summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig.cpu2
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/boot/header.S14
-rw-r--r--arch/x86/boot/setup.ld6
-rw-r--r--arch/x86/entry/entry.S23
-rw-r--r--arch/x86/entry/entry_32.S3
-rw-r--r--arch/x86/entry/entry_64.S11
-rw-r--r--arch/x86/entry/entry_64_compat.S1
-rw-r--r--arch/x86/hyperv/hv_vtl.c7
-rw-r--r--arch/x86/hyperv/ivm.c65
-rw-r--r--arch/x86/include/asm/coco.h5
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/entry-common.h1
-rw-r--r--arch/x86/include/asm/hw_irq.h2
-rw-r--r--arch/x86/include/asm/jump_label.h6
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/nospec-branch.h25
-rw-r--r--arch/x86/include/asm/rmwcc.h2
-rw-r--r--arch/x86/include/asm/set_memory.h1
-rw-r--r--arch/x86/include/asm/special_insns.h2
-rw-r--r--arch/x86/include/asm/uaccess.h10
-rw-r--r--arch/x86/include/asm/vsyscall.h10
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/cpu/bugs.c15
-rw-r--r--arch/x86/kernel/cpu/common.c4
-rw-r--r--arch/x86/kernel/cpu/intel.c178
-rw-r--r--arch/x86/kernel/e820.c8
-rw-r--r--arch/x86/kernel/fpu/signal.c13
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/kvm.c3
-rw-r--r--arch/x86/kernel/nmi.c3
-rw-r--r--arch/x86/kvm/Kconfig7
-rw-r--r--arch/x86/kvm/hyperv.c50
-rw-r--r--arch/x86/kvm/hyperv.h3
-rw-r--r--arch/x86/kvm/mmu/mmu.c42
-rw-r--r--arch/x86/kvm/svm/sev.c23
-rw-r--r--arch/x86/kvm/svm/svm_ops.h6
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c2
-rw-r--r--arch/x86/kvm/vmx/run_flags.h7
-rw-r--r--arch/x86/kvm/vmx/vmenter.S9
-rw-r--r--arch/x86/kvm/vmx/vmx.c24
-rw-r--r--arch/x86/kvm/vmx/vmx_ops.h6
-rw-r--r--arch/x86/kvm/x86.c39
-rw-r--r--arch/x86/lib/getuser.S24
-rw-r--r--arch/x86/lib/putuser.S20
-rw-r--r--arch/x86/mm/fault.c9
-rw-r--r--arch/x86/mm/ident_map.c23
-rw-r--r--arch/x86/mm/maccess.c10
-rw-r--r--arch/x86/mm/numa.c21
-rw-r--r--arch/x86/mm/pat/set_memory.c24
-rw-r--r--arch/x86/xen/smp.c12
52 files changed, 532 insertions, 267 deletions
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b9224cf2ee4d..2a7279d80460 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -379,7 +379,7 @@ config X86_CMOV
config X86_MINIMUM_CPU_FAMILY
int
default "64" if X86_64
- default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+ default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
default "5" if X86_32 && X86_CMPXCHG64
default "4"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2264db14a25d..da8f3caf2781 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -112,13 +112,13 @@ ifeq ($(CONFIG_X86_32),y)
# temporary until string.h is fixed
KBUILD_CFLAGS += -ffreestanding
- ifeq ($(CONFIG_STACKPROTECTOR),y)
- ifeq ($(CONFIG_SMP),y)
+ ifeq ($(CONFIG_STACKPROTECTOR),y)
+ ifeq ($(CONFIG_SMP),y)
KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
- else
+ else
KBUILD_CFLAGS += -mstack-protector-guard=global
- endif
endif
+ endif
else
BITS := 64
UTS_MACHINE := x86_64
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b2771710ed98..a1bbedd989e4 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -106,8 +106,7 @@ extra_header_fields:
.word 0 # MinorSubsystemVersion
.long 0 # Win32VersionValue
- .long setup_size + ZO__end + pecompat_vsize
- # SizeOfImage
+ .long setup_size + ZO__end # SizeOfImage
.long salign # SizeOfHeaders
.long 0 # CheckSum
@@ -143,7 +142,7 @@ section_table:
.ascii ".setup"
.byte 0
.byte 0
- .long setup_size - salign # VirtualSize
+ .long pecompat_fstart - salign # VirtualSize
.long salign # VirtualAddress
.long pecompat_fstart - salign # SizeOfRawData
.long salign # PointerToRawData
@@ -156,8 +155,8 @@ section_table:
#ifdef CONFIG_EFI_MIXED
.asciz ".compat"
- .long 8 # VirtualSize
- .long setup_size + ZO__end # VirtualAddress
+ .long pecompat_fsize # VirtualSize
+ .long pecompat_fstart # VirtualAddress
.long pecompat_fsize # SizeOfRawData
.long pecompat_fstart # PointerToRawData
@@ -172,17 +171,16 @@ section_table:
* modes this image supports.
*/
.pushsection ".pecompat", "a", @progbits
- .balign falign
- .set pecompat_vsize, salign
+ .balign salign
.globl pecompat_fstart
pecompat_fstart:
.byte 0x1 # Version
.byte 8 # Size
.word IMAGE_FILE_MACHINE_I386 # PE machine type
.long setup_size + ZO_efi32_pe_entry # Entrypoint
+ .byte 0x0 # Sentinel
.popsection
#else
- .set pecompat_vsize, 0
.set pecompat_fstart, setup_size
#endif
.ascii ".text"
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 83bb7efad8ae..3a2d1360abb0 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -24,6 +24,9 @@ SECTIONS
.text : { *(.text .text.*) }
.text32 : { *(.text32) }
+ .pecompat : { *(.pecompat) }
+ PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
. = ALIGN(16);
.rodata : { *(.rodata*) }
@@ -36,9 +39,6 @@ SECTIONS
. = ALIGN(16);
.data : { *(.data*) }
- .pecompat : { *(.pecompat) }
- PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
-
.signature : {
setup_sig = .;
LONG(0x5a5aaa55)
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 8c8d38f0cb1d..003379049924 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -6,6 +6,9 @@
#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/msr-index.h>
+#include <asm/unwind_hints.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
.pushsection .noinstr.text, "ax"
@@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb)
EXPORT_SYMBOL_GPL(entry_ibpb);
.popsection
+
+/*
+ * Define the VERW operand that is disguised as entry code so that
+ * it can be referenced with KPTI enabled. This ensure VERW can be
+ * used late in exit-to-user path after page tables are switched.
+ */
+.pushsection .entry.text, "ax"
+
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_START_NOALIGN(mds_verw_sel)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ .word __KERNEL_DS
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_END(mds_verw_sel);
+/* For KVM */
+EXPORT_SYMBOL_GPL(mds_verw_sel);
+
+.popsection
+
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c73047bf9f4b..fba427646805 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -885,6 +885,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
BUG_IF_WRONG_CR3 no_user_check=1
popfl
popl %eax
+ CLEAR_CPU_BUFFERS
/*
* Return back to the vDSO, which will pop ecx and edx.
@@ -954,6 +955,7 @@ restore_all_switch_stack:
/* Restore user state */
RESTORE_REGS pop=4 # skip orig_eax/error_code
+ CLEAR_CPU_BUFFERS
.Lirq_return:
/*
* ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -1146,6 +1148,7 @@ SYM_CODE_START(asm_exc_nmi)
/* Not on SYSENTER stack. */
call exc_nmi
+ CLEAR_CPU_BUFFERS
jmp .Lnmi_return
.Lnmi_from_sysenter_stack:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c40f89ab1b4c..9bb485977629 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -161,6 +161,7 @@ syscall_return_via_sysret:
SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
swapgs
+ CLEAR_CPU_BUFFERS
sysretq
SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
@@ -573,6 +574,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
.Lswapgs_and_iret:
swapgs
+ CLEAR_CPU_BUFFERS
/* Assert that the IRET frame indicates user mode. */
testb $3, 8(%rsp)
jnz .Lnative_iret
@@ -723,6 +725,8 @@ native_irq_return_ldt:
*/
popq %rax /* Restore user RAX */
+ CLEAR_CPU_BUFFERS
+
/*
* RSP now points to an ordinary IRET frame, except that the page
* is read-only and RSP[31:16] are preloaded with the userspace
@@ -1450,6 +1454,12 @@ nmi_restore:
movq $0, 5*8(%rsp) /* clear "NMI executing" */
/*
+ * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like
+ * NMI in kernel after user state is restored. For an unprivileged user
+ * these conditions are hard to meet.
+ */
+
+ /*
* iretq reads the "iret" frame and exits the NMI stack in a
* single instruction. We are returning to kernel mode, so this
* cannot result in a fault. Similarly, we don't need to worry
@@ -1466,6 +1476,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore)
UNWIND_HINT_END_OF_STACK
ENDBR
mov $-ENOSYS, %eax
+ CLEAR_CPU_BUFFERS
sysretl
SYM_CODE_END(entry_SYSCALL32_ignore)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index de94e2e84ecc..eabf48c4d4b4 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
xorl %r9d, %r9d
xorl %r10d, %r10d
swapgs
+ CLEAR_CPU_BUFFERS
sysretl
SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 96e6c51515f5..cf1b78cb2d04 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -16,6 +16,11 @@
extern struct boot_params boot_params;
static struct real_mode_header hv_vtl_real_mode_header;
+static bool __init hv_vtl_msi_ext_dest_id(void)
+{
+ return true;
+}
+
void __init hv_vtl_init_platform(void)
{
pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -38,6 +43,8 @@ void __init hv_vtl_init_platform(void)
x86_platform.legacy.warm_reset = 0;
x86_platform.legacy.reserve_bios_regions = 0;
x86_platform.legacy.devices.pnpbios = 0;
+
+ x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id;
}
static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 7dcbf153ad72..768d73de0d09 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -15,6 +15,7 @@
#include <asm/io.h>
#include <asm/coco.h>
#include <asm/mem_encrypt.h>
+#include <asm/set_memory.h>
#include <asm/mshyperv.h>
#include <asm/hypervisor.h>
#include <asm/mtrr.h>
@@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
}
/*
+ * When transitioning memory between encrypted and decrypted, the caller
+ * of set_memory_encrypted() or set_memory_decrypted() is responsible for
+ * ensuring that the memory isn't in use and isn't referenced while the
+ * transition is in progress. The transition has multiple steps, and the
+ * memory is in an inconsistent state until all steps are complete. A
+ * reference while the state is inconsistent could result in an exception
+ * that can't be cleanly fixed up.
+ *
+ * But the Linux kernel load_unaligned_zeropad() mechanism could cause a
+ * stray reference that can't be prevented by the caller, so Linux has
+ * specific code to handle this case. But when the #VC and #VE exceptions
+ * routed to a paravisor, the specific code doesn't work. To avoid this
+ * problem, mark the pages as "not present" while the transition is in
+ * progress. If load_unaligned_zeropad() causes a stray reference, a normal
+ * page fault is generated instead of #VC or #VE, and the page-fault-based
+ * handlers for load_unaligned_zeropad() resolve the reference. When the
+ * transition is complete, hv_vtom_set_host_visibility() marks the pages
+ * as "present" again.
+ */
+static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+{
+ return !set_memory_np(kbuffer, pagecount);
+}
+
+/*
* hv_vtom_set_host_visibility - Set specified memory visible to host.
*
* In Isolation VM, all guest memory is encrypted from host and guest
@@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
enum hv_mem_host_visibility visibility = enc ?
VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
u64 *pfn_array;
+ phys_addr_t paddr;
+ void *vaddr;
int ret = 0;
bool result = true;
int i, pfn;
pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
- if (!pfn_array)
- return false;
+ if (!pfn_array) {
+ result = false;
+ goto err_set_memory_p;
+ }
for (i = 0, pfn = 0; i < pagecount; i++) {
- pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE);
+ /*
+ * Use slow_virt_to_phys() because the PRESENT bit has been
+ * temporarily cleared in the PTEs. slow_virt_to_phys() works
+ * without the PRESENT bit while virt_to_hvpfn() or similar
+ * does not.
+ */
+ vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE);
+ paddr = slow_virt_to_phys(vaddr);
+ pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT;
pfn++;
if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
@@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
}
}
- err_free_pfn_array:
+err_free_pfn_array:
kfree(pfn_array);
+
+err_set_memory_p:
+ /*
+ * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present()
+ * did. Do this even if there is an error earlier in this function in
+ * order to avoid leaving the memory range in a "broken" state. Setting
+ * the PRESENT bits shouldn't fail, but return an error if it does.
+ */
+ if (set_memory_p(kbuffer, pagecount))
+ result = false;
+
return result;
}
static bool hv_vtom_tlb_flush_required(bool private)
{
- return true;
+ /*
+ * Since hv_vtom_clear_present() marks the PTEs as "not present"
+ * and flushes the TLB, they can't be in the TLB. That makes the
+ * flush controlled by this function redundant, so return "false".
+ */
+ return false;
}
static bool hv_vtom_cache_flush_required(void)
@@ -608,6 +662,7 @@ void __init hv_vtom_init(void)
x86_platform.hyper.is_private_mmio = hv_is_private_mmio;
x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
+ x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present;
x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
/* Set WB as the default cache mode. */
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 6ae2d16a7613..76c310b19b11 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -10,13 +10,14 @@ enum cc_vendor {
CC_VENDOR_INTEL,
};
-extern enum cc_vendor cc_vendor;
-
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern enum cc_vendor cc_vendor;
void cc_set_mask(u64 mask);
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
#else
+#define cc_vendor (CC_VENDOR_NONE)
+
static inline u64 cc_mkenc(u64 val)
{
return val;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a26bebbdff87..a1273698fc43 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
".pushsection .altinstr_aux,\"ax\"\n"
"6:\n"
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index fdf723b6f6d0..2b62cdd8dd12 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -95,7 +95,7 @@
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index ce8f50192ae3..7e523bb3d2d3 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
static __always_inline void arch_exit_to_user_mode(void)
{
- mds_user_clear_cpu_buffers();
amd_clear_divider();
}
#define arch_exit_to_user_mode arch_exit_to_user_mode
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b02c3cd3c0f6..edebf1020e04 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,8 +16,6 @@
#include <asm/irq_vectors.h>
-#define IRQ_MATRIX_BITS NR_VECTORS
-
#ifndef __ASSEMBLY__
#include <linux/percpu.h>
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 071572e23d3a..cbbef32517f0 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
"jmp %l[l_yes] # objtool NOPs this \n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:
static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
".byte " __stringify(BYTES_NOP5) "\n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
"jmp %l[l_yes]\n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (branch) : : l_yes);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b5b2d0fde579..d271ba20a0b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1145,6 +1145,8 @@ struct kvm_hv {
unsigned int synic_auto_eoi_used;
struct kvm_hv_syndbg hv_syndbg;
+
+ bool xsaves_xsavec_checked;
};
#endif
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 262e65539f83..2aa52cab1e46 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -315,6 +315,17 @@
#endif
.endm
+/*
+ * Macro to execute VERW instruction that mitigate transient data sampling
+ * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ *
+ * Note: Only the memory operand variant of VERW clears the CPU buffers.
+ */
+.macro CLEAR_CPU_BUFFERS
+ ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
+.endm
+
#else /* __ASSEMBLY__ */
#define ANNOTATE_RETPOLINE_SAFE \
@@ -529,13 +540,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
-DECLARE_STATIC_KEY_FALSE(mds_user_clear);
DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+extern u16 mds_verw_sel;
+
#include <asm/segment.h>
/**
@@ -562,17 +574,6 @@ static __always_inline void mds_clear_cpu_buffers(void)
}
/**
- * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
- *
- * Clear CPU buffers if the corresponding static key is enabled
- */
-static __always_inline void mds_user_clear_cpu_buffers(void)
-{
- if (static_branch_likely(&mds_user_clear))
- mds_clear_cpu_buffers();
-}
-
-/**
* mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
*
* Clear CPU buffers if the corresponding static key is enabled
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4b081e0d3306..363266cbcada 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
({ \
bool c = false; \
- asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \
+ asm goto (fullop "; j" #cc " %l[cc_label]" \
: : [var] "m" (_var), ## __VA_ARGS__ \
: clobbers : cc_label); \
if (0) { \
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index a5e89641bd2d..9aee31862b4a 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages);
int set_memory_wc(unsigned long addr, int numpages);
int set_memory_wb(unsigned long addr, int numpages);
int set_memory_np(unsigned long addr, int numpages);
+int set_memory_p(unsigned long addr, int numpages);
int set_memory_4k(unsigned long addr, int numpages);
int set_memory_encrypted(unsigned long addr, int numpages);
int set_memory_decrypted(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d6cd9344f6c7..48f8dd47cf68 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
#ifdef CONFIG_X86_USER_SHADOW_STACK
static inline int write_user_shstk_64(u64 __user *addr, u64 val)
{
- asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+ asm goto("1: wrussq %[val], (%[addr])\n"
_ASM_EXTABLE(1b, %l[fail])
:: [addr] "r" (addr), [val] "r" (val)
:: fail);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5c367c1290c3..237dc8cdd12b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);
#ifdef CONFIG_X86_32
#define __put_user_goto_u64(x, addr, label) \
- asm_volatile_goto("\n" \
+ asm goto("\n" \
"1: movl %%eax,0(%1)\n" \
"2: movl %%edx,4(%1)\n" \
_ASM_EXTABLE_UA(1b, %l2) \
@@ -295,7 +295,7 @@ do { \
} while (0)
#define __get_user_asm(x, addr, itype, ltype, label) \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: mov"itype" %[umem],%[output]\n" \
_ASM_EXTABLE_UA(1b, %l2) \
: [output] ltype(x) \
@@ -375,7 +375,7 @@ do { \
__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \
__typeof__(*(_ptr)) __old = *_old; \
__typeof__(*(_ptr)) __new = (_new); \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
_ASM_EXTABLE_UA(1b, %l[label]) \
: CC_OUT(z) (success), \
@@ -394,7 +394,7 @@ do { \
__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \
__typeof__(*(_ptr)) __old = *_old; \
__typeof__(*(_ptr)) __new = (_new); \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \
_ASM_EXTABLE_UA(1b, %l[label]) \
: CC_OUT(z) (success), \
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
* aliasing issues.
*/
#define __put_user_goto(x, addr, itype, ltype, label) \
- asm_volatile_goto("\n" \
+ asm goto("\n" \
"1: mov"itype" %0,%1\n" \
_ASM_EXTABLE_UA(1b, %l2) \
: : ltype(x), "m" (__m(addr)) \
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index ab60a71a8dcb..472f0263dbc6 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,6 +4,7 @@
#include <linux/seqlock.h>
#include <uapi/asm/vsyscall.h>
+#include <asm/page_types.h>
#ifdef CONFIG_X86_VSYSCALL_EMULATION
extern void map_vsyscall(void);
@@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code,
}
#endif
+/*
+ * The (legacy) vsyscall page is the long page in the kernel portion
+ * of the address space that has user-accessible permissions.
+ */
+static inline bool is_vsyscall_vaddr(unsigned long vaddr)
+{
+ return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
+}
+
#endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 40c7cf180c20..e66c77529ca9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2354,7 +2354,7 @@ static int mp_irqdomain_create(int ioapic)
fwspec.param_count = 1;
fwspec.param[0] = mpc_ioapic_id(ioapic);
- parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY);
+ parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI);
if (!parent) {
if (!cfg->dev)
irq_domain_free_fwnode(fn);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bb0ab8466b91..48d049cd74e7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
/* Control unconditional IBPB in switch_mm() */
DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
-/* Control MDS CPU buffer clear before returning to user space */
-DEFINE_STATIC_KEY_FALSE(mds_user_clear);
-EXPORT_SYMBOL_GPL(mds_user_clear);
/* Control MDS CPU buffer clear before idling (halt, mwait) */
DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void)
if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
mds_mitigation = MDS_MITIGATION_VMWERV;
- static_branch_enable(&mds_user_clear);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
(mds_nosmt || cpu_mitigations_auto_nosmt()))
@@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void)
* For guests that can't determine whether the correct microcode is
* present on host, enable the mitigation for UCODE_NEEDED as well.
*/
- static_branch_enable(&mds_user_clear);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (taa_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
@@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void)
*/
if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
boot_cpu_has(X86_FEATURE_RTM)))
- static_branch_enable(&mds_user_clear);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
else
static_branch_enable(&mmio_stale_data_clear);
@@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void)
if (cpu_mitigations_off())
return;
- if (!static_key_enabled(&mds_user_clear))
+ if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
goto out;
/*
- * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
- * mitigation, if necessary.
+ * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
+ * Stale Data mitigation, if necessary.
*/
if (mds_mitigation == MDS_MITIGATION_OFF &&
boot_cpu_has_bug(X86_BUG_MDS)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0b97bcde70c6..fbc4e60d027c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
get_cpu_vendor(c);
get_cpu_cap(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
+ get_cpu_address_sizes(c);
cpu_parse_early_param();
if (this_cpu->c_early_init)
@@ -1601,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
this_cpu->c_bsp_init(c);
} else {
setup_clear_cpu_cap(X86_FEATURE_CPUID);
+ get_cpu_address_sizes(c);
}
- get_cpu_address_sizes(c);
-
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
cpu_set_bug_bits(c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a927a8fc9624..40dec9b56f87 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
return false;
}
+#define MSR_IA32_TME_ACTIVATE 0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x) (x & 0x1)
+#define TME_ACTIVATE_ENABLED(x) (x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128 0
+
+#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED 0
+#define MKTME_DISABLED 1
+#define MKTME_UNINITIALIZED 2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+ u64 tme_activate, tme_policy, tme_crypto_algs;
+ int keyid_bits = 0, nr_keyids = 0;
+ static u64 tme_activate_cpu0 = 0;
+
+ rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+ if (mktme_status != MKTME_UNINITIALIZED) {
+ if (tme_activate != tme_activate_cpu0) {
+ /* Broken BIOS? */
+ pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+ pr_err_once("x86/tme: MKTME is not usable\n");
+ mktme_status = MKTME_DISABLED;
+
+ /* Proceed. We may need to exclude bits from x86_phys_bits. */
+ }
+ } else {
+ tme_activate_cpu0 = tme_activate;
+ }
+
+ if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+ pr_info_once("x86/tme: not enabled by BIOS\n");
+ mktme_status = MKTME_DISABLED;
+ return;
+ }
+
+ if (mktme_status != MKTME_UNINITIALIZED)
+ goto detect_keyid_bits;
+
+ pr_info("x86/tme: enabled by BIOS\n");
+
+ tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+ if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+ pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+ tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+ if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+ pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+ tme_crypto_algs);
+ mktme_status = MKTME_DISABLED;
+ }
+detect_keyid_bits:
+ keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+ nr_keyids = (1UL << keyid_bits) - 1;
+ if (nr_keyids) {
+ pr_info_once("x86/mktme: enabled by BIOS\n");
+ pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+ } else {
+ pr_info_once("x86/mktme: disabled by BIOS\n");
+ }
+
+ if (mktme_status == MKTME_UNINITIALIZED) {
+ /* MKTME is usable */
+ mktme_status = MKTME_ENABLED;
+ }
+
+ /*
+ * KeyID bits effectively lower the number of physical address
+ * bits. Update cpuinfo_x86::x86_phys_bits accordingly.
+ */
+ c->x86_phys_bits -= keyid_bits;
+}
+
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
@@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
*/
if (detect_extended_topology_early(c) < 0)
detect_ht_early(c);
+
+ /*
+ * Adjust the number of physical bits early because it affects the
+ * valid bits of the MTRR mask registers.
+ */
+ if (cpu_has(c, X86_FEATURE_TME))
+ detect_tme_early(c);
}
static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
-#define MSR_IA32_TME_ACTIVATE 0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x) (x & 0x1)
-#define TME_ACTIVATE_ENABLED(x) (x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128 0
-
-#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED 0
-#define MKTME_DISABLED 1
-#define MKTME_UNINITIALIZED 2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
- u64 tme_activate, tme_policy, tme_crypto_algs;
- int keyid_bits = 0, nr_keyids = 0;
- static u64 tme_activate_cpu0 = 0;
-
- rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
- if (mktme_status != MKTME_UNINITIALIZED) {
- if (tme_activate != tme_activate_cpu0) {
- /* Broken BIOS? */
- pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
- pr_err_once("x86/tme: MKTME is not usable\n");
- mktme_status = MKTME_DISABLED;
-
- /* Proceed. We may need to exclude bits from x86_phys_bits. */
- }
- } else {
- tme_activate_cpu0 = tme_activate;
- }
-
- if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
- pr_info_once("x86/tme: not enabled by BIOS\n");
- mktme_status = MKTME_DISABLED;
- return;
- }
-
- if (mktme_status != MKTME_UNINITIALIZED)
- goto detect_keyid_bits;
-
- pr_info("x86/tme: enabled by BIOS\n");
-
- tme_policy = TME_ACTIVATE_POLICY(tme_activate);
- if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
- pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
- tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
- if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
- pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
- tme_crypto_algs);
- mktme_status = MKTME_DISABLED;
- }
-detect_keyid_bits:
- keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
- nr_keyids = (1UL << keyid_bits) - 1;
- if (nr_keyids) {
- pr_info_once("x86/mktme: enabled by BIOS\n");
- pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
- } else {
- pr_info_once("x86/mktme: disabled by BIOS\n");
- }
-
- if (mktme_status == MKTME_UNINITIALIZED) {
- /* MKTME is usable */
- mktme_status = MKTME_ENABLED;
- }
-
- /*
- * KeyID bits effectively lower the number of physical address
- * bits. Update cpuinfo_x86::x86_phys_bits accordingly.
- */
- c->x86_phys_bits -= keyid_bits;
-}
-
static void init_cpuid_fault(struct cpuinfo_x86 *c)
{
u64 msr;
@@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c)
init_ia32_feat_ctl(c);
- if (cpu_has(c, X86_FEATURE_TME))
- detect_tme(c);
-
init_intel_misc_features(c);
split_lock_init();
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index fb8cf953380d..b66f540de054 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void)
e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
/*
- * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need
- * to be reserved.
+ * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
+ * kexec and do not need to be reserved.
*/
- if (data->type != SETUP_EFI && data->type != SETUP_IMA)
+ if (data->type != SETUP_EFI &&
+ data->type != SETUP_IMA &&
+ data->type != SETUP_RNG_SEED)
e820__range_update_kexec(pa_data,
sizeof(*data) + data->len,
E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 558076dbde5b..247f2225aa9f 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
* Attempt to restore the FPU registers directly from user memory.
* Pagefaults are handled and any errors returned are fatal.
*/
-static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
- bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
{
struct fpu *fpu = &current->thread.fpu;
int ret;
+ /* Restore enabled features only. */
+ xrestore &= fpu->fpstate->user_xfeatures;
retry:
fpregs_lock();
/* Ensure that XFD is up to date */
@@ -309,7 +310,7 @@ retry:
if (ret != X86_TRAP_PF)
return false;
- if (!fault_in_readable(buf, size))
+ if (!fault_in_readable(buf, fpu->fpstate->user_size))
goto retry;
return false;
}
@@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
struct user_i387_ia32_struct env;
bool success, fx_only = false;
union fpregs_state *fpregs;
- unsigned int state_size;
u64 user_xfeatures = 0;
if (use_xsave()) {
@@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
return false;
fx_only = !fx_sw_user.magic1;
- state_size = fx_sw_user.xstate_size;
user_xfeatures = fx_sw_user.xfeatures;
} else {
user_xfeatures = XFEATURE_MASK_FPSSE;
- state_size = fpu->fpstate->user_size;
}
if (likely(!ia32_fxstate)) {
/* Restore the FPU registers directly from user memory. */
- return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
- state_size);
+ return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only);
}
/*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index a38d0c93a66e..c96ae8fee95e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -568,7 +568,7 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id)
fwspec.param_count = 1;
fwspec.param[0] = hpet_id;
- parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY);
+ parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI);
if (!parent) {
irq_domain_free_fwnode(fn);
kfree(domain_info);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index dfe9945b9bec..428ee74002e1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void)
{
int cpu;
- if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+ if (cc_vendor != CC_VENDOR_AMD ||
+ !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
return;
for_each_possible_cpu(cpu) {
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 17e955ab69fe..3082cf24b69e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -563,9 +563,6 @@ nmi_restart:
}
if (this_cpu_dec_return(nmi_state))
goto nmi_restart;
-
- if (user_mode(regs))
- mds_user_clear_cpu_buffers();
}
#if IS_ENABLED(CONFIG_KVM_INTEL)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 87e3da7b0439..65ed14b6540b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -80,9 +80,10 @@ config KVM_SW_PROTECTED_VM
depends on KVM && X86_64
select KVM_GENERIC_PRIVATE_MEM
help
- Enable support for KVM software-protected VMs. Currently "protected"
- means the VM can be backed with memory provided by
- KVM_CREATE_GUEST_MEMFD.
+ Enable support for KVM software-protected VMs. Currently, software-
+ protected VMs are purely a development and testing vehicle for
+ KVM_CREATE_GUEST_MEMFD. Attempting to run a "real" VM workload as a
+ software-protected VM will fail miserably.
If unsure, say "N".
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4943f6b2bbee..8a47f8541eab 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1322,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
return false;
}
+#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839
+#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */
+
+/*
+ * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC
+ * configuration.
+ * Such configuration can result from, for example, AMD Erratum 1386 workaround.
+ *
+ * Print a notice so users aren't left wondering what's suddenly gone wrong.
+ */
+static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ /* Check again under the hv_lock. */
+ if (hv->xsaves_xsavec_checked)
+ return;
+
+ if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) !=
+ KVM_HV_WIN2016_GUEST_ID)
+ return;
+
+ hv->xsaves_xsavec_checked = true;
+
+ /* UP configurations aren't affected */
+ if (atomic_read(&kvm->online_vcpus) < 2)
+ return;
+
+ if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
+ !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC))
+ return;
+
+ pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "
+ "If it fails to boot try disabling XSAVEC in the VM config.\n");
+}
+
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+ if (!vcpu->arch.hyperv_enabled ||
+ hv->xsaves_xsavec_checked)
+ return;
+
+ mutex_lock(&hv->hv_lock);
+ __kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+ mutex_unlock(&hv->hv_lock);
+}
+
static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
bool host)
{
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 1dc0b6604526..923e64903da9 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -182,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock);
void kvm_hv_request_tsc_page_update(struct kvm *kvm);
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu);
+
void kvm_hv_init_vm(struct kvm *kvm);
void kvm_hv_destroy_vm(struct kvm *kvm);
int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
@@ -267,6 +269,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock) {}
static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {}
static inline void kvm_hv_init_vm(struct kvm *kvm) {}
static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2d6cdeab1f8a..0544700ca50b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4405,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
+ /*
+ * Check for a relevant mmu_notifier invalidation event before getting
+ * the pfn from the primary MMU, and before acquiring mmu_lock.
+ *
+ * For mmu_lock, if there is an in-progress invalidation and the kernel
+ * allows preemption, the invalidation task may drop mmu_lock and yield
+ * in response to mmu_lock being contended, which is *very* counter-
+ * productive as this vCPU can't actually make forward progress until
+ * the invalidation completes.
+ *
+ * Retrying now can also avoid unnessary lock contention in the primary
+ * MMU, as the primary MMU doesn't necessarily hold a single lock for
+ * the duration of the invalidation, i.e. faulting in a conflicting pfn
+ * can cause the invalidation to take longer by holding locks that are
+ * needed to complete the invalidation.
+ *
+ * Do the pre-check even for non-preemtible kernels, i.e. even if KVM
+ * will never yield mmu_lock in response to contention, as this vCPU is
+ * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
+ * to detect retry guarantees the worst case latency for the vCPU.
+ */
+ if (fault->slot &&
+ mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+ return RET_PF_RETRY;
+
ret = __kvm_faultin_pfn(vcpu, fault);
if (ret != RET_PF_CONTINUE)
return ret;
@@ -4415,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
if (unlikely(!fault->slot))
return kvm_handle_noslot_fault(vcpu, fault, access);
+ /*
+ * Check again for a relevant mmu_notifier invalidation event purely to
+ * avoid contending mmu_lock. Most invalidations will be detected by
+ * the previous check, but checking is extremely cheap relative to the
+ * overall cost of failing to detect the invalidation until after
+ * mmu_lock is acquired.
+ */
+ if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) {
+ kvm_release_pfn_clean(fault->pfn);
+ return RET_PF_RETRY;
+ }
+
return RET_PF_CONTINUE;
}
@@ -4442,6 +4479,11 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
return true;
+ /*
+ * Check for a relevant mmu_notifier invalidation event one last time
+ * now that mmu_lock is held, as the "unsafe" checks performed without
+ * holding mmu_lock can get false negatives.
+ */
return fault->slot &&
mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f760106c31f8..a8ce5226b3b5 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -57,7 +57,7 @@ static bool sev_es_enabled = true;
module_param_named(sev_es, sev_es_enabled, bool, 0444);
/* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = true;
+static bool sev_es_debug_swap_enabled = false;
module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
#else
#define sev_enabled false
@@ -612,8 +612,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
save->xss = svm->vcpu.arch.ia32_xss;
save->dr6 = svm->vcpu.arch.dr6;
- if (sev_es_debug_swap_enabled)
+ if (sev_es_debug_swap_enabled) {
save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+ pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
+ "This will not work starting with Linux 6.10\n");
+ }
pr_debug("Virtual Machine Save Area (VMSA):\n");
print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
@@ -1975,20 +1978,22 @@ int sev_mem_enc_register_region(struct kvm *kvm,
goto e_free;
}
- region->uaddr = range->addr;
- region->size = range->size;
-
- list_add_tail(&region->list, &sev->regions_list);
- mutex_unlock(&kvm->lock);
-
/*
* The guest may change the memory encryption attribute from C=0 -> C=1
* or vice versa for this memory range. Lets make sure caches are
* flushed to ensure that guest data gets written into memory with
- * correct C-bit.
+ * correct C-bit. Note, this must be done before dropping kvm->lock,
+ * as region and its array of pages can be freed by a different task
+ * once kvm->lock is released.
*/
sev_clflush_pages(region->pages, region->npages);
+ region->uaddr = range->addr;
+ region->size = range->size;
+
+ list_add_tail(&region->list, &sev->regions_list);
+ mutex_unlock(&kvm->lock);
+
return ret;
e_free:
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 36c8af87a707..4e725854c63a 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@
#define svm_asm(insn, clobber...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) "\n\t" \
+ asm goto("1: " __stringify(insn) "\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
::: clobber : fault); \
return; \
@@ -18,7 +18,7 @@ fault: \
#define svm_asm1(insn, op1, clobber...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \
+ asm goto("1: " __stringify(insn) " %0\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
:: op1 : clobber : fault); \
return; \
@@ -28,7 +28,7 @@ fault: \
#define svm_asm2(insn, op1, op2, clobber...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \
+ asm goto("1: " __stringify(insn) " %1, %0\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
:: op1, op2 : clobber : fault); \
return; \
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a6216c874729..315c7c2ba89b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -71,7 +71,7 @@ static int fixed_pmc_events[] = {
static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
{
struct kvm_pmc *pmc;
- u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
+ u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
int i;
pmu->fixed_ctr_ctrl = data;
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h
index edc3f16cc189..6a9bfdfbb6e5 100644
--- a/arch/x86/kvm/vmx/run_flags.h
+++ b/arch/x86/kvm/vmx/run_flags.h
@@ -2,7 +2,10 @@
#ifndef __KVM_X86_VMX_RUN_FLAGS_H
#define __KVM_X86_VMX_RUN_FLAGS_H
-#define VMX_RUN_VMRESUME (1 << 0)
-#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1)
+#define VMX_RUN_VMRESUME_SHIFT 0
+#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1
+
+#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT)
+#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
#endif /* __KVM_X86_VMX_RUN_FLAGS_H */
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 906ecd001511..2bfbf758d061 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run)
mov (%_ASM_SP), %_ASM_AX
/* Check if vmlaunch or vmresume is needed */
- test $VMX_RUN_VMRESUME, %ebx
+ bt $VMX_RUN_VMRESUME_SHIFT, %ebx
/* Load guest registers. Don't clobber flags. */
mov VCPU_RCX(%_ASM_AX), %_ASM_CX
@@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run)
/* Load guest RAX. This kills the @regs pointer! */
mov VCPU_RAX(%_ASM_AX), %_ASM_AX
- /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */
- jz .Lvmlaunch
+ /* Clobbers EFLAGS.ZF */
+ CLEAR_CPU_BUFFERS
+
+ /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */
+ jnc .Lvmlaunch
/*
* After a successful VMRESUME/VMLAUNCH, control flow "magically"
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e262bc2ba4e5..88a4ff200d04 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -388,7 +388,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
{
- vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+ /*
+ * Disable VERW's behavior of clearing CPU buffers for the guest if the
+ * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled
+ * the mitigation. Disabling the clearing behavior provides a
+ * performance boost for guests that aren't aware that manually clearing
+ * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry
+ * and VM-Exit.
+ */
+ vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) &&
+ (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
!boot_cpu_has_bug(X86_BUG_MDS) &&
!boot_cpu_has_bug(X86_BUG_TAA);
@@ -738,7 +747,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
*/
static int kvm_cpu_vmxoff(void)
{
- asm_volatile_goto("1: vmxoff\n\t"
+ asm goto("1: vmxoff\n\t"
_ASM_EXTABLE(1b, %l[fault])
::: "cc", "memory" : fault);
@@ -2784,7 +2793,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
cr4_set_bits(X86_CR4_VMXE);
- asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+ asm goto("1: vmxon %[vmxon_pointer]\n\t"
_ASM_EXTABLE(1b, %l[fault])
: : [vmxon_pointer] "m"(vmxon_pointer)
: : fault);
@@ -7224,11 +7233,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
guest_state_enter_irqoff();
- /* L1D Flush includes CPU buffer clear to mitigate MDS */
+ /*
+ * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW
+ * mitigation for MDS is done late in VMentry and is still
+ * executed in spite of L1D Flush. This is because an extra VERW
+ * should not matter much after the big hammer L1D Flush.
+ */
if (static_branch_unlikely(&vmx_l1d_should_flush))
vmx_l1d_flush(vcpu);
- else if (static_branch_unlikely(&mds_user_clear))
- mds_clear_cpu_buffers();
else if (static_branch_unlikely(&mmio_stale_data_clear) &&
kvm_arch_has_assigned_device(vcpu->kvm))
mds_clear_cpu_buffers();
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index f41ce3c24123..8060e5fc6dbd 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
- asm_volatile_goto("1: vmread %[field], %[output]\n\t"
+ asm_goto_output("1: vmread %[field], %[output]\n\t"
"jna %l[do_fail]\n\t"
_ASM_EXTABLE(1b, %l[do_exception])
@@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field)
#define vmx_asm1(insn, op1, error_args...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \
+ asm goto("1: " __stringify(insn) " %0\n\t" \
".byte 0x2e\n\t" /* branch not taken hint */ \
"jna %l[error]\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
@@ -205,7 +205,7 @@ fault: \
#define vmx_asm2(insn, op1, op2, error_args...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \
+ asm goto("1: " __stringify(insn) " %1, %0\n\t" \
".byte 0x2e\n\t" /* branch not taken hint */ \
"jna %l[error]\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 363b1c080205..e02cc710f56d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1704,22 +1704,17 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
struct kvm_msr_entry msr;
int r;
+ /* Unconditionally clear the output for simplicity */
+ msr.data = 0;
msr.index = index;
r = kvm_get_msr_feature(&msr);
- if (r == KVM_MSR_RET_INVALID) {
- /* Unconditionally clear the output for simplicity */
- *data = 0;
- if (kvm_msr_ignored_check(index, 0, false))
- r = 0;
- }
-
- if (r)
- return r;
+ if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false))
+ r = 0;
*data = msr.data;
- return 0;
+ return r;
}
static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
@@ -1782,6 +1777,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
kvm_mmu_reset_context(vcpu);
+ if (!static_cpu_has(X86_FEATURE_XSAVES) &&
+ (efer & EFER_SVME))
+ kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+
return 0;
}
@@ -2507,7 +2506,7 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
}
#ifdef CONFIG_X86_64
-static inline int gtod_is_based_on_tsc(int mode)
+static inline bool gtod_is_based_on_tsc(int mode)
{
return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
}
@@ -4581,7 +4580,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
{
return type == KVM_X86_DEFAULT_VM ||
(type == KVM_X86_SW_PROTECTED_VM &&
- IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled);
+ IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled);
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -5454,7 +5453,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
vcpu->arch.nmi_pending = 0;
atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
- kvm_make_request(KVM_REQ_NMI, vcpu);
+ if (events->nmi.pending)
+ kvm_make_request(KVM_REQ_NMI, vcpu);
}
static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
@@ -7016,6 +7016,9 @@ set_identity_unlock:
r = -EEXIST;
if (kvm->arch.vpit)
goto create_pit_unlock;
+ r = -ENOENT;
+ if (!pic_in_kernel(kvm))
+ goto create_pit_unlock;
r = -ENOMEM;
kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
if (kvm->arch.vpit)
@@ -8004,6 +8007,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
if (r < 0)
return X86EMUL_UNHANDLEABLE;
+
+ /*
+ * Mark the page dirty _before_ checking whether or not the CMPXCHG was
+ * successful, as the old value is written back on failure. Note, for
+ * live migration, this is unnecessarily conservative as CMPXCHG writes
+ * back the original value and the access is atomic, but KVM's ABI is
+ * that all writes are dirty logged, regardless of the value written.
+ */
+ kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa));
+
if (r)
return X86EMUL_CMPXCHG_FAILED;
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 20ef350a60fb..10d5ed8b5990 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception)
#endif
/* get_user */
- _ASM_EXTABLE(1b, __get_user_handle_exception)
- _ASM_EXTABLE(2b, __get_user_handle_exception)
- _ASM_EXTABLE(3b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(2b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(3b, __get_user_handle_exception)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(4b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(4b, __get_user_handle_exception)
#else
- _ASM_EXTABLE(4b, __get_user_8_handle_exception)
- _ASM_EXTABLE(5b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
#endif
/* __get_user */
- _ASM_EXTABLE(6b, __get_user_handle_exception)
- _ASM_EXTABLE(7b, __get_user_handle_exception)
- _ASM_EXTABLE(8b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(6b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(7b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(8b, __get_user_handle_exception)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(9b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(9b, __get_user_handle_exception)
#else
- _ASM_EXTABLE(9b, __get_user_8_handle_exception)
- _ASM_EXTABLE(10b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
#endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 2877f5934177..975c9c18263d 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -133,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception)
RET
SYM_CODE_END(__put_user_handle_exception)
- _ASM_EXTABLE(1b, __put_user_handle_exception)
- _ASM_EXTABLE(2b, __put_user_handle_exception)
- _ASM_EXTABLE(3b, __put_user_handle_exception)
- _ASM_EXTABLE(4b, __put_user_handle_exception)
- _ASM_EXTABLE(5b, __put_user_handle_exception)
- _ASM_EXTABLE(6b, __put_user_handle_exception)
- _ASM_EXTABLE(7b, __put_user_handle_exception)
- _ASM_EXTABLE(9b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(9b, __put_user_handle_exception)
#ifdef CONFIG_X86_32
- _ASM_EXTABLE(8b, __put_user_handle_exception)
- _ASM_EXTABLE(10b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(10b, __put_user_handle_exception)
#endif
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 679b09cfe241..d6375b3c633b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -798,15 +798,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
show_opcodes(regs, loglvl);
}
-/*
- * The (legacy) vsyscall page is the long page in the kernel portion
- * of the address space that has user-accessible permissions.
- */
-static bool is_vsyscall_vaddr(unsigned long vaddr)
-{
- return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
-}
-
static void
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
unsigned long address, u32 pkey, int si_code)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..f50cc210a981 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
for (; addr < end; addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
+ bool use_gbpage;
next = (addr & PUD_MASK) + PUD_SIZE;
if (next > end)
next = end;
- if (info->direct_gbpages) {
- pud_t pudval;
+ /* if this is already a gbpage, this portion is already mapped */
+ if (pud_large(*pud))
+ continue;
+
+ /* Is using a gbpage allowed? */
+ use_gbpage = info->direct_gbpages;
- if (pud_present(*pud))
- continue;
+ /* Don't use gbpage if it maps more than the requested region. */
+ /* at the begining: */
+ use_gbpage &= ((addr & ~PUD_MASK) == 0);
+ /* ... or at the end: */
+ use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+ /* Never overwrite existing mappings */
+ use_gbpage &= !pud_present(*pud);
+
+ if (use_gbpage) {
+ pud_t pudval;
- addr &= PUD_MASK;
pudval = __pud((addr - info->offset) | info->page_flag);
set_pud(pud, pudval);
continue;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 6993f026adec..42115ac079cf 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -3,6 +3,8 @@
#include <linux/uaccess.h>
#include <linux/kernel.h>
+#include <asm/vsyscall.h>
+
#ifdef CONFIG_X86_64
bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
{
@@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
return false;
/*
+ * Reading from the vsyscall page may cause an unhandled fault in
+ * certain cases. Though it is at an address above TASK_SIZE_MAX, it is
+ * usually considered as a user space address.
+ */
+ if (is_vsyscall_vaddr(vaddr))
+ return false;
+
+ /*
* Allow everything during early boot before 'x86_virt_bits'
* is initialized. Needed for instruction decoding in early
* exception handlers.
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index adc497b93f03..65e9a6e391c0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -934,7 +934,7 @@ static int __init cmp_memblk(const void *a, const void *b)
const struct numa_memblk *ma = *(const struct numa_memblk **)a;
const struct numa_memblk *mb = *(const struct numa_memblk **)b;
- return ma->start - mb->start;
+ return (ma->start > mb->start) - (ma->start < mb->start);
}
static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
@@ -944,14 +944,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
* @start: address to begin fill
* @end: address to end fill
*
- * Find and extend numa_meminfo memblks to cover the @start-@end
- * physical address range, such that the first memblk includes
- * @start, the last memblk includes @end, and any gaps in between
- * are filled.
+ * Find and extend numa_meminfo memblks to cover the physical
+ * address range @start-@end
*
* RETURNS:
* 0 : Success
- * NUMA_NO_MEMBLK : No memblk exists in @start-@end range
+ * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end
*/
int __init numa_fill_memblks(u64 start, u64 end)
@@ -963,17 +961,14 @@ int __init numa_fill_memblks(u64 start, u64 end)
/*
* Create a list of pointers to numa_meminfo memblks that
- * overlap start, end. Exclude (start == bi->end) since
- * end addresses in both a CFMWS range and a memblk range
- * are exclusive.
- *
- * This list of pointers is used to make in-place changes
- * that fill out the numa_meminfo memblks.
+ * overlap start, end. The list is used to make in-place
+ * changes that fill out the numa_meminfo memblks.
*/
for (int i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *bi = &mi->blk[i];
- if (start < bi->end && end >= bi->start) {
+ if (memblock_addrs_overlap(start, end - start, bi->start,
+ bi->end - bi->start)) {
blk[count] = &mi->blk[i];
count++;
}
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index e9b448d1b1b7..102880404046 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address)
* areas on 32-bit NUMA systems. The percpu areas can
* end up in this kind of memory, for instance.
*
- * This could be optimized, but it is only intended to be
- * used at initialization time, and keeping it
- * unoptimized should increase the testing coverage for
- * the more obscure platforms.
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE. This is unlike
+ * the similar vmalloc_to_page() and derivatives. Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
*/
phys_addr_t slow_virt_to_phys(void *__virt_addr)
{
@@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn)
return rc;
}
-static int set_memory_p(unsigned long *addr, int numpages)
-{
- return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
-}
-
/* Restore full speculative operation to the pfn. */
int clear_mce_nospec(unsigned long pfn)
{
unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
- return set_memory_p(&addr, 1);
+ return set_memory_p(addr, 1);
}
EXPORT_SYMBOL_GPL(clear_mce_nospec);
#endif /* CONFIG_X86_64 */
@@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages)
CPA_NO_CHECK_ALIAS, NULL);
}
+int set_memory_p(unsigned long addr, int numpages)
+{
+ return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
int set_memory_4k(unsigned long addr, int numpages)
{
return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4b0d6fff88de..1fb9a1644d94 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu)
char *resched_name, *callfunc_name, *debug_name;
resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+ if (!resched_name)
+ goto fail_mem;
per_cpu(xen_resched_irq, cpu).name = resched_name;
rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
cpu,
@@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu)
per_cpu(xen_resched_irq, cpu).irq = rc;
callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+ if (!callfunc_name)
+ goto fail_mem;
per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
cpu,
@@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu)
if (!xen_fifo_events) {
debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+ if (!debug_name)
+ goto fail_mem;
+
per_cpu(xen_debug_irq, cpu).name = debug_name;
rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
xen_debug_interrupt,
@@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu)
}
callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+ if (!callfunc_name)
+ goto fail_mem;
+
per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
cpu,
@@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu)
return 0;
+ fail_mem:
+ rc = -ENOMEM;
fail:
xen_smp_intr_free(cpu);
return rc;