immediate_exit;
+
 	/* Support for PML */
 #define PML_ENTITY_NUM		512
 	struct page *pml_pg;
@@ -2864,6 +2867,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	u16 fs_sel, gs_sel;
 	int i;
 
+	vmx->req_immediate_exit = false;
+
 	if (vmx->loaded_cpu_state)
 		return;
 
@@ -5393,9 +5398,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		 * To use VMXON (and later other VMX instructions), a guest
 		 * must first be able to turn on cr4.VMXE (see handle_vmon()).
 		 * So basically the check on whether to allow nested VMX
-		 * is here.
+		 * is here.  We operate under the default treatment of SMM,
+		 * so VMX cannot be enabled under SMM.
 		 */
-		if (!nested_vmx_allowed(vcpu))
+		if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
 			return 1;
 	}
 
@@ -6183,6 +6189,27 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
+static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	void *vapic_page;
+	u32 vppr;
+	int rvi;
+
+	if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
+		!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+		WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
+		return false;
+
+	rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+
+	vapic_page = kmap(vmx->nested.virtual_apic_page);
+	vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
+	kunmap(vmx->nested.virtual_apic_page);
+
+	return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
 						     bool nested)
 {
@@ -7966,6 +7993,9 @@ static __init int hardware_setup(void)
 		kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
 	}
 
+	if (!cpu_has_vmx_preemption_timer())
+		kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;
+
 	if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
 		u64 vmx_msr;
 
@@ -9208,7 +9238,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
 
 static int handle_preemption_timer(struct kvm_vcpu *vcpu)
 {
-	kvm_lapic_expired_hv_timer(vcpu);
+	if (!to_vmx(vcpu)->req_immediate_exit)
+		kvm_lapic_expired_hv_timer(vcpu);
 	return 1;
 }
 
@@ -10595,24 +10626,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
-static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
+{
+	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
+	if (!vmx->loaded_vmcs->hv_timer_armed)
+		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+			      PIN_BASED_VMX_PREEMPTION_TIMER);
+	vmx->loaded_vmcs->hv_timer_armed = true;
+}
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u64 tscl;
 	u32 delta_tsc;
 
-	if (vmx->hv_deadline_tsc == -1)
+	if (vmx->req_immediate_exit) {
+		vmx_arm_hv_timer(vmx, 0);
 		return;
+	}
 
-	tscl = rdtsc();
+	if (vmx->hv_deadline_tsc != -1) {
-	if (vmx->hv_deadline_tsc > tscl)
+		tscl = rdtsc();
-		/* sure to be 32 bit only because checked on set_hv_timer */
+		if (vmx->hv_deadline_tsc > tscl)
-		delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+			/* set_hv_timer ensures the delta fits in 32-bits */
-			cpu_preemption_timer_multi);
+			delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
-	else
+				cpu_preemption_timer_multi);
-		delta_tsc = 0;
+		else
+			delta_tsc = 0;
 
-	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+		vmx_arm_hv_timer(vmx, delta_tsc);
+		return;
+	}
+
+	if (vmx->loaded_vmcs->hv_timer_armed)
+		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+				PIN_BASED_VMX_PREEMPTION_TIMER);
+	vmx->loaded_vmcs->hv_timer_armed = false;
 }
 
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
@@ -10672,7 +10722,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	atomic_switch_perf_msrs(vmx);
 
-	vmx_arm_hv_timer(vcpu);
+	vmx_update_hv_timer(vcpu);
 
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -11427,16 +11477,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
 	u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (vcpu->arch.virtual_tsc_khz == 0)
+	/*
-		return;
+	 * A timer value of zero is architecturally guaranteed to cause
-
+	 * a VMExit prior to executing any instructions in the guest.
-	/* Make sure short timeouts reliably trigger an immediate vmexit.
+	 */
-	 * hrtimer_start does not guarantee this. */
+	if (preemption_timeout == 0) {
-	if (preemption_timeout <= 1) {
 		vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
 		return;
 	}
 
+	if (vcpu->arch.virtual_tsc_khz == 0)
+		return;
+
 	preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
 	preemption_timeout *= 1000000;
 	do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
@@ -11646,11 +11698,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 	 * bits 15:8 should be zero in posted_intr_nv,
 	 * the descriptor address has been already checked
 	 * in nested_get_vmcs12_pages.
+	 *
+	 * bits 5:0 of posted_intr_desc_addr should be zero.
 	 */
 	if (nested_cpu_has_posted_intr(vmcs12) &&
 	   (!nested_cpu_has_vid(vmcs12) ||
 	    !nested_exit_intr_ack_set(vcpu) ||
-	    vmcs12->posted_intr_nv & 0xff00))
+	    (vmcs12->posted_intr_nv & 0xff00) ||
+	    (vmcs12->posted_intr_desc_addr & 0x3f) ||
+	    (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr))))
 		return -EINVAL;
 
 	/* tpr shadow is needed by all apicv features. */
@@ -12076,11 +12132,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	exec_control = vmcs12->pin_based_vm_exec_control;
 
-	/* Preemption timer setting is only taken from vmcs01.  */
+	/* Preemption timer setting is computed directly in vmx_vcpu_run.  */
-	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
 	exec_control |= vmcs_config.pin_based_exec_ctrl;
-	if (vmx->hv_deadline_tsc == -1)
+	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-		exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	vmx->loaded_vmcs->hv_timer_armed = false;
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
 	if (nested_cpu_has_posted_intr(vmcs12)) {
@@ -12318,6 +12373,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	    vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
@@ -12863,6 +12921,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 	return 0;
 }
 
+static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+	to_vmx(vcpu)->req_immediate_exit = true;
+}
+
 static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
 {
 	ktime_t remaining =
@@ -13253,12 +13316,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
-	if (vmx->hv_deadline_tsc == -1)
+
-		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
-				PIN_BASED_VMX_PREEMPTION_TIMER);
-	else
-		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
-			      PIN_BASED_VMX_PREEMPTION_TIMER);
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -13462,18 +13520,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 		return -ERANGE;
 
 	vmx->hv_deadline_tsc = tscl + delta_tsc;
-	vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
-			PIN_BASED_VMX_PREEMPTION_TIMER);
-
 	return delta_tsc == 0;
 }
 
 static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	to_vmx(vcpu)->hv_deadline_tsc = -1;
-	vmx->hv_deadline_tsc = -1;
-	vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
-			PIN_BASED_VMX_PREEMPTION_TIMER);
 }
 #endif
 
@@ -13954,6 +14006,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	    ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
 		return -EINVAL;
 
+	/*
+	 * SMM temporarily disables VMX, so we cannot be in guest mode,
+	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
+	 * must be zero.
+	 */
+	if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags)
+		return -EINVAL;
+
 	if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
 	    !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
 		return -EINVAL;
@@ -14097,6 +14157,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.apicv_post_state_restore = vmx_apicv_post_state_restore,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
 	.hwapic_isr_update = vmx_hwapic_isr_update,
+	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
 	.sync_pir_to_irr = vmx_sync_pir_to_irr,
 	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
 
@@ -14130,6 +14191,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.umip_emulated = vmx_umip_emulated,
 
 	.check_nested_events = vmx_check_nested_events,
+	.request_immediate_exit = vmx_request_immediate_exit,
 
 	.sched_in = vmx_sched_in,
 

arch/x86/kvm/x86.c

@@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int r;
 
-	if (is_long_mode(vcpu) || !is_pae(vcpu))
+	if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
 		return false;
 
 	if (!test_bit(VCPU_EXREG_PDPTR,
@@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_PLATFORM_INFO:
 		if (!msr_info->host_initiated ||
-		    data & ~MSR_PLATFORM_INFO_CPUID_FAULT ||
 		    (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
 		     cpuid_fault_enabled(vcpu)))
 			return 1;
@@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.osvw.status;
 		break;
 	case MSR_PLATFORM_INFO:
+		if (!msr_info->host_initiated &&
+		    !vcpu->kvm->arch.guest_can_read_msr_platform_info)
+			return 1;
 		msr_info->data = vcpu->arch.msr_platform_info;
 		break;
 	case MSR_MISC_FEATURES_ENABLES:
@@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_GET_MSR_FEATURES:
+	case KVM_CAP_MSR_PLATFORM_INFO:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			break;
 
 		BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size));
+		r = -EFAULT;
 		if (get_user(user_data_size, &user_kvm_nested_state->size))
-			return -EFAULT;
+			break;
 
 		r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state,
 						  user_data_size);
 		if (r < 0)
-			return r;
+			break;
 
 		if (r > user_data_size) {
 			if (put_user(r, &user_kvm_nested_state->size))
-				return -EFAULT;
+				r = -EFAULT;
-			return -E2BIG;
+			else
+				r = -E2BIG;
+			break;
 		}
+
 		r = 0;
 		break;
 	}
@@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (!kvm_x86_ops->set_nested_state)
 			break;
 
+		r = -EFAULT;
 		if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state)))
-			return -EFAULT;
+			break;
 
+		r = -EINVAL;
 		if (kvm_state.size < sizeof(kvm_state))
-			return -EINVAL;
+			break;
 
 		if (kvm_state.flags &
 		    ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE))
-			return -EINVAL;
+			break;
 
 		/* nested_run_pending implies guest_mode.  */
 		if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING)
-			return -EINVAL;
+			break;
 
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
 		break;
@@ -4350,6 +4359,10 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			kvm->arch.pause_in_guest = true;
 		r = 0;
 		break;
+	case KVM_CAP_MSR_PLATFORM_INFO:
+		kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -7361,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+	smp_send_reschedule(vcpu->cpu);
+}
+EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit);
+
 /*
  * Returns 1 to let vcpu_run() continue the guest execution loop without
  * exiting to the userspace.  Otherwise, the value will be returned to the
@@ -7565,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	if (req_immediate_exit) {
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
-		smp_send_reschedule(vcpu->cpu);
+		kvm_x86_ops->request_immediate_exit(vcpu);
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
@@ -7829,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+/* Swap (qemu) user FPU context for the guest FPU context. */
+static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
+{
+	preempt_disable();
+	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
+	/* PKRU is separately restored in kvm_x86_ops->run.  */
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+				~XFEATURE_MASK_PKRU);
+	preempt_enable();
+	trace_kvm_fpu(1);
+}
+
+/* When vcpu_run ends, restore user space FPU context. */
+static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
+{
+	preempt_disable();
+	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+	preempt_enable();
+	++vcpu->stat.fpu_reload;
+	trace_kvm_fpu(0);
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
@@ -8177,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+	if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		mmu_reset_needed = 1;
 	}
@@ -8406,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
-/* Swap (qemu) user FPU context for the guest FPU context. */
-void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
-	/* PKRU is separately restored in kvm_x86_ops->run.  */
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
-				~XFEATURE_MASK_PKRU);
-	preempt_enable();
-	trace_kvm_fpu(1);
-}
-
-/* When vcpu_run ends, restore user space FPU context. */
-void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
-	preempt_enable();
-	++vcpu->stat.fpu_reload;
-	trace_kvm_fpu(0);
-}
-
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
@@ -8852,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
 	pvclock_update_vm_gtod_copy(kvm);
 
+	kvm->arch.guest_can_read_msr_platform_info = true;
+
 	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
 	INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
 
@@ -9200,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	kvm_page_track_flush_slot(kvm, slot);
 }
 
+static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	return (is_guest_mode(vcpu) &&
+			kvm_x86_ops->guest_apic_has_interrupt &&
+			kvm_x86_ops->guest_apic_has_interrupt(vcpu));
+}
+
 static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 {
 	if (!list_empty_careful(&vcpu->async_pf.done))
@@ -9224,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 		return true;
 
 	if (kvm_arch_interrupt_allowed(vcpu) &&
-	    kvm_cpu_has_interrupt(vcpu))
+	    (kvm_cpu_has_interrupt(vcpu) ||
+	    kvm_guest_apic_has_interrupt(vcpu)))
 		return true;
 
 	if (kvm_hv_has_stimer_pending(vcpu))

arch/x86/mm/init.c

@@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end)
 		set_memory_np_noalias(begin_ul, len_pages);
 }
 
+void __weak mem_encrypt_free_decrypted_mem(void) { }
+
 void __ref free_initmem(void)
 {
 	e820__reallocate_tables();
 
+	mem_encrypt_free_decrypted_mem();
+
 	free_kernel_image_pages(&__init_begin, &__init_end);
 }
 

arch/x86/mm/mem_encrypt.c

@@ -348,6 +348,30 @@ bool sev_active(void)
 EXPORT_SYMBOL(sev_active);
 
 /* Architecture __weak replacement functions */
+void __init mem_encrypt_free_decrypted_mem(void)
+{
+	unsigned long vaddr, vaddr_end, npages;
+	int r;
+
+	vaddr = (unsigned long)__start_bss_decrypted_unused;
+	vaddr_end = (unsigned long)__end_bss_decrypted;
+	npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
+
+	/*
+	 * The unused memory range was mapped decrypted, change the encryption
+	 * attribute from decrypted to encrypted before freeing it.
+	 */
+	if (mem_encrypt_active()) {
+		r = set_memory_encrypted(vaddr, npages);
+		if (r) {
+			pr_warn("failed to free unused decrypted pages\n");
+			return;
+		}
+	}
+
+	free_init_pages("unused decrypted", vaddr, vaddr_end);
+}
+
 void __init mem_encrypt_init(void)
 {
 	if (!sme_me_mask)

arch/x86/mm/pgtable.c

@@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
 {
 	unsigned long address = __fix_to_virt(idx);
 
+#ifdef CONFIG_X86_64
+       /*
+	* Ensure that the static initial page tables are covering the
+	* fixmap completely.
+	*/
+	BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
+		     (FIXMAP_PMD_NUM * PTRS_PER_PTE));
+#endif
+
 	if (idx >= __end_of_fixed_addresses) {
 		BUG();
 		return;

arch/x86/xen/mmu_pv.c

@@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* L3_k[511] -> level2_fixmap_pgt */
 	convert_pfn_mfn(level3_kernel_pgt);
 
-	/* L3_k[511][506] -> level1_fixmap_pgt */
+	/* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */
 	convert_pfn_mfn(level2_fixmap_pgt);
 
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
@@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
-	set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+	for (i = 0; i < FIXMAP_PMD_NUM; i++) {
+		set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE,
+			      PAGE_KERNEL_RO);
+	}
 
 	/* Pin down new L4 */
 	pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,

arch/x86/xen/pmu.c

@@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs,
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
 {
 	int err, ret = IRQ_NONE;
-	struct pt_regs regs;
+	struct pt_regs regs = {0};
 	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
 	uint8_t xenpmu_flags = get_xenpmu_flags();
 

block/bio.c

@@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op,
 	const int sgrp = op_stat_group(req_op);
 	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, ticks[sgrp], duration);
+	part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));
 	part_round_stats(q, cpu, part);
 	part_dec_in_flight(q, part, op_is_write(req_op));
 

block/blk-core.c

@@ -2733,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now)
 	 * containing request is enough.
 	 */
 	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
-		unsigned long duration;
 		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
-		duration = nsecs_to_jiffies(now - req->start_time_ns);
 		cpu = part_stat_lock();
 		part = req->part;
 
 		part_stat_inc(cpu, part, ios[sgrp]);
-		part_stat_add(cpu, part, ticks[sgrp], duration);
+		part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns);
 		part_round_stats(req->q, cpu, part);
 		part_dec_in_flight(req->q, part, rq_data_dir(req));
 

block/blk-mq-tag.c

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

block/blk-mq.c

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

block/elevator.c

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

block/genhd.c

@@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, ios[STAT_READ]),
 			   part_stat_read(hd, merges[STAT_READ]),
 			   part_stat_read(hd, sectors[STAT_READ]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),
+			   (unsigned int)part_stat_read_msecs(hd, STAT_READ),
 			   part_stat_read(hd, ios[STAT_WRITE]),
 			   part_stat_read(hd, merges[STAT_WRITE]),
 			   part_stat_read(hd, sectors[STAT_WRITE]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
+			   (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
 			   inflight[0],
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
 			   part_stat_read(hd, ios[STAT_DISCARD]),
 			   part_stat_read(hd, merges[STAT_DISCARD]),
 			   part_stat_read(hd, sectors[STAT_DISCARD]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))
+			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
 			);
 	}
 	disk_part_iter_exit(&piter);

block/partition-generic.c

@@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev,
 		part_stat_read(p, ios[STAT_READ]),
 		part_stat_read(p, merges[STAT_READ]),
 		(unsigned long long)part_stat_read(p, sectors[STAT_READ]),
-		jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),
+		(unsigned int)part_stat_read_msecs(p, STAT_READ),
 		part_stat_read(p, ios[STAT_WRITE]),
 		part_stat_read(p, merges[STAT_WRITE]),
 		(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
-		jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
+		(unsigned int)part_stat_read_msecs(p, STAT_WRITE),
 		inflight[0],
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
 		jiffies_to_msecs(part_stat_read(p, time_in_queue)),
 		part_stat_read(p, ios[STAT_DISCARD]),
 		part_stat_read(p, merges[STAT_DISCARD]),
 		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
-		jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));
+		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,

drivers/ata/libata-core.c

@@ -5359,10 +5359,20 @@ void ata_qc_complete(struct ata_queued_cmd *qc)
  */
 int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active)
 {
+	u64 done_mask, ap_qc_active = ap->qc_active;
 	int nr_done = 0;
-	u64 done_mask;
 
-	done_mask = ap->qc_active ^ qc_active;
+	/*
+	 * If the internal tag is set on ap->qc_active, then we care about
+	 * bit0 on the passed in qc_active mask. Move that bit up to match
+	 * the internal tag.
+	 */
+	if (ap_qc_active & (1ULL << ATA_TAG_INTERNAL)) {
+		qc_active |= (qc_active & 0x01) << ATA_TAG_INTERNAL;
+		qc_active ^= qc_active & 0x01;
+	}
+
+	done_mask = ap_qc_active ^ qc_active;
 
 	if (unlikely(done_mask & qc_active)) {
 		ata_port_err(ap, "illegal qc_active transition (%08llx->%08llx)\n",

drivers/block/floppy.c

@@ -3467,6 +3467,9 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 					  (struct floppy_struct **)&outparam);
 		if (ret)
 			return ret;
+		memcpy(&inparam.g, outparam,
+				offsetof(struct floppy_struct, name));
+		outparam = &inparam.g;
 		break;
 	case FDMSGON:
 		UDP->flags |= FTD_MSG;

drivers/block/xen-blkfront.c

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

drivers/bluetooth/hci_ldisc.c

@@ -543,6 +543,8 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 	}
 	clear_bit(HCI_UART_PROTO_SET, &hu->flags);
 
+	percpu_free_rwsem(&hu->proto_lock);
+
 	kfree(hu);
 }
 

drivers/clk/x86/clk-pmc-atom.c

@@ -55,6 +55,7 @@ struct clk_plt_data {
 	u8 nparents;
 	struct clk_plt *clks[PMC_CLK_NUM];
 	struct clk_lookup *mclk_lookup;
+	struct clk_lookup *ether_clk_lookup;
 };
 
 /* Return an index in parent table */
@@ -186,13 +187,6 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id,
 	pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
 	spin_lock_init(&pclk->lock);
 
-	/*
-	 * If the clock was already enabled by the firmware mark it as critical
-	 * to avoid it being gated by the clock framework if no driver owns it.
-	 */
-	if (plt_clk_is_enabled(&pclk->hw))
-		init.flags |= CLK_IS_CRITICAL;
-
 	ret = devm_clk_hw_register(&pdev->dev, &pclk->hw);
 	if (ret) {
 		pclk = ERR_PTR(ret);
@@ -351,11 +345,20 @@ static int plt_clk_probe(struct platform_device *pdev)
 		goto err_unreg_clk_plt;
 	}
 
+	data->ether_clk_lookup = clkdev_hw_create(&data->clks[4]->hw,
+						  "ether_clk", NULL);
+	if (!data->ether_clk_lookup) {
+		err = -ENOMEM;
+		goto err_drop_mclk;
+	}
+
 	plt_clk_free_parent_names_loop(parent_names, data->nparents);
 
 	platform_set_drvdata(pdev, data);
 	return 0;
 
+err_drop_mclk:
+	clkdev_drop(data->mclk_lookup);
 err_unreg_clk_plt:
 	plt_clk_unregister_loop(data, i);
 	plt_clk_unregister_parents(data);
@@ -369,6 +372,7 @@ static int plt_clk_remove(struct platform_device *pdev)
 
 	data = platform_get_drvdata(pdev);
 
+	clkdev_drop(data->ether_clk_lookup);
 	clkdev_drop(data->mclk_lookup);
 	plt_clk_unregister_loop(data, PMC_CLK_NUM);
 	plt_clk_unregister_parents(data);

drivers/clocksource/timer-atmel-pit.c

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

drivers/clocksource/timer-fttmr010.c

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

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

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

drivers/cpufreq/qcom-cpufreq-kryo.c

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

drivers/crypto/ccp/psp-dev.c

@@ -38,6 +38,17 @@ static DEFINE_MUTEX(sev_cmd_mutex);
 static struct sev_misc_dev *misc_dev;
 static struct psp_device *psp_master;
 
+static int psp_cmd_timeout = 100;
+module_param(psp_cmd_timeout, int, 0644);
+MODULE_PARM_DESC(psp_cmd_timeout, " default timeout value, in seconds, for PSP commands");
+
+static int psp_probe_timeout = 5;
+module_param(psp_probe_timeout, int, 0644);
+MODULE_PARM_DESC(psp_probe_timeout, " default timeout value, in seconds, during PSP device probe");
+
+static bool psp_dead;
+static int psp_timeout;
+
 static struct psp_device *psp_alloc_struct(struct sp_device *sp)
 {
 	struct device *dev = sp->dev;
@@ -82,10 +93,19 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg)
+static int sev_wait_cmd_ioc(struct psp_device *psp,
+			    unsigned int *reg, unsigned int timeout)
 {
-	wait_event(psp->sev_int_queue, psp->sev_int_rcvd);
+	int ret;
+
+	ret = wait_event_timeout(psp->sev_int_queue,
+			psp->sev_int_rcvd, timeout * HZ);
+	if (!ret)
+		return -ETIMEDOUT;
+
 	*reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg);
+
+	return 0;
 }
 
 static int sev_cmd_buffer_len(int cmd)
@@ -133,12 +153,15 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	if (!psp)
 		return -ENODEV;
 
+	if (psp_dead)
+		return -EBUSY;
+
 	/* Get the physical address of the command buffer */
 	phys_lsb = data ? lower_32_bits(__psp_pa(data)) : 0;
 	phys_msb = data ? upper_32_bits(__psp_pa(data)) : 0;
 
-	dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x\n",
+	dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n",
-		cmd, phys_msb, phys_lsb);
+		cmd, phys_msb, phys_lsb, psp_timeout);
 
 	print_hex_dump_debug("(in):  ", DUMP_PREFIX_OFFSET, 16, 2, data,
 			     sev_cmd_buffer_len(cmd), false);
@@ -154,7 +177,18 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	iowrite32(reg, psp->io_regs + psp->vdata->cmdresp_reg);
 
 	/* wait for command completion */
-	sev_wait_cmd_ioc(psp, &reg);
+	ret = sev_wait_cmd_ioc(psp, &reg, psp_timeout);
+	if (ret) {
+		if (psp_ret)
+			*psp_ret = 0;
+
+		dev_err(psp->dev, "sev command %#x timed out, disabling PSP \n", cmd);
+		psp_dead = true;
+
+		return ret;
+	}
+
+	psp_timeout = psp_cmd_timeout;
 
 	if (psp_ret)
 		*psp_ret = reg & PSP_CMDRESP_ERR_MASK;
@@ -888,6 +922,8 @@ void psp_pci_init(void)
 
 	psp_master = sp->psp_data;
 
+	psp_timeout = psp_probe_timeout;
+
 	if (sev_get_api_version())
 		goto err;
 

drivers/dax/device.c

@@ -535,6 +535,11 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
 }
 
+static const struct address_space_operations dev_dax_aops = {
+	.set_page_dirty		= noop_set_page_dirty,
+	.invalidatepage		= noop_invalidatepage,
+};
+
 static int dax_open(struct inode *inode, struct file *filp)
 {
 	struct dax_device *dax_dev = inode_dax(inode);
@@ -544,6 +549,7 @@ static int dax_open(struct inode *inode, struct file *filp)
 	dev_dbg(&dev_dax->dev, "trace\n");
 	inode->i_mapping = __dax_inode->i_mapping;
 	inode->i_mapping->host = __dax_inode;
+	inode->i_mapping->a_ops = &dev_dax_aops;
 	filp->f_mapping = inode->i_mapping;
 	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
 	filp->private_data = dev_dax;

drivers/firmware/efi/Kconfig

@@ -90,14 +90,17 @@ config EFI_ARMSTUB
 config EFI_ARMSTUB_DTB_LOADER
 	bool "Enable the DTB loader"
 	depends on EFI_ARMSTUB
+	default y
 	help
 	  Select this config option to add support for the dtb= command
 	  line parameter, allowing a device tree blob to be loaded into
 	  memory from the EFI System Partition by the stub.
 
-	  The device tree is typically provided by the platform or by
+	  If the device tree is provided by the platform or by
-	  the bootloader, so this option is mostly for development
+	  the bootloader this option may not be needed.
-	  purposes only.
+	  But, for various development reasons and to maintain existing
+	  functionality for bootloaders that do not have such support
+	  this option is necessary.
 
 config EFI_BOOTLOADER_CONTROL
 	tristate "EFI Bootloader Control"

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

@@ -272,7 +272,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
 
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
-			void **cpu_ptr)
+			void **cpu_ptr, bool mqd_gfx9)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 	struct amdgpu_bo *bo = NULL;
@@ -287,6 +287,10 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
 	bp.type = ttm_bo_type_kernel;
 	bp.resv = NULL;
+
+	if (mqd_gfx9)
+		bp.flags |= AMDGPU_GEM_CREATE_MQD_GFX9;
+
 	r = amdgpu_bo_create(adev, &bp, &bo);
 	if (r) {
 		dev_err(adev->dev,

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

@@ -136,7 +136,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
-			void **cpu_ptr);
+			void **cpu_ptr, bool mqd_gfx9);
 void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
 void get_local_mem_info(struct kgd_dev *kgd,
 			struct kfd_local_mem_info *mem_info);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c

@@ -685,7 +685,7 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 
 	while (true) {
 		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
-		if (temp & SDMA0_STATUS_REG__RB_CMD_IDLE__SHIFT)
+		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
 		if (time_after(jiffies, end_jiffies))
 			return -ETIME;

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

@@ -367,12 +367,14 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 				break;
 			case CHIP_POLARIS10:
 				if (type == CGS_UCODE_ID_SMU) {
-					if ((adev->pdev->device == 0x67df) &&
+					if (((adev->pdev->device == 0x67df) &&
-					    ((adev->pdev->revision == 0xe0) ||
+					     ((adev->pdev->revision == 0xe0) ||
-					     (adev->pdev->revision == 0xe3) ||
+					      (adev->pdev->revision == 0xe3) ||
-					     (adev->pdev->revision == 0xe4) ||
+					      (adev->pdev->revision == 0xe4) ||
-					     (adev->pdev->revision == 0xe5) ||
+					      (adev->pdev->revision == 0xe5) ||
-					     (adev->pdev->revision == 0xe7) ||
+					      (adev->pdev->revision == 0xe7) ||
+					      (adev->pdev->revision == 0xef))) ||
+					    ((adev->pdev->device == 0x6fdf) &&
 					     (adev->pdev->revision == 0xef))) {
 						info->is_kicker = true;
 						strcpy(fw_name, "amdgpu/polaris10_k_smc.bin");

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

@@ -740,6 +740,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x67CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
 	{0x1002, 0x67CC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
 	{0x1002, 0x67CF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
+	{0x1002, 0x6FDF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10},
 	/* Polaris12 */
 	{0x1002, 0x6980, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},
 	{0x1002, 0x6981, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12},

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

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

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

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

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

@@ -457,7 +457,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	if (kfd->kfd2kgd->init_gtt_mem_allocation(
 			kfd->kgd, size, &kfd->gtt_mem,
-			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr)){
+			&kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr,
+			false)) {
 		dev_err(kfd_device, "Could not allocate %d bytes\n", size);
 		goto out;
 	}

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

@@ -62,9 +62,20 @@ int kfd_iommu_device_init(struct kfd_dev *kfd)
 	struct amd_iommu_device_info iommu_info;
 	unsigned int pasid_limit;
 	int err;
+	struct kfd_topology_device *top_dev;
 
-	if (!kfd->device_info->needs_iommu_device)
+	top_dev = kfd_topology_device_by_id(kfd->id);
+
+	/*
+	 * Overwrite ATS capability according to needs_iommu_device to fix
+	 * potential missing corresponding bit in CRAT of BIOS.
+	 */
+	if (!kfd->device_info->needs_iommu_device) {
+		top_dev->node_props.capability &= ~HSA_CAP_ATS_PRESENT;
 		return 0;
+	}
+
+	top_dev->node_props.capability |= HSA_CAP_ATS_PRESENT;
 
 	iommu_info.flags = 0;
 	err = amd_iommu_device_info(kfd->pdev, &iommu_info);

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c

@@ -88,7 +88,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 				ALIGN(sizeof(struct v9_mqd), PAGE_SIZE),
 			&((*mqd_mem_obj)->gtt_mem),
 			&((*mqd_mem_obj)->gpu_addr),
-			(void *)&((*mqd_mem_obj)->cpu_ptr));
+			(void *)&((*mqd_mem_obj)->cpu_ptr), true);
 	} else
 		retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct v9_mqd),
 				mqd_mem_obj);

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

@@ -806,6 +806,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu);
 int kfd_topology_remove_device(struct kfd_dev *gpu);
 struct kfd_topology_device *kfd_topology_device_by_proximity_domain(
 						uint32_t proximity_domain);
+struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id);
 struct kfd_dev *kfd_device_by_id(uint32_t gpu_id);
 struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev);
 int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev);

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

@@ -63,22 +63,33 @@ struct kfd_topology_device *kfd_topology_device_by_proximity_domain(
 	return device;
 }
 
-struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
+struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id)
 {
-	struct kfd_topology_device *top_dev;
+	struct kfd_topology_device *top_dev = NULL;
-	struct kfd_dev *device = NULL;
+	struct kfd_topology_device *ret = NULL;
 
 	down_read(&topology_lock);
 
 	list_for_each_entry(top_dev, &topology_device_list, list)
 		if (top_dev->gpu_id == gpu_id) {
-			device = top_dev->gpu;
+			ret = top_dev;
 			break;
 		}
 
 	up_read(&topology_lock);
 
-	return device;
+	return ret;
+}
+
+struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
+{
+	struct kfd_topology_device *top_dev;
+
+	top_dev = kfd_topology_device_by_id(gpu_id);
+	if (!top_dev)
+		return NULL;
+
+	return top_dev->gpu;
 }
 
 struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev)

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -292,7 +292,7 @@ struct tile_config {
 struct kfd2kgd_calls {
 	int (*init_gtt_mem_allocation)(struct kgd_dev *kgd, size_t size,
 					void **mem_obj, uint64_t *gpu_addr,
-					void **cpu_ptr);
+					void **cpu_ptr, bool mqd_gfx9);
 
 	void (*free_gtt_mem)(struct kgd_dev *kgd, void *mem_obj);
 

drivers/gpu/drm/arm/malidp_drv.c

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

drivers/gpu/drm/arm/malidp_hw.c

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

drivers/gpu/drm/arm/malidp_hw.h

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

drivers/gpu/drm/arm/malidp_mw.c

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