Merge tag 'x86-urgent-2020-08-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Misc fixes and small updates all around the place:

   - Fix mitigation state sysfs output

   - Fix an FPU xstate/sxave code assumption bug triggered by
     Architectural LBR support

   - Fix Lightning Mountain SoC TSC frequency enumeration bug

   - Fix kexec debug output

   - Fix kexec memory range assumption bug

   - Fix a boundary condition in the crash kernel code

   - Optimize porgatory.ro generation a bit

   - Enable ACRN guests to use X2APIC mode

   - Reduce a __text_poke() IRQs-off critical section for the benefit of
     PREEMPT_RT"

* tag 'x86-urgent-2020-08-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/alternatives: Acquire pte lock with interrupts enabled
  x86/bugs/multihit: Fix mitigation reporting when VMX is not in use
  x86/fpu/xstate: Fix an xstate size check warning with architectural LBRs
  x86/purgatory: Don't generate debug info for purgatory.ro
  x86/tsr: Fix tsc frequency enumeration bug on Lightning Mountain SoC
  kexec_file: Correctly output debugging information for the PT_LOAD ELF header
  kexec: Improve & fix crash_exclude_mem_range() to handle overlapping ranges
  x86/crash: Correct the address boundary of function parameters
  x86/acrn: Remove redundant chars from ACRN signature
  x86/acrn: Allow ACRN guest to use X2APIC mode

Documentation/admin-guide/hw-vuln/multihit.rst

@@ -80,6 +80,10 @@ The possible values in this file are:
        - The processor is not vulnerable.
      * - KVM: Mitigation: Split huge pages
        - Software changes mitigate this issue.
+     * - KVM: Mitigation: VMX unsupported
+       - KVM is not vulnerable because Virtual Machine Extensions (VMX) is not supported.
+     * - KVM: Mitigation: VMX disabled
+       - KVM is not vulnerable because Virtual Machine Extensions (VMX) is disabled.
      * - KVM: Vulnerable
        - The processor is vulnerable, but no mitigation enabled
 

arch/x86/kernel/alternative.c

@@ -875,8 +875,6 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));
 
-	local_irq_save(flags);
-
 	/*
 	 * Map the page without the global bit, as TLB flushing is done with
 	 * flush_tlb_mm_range(), which is intended for non-global PTEs.
@@ -893,6 +891,8 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	VM_BUG_ON(!ptep);
 
+	local_irq_save(flags);
+
 	pte = mk_pte(pages[0], pgprot);
 	set_pte_at(poking_mm, poking_addr, ptep, pte);
 
@@ -942,8 +942,8 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	 */
 	BUG_ON(memcmp(addr, opcode, len));
 
-	pte_unmap_unlock(ptep, ptl);
 	local_irq_restore(flags);
+	pte_unmap_unlock(ptep, ptl);
 	return addr;
 }
 

arch/x86/kernel/cpu/acrn.c

@@ -11,14 +11,15 @@
 
 #include <linux/interrupt.h>
 #include <asm/apic.h>
+#include <asm/cpufeatures.h>
 #include <asm/desc.h>
 #include <asm/hypervisor.h>
 #include <asm/idtentry.h>
 #include <asm/irq_regs.h>
 
-static uint32_t __init acrn_detect(void)
+static u32 __init acrn_detect(void)
 {
-	return hypervisor_cpuid_base("ACRNACRNACRN\0\0", 0);
+	return hypervisor_cpuid_base("ACRNACRNACRN", 0);
 }
 
 static void __init acrn_init_platform(void)
@@ -29,12 +30,7 @@ static void __init acrn_init_platform(void)
 
 static bool acrn_x2apic_available(void)
 {
-	/*
-	 * x2apic is not supported for now. Future enablement will have to check
-	 * X86_FEATURE_X2APIC to determine whether x2apic is supported in the
-	 * guest.
-	 */
-	return false;
+	return boot_cpu_has(X86_FEATURE_X2APIC);
 }
 
 static void (*acrn_intr_handler)(void);

arch/x86/kernel/cpu/bugs.c

@@ -31,6 +31,7 @@
 #include <asm/intel-family.h>
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
+#include <asm/tlbflush.h>
 
 #include "cpu.h"
 
@@ -1549,7 +1550,12 @@ static ssize_t l1tf_show_state(char *buf)
 
 static ssize_t itlb_multihit_show_state(char *buf)
 {
-	if (itlb_multihit_kvm_mitigation)
+	if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) ||
+	    !boot_cpu_has(X86_FEATURE_VMX))
+		return sprintf(buf, "KVM: Mitigation: VMX unsupported\n");
+	else if (!(cr4_read_shadow() & X86_CR4_VMXE))
+		return sprintf(buf, "KVM: Mitigation: VMX disabled\n");
+	else if (itlb_multihit_kvm_mitigation)
 		return sprintf(buf, "KVM: Mitigation: Split huge pages\n");
 	else
 		return sprintf(buf, "KVM: Vulnerable\n");

arch/x86/kernel/crash.c

@@ -230,7 +230,7 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
 	int ret = 0;
 
 	/* Exclude the low 1M because it is always reserved */
-	ret = crash_exclude_mem_range(cmem, 0, 1<<20);
+	ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1);
 	if (ret)
 		return ret;
 

arch/x86/kernel/fpu/xstate.c

@@ -611,6 +611,10 @@ static void check_xstate_against_struct(int nr)
  * This essentially double-checks what the cpu told us about
  * how large the XSAVE buffer needs to be.  We are recalculating
  * it to be safe.
+ *
+ * Dynamic XSAVE features allocate their own buffers and are not
+ * covered by these checks. Only the size of the buffer for task->fpu
+ * is checked here.
  */
 static void do_extra_xstate_size_checks(void)
 {
@@ -673,6 +677,33 @@ static unsigned int __init get_xsaves_size(void)
 	return ebx;
 }
 
+/*
+ * Get the total size of the enabled xstates without the dynamic supervisor
+ * features.
+ */
+static unsigned int __init get_xsaves_size_no_dynamic(void)
+{
+	u64 mask = xfeatures_mask_dynamic();
+	unsigned int size;
+
+	if (!mask)
+		return get_xsaves_size();
+
+	/* Disable dynamic features. */
+	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+
+	/*
+	 * Ask the hardware what size is required of the buffer.
+	 * This is the size required for the task->fpu buffer.
+	 */
+	size = get_xsaves_size();
+
+	/* Re-enable dynamic features so XSAVES will work on them again. */
+	wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+
+	return size;
+}
+
 static unsigned int __init get_xsave_size(void)
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -710,7 +741,7 @@ static int __init init_xstate_size(void)
 	xsave_size = get_xsave_size();
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		possible_xstate_size = get_xsaves_size();
+		possible_xstate_size = get_xsaves_size_no_dynamic();
 	else
 		possible_xstate_size = xsave_size;
 

arch/x86/kernel/tsc_msr.c

@@ -134,10 +134,15 @@ static const struct freq_desc freq_desc_ann = {
 	.mask = 0x0f,
 };
 
-/* 24 MHz crystal? : 24 * 13 / 4 = 78 MHz */
+/*
+ * 24 MHz crystal? : 24 * 13 / 4 = 78 MHz
+ * Frequency step for Lightning Mountain SoC is fixed to 78 MHz,
+ * so all the frequency entries are 78000.
+ */
 static const struct freq_desc freq_desc_lgm = {
 	.use_msr_plat = true,
-	.freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 },
+	.freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000,
+		   78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 },
 	.mask = 0x0f,
 };
 

arch/x86/purgatory/Makefile

@@ -32,7 +32,7 @@ KCOV_INSTRUMENT := n
 # make up the standalone purgatory.ro
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
-PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
+PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0
 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
 PURGATORY_CFLAGS += -fno-stack-protector
 
@@ -64,6 +64,9 @@ CFLAGS_sha256.o			+= $(PURGATORY_CFLAGS)
 CFLAGS_REMOVE_string.o		+= $(PURGATORY_CFLAGS_REMOVE)
 CFLAGS_string.o			+= $(PURGATORY_CFLAGS)
 
+AFLAGS_REMOVE_setup-x86_$(BITS).o	+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_entry64.o			+= -Wa,-gdwarf-2
+
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
 

kernel/kexec_file.c

@@ -1169,24 +1169,26 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 			    unsigned long long mstart, unsigned long long mend)
 {
 	int i, j;
-	unsigned long long start, end;
+	unsigned long long start, end, p_start, p_end;
 	struct crash_mem_range temp_range = {0, 0};
 
 	for (i = 0; i < mem->nr_ranges; i++) {
 		start = mem->ranges[i].start;
 		end = mem->ranges[i].end;
+		p_start = mstart;
+		p_end = mend;
 
 		if (mstart > end || mend < start)
 			continue;
 
 		/* Truncate any area outside of range */
 		if (mstart < start)
-			mstart = start;
+			p_start = start;
 		if (mend > end)
-			mend = end;
+			p_end = end;
 
 		/* Found completely overlapping range */
-		if (mstart == start && mend == end) {
+		if (p_start == start && p_end == end) {
 			mem->ranges[i].start = 0;
 			mem->ranges[i].end = 0;
 			if (i < mem->nr_ranges - 1) {
@@ -1197,20 +1199,29 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 					mem->ranges[j].end =
 							mem->ranges[j+1].end;
 				}
+
+				/*
+				 * Continue to check if there are another overlapping ranges
+				 * from the current position because of shifting the above
+				 * mem ranges.
+				 */
+				i--;
+				mem->nr_ranges--;
+				continue;
 			}
 			mem->nr_ranges--;
 			return 0;
 		}
 
-		if (mstart > start && mend < end) {
+		if (p_start > start && p_end < end) {
 			/* Split original range */
-			mem->ranges[i].end = mstart - 1;
-			temp_range.start = mend + 1;
+			mem->ranges[i].end = p_start - 1;
+			temp_range.start = p_end + 1;
 			temp_range.end = end;
-		} else if (mstart != start)
-			mem->ranges[i].end = mstart - 1;
+		} else if (p_start != start)
+			mem->ranges[i].end = p_start - 1;
 		else
-			mem->ranges[i].start = mend + 1;
+			mem->ranges[i].start = p_end + 1;
 		break;
 	}
 
@@ -1247,7 +1258,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	unsigned long long notes_addr;
 	unsigned long mstart, mend;
 
-	/* extra phdr for vmcoreinfo elf note */
+	/* extra phdr for vmcoreinfo ELF note */
 	nr_phdr = nr_cpus + 1;
 	nr_phdr += mem->nr_ranges;
 
@@ -1255,7 +1266,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
 	 * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
 	 * I think this is required by tools like gdb. So same physical
-	 * memory will be mapped in two elf headers. One will contain kernel
+	 * memory will be mapped in two ELF headers. One will contain kernel
 	 * text virtual addresses and other will have __va(physical) addresses.
 	 */
 
@@ -1282,7 +1293,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
 	ehdr->e_phentsize = sizeof(Elf64_Phdr);
 
-	/* Prepare one phdr of type PT_NOTE for each present cpu */
+	/* Prepare one phdr of type PT_NOTE for each present CPU */
 	for_each_present_cpu(cpu) {
 		phdr->p_type = PT_NOTE;
 		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
@@ -1324,10 +1335,10 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
 		phdr->p_align = 0;
 		ehdr->e_phnum++;
-		phdr++;
-		pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+		pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
 			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
 			ehdr->e_phnum, phdr->p_offset);
+		phdr++;
 	}
 
 	*addr = buf;