17 files changed, 411 insertions, 126 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 2ff3e600f426..6aef9ee28a39 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -84,7 +84,7 @@ obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o
 obj-$(CONFIG_INTEL_TXT)		+= tboot.o
 obj-$(CONFIG_ISA_DMA_API)	+= i8237.o
-obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
+obj-y				+= stacktrace.o
 obj-y				+= cpu/
 obj-y				+= acpi/
 obj-y				+= reboot.o
diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c
index 03bb2f343ddb..8a25b1c0d480 100644
--- a/arch/x86/kernel/cc_platform.c
+++ b/arch/x86/kernel/cc_platform.c
@@ -50,6 +50,14 @@ static bool amd_cc_platform_has(enum cc_attr attr)
 	case CC_ATTR_GUEST_STATE_ENCRYPT:
 		return sev_status & MSR_AMD64_SEV_ES_ENABLED;
 
+	/*
+	 * With SEV, the rep string I/O instructions need to be unrolled
+	 * but SEV-ES supports them through the #VC handler.
+	 */
+	case CC_ATTR_GUEST_UNROLL_STRING_IO:
+		return (sev_status & MSR_AMD64_SEV_ENABLED) &&
+			!(sev_status & MSR_AMD64_SEV_ES_ENABLED);
+
 	default:
 		return false;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0083464de5e3..79b3d67addcc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -384,7 +384,7 @@ set_register:
 }
 EXPORT_SYMBOL(native_write_cr0);
 
-void native_write_cr4(unsigned long val)
+void __no_profile native_write_cr4(unsigned long val)
 {
 	unsigned long bits_changed = 0;
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c9f0f3d63f75..eaf25a234ff5 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -282,7 +282,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	u64 shift = 64 - width, chunks;
 
 	chunks = (cur_msr << shift) - (prev_msr << shift);
-	return chunks >>= shift;
+	return chunks >> shift;
 }
 
 static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 8471a8b9b48e..4b41efc9e367 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -6,11 +6,13 @@
 #include <linux/highmem.h>
 #include <linux/kthread.h>
 #include <linux/miscdevice.h>
+#include <linux/node.h>
 #include <linux/pagemap.h>
 #include <linux/ratelimit.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
+#include <linux/sysfs.h>
 #include <asm/sgx.h>
 #include "driver.h"
 #include "encl.h"
@@ -20,6 +22,7 @@ struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
 static int sgx_nr_epc_sections;
 static struct task_struct *ksgxd_tsk;
 static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq);
+static DEFINE_XARRAY(sgx_epc_address_space);
 
 /*
  * These variables are part of the state of the reclaimer, and must be accessed
@@ -60,6 +63,24 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
 
 		page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
 
+		/*
+		 * Checking page->poison without holding the node->lock
+		 * is racy, but losing the race (i.e. poison is set just
+		 * after the check) just means __eremove() will be uselessly
+		 * called for a page that sgx_free_epc_page() will put onto
+		 * the node->sgx_poison_page_list later.
+		 */
+		if (page->poison) {
+			struct sgx_epc_section *section = &sgx_epc_sections[page->section];
+			struct sgx_numa_node *node = section->node;
+
+			spin_lock(&node->lock);
+			list_move(&page->list, &node->sgx_poison_page_list);
+			spin_unlock(&node->lock);
+
+			continue;
+		}
+
 		ret = __eremove(sgx_get_epc_virt_addr(page));
 		if (!ret) {
 			/*
@@ -471,6 +492,7 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
 
 	page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list);
 	list_del_init(&page->list);
+	page->flags = 0;
 
 	spin_unlock(&node->lock);
 	atomic_long_dec(&sgx_nr_free_pages);
@@ -624,7 +646,12 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
 
 	spin_lock(&node->lock);
 
-	list_add_tail(&page->list, &node->free_page_list);
+	page->owner = NULL;
+	if (page->poison)
+		list_add(&page->list, &node->sgx_poison_page_list);
+	else
+		list_add_tail(&page->list, &node->free_page_list);
+	page->flags = SGX_EPC_PAGE_IS_FREE;
 
 	spin_unlock(&node->lock);
 	atomic_long_inc(&sgx_nr_free_pages);
@@ -648,17 +675,102 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
 	}
 
 	section->phys_addr = phys_addr;
+	xa_store_range(&sgx_epc_address_space, section->phys_addr,
+		       phys_addr + size - 1, section, GFP_KERNEL);
 
 	for (i = 0; i < nr_pages; i++) {
 		section->pages[i].section = index;
 		section->pages[i].flags = 0;
 		section->pages[i].owner = NULL;
+		section->pages[i].poison = 0;
 		list_add_tail(&section->pages[i].list, &sgx_dirty_page_list);
 	}
 
 	return true;
 }
 
+bool arch_is_platform_page(u64 paddr)
+{
+	return !!xa_load(&sgx_epc_address_space, paddr);
+}
+EXPORT_SYMBOL_GPL(arch_is_platform_page);
+
+static struct sgx_epc_page *sgx_paddr_to_page(u64 paddr)
+{
+	struct sgx_epc_section *section;
+
+	section = xa_load(&sgx_epc_address_space, paddr);
+	if (!section)
+		return NULL;
+
+	return &section->pages[PFN_DOWN(paddr - section->phys_addr)];
+}
+
+/*
+ * Called in process context to handle a hardware reported
+ * error in an SGX EPC page.
+ * If the MF_ACTION_REQUIRED bit is set in flags, then the
+ * context is the task that consumed the poison data. Otherwise
+ * this is called from a kernel thread unrelated to the page.
+ */
+int arch_memory_failure(unsigned long pfn, int flags)
+{
+	struct sgx_epc_page *page = sgx_paddr_to_page(pfn << PAGE_SHIFT);
+	struct sgx_epc_section *section;
+	struct sgx_numa_node *node;
+
+	/*
+	 * mm/memory-failure.c calls this routine for all errors
+	 * where there isn't a "struct page" for the address. But that
+	 * includes other address ranges besides SGX.
+	 */
+	if (!page)
+		return -ENXIO;
+
+	/*
+	 * If poison was consumed synchronously. Send a SIGBUS to
+	 * the task. Hardware has already exited the SGX enclave and
+	 * will not allow re-entry to an enclave that has a memory
+	 * error. The signal may help the task understand why the
+	 * enclave is broken.
+	 */
+	if (flags & MF_ACTION_REQUIRED)
+		force_sig(SIGBUS);
+
+	section = &sgx_epc_sections[page->section];
+	node = section->node;
+
+	spin_lock(&node->lock);
+
+	/* Already poisoned? Nothing more to do */
+	if (page->poison)
+		goto out;
+
+	page->poison = 1;
+
+	/*
+	 * If the page is on a free list, move it to the per-node
+	 * poison page list.
+	 */
+	if (page->flags & SGX_EPC_PAGE_IS_FREE) {
+		list_move(&page->list, &node->sgx_poison_page_list);
+		goto out;
+	}
+
+	/*
+	 * TBD: Add additional plumbing to enable pre-emptive
+	 * action for asynchronous poison notification. Until
+	 * then just hope that the poison:
+	 * a) is not accessed - sgx_free_epc_page() will deal with it
+	 *    when the user gives it back
+	 * b) results in a recoverable machine check rather than
+	 *    a fatal one
+	 */
+out:
+	spin_unlock(&node->lock);
+	return 0;
+}
+
 /**
  * A section metric is concatenated in a way that @low bits 12-31 define the
  * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the
@@ -670,6 +782,48 @@ static inline u64 __init sgx_calc_section_metric(u64 low, u64 high)
 	       ((high & GENMASK_ULL(19, 0)) << 32);
 }
 
+#ifdef CONFIG_NUMA
+static ssize_t sgx_total_bytes_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%lu\n", sgx_numa_nodes[dev->id].size);
+}
+static DEVICE_ATTR_RO(sgx_total_bytes);
+
+static umode_t arch_node_attr_is_visible(struct kobject *kobj,
+		struct attribute *attr, int idx)
+{
+	/* Make all x86/ attributes invisible when SGX is not initialized: */
+	if (nodes_empty(sgx_numa_mask))
+		return 0;
+
+	return attr->mode;
+}
+
+static struct attribute *arch_node_dev_attrs[] = {
+	&dev_attr_sgx_total_bytes.attr,
+	NULL,
+};
+
+const struct attribute_group arch_node_dev_group = {
+	.name = "x86",
+	.attrs = arch_node_dev_attrs,
+	.is_visible = arch_node_attr_is_visible,
+};
+
+static void __init arch_update_sysfs_visibility(int nid)
+{
+	struct node *node = node_devices[nid];
+	int ret;
+
+	ret = sysfs_update_group(&node->dev.kobj, &arch_node_dev_group);
+
+	if (ret)
+		pr_err("sysfs update failed (%d), files may be invisible", ret);
+}
+#else /* !CONFIG_NUMA */
+static void __init arch_update_sysfs_visibility(int nid) {}
+#endif
+
 static bool __init sgx_page_cache_init(void)
 {
 	u32 eax, ebx, ecx, edx, type;
@@ -713,10 +867,16 @@ static bool __init sgx_page_cache_init(void)
 		if (!node_isset(nid, sgx_numa_mask)) {
 			spin_lock_init(&sgx_numa_nodes[nid].lock);
 			INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list);
+			INIT_LIST_HEAD(&sgx_numa_nodes[nid].sgx_poison_page_list);
 			node_set(nid, sgx_numa_mask);
+			sgx_numa_nodes[nid].size = 0;
+
+			/* Make SGX-specific node sysfs files visible: */
+			arch_update_sysfs_visibility(nid);
 		}
 
 		sgx_epc_sections[i].node =  &sgx_numa_nodes[nid];
+		sgx_numa_nodes[nid].size += size;
 
 		sgx_nr_epc_sections++;
 	}
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 4628acec0009..0f17def9fe6f 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -26,9 +26,13 @@
 /* Pages, which are being tracked by the page reclaimer. */
 #define SGX_EPC_PAGE_RECLAIMER_TRACKED	BIT(0)
 
+/* Pages on free list */
+#define SGX_EPC_PAGE_IS_FREE		BIT(1)
+
 struct sgx_epc_page {
 	unsigned int section;
-	unsigned int flags;
+	u16 flags;
+	u16 poison;
 	struct sgx_encl_page *owner;
 	struct list_head list;
 };
@@ -39,6 +43,8 @@ struct sgx_epc_page {
  */
 struct sgx_numa_node {
 	struct list_head free_page_list;
+	struct list_head sgx_poison_page_list;
+	unsigned long size;
 	spinlock_t lock;
 };
 
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8ea306b1bf8e..dd3777ac0443 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -99,6 +99,19 @@ bool irq_fpu_usable(void)
 EXPORT_SYMBOL(irq_fpu_usable);
 
 /*
+ * Track AVX512 state use because it is known to slow the max clock
+ * speed of the core.
+ */
+static void update_avx_timestamp(struct fpu *fpu)
+{
+
+#define AVX512_TRACKING_MASK	(XFEATURE_MASK_ZMM_Hi256 | XFEATURE_MASK_Hi16_ZMM)
+
+	if (fpu->fpstate->regs.xsave.header.xfeatures & AVX512_TRACKING_MASK)
+		fpu->avx512_timestamp = jiffies;
+}
+
+/*
  * Save the FPU register state in fpu->fpstate->regs. The register state is
  * preserved.
  *
@@ -116,13 +129,7 @@ void save_fpregs_to_fpstate(struct fpu *fpu)
 {
 	if (likely(use_xsave())) {
 		os_xsave(fpu->fpstate);
-
-		/*
-		 * AVX512 state is tracked here because its use is
-		 * known to slow the max clock speed of the core.
-		 */
-		if (fpu->fpstate->regs.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
-			fpu->avx512_timestamp = jiffies;
+		update_avx_timestamp(fpu);
 		return;
 	}
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index d5958278eba6..91d4b6de58ab 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 				      struct fpstate *fpstate)
 {
 	struct xregs_state __user *x = buf;
-	struct _fpx_sw_bytes sw_bytes;
+	struct _fpx_sw_bytes sw_bytes = {};
 	u32 xfeatures;
 	int err;
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index fc5371a7e9d1..de563db9cdcd 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -126,6 +126,36 @@ static bool __head check_la57_support(unsigned long physaddr)
 }
 #endif
 
+static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
+{
+	unsigned long vaddr, vaddr_end;
+	int i;
+
+	/* Encrypt the kernel and related (if SME is active) */
+	sme_encrypt_kernel(bp);
+
+	/*
+	 * Clear the memory encryption mask from the .bss..decrypted section.
+	 * The bss section will be memset to zero later in the initialization so
+	 * there is no need to zero it after changing the memory encryption
+	 * attribute.
+	 */
+	if (sme_get_me_mask()) {
+		vaddr = (unsigned long)__start_bss_decrypted;
+		vaddr_end = (unsigned long)__end_bss_decrypted;
+		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+			i = pmd_index(vaddr);
+			pmd[i] -= sme_get_me_mask();
+		}
+	}
+
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
+}
+
 /* Code in __startup_64() can be relocated during execution, but the compiler
  * doesn't have to generate PC-relative relocations when accessing globals from
  * that function. Clang actually does not generate them, which leads to
@@ -135,7 +165,6 @@ static bool __head check_la57_support(unsigned long physaddr)
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
-	unsigned long vaddr, vaddr_end;
 	unsigned long load_delta, *p;
 	unsigned long pgtable_flags;
 	pgdval_t *pgd;
@@ -276,34 +305,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 */
 	*fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask();
 
-	/* Encrypt the kernel and related (if SME is active) */
-	sme_encrypt_kernel(bp);
-
-	/*
-	 * Clear the memory encryption mask from the .bss..decrypted section.
-	 * The bss section will be memset to zero later in the initialization so
-	 * there is no need to zero it after changing the memory encryption
-	 * attribute.
-	 *
-	 * This is early code, use an open coded check for SME instead of
-	 * using cc_platform_has(). This eliminates worries about removing
-	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
-	 * function.
-	 */
-	if (sme_get_me_mask()) {
-		vaddr = (unsigned long)__start_bss_decrypted;
-		vaddr_end = (unsigned long)__end_bss_decrypted;
-		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
-			i = pmd_index(vaddr);
-			pmd[i] -= sme_get_me_mask();
-		}
-	}
-
-	/*
-	 * Return the SME encryption mask (if SME is active) to be used as a
-	 * modifier for the initial pgdir entry programmed into CR3.
-	 */
-	return sme_get_me_mask();
+	return sme_postprocess_startup(bp, pmd);
 }
 
 unsigned long __startup_secondary_64(void)
@@ -485,6 +487,10 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 
 	clear_bss();
 
+	/*
+	 * This needs to happen *before* kasan_early_init() because latter maps stuff
+	 * into that page.
+	 */
 	clear_page(init_top_pgt);
 
 	/*
@@ -496,6 +502,16 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 
 	kasan_early_init();
 
+	/*
+	 * Flush global TLB entries which could be left over from the trampoline page
+	 * table.
+	 *
+	 * This needs to happen *after* kasan_early_init() as KASAN-enabled .configs
+	 * instrument native_write_cr4() so KASAN must be initialized for that
+	 * instrumentation to work.
+	 */
+	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));
+
 	idt_setup_early_handler();
 
 	copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d8b3ebd2bb85..9c63fc5988cd 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -166,9 +166,26 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	call	sev_verify_cbit
 	popq	%rsi
 
-	/* Switch to new page-table */
+	/*
+	 * Switch to new page-table
+	 *
+	 * For the boot CPU this switches to early_top_pgt which still has the
+	 * indentity mappings present. The secondary CPUs will switch to the
+	 * init_top_pgt here, away from the trampoline_pgd and unmap the
+	 * indentity mapped ranges.
+	 */
 	movq	%rax, %cr3
 
+	/*
+	 * Do a global TLB flush after the CR3 switch to make sure the TLB
+	 * entries from the identity mapping are flushed.
+	 */
+	movq	%cr4, %rcx
+	movq	%rcx, %rax
+	xorq	$X86_CR4_PGE, %rcx
+	movq	%rcx, %cr4
+	movq	%rax, %cr4
+
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax
 	ANNOTATE_RETPOLINE_SAFE
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 0a40df66a40d..fa700b46588e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -113,17 +113,9 @@ void __noreturn machine_real_restart(unsigned int type)
 	spin_unlock(&rtc_lock);
 
 	/*
-	 * Switch back to the initial page table.
+	 * Switch to the trampoline page table.
 	 */
-#ifdef CONFIG_X86_32
-	load_cr3(initial_page_table);
-#else
-	write_cr3(real_mode_header->trampoline_pgd);
-
-	/* Exiting long mode will fail if CR4.PCIDE is set. */
-	if (boot_cpu_has(X86_FEATURE_PCID))
-		cr4_clear_bits(X86_CR4_PCIDE);
-#endif
+	load_trampoline_pgtable();
 
 	/* Jump to the identity-mapped low memory code */
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f5129bd49dc..f7a132eb794d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -714,9 +714,6 @@ static void __init early_reserve_memory(void)
 
 	early_reserve_initrd();
 
-	if (efi_enabled(EFI_BOOT))
-		efi_memblock_x86_reserve_range();
-
 	memblock_x86_reserve_range_setup_data();
 
 	reserve_ibft_region();
@@ -743,28 +740,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 	return 0;
 }
 
-static char * __init prepare_command_line(void)
-{
-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
-	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
-	if (builtin_cmdline[0]) {
-		/* append boot loader cmdline to builtin */
-		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
-		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
-		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-	}
-#endif
-#endif
-
-	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
-
-	parse_early_param();
-
-	return command_line;
-}
-
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -854,23 +829,6 @@ void __init setup_arch(char **cmdline_p)
 	x86_init.oem.arch_setup();
 
 	/*
-	 * x86_configure_nx() is called before parse_early_param() (called by
-	 * prepare_command_line()) to detect whether hardware doesn't support
-	 * NX (so that the early EHCI debug console setup can safely call
-	 * set_fixmap()). It may then be called again from within noexec_setup()
-	 * during parsing early parameters to honor the respective command line
-	 * option.
-	 */
-	x86_configure_nx();
-
-	/*
-	 * This parses early params and it needs to run before
-	 * early_reserve_memory() because latter relies on such settings
-	 * supplied as early params.
-	 */
-	*cmdline_p = prepare_command_line();
-
-	/*
 	 * Do some memory reservations *before* memory is added to memblock, so
 	 * memblock allocations won't overwrite it.
 	 *
@@ -903,6 +861,36 @@ void __init setup_arch(char **cmdline_p)
 	bss_resource.start = __pa_symbol(__bss_start);
 	bss_resource.end = __pa_symbol(__bss_stop)-1;
 
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+	if (builtin_cmdline[0]) {
+		/* append boot loader cmdline to builtin */
+		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+	}
+#endif
+#endif
+
+	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = command_line;
+
+	/*
+	 * x86_configure_nx() is called before parse_early_param() to detect
+	 * whether hardware doesn't support NX (so that the early EHCI debug
+	 * console setup can safely call set_fixmap()). It may then be called
+	 * again from within noexec_setup() during parsing early parameters
+	 * to honor the respective command line option.
+	 */
+	x86_configure_nx();
+
+	parse_early_param();
+
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 787dc5f568b5..ce987688bbc0 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -221,7 +221,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 
 fail:
 	/* Terminate the guest */
-	sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+	sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 }
 
 static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 09c06c025626..e6d316a01fdd 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -26,6 +26,7 @@
 #include <asm/fpu/xcr.h>
 #include <asm/processor.h>
 #include <asm/realmode.h>
+#include <asm/setup.h>
 #include <asm/traps.h>
 #include <asm/svm.h>
 #include <asm/smp.h>
@@ -86,9 +87,6 @@ struct ghcb_state {
 static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
 DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
 
-/* Needed in vc_early_forward_exception */
-void do_early_exception(struct pt_regs *regs, int trapnr);
-
 static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
 	unsigned long sp = regs->sp;
@@ -209,9 +207,6 @@ static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
 	return ghcb;
 }
 
-/* Needed in vc_early_forward_exception */
-void do_early_exception(struct pt_regs *regs, int trapnr);
-
 static inline u64 sev_es_rd_ghcb_msr(void)
 {
 	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
@@ -294,11 +289,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 				   char *dst, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
-	char __user *target = (char __user *)dst;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __put_user() independent of whether kernel or user
@@ -320,26 +310,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *target = (u8 __user *)dst;
+
 		memcpy(&d1, buf, 1);
 		if (__put_user(d1, target))
 			goto fault;
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *target = (u16 __user *)dst;
+
 		memcpy(&d2, buf, 2);
 		if (__put_user(d2, target))
 			goto fault;
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *target = (u32 __user *)dst;
+
 		memcpy(&d4, buf, 4);
 		if (__put_user(d4, target))
 			goto fault;
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *target = (u64 __user *)dst;
+
 		memcpy(&d8, buf, 8);
 		if (__put_user(d8, target))
 			goto fault;
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
@@ -362,11 +368,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 				  char *src, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT;
-	char __user *s = (char __user *)src;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __get_user() independent of whether kernel or user
@@ -388,26 +389,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *s = (u8 __user *)src;
+
 		if (__get_user(d1, s))
 			goto fault;
 		memcpy(buf, &d1, 1);
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *s = (u16 __user *)src;
+
 		if (__get_user(d2, s))
 			goto fault;
 		memcpy(buf, &d2, 2);
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *s = (u32 __user *)src;
+
 		if (__get_user(d4, s))
 			goto fault;
 		memcpy(buf, &d4, 4);
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *s = (u64 __user *)src;
 		if (__get_user(d8, s))
 			goto fault;
 		memcpy(buf, &d8, 8);
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
@@ -1321,7 +1337,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
 		show_regs(regs);
 
 		/* Ask hypervisor to sev_es_terminate */
-		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 
 		/* If that fails and we get here - just panic */
 		panic("Returned from Terminate-Request to Hypervisor\n");
@@ -1369,7 +1385,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
 
 	/* Do initial setup or terminate the guest */
 	if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
-		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ac2909f0cab3..617012f4619f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -579,6 +579,17 @@ static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 	{ NULL, },
 };
 
+static struct sched_domain_topology_level x86_hybrid_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 static struct sched_domain_topology_level x86_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
@@ -1469,8 +1480,11 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 
 	calculate_max_logical_packages();
 
+	/* XXX for now assume numa-in-package and hybrid don't overlap */
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		set_sched_topology(x86_hybrid_topology);
 
 	nmi_selftest();
 	impress_friends();
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2e076a459a0c..a698196377be 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason)
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
+static void __init tsc_disable_clocksource_watchdog(void)
+{
+	clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+	clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+}
+
 static void __init check_system_tsc_reliable(void)
 {
 #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
@@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void)
 #endif
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		tsc_clocksource_reliable = 1;
+
+	/*
+	 * Disable the clocksource watchdog when the system has:
+	 *  - TSC running at constant frequency
+	 *  - TSC which does not stop in C-States
+	 *  - the TSC_ADJUST register which allows to detect even minimal
+	 *    modifications
+	 *  - not more than two sockets. As the number of sockets cannot be
+	 *    evaluated at the early boot stage where this has to be
+	 *    invoked, check the number of online memory nodes as a
+	 *    fallback solution which is an reasonable estimate.
+	 */
+	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
+	    boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
+	    nr_online_nodes <= 2)
+		tsc_disable_clocksource_watchdog();
 }
 
 /*
@@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void)
 	if (tsc_unstable)
 		goto unreg;
 
-	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
 
@@ -1527,7 +1547,7 @@ void __init tsc_init(void)
 	}
 
 	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+		tsc_disable_clocksource_watchdog();
 
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 50a4515fe0ad..9452dc9664b5 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -30,6 +30,7 @@ struct tsc_adjust {
 };
 
 static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust);
+static struct timer_list tsc_sync_check_timer;
 
 /*
  * TSC's on different sockets may be reset asynchronously.
@@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume)
 	}
 }
 
+/*
+ * Normally the tsc_sync will be checked every time system enters idle
+ * state, but there is still caveat that a system won't enter idle,
+ * either because it's too busy or configured purposely to not enter
+ * idle.
+ *
+ * So setup a periodic timer (every 10 minutes) to make sure the check
+ * is always on.
+ */
+
+#define SYNC_CHECK_INTERVAL		(HZ * 600)
+
+static void tsc_sync_check_timer_fn(struct timer_list *unused)
+{
+	int next_cpu;
+
+	tsc_verify_tsc_adjust(false);
+
+	/* Run the check for all onlined CPUs in turn */
+	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(cpu_online_mask);
+
+	tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL;
+	add_timer_on(&tsc_sync_check_timer, next_cpu);
+}
+
+static int __init start_sync_check_timer(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable)
+		return 0;
+
+	timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0);
+	tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL;
+	add_timer(&tsc_sync_check_timer);
+
+	return 0;
+}
+late_initcall(start_sync_check_timer);
+
 static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
 				   unsigned int cpu, bool bootcpu)
 {