7 files changed, 80 insertions, 68 deletions

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index cb4a16292aa7..40bdaea97fe7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -668,6 +668,45 @@ EXPORT_SYMBOL_GPL(l1tf_mitigation);
 enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
 
+/*
+ * These CPUs all support 44bits physical address space internally in the
+ * cache but CPUID can report a smaller number of physical address bits.
+ *
+ * The L1TF mitigation uses the top most address bit for the inversion of
+ * non present PTEs. When the installed memory reaches into the top most
+ * address bit due to memory holes, which has been observed on machines
+ * which report 36bits physical address bits and have 32G RAM installed,
+ * then the mitigation range check in l1tf_select_mitigation() triggers.
+ * This is a false positive because the mitigation is still possible due to
+ * the fact that the cache uses 44bit internally. Use the cache bits
+ * instead of the reported physical bits and adjust them on the affected
+ * machines to 44bit if the reported bits are less than 44.
+ */
+static void override_cache_bits(struct cpuinfo_x86 *c)
+{
+	if (c->x86 != 6)
+		return;
+
+	switch (c->x86_model) {
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_HASWELL_CORE:
+	case INTEL_FAM6_HASWELL_ULT:
+	case INTEL_FAM6_HASWELL_GT3E:
+	case INTEL_FAM6_BROADWELL_CORE:
+	case INTEL_FAM6_BROADWELL_GT3E:
+	case INTEL_FAM6_SKYLAKE_MOBILE:
+	case INTEL_FAM6_SKYLAKE_DESKTOP:
+	case INTEL_FAM6_KABYLAKE_MOBILE:
+	case INTEL_FAM6_KABYLAKE_DESKTOP:
+		if (c->x86_cache_bits < 44)
+			c->x86_cache_bits = 44;
+		break;
+	}
+}
+
 static void __init l1tf_select_mitigation(void)
 {
 	u64 half_pa;
@@ -675,6 +714,8 @@ static void __init l1tf_select_mitigation(void)
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return;
 
+	override_cache_bits(&boot_cpu_data);
+
 	switch (l1tf_mitigation) {
 	case L1TF_MITIGATION_OFF:
 	case L1TF_MITIGATION_FLUSH_NOWARN:
@@ -694,14 +735,13 @@ static void __init l1tf_select_mitigation(void)
 	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");
+		pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
+				half_pa);
+		pr_info("However, doing so will make a part of your RAM unusable.\n");
+		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
 		return;
 	}
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 84dee5ab745a..44c4ef3d989b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -919,6 +919,7 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
 		c->x86_phys_bits = 36;
 #endif
+	c->x86_cache_bits = c->x86_phys_bits;
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 401e8c133108..fc3c07fe7df5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -150,6 +150,9 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
 		return false;
 
+	if (c->x86 != 6)
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
 		    c->x86_stepping == spectre_bad_microcodes[i].stepping)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 374d1aa66952..ceb67cd5918f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -113,21 +113,6 @@ static inline void mce_register_injector_chain(struct notifier_block *nb)	{ }
 static inline void mce_unregister_injector_chain(struct notifier_block *nb)	{ }
 #endif
 
-#ifndef CONFIG_X86_64
-/*
- * On 32-bit systems it would be difficult to safely unmap a poison page
- * from the kernel 1:1 map because there are no non-canonical addresses that
- * we can use to refer to the address without risking a speculative access.
- * However, this isn't much of an issue because:
- * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which
- *    are only mapped into the kernel as needed
- * 2) Few people would run a 32-bit kernel on a machine that supports
- *    recoverable errors because they have too much memory to boot 32-bit.
- */
-static inline void mce_unmap_kpfn(unsigned long pfn) {}
-#define mce_unmap_kpfn mce_unmap_kpfn
-#endif
-
 struct mca_config {
 	bool dont_log_ce;
 	bool cmci_disabled;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 4b767284b7f5..953b3ce92dcc 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -42,6 +42,7 @@
 #include <linux/irq_work.h>
 #include <linux/export.h>
 #include <linux/jump_label.h>
+#include <linux/set_memory.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -50,7 +51,6 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/reboot.h>
-#include <asm/set_memory.h>
 
 #include "mce-internal.h"
 
@@ -108,10 +108,6 @@ static struct irq_work mce_irq_work;
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
 
-#ifndef mce_unmap_kpfn
-static void mce_unmap_kpfn(unsigned long pfn);
-#endif
-
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
@@ -602,7 +598,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
 		if (!memory_failure(pfn, 0))
-			mce_unmap_kpfn(pfn);
+			set_mce_nospec(pfn);
 	}
 
 	return NOTIFY_OK;
@@ -1072,38 +1068,10 @@ static int do_memory_failure(struct mce *m)
 	if (ret)
 		pr_err("Memory error not recovered");
 	else
-		mce_unmap_kpfn(m->addr >> PAGE_SHIFT);
+		set_mce_nospec(m->addr >> PAGE_SHIFT);
 	return ret;
 }
 
-#ifndef mce_unmap_kpfn
-static void mce_unmap_kpfn(unsigned long pfn)
-{
-	unsigned long decoy_addr;
-
-	/*
-	 * Unmap this page from the kernel 1:1 mappings to make sure
-	 * we don't log more errors because of speculative access to
-	 * the page.
-	 * We would like to just call:
-	 *	set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
-	 * but doing that would radically increase the odds of a
-	 * speculative access to the poison page because we'd have
-	 * the virtual address of the kernel 1:1 mapping sitting
-	 * around in registers.
-	 * Instead we get tricky.  We create a non-canonical address
-	 * that looks just like the one we want, but has bit 63 flipped.
-	 * This relies on set_memory_np() not checking whether we passed
-	 * a legal address.
-	 */
-
-	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
-
-	if (set_memory_np(decoy_addr, 1))
-		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
-}
-#endif
-
 
 /*
  * Cases where we avoid rendezvous handler timeout:
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 0624957aa068..07b5fc00b188 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	struct microcode_amd *mc_amd;
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
+	enum ucode_state ret;
 	u32 rev, dummy;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
@@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu)
 
 	/* need to apply patch? */
 	if (rev >= mc_amd->hdr.patch_id) {
-		c->microcode = rev;
-		uci->cpu_sig.rev = rev;
-		return UCODE_OK;
+		ret = UCODE_OK;
+		goto out;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
@@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu)
 			cpu, mc_amd->hdr.patch_id);
 		return UCODE_ERROR;
 	}
-	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
-		mc_amd->hdr.patch_id);
 
-	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
-	c->microcode = mc_amd->hdr.patch_id;
+	rev = mc_amd->hdr.patch_id;
+	ret = UCODE_UPDATED;
+
+	pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
 
-	return UCODE_UPDATED;
+out:
+	uci->cpu_sig.rev = rev;
+	c->microcode	 = rev;
+
+	/* Update boot_cpu_data's revision too, if we're on the BSP: */
+	if (c->cpu_index == boot_cpu_data.cpu_index)
+		boot_cpu_data.microcode = rev;
+
+	return ret;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 97ccf4c3b45b..16936a24795c 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
+	enum ucode_state ret;
 	static int prev_rev;
 	u32 rev;
 
@@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu)
 	 */
 	rev = intel_get_microcode_revision();
 	if (rev >= mc->hdr.rev) {
-		uci->cpu_sig.rev = rev;
-		c->microcode = rev;
-		return UCODE_OK;
+		ret = UCODE_OK;
+		goto out;
 	}
 
 	/*
@@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
+	ret = UCODE_UPDATED;
+
+out:
 	uci->cpu_sig.rev = rev;
-	c->microcode = rev;
+	c->microcode	 = rev;
+
+	/* Update boot_cpu_data's revision too, if we're on the BSP: */
+	if (c->cpu_index == boot_cpu_data.cpu_index)
+		boot_cpu_data.microcode = rev;
 
-	return UCODE_UPDATED;
+	return ret;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,