summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig4
-rw-r--r--arch/x86/kernel/acpi/boot.c2
-rw-r--r--arch/x86/kernel/alternative.c14
-rw-r--r--arch/x86/kernel/head_64.S16
-rw-r--r--arch/x86/kvm/svm/sev.c19
-rw-r--r--arch/x86/kvm/svm/svm.c1
-rw-r--r--arch/x86/kvm/svm/svm.h2
-rw-r--r--arch/x86/lib/csum-partial_64.c105
-rw-r--r--arch/x86/xen/Kconfig1
9 files changed, 88 insertions, 76 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3762f41bb092..1566748f16c4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2072,7 +2072,7 @@ config ARCH_SUPPORTS_KEXEC
def_bool y
config ARCH_SUPPORTS_KEXEC_FILE
- def_bool X86_64 && CRYPTO && CRYPTO_SHA256
+ def_bool X86_64
config ARCH_SELECTS_KEXEC_FILE
def_bool y
@@ -2080,7 +2080,7 @@ config ARCH_SELECTS_KEXEC_FILE
select HAVE_IMA_KEXEC if IMA
config ARCH_SUPPORTS_KEXEC_PURGATORY
- def_bool KEXEC_FILE
+ def_bool y
config ARCH_SUPPORTS_KEXEC_SIG
def_bool y
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1a0dd80d81ac..85a3ce2a3666 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -293,6 +293,7 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
processor->processor_id, /* ACPI ID */
processor->lapic_flags & ACPI_MADT_ENABLED);
+ has_lapic_cpus = true;
return 0;
}
@@ -1134,7 +1135,6 @@ static int __init acpi_parse_madt_lapic_entries(void)
if (!count) {
count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
acpi_parse_lapic, MAX_LOCAL_APIC);
- has_lapic_cpus = count > 0;
x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
acpi_parse_x2apic, MAX_LOCAL_APIC);
}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 49c2a62ba5e4..183d42302243 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -256,6 +256,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
}
}
+static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ optimize_nops(instr, len);
+ sync_core();
+ local_irq_restore(flags);
+}
+
/*
* In this context, "source" is where the instructions are placed in the
* section .altinstr_replacement, for example during kernel build by the
@@ -439,7 +449,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
* patch if feature is *NOT* present.
*/
if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
- optimize_nops(instr, a->instrlen);
+ optimize_nops_inplace(instr, a->instrlen);
continue;
}
@@ -1756,8 +1766,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode,
} else {
local_irq_save(flags);
memcpy(addr, opcode, len);
- local_irq_restore(flags);
sync_core();
+ local_irq_restore(flags);
/*
* Could also do a CLFLUSH here to speed up CPU recovery; but
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 086a2c3aaaa0..0f8103240fda 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -255,6 +255,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
testl $X2APIC_ENABLE, %eax
jnz .Lread_apicid_msr
+#ifdef CONFIG_X86_X2APIC
+ /*
+ * If system is in X2APIC mode then MMIO base might not be
+ * mapped causing the MMIO read below to fault. Faults can't
+ * be handled at that point.
+ */
+ cmpl $0, x2apic_mode(%rip)
+ jz .Lread_apicid_mmio
+
+ /* Force the AP into X2APIC mode. */
+ orl $X2APIC_ENABLE, %eax
+ wrmsr
+ jmp .Lread_apicid_msr
+#endif
+
+.Lread_apicid_mmio:
/* Read the APIC ID from the fix-mapped MMIO space. */
movq apic_mmio_base(%rip), %rcx
addq $APIC_ID, %rcx
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4900c078045a..6ee925d66648 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
}
+
+ /*
+ * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
+ * the host/guest supports its use.
+ *
+ * guest_can_use() checks a number of requirements on the host/guest to
+ * ensure that MSR_IA32_XSS is available, but it might report true even
+ * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host
+ * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better
+ * to further check that the guest CPUID actually supports
+ * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved
+ * guests will still get intercepted and caught in the normal
+ * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths.
+ */
+ if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
+ guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
+ else
+ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
}
void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f3bb30b40876..a8bd4e909a1e 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs {
{ .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
{ .index = MSR_IA32_LASTINTFROMIP, .always = false },
{ .index = MSR_IA32_LASTINTTOIP, .always = false },
+ { .index = MSR_IA32_XSS, .always = false },
{ .index = MSR_EFER, .always = false },
{ .index = MSR_IA32_CR_PAT, .always = false },
{ .index = MSR_AMD64_SEV_ES_GHCB, .always = true },
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be67ab7fdd10..c409f934c377 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -30,7 +30,7 @@
#define IOPM_SIZE PAGE_SIZE * 3
#define MSRPM_SIZE PAGE_SIZE * 2
-#define MAX_DIRECT_ACCESS_MSRS 46
+#define MAX_DIRECT_ACCESS_MSRS 47
#define MSRPM_OFFSETS 32
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index cea25ca8b8cf..c9dae65ac01b 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -11,26 +11,23 @@
#include <asm/checksum.h>
#include <asm/word-at-a-time.h>
-static inline unsigned short from32to16(unsigned a)
+static inline __wsum csum_finalize_sum(u64 temp64)
{
- unsigned short b = a >> 16;
- asm("addw %w2,%w0\n\t"
- "adcw $0,%w0\n"
- : "=r" (b)
- : "0" (b), "r" (a));
- return b;
+ return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32);
}
-static inline __wsum csum_tail(u64 temp64, int odd)
+static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5])
{
- unsigned int result;
-
- result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
- if (unlikely(odd)) {
- result = from32to16(result);
- result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
- }
- return (__force __wsum)result;
+ asm("addq %1,%0\n\t"
+ "adcq %2,%0\n\t"
+ "adcq %3,%0\n\t"
+ "adcq %4,%0\n\t"
+ "adcq %5,%0\n\t"
+ "adcq $0,%0"
+ :"+r" (sum)
+ :"m" (m[0]), "m" (m[1]), "m" (m[2]),
+ "m" (m[3]), "m" (m[4]));
+ return sum;
}
/*
@@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd)
__wsum csum_partial(const void *buff, int len, __wsum sum)
{
u64 temp64 = (__force u64)sum;
- unsigned odd;
- odd = 1 & (unsigned long) buff;
- if (unlikely(odd)) {
- if (unlikely(len == 0))
- return sum;
- temp64 = ror32((__force u32)sum, 8);
- temp64 += (*(unsigned char *)buff << 8);
- len--;
- buff++;
+ /* Do two 40-byte chunks in parallel to get better ILP */
+ if (likely(len >= 80)) {
+ u64 temp64_2 = 0;
+ do {
+ temp64 = update_csum_40b(temp64, buff);
+ temp64_2 = update_csum_40b(temp64_2, buff + 40);
+ buff += 80;
+ len -= 80;
+ } while (len >= 80);
+
+ asm("addq %1,%0\n\t"
+ "adcq $0,%0"
+ :"+r" (temp64): "r" (temp64_2));
}
/*
- * len == 40 is the hot case due to IPv6 headers, but annotating it likely()
- * has noticeable negative affect on codegen for all other cases with
- * minimal performance benefit here.
+ * len == 40 is the hot case due to IPv6 headers, so return
+ * early for that exact case without checking the tail bytes.
*/
- if (len == 40) {
- asm("addq 0*8(%[src]),%[res]\n\t"
- "adcq 1*8(%[src]),%[res]\n\t"
- "adcq 2*8(%[src]),%[res]\n\t"
- "adcq 3*8(%[src]),%[res]\n\t"
- "adcq 4*8(%[src]),%[res]\n\t"
- "adcq $0,%[res]"
- : [res] "+r"(temp64)
- : [src] "r"(buff), "m"(*(const char(*)[40])buff));
- return csum_tail(temp64, odd);
- }
- if (unlikely(len >= 64)) {
- /*
- * Extra accumulators for better ILP in the loop.
- */
- u64 tmp_accum, tmp_carries;
-
- asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t"
- "xorl %k[tmp_carries],%k[tmp_carries]\n\t"
- "subl $64, %[len]\n\t"
- "1:\n\t"
- "addq 0*8(%[src]),%[res]\n\t"
- "adcq 1*8(%[src]),%[res]\n\t"
- "adcq 2*8(%[src]),%[res]\n\t"
- "adcq 3*8(%[src]),%[res]\n\t"
- "adcl $0,%k[tmp_carries]\n\t"
- "addq 4*8(%[src]),%[tmp_accum]\n\t"
- "adcq 5*8(%[src]),%[tmp_accum]\n\t"
- "adcq 6*8(%[src]),%[tmp_accum]\n\t"
- "adcq 7*8(%[src]),%[tmp_accum]\n\t"
- "adcl $0,%k[tmp_carries]\n\t"
- "addq $64, %[src]\n\t"
- "subl $64, %[len]\n\t"
- "jge 1b\n\t"
- "addq %[tmp_accum],%[res]\n\t"
- "adcq %[tmp_carries],%[res]\n\t"
- "adcq $0,%[res]"
- : [tmp_accum] "=&r"(tmp_accum),
- [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64),
- [len] "+r"(len), [src] "+r"(buff)
- : "m"(*(const char *)buff));
+ if (len >= 40) {
+ temp64 = update_csum_40b(temp64, buff);
+ len -= 40;
+ if (!len)
+ return csum_finalize_sum(temp64);
+ buff += 40;
}
if (len & 32) {
@@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
: [res] "+r"(temp64)
: [trail] "r"(trail));
}
- return csum_tail(temp64, odd);
+ return csum_finalize_sum(temp64);
}
EXPORT_SYMBOL(csum_partial);
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 9b1ec5d8c99c..a65fc2ae15b4 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,6 +9,7 @@ config XEN
select PARAVIRT_CLOCK
select X86_HV_CALLBACK_VECTOR
depends on X86_64 || (X86_32 && X86_PAE)
+ depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
depends on X86_LOCAL_APIC && X86_TSC
help
This is the Linux Xen port. Enabling this will allow the