Merge branch 'next' into for-linus

Prepare input updates for 5.3 merge window.

101 files changed, 1538 insertions, 827 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8824d01c0c35..00b7e27bc2b7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -49,7 +49,8 @@ obj-$(CONFIG_COMPAT)	+= signal_compat.o
 obj-y			+= traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o dumpstack.o nmi.o
 obj-$(CONFIG_MODIFY_LDT_SYSCALL)	+= ldt.o
-obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
+obj-y			+= setup.o x86_init.o i8259.o irqinit.o
+obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o
@@ -150,3 +151,7 @@ ifeq ($(CONFIG_X86_64),y)
 	obj-$(CONFIG_MMCONF_FAM10H)	+= mmconf-fam10h_64.o
 	obj-y				+= vsmp_64.o
 endif
+
+ifdef CONFIG_EFI
+obj-$(CONFIG_IMA)			+= ima_arch.o
+endif
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 06635fbca81c..8dcbf6890714 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -848,7 +848,7 @@ EXPORT_SYMBOL(acpi_unregister_ioapic);
 /**
  * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base
  *			    has been registered
- * @handle:	ACPI handle of the IOAPIC deivce
+ * @handle:	ACPI handle of the IOAPIC device
  * @gsi_base:	GSI base associated with the IOAPIC
  *
  * Assume caller holds some type of lock to serialize acpi_ioapic_registered()
@@ -935,6 +935,9 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
 #define HPET_RESOURCE_NAME_SIZE 9
 	hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE,
 				  SMP_CACHE_BYTES);
+	if (!hpet_res)
+		panic("%s: Failed to allocate %zu bytes\n", __func__,
+		      sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE);
 
 	hpet_res->name = (void *)&hpet_res[1];
 	hpet_res->flags = IORESOURCE_MEM;
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 0c26b1b44e51..4203d4f0c68d 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -90,7 +90,7 @@ ret_point:
 .data
 ALIGN
 ENTRY(saved_magic)	.long	0
-ENTRY(saved_eip)	.long	0
+saved_eip:		.long 0
 
 # saved registers
 saved_idt:	.long	0,0
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 50b8ed0317a3..510fa12aab73 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -125,12 +125,12 @@ ENTRY(do_suspend_lowlevel)
 ENDPROC(do_suspend_lowlevel)
 
 .data
-ENTRY(saved_rbp)	.quad	0
-ENTRY(saved_rsi)	.quad	0
-ENTRY(saved_rdi)	.quad	0
-ENTRY(saved_rbx)	.quad	0
+saved_rbp:		.quad	0
+saved_rsi:		.quad	0
+saved_rdi:		.quad	0
+saved_rbx:		.quad	0
 
-ENTRY(saved_rip)	.quad	0
-ENTRY(saved_rsp)	.quad	0
+saved_rip:		.quad	0
+saved_rsp:		.quad	0
 
 ENTRY(saved_magic)	.quad	0
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ebeac487a20c..9a79c7808f9c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,7 @@
 #include <linux/stop_machine.h>
 #include <linux/slab.h>
 #include <linux/kdebug.h>
+#include <linux/kprobes.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -393,10 +394,10 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			continue;
 		}
 
-		DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d",
+		DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
 			a->cpuid >> 5,
 			a->cpuid & 0x1f,
-			instr, a->instrlen,
+			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 
 		DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
@@ -764,8 +765,8 @@ int poke_int3_handler(struct pt_regs *regs)
 	regs->ip = (unsigned long) bp_int3_handler;
 
 	return 1;
-
 }
+NOKPROBE_SYMBOL(poke_int3_handler);
 
 /**
  * text_poke_bp() -- update instructions on live kernel on SMP
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 3f9d1b4019bb..2c0aa34af69c 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -50,8 +50,6 @@ static unsigned long iommu_pages;	/* .. and in pages */
 
 static u32 *iommu_gatt_base;		/* Remapping table */
 
-static dma_addr_t bad_dma_addr;
-
 /*
  * If this is disabled the IOMMU will use an optimized flushing strategy
  * of only flushing when an mapping is reused. With it true the GART is
@@ -74,8 +72,6 @@ static u32 gart_unmapped_entry;
 	(((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT)
 #define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28))
 
-#define EMERGENCY_PAGES 32 /* = 128KB */
-
 #ifdef CONFIG_AGP
 #define AGPEXTERN extern
 #else
@@ -155,9 +151,6 @@ static void flush_gart(void)
 
 #ifdef CONFIG_IOMMU_LEAK
 /* Debugging aid for drivers that don't free their IOMMU tables */
-static int leak_trace;
-static int iommu_leak_pages = 20;
-
 static void dump_leak(void)
 {
 	static int dump;
@@ -184,14 +177,6 @@ static void iommu_full(struct device *dev, size_t size, int dir)
 	 */
 
 	dev_err(dev, "PCI-DMA: Out of IOMMU space for %lu bytes\n", size);
-
-	if (size > PAGE_SIZE*EMERGENCY_PAGES) {
-		if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
-			panic("PCI-DMA: Memory would be corrupted\n");
-		if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
-			panic(KERN_ERR
-				"PCI-DMA: Random memory would be DMAed\n");
-	}
 #ifdef CONFIG_IOMMU_LEAK
 	dump_leak();
 #endif
@@ -220,7 +205,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 	int i;
 
 	if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
-		return bad_dma_addr;
+		return DMA_MAPPING_ERROR;
 
 	iommu_page = alloc_iommu(dev, npages, align_mask);
 	if (iommu_page == -1) {
@@ -229,7 +214,7 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 		if (panic_on_overflow)
 			panic("dma_map_area overflow %lu bytes\n", size);
 		iommu_full(dev, size, dir);
-		return bad_dma_addr;
+		return DMA_MAPPING_ERROR;
 	}
 
 	for (i = 0; i < npages; i++) {
@@ -271,7 +256,15 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	int npages;
 	int i;
 
-	if (dma_addr < iommu_bus_base + EMERGENCY_PAGES*PAGE_SIZE ||
+	if (WARN_ON_ONCE(dma_addr == DMA_MAPPING_ERROR))
+		return;
+
+	/*
+	 * This driver will not always use a GART mapping, but might have
+	 * created a direct mapping instead.  If that is the case there is
+	 * nothing to unmap here.
+	 */
+	if (dma_addr < iommu_bus_base ||
 	    dma_addr >= iommu_bus_base + iommu_size)
 		return;
 
@@ -315,7 +308,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
 
 		if (nonforced_iommu(dev, addr, s->length)) {
 			addr = dma_map_area(dev, addr, s->length, dir, 0);
-			if (addr == bad_dma_addr) {
+			if (addr == DMA_MAPPING_ERROR) {
 				if (i > 0)
 					gart_unmap_sg(dev, sg, i, dir, 0);
 				nents = 0;
@@ -471,7 +464,7 @@ error:
 
 	iommu_full(dev, pages << PAGE_SHIFT, dir);
 	for_each_sg(sg, s, nents, i)
-		s->dma_address = bad_dma_addr;
+		s->dma_address = DMA_MAPPING_ERROR;
 	return 0;
 }
 
@@ -490,7 +483,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 	*dma_addr = dma_map_area(dev, virt_to_phys(vaddr), size,
 			DMA_BIDIRECTIONAL, (1UL << get_order(size)) - 1);
 	flush_gart();
-	if (unlikely(*dma_addr == bad_dma_addr))
+	if (unlikely(*dma_addr == DMA_MAPPING_ERROR))
 		goto out_free;
 	return vaddr;
 out_free:
@@ -507,11 +500,6 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 	dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
 }
 
-static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return (dma_addr == bad_dma_addr);
-}
-
 static int no_agp;
 
 static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
@@ -695,7 +683,6 @@ static const struct dma_map_ops gart_dma_ops = {
 	.unmap_page			= gart_unmap_page,
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
-	.mapping_error			= gart_mapping_error,
 	.dma_supported			= dma_direct_supported,
 };
 
@@ -730,7 +717,6 @@ int __init gart_iommu_init(void)
 	unsigned long aper_base, aper_size;
 	unsigned long start_pfn, end_pfn;
 	unsigned long scratch;
-	long i;
 
 	if (!amd_nb_has_feature(AMD_NB_GART))
 		return 0;
@@ -774,29 +760,12 @@ int __init gart_iommu_init(void)
 	if (!iommu_gart_bitmap)
 		panic("Cannot allocate iommu bitmap\n");
 
-#ifdef CONFIG_IOMMU_LEAK
-	if (leak_trace) {
-		int ret;
-
-		ret = dma_debug_resize_entries(iommu_pages);
-		if (ret)
-			pr_debug("PCI-DMA: Cannot trace all the entries\n");
-	}
-#endif
-
-	/*
-	 * Out of IOMMU space handling.
-	 * Reserve some invalid pages at the beginning of the GART.
-	 */
-	bitmap_set(iommu_gart_bitmap, 0, EMERGENCY_PAGES);
-
 	pr_info("PCI-DMA: Reserving %luMB of IOMMU area in the AGP aperture\n",
 	       iommu_size >> 20);
 
 	agp_memory_reserved	= iommu_size;
 	iommu_start		= aper_size - iommu_size;
 	iommu_bus_base		= info.aper_base + iommu_start;
-	bad_dma_addr		= iommu_bus_base;
 	iommu_gatt_base		= agp_gatt_table + (iommu_start>>PAGE_SHIFT);
 
 	/*
@@ -838,8 +807,6 @@ int __init gart_iommu_init(void)
 	if (!scratch)
 		panic("Cannot allocate iommu scratch page");
 	gart_unmapped_entry = GPTE_ENCODE(__pa(scratch));
-	for (i = EMERGENCY_PAGES; i < iommu_pages; i++)
-		iommu_gatt_base[i] = gart_unmapped_entry;
 
 	flush_gart();
 	dma_ops = &gart_dma_ops;
@@ -853,16 +820,6 @@ void __init gart_parse_options(char *p)
 {
 	int arg;
 
-#ifdef CONFIG_IOMMU_LEAK
-	if (!strncmp(p, "leak", 4)) {
-		leak_trace = 1;
-		p += 4;
-		if (*p == '=')
-			++p;
-		if (isdigit(*p) && get_option(&p, &arg))
-			iommu_leak_pages = arg;
-	}
-#endif
 	if (isdigit(*p) && get_option(&p, &arg))
 		iommu_size = arg;
 	if (!strncmp(p, "fullflush", 9))
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index a6eca647bc76..cc51275c8759 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -11,14 +11,15 @@
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
+#include <linux/pci_ids.h>
 #include <asm/amd_nb.h>
 
 #define PCI_DEVICE_ID_AMD_17H_ROOT	0x1450
 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT	0x15d0
-#define PCI_DEVICE_ID_AMD_17H_DF_F3	0x1463
+#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT	0x1480
 #define PCI_DEVICE_ID_AMD_17H_DF_F4	0x1464
-#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
+#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
 
 /* Protect the PCI config register pairs used for SMN and DF indirect access. */
 static DEFINE_MUTEX(smn_mutex);
@@ -28,9 +29,11 @@ static u32 *flush_words;
 static const struct pci_device_id amd_root_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) },
 	{}
 };
 
+
 #define PCI_DEVICE_ID_AMD_CNB17H_F4     0x1704
 
 const struct pci_device_id amd_nb_misc_ids[] = {
@@ -44,6 +47,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{}
 };
@@ -57,6 +61,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
 	{}
 };
@@ -214,7 +219,10 @@ int amd_cache_northbridges(void)
 	const struct pci_device_id *root_ids = amd_root_ids;
 	struct pci_dev *root, *misc, *link;
 	struct amd_northbridge *nb;
-	u16 i = 0;
+	u16 roots_per_misc = 0;
+	u16 misc_count = 0;
+	u16 root_count = 0;
+	u16 i, j;
 
 	if (amd_northbridges.num)
 		return 0;
@@ -227,26 +235,55 @@ int amd_cache_northbridges(void)
 
 	misc = NULL;
 	while ((misc = next_northbridge(misc, misc_ids)) != NULL)
-		i++;
+		misc_count++;
 
-	if (!i)
+	if (!misc_count)
 		return -ENODEV;
 
-	nb = kcalloc(i, sizeof(struct amd_northbridge), GFP_KERNEL);
+	root = NULL;
+	while ((root = next_northbridge(root, root_ids)) != NULL)
+		root_count++;
+
+	if (root_count) {
+		roots_per_misc = root_count / misc_count;
+
+		/*
+		 * There should be _exactly_ N roots for each DF/SMN
+		 * interface.
+		 */
+		if (!roots_per_misc || (root_count % roots_per_misc)) {
+			pr_info("Unsupported AMD DF/PCI configuration found\n");
+			return -ENODEV;
+		}
+	}
+
+	nb = kcalloc(misc_count, sizeof(struct amd_northbridge), GFP_KERNEL);
 	if (!nb)
 		return -ENOMEM;
 
 	amd_northbridges.nb = nb;
-	amd_northbridges.num = i;
+	amd_northbridges.num = misc_count;
 
 	link = misc = root = NULL;
-	for (i = 0; i != amd_northbridges.num; i++) {
+	for (i = 0; i < amd_northbridges.num; i++) {
 		node_to_amd_nb(i)->root = root =
 			next_northbridge(root, root_ids);
 		node_to_amd_nb(i)->misc = misc =
 			next_northbridge(misc, misc_ids);
 		node_to_amd_nb(i)->link = link =
 			next_northbridge(link, link_ids);
+
+		/*
+		 * If there are more PCI root devices than data fabric/
+		 * system management network interfaces, then the (N)
+		 * PCI roots per DF/SMN interface are functionally the
+		 * same (for DF/SMN access) and N-1 are redundant.  N-1
+		 * PCI roots should be skipped per DF/SMN interface so
+		 * the following DF/SMN interfaces get mapped to
+		 * correct PCI roots.
+		 */
+		for (j = 1; j < roots_per_misc; j++)
+			root = next_northbridge(root, root_ids);
 	}
 
 	if (amd_gart_present())
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 2c4d5ece7456..294ed4392a0e 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -14,6 +14,7 @@
 #define pr_fmt(fmt) "AGP: " fmt
 
 #include <linux/kernel.h>
+#include <linux/kcore.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
@@ -57,7 +58,7 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
-#ifdef CONFIG_PROC_VMCORE
+#if defined(CONFIG_PROC_VMCORE) || defined(CONFIG_PROC_KCORE)
 /*
  * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
  * use the same range because it will remain configured in the northbridge.
@@ -66,20 +67,25 @@ int fix_aperture __initdata = 1;
  */
 static unsigned long aperture_pfn_start, aperture_page_count;
 
-static int gart_oldmem_pfn_is_ram(unsigned long pfn)
+static int gart_mem_pfn_is_ram(unsigned long pfn)
 {
 	return likely((pfn < aperture_pfn_start) ||
 		      (pfn >= aperture_pfn_start + aperture_page_count));
 }
 
-static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+static void __init exclude_from_core(u64 aper_base, u32 aper_order)
 {
 	aperture_pfn_start = aper_base >> PAGE_SHIFT;
 	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
-	WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+#ifdef CONFIG_PROC_VMCORE
+	WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram));
+#endif
+#ifdef CONFIG_PROC_KCORE
+	WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram));
+#endif
 }
 #else
-static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+static void exclude_from_core(u64 aper_base, u32 aper_order)
 {
 }
 #endif
@@ -264,18 +270,23 @@ static int __init parse_gart_mem(char *p)
 }
 early_param("gart_fix_e820", parse_gart_mem);
 
+/*
+ * With kexec/kdump, if the first kernel doesn't shut down the GART and the
+ * second kernel allocates a different GART region, there might be two
+ * overlapping GART regions present:
+ *
+ * - the first still used by the GART initialized in the first kernel.
+ * - (sub-)set of it used as normal RAM by the second kernel.
+ *
+ * which leads to memory corruptions and a kernel panic eventually.
+ *
+ * This can also happen if the BIOS has forgotten to mark the GART region
+ * as reserved.
+ *
+ * Try to update the e820 map to mark that new region as reserved.
+ */
 void __init early_gart_iommu_check(void)
 {
-	/*
-	 * in case it is enabled before, esp for kexec/kdump,
-	 * previous kernel already enable that. memset called
-	 * by allocate_aperture/__alloc_bootmem_nopanic cause restart.
-	 * or second kernel have different position for GART hole. and new
-	 * kernel could use hole as RAM that is still used by GART set by
-	 * first kernel
-	 * or BIOS forget to put that in reserved.
-	 * try to update e820 to make that region as reserved.
-	 */
 	u32 agp_aper_order = 0;
 	int i, fix, slot, valid_agp = 0;
 	u32 ctl;
@@ -469,7 +480,7 @@ out:
 			 * may have allocated the range over its e820 RAM
 			 * and fixed up the northbridge
 			 */
-			exclude_from_vmcore(last_aper_base, last_aper_order);
+			exclude_from_core(last_aper_base, last_aper_order);
 
 			return 1;
 		}
@@ -515,7 +526,7 @@ out:
 	 * overlap with the first kernel's memory. We can't access the
 	 * range through vmcore even though it should be part of the dump.
 	 */
-	exclude_from_vmcore(aper_alloc, aper_order);
+	exclude_from_core(aper_alloc, aper_order);
 
 	/* Fix up the north bridges */
 	for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 32b2b7a41ef5..b7bcdd781651 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -44,6 +44,7 @@
 #include <asm/mpspec.h>
 #include <asm/i8259.h>
 #include <asm/proto.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index e84c9eb4e5b4..0005c284a5c5 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -8,6 +8,7 @@
  * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
  * James Cleverdon.
  */
+#include <linux/acpi.h>
 #include <linux/errno.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
@@ -16,13 +17,13 @@
 #include <linux/ctype.h>
 #include <linux/hardirq.h>
 #include <linux/export.h>
+
 #include <asm/smp.h>
-#include <asm/apic.h>
 #include <asm/ipi.h>
+#include <asm/apic.h>
+#include <asm/apic_flat_64.h>
 #include <asm/jailhouse_para.h>
 
-#include <linux/acpi.h>
-
 static struct apic apic_physflat;
 static struct apic apic_flat;
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 2953bbf05c08..53aa234a6803 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -812,6 +812,7 @@ static int irq_polarity(int idx)
 		return IOAPIC_POL_HIGH;
 	case MP_IRQPOL_RESERVED:
 		pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+		/* fall through */
 	case MP_IRQPOL_ACTIVE_LOW:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_POL_LOW;
@@ -859,6 +860,7 @@ static int irq_trigger(int idx)
 		return IOAPIC_EDGE;
 	case MP_IRQTRIG_RESERVED:
 		pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+		/* fall through */
 	case MP_IRQTRIG_LEVEL:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_LEVEL;
@@ -2579,6 +2581,8 @@ static struct resource * __init ioapic_setup_resources(void)
 	n *= nr_ioapics;
 
 	mem = memblock_alloc(n, SMP_CACHE_BYTES);
+	if (!mem)
+		panic("%s: Failed to allocate %lu bytes\n", __func__, n);
 	res = (void *)mem;
 
 	mem += sizeof(struct resource) * nr_ioapics;
@@ -2623,6 +2627,9 @@ fake_ioapic_page:
 #endif
 			ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE,
 								    PAGE_SIZE);
+			if (!ioapic_phys)
+				panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+				      __func__, PAGE_SIZE, PAGE_SIZE);
 			ioapic_phys = __pa(ioapic_phys);
 		}
 		set_fixmap_nocache(idx, ioapic_phys);
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 652e7ffa9b9d..3173e07d3791 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <asm/irqdomain.h>
 #include <asm/hw_irq.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 391f358ebb4c..1e225528f0d7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -27,6 +27,7 @@
 #include <linux/crash_dump.h>
 #include <linux/reboot.h>
 #include <linux/memory.h>
+#include <linux/numa.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -1079,7 +1080,7 @@ late_initcall(uv_init_heartbeat);
 #endif /* !CONFIG_HOTPLUG_CPU */
 
 /* Direct Legacy VGA I/O traffic to designated IOH */
-int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags)
+static int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags)
 {
 	int domain, bus, rc;
 
@@ -1148,7 +1149,7 @@ static void get_mn(struct mn *mnp)
 	mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0;
 }
 
-void __init uv_init_hub_info(struct uv_hub_info_s *hi)
+static void __init uv_init_hub_info(struct uv_hub_info_s *hi)
 {
 	union uvh_node_id_u node_id;
 	struct mn mn;
@@ -1390,7 +1391,7 @@ static void __init build_socket_tables(void)
 	}
 
 	/* Set socket -> node values: */
-	lnid = -1;
+	lnid = NUMA_NO_NODE;
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
 		int apicid, sockid;
@@ -1521,7 +1522,7 @@ static void __init uv_system_init_hub(void)
 			new_hub->pnode = 0xffff;
 
 		new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
-		new_hub->memory_nid = -1;
+		new_hub->memory_nid = NUMA_NO_NODE;
 		new_hub->nr_possible_cpus = 0;
 		new_hub->nr_online_cpus = 0;
 	}
@@ -1538,7 +1539,7 @@ static void __init uv_system_init_hub(void)
 
 		uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
 		uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
-		if (uv_cpu_hub_info(cpu)->memory_nid == -1)
+		if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE)
 			uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
 
 		/* Init memoryless node: */
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 72adf6c335dc..168543d077d7 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -29,7 +29,8 @@
 # include "asm-offsets_64.c"
 #endif
 
-void common(void) {
+static void __used common(void)
+{
 	BLANK();
 	OFFSET(TASK_threadsp, task_struct, thread.sp);
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 1979a76bfadd..5136e6818da8 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -9,6 +9,7 @@
 #include <linux/memblock.h>
 
 #include <asm/proto.h>
+#include <asm/setup.h>
 
 /*
  * Some BIOSes seem to corrupt the low 64k of memory during events
@@ -136,7 +137,7 @@ void __init setup_bios_corruption_check(void)
 }
 
 
-void check_for_bios_corruption(void)
+static void check_for_bios_corruption(void)
 {
 	int i;
 	int corruption = 0;
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 1f5d2291c31e..cfd24f9f7614 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,13 +36,10 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
-CFLAGS_intel_rdt_pseudo_lock.o = -I$(src)
-
-obj-$(CONFIG_X86_MCE)			+= mcheck/
+obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= resctrl/
 
 obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index eeea634bee0a..01004bfb1a1b 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -15,6 +15,7 @@
 #include <asm/smp.h>
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
+#include <asm/debugreg.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -818,11 +819,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
-	/*
-	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
-	 * all up to and including B1.
-	 */
-	if (c->x86_model <= 1 && c->x86_stepping <= 1)
+
+	/* Fix erratum 1076: CPB feature bit not being set in CPUID. */
+	if (!cpu_has(c, X86_FEATURE_CPB))
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 7eba34df54c3..804c49493938 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -12,6 +12,7 @@
 #include <linux/ktime.h>
 #include <linux/math64.h>
 #include <linux/percpu.h>
+#include <linux/cpufreq.h>
 #include <linux/smp.h>
 
 #include "cpu.h"
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 500278f5308e..b91b3bfa5cfb 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -32,6 +32,8 @@
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
 
+#include "cpu.h"
+
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
@@ -54,7 +56,7 @@ static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
 u64 __ro_after_init x86_amd_ls_cfg_base;
 u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
 
-/* Control conditional STIPB in switch_to() */
+/* Control conditional STIBP in switch_to() */
 DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 /* Control conditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
@@ -69,7 +71,7 @@ void __init check_bugs(void)
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_check_topology_early();
+	cpu_smt_check_topology();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
@@ -213,7 +215,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
 static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init =
 	SPECTRE_V2_USER_NONE;
 
-#ifdef RETPOLINE
+#ifdef CONFIG_RETPOLINE
 static bool spectre_v2_bad_module;
 
 bool retpoline_module_ok(bool has_retpoline)
@@ -262,17 +264,18 @@ enum spectre_v2_user_cmd {
 };
 
 static const char * const spectre_v2_user_strings[] = {
-	[SPECTRE_V2_USER_NONE]		= "User space: Vulnerable",
-	[SPECTRE_V2_USER_STRICT]	= "User space: Mitigation: STIBP protection",
-	[SPECTRE_V2_USER_PRCTL]		= "User space: Mitigation: STIBP via prctl",
-	[SPECTRE_V2_USER_SECCOMP]	= "User space: Mitigation: STIBP via seccomp and prctl",
+	[SPECTRE_V2_USER_NONE]			= "User space: Vulnerable",
+	[SPECTRE_V2_USER_STRICT]		= "User space: Mitigation: STIBP protection",
+	[SPECTRE_V2_USER_STRICT_PREFERRED]	= "User space: Mitigation: STIBP always-on protection",
+	[SPECTRE_V2_USER_PRCTL]			= "User space: Mitigation: STIBP via prctl",
+	[SPECTRE_V2_USER_SECCOMP]		= "User space: Mitigation: STIBP via seccomp and prctl",
 };
 
 static const struct {
 	const char			*option;
 	enum spectre_v2_user_cmd	cmd;
 	bool				secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
 	{ "auto",		SPECTRE_V2_USER_CMD_AUTO,		false },
 	{ "off",		SPECTRE_V2_USER_CMD_NONE,		false },
 	{ "on",			SPECTRE_V2_USER_CMD_FORCE,		true  },
@@ -355,6 +358,15 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 		break;
 	}
 
+	/*
+	 * At this point, an STIBP mode other than "off" has been set.
+	 * If STIBP support is not being forced, check if STIBP always-on
+	 * is preferred.
+	 */
+	if (mode != SPECTRE_V2_USER_STRICT &&
+	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
+		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+
 	/* Initialize Indirect Branch Prediction Barrier */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
@@ -379,12 +391,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 			"always-on" : "conditional");
 	}
 
-	/* If enhanced IBRS is enabled no STIPB required */
+	/* If enhanced IBRS is enabled no STIBP required */
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
 		return;
 
 	/*
-	 * If SMT is not possible or STIBP is not available clear the STIPB
+	 * If SMT is not possible or STIBP is not available clear the STIBP
 	 * mode.
 	 */
 	if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP))
@@ -407,7 +419,7 @@ static const struct {
 	const char *option;
 	enum spectre_v2_mitigation_cmd cmd;
 	bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
 	{ "off",		SPECTRE_V2_CMD_NONE,		  false },
 	{ "on",			SPECTRE_V2_CMD_FORCE,		  true  },
 	{ "retpoline",		SPECTRE_V2_CMD_RETPOLINE,	  false },
@@ -610,6 +622,7 @@ void arch_smt_update(void)
 	case SPECTRE_V2_USER_NONE:
 		break;
 	case SPECTRE_V2_USER_STRICT:
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
 		update_stibp_strict();
 		break;
 	case SPECTRE_V2_USER_PRCTL:
@@ -645,7 +658,7 @@ static const char * const ssb_strings[] = {
 static const struct {
 	const char *option;
 	enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[]  __initdata = {
+} ssb_mitigation_options[]  __initconst = {
 	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },    /* Platform decides */
 	{ "on",		SPEC_STORE_BYPASS_CMD_ON },      /* Disable Speculative Store Bypass */
 	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },    /* Don't touch Speculative Store Bypass */
@@ -785,15 +798,25 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (task_spec_ssb_force_disable(task))
 			return -EPERM;
 		task_clear_spec_ssb_disable(task);
+		task_clear_spec_ssb_noexec(task);
 		task_update_spec_tif(task);
 		break;
 	case PR_SPEC_DISABLE:
 		task_set_spec_ssb_disable(task);
+		task_clear_spec_ssb_noexec(task);
 		task_update_spec_tif(task);
 		break;
 	case PR_SPEC_FORCE_DISABLE:
 		task_set_spec_ssb_disable(task);
 		task_set_spec_ssb_force_disable(task);
+		task_clear_spec_ssb_noexec(task);
+		task_update_spec_tif(task);
+		break;
+	case PR_SPEC_DISABLE_NOEXEC:
+		if (task_spec_ssb_force_disable(task))
+			return -EPERM;
+		task_set_spec_ssb_disable(task);
+		task_set_spec_ssb_noexec(task);
 		task_update_spec_tif(task);
 		break;
 	default:
@@ -812,7 +835,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		 * Indirect branch speculation is always disabled in strict
 		 * mode.
 		 */
-		if (spectre_v2_user == SPECTRE_V2_USER_STRICT)
+		if (spectre_v2_user == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED)
 			return -EPERM;
 		task_clear_spec_ib_disable(task);
 		task_update_spec_tif(task);
@@ -825,7 +849,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		 */
 		if (spectre_v2_user == SPECTRE_V2_USER_NONE)
 			return -EPERM;
-		if (spectre_v2_user == SPECTRE_V2_USER_STRICT)
+		if (spectre_v2_user == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED)
 			return 0;
 		task_set_spec_ib_disable(task);
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
@@ -870,6 +895,8 @@ static int ssb_prctl_get(struct task_struct *task)
 	case SPEC_STORE_BYPASS_PRCTL:
 		if (task_spec_ssb_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ssb_noexec(task))
+			return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC;
 		if (task_spec_ssb_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
@@ -896,6 +923,7 @@ static int ib_prctl_get(struct task_struct *task)
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
 	case SPECTRE_V2_USER_STRICT:
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
 		return PR_SPEC_DISABLE;
 	default:
 		return PR_SPEC_NOT_AFFECTED;
@@ -1002,7 +1030,8 @@ static void __init l1tf_select_mitigation(void)
 #endif
 
 	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
-	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
+	if (l1tf_mitigation != L1TF_MITIGATION_OFF &&
+			e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
 		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
 		pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
 				half_pa);
@@ -1088,6 +1117,8 @@ static char *stibp_state(void)
 		return ", STIBP: disabled";
 	case SPECTRE_V2_USER_STRICT:
 		return ", STIBP: forced";
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
+		return ", STIBP: always-on";
 	case SPECTRE_V2_USER_PRCTL:
 	case SPECTRE_V2_USER_SECCOMP:
 		if (static_key_enabled(&switch_to_cond_stibp))
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index dc1b9342e9c4..395d46f78582 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -17,6 +17,7 @@
 #include <linux/pci.h>
 
 #include <asm/cpufeature.h>
+#include <asm/cacheinfo.h>
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
@@ -247,6 +248,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	switch (leaf) {
 	case 1:
 		l1 = &l1i;
+		/* fall through */
 	case 0:
 		if (!l1->val)
 			return;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ffb181f959d2..cb28e98a0659 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -353,7 +353,7 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
 
 	cr4_set_bits(X86_CR4_UMIP);
 
-	pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n");
+	pr_info_once("x86/cpu: User Mode Instruction Prevention (UMIP) activated\n");
 
 	return;
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index da5446acc241..5eb946b9a9f3 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -49,9 +49,6 @@ extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern u32 get_scattered_cpuid_leaf(unsigned int level,
-				    unsigned int sub_leaf,
-				    enum cpuid_regs_idx reg);
 extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index d12226f60168..1d9b8aaea06c 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -124,7 +124,7 @@ static void set_cx86_reorder(void)
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
 
 	/* Load/Store Serialize to mem access disable (=reorder it) */
-	setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80);
+	setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80);
 	/* set load/store serialize from 1GB to 4GB */
 	ccr3 |= 0xe0;
 	setCx86(CX86_CCR3, ccr3);
@@ -135,11 +135,11 @@ static void set_cx86_memwb(void)
 	pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
 
 	/* CCR2 bit 2: unlock NW bit */
-	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04);
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04);
 	/* set 'Not Write-through' */
 	write_cr0(read_cr0() | X86_CR0_NW);
 	/* CCR2 bit 2: lock NW bit and set WT1 */
-	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14);
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14);
 }
 
 /*
@@ -153,14 +153,14 @@ static void geode_configure(void)
 	local_irq_save(flags);
 
 	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88);
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
 
 
 	/* FPU fast, DTE cache, Mem bypass */
-	setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38);
+	setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38);
 	setCx86(CX86_CCR3, ccr3);			/* disable MAPEN */
 
 	set_cx86_memwb();
@@ -296,7 +296,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 		/* GXm supports extended cpuid levels 'ala' AMD */
 		if (c->cpuid_level == 2) {
 			/* Enable cxMMX extensions (GX1 Datasheet 54) */
-			setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1);
+			setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);
 
 			/*
 			 * GXm : 0x30 ... 0x5f GXm  datasheet 51
@@ -319,7 +319,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 		if (dir1 > 7) {
 			dir0_msn++;  /* M II */
 			/* Enable MMX extensions (App note 108) */
-			setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1);
+			setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1);
 		} else {
 			/* A 6x86MX - it has the bug. */
 			set_cpu_bug(c, X86_BUG_COMA);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fc3c07fe7df5..3142fd7a9b32 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -611,8 +611,8 @@ static void init_intel_energy_perf(struct cpuinfo_x86 *c)
 	if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
 		return;
 
-	pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
-	pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
+	pr_info_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+	pr_info_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
 	epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
 	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
 }
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 3fed38812eea..6dd78d8235e4 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -48,3 +48,34 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	return NULL;
 }
 EXPORT_SYMBOL(x86_match_cpu);
+
+static const struct x86_cpu_desc *
+x86_match_cpu_with_stepping(const struct x86_cpu_desc *match)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	const struct x86_cpu_desc *m;
+
+	for (m = match; m->x86_family | m->x86_model; m++) {
+		if (c->x86_vendor != m->x86_vendor)
+			continue;
+		if (c->x86 != m->x86_family)
+			continue;
+		if (c->x86_model != m->x86_model)
+			continue;
+		if (c->x86_stepping != m->x86_stepping)
+			continue;
+		return m;
+	}
+	return NULL;
+}
+
+bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table)
+{
+	const struct x86_cpu_desc *res = x86_match_cpu_with_stepping(table);
+
+	if (!res || res->x86_microcode_rev > boot_cpu_data.microcode)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(x86_cpu_has_min_microcode_rev);
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mce/Makefile
index bcc7c54c7041..9f020c994154 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mce/Makefile
@@ -1,14 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y				=  mce.o mce-severity.o mce-genpool.o
+obj-y				=  core.o severity.o genpool.o
 
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
-obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
-obj-$(CONFIG_X86_MCE_AMD)	+= mce_amd.o
+obj-$(CONFIG_X86_MCE_INTEL)	+= intel.o
+obj-$(CONFIG_X86_MCE_AMD)	+= amd.o
 obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
+
+mce-inject-y			:= inject.o
 obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
 
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
 
-obj-$(CONFIG_ACPI_APEI)		+= mce-apei.o
+obj-$(CONFIG_ACPI_APEI)		+= apei.o
 
 obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mce/amd.c
index e12454e21b8a..e64de5149e50 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -23,12 +23,13 @@
 #include <linux/string.h>
 
 #include <asm/amd_nb.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 #define NR_BLOCKS         5
 #define THRESHOLD_MAX     0xFFF
@@ -87,11 +88,17 @@ static struct smca_bank_name smca_names[] = {
 	[SMCA_FP]	= { "floating_point",	"Floating Point Unit" },
 	[SMCA_L3_CACHE]	= { "l3_cache",		"L3 Cache" },
 	[SMCA_CS]	= { "coherent_slave",	"Coherent Slave" },
+	[SMCA_CS_V2]	= { "coherent_slave",	"Coherent Slave" },
 	[SMCA_PIE]	= { "pie",		"Power, Interrupts, etc." },
 	[SMCA_UMC]	= { "umc",		"Unified Memory Controller" },
 	[SMCA_PB]	= { "param_block",	"Parameter Block" },
 	[SMCA_PSP]	= { "psp",		"Platform Security Processor" },
+	[SMCA_PSP_V2]	= { "psp",		"Platform Security Processor" },
 	[SMCA_SMU]	= { "smu",		"System Management Unit" },
+	[SMCA_SMU_V2]	= { "smu",		"System Management Unit" },
+	[SMCA_MP5]	= { "mp5",		"Microprocessor 5 Unit" },
+	[SMCA_NBIO]	= { "nbio",		"Northbridge IO Unit" },
+	[SMCA_PCIE]	= { "pcie",		"PCI Express Unit" },
 };
 
 static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
@@ -99,7 +106,7 @@ static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
 	[0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
 };
 
-const char *smca_get_name(enum smca_bank_types t)
+static const char *smca_get_name(enum smca_bank_types t)
 {
 	if (t >= N_SMCA_BANK_TYPES)
 		return NULL;
@@ -137,30 +144,42 @@ static struct smca_hwid smca_hwid_mcatypes[] = {
 	{ SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 },
 
 	/* ZN Core (HWID=0xB0) MCA types */
-	{ SMCA_LS,	 HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF },
+	{ SMCA_LS,	 HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF },
 	{ SMCA_IF,	 HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
 	{ SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF },
 	{ SMCA_DE,	 HWID_MCATYPE(0xB0, 0x3), 0x1FF },
 	/* HWID 0xB0 MCATYPE 0x4 is Reserved */
-	{ SMCA_EX,	 HWID_MCATYPE(0xB0, 0x5), 0x7FF },
+	{ SMCA_EX,	 HWID_MCATYPE(0xB0, 0x5), 0xFFF },
 	{ SMCA_FP,	 HWID_MCATYPE(0xB0, 0x6), 0x7F },
 	{ SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7), 0xFF },
 
 	/* Data Fabric MCA types */
 	{ SMCA_CS,	 HWID_MCATYPE(0x2E, 0x0), 0x1FF },
-	{ SMCA_PIE,	 HWID_MCATYPE(0x2E, 0x1), 0xF },
+	{ SMCA_PIE,	 HWID_MCATYPE(0x2E, 0x1), 0x1F },
+	{ SMCA_CS_V2,	 HWID_MCATYPE(0x2E, 0x2), 0x3FFF },
 
 	/* Unified Memory Controller MCA type */
-	{ SMCA_UMC,	 HWID_MCATYPE(0x96, 0x0), 0x3F },
+	{ SMCA_UMC,	 HWID_MCATYPE(0x96, 0x0), 0xFF },
 
 	/* Parameter Block MCA type */
 	{ SMCA_PB,	 HWID_MCATYPE(0x05, 0x0), 0x1 },
 
 	/* Platform Security Processor MCA type */
 	{ SMCA_PSP,	 HWID_MCATYPE(0xFF, 0x0), 0x1 },
+	{ SMCA_PSP_V2,	 HWID_MCATYPE(0xFF, 0x1), 0x3FFFF },
 
 	/* System Management Unit MCA type */
 	{ SMCA_SMU,	 HWID_MCATYPE(0x01, 0x0), 0x1 },
+	{ SMCA_SMU_V2,	 HWID_MCATYPE(0x01, 0x1), 0x7FF },
+
+	/* Microprocessor 5 Unit MCA type */
+	{ SMCA_MP5,	 HWID_MCATYPE(0x01, 0x2), 0x3FF },
+
+	/* Northbridge IO Unit MCA type */
+	{ SMCA_NBIO,	 HWID_MCATYPE(0x18, 0x0), 0x1F },
+
+	/* PCI Express Unit MCA type */
+	{ SMCA_PCIE,	 HWID_MCATYPE(0x46, 0x0), 0x1F },
 };
 
 struct smca_bank smca_banks[MAX_NR_BANKS];
@@ -544,6 +563,40 @@ out:
 	return offset;
 }
 
+/*
+ * Turn off MC4_MISC thresholding banks on all family 0x15 models since
+ * they're not supported there.
+ */
+void disable_err_thresholding(struct cpuinfo_x86 *c)
+{
+	int i;
+	u64 hwcr;
+	bool need_toggle;
+	u32 msrs[] = {
+		0x00000413, /* MC4_MISC0 */
+		0xc0000408, /* MC4_MISC1 */
+	};
+
+	if (c->x86 != 0x15)
+		return;
+
+	rdmsrl(MSR_K7_HWCR, hwcr);
+
+	/* McStatusWrEn has to be set */
+	need_toggle = !(hwcr & BIT(18));
+
+	if (need_toggle)
+		wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
+
+	/* Clear CntP bit safely */
+	for (i = 0; i < ARRAY_SIZE(msrs); i++)
+		msr_clear_bit(msrs[i], 62);
+
+	/* restore old settings */
+	if (need_toggle)
+		wrmsrl(MSR_K7_HWCR, hwcr);
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
@@ -551,6 +604,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 	unsigned int bank, block, cpu = smp_processor_id();
 	int offset = -1;
 
+	disable_err_thresholding(c);
+
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (mce_flags.smca)
 			smca_configure(bank, cpu);
@@ -824,7 +879,7 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 	mce_log(&m);
 }
 
-asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(void)
+asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 2eee85379689..c038e5c00a59 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -36,7 +36,7 @@
 #include <acpi/ghes.h>
 #include <asm/mce.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
@@ -64,11 +64,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
 
 #define CPER_CREATOR_MCE						\
-	UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,	\
-		0x64, 0x90, 0xb8, 0x9d)
+	GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,	\
+		  0x64, 0x90, 0xb8, 0x9d)
 #define CPER_SECTION_TYPE_MCE						\
-	UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
-		0x04, 0x4a, 0x38, 0xfc)
+	GUID_INIT(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
+		  0x04, 0x4a, 0x38, 0xfc)
 
 /*
  * CPER specification (in UEFI specification 2.3 appendix N) requires
@@ -135,7 +135,7 @@ retry:
 		goto out;
 	/* try to skip other type records in storage */
 	else if (rc != sizeof(rcd) ||
-		 uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE))
+		 !guid_equal(&rcd.hdr.creator_id, &CPER_CREATOR_MCE))
 		goto retry;
 	memcpy(m, &rcd.mce, sizeof(*m));
 	rc = sizeof(*m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mce/core.c
index 36d2696c9563..b7fb541a4873 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -8,8 +8,6 @@
  * Author: Andi Kleen
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/thread_info.h>
 #include <linux/capability.h>
 #include <linux/miscdevice.h>
@@ -52,7 +50,7 @@
 #include <asm/msr.h>
 #include <asm/reboot.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 static DEFINE_MUTEX(mce_log_mutex);
 
@@ -686,7 +684,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
  * errors here. However this would be quite problematic --
  * we would need to reimplement the Monarch handling and
  * it would mess up the exclusion between exception handler
- * and poll hander -- * so we skip this for now.
+ * and poll handler -- * so we skip this for now.
  * These cases should not happen anyways, or only when the CPU
  * is already totally * confused. In this case it's likely it will
  * not fully execute the machine check handler either.
@@ -786,6 +784,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			quirk_no_way_out(i, m, regs);
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			m->bank = i;
 			mce_read_aux(m, i);
 			*msg = tmp;
 			return 1;
@@ -1613,36 +1612,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 0x15 && c->x86_model <= 0xf)
 			mce_flags.overflow_recov = 1;
 
-		/*
-		 * Turn off MC4_MISC thresholding banks on those models since
-		 * they're not supported there.
-		 */
-		if (c->x86 == 0x15 &&
-		    (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) {
-			int i;
-			u64 hwcr;
-			bool need_toggle;
-			u32 msrs[] = {
-				0x00000413, /* MC4_MISC0 */
-				0xc0000408, /* MC4_MISC1 */
-			};
-
-			rdmsrl(MSR_K7_HWCR, hwcr);
-
-			/* McStatusWrEn has to be set */
-			need_toggle = !(hwcr & BIT(18));
-
-			if (need_toggle)
-				wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
-
-			/* Clear CntP bit safely */
-			for (i = 0; i < ARRAY_SIZE(msrs); i++)
-				msr_clear_bit(msrs[i], 62);
-
-			/* restore old settings */
-			if (need_toggle)
-				wrmsrl(MSR_K7_HWCR, hwcr);
-		}
 	}
 
 	if (c->x86_vendor == X86_VENDOR_INTEL) {
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index 27f394ac983f..9690ec5c8051 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -8,14 +8,12 @@
  * Author: Andi Kleen
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/miscdevice.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 static BLOCKING_NOTIFIER_HEAD(mce_injector_chain);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index 217cd4449bc9..3395549c51d3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -10,7 +10,7 @@
 #include <linux/mm.h>
 #include <linux/genalloc.h>
 #include <linux/llist.h>
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * printk() is not safe in MCE context. This is a lock-less memory allocator
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 1fc424c40a31..8492ef7d9015 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -38,7 +38,7 @@
 #include <asm/nmi.h>
 #include <asm/smp.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * Collect all the MCi_XXX settings
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mce/intel.c
index d05be307d081..e43eb6732630 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -18,7 +18,7 @@
 #include <asm/msr.h>
 #include <asm/mce.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * Support for Intel Correct Machine Check Interrupts. This allows
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mce/internal.h
index ceb67cd5918f..af5eab1e65e2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -2,6 +2,9 @@
 #ifndef __X86_MCE_INTERNAL_H__
 #define __X86_MCE_INTERNAL_H__
 
+#undef pr_fmt
+#define pr_fmt(fmt) "mce: " fmt
+
 #include <linux/device.h>
 #include <asm/mce.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mce/p5.c
index 5cddf831720f..4ae6df556526 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mce/p5.c
@@ -14,6 +14,8 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
+#include "internal.h"
+
 /* By default disabled */
 int mce_p5_enabled __read_mostly;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 44396d521987..65201e180fe0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -16,7 +16,7 @@
 #include <asm/mce.h>
 #include <linux/uaccess.h>
 
-#include "mce-internal.h"
+#include "internal.h"
 
 /*
  * Grade an mce by severity. In general the most severe ones are processed
@@ -165,6 +165,11 @@ static struct severity {
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
 		KERNEL
 		),
+	MCESEV(
+		PANIC, "Instruction fetch error in kernel",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+		KERNEL
+		),
 #endif
 	MCESEV(
 		PANIC, "Action required: unknown MCACOD",
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index 2da67b70ba98..10a3b0599300 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -25,11 +25,14 @@
 #include <linux/cpu.h>
 
 #include <asm/processor.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
+#include "internal.h"
+
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL		(300 * HZ)
 
@@ -390,7 +393,7 @@ static void unexpected_thermal_interrupt(void)
 
 static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
 
-asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *r)
+asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index 2b584b319eff..28812cc15300 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -6,10 +6,13 @@
 #include <linux/kernel.h>
 
 #include <asm/irq_vectors.h>
+#include <asm/traps.h>
 #include <asm/apic.h>
 #include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 
+#include "internal.h"
+
 static void default_threshold_interrupt(void)
 {
 	pr_err("Unexpected threshold interrupt at vector %x\n",
@@ -18,7 +21,7 @@ static void default_threshold_interrupt(void)
 
 void (*mce_threshold_vector)(void) = default_threshold_interrupt;
 
-asmlinkage __visible void __irq_entry smp_threshold_interrupt(void)
+asmlinkage __visible void __irq_entry smp_threshold_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c
index 3b45b270a865..a30ea13cccc2 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mce/winchip.c
@@ -13,6 +13,8 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
+#include "internal.h"
+
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 07b5fc00b188..e1f3ba19ba54 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -5,7 +5,7 @@
  *  CPUs and later.
  *
  *  Copyright (C) 2008-2011 Advanced Micro Devices Inc.
- *	          2013-2016 Borislav Petkov <bp@alien8.de>
+ *	          2013-2018 Borislav Petkov <bp@alien8.de>
  *
  *  Author: Peter Oruba <peter.oruba@amd.com>
  *
@@ -38,7 +38,10 @@
 #include <asm/cpu.h>
 #include <asm/msr.h>
 
-static struct equiv_cpu_entry *equiv_cpu_table;
+static struct equiv_cpu_table {
+	unsigned int num_entries;
+	struct equiv_cpu_entry *entry;
+} equiv_table;
 
 /*
  * This points to the current valid container of microcode patches which we will
@@ -63,13 +66,225 @@ static u8 amd_ucode_patch[PATCH_MAX_SIZE];
 static const char
 ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
 
-static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig)
+static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig)
 {
-	for (; equiv_table && equiv_table->installed_cpu; equiv_table++) {
-		if (sig == equiv_table->installed_cpu)
-			return equiv_table->equiv_cpu;
+	unsigned int i;
+
+	if (!et || !et->num_entries)
+		return 0;
+
+	for (i = 0; i < et->num_entries; i++) {
+		struct equiv_cpu_entry *e = &et->entry[i];
+
+		if (sig == e->installed_cpu)
+			return e->equiv_cpu;
+
+		e++;
+	}
+	return 0;
+}
+
+/*
+ * Check whether there is a valid microcode container file at the beginning
+ * of @buf of size @buf_size. Set @early to use this function in the early path.
+ */
+static bool verify_container(const u8 *buf, size_t buf_size, bool early)
+{
+	u32 cont_magic;
+
+	if (buf_size <= CONTAINER_HDR_SZ) {
+		if (!early)
+			pr_debug("Truncated microcode container header.\n");
+
+		return false;
+	}
+
+	cont_magic = *(const u32 *)buf;
+	if (cont_magic != UCODE_MAGIC) {
+		if (!early)
+			pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
+
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Check whether there is a valid, non-truncated CPU equivalence table at the
+ * beginning of @buf of size @buf_size. Set @early to use this function in the
+ * early path.
+ */
+static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
+{
+	const u32 *hdr = (const u32 *)buf;
+	u32 cont_type, equiv_tbl_len;
+
+	if (!verify_container(buf, buf_size, early))
+		return false;
+
+	cont_type = hdr[1];
+	if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) {
+		if (!early)
+			pr_debug("Wrong microcode container equivalence table type: %u.\n",
+			       cont_type);
+
+		return false;
+	}
+
+	buf_size -= CONTAINER_HDR_SZ;
+
+	equiv_tbl_len = hdr[2];
+	if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) ||
+	    buf_size < equiv_tbl_len) {
+		if (!early)
+			pr_debug("Truncated equivalence table.\n");
+
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Check whether there is a valid, non-truncated microcode patch section at the
+ * beginning of @buf of size @buf_size. Set @early to use this function in the
+ * early path.
+ *
+ * On success, @sh_psize returns the patch size according to the section header,
+ * to the caller.
+ */
+static bool
+__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early)
+{
+	u32 p_type, p_size;
+	const u32 *hdr;
+
+	if (buf_size < SECTION_HDR_SIZE) {
+		if (!early)
+			pr_debug("Truncated patch section.\n");
+
+		return false;
+	}
+
+	hdr = (const u32 *)buf;
+	p_type = hdr[0];
+	p_size = hdr[1];
+
+	if (p_type != UCODE_UCODE_TYPE) {
+		if (!early)
+			pr_debug("Invalid type field (0x%x) in container file section header.\n",
+				p_type);
+
+		return false;
+	}
+
+	if (p_size < sizeof(struct microcode_header_amd)) {
+		if (!early)
+			pr_debug("Patch of size %u too short.\n", p_size);
+
+		return false;
+	}
+
+	*sh_psize = p_size;
+
+	return true;
+}
+
+/*
+ * Check whether the passed remaining file @buf_size is large enough to contain
+ * a patch of the indicated @sh_psize (and also whether this size does not
+ * exceed the per-family maximum). @sh_psize is the size read from the section
+ * header.
+ */
+static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size)
+{
+	u32 max_size;
+
+	if (family >= 0x15)
+		return min_t(u32, sh_psize, buf_size);
+
+#define F1XH_MPB_MAX_SIZE 2048
+#define F14H_MPB_MAX_SIZE 1824
+
+	switch (family) {
+	case 0x10 ... 0x12:
+		max_size = F1XH_MPB_MAX_SIZE;
+		break;
+	case 0x14:
+		max_size = F14H_MPB_MAX_SIZE;
+		break;
+	default:
+		WARN(1, "%s: WTF family: 0x%x\n", __func__, family);
+		return 0;
+		break;
+	}
+
+	if (sh_psize > min_t(u32, buf_size, max_size))
+		return 0;
+
+	return sh_psize;
+}
+
+/*
+ * Verify the patch in @buf.
+ *
+ * Returns:
+ * negative: on error
+ * positive: patch is not for this family, skip it
+ * 0: success
+ */
+static int
+verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early)
+{
+	struct microcode_header_amd *mc_hdr;
+	unsigned int ret;
+	u32 sh_psize;
+	u16 proc_id;
+	u8 patch_fam;
+
+	if (!__verify_patch_section(buf, buf_size, &sh_psize, early))
+		return -1;
+
+	/*
+	 * The section header length is not included in this indicated size
+	 * but is present in the leftover file length so we need to subtract
+	 * it before passing this value to the function below.
+	 */
+	buf_size -= SECTION_HDR_SIZE;
+
+	/*
+	 * Check if the remaining buffer is big enough to contain a patch of
+	 * size sh_psize, as the section claims.
+	 */
+	if (buf_size < sh_psize) {
+		if (!early)
+			pr_debug("Patch of size %u truncated.\n", sh_psize);
+
+		return -1;
+	}
+
+	ret = __verify_patch_size(family, sh_psize, buf_size);
+	if (!ret) {
+		if (!early)
+			pr_debug("Per-family patch size mismatch.\n");
+		return -1;
+	}
+
+	*patch_size = sh_psize;
+
+	mc_hdr	= (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE);
+	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+		if (!early)
+			pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
+		return -1;
 	}
 
+	proc_id	= mc_hdr->processor_rev_id;
+	patch_fam = 0xf + (proc_id >> 12);
+	if (patch_fam != family)
+		return 1;
+
 	return 0;
 }
 
@@ -80,26 +295,28 @@ static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig)
  * Returns the amount of bytes consumed while scanning. @desc contains all the
  * data we're going to use in later stages of the application.
  */
-static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
+static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
 {
-	struct equiv_cpu_entry *eq;
-	ssize_t orig_size = size;
+	struct equiv_cpu_table table;
+	size_t orig_size = size;
 	u32 *hdr = (u32 *)ucode;
 	u16 eq_id;
 	u8 *buf;
 
-	/* Am I looking at an equivalence table header? */
-	if (hdr[0] != UCODE_MAGIC ||
-	    hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE ||
-	    hdr[2] == 0)
-		return CONTAINER_HDR_SZ;
+	if (!verify_equivalence_table(ucode, size, true))
+		return 0;
 
 	buf = ucode;
 
-	eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ);
+	table.entry = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ);
+	table.num_entries = hdr[2] / sizeof(struct equiv_cpu_entry);
 
-	/* Find the equivalence ID of our CPU in this table: */
-	eq_id = find_equiv_id(eq, desc->cpuid_1_eax);
+	/*
+	 * Find the equivalence ID of our CPU in this table. Even if this table
+	 * doesn't contain a patch for the CPU, scan through the whole container
+	 * so that it can be skipped in case there are other containers appended.
+	 */
+	eq_id = find_equiv_id(&table, desc->cpuid_1_eax);
 
 	buf  += hdr[2] + CONTAINER_HDR_SZ;
 	size -= hdr[2] + CONTAINER_HDR_SZ;
@@ -111,29 +328,29 @@ static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
 	while (size > 0) {
 		struct microcode_amd *mc;
 		u32 patch_size;
+		int ret;
+
+		ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true);
+		if (ret < 0) {
+			/*
+			 * Patch verification failed, skip to the next
+			 * container, if there's one:
+			 */
+			goto out;
+		} else if (ret > 0) {
+			goto skip;
+		}
 
-		hdr = (u32 *)buf;
-
-		if (hdr[0] != UCODE_UCODE_TYPE)
-			break;
-
-		/* Sanity-check patch size. */
-		patch_size = hdr[1];
-		if (patch_size > PATCH_MAX_SIZE)
-			break;
-
-		/* Skip patch section header: */
-		buf  += SECTION_HDR_SIZE;
-		size -= SECTION_HDR_SIZE;
-
-		mc = (struct microcode_amd *)buf;
+		mc = (struct microcode_amd *)(buf + SECTION_HDR_SIZE);
 		if (eq_id == mc->hdr.processor_rev_id) {
 			desc->psize = patch_size;
 			desc->mc = mc;
 		}
 
-		buf  += patch_size;
-		size -= patch_size;
+skip:
+		/* Skip patch section header too: */
+		buf  += patch_size + SECTION_HDR_SIZE;
+		size -= patch_size + SECTION_HDR_SIZE;
 	}
 
 	/*
@@ -150,6 +367,7 @@ static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
 		return 0;
 	}
 
+out:
 	return orig_size - size;
 }
 
@@ -159,15 +377,18 @@ static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
  */
 static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
 {
-	ssize_t rem = size;
-
-	while (rem >= 0) {
-		ssize_t s = parse_container(ucode, rem, desc);
+	while (size) {
+		size_t s = parse_container(ucode, size, desc);
 		if (!s)
 			return;
 
-		ucode += s;
-		rem   -= s;
+		/* catch wraparound */
+		if (size >= s) {
+			ucode += s;
+			size  -= s;
+		} else {
+			return;
+		}
 	}
 }
 
@@ -364,21 +585,7 @@ void reload_ucode_amd(void)
 static u16 __find_equiv_id(unsigned int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	return find_equiv_id(equiv_cpu_table, uci->cpu_sig.sig);
-}
-
-static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu)
-{
-	int i = 0;
-
-	BUG_ON(!equiv_cpu_table);
-
-	while (equiv_cpu_table[i].equiv_cpu != 0) {
-		if (equiv_cpu == equiv_cpu_table[i].equiv_cpu)
-			return equiv_cpu_table[i].installed_cpu;
-		i++;
-	}
-	return 0;
+	return find_equiv_id(&equiv_table, uci->cpu_sig.sig);
 }
 
 /*
@@ -461,43 +668,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 	return 0;
 }
 
-static unsigned int verify_patch_size(u8 family, u32 patch_size,
-				      unsigned int size)
-{
-	u32 max_size;
-
-#define F1XH_MPB_MAX_SIZE 2048
-#define F14H_MPB_MAX_SIZE 1824
-#define F15H_MPB_MAX_SIZE 4096
-#define F16H_MPB_MAX_SIZE 3458
-#define F17H_MPB_MAX_SIZE 3200
-
-	switch (family) {
-	case 0x14:
-		max_size = F14H_MPB_MAX_SIZE;
-		break;
-	case 0x15:
-		max_size = F15H_MPB_MAX_SIZE;
-		break;
-	case 0x16:
-		max_size = F16H_MPB_MAX_SIZE;
-		break;
-	case 0x17:
-		max_size = F17H_MPB_MAX_SIZE;
-		break;
-	default:
-		max_size = F1XH_MPB_MAX_SIZE;
-		break;
-	}
-
-	if (patch_size > min_t(u32, size, max_size)) {
-		pr_err("patch size mismatch\n");
-		return 0;
-	}
-
-	return patch_size;
-}
-
 static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -548,34 +718,34 @@ out:
 	return ret;
 }
 
-static int install_equiv_cpu_table(const u8 *buf)
+static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size)
 {
-	unsigned int *ibuf = (unsigned int *)buf;
-	unsigned int type = ibuf[1];
-	unsigned int size = ibuf[2];
+	u32 equiv_tbl_len;
+	const u32 *hdr;
 
-	if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-		pr_err("empty section/"
-		       "invalid type field in container file section header\n");
-		return -EINVAL;
-	}
+	if (!verify_equivalence_table(buf, buf_size, false))
+		return 0;
+
+	hdr = (const u32 *)buf;
+	equiv_tbl_len = hdr[2];
 
-	equiv_cpu_table = vmalloc(size);
-	if (!equiv_cpu_table) {
+	equiv_table.entry = vmalloc(equiv_tbl_len);
+	if (!equiv_table.entry) {
 		pr_err("failed to allocate equivalent CPU table\n");
-		return -ENOMEM;
+		return 0;
 	}
 
-	memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
+	memcpy(equiv_table.entry, buf + CONTAINER_HDR_SZ, equiv_tbl_len);
+	equiv_table.num_entries = equiv_tbl_len / sizeof(struct equiv_cpu_entry);
 
 	/* add header length */
-	return size + CONTAINER_HDR_SZ;
+	return equiv_tbl_len + CONTAINER_HDR_SZ;
 }
 
 static void free_equiv_cpu_table(void)
 {
-	vfree(equiv_cpu_table);
-	equiv_cpu_table = NULL;
+	vfree(equiv_table.entry);
+	memset(&equiv_table, 0, sizeof(equiv_table));
 }
 
 static void cleanup(void)
@@ -585,47 +755,23 @@ static void cleanup(void)
 }
 
 /*
- * We return the current size even if some of the checks failed so that
+ * Return a non-negative value even if some of the checks failed so that
  * we can skip over the next patch. If we return a negative value, we
  * signal a grave error like a memory allocation has failed and the
  * driver cannot continue functioning normally. In such cases, we tear
  * down everything we've used up so far and exit.
  */
-static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
+static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
+				unsigned int *patch_size)
 {
 	struct microcode_header_amd *mc_hdr;
 	struct ucode_patch *patch;
-	unsigned int patch_size, crnt_size, ret;
-	u32 proc_fam;
 	u16 proc_id;
+	int ret;
 
-	patch_size  = *(u32 *)(fw + 4);
-	crnt_size   = patch_size + SECTION_HDR_SIZE;
-	mc_hdr	    = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
-	proc_id	    = mc_hdr->processor_rev_id;
-
-	proc_fam = find_cpu_family_by_equiv_cpu(proc_id);
-	if (!proc_fam) {
-		pr_err("No patch family for equiv ID: 0x%04x\n", proc_id);
-		return crnt_size;
-	}
-
-	/* check if patch is for the current family */
-	proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
-	if (proc_fam != family)
-		return crnt_size;
-
-	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
-		pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n",
-			mc_hdr->patch_id);
-		return crnt_size;
-	}
-
-	ret = verify_patch_size(family, patch_size, leftover);
-	if (!ret) {
-		pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
-		return crnt_size;
-	}
+	ret = verify_patch(family, fw, leftover, patch_size, false);
+	if (ret)
+		return ret;
 
 	patch = kzalloc(sizeof(*patch), GFP_KERNEL);
 	if (!patch) {
@@ -633,13 +779,16 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 		return -EINVAL;
 	}
 
-	patch->data = kmemdup(fw + SECTION_HDR_SIZE, patch_size, GFP_KERNEL);
+	patch->data = kmemdup(fw + SECTION_HDR_SIZE, *patch_size, GFP_KERNEL);
 	if (!patch->data) {
 		pr_err("Patch data allocation failure.\n");
 		kfree(patch);
 		return -EINVAL;
 	}
 
+	mc_hdr      = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
+	proc_id     = mc_hdr->processor_rev_id;
+
 	INIT_LIST_HEAD(&patch->plist);
 	patch->patch_id  = mc_hdr->patch_id;
 	patch->equiv_cpu = proc_id;
@@ -650,39 +799,38 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 	/* ... and add to cache. */
 	update_cache(patch);
 
-	return crnt_size;
+	return 0;
 }
 
 static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 					     size_t size)
 {
-	enum ucode_state ret = UCODE_ERROR;
-	unsigned int leftover;
 	u8 *fw = (u8 *)data;
-	int crnt_size = 0;
-	int offset;
+	size_t offset;
 
-	offset = install_equiv_cpu_table(data);
-	if (offset < 0) {
-		pr_err("failed to create equivalent cpu table\n");
-		return ret;
-	}
-	fw += offset;
-	leftover = size - offset;
+	offset = install_equiv_cpu_table(data, size);
+	if (!offset)
+		return UCODE_ERROR;
+
+	fw   += offset;
+	size -= offset;
 
 	if (*(u32 *)fw != UCODE_UCODE_TYPE) {
 		pr_err("invalid type field in container file section header\n");
 		free_equiv_cpu_table();
-		return ret;
+		return UCODE_ERROR;
 	}
 
-	while (leftover) {
-		crnt_size = verify_and_add_patch(family, fw, leftover);
-		if (crnt_size < 0)
-			return ret;
+	while (size > 0) {
+		unsigned int crnt_size = 0;
+		int ret;
 
-		fw	 += crnt_size;
-		leftover -= crnt_size;
+		ret = verify_and_add_patch(family, fw, size, &crnt_size);
+		if (ret < 0)
+			return UCODE_ERROR;
+
+		fw   +=  crnt_size + SECTION_HDR_SIZE;
+		size -= (crnt_size + SECTION_HDR_SIZE);
 	}
 
 	return UCODE_OK;
@@ -707,7 +855,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 	if (!p) {
 		return ret;
 	} else {
-		if (boot_cpu_data.microcode == p->patch_id)
+		if (boot_cpu_data.microcode >= p->patch_id)
 			return ret;
 
 		ret = UCODE_NEW;
@@ -761,10 +909,8 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 	}
 
 	ret = UCODE_ERROR;
-	if (*(u32 *)fw->data != UCODE_MAGIC) {
-		pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
+	if (!verify_container(fw->data, fw->size, false))
 		goto fw_release;
-	}
 
 	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 2637ff09d6a0..5260185cbf7b 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -434,9 +434,10 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 			       size_t len, loff_t *ppos)
 {
 	ssize_t ret = -EINVAL;
+	unsigned long nr_pages = totalram_pages();
 
-	if ((len >> PAGE_SHIFT) > totalram_pages) {
-		pr_err("too much data (max %ld pages)\n", totalram_pages);
+	if ((len >> PAGE_SHIFT) > nr_pages) {
+		pr_err("too much data (max %ld pages)\n", nr_pages);
 		return ret;
 	}
 
@@ -607,6 +608,8 @@ static int microcode_reload_late(void)
 	if (ret > 0)
 		microcode_check();
 
+	pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
+
 	return ret;
 }
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e81a2db42df7..3fa238a137d2 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -328,6 +328,18 @@ static void __init ms_hyperv_init_platform(void)
 # ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
 # endif
+
+	/*
+	 * Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic,
+	 * set x2apic destination mode to physcial mode when x2apic is available
+	 * and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs
+	 * have 8-bit APIC id.
+	 */
+# ifdef CONFIG_X86_X2APIC
+	if (x2apic_supported())
+		x2apic_phys = 1;
+# endif
+
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 3668c5df90c6..5bd011737272 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -296,7 +296,7 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
 			unsigned long sizek)
 {
 	unsigned long hole_basek, hole_sizek;
-	unsigned long second_basek, second_sizek;
+	unsigned long second_sizek;
 	unsigned long range0_basek, range0_sizek;
 	unsigned long range_basek, range_sizek;
 	unsigned long chunk_sizek;
@@ -304,7 +304,6 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
 
 	hole_basek = 0;
 	hole_sizek = 0;
-	second_basek = 0;
 	second_sizek = 0;
 	chunk_sizek = state->chunk_sizek;
 	gran_sizek = state->gran_sizek;
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
new file mode 100644
index 000000000000..4a06c37b9cf1
--- /dev/null
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_X86_CPU_RESCTRL)	+= core.o rdtgroup.o monitor.o
+obj-$(CONFIG_X86_CPU_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+CFLAGS_pseudo_lock.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/resctrl/core.c
index 44272b7107ad..c3a9dc63edf2 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
  * Software Developer Manual June 2016, volume 3, section 17.17.
  */
 
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+#define pr_fmt(fmt)	"resctrl: " fmt
 
 #include <linux/slab.h>
 #include <linux/err.h>
@@ -30,22 +30,19 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/intel-family.h>
-#include <asm/intel_rdt_sched.h>
-#include "intel_rdt.h"
-
-#define MBA_IS_LINEAR	0x4
-#define MBA_MAX_MBPS	U32_MAX
+#include <asm/resctrl_sched.h>
+#include "internal.h"
 
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
 /*
- * The cached intel_pqr_state is strictly per CPU and can never be
+ * The cached resctrl_pqr_state is strictly per CPU and can never be
  * updated from a remote CPU. Functions which modify the state
  * are called with interrupts disabled and no preemption, which
  * is sufficient for the protection.
  */
-DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 /*
  * Used to store the max resource name width and max resource data width
@@ -60,9 +57,13 @@ int max_name_width, max_data_width;
 bool rdt_alloc_capable;
 
 static void
-mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
+		struct rdt_resource *r);
 static void
 cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+static void
+mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
+	      struct rdt_resource *r);
 
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
@@ -72,7 +73,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L3,
 		.name			= "L3",
 		.domains		= domain_init(RDT_RESOURCE_L3),
-		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 3,
 		.cache = {
@@ -89,7 +90,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L3DATA,
 		.name			= "L3DATA",
 		.domains		= domain_init(RDT_RESOURCE_L3DATA),
-		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 3,
 		.cache = {
@@ -106,7 +107,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L3CODE,
 		.name			= "L3CODE",
 		.domains		= domain_init(RDT_RESOURCE_L3CODE),
-		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 3,
 		.cache = {
@@ -123,7 +124,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L2,
 		.name			= "L2",
 		.domains		= domain_init(RDT_RESOURCE_L2),
-		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 2,
 		.cache = {
@@ -140,7 +141,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L2DATA,
 		.name			= "L2DATA",
 		.domains		= domain_init(RDT_RESOURCE_L2DATA),
-		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 2,
 		.cache = {
@@ -157,7 +158,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_L2CODE,
 		.name			= "L2CODE",
 		.domains		= domain_init(RDT_RESOURCE_L2CODE),
-		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
 		.cache_level		= 2,
 		.cache = {
@@ -174,10 +175,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.rid			= RDT_RESOURCE_MBA,
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
-		.msr_base		= IA32_MBA_THRTL_BASE,
-		.msr_update		= mba_wrmsr,
 		.cache_level		= 3,
-		.parse_ctrlval		= parse_bw,
 		.format_str		= "%d=%*u",
 		.fflags			= RFTYPE_RES_MB,
 	},
@@ -211,9 +209,10 @@ static inline void cache_alloc_hsw_probe(void)
 	struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
 	u32 l, h, max_cbm = BIT_MASK(20) - 1;
 
-	if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
+	if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0))
 		return;
-	rdmsr(IA32_L3_CBM_BASE, l, h);
+
+	rdmsr(MSR_IA32_L3_CBM_BASE, l, h);
 
 	/* If all the bits were set in MSR, return success */
 	if (l != max_cbm)
@@ -259,7 +258,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
 	return false;
 }
 
-static bool rdt_get_mem_config(struct rdt_resource *r)
+static bool __get_mem_config_intel(struct rdt_resource *r)
 {
 	union cpuid_0x10_3_eax eax;
 	union cpuid_0x10_x_edx edx;
@@ -285,6 +284,30 @@ static bool rdt_get_mem_config(struct rdt_resource *r)
 	return true;
 }
 
+static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
+{
+	union cpuid_0x10_3_eax eax;
+	union cpuid_0x10_x_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->default_ctrl = MAX_MBA_BW_AMD;
+
+	/* AMD does not use delay */
+	r->membw.delay_linear = false;
+
+	r->membw.min_bw = 0;
+	r->membw.bw_gran = 1;
+	/* Max value is 2048, Data width should be 4 in decimal */
+	r->data_width = 4;
+
+	r->alloc_capable = true;
+	r->alloc_enabled = true;
+
+	return true;
+}
+
 static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 {
 	union cpuid_0x10_1_eax eax;
@@ -344,6 +367,15 @@ static int get_cache_id(int cpu, int level)
 	return -1;
 }
 
+static void
+mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + i, d->ctrl_val[i]);
+}
+
 /*
  * Map the memory b/w percentage value to delay values
  * that can be written to QOS_MSRs.
@@ -359,7 +391,8 @@ u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 }
 
 static void
-mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
+		struct rdt_resource *r)
 {
 	unsigned int i;
 
@@ -421,7 +454,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	struct list_head *l;
 
 	if (id < 0)
-		return ERR_PTR(id);
+		return ERR_PTR(-ENODEV);
 
 	list_for_each(l, &r->domains) {
 		d = list_entry(l, struct rdt_domain, list);
@@ -639,7 +672,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 static void clear_closid_rmid(int cpu)
 {
-	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
 
 	state->default_closid = 0;
 	state->default_rmid = 0;
@@ -648,7 +681,7 @@ static void clear_closid_rmid(int cpu)
 	wrmsr(IA32_PQR_ASSOC, 0, 0);
 }
 
-static int intel_rdt_online_cpu(unsigned int cpu)
+static int resctrl_online_cpu(unsigned int cpu)
 {
 	struct rdt_resource *r;
 
@@ -674,7 +707,7 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
 	}
 }
 
-static int intel_rdt_offline_cpu(unsigned int cpu)
+static int resctrl_offline_cpu(unsigned int cpu)
 {
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
@@ -794,6 +827,19 @@ static bool __init rdt_cpu_has(int flag)
 	return ret;
 }
 
+static __init bool get_mem_config(void)
+{
+	if (!rdt_cpu_has(X86_FEATURE_MBA))
+		return false;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]);
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]);
+
+	return false;
+}
+
 static __init bool get_rdt_alloc_resources(void)
 {
 	bool ret = false;
@@ -818,10 +864,9 @@ static __init bool get_rdt_alloc_resources(void)
 		ret = true;
 	}
 
-	if (rdt_cpu_has(X86_FEATURE_MBA)) {
-		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
-			ret = true;
-	}
+	if (get_mem_config())
+		ret = true;
+
 	return ret;
 }
 
@@ -840,7 +885,7 @@ static __init bool get_rdt_mon_resources(void)
 	return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]);
 }
 
-static __init void rdt_quirks(void)
+static __init void __check_quirks_intel(void)
 {
 	switch (boot_cpu_data.x86_model) {
 	case INTEL_FAM6_HASWELL_X:
@@ -855,30 +900,91 @@ static __init void rdt_quirks(void)
 	}
 }
 
+static __init void check_quirks(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		__check_quirks_intel();
+}
+
 static __init bool get_rdt_resources(void)
 {
-	rdt_quirks();
 	rdt_alloc_capable = get_rdt_alloc_resources();
 	rdt_mon_capable = get_rdt_mon_resources();
 
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+static __init void rdt_init_res_defs_intel(void)
+{
+	struct rdt_resource *r;
+
+	for_each_rdt_resource(r) {
+		if (r->rid == RDT_RESOURCE_L3 ||
+		    r->rid == RDT_RESOURCE_L3DATA ||
+		    r->rid == RDT_RESOURCE_L3CODE ||
+		    r->rid == RDT_RESOURCE_L2 ||
+		    r->rid == RDT_RESOURCE_L2DATA ||
+		    r->rid == RDT_RESOURCE_L2CODE)
+			r->cbm_validate = cbm_validate_intel;
+		else if (r->rid == RDT_RESOURCE_MBA) {
+			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
+			r->msr_update = mba_wrmsr_intel;
+			r->parse_ctrlval = parse_bw_intel;
+		}
+	}
+}
+
+static __init void rdt_init_res_defs_amd(void)
+{
+	struct rdt_resource *r;
+
+	for_each_rdt_resource(r) {
+		if (r->rid == RDT_RESOURCE_L3 ||
+		    r->rid == RDT_RESOURCE_L3DATA ||
+		    r->rid == RDT_RESOURCE_L3CODE ||
+		    r->rid == RDT_RESOURCE_L2 ||
+		    r->rid == RDT_RESOURCE_L2DATA ||
+		    r->rid == RDT_RESOURCE_L2CODE)
+			r->cbm_validate = cbm_validate_amd;
+		else if (r->rid == RDT_RESOURCE_MBA) {
+			r->msr_base = MSR_IA32_MBA_BW_BASE;
+			r->msr_update = mba_wrmsr_amd;
+			r->parse_ctrlval = parse_bw_amd;
+		}
+	}
+}
+
+static __init void rdt_init_res_defs(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		rdt_init_res_defs_intel();
+	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		rdt_init_res_defs_amd();
+}
+
 static enum cpuhp_state rdt_online;
 
-static int __init intel_rdt_late_init(void)
+static int __init resctrl_late_init(void)
 {
 	struct rdt_resource *r;
 	int state, ret;
 
+	/*
+	 * Initialize functions(or definitions) that are different
+	 * between vendors here.
+	 */
+	rdt_init_res_defs();
+
+	check_quirks();
+
 	if (!get_rdt_resources())
 		return -ENODEV;
 
 	rdt_init_padding();
 
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
-				  "x86/rdt/cat:online:",
-				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
+				  "x86/resctrl/cat:online:",
+				  resctrl_online_cpu, resctrl_offline_cpu);
 	if (state < 0)
 		return state;
 
@@ -890,20 +996,20 @@ static int __init intel_rdt_late_init(void)
 	rdt_online = state;
 
 	for_each_alloc_capable_rdt_resource(r)
-		pr_info("Intel RDT %s allocation detected\n", r->name);
+		pr_info("%s allocation detected\n", r->name);
 
 	for_each_mon_capable_rdt_resource(r)
-		pr_info("Intel RDT %s monitoring detected\n", r->name);
+		pr_info("%s monitoring detected\n", r->name);
 
 	return 0;
 }
 
-late_initcall(intel_rdt_late_init);
+late_initcall(resctrl_late_init);
 
-static void __exit intel_rdt_exit(void)
+static void __exit resctrl_exit(void)
 {
 	cpuhp_remove_state(rdt_online);
 	rdtgroup_exit();
 }
 
-__exitcall(intel_rdt_exit);
+__exitcall(resctrl_exit);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index efa4a519f5e5..2dbd990a2eb7 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -27,7 +27,54 @@
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include "intel_rdt.h"
+#include "internal.h"
+
+/*
+ * Check whether MBA bandwidth percentage value is correct. The value is
+ * checked against the minimum and maximum bandwidth values specified by
+ * the hardware. The allocated bandwidth percentage is rounded to the next
+ * control step available on the hardware.
+ */
+static bool bw_validate_amd(char *buf, unsigned long *data,
+			    struct rdt_resource *r)
+{
+	unsigned long bw;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &bw);
+	if (ret) {
+		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
+		return false;
+	}
+
+	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
+				    r->membw.min_bw, r->default_ctrl);
+		return false;
+	}
+
+	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
+	return true;
+}
+
+int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
+		 struct rdt_domain *d)
+{
+	unsigned long bw_val;
+
+	if (d->have_new_ctrl) {
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+		return -EINVAL;
+	}
+
+	if (!bw_validate_amd(data->buf, &bw_val, r))
+		return -EINVAL;
+
+	d->new_ctrl = bw_val;
+	d->have_new_ctrl = true;
+
+	return 0;
+}
 
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
@@ -65,13 +112,13 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
-	     struct rdt_domain *d)
+int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
+		   struct rdt_domain *d)
 {
 	unsigned long bw_val;
 
 	if (d->have_new_ctrl) {
-		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
@@ -89,7 +136,7 @@ int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
+bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -97,12 +144,12 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 
 	ret = kstrtoul(buf, 16, &val);
 	if (ret) {
-		rdt_last_cmd_printf("non-hex character in mask %s\n", buf);
+		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
 		return false;
 	}
 
 	if (val == 0 || val > r->default_ctrl) {
-		rdt_last_cmd_puts("mask out of range\n");
+		rdt_last_cmd_puts("Mask out of range\n");
 		return false;
 	}
 
@@ -110,12 +157,12 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
 	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
-		rdt_last_cmd_printf("mask %lx has non-consecutive 1-bits\n", val);
+		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
 		return false;
 	}
 
 	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("Need at least %d bits in mask\n",
+		rdt_last_cmd_printf("Need at least %d bits in the mask\n",
 				    r->cache.min_cbm_bits);
 		return false;
 	}
@@ -125,6 +172,30 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 }
 
 /*
+ * Check whether a cache bit mask is valid. AMD allows non-contiguous
+ * bitmasks
+ */
+bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret) {
+		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
+		return false;
+	}
+
+	if (val > r->default_ctrl) {
+		rdt_last_cmd_puts("Mask out of range\n");
+		return false;
+	}
+
+	*data = val;
+	return true;
+}
+
+/*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
@@ -135,7 +206,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
-		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
@@ -145,17 +216,17 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	 */
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
-		rdt_last_cmd_printf("pseudo-locked region in hierarchy\n");
+		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
 		return -EINVAL;
 	}
 
-	if (!cbm_validate(data->buf, &cbm_val, r))
+	if (!r->cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
 	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
 	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
 	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
-		rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n");
+		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
 		return -EINVAL;
 	}
 
@@ -164,14 +235,14 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	 * either is exclusive.
 	 */
 	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
-		rdt_last_cmd_printf("overlaps with exclusive group\n");
+		rdt_last_cmd_puts("Overlaps with exclusive group\n");
 		return -EINVAL;
 	}
 
 	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
 		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			rdt_last_cmd_printf("overlaps with other group\n");
+			rdt_last_cmd_puts("Overlaps with other group\n");
 			return -EINVAL;
 		}
 	}
@@ -293,7 +364,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok,
 		if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
 			return parse_line(tok, r, rdtgrp);
 	}
-	rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
+	rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
 	return -EINVAL;
 }
 
@@ -326,7 +397,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	 */
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("resource group is pseudo-locked\n");
+		rdt_last_cmd_puts("Resource group is pseudo-locked\n");
 		goto out;
 	}
 
@@ -467,7 +538,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	r = &rdt_resources_all[resid];
 	d = rdt_find_domain(r, domid, NULL);
-	if (!d) {
+	if (IS_ERR_OR_NULL(d)) {
 		ret = -ENOENT;
 		goto out;
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3736f6dc9545..e49b77283924 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -1,20 +1,25 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_INTEL_RDT_H
-#define _ASM_X86_INTEL_RDT_H
+#ifndef _ASM_X86_RESCTRL_INTERNAL_H
+#define _ASM_X86_RESCTRL_INTERNAL_H
 
 #include <linux/sched.h>
 #include <linux/kernfs.h>
+#include <linux/fs_context.h>
 #include <linux/jump_label.h>
 
-#define IA32_L3_QOS_CFG		0xc81
-#define IA32_L2_QOS_CFG		0xc82
-#define IA32_L3_CBM_BASE	0xc90
-#define IA32_L2_CBM_BASE	0xd10
-#define IA32_MBA_THRTL_BASE	0xd50
+#define MSR_IA32_L3_QOS_CFG		0xc81
+#define MSR_IA32_L2_QOS_CFG		0xc82
+#define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_IA32_L2_CBM_BASE		0xd10
+#define MSR_IA32_MBA_THRTL_BASE		0xd50
+#define MSR_IA32_MBA_BW_BASE		0xc0000200
 
-#define L3_QOS_CDP_ENABLE	0x01ULL
+#define MSR_IA32_QM_CTR			0x0c8e
+#define MSR_IA32_QM_EVTSEL		0x0c8d
 
-#define L2_QOS_CDP_ENABLE	0x01ULL
+#define L3_QOS_CDP_ENABLE		0x01ULL
+
+#define L2_QOS_CDP_ENABLE		0x01ULL
 
 /*
  * Event IDs are used to program IA32_QM_EVTSEL before reading event
@@ -29,10 +34,28 @@
 #define MBM_CNTR_WIDTH			24
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
+#define MBA_IS_LINEAR			0x4
+#define MBA_MAX_MBPS			U32_MAX
+#define MAX_MBA_BW_AMD			0x800
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
 
+
+struct rdt_fs_context {
+	struct kernfs_fs_context	kfc;
+	bool				enable_cdpl2;
+	bool				enable_cdpl3;
+	bool				enable_mba_mbps;
+};
+
+static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	return container_of(kfc, struct rdt_fs_context, kfc);
+}
+
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 
 /**
@@ -69,7 +92,7 @@ struct rmid_read {
 	u64			val;
 };
 
-extern unsigned int intel_cqm_threshold;
+extern unsigned int resctrl_cqm_threshold;
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
 extern unsigned int rdt_mon_features;
@@ -391,9 +414,9 @@ struct rdt_parse_data {
  * struct rdt_resource - attributes of an RDT resource
  * @rid:		The index of the resource
  * @alloc_enabled:	Is allocation enabled on this machine
- * @mon_enabled:		Is monitoring enabled for this feature
+ * @mon_enabled:	Is monitoring enabled for this feature
  * @alloc_capable:	Is allocation available on this machine
- * @mon_capable:		Is monitor feature available on this machine
+ * @mon_capable:	Is monitor feature available on this machine
  * @name:		Name to use in "schemata" file
  * @num_closid:		Number of CLOSIDs available
  * @cache_level:	Which cache level defines scope of this resource
@@ -405,10 +428,11 @@ struct rdt_parse_data {
  * @cache:		Cache allocation related data
  * @format_str:		Per resource format string to show domain value
  * @parse_ctrlval:	Per resource function pointer to parse control values
- * @evt_list:			List of monitoring events
- * @num_rmid:			Number of RMIDs available
- * @mon_scale:			cqm counter * mon_scale = occupancy in bytes
- * @fflags:			flags to choose base and info files
+ * @cbm_validate	Cache bitmask validate function
+ * @evt_list:		List of monitoring events
+ * @num_rmid:		Number of RMIDs available
+ * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
+ * @fflags:		flags to choose base and info files
  */
 struct rdt_resource {
 	int			rid;
@@ -431,6 +455,7 @@ struct rdt_resource {
 	int (*parse_ctrlval)(struct rdt_parse_data *data,
 			     struct rdt_resource *r,
 			     struct rdt_domain *d);
+	bool (*cbm_validate)(char *buf, u32 *data, struct rdt_resource *r);
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
@@ -439,8 +464,10 @@ struct rdt_resource {
 
 int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 	      struct rdt_domain *d);
-int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
-	     struct rdt_domain *d);
+int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
+		   struct rdt_domain *d);
+int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
+		 struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -463,6 +490,10 @@ enum {
 	RDT_NUM_RESOURCES,
 };
 
+#define for_each_rdt_resource(r)					      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)
+
 #define for_each_capable_rdt_resource(r)				      \
 	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
 	     r++)							      \
@@ -567,5 +598,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
 void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
+bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
+bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
 
-#endif /* _ASM_X86_INTEL_RDT_H */
+#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index b0f3aed76b75..1573a0a6b525 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -26,10 +26,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
-#include "intel_rdt.h"
-
-#define MSR_IA32_QM_CTR		0x0c8e
-#define MSR_IA32_QM_EVTSEL		0x0c8d
+#include "internal.h"
 
 struct rmid_entry {
 	u32				rmid;
@@ -73,7 +70,7 @@ unsigned int rdt_mon_features;
  * This is the threshold cache occupancy at which we will consider an
  * RMID available for re-allocation.
  */
-unsigned int intel_cqm_threshold;
+unsigned int resctrl_cqm_threshold;
 
 static inline struct rmid_entry *__rmid_entry(u32 rmid)
 {
@@ -107,7 +104,7 @@ static bool rmid_dirty(struct rmid_entry *entry)
 {
 	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
 
-	return val >= intel_cqm_threshold;
+	return val >= resctrl_cqm_threshold;
 }
 
 /*
@@ -187,7 +184,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	list_for_each_entry(d, &r->domains, list) {
 		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
 			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
-			if (val <= intel_cqm_threshold)
+			if (val <= resctrl_cqm_threshold)
 				continue;
 		}
 
@@ -504,11 +501,8 @@ out_unlock:
 void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
-	struct rdt_resource *r;
 	int cpu;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3];
-
 	cpu = cpumask_any(&dom->cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
@@ -625,6 +619,7 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 
 int rdt_get_mon_l3_config(struct rdt_resource *r)
 {
+	unsigned int cl_size = boot_cpu_data.x86_cache_size;
 	int ret;
 
 	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
@@ -637,10 +632,10 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	 *
 	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
 	 */
-	intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid;
+	resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
 
 	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
-	intel_cqm_threshold /= r->mon_scale;
+	resctrl_cqm_threshold /= r->mon_scale;
 
 	ret = dom_data_init(r);
 	if (ret)
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 815b4e92522c..604c0e3bcc83 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -24,21 +24,14 @@
 
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
-#include <asm/intel_rdt_sched.h>
+#include <asm/resctrl_sched.h>
 #include <asm/perf_event.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
-#include "intel_rdt.h"
+#include "internal.h"
 
 #define CREATE_TRACE_POINTS
-#include "intel_rdt_pseudo_lock_event.h"
-
-/*
- * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
- * prefetcher state. Details about this register can be found in the MSR
- * tables for specific platforms found in Intel's SDM.
- */
-#define MSR_MISC_FEATURE_CONTROL	0x000001a4
+#include "pseudo_lock_event.h"
 
 /*
  * The bits needed to disable hardware prefetching varies based on the
@@ -213,7 +206,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 	for_each_cpu(cpu, &plr->d->cpu_mask) {
 		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
 		if (!pm_req) {
-			rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
+			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
 			ret = -ENOMEM;
 			goto out_err;
 		}
@@ -222,7 +215,7 @@ static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
 					     DEV_PM_QOS_RESUME_LATENCY,
 					     30);
 		if (ret < 0) {
-			rdt_last_cmd_printf("fail to add latency req cpu%d\n",
+			rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
 					    cpu);
 			kfree(pm_req);
 			ret = -1;
@@ -289,7 +282,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	plr->cpu = cpumask_first(&plr->d->cpu_mask);
 
 	if (!cpu_online(plr->cpu)) {
-		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
+		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
 				    plr->cpu);
 		ret = -ENODEV;
 		goto out_region;
@@ -307,7 +300,7 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	}
 
 	ret = -1;
-	rdt_last_cmd_puts("unable to determine cache line size\n");
+	rdt_last_cmd_puts("Unable to determine cache line size\n");
 out_region:
 	pseudo_lock_region_clear(plr);
 	return ret;
@@ -361,14 +354,14 @@ static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
 	 * KMALLOC_MAX_SIZE.
 	 */
 	if (plr->size > KMALLOC_MAX_SIZE) {
-		rdt_last_cmd_puts("requested region exceeds maximum size\n");
+		rdt_last_cmd_puts("Requested region exceeds maximum size\n");
 		ret = -E2BIG;
 		goto out_region;
 	}
 
 	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
 	if (!plr->kmem) {
-		rdt_last_cmd_puts("unable to allocate memory\n");
+		rdt_last_cmd_puts("Unable to allocate memory\n");
 		ret = -ENOMEM;
 		goto out_region;
 	}
@@ -665,7 +658,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 * default closid associated with it.
 	 */
 	if (rdtgrp == &rdtgroup_default) {
-		rdt_last_cmd_puts("cannot pseudo-lock default group\n");
+		rdt_last_cmd_puts("Cannot pseudo-lock default group\n");
 		return -EINVAL;
 	}
 
@@ -707,17 +700,17 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 */
 	prefetch_disable_bits = get_prefetch_disable_bits();
 	if (prefetch_disable_bits == 0) {
-		rdt_last_cmd_puts("pseudo-locking not supported\n");
+		rdt_last_cmd_puts("Pseudo-locking not supported\n");
 		return -EINVAL;
 	}
 
 	if (rdtgroup_monitor_in_progress(rdtgrp)) {
-		rdt_last_cmd_puts("monitoring in progress\n");
+		rdt_last_cmd_puts("Monitoring in progress\n");
 		return -EINVAL;
 	}
 
 	if (rdtgroup_tasks_assigned(rdtgrp)) {
-		rdt_last_cmd_puts("tasks assigned to resource group\n");
+		rdt_last_cmd_puts("Tasks assigned to resource group\n");
 		return -EINVAL;
 	}
 
@@ -727,13 +720,13 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	}
 
 	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
-		rdt_last_cmd_puts("unable to modify resctrl permissions\n");
+		rdt_last_cmd_puts("Unable to modify resctrl permissions\n");
 		return -EIO;
 	}
 
 	ret = pseudo_lock_init(rdtgrp);
 	if (ret) {
-		rdt_last_cmd_puts("unable to init pseudo-lock region\n");
+		rdt_last_cmd_puts("Unable to init pseudo-lock region\n");
 		goto out_release;
 	}
 
@@ -770,7 +763,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 	if (rdt_mon_capable) {
 		ret = alloc_rmid();
 		if (ret < 0) {
-			rdt_last_cmd_puts("out of RMIDs\n");
+			rdt_last_cmd_puts("Out of RMIDs\n");
 			return ret;
 		}
 		rdtgrp->mon.rmid = ret;
@@ -1304,7 +1297,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 					"pseudo_lock/%u", plr->cpu);
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
-		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
+		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
 		goto out_cstates;
 	}
 
@@ -1322,13 +1315,13 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		 * the cleared, but not freed, plr struct resulting in an
 		 * empty pseudo-locking loop.
 		 */
-		rdt_last_cmd_puts("locking thread interrupted\n");
+		rdt_last_cmd_puts("Locking thread interrupted\n");
 		goto out_cstates;
 	}
 
 	ret = pseudo_lock_minor_get(&new_minor);
 	if (ret < 0) {
-		rdt_last_cmd_puts("unable to obtain a new minor number\n");
+		rdt_last_cmd_puts("Unable to obtain a new minor number\n");
 		goto out_cstates;
 	}
 
@@ -1360,7 +1353,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	if (IS_ERR(dev)) {
 		ret = PTR_ERR(dev);
-		rdt_last_cmd_printf("failed to create character device: %d\n",
+		rdt_last_cmd_printf("Failed to create character device: %d\n",
 				    ret);
 		goto out_debugfs;
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h
index 2c041e6d9f05..428ebbd4270b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h
@@ -39,5 +39,5 @@ TRACE_EVENT(pseudo_lock_l3,
 
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event
+#define TRACE_INCLUDE_FILE pseudo_lock_event
 #include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index f27b8115ffa2..85212a32b54d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -24,6 +24,7 @@
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
 #include <linux/fs.h>
+#include <linux/fs_parser.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
 #include <linux/seq_buf.h>
@@ -32,11 +33,12 @@
 #include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/task_work.h>
+#include <linux/user_namespace.h>
 
 #include <uapi/linux/magic.h>
 
-#include <asm/intel_rdt_sched.h>
-#include "intel_rdt.h"
+#include <asm/resctrl_sched.h>
+#include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
@@ -298,7 +300,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 }
 
 /*
- * This is safe against intel_rdt_sched_in() called from __switch_to()
+ * This is safe against resctrl_sched_in() called from __switch_to()
  * because __switch_to() is executed with interrupts disabled. A local call
  * from update_closid_rmid() is proteced against __switch_to() because
  * preemption is disabled.
@@ -317,7 +319,7 @@ static void update_cpu_closid_rmid(void *info)
 	 * executing task might have its own closid selected. Just reuse
 	 * the context switch code.
 	 */
-	intel_rdt_sched_in();
+	resctrl_sched_in();
 }
 
 /*
@@ -345,7 +347,7 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
 	/* Check whether cpus belong to parent ctrl group */
 	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
 	if (cpumask_weight(tmpmask)) {
-		rdt_last_cmd_puts("can only add CPUs to mongroup that belong to parent\n");
+		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
 		return -EINVAL;
 	}
 
@@ -470,14 +472,14 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 	rdt_last_cmd_clear();
 	if (!rdtgrp) {
 		ret = -ENOENT;
-		rdt_last_cmd_puts("directory was removed\n");
+		rdt_last_cmd_puts("Directory was removed\n");
 		goto unlock;
 	}
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
 	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
 		goto unlock;
 	}
 
@@ -487,7 +489,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		ret = cpumask_parse(buf, newmask);
 
 	if (ret) {
-		rdt_last_cmd_puts("bad cpu list/mask\n");
+		rdt_last_cmd_puts("Bad CPU list/mask\n");
 		goto unlock;
 	}
 
@@ -495,7 +497,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
 	if (cpumask_weight(tmpmask)) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("can only assign online cpus\n");
+		rdt_last_cmd_puts("Can only assign online CPUs\n");
 		goto unlock;
 	}
 
@@ -542,7 +544,7 @@ static void move_myself(struct callback_head *head)
 
 	preempt_disable();
 	/* update PQR_ASSOC MSR to make resource group go into effect */
-	intel_rdt_sched_in();
+	resctrl_sched_in();
 	preempt_enable();
 
 	kfree(callback);
@@ -574,7 +576,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 		 */
 		atomic_dec(&rdtgrp->waitcount);
 		kfree(callback);
-		rdt_last_cmd_puts("task exited\n");
+		rdt_last_cmd_puts("Task exited\n");
 	} else {
 		/*
 		 * For ctrl_mon groups move both closid and rmid.
@@ -692,7 +694,7 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
 	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
 		goto unlock;
 	}
 
@@ -926,7 +928,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
 {
 	struct rdt_resource *r = of->kn->parent->priv;
 
-	seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale);
+	seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale);
 
 	return 0;
 }
@@ -945,7 +947,7 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	if (bytes > (boot_cpu_data.x86_cache_size * 1024))
 		return -EINVAL;
 
-	intel_cqm_threshold = bytes / r->mon_scale;
+	resctrl_cqm_threshold = bytes / r->mon_scale;
 
 	return nbytes;
 }
@@ -1029,7 +1031,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	 * peer RDT CDP resource. Hence the WARN.
 	 */
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
-	if (WARN_ON(!_d_cdp)) {
+	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
 		ret = -EINVAL;
 	}
@@ -1158,14 +1160,14 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 		list_for_each_entry(d, &r->domains, list) {
 			if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
 						  rdtgrp->closid, false)) {
-				rdt_last_cmd_puts("schemata overlaps\n");
+				rdt_last_cmd_puts("Schemata overlaps\n");
 				return false;
 			}
 		}
 	}
 
 	if (!has_cache) {
-		rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n");
+		rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
 		return false;
 	}
 
@@ -1206,7 +1208,7 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 		goto out;
 
 	if (mode == RDT_MODE_PSEUDO_LOCKED) {
-		rdt_last_cmd_printf("cannot change pseudo-locked group\n");
+		rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1235,7 +1237,7 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 			goto out;
 		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
 	} else {
-		rdt_last_cmd_printf("unknown/unsupported mode\n");
+		rdt_last_cmd_puts("Unknown or unsupported mode\n");
 		ret = -EINVAL;
 	}
 
@@ -1722,14 +1724,14 @@ static void l3_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
 }
 
 static void l2_qos_cfg_update(void *arg)
 {
 	bool *enable = arg;
 
-	wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
+	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
 }
 
 static inline bool is_mba_linear(void)
@@ -1858,43 +1860,6 @@ static void cdp_disable_all(void)
 		cdpl2_disable();
 }
 
-static int parse_rdtgroupfs_options(char *data)
-{
-	char *token, *o = data;
-	int ret = 0;
-
-	while ((token = strsep(&o, ",")) != NULL) {
-		if (!*token) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		if (!strcmp(token, "cdp")) {
-			ret = cdpl3_enable();
-			if (ret)
-				goto out;
-		} else if (!strcmp(token, "cdpl2")) {
-			ret = cdpl2_enable();
-			if (ret)
-				goto out;
-		} else if (!strcmp(token, "mba_MBps")) {
-			ret = set_mba_sc(true);
-			if (ret)
-				goto out;
-		} else {
-			ret = -EINVAL;
-			goto out;
-		}
-	}
-
-	return 0;
-
-out:
-	pr_err("Invalid mount option \"%s\"\n", token);
-
-	return ret;
-}
-
 /*
  * We don't allow rdtgroup directories to be created anywhere
  * except the root directory. Thus when looking for the rdtgroup
@@ -1966,13 +1931,27 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
 			     struct rdtgroup *prgrp,
 			     struct kernfs_node **mon_data_kn);
 
-static struct dentry *rdt_mount(struct file_system_type *fs_type,
-				int flags, const char *unused_dev_name,
-				void *data)
+static int rdt_enable_ctx(struct rdt_fs_context *ctx)
 {
+	int ret = 0;
+
+	if (ctx->enable_cdpl2)
+		ret = cdpl2_enable();
+
+	if (!ret && ctx->enable_cdpl3)
+		ret = cdpl3_enable();
+
+	if (!ret && ctx->enable_mba_mbps)
+		ret = set_mba_sc(true);
+
+	return ret;
+}
+
+static int rdt_get_tree(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
 	struct rdt_domain *dom;
 	struct rdt_resource *r;
-	struct dentry *dentry;
 	int ret;
 
 	cpus_read_lock();
@@ -1981,53 +1960,42 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 	 * resctrl file system can only be mounted once.
 	 */
 	if (static_branch_unlikely(&rdt_enable_key)) {
-		dentry = ERR_PTR(-EBUSY);
+		ret = -EBUSY;
 		goto out;
 	}
 
-	ret = parse_rdtgroupfs_options(data);
-	if (ret) {
-		dentry = ERR_PTR(ret);
+	ret = rdt_enable_ctx(ctx);
+	if (ret < 0)
 		goto out_cdp;
-	}
 
 	closid_init();
 
 	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
-	if (ret) {
-		dentry = ERR_PTR(ret);
-		goto out_cdp;
-	}
+	if (ret < 0)
+		goto out_mba;
 
 	if (rdt_mon_capable) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
 					  NULL, "mon_groups",
 					  &kn_mongrp);
-		if (ret) {
-			dentry = ERR_PTR(ret);
+		if (ret < 0)
 			goto out_info;
-		}
 		kernfs_get(kn_mongrp);
 
 		ret = mkdir_mondata_all(rdtgroup_default.kn,
 					&rdtgroup_default, &kn_mondata);
-		if (ret) {
-			dentry = ERR_PTR(ret);
+		if (ret < 0)
 			goto out_mongrp;
-		}
 		kernfs_get(kn_mondata);
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
 	ret = rdt_pseudo_lock_init();
-	if (ret) {
-		dentry = ERR_PTR(ret);
+	if (ret)
 		goto out_mondata;
-	}
 
-	dentry = kernfs_mount(fs_type, flags, rdt_root,
-			      RDTGROUP_SUPER_MAGIC, NULL);
-	if (IS_ERR(dentry))
+	ret = kernfs_get_tree(fc);
+	if (ret < 0)
 		goto out_psl;
 
 	if (rdt_alloc_capable)
@@ -2056,14 +2024,95 @@ out_mongrp:
 		kernfs_remove(kn_mongrp);
 out_info:
 	kernfs_remove(kn_info);
+out_mba:
+	if (ctx->enable_mba_mbps)
+		set_mba_sc(false);
 out_cdp:
 	cdp_disable_all();
 out:
 	rdt_last_cmd_clear();
 	mutex_unlock(&rdtgroup_mutex);
 	cpus_read_unlock();
+	return ret;
+}
 
-	return dentry;
+enum rdt_param {
+	Opt_cdp,
+	Opt_cdpl2,
+	Opt_mba_mbps,
+	nr__rdt_params
+};
+
+static const struct fs_parameter_spec rdt_param_specs[] = {
+	fsparam_flag("cdp",		Opt_cdp),
+	fsparam_flag("cdpl2",		Opt_cdpl2),
+	fsparam_flag("mba_MBps",	Opt_mba_mbps),
+	{}
+};
+
+static const struct fs_parameter_description rdt_fs_parameters = {
+	.name		= "rdt",
+	.specs		= rdt_param_specs,
+};
+
+static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, &rdt_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cdp:
+		ctx->enable_cdpl3 = true;
+		return 0;
+	case Opt_cdpl2:
+		ctx->enable_cdpl2 = true;
+		return 0;
+	case Opt_mba_mbps:
+		if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+			return -EINVAL;
+		ctx->enable_mba_mbps = true;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void rdt_fs_context_free(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+
+	kernfs_free_fs_context(fc);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations rdt_fs_context_ops = {
+	.free		= rdt_fs_context_free,
+	.parse_param	= rdt_parse_param,
+	.get_tree	= rdt_get_tree,
+};
+
+static int rdt_init_fs_context(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->kfc.root = rdt_root;
+	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
+	fc->fs_private = &ctx->kfc;
+	fc->ops = &rdt_fs_context_ops;
+	if (fc->user_ns)
+		put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(&init_user_ns);
+	fc->global = true;
+	return 0;
 }
 
 static int reset_all_ctrls(struct rdt_resource *r)
@@ -2236,9 +2285,10 @@ static void rdt_kill_sb(struct super_block *sb)
 }
 
 static struct file_system_type rdt_fs_type = {
-	.name    = "resctrl",
-	.mount   = rdt_mount,
-	.kill_sb = rdt_kill_sb,
+	.name			= "resctrl",
+	.init_fs_context	= rdt_init_fs_context,
+	.parameters		= &rdt_fs_parameters,
+	.kill_sb		= rdt_kill_sb,
 };
 
 static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
@@ -2540,7 +2590,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			tmp_cbm = d->new_ctrl;
 			if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
 			    r->cache.min_cbm_bits) {
-				rdt_last_cmd_printf("no space on %s:%d\n",
+				rdt_last_cmd_printf("No space on %s:%d\n",
 						    r->name, d->id);
 				return -ENOSPC;
 			}
@@ -2557,12 +2607,13 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			continue;
 		ret = update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
-			rdt_last_cmd_puts("failed to initialize allocations\n");
+			rdt_last_cmd_puts("Failed to initialize allocations\n");
 			return ret;
 		}
-		rdtgrp->mode = RDT_MODE_SHAREABLE;
 	}
 
+	rdtgrp->mode = RDT_MODE_SHAREABLE;
+
 	return 0;
 }
 
@@ -2580,7 +2631,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	rdt_last_cmd_clear();
 	if (!prdtgrp) {
 		ret = -ENODEV;
-		rdt_last_cmd_puts("directory was removed\n");
+		rdt_last_cmd_puts("Directory was removed\n");
 		goto out_unlock;
 	}
 
@@ -2588,7 +2639,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
 		ret = -EINVAL;
-		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
 		goto out_unlock;
 	}
 
@@ -2596,7 +2647,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
 	if (!rdtgrp) {
 		ret = -ENOSPC;
-		rdt_last_cmd_puts("kernel out of memory\n");
+		rdt_last_cmd_puts("Kernel out of memory\n");
 		goto out_unlock;
 	}
 	*r = rdtgrp;
@@ -2637,7 +2688,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	if (rdt_mon_capable) {
 		ret = alloc_rmid();
 		if (ret < 0) {
-			rdt_last_cmd_puts("out of RMIDs\n");
+			rdt_last_cmd_puts("Out of RMIDs\n");
 			goto out_destroy;
 		}
 		rdtgrp->mon.rmid = ret;
@@ -2725,7 +2776,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	kn = rdtgrp->kn;
 	ret = closid_alloc();
 	if (ret < 0) {
-		rdt_last_cmd_puts("out of CLOSIDs\n");
+		rdt_last_cmd_puts("Out of CLOSIDs\n");
 		goto out_common_fail;
 	}
 	closid = ret;
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 772c219b6889..94aa1c72ca98 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -5,9 +5,10 @@
 #include <linux/cpu.h>
 
 #include <asm/pat.h>
+#include <asm/apic.h>
 #include <asm/processor.h>
 
-#include <asm/apic.h>
+#include "cpu.h"
 
 struct cpuid_bit {
 	u16 feature;
@@ -17,7 +18,11 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
-/* Please keep the leaf sorted by cpuid_bit.level for faster search. */
+/*
+ * Please keep the leaf sorted by cpuid_bit.level for faster search.
+ * X86_FEATURE_MBA is supported by both Intel and AMD. But the CPUID
+ * levels are different and there is a separate entry for each.
+ */
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
@@ -29,6 +34,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
+	{ X86_FEATURE_MBA,		CPUID_EBX,  6, 0x80000008, 0 },
 	{ X86_FEATURE_SME,		CPUID_EAX,  0, 0x8000001f, 0 },
 	{ X86_FEATURE_SEV,		CPUID_EAX,  1, 0x8000001f, 0 },
 	{ 0, 0, 0, 0, 0 }
@@ -56,27 +62,3 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, cb->feature);
 	}
 }
-
-u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
-			     enum cpuid_regs_idx reg)
-{
-	const struct cpuid_bit *cb;
-	u32 cpuid_val = 0;
-
-	for (cb = cpuid_bits; cb->feature; cb++) {
-
-		if (level > cb->level)
-			continue;
-
-		if (level < cb->level)
-			break;
-
-		if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
-			if (cpu_has(&boot_cpu_data, cb->feature))
-				cpuid_val |= BIT(cb->bit);
-		}
-	}
-
-	return cpuid_val;
-}
-EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 71ca064e3794..8f6c784141d1 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -10,6 +10,8 @@
 #include <asm/pat.h>
 #include <asm/processor.h>
 
+#include "cpu.h"
+
 /* leaf 0xb SMT level */
 #define SMT_LEVEL	0
 
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index f631a3f15587..17ffc869cab8 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -37,6 +37,7 @@
 #include <asm/reboot.h>
 #include <asm/virtext.h>
 #include <asm/intel_pt.h>
+#include <asm/crash.h>
 
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
@@ -469,6 +470,7 @@ int crash_load_segments(struct kimage *image)
 
 	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret) {
 		vfree((void *)image->arch.elf_headers);
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index eb8ab3915268..22369dd5de3b 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -62,7 +62,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
 
 /**
  * copy_oldmem_page_encrypted - same as copy_oldmem_page() above but ioremap the
- * memory with the encryption mask set to accomodate kdump on SME-enabled
+ * memory with the encryption mask set to accommodate kdump on SME-enabled
  * machines.
  */
 ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize,
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 7299dcbf8e85..8d85e00bb40a 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -23,6 +23,7 @@
 #include <asm/pci_x86.h>
 #include <asm/setup.h>
 #include <asm/i8259.h>
+#include <asm/prom.h>
 
 __initdata u64 initial_dtb;
 char __initdata cmd_line[COMMAND_LINE_SIZE];
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 50895c2f937d..2879e234e193 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -14,6 +14,7 @@
 #include <linux/acpi.h>
 #include <linux/firmware-map.h>
 #include <linux/sort.h>
+#include <linux/memory_hotplug.h>
 
 #include <asm/e820/api.h>
 #include <asm/setup.h>
@@ -671,21 +672,18 @@ __init void e820__reallocate_tables(void)
 	int size;
 
 	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries;
-	n = kmalloc(size, GFP_KERNEL);
+	n = kmemdup(e820_table, size, GFP_KERNEL);
 	BUG_ON(!n);
-	memcpy(n, e820_table, size);
 	e820_table = n;
 
 	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_kexec->nr_entries;
-	n = kmalloc(size, GFP_KERNEL);
+	n = kmemdup(e820_table_kexec, size, GFP_KERNEL);
 	BUG_ON(!n);
-	memcpy(n, e820_table_kexec, size);
 	e820_table_kexec = n;
 
 	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries;
-	n = kmalloc(size, GFP_KERNEL);
+	n = kmemdup(e820_table_firmware, size, GFP_KERNEL);
 	BUG_ON(!n);
-	memcpy(n, e820_table_firmware, size);
 	e820_table_firmware = n;
 }
 
@@ -778,7 +776,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
 {
 	u64 addr;
 
-	addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
+	addr = memblock_phys_alloc(size, align);
 	if (addr) {
 		e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n");
@@ -881,6 +879,10 @@ static int __init parse_memopt(char *p)
 
 	e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	max_mem_size = mem_size;
+#endif
+
 	return 0;
 }
 early_param("mem", parse_memopt);
@@ -1095,6 +1097,9 @@ void __init e820__reserve_resources(void)
 
 	res = memblock_alloc(sizeof(*res) * e820_table->nr_entries,
 			     SMP_CACHE_BYTES);
+	if (!res)
+		panic("%s: Failed to allocate %zu bytes\n", __func__,
+		      sizeof(*res) * e820_table->nr_entries);
 	e820_res = res;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 374a52fa5296..9b33904251a9 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -388,10 +388,6 @@ static int __init setup_early_printk(char *buf)
 		if (!strncmp(buf, "xen", 3))
 			early_console_register(&xenboot_console, keep);
 #endif
-#ifdef CONFIG_EARLY_PRINTK_EFI
-		if (!strncmp(buf, "efi", 3))
-			early_console_register(&early_efi_console, keep);
-#endif
 #ifdef CONFIG_EARLY_PRINTK_USB_XDBC
 		if (!strncmp(buf, "xdbc", 4))
 			early_xdbc_parse_parameter(buf + 4);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 2ea85b32421a..2e5003fef51a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -93,7 +93,7 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
-void __kernel_fpu_begin(void)
+static void __kernel_fpu_begin(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
@@ -111,9 +111,8 @@ void __kernel_fpu_begin(void)
 		__cpu_invalidate_fpregs_state();
 	}
 }
-EXPORT_SYMBOL(__kernel_fpu_begin);
 
-void __kernel_fpu_end(void)
+static void __kernel_fpu_end(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
@@ -122,7 +121,6 @@ void __kernel_fpu_end(void)
 
 	kernel_fpu_enable();
 }
-EXPORT_SYMBOL(__kernel_fpu_end);
 
 void kernel_fpu_begin(void)
 {
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index d99a8ee9e185..f6a1d299627c 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -164,7 +164,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
 
-	if (!access_ok(VERIFY_WRITE, buf, size))
+	if (!access_ok(buf, size))
 		return -EACCES;
 
 	if (!static_cpu_has(X86_FEATURE_FPU))
@@ -281,7 +281,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		return 0;
 	}
 
-	if (!access_ok(VERIFY_READ, buf, size))
+	if (!access_ok(buf, size))
 		return -EACCES;
 
 	fpu__initialize(fpu);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 87a57b7642d3..d7432c2b1051 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -444,7 +444,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
 	 * format. Checking a supervisor state's uncompacted offset is
 	 * an error.
 	 */
-	if (XFEATURE_MASK_SUPERVISOR & (1 << xfeature_nr)) {
+	if (XFEATURE_MASK_SUPERVISOR & BIT_ULL(xfeature_nr)) {
 		WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
 		return -1;
 	}
@@ -669,7 +669,7 @@ static bool is_supported_xstate_size(unsigned int test_xstate_size)
 	return false;
 }
 
-static int init_xstate_size(void)
+static int __init init_xstate_size(void)
 {
 	/* Recompute the context size for enabled features: */
 	unsigned int possible_xstate_size;
@@ -808,10 +808,8 @@ void fpu__resume_cpu(void)
  * Given an xstate feature mask, calculate where in the xsave
  * buffer the state is.  Callers should ensure that the buffer
  * is valid.
- *
- * Note: does not work for compacted buffers.
  */
-void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
+static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
 {
 	int feature_nr = fls64(xstate_feature_mask) - 1;
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 7ee8067cbf45..ef49517f6bb2 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -49,7 +49,7 @@ int ftrace_arch_code_modify_post_process(void)
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
-		unsigned char e8;
+		unsigned char op;
 		int offset;
 	} __attribute__((packed));
 };
@@ -59,20 +59,23 @@ static int ftrace_calc_offset(long ip, long addr)
 	return (int)(addr - ip);
 }
 
-static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *
+ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
-	calc.e8		= 0xe8;
+	calc.op		= op;
 	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
 
-	/*
-	 * No locking needed, this must be called via kstop_machine
-	 * which in essence is like running on a uniprocessor machine.
-	 */
 	return calc.code;
 }
 
+static unsigned char *
+ftrace_call_replace(unsigned long ip, unsigned long addr)
+{
+	return ftrace_text_replace(0xe8, ip, addr);
+}
+
 static inline int
 within(unsigned long addr, unsigned long start, unsigned long end)
 {
@@ -269,7 +272,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
-static int is_ftrace_caller(unsigned long ip)
+static nokprobe_inline int is_ftrace_caller(unsigned long ip)
 {
 	if (ip == ftrace_update_func)
 		return 1;
@@ -299,6 +302,7 @@ int ftrace_int3_handler(struct pt_regs *regs)
 
 	return 1;
 }
+NOKPROBE_SYMBOL(ftrace_int3_handler);
 
 static int ftrace_write(unsigned long ip, const char *val, int size)
 {
@@ -664,22 +668,6 @@ int __init ftrace_dyn_arch_init(void)
 	return 0;
 }
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
-static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
-{
-	static union ftrace_code_union calc;
-
-	/* Jmp not a call (ignore the .e8) */
-	calc.e8		= 0xe9;
-	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
-
-	/*
-	 * ftrace external locks synchronize the access to the static variable.
-	 */
-	return calc.code;
-}
-#endif
-
 /* Currently only x86_64 supports dynamic trampolines */
 #ifdef CONFIG_X86_64
 
@@ -733,18 +721,20 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
+#define RET_SIZE		1
+
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 {
-	unsigned const char *jmp;
 	unsigned long start_offset;
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long offset;
 	unsigned long size;
-	unsigned long ip;
+	unsigned long retq;
 	unsigned long *ptr;
 	void *trampoline;
+	void *ip;
 	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	union ftrace_op_code_union op_ptr;
@@ -764,27 +754,27 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/*
 	 * Allocate enough size to store the ftrace_caller code,
-	 * the jmp to ftrace_epilogue, as well as the address of
-	 * the ftrace_ops this trampoline is used for.
+	 * the iret , as well as the address of the ftrace_ops this
+	 * trampoline is used for.
 	 */
-	trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
+	trampoline = alloc_tramp(size + RET_SIZE + sizeof(void *));
 	if (!trampoline)
 		return 0;
 
-	*tramp_size = size + MCOUNT_INSN_SIZE + sizeof(void *);
+	*tramp_size = size + RET_SIZE + sizeof(void *);
 
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
-	if (WARN_ON(ret < 0)) {
-		tramp_free(trampoline, *tramp_size);
-		return 0;
-	}
+	if (WARN_ON(ret < 0))
+		goto fail;
 
-	ip = (unsigned long)trampoline + size;
+	ip = trampoline + size;
 
-	/* The trampoline ends with a jmp to ftrace_epilogue */
-	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_epilogue);
-	memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
+	/* The trampoline ends with ret(q) */
+	retq = (unsigned long)ftrace_stub;
+	ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+	if (WARN_ON(ret < 0))
+		goto fail;
 
 	/*
 	 * The address of the ftrace_ops that is used for this trampoline
@@ -794,17 +784,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 * the global function_trace_op variable.
 	 */
 
-	ptr = (unsigned long *)(trampoline + size + MCOUNT_INSN_SIZE);
+	ptr = (unsigned long *)(trampoline + size + RET_SIZE);
 	*ptr = (unsigned long)ops;
 
 	op_offset -= start_offset;
 	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
 
 	/* Are we pointing to the reference? */
-	if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
-		tramp_free(trampoline, *tramp_size);
-		return 0;
-	}
+	if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0))
+		goto fail;
 
 	/* Load the contents of ptr into the callback parameter */
 	offset = (unsigned long)ptr;
@@ -819,6 +807,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
 	return (unsigned long)trampoline;
+fail:
+	tramp_free(trampoline, *tramp_size);
+	return 0;
 }
 
 static unsigned long calc_trampoline_call_offset(bool save_regs)
@@ -888,8 +879,8 @@ static void *addr_from_call(void *ptr)
 		return NULL;
 
 	/* Make sure this is a call */
-	if (WARN_ON_ONCE(calc.e8 != 0xe8)) {
-		pr_warn("Expected e8, got %x\n", calc.e8);
+	if (WARN_ON_ONCE(calc.op != 0xe8)) {
+		pr_warn("Expected e8, got %x\n", calc.op);
 		return NULL;
 	}
 
@@ -960,6 +951,11 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_graph_call(void);
 
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
+{
+	return ftrace_text_replace(0xe9, ip, addr);
+}
+
 static int ftrace_mod_jmp(unsigned long ip, void *func)
 {
 	unsigned char *new;
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 91b2cff4b79a..75f2b36b41a6 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -171,9 +171,6 @@ GLOBAL(ftrace_call)
 	restore_mcount_regs
 
 	/*
-	 * The copied trampoline must call ftrace_epilogue as it
-	 * still may need to call the function graph tracer.
-	 *
 	 * The code up to this label is copied into trampolines so
 	 * think twice before adding any new code or changing the
 	 * layout here.
@@ -185,7 +182,10 @@ GLOBAL(ftrace_graph_call)
 	jmp ftrace_stub
 #endif
 
-/* This is weak to keep gas from relaxing the jumps */
+/*
+ * This is weak to keep gas from relaxing the jumps.
+ * It is also used to copy the retq for trampolines.
+ */
 WEAK(ftrace_stub)
 	retq
 ENDPROC(ftrace_caller)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 747c758f67b7..d1dbe8e4eb82 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -386,7 +386,7 @@ NEXT_PAGE(early_dynamic_pgts)
 
 	.data
 
-#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
+#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH)
 NEXT_PGD_PAGE(init_top_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + L4_PAGE_OFFSET*8, 0
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b0acb22e5a46..fb32925a2e62 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -21,10 +21,6 @@
 
 #define HPET_MASK			CLOCKSOURCE_MASK(32)
 
-/* FSEC = 10^-15
-   NSEC = 10^-9 */
-#define FSEC_PER_NSEC			1000000L
-
 #define HPET_DEV_USED_BIT		2
 #define HPET_DEV_USED			(1 << HPET_DEV_USED_BIT)
 #define HPET_DEV_VALID			0x8
@@ -909,6 +905,8 @@ int __init hpet_enable(void)
 		return 0;
 
 	hpet_set_mapping();
+	if (!hpet_virt_address)
+		return 0;
 
 	/*
 	 * Read the period and check for a sane value:
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 34a5c1715148..d73083021002 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -261,12 +261,8 @@ static int arch_build_bp_info(struct perf_event *bp,
 		 * allow kernel breakpoints at all.
 		 */
 		if (attr->bp_addr >= TASK_SIZE_MAX) {
-#ifdef CONFIG_KPROBES
 			if (within_kprobe_blacklist(attr->bp_addr))
 				return -EINVAL;
-#else
-			return -EINVAL;
-#endif
 		}
 
 		hw->type = X86_BREAKPOINT_EXECUTE;
@@ -279,6 +275,7 @@ static int arch_build_bp_info(struct perf_event *bp,
 			hw->len = X86_BREAKPOINT_LEN_X;
 			return 0;
 		}
+		/* fall through */
 	default:
 		return -EINVAL;
 	}
@@ -357,6 +354,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 #endif
 	default:
 		WARN_ON_ONCE(1);
+		return -EINVAL;
 	}
 
 	/*
diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c
new file mode 100644
index 000000000000..e47cd9390ab4
--- /dev/null
+++ b/arch/x86/kernel/ima_arch.c
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 IBM Corporation
+ */
+#include <linux/efi.h>
+#include <linux/ima.h>
+
+extern struct boot_params boot_params;
+
+static enum efi_secureboot_mode get_sb_mode(void)
+{
+	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
+	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
+	efi_status_t status;
+	unsigned long size;
+	u8 secboot;
+
+	size = sizeof(secboot);
+
+	/* Get variable contents into buffer */
+	status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+				  NULL, &size, &secboot);
+	if (status == EFI_NOT_FOUND) {
+		pr_info("ima: secureboot mode disabled\n");
+		return efi_secureboot_mode_disabled;
+	}
+
+	if (status != EFI_SUCCESS) {
+		pr_info("ima: secureboot mode unknown\n");
+		return efi_secureboot_mode_unknown;
+	}
+
+	if (secboot == 0) {
+		pr_info("ima: secureboot mode disabled\n");
+		return efi_secureboot_mode_disabled;
+	}
+
+	pr_info("ima: secureboot mode enabled\n");
+	return efi_secureboot_mode_enabled;
+}
+
+bool arch_ima_get_secureboot(void)
+{
+	static enum efi_secureboot_mode sb_mode;
+	static bool initialized;
+
+	if (!initialized && efi_enabled(EFI_BOOT)) {
+		sb_mode = boot_params.secure_boot;
+
+		if (sb_mode == efi_secureboot_mode_unset)
+			sb_mode = get_sb_mode();
+		initialized = true;
+	}
+
+	if (sb_mode == efi_secureboot_mode_enabled)
+		return true;
+	else
+		return false;
+}
+
+/* secureboot arch rules */
+static const char * const sb_arch_rules[] = {
+#if !IS_ENABLED(CONFIG_KEXEC_VERIFY_SIG)
+	"appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig",
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
+	"measure func=KEXEC_KERNEL_CHECK",
+	NULL
+};
+
+const char * const *arch_get_ima_policy(void)
+{
+	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot())
+		return sb_arch_rules;
+	return NULL;
+}
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 108c48d0d40e..1b2ee55a2dfb 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -19,6 +19,7 @@
 #include <asm/pci_x86.h>
 #include <asm/reboot.h>
 #include <asm/setup.h>
+#include <asm/jailhouse_para.h>
 
 static __initdata struct jailhouse_setup_data setup_data;
 static unsigned int precalibrated_tsc_khz;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index aac0c1f7e354..f99bd26bd3f1 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -16,8 +16,6 @@
 #include <asm/alternative.h>
 #include <asm/text-patching.h>
 
-#ifdef HAVE_JUMP_LABEL
-
 union jump_code_union {
 	char code[JUMP_LABEL_NOP_SIZE];
 	struct {
@@ -130,5 +128,3 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 	if (jlstate == JL_STATE_UPDATE)
 		__jump_label_transform(entry, type, text_poke_early, 1);
 }
-
-#endif
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 278cd07228dd..22f60dd26460 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 	struct efi_info *current_ei = &boot_params.efi_info;
 	struct efi_info *ei = &params->efi_info;
 
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return 0;
+
 	if (!current_ei->efi_memmap_size)
 		return 0;
 
@@ -215,6 +218,9 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	params->screen_info.ext_mem_k = 0;
 	params->alt_mem_k = 0;
 
+	/* Always fill in RSDP: it is either 0 or a valid value */
+	params->acpi_rsdp_addr = boot_params.acpi_rsdp_addr;
+
 	/* Default APM info */
 	memset(&params->apm_bios_info, 0, sizeof(params->apm_bios_info));
 
@@ -253,7 +259,6 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	setup_efi_state(params, params_load_addr, efi_map_offset, efi_map_sz,
 			efi_setup_data_offset);
 #endif
-
 	/* Setup EDD info */
 	memcpy(params->eddbuf, boot_params.eddbuf,
 				EDDMAXNR * sizeof(struct edd_info));
@@ -434,6 +439,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	kbuf.memsz = PAGE_ALIGN(header->init_size);
 	kbuf.buf_align = header->kernel_alignment;
 	kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out_free_params;
@@ -448,6 +454,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
 		kbuf.buf_min = MIN_INITRD_LOAD_ADDR;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
 			goto out_free_params;
@@ -531,9 +538,17 @@ static int bzImage64_cleanup(void *loader_data)
 #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG
 static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 {
-	return verify_pefile_signature(kernel, kernel_len,
-				       VERIFY_USE_SECONDARY_KEYRING,
-				       VERIFYING_KEXEC_PE_SIGNATURE);
+	int ret;
+
+	ret = verify_pefile_signature(kernel, kernel_len,
+				      VERIFY_USE_SECONDARY_KEYRING,
+				      VERIFYING_KEXEC_PE_SIGNATURE);
+	if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) {
+		ret = verify_pefile_signature(kernel, kernel_len,
+					      VERIFY_USE_PLATFORM_KEYRING,
+					      VERIFYING_KEXEC_PE_SIGNATURE);
+	}
+	return ret;
 }
 #endif
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 8e36f249646e..4ff6b4cdb941 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -422,21 +422,16 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 /**
  *	kgdb_roundup_cpus - Get other CPUs into a holding pattern
- *	@flags: Current IRQ state
  *
  *	On SMP systems, we need to get the attention of the other CPUs
  *	and get them be in a known state.  This should do what is needed
  *	to get the other CPUs to call kgdb_wait(). Note that on some arches,
  *	the NMI approach is not used for rounding up all the CPUs. For example,
- *	in case of MIPS, smp_call_function() is used to roundup CPUs. In
- *	this case, we have to make sure that interrupts are enabled before
- *	calling smp_call_function(). The argument to this function is
- *	the flags that will be used when restoring the interrupts. There is
- *	local_irq_save() call before kgdb_roundup_cpus().
+ *	in case of MIPS, smp_call_function() is used to roundup CPUs.
  *
  *	On non-SMP systems, this is not called.
  */
-void kgdb_roundup_cpus(unsigned long flags)
+void kgdb_roundup_cpus(void)
 {
 	apic->send_IPI_allbutself(APIC_DM_NMI);
 }
@@ -472,6 +467,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 		ptr = &remcomInBuffer[1];
 		if (kgdb_hex2long(&ptr, &addr))
 			linux_regs->ip = addr;
+		/* fall through */
 	case 'D':
 	case 'k':
 		/* clear the trace bit */
@@ -804,7 +800,7 @@ knl_write:
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
-struct kgdb_arch arch_kgdb_ops = {
+const struct kgdb_arch arch_kgdb_ops = {
 	/* Breakpoint instruction: */
 	.gdb_bpt_instr		= { 0xcc },
 	.flags			= KGDB_HW_BREAKPOINT,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index c33b06f5faa4..fed46ddb1eef 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	unsigned long *sara = stack_addr(regs);
 
 	ri->ret_addr = (kprobe_opcode_t *) *sara;
+	ri->fp = sara;
 
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
@@ -748,26 +749,48 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
+static struct kprobe kretprobe_kprobe = {
+	.addr = (void *)kretprobe_trampoline,
+};
+
 /*
  * Called from kretprobe_trampoline
  */
-__visible __used void *trampoline_handler(struct pt_regs *regs)
+static __used void *trampoline_handler(struct pt_regs *regs)
 {
+	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 	kprobe_opcode_t *correct_ret_addr = NULL;
+	void *frame_pointer;
+	bool skipped = false;
+
+	preempt_disable();
+
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never run in kprobe handler, kprobe must not
+	 * be running at this point.
+	 */
+	kcb = get_kprobe_ctlblk();
+	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
+	/* On x86-64, we use pt_regs->sp for return address holder. */
+	frame_pointer = &regs->sp;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
 	regs->gs = 0;
+	/* On x86-32, we use pt_regs->flags for return address holder. */
+	frame_pointer = &regs->flags;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
@@ -789,8 +812,25 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be poped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
 
 		if (orig_ret_address != trampoline_address)
 			/*
@@ -808,14 +848,15 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		if (ri->fp != frame_pointer)
+			continue;
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
+			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +872,9 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
@@ -1026,12 +1070,17 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 }
 NOKPROBE_SYMBOL(kprobe_fault_handler);
 
-bool arch_within_kprobe_blacklist(unsigned long addr)
+int __init arch_populate_kprobe_blacklist(void)
 {
-	return  (addr >= (unsigned long)__kprobes_text_start &&
-		 addr < (unsigned long)__kprobes_text_end) ||
-		(addr >= (unsigned long)__entry_text_start &&
-		 addr < (unsigned long)__entry_text_end);
+	int ret;
+
+	ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+					 (unsigned long)__irqentry_text_end);
+	if (ret)
+		return ret;
+
+	return kprobe_add_area_blacklist((unsigned long)__entry_text_start,
+					 (unsigned long)__entry_text_end);
 }
 
 int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 6adf6e6c2933..f14262952015 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -97,6 +97,7 @@ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
 }
 
 asm (
+			".pushsection .rodata\n"
 			"optprobe_template_func:\n"
 			".global optprobe_template_entry\n"
 			"optprobe_template_entry:\n"
@@ -136,8 +137,7 @@ asm (
 #endif
 			".global optprobe_template_end\n"
 			"optprobe_template_end:\n"
-			".type optprobe_template_func, @function\n"
-			".size optprobe_template_func, .-optprobe_template_func\n");
+			".popsection\n");
 
 void optprobe_template_func(void);
 STACK_FRAME_NON_STANDARD(optprobe_template_func);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index ba4bfb7f6a36..5c93a65ee1e5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,6 +457,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 #else
 	u64 ipi_bitmap = 0;
 #endif
+	long ret;
 
 	if (cpumask_empty(mask))
 		return;
@@ -482,8 +483,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 		} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
 			max = apic_id < max ? max : apic_id;
 		} else {
-			kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+			ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
 				(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+			WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
 			min = max = apic_id;
 			ipi_bitmap = 0;
 		}
@@ -491,8 +493,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 	}
 
 	if (ipi_bitmap) {
-		kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+		ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
 			(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+		WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
 	}
 
 	local_irq_restore(flags);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 30084ecaa20f..904494b924c1 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*  KVM paravirtual clock driver. A clocksource implementation
     Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc.
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with this program; if not, write to the Free Software
-    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
 
 #include <linux/clocksource.h>
@@ -117,12 +104,8 @@ static u64 kvm_sched_clock_read(void)
 
 static inline void kvm_sched_clock_init(bool stable)
 {
-	if (!stable) {
-		pv_ops.time.sched_clock = kvm_clock_read;
+	if (!stable)
 		clear_sched_clock_stable();
-		return;
-	}
-
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_ops.time.sched_clock = kvm_sched_clock_read;
 
@@ -368,6 +351,20 @@ void __init kvmclock_init(void)
 	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
 	kvm_get_preset_lpj();
+
+	/*
+	 * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate
+	 * with P/T states and does not stop in deep C-states.
+	 *
+	 * Invariant TSC exposed by host means kvmclock is not necessary:
+	 * can use TSC as clocksource.
+	 *
+	 */
+	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
+	    !check_tsc_unstable())
+		kvm_clock.rating = 299;
+
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
 }
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4c8acdfdc5a7..ceba408ea982 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -352,6 +352,8 @@ void machine_kexec(struct kimage *image)
 
 void arch_crash_save_vmcoreinfo(void)
 {
+	u64 sme_mask = sme_me_mask;
+
 	VMCOREINFO_NUMBER(phys_base);
 	VMCOREINFO_SYMBOL(init_top_pgt);
 	vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
@@ -364,6 +366,7 @@ void arch_crash_save_vmcoreinfo(void)
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
 			      kaslr_offset());
 	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
+	VMCOREINFO_NUMBER(sme_mask);
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 3482460d984d..1bfe5c6e6cfe 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -598,8 +598,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			mpf_base = base;
 			mpf_found = true;
 
-			pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n",
-				base, base + sizeof(*mpf) - 1, mpf);
+			pr_info("found SMP MP-table at [mem %#010lx-%#010lx]\n",
+				base, base + sizeof(*mpf) - 1);
 
 			memblock_reserve(base, sizeof(*mpf));
 			if (mpf->physptr)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index bbfc8b1e9104..c70720f61a34 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -51,8 +51,6 @@
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
-#define CALGARY_MAPPING_ERROR	0
-
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
 #else
@@ -157,8 +155,6 @@ static const unsigned long phb_debug_offsets[] = {
 
 #define PHB_DEBUG_STUFF_OFFSET	0x0020
 
-#define EMERGENCY_PAGES 32 /* = 128KB */
-
 unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED;
 static int translate_empty_slots __read_mostly = 0;
 static int calgary_detected __read_mostly = 0;
@@ -255,7 +251,7 @@ static unsigned long iommu_range_alloc(struct device *dev,
 			if (panic_on_overflow)
 				panic("Calgary: fix the allocator.\n");
 			else
-				return CALGARY_MAPPING_ERROR;
+				return DMA_MAPPING_ERROR;
 		}
 	}
 
@@ -274,11 +270,10 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	dma_addr_t ret;
 
 	entry = iommu_range_alloc(dev, tbl, npages);
-
-	if (unlikely(entry == CALGARY_MAPPING_ERROR)) {
+	if (unlikely(entry == DMA_MAPPING_ERROR)) {
 		pr_warn("failed to allocate %u pages in iommu %p\n",
 			npages, tbl);
-		return CALGARY_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	/* set the return dma address */
@@ -294,12 +289,10 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned int npages)
 {
 	unsigned long entry;
-	unsigned long badend;
 	unsigned long flags;
 
 	/* were we called with bad_dma_address? */
-	badend = CALGARY_MAPPING_ERROR + (EMERGENCY_PAGES * PAGE_SIZE);
-	if (unlikely(dma_addr < badend)) {
+	if (unlikely(dma_addr == DMA_MAPPING_ERROR)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
 		return;
@@ -383,7 +376,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 		npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE);
 
 		entry = iommu_range_alloc(dev, tbl, npages);
-		if (entry == CALGARY_MAPPING_ERROR) {
+		if (entry == DMA_MAPPING_ERROR) {
 			/* makes sure unmap knows to stop */
 			s->dma_length = 0;
 			goto error;
@@ -401,7 +394,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 error:
 	calgary_unmap_sg(dev, sg, nelems, dir, 0);
 	for_each_sg(sg, s, nelems, i) {
-		sg->dma_address = CALGARY_MAPPING_ERROR;
+		sg->dma_address = DMA_MAPPING_ERROR;
 		sg->dma_length = 0;
 	}
 	return 0;
@@ -454,7 +447,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 
 	/* set up tces to cover the allocated range */
 	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-	if (mapping == CALGARY_MAPPING_ERROR)
+	if (mapping == DMA_MAPPING_ERROR)
 		goto free;
 	*dma_handle = mapping;
 	return ret;
@@ -479,11 +472,6 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static int calgary_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == CALGARY_MAPPING_ERROR;
-}
-
 static const struct dma_map_ops calgary_dma_ops = {
 	.alloc = calgary_alloc_coherent,
 	.free = calgary_free_coherent,
@@ -491,7 +479,6 @@ static const struct dma_map_ops calgary_dma_ops = {
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
 	.unmap_page = calgary_unmap_page,
-	.mapping_error = calgary_mapping_error,
 	.dma_supported = dma_direct_supported,
 };
 
@@ -739,9 +726,6 @@ static void __init calgary_reserve_regions(struct pci_dev *dev)
 	u64 start;
 	struct iommu_table *tbl = pci_iommu(dev->bus);
 
-	/* reserve EMERGENCY_PAGES from bad_dma_address and up */
-	iommu_range_reserve(tbl, CALGARY_MAPPING_ERROR, EMERGENCY_PAGES);
-
 	/* avoid the BIOS/VGA first 640KB-1MB region */
 	/* for CalIOC2 - avoid the entire first MB */
 	if (is_calgary(dev->device)) {
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f4562fcec681..d460998ae828 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -17,7 +17,7 @@
 
 static bool disable_dac_quirk __read_mostly;
 
-const struct dma_map_ops *dma_ops = &dma_direct_ops;
+const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 #ifdef CONFIG_IOMMU_DEBUG
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index bd08b9e1c9e2..5f5302028a9a 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -62,10 +62,8 @@ IOMMU_INIT(pci_swiotlb_detect_4gb,
 
 void __init pci_swiotlb_init(void)
 {
-	if (swiotlb) {
+	if (swiotlb)
 		swiotlb_init(0);
-		dma_ops = &swiotlb_dma_ops;
-	}
 }
 
 void __init pci_swiotlb_late_init(void)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7d31192296a8..957eae13b370 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -22,6 +22,8 @@
 #include <linux/utsname.h>
 #include <linux/stackprotector.h>
 #include <linux/cpuidle.h>
+#include <linux/acpi.h>
+#include <linux/elf-randomize.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/cpu.h>
@@ -39,6 +41,7 @@
 #include <asm/desc.h>
 #include <asm/prctl.h>
 #include <asm/spec-ctrl.h>
+#include <asm/proto.h>
 
 #include "process.h"
 
@@ -252,6 +255,18 @@ void arch_setup_new_exec(void)
 	/* If cpuid was previously disabled for this task, re-enable it. */
 	if (test_thread_flag(TIF_NOCPUID))
 		enable_cpuid();
+
+	/*
+	 * Don't inherit TIF_SSBD across exec boundary when
+	 * PR_SPEC_DISABLE_NOEXEC is used.
+	 */
+	if (test_thread_flag(TIF_SSBD) &&
+	    task_spec_ssb_noexec(current)) {
+		clear_thread_flag(TIF_SSBD);
+		task_clear_spec_ssb_disable(current);
+		task_clear_spec_ssb_noexec(current);
+		speculation_ctrl_update(task_thread_info(current)->flags);
+	}
 }
 
 static inline void switch_to_bitmap(struct thread_struct *prev,
@@ -411,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
 	u64 msr = x86_spec_ctrl_base;
 	bool updmsr = false;
 
+	lockdep_assert_irqs_disabled();
+
 	/*
 	 * If TIF_SSBD is different, select the proper mitigation
 	 * method. Note that if SSBD mitigation is disabled or permanentely
@@ -462,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
 
 void speculation_ctrl_update(unsigned long tif)
 {
+	unsigned long flags;
+
 	/* Forced update. Make sure all relevant TIF flags are different */
-	preempt_disable();
+	local_irq_save(flags);
 	__speculation_ctrl_update(~tif, tif);
-	preempt_enable();
+	local_irq_restore(flags);
 }
 
 /* Called from seccomp/prctl update */
@@ -793,7 +812,7 @@ unsigned long get_wchan(struct task_struct *p)
 	unsigned long start, bottom, top, sp, fp, ip, ret = 0;
 	int count = 0;
 
-	if (!p || p == current || p->state == TASK_RUNNING)
+	if (p == current || p->state == TASK_RUNNING)
 		return 0;
 
 	if (!try_get_task_stack(p))
diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h
index 898e97cf6629..320ab978fb1f 100644
--- a/arch/x86/kernel/process.h
+++ b/arch/x86/kernel/process.h
@@ -19,7 +19,7 @@ static inline void switch_to_extra(struct task_struct *prev,
 	if (IS_ENABLED(CONFIG_SMP)) {
 		/*
 		 * Avoid __switch_to_xtra() invocation when conditional
-		 * STIPB is disabled and the only different bit is
+		 * STIBP is disabled and the only different bit is
 		 * TIF_SPEC_IB. For CONFIG_SMP=n TIF_SPEC_IB is not
 		 * in the TIF_WORK_CTXSW masks.
 		 */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index d3e593eb189f..e471d8e6f0b2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -44,9 +44,6 @@
 #include <asm/processor.h>
 #include <asm/fpu/internal.h>
 #include <asm/desc.h>
-#ifdef CONFIG_MATH_EMULATION
-#include <asm/math_emu.h>
-#endif
 
 #include <linux/err.h>
 
@@ -56,7 +53,7 @@
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
 #include <asm/vm86.h>
-#include <asm/intel_rdt_sched.h>
+#include <asm/resctrl_sched.h>
 #include <asm/proto.h>
 
 #include "process.h"
@@ -298,7 +295,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(current_task, next_p);
 
 	/* Load the Intel cache allocation PQR MSR. */
-	intel_rdt_sched_in();
+	resctrl_sched_in();
 
 	return prev_p;
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ddd4fa718c43..6a62f4af9fcf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
 #include <asm/switch_to.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/vdso.h>
-#include <asm/intel_rdt_sched.h>
+#include <asm/resctrl_sched.h>
 #include <asm/unistd.h>
 #include <asm/fsgsbase.h>
 #ifdef CONFIG_IA32_EMULATION
@@ -68,7 +68,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
 	unsigned long d0, d1, d2, d3, d6, d7;
 	unsigned int fsindex, gsindex;
-	unsigned int ds, cs, es;
+	unsigned int ds, es;
 
 	show_iret_regs(regs);
 
@@ -100,7 +100,6 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 	}
 
 	asm("movl %%ds,%0" : "=r" (ds));
-	asm("movl %%cs,%0" : "=r" (cs));
 	asm("movl %%es,%0" : "=r" (es));
 	asm("movl %%fs,%0" : "=r" (fsindex));
 	asm("movl %%gs,%0" : "=r" (gsindex));
@@ -116,7 +115,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 
 	printk(KERN_DEFAULT "FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
 	       fs, fsindex, gs, gsindex, shadowgs);
-	printk(KERN_DEFAULT "CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
+	printk(KERN_DEFAULT "CS:  %04lx DS: %04x ES: %04x CR0: %016lx\n", regs->cs, ds,
 			es, cr0);
 	printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
 			cr4);
@@ -622,7 +621,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	}
 
 	/* Load the Intel cache allocation PQR MSR. */
-	intel_rdt_sched_in();
+	resctrl_sched_in();
 
 	return prev_p;
 }
@@ -646,7 +645,7 @@ void set_personality_64bit(void)
 	/* TBD: overwrites user setup. Should have two bits.
 	   But 64bit processes have always behaved this way,
 	   so it's not too bad. The main problem is just that
-	   32bit childs are affected again. */
+	   32bit children are affected again. */
 	current->personality &= ~READ_IMPLIES_EXEC;
 }
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 736348ead421..8451f38ad399 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -7,6 +7,7 @@
 #include <linux/irq.h>
 
 #include <asm/hpet.h>
+#include <asm/setup.h>
 
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 725624b6c0c0..8fd3cedd9acc 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
 	return 0;
 }
 
+/*
+ * Some machines don't handle the default ACPI reboot method and
+ * require the EFI reboot method:
+ */
+static int __init set_efi_reboot(const struct dmi_system_id *d)
+{
+	if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) {
+		reboot_type = BOOT_EFI;
+		pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident);
+	}
+	return 0;
+}
+
 void __noreturn machine_real_restart(unsigned int type)
 {
 	local_irq_disable();
@@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
 		},
 	},
+	{	/* Handle reboot issue on Acer TravelMate X514-51T */
+		.callback = set_efi_reboot,
+		.ident = "Acer TravelMate X514-51T",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"),
+		},
+	},
 
 	/* Apple */
 	{	/* Handle problems with rebooting on Apple MacBook5 */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d494b9bfe618..3d872a527cd9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -50,6 +50,7 @@
 #include <linux/kvm_para.h>
 #include <linux/dma-contiguous.h>
 #include <xen/xen.h>
+#include <uapi/linux/mount.h>
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index e8796fcd7e5a..4bf46575568a 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -106,22 +106,22 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 	void *ptr;
 
 	if (!node_online(node) || !NODE_DATA(node)) {
-		ptr = memblock_alloc_from_nopanic(size, align, goal);
+		ptr = memblock_alloc_from(size, align, goal);
 		pr_info("cpu %d has no node %d or node-local memory\n",
 			cpu, node);
 		pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
 			 cpu, size, __pa(ptr));
 	} else {
-		ptr = memblock_alloc_try_nid_nopanic(size, align, goal,
-						     MEMBLOCK_ALLOC_ACCESSIBLE,
-						     node);
+		ptr = memblock_alloc_try_nid(size, align, goal,
+					     MEMBLOCK_ALLOC_ACCESSIBLE,
+					     node);
 
 		pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n",
 			 cpu, size, node, __pa(ptr));
 	}
 	return ptr;
 #else
-	return memblock_alloc_from_nopanic(size, align, goal);
+	return memblock_alloc_from(size, align, goal);
 #endif
 }
 
@@ -171,7 +171,7 @@ void __init setup_per_cpu_areas(void)
 	unsigned long delta;
 	int rc;
 
-	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%d\n",
+	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%u\n",
 		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
 
 	/*
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 92a3b312a53c..08dfd4c1a4f9 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -322,7 +322,7 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
 
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		return -EFAULT;
 
 	if (__put_user(sig, &frame->sig))
@@ -385,7 +385,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
 
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		return -EFAULT;
 
 	put_user_try {
@@ -465,7 +465,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
 
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		return -EFAULT;
 
 	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
@@ -547,7 +547,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
 
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		return -EFAULT;
 
 	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
@@ -610,7 +610,7 @@ SYSCALL_DEFINE0(sigreturn)
 
 	frame = (struct sigframe __user *)(regs->sp - 8);
 
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 	if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1
 		&& __copy_from_user(&set.sig[1], &frame->extramask,
@@ -642,7 +642,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	unsigned long uc_flags;
 
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
@@ -871,7 +871,7 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
 
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a9134d1910b9..ce1a67b70168 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -56,6 +56,7 @@
 #include <linux/stackprotector.h>
 #include <linux/gfp.h>
 #include <linux/cpuidle.h>
+#include <linux/numa.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -149,7 +150,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
  */
 static void smp_callin(void)
 {
-	int cpuid, phys_id;
+	int cpuid;
 
 	/*
 	 * If waken up by an INIT in an 82489DX configuration
@@ -160,11 +161,6 @@ static void smp_callin(void)
 	cpuid = smp_processor_id();
 
 	/*
-	 * (This works even if the APIC is not enabled.)
-	 */
-	phys_id = read_apic_id();
-
-	/*
 	 * the boot CPU has finished the init stage and is spinning
 	 * on callin_map until we finish. We are free to set up this
 	 * CPU, first the APIC. (this is probably redundant on most
@@ -841,7 +837,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 /* reduce the number of lines printed when booting a large cpu count system */
 static void announce_cpu(int cpu, int apicid)
 {
-	static int current_node = -1;
+	static int current_node = NUMA_NO_NODE;
 	int node = early_cpu_to_node(cpu);
 	static int width, node_width;
 
@@ -1347,7 +1343,7 @@ void __init calculate_max_logical_packages(void)
 	 * extrapolate the boot cpu's data to all packages.
 	 */
 	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
-	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
 }
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 7627455047c2..5c2d71a1dc06 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -177,7 +177,7 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 {
 	int ret;
 
-	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+	if (!access_ok(fp, sizeof(*frame)))
 		return 0;
 
 	ret = 1;
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index 623965e86b65..fa51723571c8 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -19,12 +19,15 @@
 
 #include <linux/dmi.h>
 #include <linux/err.h>
+#include <linux/efi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/pci.h>
 #include <linux/screen_info.h>
 #include <video/vga.h>
+
+#include <asm/efi.h>
 #include <asm/sysfb.h>
 
 enum {
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a2486f444073..6e5ef8fb8a02 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/init_task.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
index 5bd30c442794..496748ed266a 100644
--- a/arch/x86/kernel/tracepoint.c
+++ b/arch/x86/kernel/tracepoint.c
@@ -10,6 +10,8 @@
 
 #include <asm/hw_irq.h>
 #include <asm/desc.h>
+#include <asm/trace/exceptions.h>
+#include <asm/trace/irq_vectors.h>
 
 DEFINE_STATIC_KEY_FALSE(trace_pagefault_key);
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9b7c4ca8f0a7..d26f9e9c3d83 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -111,6 +111,7 @@ void ist_enter(struct pt_regs *regs)
 	/* This code is a bit fragile.  Test it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
 }
+NOKPROBE_SYMBOL(ist_enter);
 
 void ist_exit(struct pt_regs *regs)
 {
@@ -880,12 +881,12 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-	unsigned long cr0;
+	unsigned long cr0 = read_cr0();
 
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 
 #ifdef CONFIG_MATH_EMULATION
-	if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) {
+	if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) {
 		struct math_emu_info info = { };
 
 		cond_local_irq_enable(regs);
@@ -897,7 +898,6 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #endif
 
 	/* This should not happen. */
-	cr0 = read_cr0();
 	if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
 		/* Try to fix it up and carry on. */
 		write_cr0(cr0 & ~X86_CR0_TS);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e9f777bfed40..3fae23834069 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -297,15 +297,16 @@ static int __init tsc_setup(char *str)
 
 __setup("tsc=", tsc_setup);
 
-#define MAX_RETRIES     5
-#define SMI_TRESHOLD    50000
+#define MAX_RETRIES		5
+#define TSC_DEFAULT_THRESHOLD	0x20000
 
 /*
- * Read TSC and the reference counters. Take care of SMI disturbance
+ * Read TSC and the reference counters. Take care of any disturbances
  */
 static u64 tsc_read_refs(u64 *p, int hpet)
 {
 	u64 t1, t2;
+	u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD;
 	int i;
 
 	for (i = 0; i < MAX_RETRIES; i++) {
@@ -315,7 +316,7 @@ static u64 tsc_read_refs(u64 *p, int hpet)
 		else
 			*p = acpi_pm_read_early();
 		t2 = get_cycles();
-		if ((t2 - t1) < SMI_TRESHOLD)
+		if ((t2 - t1) < thresh)
 			return t2;
 	}
 	return ULLONG_MAX;
@@ -703,15 +704,15 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 	 * zero. In each wait loop iteration we read the TSC and check
 	 * the delta to the previous read. We keep track of the min
 	 * and max values of that delta. The delta is mostly defined
-	 * by the IO time of the PIT access, so we can detect when a
-	 * SMI/SMM disturbance happened between the two reads. If the
+	 * by the IO time of the PIT access, so we can detect when
+	 * any disturbance happened between the two reads. If the
 	 * maximum time is significantly larger than the minimum time,
 	 * then we discard the result and have another try.
 	 *
 	 * 2) Reference counter. If available we use the HPET or the
 	 * PMTIMER as a reference to check the sanity of that value.
 	 * We use separate TSC readouts and check inside of the
-	 * reference read for a SMI/SMM disturbance. We dicard
+	 * reference read for any possible disturbance. We dicard
 	 * disturbed values here as well. We do that around the PIT
 	 * calibration delay loop as we have to wait for a certain
 	 * amount of time anyway.
@@ -744,7 +745,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 		if (ref1 == ref2)
 			continue;
 
-		/* Check, whether the sampling was disturbed by an SMI */
+		/* Check, whether the sampling was disturbed */
 		if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
 			continue;
 
@@ -1268,7 +1269,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
  */
 static void tsc_refine_calibration_work(struct work_struct *work)
 {
-	static u64 tsc_start = -1, ref_start;
+	static u64 tsc_start = ULLONG_MAX, ref_start;
 	static int hpet;
 	u64 tsc_stop, ref_stop, delta;
 	unsigned long freq;
@@ -1283,14 +1284,15 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	 * delayed the first time we expire. So set the workqueue
 	 * again once we know timers are working.
 	 */
-	if (tsc_start == -1) {
+	if (tsc_start == ULLONG_MAX) {
+restart:
 		/*
 		 * Only set hpet once, to avoid mixing hardware
 		 * if the hpet becomes enabled later.
 		 */
 		hpet = is_hpet_enabled();
-		schedule_delayed_work(&tsc_irqwork, HZ);
 		tsc_start = tsc_read_refs(&ref_start, hpet);
+		schedule_delayed_work(&tsc_irqwork, HZ);
 		return;
 	}
 
@@ -1300,9 +1302,9 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	if (ref_start == ref_stop)
 		goto out;
 
-	/* Check, whether the sampling was disturbed by an SMI */
-	if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
-		goto out;
+	/* Check, whether the sampling was disturbed */
+	if (tsc_stop == ULLONG_MAX)
+		goto restart;
 
 	delta = tsc_stop - tsc_start;
 	delta *= 1000000LL;
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 3dc26f95d46e..9b9fd4826e7a 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -320,10 +320,14 @@ bool unwind_next_frame(struct unwind_state *state)
 	}
 
 	/* Get the next frame pointer: */
-	if (state->regs)
+	if (state->next_bp) {
+		next_bp = state->next_bp;
+		state->next_bp = NULL;
+	} else if (state->regs) {
 		next_bp = (unsigned long *)state->regs->bp;
-	else
+	} else {
 		next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task, *state->bp);
+	}
 
 	/* Move to the next frame if it's safe: */
 	if (!update_stack_state(state, next_bp))
@@ -398,6 +402,21 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 
 	bp = get_frame_pointer(task, regs);
 
+	/*
+	 * If we crash with IP==0, the last successfully executed instruction
+	 * was probably an indirect function call with a NULL function pointer.
+	 * That means that SP points into the middle of an incomplete frame:
+	 * *SP is a return pointer, and *(SP-sizeof(unsigned long)) is where we
+	 * would have written a frame pointer if we hadn't crashed.
+	 * Pretend that the frame is complete and that BP points to it, but save
+	 * the real BP so that we can use it when looking for the next frame.
+	 */
+	if (regs && regs->ip == 0 &&
+	    (unsigned long *)kernel_stack_pointer(regs) >= first_frame) {
+		state->next_bp = bp;
+		bp = ((unsigned long *)kernel_stack_pointer(regs)) - 1;
+	}
+
 	/* Initialize stack info and make sure the frame data is accessible: */
 	get_stack_info(bp, state->task, &state->stack_info,
 		       &state->stack_mask);
@@ -410,7 +429,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	 */
 	while (!unwind_done(state) &&
 	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
-			state->bp < first_frame))
+			(state->next_bp == NULL && state->bp < first_frame)))
 		unwind_next_frame(state);
 }
 EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 26038eacf74a..89be1be1790c 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -113,6 +113,20 @@ static struct orc_entry *orc_ftrace_find(unsigned long ip)
 }
 #endif
 
+/*
+ * If we crash with IP==0, the last successfully executed instruction
+ * was probably an indirect function call with a NULL function pointer,
+ * and we don't have unwind information for NULL.
+ * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function
+ * pointer into its parent and then continue normally from there.
+ */
+static struct orc_entry null_orc_entry = {
+	.sp_offset = sizeof(long),
+	.sp_reg = ORC_REG_SP,
+	.bp_reg = ORC_REG_UNDEFINED,
+	.type = ORC_TYPE_CALL
+};
+
 static struct orc_entry *orc_find(unsigned long ip)
 {
 	static struct orc_entry *orc;
@@ -120,6 +134,9 @@ static struct orc_entry *orc_find(unsigned long ip)
 	if (!orc_init)
 		return NULL;
 
+	if (ip == 0)
+		return &null_orc_entry;
+
 	/* For non-init vmlinux addresses, use the fast lookup table: */
 	if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) {
 		unsigned int idx, start, stop;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 843feb94a950..ccf03416e434 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -745,6 +745,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 		 * OPCODE1() of the "short" jmp which checks the same condition.
 		 */
 		opc1 = OPCODE2(insn) - 0x10;
+		/* fall through */
 	default:
 		if (!is_cond_jmp_opcode(opc1))
 			return -ENOSYS;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index c2fd39752da8..a092b6b40c6b 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -114,7 +114,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask);
 	user = vm86->user_vm86;
 
-	if (!access_ok(VERIFY_WRITE, user, vm86->vm86plus.is_vm86pus ?
+	if (!access_ok(user, vm86->vm86plus.is_vm86pus ?
 		       sizeof(struct vm86plus_struct) :
 		       sizeof(struct vm86_struct))) {
 		pr_alert("could not access userspace vm86 info\n");
@@ -278,7 +278,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	if (vm86->saved_sp0)
 		return -EPERM;
 
-	if (!access_ok(VERIFY_READ, user_vm86, plus ?
+	if (!access_ok(user_vm86, plus ?
 		       sizeof(struct vm86_struct) :
 		       sizeof(struct vm86plus_struct)))
 		return -EFAULT;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0d618ee634ac..a5127b2c195f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -31,7 +31,7 @@
 
 #undef i386     /* in case the preprocessor is a 32bit one */
 
-OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT)
 
 #ifdef CONFIG_X86_32
 OUTPUT_ARCH(i386)
@@ -362,7 +362,7 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
-		*(.bss)
+		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
 		__bss_stop = .;
@@ -401,7 +401,7 @@ SECTIONS
  * Per-cpu symbols which need to be offset from __per_cpu_load
  * for the boot processor.
  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
 INIT_PER_CPU(gdt_page);
 INIT_PER_CPU(irq_stack_union);