4.18.1-stable review

@@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnb
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (tgt_clobbers & ~site_clobbers)
-		return len;	/* target would clobber too much for this site */
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe8; /* call */
 	b->delta = delta;

@@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbu
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe9;	/* jmp */
 	b->delta = delta;

@@ -313,23 +313,6 @@ static enum spectre_v2_mitigation_cmd __
 	return cmd;
 }
 
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
-{
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6) {
-		switch (boot_cpu_data.x86_model) {
-		case INTEL_FAM6_SKYLAKE_MOBILE:
-		case INTEL_FAM6_SKYLAKE_DESKTOP:
-		case INTEL_FAM6_SKYLAKE_X:
-		case INTEL_FAM6_KABYLAKE_MOBILE:
-		case INTEL_FAM6_KABYLAKE_DESKTOP:
-			return true;
-		}
-	}
-	return false;
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();

@@ -390,22 +373,15 @@ retpoline_auto:
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP nor PTI are available, there is a risk of
-	 * hitting userspace addresses in the RSB after a context switch
-	 * from a shallow call stack to a deeper one. To prevent this fill
-	 * the entire RSB, even when using IBRS.
+	 * If spectre v2 protection has been enabled, unconditionally fill
+	 * RSB during a context switch; this protects against two independent
+	 * issues:
 	 *
-	 * Skylake era CPUs have a separate issue with *underflow* of the
-	 * RSB, when they will predict 'ret' targets from the generic BTB.
-	 * The proper mitigation for this is IBRS. If IBRS is not supported
-	 * or deactivated in favour of retpolines the RSB fill on context
-	 * switch is required.
+	 *	- RSB underflow (and switch to BTB) on Skylake+
+	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
 	 */
-	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
-	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
-		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
-	}
+	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {

@@ -395,8 +395,6 @@ int __copy_instruction(u8 *dest, u8 *src
 			  - (u8 *) real;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
-			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
-				src, real, insn->displacement.value);
 			return 0;
 		}
 		disp = (u8 *) dest + insn_offset_displacement(insn);

@@ -640,8 +638,7 @@ static int reenter_kprobe(struct kprobe
 		 * Raise a BUG or we'll continue in an endless reentering loop
 		 * and eventually a stack overflow.
 		 */
-		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
-		       p->addr);
+		pr_err("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 	default:

@@ -13,6 +13,8 @@
  * Interrupt control:
  */
 
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
 extern inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;

@@ -29,8 +29,13 @@
 #define N_EXCEPTION_STACKS 1
 
 #ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT	44
+/*
+ * This is beyond the 44 bit limit imposed by the 32bit long pfns,
+ * but we need the full mask to make sure inverted PROT_NONE
+ * entries have all the host bits set in a guest.
+ * The real limit is still 44 bits.
+ */
+#define __PHYSICAL_MASK_SHIFT	52
 #define __VIRTUAL_MASK_SHIFT	32
 
 #else  /* !CONFIG_X86_PAE */

@@ -273,7 +273,7 @@ static inline int pgd_large(pgd_t pgd) {
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | OFFSET (14->63) | TYPE (9-13)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) |  OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above

@@ -287,19 +287,28 @@ static inline int pgd_large(pgd_t pgd) {
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  */
-#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
-#define SWP_TYPE_BITS 5
-/* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
-#define __swp_type(x)			(((x).val >> (SWP_TYPE_FIRST_BIT)) \
-					 & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)			((x).val >> SWP_OFFSET_FIRST_BIT)
-#define __swp_entry(type, offset)	((swp_entry_t) { \
-					 ((type) << (SWP_TYPE_FIRST_BIT)) \
-					 | ((offset) << SWP_OFFSET_FIRST_BIT) })
+/* Extract the high bits for type */
+#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
+
+/* Shift up (to get rid of type), then down to get value */
+#define __swp_offset(x) ((x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+
+/*
+ * Shift the offset up "too far" by TYPE bits, then down again
+ */
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+	((unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
+
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val((pmd)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })

@@ -273,7 +273,7 @@ static inline int pgd_large(pgd_t pgd) {
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) |  OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above

@@ -286,6 +286,9 @@ static inline int pgd_large(pgd_t pgd) {
  *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
+ *
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
  */
 #define SWP_TYPE_BITS		5
 

@@ -300,13 +303,15 @@ static inline int pgd_large(pgd_t pgd) {
 #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
 
 /* Shift up (to get rid of type), then down to get value */
-#define __swp_offset(x) ((x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
 
 /*
  * Shift the offset up "too far" by TYPE bits, then down again
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
  */
 #define __swp_entry(type, offset) ((swp_entry_t) { \
-	((unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	(~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
 	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
 
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })

@@ -95,4 +95,21 @@ static inline unsigned long pte_bitop(un
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+	return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_H */

@@ -295,4 +295,6 @@ static inline pte_t gup_get_pte(pte_t *p
 	return pte;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return (val & (_PAGE_PRESENT|_PAGE_PROTNONE)) == _PAGE_PROTNONE;
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+	return __pte_needs_invert(val) ?  ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	/*
+	 * When a PTE transitions from NONE to !NONE or vice-versa
+	 * invert the PFN part to stop speculation.
+	 * pte_pfn undoes this when needed.
+	 */
+	if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+		val = (val & ~mask) | (~val & mask);
+	return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif

92 lines not on this page · raw message

@@ -357,5 +357,7 @@ static inline bool gup_fast_permitted(un
 	return true;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */

@@ -823,6 +823,12 @@ void __init setup_arch(char **cmdline_p)
 	memblock_reserve(__pa_symbol(_text),
 			 (unsigned long)__bss_stop - (unsigned long)_text);
 
+	/*
+	 * Make sure page 0 is always reserved because on systems with
+	 * L1TF its contents can be leaked to user processes.
+	 */
+	memblock_reserve(0, PAGE_SIZE);
+
 	early_reserve_initrd();
 
 	/*

@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */

@@ -373,5 +374,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

@@ -181,6 +181,11 @@ extern const struct seq_operations cpuin
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
+static inline unsigned long l1tf_pfn_limit(void)
+{
+	return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1;
+}
+
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);

@@ -28,9 +28,11 @@
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
 #include <asm/hypervisor.h>
+#include <asm/e820/api.h>
 
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
+static void __init l1tf_select_mitigation(void);
 
 /*
  * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any

@@ -82,6 +84,8 @@ void __init check_bugs(void)
 	 */
 	ssb_select_mitigation();
 
+	l1tf_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.

@@ -207,6 +211,32 @@ static void x86_amd_ssb_disable(void)
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	/*
+	 * This is extremely unlikely to happen because almost all
+	 * systems have far more MAX_PA/2 than RAM can be fit into
+	 * DIMM slots.
+	 */
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (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");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 

@@ -660,6 +690,11 @@ static ssize_t cpu_show_common(struct de
 	case X86_BUG_SPEC_STORE_BYPASS:
 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
 
+	case X86_BUG_L1TF:
+		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
+			return sprintf(buf, "Mitigation: Page Table Inversion\n");
+		break;
+
 	default:
 		break;
 	}

@@ -686,4 +721,9 @@ ssize_t cpu_show_spec_store_bypass(struc
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
 }
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
+}
 #endif

@@ -987,6 +987,21 @@ static const __initconst struct x86_cpu_
 	{}
 };
 
+static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
+	/* in addition to cpu_no_speculation */
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MOOREFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_DENVERTON	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GEMINI_LAKE	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	{}
+};
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;

@@ -1013,6 +1028,11 @@ static void __init cpu_set_bug_bits(stru
 		return;
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+
+	if (x86_match_cpu(cpu_no_l1tf))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_L1TF);
 }
 
 /*

@@ -540,16 +540,24 @@ ssize_t __weak cpu_show_spec_store_bypas
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
+static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
 	&dev_attr_spec_store_bypass.attr,
+	&dev_attr_l1tf.attr,
 	NULL
 };
 

@@ -55,6 +55,8 @@ extern ssize_t cpu_show_spectre_v2(struc
 				   struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
 					  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,

@@ -1338,6 +1338,14 @@ static inline bool pud_access_permitted(
 	return __pte_access_permitted(pud_val(pud), write);
 }
 
+#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
+extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return boot_cpu_has_bug(X86_BUG_L1TF);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 

@@ -240,3 +240,24 @@ int valid_mmap_phys_addr_range(unsigned
 
 	return phys_addr_valid(addr + count - 1);
 }
+
+/*
+ * Only allow root to set high MMIO mappings to PROT_NONE.
+ * This prevents an unpriv. user to set them to PROT_NONE and invert
+ * them, then pointing to valid memory for L1TF speculation.
+ *
+ * Note: for locked down kernels may want to disable the root override.
+ */
+bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return true;
+	if (!__pte_needs_invert(pgprot_val(prot)))
+		return true;
+	/* If it's real memory always allow */
+	if (pfn_valid(pfn))
+		return true;
+	if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+		return false;
+	return true;
+}

@@ -1097,4 +1097,16 @@ static inline void init_espfix_bsp(void)
 #endif
 #endif
 
+#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
+static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	return true;
+}
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return false;
+}
+#endif
+
 #endif /* _ASM_GENERIC_PGTABLE_H */

@@ -1884,6 +1884,9 @@ int vm_insert_pfn_prot(struct vm_area_st
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
 
+	if (!pfn_modify_allowed(pfn, pgprot))
+		return -EACCES;
+
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,

@@ -1919,6 +1922,9 @@ static int __vm_insert_mixed(struct vm_a
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
+	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+		return -EACCES;
+
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
 	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*

@@ -1980,6 +1986,7 @@ static int remap_pte_range(struct mm_str
 {
 	pte_t *pte;
 	spinlock_t *ptl;
+	int err = 0;
 
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)

@@ -1987,12 +1994,16 @@ static int remap_pte_range(struct mm_str
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
+		if (!pfn_modify_allowed(pfn, prot)) {
+			err = -EACCES;
+			break;
+		}
 		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
-	return 0;
+	return err;
 }
 
 static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,

@@ -2001,6 +2012,7 @@ static inline int remap_pmd_range(struct
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pmd = pmd_alloc(mm, pud, addr);

@@ -2009,9 +2021,10 @@ static inline int remap_pmd_range(struct
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
-		if (remap_pte_range(mm, pmd, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pte_range(mm, pmd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }

@@ -2022,6 +2035,7 @@ static inline int remap_pud_range(struct
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pud = pud_alloc(mm, p4d, addr);

@@ -2029,9 +2043,10 @@ static inline int remap_pud_range(struct
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (remap_pmd_range(mm, pud, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pmd_range(mm, pud, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }

@@ -2042,6 +2057,7 @@ static inline int remap_p4d_range(struct
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	p4d = p4d_alloc(mm, pgd, addr);

@@ -2049,9 +2065,10 @@ static inline int remap_p4d_range(struct
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (remap_pud_range(mm, p4d, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }

61 lines not on this page · raw message

@@ -4,6 +4,8 @@
 #include <linux/swap.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>	/* for max_low_pfn */
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>

@@ -880,3 +882,16 @@ void update_cache_mode_entry(unsigned en
 	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
 	__pte2cachemode_tbl[entry] = cache;
 }
+
+unsigned long max_swapfile_size(void)
+{
+	unsigned long pages;
+
+	pages = generic_max_swapfile_size();
+
+	if (boot_cpu_has_bug(X86_BUG_L1TF)) {
+		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+		pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages);
+	}
+	return pages;
+}

@@ -10,5 +10,7 @@ extern spinlock_t swap_lock;
 extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
+extern unsigned long generic_max_swapfile_size(void);
+extern unsigned long max_swapfile_size(void);
 
 #endif /* _LINUX_SWAPFILE_H */

58 lines not on this page · raw message

@@ -211,32 +211,6 @@ static void x86_amd_ssb_disable(void)
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
-static void __init l1tf_select_mitigation(void)
-{
-	u64 half_pa;
-
-	if (!boot_cpu_has_bug(X86_BUG_L1TF))
-		return;
-
-#if CONFIG_PGTABLE_LEVELS == 2
-	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
-	return;
-#endif
-
-	/*
-	 * This is extremely unlikely to happen because almost all
-	 * systems have far more MAX_PA/2 than RAM can be fit into
-	 * DIMM slots.
-	 */
-	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
-	if (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");
-		return;
-	}
-
-	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
-}
-
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 

@@ -660,6 +634,35 @@ void x86_spec_ctrl_setup_ap(void)
 		x86_amd_ssb_disable();
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"L1TF: " fmt
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	/*
+	 * This is extremely unlikely to happen because almost all
+	 * systems have far more MAX_PA/2 than RAM can be fit into
+	 * DIMM slots.
+	 */
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (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");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+#undef pr_fmt
+
 #ifdef CONFIG_SYSFS
 
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,

@@ -5774,6 +5774,18 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * The sched_smt_present static key needs to be evaluated on every
+	 * hotplug event because at boot time SMT might be disabled when
+	 * the number of booted CPUs is limited.
+	 *
+	 * If then later a sibling gets hotplugged, then the key would stay
+	 * off and SMT scheduling would never be functional.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+		static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {

@@ -5871,22 +5883,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	sched_init_numa();

@@ -5908,8 +5904,6 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }
 

@@ -6237,6 +6237,7 @@ static inline int find_idlest_cpu(struct
 }
 
 #ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {

@@ -502,6 +502,12 @@ extern int default_check_phys_apicid_pre
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_SMP
+bool apic_id_is_primary_thread(unsigned int id);
+#else
+static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
+#endif
+
 extern void irq_enter(void);
 extern void irq_exit(void);
 

@@ -123,13 +123,15 @@ static inline int topology_max_smt_threa
 }
 
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-extern int topology_phys_to_logical_pkg(unsigned int pkg);
+int topology_phys_to_logical_pkg(unsigned int pkg);
+bool topology_is_primary_thread(unsigned int cpu);
 #else
 #define topology_max_packages()			(1)
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
+static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)

@@ -2192,6 +2192,21 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+/**
+ * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
+ * @id:	APIC ID to check
+ */
+bool apic_id_is_primary_thread(unsigned int apicid)
+{
+	u32 mask;
+
+	if (smp_num_siblings == 1)
+		return true;
+	/* Isolate the SMT bit(s) in the APICID and check for 0 */
+	mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
+	return !(apicid & mask);
+}
+
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.

@@ -271,6 +271,15 @@ static void notrace start_secondary(void
 }
 
 /**
+ * topology_is_primary_thread - Check whether CPU is the primary SMT thread
+ * @cpu:	CPU to check
+ */
+bool topology_is_primary_thread(unsigned int cpu)
+{
+	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
+}
+
+/**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
  * Returns logical package id or -1 if not found

@@ -125,6 +125,7 @@ static inline int topology_max_smt_threa
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
 int topology_phys_to_logical_pkg(unsigned int pkg);
 bool topology_is_primary_thread(unsigned int cpu);
+bool topology_smt_supported(void);
 #else
 #define topology_max_packages()			(1)
 static inline int

@@ -132,6 +133,7 @@ topology_update_package_map(unsigned int
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline bool topology_smt_supported(void) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)

@@ -280,6 +280,14 @@ bool topology_is_primary_thread(unsigned
 }
 
 /**
+ * topology_smt_supported - Check whether SMT is supported by the CPUs
+ */
+bool topology_smt_supported(void)
+{
+	return smp_num_siblings > 1;
+}
+
+/**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
  * Returns logical package id or -1 if not found

@@ -754,7 +754,6 @@ static int takedown_cpu(unsigned int cpu
 
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
-	smpboot_park_threads(cpu);
 
 	/*
 	 * Prevent irq alloc/free while the dying cpu reorganizes the

@@ -1332,7 +1331,7 @@ static struct cpuhp_step cpuhp_hp_states
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
 		.startup.single		= smpboot_unpark_threads,
-		.teardown.single	= NULL,
+		.teardown.single	= smpboot_park_threads,
 	},
 	[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
 		.name			= "irq/affinity:online",

@@ -906,20 +906,19 @@ out:
 	return ret;
 }
 
+static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
+{
+	if (cpu_hotplug_disabled)
+		return -EBUSY;
+	return _cpu_down(cpu, 0, target);
+}
+
 static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
 	cpu_maps_update_begin();
-
-	if (cpu_hotplug_disabled) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	err = _cpu_down(cpu, 0, target);
-
-out:
+	err = cpu_down_maps_locked(cpu, target);
 	cpu_maps_update_done();
 	return err;
 }

@@ -168,4 +168,17 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+#else
+# define cpu_smt_control		(CPU_SMT_ENABLED)
+#endif
+
 #endif /* _LINUX_CPU_H_ */

192 lines not on this page · raw message

@@ -666,13 +666,12 @@ void detect_ht(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
 	int index_msb, core_bits;
-	static bool printed;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
 		return;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		goto out;
+		return;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
 		return;

@@ -681,14 +680,14 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
+	if (!smp_num_siblings)
+		smp_num_siblings = 1;
+
 	if (smp_num_siblings == 1) {
 		pr_info_once("CPU0: Hyper-Threading is disabled\n");
-		goto out;
+		return;
 	}
 
-	if (smp_num_siblings <= 1)
-		goto out;
-
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
 

@@ -700,15 +699,6 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
 				       ((1 << core_bits) - 1);
-
-out:
-	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-			c->phys_proc_id);
-		pr_info("CPU: Processor Core ID: %d\n",
-			c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 }
 

@@ -33,7 +33,6 @@ int detect_extended_topology(struct cpui
 	unsigned int eax, ebx, ecx, edx, sub_index;
 	unsigned int ht_mask_width, core_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
-	static bool printed;
 
 	if (c->cpuid_level < 0xb)
 		return -1;

@@ -86,15 +85,6 @@ int detect_extended_topology(struct cpui
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
-
-	if (!printed) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-		       c->phys_proc_id);
-		if (c->x86_max_cores > 1)
-			pr_info("CPU: Processor Core ID: %d\n",
-			       c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 	return 0;
 }

@@ -857,10 +857,6 @@ static void init_amd(struct cpuinfo_x86
 		srat_detect_node(c);
 	}
 
-#ifdef CONFIG_X86_32
-	detect_ht(c);
-#endif
-
 	init_amd_cacheinfo(c);
 
 	if (c->x86 >= 0xf)

@@ -661,32 +661,36 @@ static void cpu_detect_tlb(struct cpuinf
 		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
 }
 
-void detect_ht(struct cpuinfo_x86 *c)
+int detect_ht_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
-	int index_msb, core_bits;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
-		return;
+		return -1;
 
 	cpuid(1, &eax, &ebx, &ecx, &edx);
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
+	if (smp_num_siblings == 1)
+		pr_info_once("CPU0: Hyper-Threading is disabled\n");
+#endif
+	return 0;
+}
 
-	if (!smp_num_siblings)
-		smp_num_siblings = 1;
+void detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	int index_msb, core_bits;
 
-	if (smp_num_siblings == 1) {
-		pr_info_once("CPU0: Hyper-Threading is disabled\n");
+	if (detect_ht_early(c) < 0)
 		return;
-	}
 
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);

@@ -56,6 +56,7 @@ extern void init_amd_cacheinfo(struct cp
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
 extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern int detect_ht_early(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);

@@ -55,6 +55,7 @@ extern void init_intel_cacheinfo(struct
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
 extern int detect_extended_topology(struct cpuinfo_x86 *c);
 extern int detect_ht_early(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);

@@ -22,17 +22,10 @@
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-/*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
- * exists, use it for populating initial_apicid and cpu topology
- * detection.
- */
-int detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
-	unsigned int core_select_mask, core_level_siblings;
+	unsigned int eax, ebx, ecx, edx;
 
 	if (c->cpuid_level < 0xb)
 		return -1;

@@ -51,10 +44,30 @@ int detect_extended_topology(struct cpui
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
 	c->initial_apicid = edx;
+	smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+#endif
+	return 0;
+}
+
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+int detect_extended_topology(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int core_select_mask, core_level_siblings;
+
+	if (detect_extended_topology_early(c) < 0)
+		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 

@@ -301,6 +301,13 @@ static void early_init_intel(struct cpui
 	}
 
 	check_mpx_erratum(c);
+
+	/*
+	 * Get the number of SMT siblings early from the extended topology
+	 * leaf, if available. Otherwise try the legacy SMT detection.
+	 */
+	if (detect_extended_topology_early(c) < 0)
+		detect_ht_early(c);
 }
 
 #ifdef CONFIG_X86_32

@@ -850,12 +850,9 @@ static void init_amd(struct cpuinfo_x86
 
 	cpu_detect_cache_sizes(c);
 
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level >= 0x80000008) {
-		amd_detect_cmp(c);
-		amd_get_topology(c);
-		srat_detect_node(c);
-	}
+	amd_detect_cmp(c);
+	amd_get_topology(c);
+	srat_detect_node(c);
 
 	init_amd_cacheinfo(c);
 

@@ -315,6 +315,17 @@ static void legacy_fixup_core_id(struct
 	c->cpu_core_id %= cus_per_node;
 }
 
+
+static void amd_get_topology_early(struct cpuinfo_x86 *c)
+{
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+	}
+}
+
 /*
  * Fixup core topology information for
  * (1) AMD multi-node processors

@@ -683,6 +694,8 @@ static void early_init_amd(struct cpuinf
 		set_cpu_bug(c, X86_BUG_AMD_E400);
 
 	early_detect_mem_encrypt(c);
+
+	amd_get_topology_early(c);
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)

@@ -891,7 +891,15 @@ unsigned long max_swapfile_size(void)
 
 	if (boot_cpu_has_bug(X86_BUG_L1TF)) {
 		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
-		pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages);
+		unsigned long l1tf_limit = l1tf_pfn_limit() + 1;
+		/*
+		 * We encode swap offsets also with 3 bits below those for pfn
+		 * which makes the usable limit higher.
+		 */
+#ifdef CONFIG_X86_64
+		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
+#endif
+		pages = min_t(unsigned long, l1tf_limit, pages);
 	}
 	return pages;
 }

@@ -342,6 +342,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 

@@ -318,12 +318,8 @@ static void legacy_fixup_core_id(struct
 
 static void amd_get_topology_early(struct cpuinfo_x86 *c)
 {
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		u32 eax, ebx, ecx, edx;
-
-		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
-	}
+	if (cpu_has(c, X86_FEATURE_TOPOEXT))
+		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
 }
 
 /*

@@ -345,7 +341,6 @@ static void amd_get_topology(struct cpui
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
 		node_id  = ecx & 0xff;
-		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
 
 		if (c->x86 == 0x15)
 			c->cu_id = ebx & 0xff;

@@ -624,6 +619,7 @@ clear_sev:
 
 static void early_init_amd(struct cpuinfo_x86 *c)
 {
+	u64 value;
 	u32 dummy;
 
 	early_init_amd_mc(c);

@@ -695,6 +691,20 @@ static void early_init_amd(struct cpuinf
 
 	early_detect_mem_encrypt(c);
 
+	/* Re-enable TopologyExtensions if switched off by BIOS */
+	if (c->x86 == 0x15 &&
+	    (c->x86_model >= 0x10 && c->x86_model <= 0x6f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+
+		if (msr_set_bit(0xc0011005, 54) > 0) {
+			rdmsrl(0xc0011005, value);
+			if (value & BIT_64(54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+			}
+		}
+	}
+
 	amd_get_topology_early(c);
 }
 

@@ -787,19 +797,6 @@ static void init_amd_bd(struct cpuinfo_x
 {
 	u64 value;
 
-	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
-	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
-
-		if (msr_set_bit(0xc0011005, 54) > 0) {
-			rdmsrl(0xc0011005, value);
-			if (value & BIT_64(54)) {
-				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
-			}
-		}
-	}
-
 	/*
 	 * The way access filter has a performance penalty on some workloads.
 	 * Disable it on the affected CPUs.

@@ -241,12 +241,43 @@ static inline pud_t native_pudp_get_and_
 #endif
 
 /* Encode and de-code a swap entry */
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
+
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)			(((x).val) & 0x1f)
 #define __swp_offset(x)			((x).val >> 5)
 #define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
+
+/*
+ * Normally, __swp_entry() converts from arch-independent swp_entry_t to
+ * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
+ * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
+ * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
+ * __swp_entry_to_pte() through the following helper macro based on 64bit
+ * __swp_entry().
+ */
+#define __swp_pteval_entry(type, offset) ((pteval_t) { \
+	(~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
+
+#define __swp_entry_to_pte(x)	((pte_t){ .pte = \
+		__swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
+/*
+ * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
+ * swp_entry_t, but also has to convert it from 64bit to the 32bit
+ * intermediate representation, using the following macros based on 64bit
+ * __swp_type() and __swp_offset().
+ */
+#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
+#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
+
+#define __pte_to_swp_entry(pte)	(__swp_entry(__pteval_swp_type(pte), \
+					     __pteval_swp_offset(pte)))
 
 #define gup_get_pte gup_get_pte
 /*

@@ -896,7 +896,7 @@ unsigned long max_swapfile_size(void)
 		 * We encode swap offsets also with 3 bits below those for pfn
 		 * which makes the usable limit higher.
 		 */
-#ifdef CONFIG_X86_64
+#if CONFIG_PGTABLE_LEVELS > 2
 		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
 #endif
 		pages = min_t(unsigned long, l1tf_limit, pages);

@@ -191,21 +191,21 @@ static inline u64 protnone_mask(u64 val)
 
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	unsigned long pfn = pte_val(pte);
+	phys_addr_t pfn = pte_val(pte);
 	pfn ^= protnone_mask(pfn);
 	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	unsigned long pfn = pmd_val(pmd);
+	phys_addr_t pfn = pmd_val(pmd);
 	pfn ^= protnone_mask(pfn);
 	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	unsigned long pfn = pud_val(pud);
+	phys_addr_t pfn = pud_val(pud);
 	pfn ^= protnone_mask(pfn);
 	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }

@@ -555,7 +555,7 @@ static inline pgprotval_t check_pgprot(p
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PTE_PFN_MASK;
 	return __pte(pfn | check_pgprot(pgprot));

@@ -563,7 +563,7 @@ static inline pte_t pfn_pte(unsigned lon
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PHYSICAL_PMD_PAGE_MASK;
 	return __pmd(pfn | check_pgprot(pgprot));

@@ -571,7 +571,7 @@ static inline pmd_t pfn_pmd(unsigned lon
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
-	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PHYSICAL_PUD_PAGE_MASK;
 	return __pud(pfn | check_pgprot(pgprot));

@@ -504,10 +504,8 @@ extern int default_check_phys_apicid_pre
 
 #ifdef CONFIG_SMP
 bool apic_id_is_primary_thread(unsigned int id);
-bool apic_id_disabled(unsigned int id);
 #else
 static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
-static inline bool apic_id_disabled(unsigned int id) { return false; }
 #endif
 
 extern void irq_enter(void);

@@ -181,8 +181,7 @@ static int acpi_register_lapic(int id, u
 	}
 
 	if (!enabled) {
-		if (!apic_id_disabled(id))
-			++disabled_cpus;
+		++disabled_cpus;
 		return -EINVAL;
 	}
 

@@ -2207,16 +2207,6 @@ bool apic_id_is_primary_thread(unsigned
 	return !(apicid & mask);
 }
 
-/**
- * apic_id_disabled - Check whether APIC ID is disabled via SMT control
- * @id:	APIC ID to check
- */
-bool apic_id_disabled(unsigned int id)
-{
-	return (cpu_smt_control == CPU_SMT_FORCE_DISABLED &&
-		!apic_id_is_primary_thread(id));
-}
-
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.

@@ -2312,15 +2302,6 @@ int generic_processor_info(int apicid, i
 		return -EINVAL;
 	}
 
-	/*
-	 * If SMT is force disabled and the APIC ID belongs to
-	 * a secondary thread, ignore it.
-	 */
-	if (apic_id_disabled(apicid)) {
-		pr_info_once("Ignoring secondary SMT threads\n");
-		return -EINVAL;
-	}
-
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
 		 * x86_bios_cpu_apicid is required to have processors listed

@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	bool			booted_once;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;

@@ -342,6 +343,40 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_control = CPU_SMT_DISABLED;
+	if (str && !strcmp(str, "force")) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	}
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	if (cpu_smt_control == CPU_SMT_ENABLED)
+		return true;
+
+	if (topology_is_primary_thread(cpu))
+		return true;
+
+	/*
+	 * On x86 it's required to boot all logical CPUs at least once so
+	 * that the init code can get a chance to set CR4.MCE on each
+	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * core will shutdown the machine.
+	 */
+	return !per_cpu(cpuhp_state, cpu).booted_once;
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {

@@ -422,6 +457,16 @@ static int bringup_wait_for_ap(unsigned
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
 
+	/*
+	 * SMT soft disabling on X86 requires to bring the CPU out of the
+	 * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit.  The
+	 * CPU marked itself as booted_once in cpu_notify_starting() so the
+	 * cpu_smt_allowed() check will now return false if this is not the
+	 * primary sibling.
+	 */
+	if (!cpu_smt_allowed(cpu))
+		return -ECANCELED;
+
 	if (st->target <= CPUHP_AP_ONLINE_IDLE)
 		return 0;
 

@@ -933,29 +978,6 @@ EXPORT_SYMBOL(cpu_down);
 #define takedown_cpu		NULL
 #endif /*CONFIG_HOTPLUG_CPU*/
 
-#ifdef CONFIG_HOTPLUG_SMT
-enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
-
-static int __init smt_cmdline_disable(char *str)
-{
-	cpu_smt_control = CPU_SMT_DISABLED;
-	if (str && !strcmp(str, "force")) {
-		pr_info("SMT: Force disabled\n");
-		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
-	}
-	return 0;
-}
-early_param("nosmt", smt_cmdline_disable);
-
-static inline bool cpu_smt_allowed(unsigned int cpu)
-{
-	return cpu_smt_control == CPU_SMT_ENABLED ||
-		topology_is_primary_thread(cpu);
-}
-#else
-static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
-#endif
-
 /**
  * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
  * @cpu: cpu that just started

@@ -970,6 +992,7 @@ void notify_cpu_starting(unsigned int cp
 	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
+	st->booted_once = true;
 	while (st->state < target) {
 		st->state++;
 		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);

@@ -2180,5 +2203,6 @@ void __init boot_cpu_init(void)
  */
 void __init boot_cpu_hotplug_init(void)
 {
-	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+	this_cpu_write(cpuhp_state.booted_once, true);
+	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }

@@ -71,6 +71,9 @@ static const struct x86_cpu_id vmx_cpu_i
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
 
+static bool __read_mostly nosmt;
+module_param(nosmt, bool, S_IRUGO);
+
 static bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
 

@@ -10403,10 +10406,20 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
+#define L1TF_MSG "SMT enabled with L1TF CPU bug present. Refer to CVE-2018-3620 for details.\n"
+
 static int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
 		kvm->arch.pause_in_guest = true;
+
+	if (boot_cpu_has(X86_BUG_L1TF) && cpu_smt_control == CPU_SMT_ENABLED) {
+		if (nosmt) {
+			pr_err(L1TF_MSG);
+			return -EOPNOTSUPP;
+		}
+		pr_warn(L1TF_MSG);
+	}
 	return 0;
 }
 

@@ -345,6 +345,7 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 
 #ifdef CONFIG_HOTPLUG_SMT
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+EXPORT_SYMBOL_GPL(cpu_smt_control);
 
 static int __init smt_cmdline_disable(char *str)
 {

77 lines not on this page · raw message

@@ -9599,6 +9599,46 @@ static int vmx_handle_exit(struct kvm_vc
 	}
 }
 
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static void __maybe_unused vmx_l1d_flush(void)
+{
+	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+
+	asm volatile(
+		/* First ensure the pages are in the TLB */
+		"xorl	%%eax, %%eax\n"
+		".Lpopulate_tlb:\n\t"
+		"movzbl	(%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$4096, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lpopulate_tlb\n\t"
+		"xorl	%%eax, %%eax\n\t"
+		"cpuid\n\t"
+		/* Now fill the cache */
+		"xorl	%%eax, %%eax\n"
+		".Lfill_cache:\n"
+		"movzbl	(%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$64, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lfill_cache\n\t"
+		"lfence\n"
+		:: [empty_zp] "r" (vmx_l1d_flush_pages),
+		    [size] "r" (size)
+		: "eax", "ebx", "ecx", "edx");
+}
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);

@@ -13198,13 +13238,29 @@ static struct kvm_x86_ops vmx_x86_ops __
 	.enable_smi_window = enable_smi_window,
 };
 
-static void __init vmx_setup_l1d_flush(void)
+static int __init vmx_setup_l1d_flush(void)
 {
+	struct page *page;
+
 	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
 	    !boot_cpu_has_bug(X86_BUG_L1TF))
-		return;
+		return 0;
+
+	page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+	if (!page)
+		return -ENOMEM;
 
+	vmx_l1d_flush_pages = page_address(page);
 	static_branch_enable(&vmx_l1d_should_flush);
+	return 0;
+}
+
+static void vmx_free_l1d_flush_pages(void)
+{
+	if (vmx_l1d_flush_pages) {
+		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+		vmx_l1d_flush_pages = NULL;
+	}
 }
 
 static int __init vmx_init(void)

@@ -13240,12 +13296,16 @@ static int __init vmx_init(void)
 	}
 #endif
 
-	vmx_setup_l1d_flush();
+	r = vmx_setup_l1d_flush();
+	if (r)
+		return r;
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
-                     __alignof__(struct vcpu_vmx), THIS_MODULE);
-	if (r)
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
+	if (r) {
+		vmx_free_l1d_flush_pages();
 		return r;
+	}
 
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,

@@ -13287,6 +13347,7 @@ static void __exit vmx_exit(void)
 		static_branch_disable(&enable_evmcs);
 	}
 #endif
+	vmx_free_l1d_flush_pages();
 }
 
 module_init(vmx_init)

@@ -76,6 +76,12 @@
 						    * control required.
 						    */
 
+#define MSR_IA32_FLUSH_CMD		0x0000010b
+#define L1D_FLUSH			(1 << 0)   /*
+						    * Writeback and invalidate the
+						    * L1 data cache.
+						    */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 

@@ -9616,6 +9616,11 @@ static void __maybe_unused vmx_l1d_flush
 {
 	int size = PAGE_SIZE << L1D_CACHE_ORDER;
 
+	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		return;
+	}
+
 	asm volatile(
 		/* First ensure the pages are in the TLB */
 		"xorl	%%eax, %%eax\n"

@@ -13246,11 +13251,13 @@ static int __init vmx_setup_l1d_flush(vo
 	    !boot_cpu_has_bug(X86_BUG_L1TF))
 		return 0;
 
-	page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
-	if (!page)
-		return -ENOMEM;
+	if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+		if (!page)
+			return -ENOMEM;
+		vmx_l1d_flush_pages = page_address(page);
+	}
 
-	vmx_l1d_flush_pages = page_address(page);
 	static_branch_enable(&vmx_l1d_should_flush);
 	return 0;
 }

@@ -713,6 +713,9 @@ struct kvm_vcpu_arch {
 
 	/* be preempted when it's in kernel-mode(cpl=0) */
 	bool preempted_in_kernel;
+
+	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
+	bool l1tf_flush_l1d;
 };
 
 struct kvm_lpage_info {

@@ -881,6 +884,7 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 	u64 irq_window_exits;
 	u64 nmi_window_exits;
+	u64 l1d_flush;
 	u64 halt_exits;
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;

@@ -3840,6 +3840,7 @@ int kvm_handle_page_fault(struct kvm_vcp
 {
 	int r = 1;
 
+	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
 		trace_kvm_page_fault(fault_address, error_code);

@@ -9612,9 +9612,20 @@ static int vmx_handle_exit(struct kvm_vc
 #define L1D_CACHE_ORDER 4
 static void *vmx_l1d_flush_pages;
 
-static void __maybe_unused vmx_l1d_flush(void)
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 {
 	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+	bool always;
+
+	/*
+	 * If the mitigation mode is 'flush always', keep the flush bit
+	 * set, otherwise clear it. It gets set again either from
+	 * vcpu_run() or from one of the unsafe VMEXIT handlers.
+	 */
+	always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+	vcpu->arch.l1tf_flush_l1d = always;
+
+	vcpu->stat.l1d_flush++;
 
 	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
 		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);

@@ -9883,6 +9894,7 @@ static void vmx_handle_external_intr(str
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
+		vcpu->arch.l1tf_flush_l1d = true;
 	}
 }
 STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);

@@ -10140,6 +10152,11 @@ static void __noclone vmx_vcpu_run(struc
 	evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
 		(unsigned long)&current_evmcs->host_rsp : 0;
 
+	if (static_branch_unlikely(&vmx_l1d_should_flush)) {
+		if (vcpu->arch.l1tf_flush_l1d)
+			vmx_l1d_flush(vcpu);
+	}
+
 	asm(
 		/* Store host registers */
 		"push %%" _ASM_DX "; push %%" _ASM_BP ";"

@@ -12005,6 +12022,9 @@ static int nested_vmx_run(struct kvm_vcp
 		return ret;
 	}
 
+	/* Hide L1D cache contents from the nested guest.  */
+	vmx->vcpu.arch.l1tf_flush_l1d = true;
+
 	/*
 	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
 	 * by event injection, halt vcpu.

@@ -195,6 +195,7 @@ struct kvm_stats_debugfs_item debugfs_en
 	{ "irq_injections", VCPU_STAT(irq_injections) },
 	{ "nmi_injections", VCPU_STAT(nmi_injections) },
 	{ "req_event", VCPU_STAT(req_event) },
+	{ "l1d_flush", VCPU_STAT(l1d_flush) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
 	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },

@@ -4876,6 +4877,9 @@ static int emulator_write_std(struct x86
 int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
 				unsigned int bytes, struct x86_exception *exception)
 {
+	/* kvm_write_guest_virt_system can pull in tons of pages. */
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }

@@ -6052,6 +6056,8 @@ int x86_emulate_instruction(struct kvm_v
 	bool writeback = true;
 	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	/*
 	 * Clear write_fault_to_shadow_pgtable here to ensure it is
 	 * never reused.

@@ -7581,6 +7587,7 @@ static int vcpu_run(struct kvm_vcpu *vcp
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
 		if (kvm_vcpu_running(vcpu)) {

@@ -8700,6 +8707,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcp
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	vcpu->arch.l1tf_flush_l1d = true;
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 

@@ -808,6 +808,11 @@ static inline int pi_test_sn(struct pi_d
 			(unsigned long *)&pi_desc->control);
 }
 
+struct vmx_msrs {
+	unsigned int		nr;
+	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;

@@ -841,9 +846,8 @@ struct vcpu_vmx {
 	struct loaded_vmcs   *loaded_vmcs;
 	bool                  __launched; /* temporary, used in vmx_vcpu_run */
 	struct msr_autoload {
-		unsigned nr;
-		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
-		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+		struct vmx_msrs guest;
+		struct vmx_msrs host;
 	} msr_autoload;
 	struct {
 		int           loaded;

@@ -2451,18 +2455,18 @@ static void clear_atomic_switch_msr(stru
 		}
 		break;
 	}
-
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
+	for (i = 0; i < m->guest.nr; ++i)
+		if (m->guest.val[i].index == msr)
 			break;
 
-	if (i == m->nr)
+	if (i == m->guest.nr)
 		return;
-	--m->nr;
-	m->guest[i] = m->guest[m->nr];
-	m->host[i] = m->host[m->nr];
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+	--m->guest.nr;
+	--m->host.nr;
+	m->guest.val[i] = m->guest.val[m->guest.nr];
+	m->host.val[i] = m->host.val[m->host.nr];
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 }
 
 static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,

@@ -2514,24 +2518,25 @@ static void add_atomic_switch_msr(struct
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
+	for (i = 0; i < m->guest.nr; ++i)
+		if (m->guest.val[i].index == msr)
 			break;
 
 	if (i == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i == m->nr) {
-		++m->nr;
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+	} else if (i == m->guest.nr) {
+		++m->guest.nr;
+		++m->host.nr;
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 	}
 
-	m->guest[i].index = msr;
-	m->guest[i].value = guest_val;
-	m->host[i].index = msr;
-	m->host[i].value = host_val;
+	m->guest.val[i].index = msr;
+	m->guest.val[i].value = guest_val;
+	m->host.val[i].index = msr;
+	m->host.val[i].value = host_val;
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)

@@ -6325,9 +6330,9 @@ static void vmx_vcpu_setup(struct vcpu_v
 
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);

@@ -11383,10 +11388,10 @@ static void prepare_vmcs02_full(struct k
 	 * Set the MSR load/store lists to match L0's settings.
 	 */
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	set_cr4_guest_host_mask(vmx);
 

@@ -12545,8 +12550,8 @@ static void nested_vmx_vmexit(struct kvm
 	vmx_segment_cache_clear(vmx);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,

@@ -2432,9 +2432,20 @@ static void clear_atomic_switch_msr_spec
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+	unsigned int i;
+
+	for (i = 0; i < m->nr; ++i) {
+		if (m->val[i].index == msr)
+			return i;
+	}
+	return -ENOENT;
+}
+
 static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 {
-	unsigned i;
+	int i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {

@@ -2455,11 +2466,8 @@ static void clear_atomic_switch_msr(stru
 		}
 		break;
 	}
-	for (i = 0; i < m->guest.nr; ++i)
-		if (m->guest.val[i].index == msr)
-			break;
-
-	if (i == m->guest.nr)
+	i = find_msr(&m->guest, msr);
+	if (i < 0)
 		return;
 	--m->guest.nr;
 	--m->host.nr;

@@ -2483,7 +2491,7 @@ static void add_atomic_switch_msr_specia
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 				  u64 guest_val, u64 host_val)
 {
-	unsigned i;
+	int i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {

@@ -2518,16 +2526,13 @@ static void add_atomic_switch_msr(struct
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	for (i = 0; i < m->guest.nr; ++i)
-		if (m->guest.val[i].index == msr)
-			break;
-
+	i = find_msr(&m->guest, msr);
 	if (i == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i == m->guest.nr) {
-		++m->guest.nr;
+	} else if (i < 0) {
+		i = m->guest.nr++;
 		++m->host.nr;
 		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);