summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig26
-rw-r--r--arch/x86/Kconfig.cpu14
-rw-r--r--arch/x86/Kconfig.debug1
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/eboot.c10
-rw-r--r--arch/x86/boot/compressed/kaslr.c18
-rw-r--r--arch/x86/boot/compressed/mem_encrypt.S19
-rw-r--r--arch/x86/boot/compressed/misc.h1
-rw-r--r--arch/x86/boot/header.S6
-rw-r--r--arch/x86/boot/tools/build.c7
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/crypto/Makefile5
-rw-r--r--arch/x86/crypto/aegis128-aesni-glue.c1
-rw-r--r--arch/x86/crypto/aegis128l-aesni-glue.c1
-rw-r--r--arch/x86/crypto/aegis256-aesni-glue.c1
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c47
-rw-r--r--arch/x86/crypto/fpu.c207
-rw-r--r--arch/x86/crypto/morus1280-sse2-glue.c1
-rw-r--r--arch/x86/crypto/morus640-sse2-glue.c1
-rw-r--r--arch/x86/crypto/sha1-mb/Makefile14
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb.c1011
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_ctx.h134
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_mgr.h110
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S287
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S304
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c64
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S209
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_x8_avx2.S492
-rw-r--r--arch/x86/crypto/sha256-mb/Makefile14
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb.c1013
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_ctx.h134
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_mgr.h108
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S304
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S307
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c65
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S214
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_x8_avx2.S598
-rw-r--r--arch/x86/crypto/sha512-mb/Makefile12
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb.c1047
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb_ctx.h128
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb_mgr.h104
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S281
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S297
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c69
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S224
-rw-r--r--arch/x86/crypto/sha512-mb/sha512_x4_avx2.S531
-rw-r--r--arch/x86/entry/calling.h2
-rw-r--r--arch/x86/entry/entry_32.S21
-rw-r--r--arch/x86/entry/entry_64.S138
-rw-r--r--arch/x86/entry/vdso/Makefile16
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c220
-rw-r--r--arch/x86/entry/vdso/vgetcpu.c8
-rw-r--r--arch/x86/entry/vdso/vma.c38
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c9
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_gtod.c51
-rw-r--r--arch/x86/events/amd/core.c4
-rw-r--r--arch/x86/events/amd/uncore.c30
-rw-r--r--arch/x86/events/core.c41
-rw-r--r--arch/x86/events/intel/core.c346
-rw-r--r--arch/x86/events/intel/cstate.c8
-rw-r--r--arch/x86/events/intel/lbr.c4
-rw-r--r--arch/x86/events/intel/pt.c2
-rw-r--r--arch/x86/events/intel/rapl.c4
-rw-r--r--arch/x86/events/intel/uncore_snbep.c14
-rw-r--r--arch/x86/events/msr.c8
-rw-r--r--arch/x86/events/perf_event.h4
-rw-r--r--arch/x86/hyperv/Makefile4
-rw-r--r--arch/x86/hyperv/hv_apic.c9
-rw-r--r--arch/x86/hyperv/hv_init.c19
-rw-r--r--arch/x86/hyperv/hv_spinlock.c88
-rw-r--r--arch/x86/hyperv/mmu.c4
-rw-r--r--arch/x86/include/asm/acpi.h7
-rw-r--r--arch/x86/include/asm/alternative-asm.h20
-rw-r--r--arch/x86/include/asm/alternative.h11
-rw-r--r--arch/x86/include/asm/amd_nb.h3
-rw-r--r--arch/x86/include/asm/asm.h57
-rw-r--r--arch/x86/include/asm/atomic.h20
-rw-r--r--arch/x86/include/asm/atomic64_32.h8
-rw-r--r--arch/x86/include/asm/atomic64_64.h20
-rw-r--r--arch/x86/include/asm/bitops.h9
-rw-r--r--arch/x86/include/asm/bug.h98
-rw-r--r--arch/x86/include/asm/cacheinfo.h1
-rw-r--r--arch/x86/include/asm/cmpxchg.h10
-rw-r--r--arch/x86/include/asm/compat.h21
-rw-r--r--arch/x86/include/asm/cpu_entry_area.h2
-rw-r--r--arch/x86/include/asm/cpufeature.h82
-rw-r--r--arch/x86/include/asm/debugreg.h2
-rw-r--r--arch/x86/include/asm/desc.h4
-rw-r--r--arch/x86/include/asm/efi.h1
-rw-r--r--arch/x86/include/asm/elf.h9
-rw-r--r--arch/x86/include/asm/extable.h3
-rw-r--r--arch/x86/include/asm/fixmap.h12
-rw-r--r--arch/x86/include/asm/fpu/internal.h4
-rw-r--r--arch/x86/include/asm/fsgsbase.h49
-rw-r--r--arch/x86/include/asm/futex.h6
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h21
-rw-r--r--arch/x86/include/asm/intel-family.h33
-rw-r--r--arch/x86/include/asm/io.h15
-rw-r--r--arch/x86/include/asm/irq_remapping.h2
-rw-r--r--arch/x86/include/asm/irqflags.h16
-rw-r--r--arch/x86/include/asm/jump_label.h80
-rw-r--r--arch/x86/include/asm/kdebug.h12
-rw-r--r--arch/x86/include/asm/kexec.h2
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h97
-rw-r--r--arch/x86/include/asm/local.h8
-rw-r--r--arch/x86/include/asm/mce.h55
-rw-r--r--arch/x86/include/asm/mem_encrypt.h7
-rw-r--r--arch/x86/include/asm/mmu_context.h4
-rw-r--r--arch/x86/include/asm/mpx.h12
-rw-r--r--arch/x86/include/asm/mshyperv.h2
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/include/asm/msr.h4
-rw-r--r--arch/x86/include/asm/nospec-branch.h17
-rw-r--r--arch/x86/include/asm/page_64_types.h15
-rw-r--r--arch/x86/include/asm/paravirt.h415
-rw-r--r--arch/x86/include/asm/paravirt_types.h138
-rw-r--r--arch/x86/include/asm/percpu.h8
-rw-r--r--arch/x86/include/asm/perf_event.h9
-rw-r--r--arch/x86/include/asm/pgalloc.h2
-rw-r--r--arch/x86/include/asm/pgtable-2level.h9
-rw-r--r--arch/x86/include/asm/pgtable-3level_types.h2
-rw-r--r--arch/x86/include/asm/pgtable.h9
-rw-r--r--arch/x86/include/asm/pgtable_64.h23
-rw-r--r--arch/x86/include/asm/pgtable_types.h2
-rw-r--r--arch/x86/include/asm/preempt.h2
-rw-r--r--arch/x86/include/asm/processor.h13
-rw-r--r--arch/x86/include/asm/ptrace.h48
-rw-r--r--arch/x86/include/asm/qspinlock.h15
-rw-r--r--arch/x86/include/asm/refcount.h79
-rw-r--r--arch/x86/include/asm/rmwcc.h69
-rw-r--r--arch/x86/include/asm/sections.h1
-rw-r--r--arch/x86/include/asm/segment.h48
-rw-r--r--arch/x86/include/asm/special_insns.h4
-rw-r--r--arch/x86/include/asm/string_64.h20
-rw-r--r--arch/x86/include/asm/suspend.h8
-rw-r--r--arch/x86/include/asm/suspend_32.h4
-rw-r--r--arch/x86/include/asm/tlb.h21
-rw-r--r--arch/x86/include/asm/tlbflush.h33
-rw-r--r--arch/x86/include/asm/trace/mpx.h4
-rw-r--r--arch/x86/include/asm/uaccess.h22
-rw-r--r--arch/x86/include/asm/unistd.h3
-rw-r--r--arch/x86/include/asm/uv/uv.h6
-rw-r--r--arch/x86/include/asm/vgtod.h79
-rw-r--r--arch/x86/include/asm/virtext.h7
-rw-r--r--arch/x86/include/asm/vmx.h13
-rw-r--r--arch/x86/include/asm/x86_init.h2
-rw-r--r--arch/x86/include/asm/xen/events.h2
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h4
-rw-r--r--arch/x86/include/uapi/asm/kvm.h9
-rw-r--r--arch/x86/include/uapi/asm/siginfo.h2
-rw-r--r--arch/x86/kernel/acpi/boot.c6
-rw-r--r--arch/x86/kernel/alternative.c6
-rw-r--r--arch/x86/kernel/amd_gart_64.c6
-rw-r--r--arch/x86/kernel/amd_nb.c49
-rw-r--r--arch/x86/kernel/apic/apic.c7
-rw-r--r--arch/x86/kernel/apic/probe_32.c1
-rw-r--r--arch/x86/kernel/apic/vector.c11
-rw-r--r--arch/x86/kernel/apm_32.c2
-rw-r--r--arch/x86/kernel/asm-offsets.c18
-rw-r--r--arch/x86/kernel/asm-offsets_64.c9
-rw-r--r--arch/x86/kernel/check.c28
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/bugs.c62
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c31
-rw-r--r--arch/x86/kernel/cpu/common.c77
-rw-r--r--arch/x86/kernel/cpu/cpu.h1
-rw-r--r--arch/x86/kernel/cpu/cyrix.c2
-rw-r--r--arch/x86/kernel/cpu/hygon.c408
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.c17
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.h23
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c39
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c405
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c263
-rw-r--r--arch/x86/kernel/cpu/mcheck/dev-mcelog.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c6
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c22
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c24
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c17
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c14
-rw-r--r--arch/x86/kernel/cpu/mtrr/cleanup.c3
-rw-r--r--arch/x86/kernel/cpu/mtrr/mtrr.c2
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c2
-rw-r--r--arch/x86/kernel/cpu/vmware.c4
-rw-r--r--arch/x86/kernel/crash_dump_64.c60
-rw-r--r--arch/x86/kernel/dumpstack.c11
-rw-r--r--arch/x86/kernel/eisa.c10
-rw-r--r--arch/x86/kernel/fpu/signal.c1
-rw-r--r--arch/x86/kernel/head32.c1
-rw-r--r--arch/x86/kernel/head64.c22
-rw-r--r--arch/x86/kernel/head_64.S18
-rw-r--r--arch/x86/kernel/jump_label.c62
-rw-r--r--arch/x86/kernel/kprobes/core.c48
-rw-r--r--arch/x86/kernel/kprobes/opt.c2
-rw-r--r--arch/x86/kernel/kvm.c19
-rw-r--r--arch/x86/kernel/kvmclock.c56
-rw-r--r--arch/x86/kernel/ldt.c2
-rw-r--r--arch/x86/kernel/macros.S16
-rw-r--r--arch/x86/kernel/module.c6
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c15
-rw-r--r--arch/x86/kernel/paravirt.c320
-rw-r--r--arch/x86/kernel/paravirt_patch_32.c87
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c97
-rw-r--r--arch/x86/kernel/pci-swiotlb.c2
-rw-r--r--arch/x86/kernel/process_32.c4
-rw-r--r--arch/x86/kernel/process_64.c197
-rw-r--r--arch/x86/kernel/ptrace.c57
-rw-r--r--arch/x86/kernel/setup.c19
-rw-r--r--arch/x86/kernel/smpboot.c4
-rw-r--r--arch/x86/kernel/time.c24
-rw-r--r--arch/x86/kernel/topology.c4
-rw-r--r--arch/x86/kernel/traps.c196
-rw-r--r--arch/x86/kernel/tsc.c16
-rw-r--r--arch/x86/kernel/tsc_msr.c10
-rw-r--r--arch/x86/kernel/umip.c8
-rw-r--r--arch/x86/kernel/uprobes.c2
-rw-r--r--arch/x86/kernel/vm86_32.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S29
-rw-r--r--arch/x86/kernel/vsmp_64.c26
-rw-r--r--arch/x86/kernel/x86_init.c3
-rw-r--r--arch/x86/kvm/emulate.c11
-rw-r--r--arch/x86/kvm/hyperv.c280
-rw-r--r--arch/x86/kvm/hyperv.h4
-rw-r--r--arch/x86/kvm/lapic.c94
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/kvm/mmu.c451
-rw-r--r--arch/x86/kvm/mmu.h13
-rw-r--r--arch/x86/kvm/mmu_audit.c12
-rw-r--r--arch/x86/kvm/paging_tmpl.h15
-rw-r--r--arch/x86/kvm/svm.c96
-rw-r--r--arch/x86/kvm/trace.h42
-rw-r--r--arch/x86/kvm/vmx.c2563
-rw-r--r--arch/x86/kvm/vmx_shadow_fields.h5
-rw-r--r--arch/x86/kvm/x86.c375
-rw-r--r--arch/x86/kvm/x86.h4
-rw-r--r--arch/x86/lib/checksum_32.S4
-rw-r--r--arch/x86/lib/copy_user_64.S90
-rw-r--r--arch/x86/lib/csum-copy_64.S8
-rw-r--r--arch/x86/lib/getuser.S12
-rw-r--r--arch/x86/lib/putuser.S10
-rw-r--r--arch/x86/lib/usercopy_32.c126
-rw-r--r--arch/x86/lib/usercopy_64.c8
-rw-r--r--arch/x86/mm/cpu_entry_area.c36
-rw-r--r--arch/x86/mm/dump_pagetables.c35
-rw-r--r--arch/x86/mm/extable.c114
-rw-r--r--arch/x86/mm/fault.c478
-rw-r--r--arch/x86/mm/init.c4
-rw-r--r--arch/x86/mm/init_32.c23
-rw-r--r--arch/x86/mm/ioremap.c24
-rw-r--r--arch/x86/mm/mem_encrypt.c24
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c1
-rw-r--r--arch/x86/mm/mpx.c30
-rw-r--r--arch/x86/mm/pageattr.c627
-rw-r--r--arch/x86/mm/pgtable.c27
-rw-r--r--arch/x86/mm/pti.c33
-rw-r--r--arch/x86/mm/tlb.c198
-rw-r--r--arch/x86/pci/acpi.c2
-rw-r--r--arch/x86/pci/amd_bus.c6
-rw-r--r--arch/x86/pci/fixup.c12
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c6
-rw-r--r--arch/x86/platform/efi/early_printk.c8
-rw-r--r--arch/x86/platform/efi/efi_32.c3
-rw-r--r--arch/x86/platform/efi/efi_64.c10
-rw-r--r--arch/x86/platform/efi/quirks.c78
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c17
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bt.c2
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-rtc.c3
-rw-r--r--arch/x86/platform/ts5500/ts5500.c1
-rw-r--r--arch/x86/power/Makefile2
-rw-r--r--arch/x86/power/hibernate.c248
-rw-r--r--arch/x86/power/hibernate_32.c52
-rw-r--r--arch/x86/power/hibernate_64.c224
-rw-r--r--arch/x86/power/hibernate_asm_32.S37
-rw-r--r--arch/x86/power/hibernate_asm_64.S2
-rw-r--r--arch/x86/tools/relocs.c10
-rw-r--r--arch/x86/um/asm/elf.h3
-rw-r--r--arch/x86/xen/Kconfig2
-rw-r--r--arch/x86/xen/Makefile41
-rw-r--r--arch/x86/xen/efi.c14
-rw-r--r--arch/x86/xen/enlighten.c3
-rw-r--r--arch/x86/xen/enlighten_hvm.c2
-rw-r--r--arch/x86/xen/enlighten_pv.c31
-rw-r--r--arch/x86/xen/enlighten_pvh.c3
-rw-r--r--arch/x86/xen/grant-table.c25
-rw-r--r--arch/x86/xen/irq.c2
-rw-r--r--arch/x86/xen/mmu.c188
-rw-r--r--arch/x86/xen/mmu_hvm.c2
-rw-r--r--arch/x86/xen/mmu_pv.c176
-rw-r--r--arch/x86/xen/p2m.c2
-rw-r--r--arch/x86/xen/pci-swiotlb-xen.c2
-rw-r--r--arch/x86/xen/platform-pci-unplug.c19
-rw-r--r--arch/x86/xen/pmu.c15
-rw-r--r--arch/x86/xen/smp_pv.c2
-rw-r--r--arch/x86/xen/spinlock.c11
-rw-r--r--arch/x86/xen/time.c4
-rw-r--r--arch/x86/xen/vdso.h2
-rw-r--r--arch/x86/xen/xen-asm_64.S8
-rw-r--r--arch/x86/xen/xen-pvh.S15
302 files changed, 8520 insertions, 13229 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..cbd5f28ea8e2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -48,6 +48,7 @@ config X86
select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
select ANON_INODES
select ARCH_CLOCKSOURCE_DATA
+ select ARCH_CLOCKSOURCE_INIT
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_DEBUG_VIRTUAL
@@ -119,6 +120,7 @@ config X86
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if X86_64
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS if MMU
@@ -447,7 +449,6 @@ config RETPOLINE
config INTEL_RDT
bool "Intel Resource Director Technology support"
- default n
depends on X86 && CPU_SUP_INTEL
select KERNFS
help
@@ -523,6 +524,7 @@ config X86_VSMP
bool "ScaleMP vSMP"
select HYPERVISOR_GUEST
select PARAVIRT
+ select PARAVIRT_XXL
depends on X86_64 && PCI
depends on X86_EXTENDED_PLATFORM
depends on SMP
@@ -701,7 +703,6 @@ config STA2X11
select SWIOTLB
select MFD_STA2X11
select GPIOLIB
- default n
---help---
This adds support for boards based on the STA2X11 IO-Hub,
a.k.a. "ConneXt". The chip is used in place of the standard
@@ -754,6 +755,9 @@ config PARAVIRT
over full virtualization. However, when run without a hypervisor
the kernel is theoretically slower and slightly larger.
+config PARAVIRT_XXL
+ bool
+
config PARAVIRT_DEBUG
bool "paravirt-ops debugging"
depends on PARAVIRT && DEBUG_KERNEL
@@ -799,7 +803,6 @@ config KVM_GUEST
config KVM_DEBUG_FS
bool "Enable debug information for KVM Guests in debugfs"
depends on KVM_GUEST && DEBUG_FS
- default n
---help---
This option enables collection of various statistics for KVM guest.
Statistics are displayed in debugfs filesystem. Enabling this option
@@ -808,7 +811,6 @@ config KVM_DEBUG_FS
config PARAVIRT_TIME_ACCOUNTING
bool "Paravirtual steal time accounting"
depends on PARAVIRT
- default n
---help---
Select this option to enable fine granularity task steal time
accounting. Time spent executing other tasks in parallel with
@@ -1168,7 +1170,6 @@ source "arch/x86/events/Kconfig"
config X86_LEGACY_VM86
bool "Legacy VM86 support"
- default n
depends on X86_32
---help---
This option allows user programs to put the CPU into V8086
@@ -1491,6 +1492,14 @@ config X86_DIRECT_GBPAGES
supports them), so don't confuse the user by printing
that we have them enabled.
+config X86_CPA_STATISTICS
+ bool "Enable statistic for Change Page Attribute"
+ depends on DEBUG_FS
+ ---help---
+ Expose statistics about the Change Page Attribute mechanims, which
+ helps to determine the effectivness of preserving large and huge
+ page mappings when mapping protections are changed.
+
config ARCH_HAS_MEM_ENCRYPT
def_bool y
@@ -2220,7 +2229,6 @@ config HOTPLUG_CPU
config BOOTPARAM_HOTPLUG_CPU0
bool "Set default setting of cpu0_hotpluggable"
- default n
depends on HOTPLUG_CPU
---help---
Set whether default state of cpu0_hotpluggable is on or off.
@@ -2422,7 +2430,7 @@ menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
def_bool y
- depends on X86_64 && HIBERNATION
+ depends on HIBERNATION
source "kernel/power/Kconfig"
@@ -2742,8 +2750,7 @@ config OLPC
config OLPC_XO1_PM
bool "OLPC XO-1 Power Management"
- depends on OLPC && MFD_CS5535 && PM_SLEEP
- select MFD_CORE
+ depends on OLPC && MFD_CS5535=y && PM_SLEEP
---help---
Add support for poweroff and suspend of the OLPC XO-1 laptop.
@@ -2825,7 +2832,6 @@ source "drivers/pcmcia/Kconfig"
config RAPIDIO
tristate "RapidIO support"
depends on PCI
- default n
help
If enabled this option will include drivers and the core
infrastructure code to support RapidIO interconnect devices.
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 638411f22267..6adce15268bd 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -426,6 +426,20 @@ config CPU_SUP_AMD
If unsure, say N.
+config CPU_SUP_HYGON
+ default y
+ bool "Support Hygon processors" if PROCESSOR_SELECT
+ select CPU_SUP_AMD
+ help
+ This enables detection, tunings and quirks for Hygon processors
+
+ You need this enabled if you want your kernel to run on an
+ Hygon CPU. Disabling this option on other types of CPUs
+ makes the kernel a tiny bit smaller. Disabling it on an Hygon
+ CPU might render the kernel unbootable.
+
+ If unsure, say N.
+
config CPU_SUP_CENTAUR
default y
bool "Support Centaur processors" if PROCESSOR_SELECT
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 7d68f0c7cfb1..0723dff17e6c 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -314,7 +314,6 @@ config DEBUG_NMI_SELFTEST
config DEBUG_IMR_SELFTEST
bool "Isolated Memory Region self test"
- default n
depends on INTEL_IMR
---help---
This option enables automated sanity testing of the IMR code.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8f6e7eb8ae9f..5b562e464009 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -193,7 +193,6 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
-asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1)
@@ -237,6 +236,13 @@ archscripts: scripts_basic
archheaders:
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
+archmacros:
+ $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
+
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+export ASM_MACRO_FLAGS
+KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
+
###
# Kernel objects
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 28764dacf018..466f66c8a7f8 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -37,6 +37,7 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += -Wno-pointer-sign
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
GCOV_PROFILE := n
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 1458b1700fc7..8b4c5e001157 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -738,6 +738,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
struct desc_struct *desc;
void *handle;
efi_system_table_t *_table;
+ unsigned long cmdline_paddr;
efi_early = c;
@@ -756,6 +757,15 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
setup_boot_services32(efi_early);
/*
+ * make_boot_params() may have been called before efi_main(), in which
+ * case this is the second time we parse the cmdline. This is ok,
+ * parsing the cmdline multiple times does not have side-effects.
+ */
+ cmdline_paddr = ((u64)hdr->cmd_line_ptr |
+ ((u64)boot_params->ext_cmd_line_ptr << 32));
+ efi_parse_options((char *)cmdline_paddr);
+
+ /*
* If the boot loader gave us a value for secure_boot then we use that,
* otherwise we ask the BIOS.
*/
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index d1e19f358b6e..9ed9709d9947 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -241,7 +241,7 @@ static void parse_gb_huge_pages(char *param, char *val)
}
-static int handle_mem_options(void)
+static void handle_mem_options(void)
{
char *args = (char *)get_cmd_line_ptr();
size_t len = strlen((char *)args);
@@ -251,7 +251,7 @@ static int handle_mem_options(void)
if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
!strstr(args, "hugepages"))
- return 0;
+ return;
tmp_cmdline = malloc(len + 1);
if (!tmp_cmdline)
@@ -269,8 +269,7 @@ static int handle_mem_options(void)
/* Stop at -- */
if (!val && strcmp(param, "--") == 0) {
warn("Only '--' specified in cmdline");
- free(tmp_cmdline);
- return -1;
+ goto out;
}
if (!strcmp(param, "memmap")) {
@@ -283,16 +282,16 @@ static int handle_mem_options(void)
if (!strcmp(p, "nopentium"))
continue;
mem_size = memparse(p, &p);
- if (mem_size == 0) {
- free(tmp_cmdline);
- return -EINVAL;
- }
+ if (mem_size == 0)
+ goto out;
+
mem_limit = mem_size;
}
}
+out:
free(tmp_cmdline);
- return 0;
+ return;
}
/*
@@ -578,7 +577,6 @@ static void process_mem_region(struct mem_vector *entry,
unsigned long image_size)
{
struct mem_vector region, overlap;
- struct slot_area slot_area;
unsigned long start_orig, end;
struct mem_vector cur_entry;
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index eaa843a52907..a480356e0ed8 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit)
push %ebx
push %ecx
push %edx
- push %edi
-
- /*
- * RIP-relative addressing is needed to access the encryption bit
- * variable. Since we are running in 32-bit mode we need this call/pop
- * sequence to get the proper relative addressing.
- */
- call 1f
-1: popl %edi
- subl $1b, %edi
-
- movl enc_bit(%edi), %eax
- cmpl $0, %eax
- jge .Lsev_exit
/* Check if running under a hypervisor */
movl $1, %eax
@@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit)
movl %ebx, %eax
andl $0x3f, %eax /* Return the encryption bit location */
- movl %eax, enc_bit(%edi)
jmp .Lsev_exit
.Lno_sev:
xor %eax, %eax
- movl %eax, enc_bit(%edi)
.Lsev_exit:
- pop %edi
pop %edx
pop %ecx
pop %ebx
@@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask)
ENDPROC(set_sev_encryption_mask)
.data
-enc_bit:
- .int 0xffffffff
#ifdef CONFIG_AMD_MEM_ENCRYPT
.balign 8
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index a423bdb42686..a1d5918765f3 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -9,6 +9,7 @@
* paravirt and debugging variants are added.)
*/
#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_XXL
#undef CONFIG_PARAVIRT_SPINLOCKS
#undef CONFIG_KASAN
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 850b8762e889..4c881c850125 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -300,7 +300,7 @@ _start:
# Part 2 of the header, from the old setup.S
.ascii "HdrS" # header signature
- .word 0x020d # header version number (>= 0x0105)
+ .word 0x020e # header version number (>= 0x0105)
# or else old loadlin-1.5 will fail)
.globl realmode_swtch
realmode_swtch: .word 0, 0 # default_switch, SETUPSEG
@@ -558,6 +558,10 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr
init_size: .long INIT_SIZE # kernel initialization size
handover_offset: .long 0 # Filled in by build.c
+acpi_rsdp_addr: .quad 0 # 64-bit physical pointer to the
+ # ACPI RSDP table, added with
+ # version 2.14
+
# End of setup header #####################################################
.section ".entrytext", "ax"
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index d4e6cd4577e5..bf0e82400358 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -391,6 +391,13 @@ int main(int argc, char ** argv)
die("Unable to mmap '%s': %m", argv[2]);
/* Number of 16-byte paragraphs, including space for a 4-byte CRC */
sys_size = (sz + 15 + 4) / 16;
+#ifdef CONFIG_EFI_STUB
+ /*
+ * COFF requires minimum 32-byte alignment of sections, and
+ * adding a signature is problematic without that alignment.
+ */
+ sys_size = (sys_size + 1) & ~1;
+#endif
/* Patch the setup code with the appropriate size parameters */
buf[0x1f1] = setup_sectors-1;
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 0eb9f92f3717..6c3ab05c231d 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -247,6 +247,7 @@ CONFIG_USB_HIDDEV=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index e32fc1f274d8..ac9ae487cfeb 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -243,6 +243,7 @@ CONFIG_USB_HIDDEV=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index a450ad573dcb..a4b0007a54e1 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -60,9 +60,6 @@ endif
ifeq ($(avx2_supported),yes)
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
- obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb/
- obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb/
- obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb/
obj-$(CONFIG_CRYPTO_MORUS1280_AVX2) += morus1280-avx2.o
endif
@@ -106,7 +103,7 @@ ifeq ($(avx2_supported),yes)
morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o
endif
-aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
+aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index acd11b3bf639..2a356b948720 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
index 2071c3d1ae07..dbe8bb980da1 100644
--- a/arch/x86/crypto/aegis128l-aesni-glue.c
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
index b5f2a8fd5a71..8bebda2de92f 100644
--- a/arch/x86/crypto/aegis256-aesni-glue.c
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index acbe7e8336d8..661f7daf43da 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -102,9 +102,6 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv);
-int crypto_fpu_init(void);
-void crypto_fpu_exit(void);
-
#define AVX_GEN2_OPTSIZE 640
#define AVX_GEN4_OPTSIZE 4096
@@ -817,7 +814,7 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req,
/* Linearize assoc, if not already linear */
if (req->src->length >= assoclen && req->src->length &&
(!PageHighMem(sg_page(req->src)) ||
- req->src->offset + req->src->length < PAGE_SIZE)) {
+ req->src->offset + req->src->length <= PAGE_SIZE)) {
scatterwalk_start(&assoc_sg_walk, req->src);
assoc = scatterwalk_map(&assoc_sg_walk);
} else {
@@ -1253,22 +1250,6 @@ static struct skcipher_alg aesni_skciphers[] = {
static
struct simd_skcipher_alg *aesni_simd_skciphers[ARRAY_SIZE(aesni_skciphers)];
-static struct {
- const char *algname;
- const char *drvname;
- const char *basename;
- struct simd_skcipher_alg *simd;
-} aesni_simd_skciphers2[] = {
-#if (defined(MODULE) && IS_ENABLED(CONFIG_CRYPTO_PCBC)) || \
- IS_BUILTIN(CONFIG_CRYPTO_PCBC)
- {
- .algname = "pcbc(aes)",
- .drvname = "pcbc-aes-aesni",
- .basename = "fpu(pcbc(__aes-aesni))",
- },
-#endif
-};
-
#ifdef CONFIG_X86_64
static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
unsigned int key_len)
@@ -1422,10 +1403,6 @@ static void aesni_free_simds(void)
for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers) &&
aesni_simd_skciphers[i]; i++)
simd_skcipher_free(aesni_simd_skciphers[i]);
-
- for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++)
- if (aesni_simd_skciphers2[i].simd)
- simd_skcipher_free(aesni_simd_skciphers2[i].simd);
}
static int __init aesni_init(void)
@@ -1469,13 +1446,9 @@ static int __init aesni_init(void)
#endif
#endif
- err = crypto_fpu_init();
- if (err)
- return err;
-
err = crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
if (err)
- goto fpu_exit;
+ return err;
err = crypto_register_skciphers(aesni_skciphers,
ARRAY_SIZE(aesni_skciphers));
@@ -1499,18 +1472,6 @@ static int __init aesni_init(void)
aesni_simd_skciphers[i] = simd;
}
- for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++) {
- algname = aesni_simd_skciphers2[i].algname;
- drvname = aesni_simd_skciphers2[i].drvname;
- basename = aesni_simd_skciphers2[i].basename;
- simd = simd_skcipher_create_compat(algname, drvname, basename);
- err = PTR_ERR(simd);
- if (IS_ERR(simd))
- continue;
-
- aesni_simd_skciphers2[i].simd = simd;
- }
-
return 0;
unregister_simds:
@@ -1521,8 +1482,6 @@ unregister_skciphers:
ARRAY_SIZE(aesni_skciphers));
unregister_algs:
crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
-fpu_exit:
- crypto_fpu_exit();
return err;
}
@@ -1533,8 +1492,6 @@ static void __exit aesni_exit(void)
crypto_unregister_skciphers(aesni_skciphers,
ARRAY_SIZE(aesni_skciphers));
crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
-
- crypto_fpu_exit();
}
late_initcall(aesni_init);
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
deleted file mode 100644
index 406680476c52..000000000000
--- a/arch/x86/crypto/fpu.c
+++ /dev/null
@@ -1,207 +0,0 @@
-/*
- * FPU: Wrapper for blkcipher touching fpu
- *
- * Copyright (c) Intel Corp.
- * Author: Huang Ying <ying.huang@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/skcipher.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <asm/fpu/api.h>
-
-struct crypto_fpu_ctx {
- struct crypto_skcipher *child;
-};
-
-static int crypto_fpu_setkey(struct crypto_skcipher *parent, const u8 *key,
- unsigned int keylen)
-{
- struct crypto_fpu_ctx *ctx = crypto_skcipher_ctx(parent);
- struct crypto_skcipher *child = ctx->child;
- int err;
-
- crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
- crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
- CRYPTO_TFM_REQ_MASK);
- err = crypto_skcipher_setkey(child, key, keylen);
- crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
- CRYPTO_TFM_RES_MASK);
- return err;
-}
-
-static int crypto_fpu_encrypt(struct skcipher_request *req)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct crypto_fpu_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct crypto_skcipher *child = ctx->child;
- SKCIPHER_REQUEST_ON_STACK(subreq, child);
- int err;
-
- skcipher_request_set_tfm(subreq, child);
- skcipher_request_set_callback(subreq, 0, NULL, NULL);
- skcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
- req->iv);
-
- kernel_fpu_begin();
- err = crypto_skcipher_encrypt(subreq);
- kernel_fpu_end();
-
- skcipher_request_zero(subreq);
- return err;
-}
-
-static int crypto_fpu_decrypt(struct skcipher_request *req)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct crypto_fpu_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct crypto_skcipher *child = ctx->child;
- SKCIPHER_REQUEST_ON_STACK(subreq, child);
- int err;
-
- skcipher_request_set_tfm(subreq, child);
- skcipher_request_set_callback(subreq, 0, NULL, NULL);
- skcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen,
- req->iv);
-
- kernel_fpu_begin();
- err = crypto_skcipher_decrypt(subreq);
- kernel_fpu_end();
-
- skcipher_request_zero(subreq);
- return err;
-}
-
-static int crypto_fpu_init_tfm(struct crypto_skcipher *tfm)
-{
- struct skcipher_instance *inst = skcipher_alg_instance(tfm);
- struct crypto_fpu_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct crypto_skcipher_spawn *spawn;
- struct crypto_skcipher *cipher;
-
- spawn = skcipher_instance_ctx(inst);
- cipher = crypto_spawn_skcipher(spawn);
- if (IS_ERR(cipher))
- return PTR_ERR(cipher);
-
- ctx->child = cipher;
-
- return 0;
-}
-
-static void crypto_fpu_exit_tfm(struct crypto_skcipher *tfm)
-{
- struct crypto_fpu_ctx *ctx = crypto_skcipher_ctx(tfm);
-
- crypto_free_skcipher(ctx->child);
-}
-
-static void crypto_fpu_free(struct skcipher_instance *inst)
-{
- crypto_drop_skcipher(skcipher_instance_ctx(inst));
- kfree(inst);
-}
-
-static int crypto_fpu_create(struct crypto_template *tmpl, struct rtattr **tb)
-{
- struct crypto_skcipher_spawn *spawn;
- struct skcipher_instance *inst;
- struct crypto_attr_type *algt;
- struct skcipher_alg *alg;
- const char *cipher_name;
- int err;
-
- algt = crypto_get_attr_type(tb);
- if (IS_ERR(algt))
- return PTR_ERR(algt);
-
- if ((algt->type ^ (CRYPTO_ALG_INTERNAL | CRYPTO_ALG_TYPE_SKCIPHER)) &
- algt->mask)
- return -EINVAL;
-
- if (!(algt->mask & CRYPTO_ALG_INTERNAL))
- return -EINVAL;
-
- cipher_name = crypto_attr_alg_name(tb[1]);
- if (IS_ERR(cipher_name))
- return PTR_ERR(cipher_name);
-
- inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
- if (!inst)
- return -ENOMEM;
-
- spawn = skcipher_instance_ctx(inst);
-
- crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
- err = crypto_grab_skcipher(spawn, cipher_name, CRYPTO_ALG_INTERNAL,
- CRYPTO_ALG_INTERNAL | CRYPTO_ALG_ASYNC);
- if (err)
- goto out_free_inst;
-
- alg = crypto_skcipher_spawn_alg(spawn);
-
- err = crypto_inst_setname(skcipher_crypto_instance(inst), "fpu",
- &alg->base);
- if (err)
- goto out_drop_skcipher;
-
- inst->alg.base.cra_flags = CRYPTO_ALG_INTERNAL;
- inst->alg.base.cra_priority = alg->base.cra_priority;
- inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
- inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
-
- inst->alg.ivsize = crypto_skcipher_alg_ivsize(alg);
- inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg);
- inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(alg);
-
- inst->alg.base.cra_ctxsize = sizeof(struct crypto_fpu_ctx);
-
- inst->alg.init = crypto_fpu_init_tfm;
- inst->alg.exit = crypto_fpu_exit_tfm;
-
- inst->alg.setkey = crypto_fpu_setkey;
- inst->alg.encrypt = crypto_fpu_encrypt;
- inst->alg.decrypt = crypto_fpu_decrypt;
-
- inst->free = crypto_fpu_free;
-
- err = skcipher_register_instance(tmpl, inst);
- if (err)
- goto out_drop_skcipher;
-
-out:
- return err;
-
-out_drop_skcipher:
- crypto_drop_skcipher(spawn);
-out_free_inst:
- kfree(inst);
- goto out;
-}
-
-static struct crypto_template crypto_fpu_tmpl = {
- .name = "fpu",
- .create = crypto_fpu_create,
- .module = THIS_MODULE,
-};
-
-int __init crypto_fpu_init(void)
-{
- return crypto_register_template(&crypto_fpu_tmpl);
-}
-
-void crypto_fpu_exit(void)
-{
- crypto_unregister_template(&crypto_fpu_tmpl);
-}
-
-MODULE_ALIAS_CRYPTO("fpu");
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
index 95cf857d2cbb..f40244eaf14d 100644
--- a/arch/x86/crypto/morus1280-sse2-glue.c
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
static int __init crypto_morus1280_sse2_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
index 615fb7bc9a32..9afaf8f8565a 100644
--- a/arch/x86/crypto/morus640-sse2-glue.c
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
static int __init crypto_morus640_sse2_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/sha1-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile
deleted file mode 100644
index 815ded3ba90e..000000000000
--- a/arch/x86/crypto/sha1-mb/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Arch-specific CryptoAPI modules.
-#
-
-OBJECT_FILES_NON_STANDARD := y
-
-avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
- $(comma)4)$(comma)%ymm2,yes,no)
-ifeq ($(avx2_supported),yes)
- obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb.o
- sha1-mb-y := sha1_mb.o sha1_mb_mgr_flush_avx2.o \
- sha1_mb_mgr_init_avx2.o sha1_mb_mgr_submit_avx2.o sha1_x8_avx2.o
-endif
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
deleted file mode 100644
index b93805664c1d..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb.c
+++ /dev/null
@@ -1,1011 +0,0 @@
-/*
- * Multi buffer SHA1 algorithm Glue Code
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
-#include <crypto/mcryptd.h>
-#include <crypto/crypto_wq.h>
-#include <asm/byteorder.h>
-#include <linux/hardirq.h>
-#include <asm/fpu/api.h>
-#include "sha1_mb_ctx.h"
-
-#define FLUSH_INTERVAL 1000 /* in usec */
-
-static struct mcryptd_alg_state sha1_mb_alg_state;
-
-struct sha1_mb_ctx {
- struct mcryptd_ahash *mcryptd_tfm;
-};
-
-static inline struct mcryptd_hash_request_ctx
- *cast_hash_to_mcryptd_ctx(struct sha1_hash_ctx *hash_ctx)
-{
- struct ahash_request *areq;
-
- areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
- return container_of(areq, struct mcryptd_hash_request_ctx, areq);
-}
-
-static inline struct ahash_request
- *cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
-{
- return container_of((void *) ctx, struct ahash_request, __ctx);
-}
-
-static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
- struct ahash_request *areq)
-{
- rctx->flag = HASH_UPDATE;
-}
-
-static asmlinkage void (*sha1_job_mgr_init)(struct sha1_mb_mgr *state);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)
- (struct sha1_mb_mgr *state, struct job_sha1 *job);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)
- (struct sha1_mb_mgr *state);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)
- (struct sha1_mb_mgr *state);
-
-static inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2],
- uint64_t total_len)
-{
- uint32_t i = total_len & (SHA1_BLOCK_SIZE - 1);
-
- memset(&padblock[i], 0, SHA1_BLOCK_SIZE);
- padblock[i] = 0x80;
-
- i += ((SHA1_BLOCK_SIZE - 1) &
- (0 - (total_len + SHA1_PADLENGTHFIELD_SIZE + 1)))
- + 1 + SHA1_PADLENGTHFIELD_SIZE;
-
-#if SHA1_PADLENGTHFIELD_SIZE == 16
- *((uint64_t *) &padblock[i - 16]) = 0;
-#endif
-
- *((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
-
- /* Number of extra blocks to hash */
- return i >> SHA1_LOG2_BLOCK_SIZE;
-}
-
-static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr,
- struct sha1_hash_ctx *ctx)
-{
- while (ctx) {
- if (ctx->status & HASH_CTX_STS_COMPLETE) {
- /* Clear PROCESSING bit */
- ctx->status = HASH_CTX_STS_COMPLETE;
- return ctx;
- }
-
- /*
- * If the extra blocks are empty, begin hashing what remains
- * in the user's buffer.
- */
- if (ctx->partial_block_buffer_length == 0 &&
- ctx->incoming_buffer_length) {
-
- const void *buffer = ctx->incoming_buffer;
- uint32_t len = ctx->incoming_buffer_length;
- uint32_t copy_len;
-
- /*
- * Only entire blocks can be hashed.
- * Copy remainder to extra blocks buffer.
- */
- copy_len = len & (SHA1_BLOCK_SIZE-1);
-
- if (copy_len) {
- len -= copy_len;
- memcpy(ctx->partial_block_buffer,
- ((const char *) buffer + len),
- copy_len);
- ctx->partial_block_buffer_length = copy_len;
- }
-
- ctx->incoming_buffer_length = 0;
-
- /* len should be a multiple of the block size now */
- assert((len % SHA1_BLOCK_SIZE) == 0);
-
- /* Set len to the number of blocks to be hashed */
- len >>= SHA1_LOG2_BLOCK_SIZE;
-
- if (len) {
-
- ctx->job.buffer = (uint8_t *) buffer;
- ctx->job.len = len;
- ctx = (struct sha1_hash_ctx *)sha1_job_mgr_submit(&mgr->mgr,
- &ctx->job);
- continue;
- }
- }
-
- /*
- * If the extra blocks are not empty, then we are
- * either on the last block(s) or we need more
- * user input before continuing.
- */
- if (ctx->status & HASH_CTX_STS_LAST) {
-
- uint8_t *buf = ctx->partial_block_buffer;
- uint32_t n_extra_blocks =
- sha1_pad(buf, ctx->total_length);
-
- ctx->status = (HASH_CTX_STS_PROCESSING |
- HASH_CTX_STS_COMPLETE);
- ctx->job.buffer = buf;
- ctx->job.len = (uint32_t) n_extra_blocks;
- ctx = (struct sha1_hash_ctx *)
- sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
- continue;
- }
-
- ctx->status = HASH_CTX_STS_IDLE;
- return ctx;
- }
-
- return NULL;
-}
-
-static struct sha1_hash_ctx
- *sha1_ctx_mgr_get_comp_ctx(struct sha1_ctx_mgr *mgr)
-{
- /*
- * If get_comp_job returns NULL, there are no jobs complete.
- * If get_comp_job returns a job, verify that it is safe to return to
- * the user.
- * If it is not ready, resubmit the job to finish processing.
- * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
- * Otherwise, all jobs currently being managed by the hash_ctx_mgr
- * still need processing.
- */
- struct sha1_hash_ctx *ctx;
-
- ctx = (struct sha1_hash_ctx *) sha1_job_mgr_get_comp_job(&mgr->mgr);
- return sha1_ctx_mgr_resubmit(mgr, ctx);
-}
-
-static void sha1_ctx_mgr_init(struct sha1_ctx_mgr *mgr)
-{
- sha1_job_mgr_init(&mgr->mgr);
-}
-
-static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
- struct sha1_hash_ctx *ctx,
- const void *buffer,
- uint32_t len,
- int flags)
-{
- if (flags & ~(HASH_UPDATE | HASH_LAST)) {
- /* User should not pass anything other than UPDATE or LAST */
- ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
- return ctx;
- }
-
- if (ctx->status & HASH_CTX_STS_PROCESSING) {
- /* Cannot submit to a currently processing job. */
- ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
- return ctx;
- }
-
- if (ctx->status & HASH_CTX_STS_COMPLETE) {
- /* Cannot update a finished job. */
- ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
- return ctx;
- }
-
- /*
- * If we made it here, there were no errors during this call to
- * submit
- */
- ctx->error = HASH_CTX_ERROR_NONE;
-
- /* Store buffer ptr info from user */
- ctx->incoming_buffer = buffer;
- ctx->incoming_buffer_length = len;
-
- /*
- * Store the user's request flags and mark this ctx as currently
- * being processed.
- */
- ctx->status = (flags & HASH_LAST) ?
- (HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
- HASH_CTX_STS_PROCESSING;
-
- /* Advance byte counter */
- ctx->total_length += len;
-
- /*
- * If there is anything currently buffered in the extra blocks,
- * append to it until it contains a whole block.
- * Or if the user's buffer contains less than a whole block,
- * append as much as possible to the extra block.
- */
- if (ctx->partial_block_buffer_length || len < SHA1_BLOCK_SIZE) {
- /*
- * Compute how many bytes to copy from user buffer into
- * extra block
- */
- uint32_t copy_len = SHA1_BLOCK_SIZE -
- ctx->partial_block_buffer_length;
- if (len < copy_len)
- copy_len = len;
-
- if (copy_len) {
- /* Copy and update relevant pointers and counters */
- memcpy(&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
- buffer, copy_len);
-
- ctx->partial_block_buffer_length += copy_len;
- ctx->incoming_buffer = (const void *)
- ((const char *)buffer + copy_len);
- ctx->incoming_buffer_length = len - copy_len;
- }
-
- /*
- * The extra block should never contain more than 1 block
- * here
- */
- assert(ctx->partial_block_buffer_length <= SHA1_BLOCK_SIZE);
-
- /*
- * If the extra block buffer contains exactly 1 block, it can
- * be hashed.
- */
- if (ctx->partial_block_buffer_length >= SHA1_BLOCK_SIZE) {
- ctx->partial_block_buffer_length = 0;
-
- ctx->job.buffer = ctx->partial_block_buffer;
- ctx->job.len = 1;
- ctx = (struct sha1_hash_ctx *)
- sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
- }
- }
-
- return sha1_ctx_mgr_resubmit(mgr, ctx);
-}
-
-static struct sha1_hash_ctx *sha1_ctx_mgr_flush(struct sha1_ctx_mgr *mgr)
-{
- struct sha1_hash_ctx *ctx;
-
- while (1) {
- ctx = (struct sha1_hash_ctx *) sha1_job_mgr_flush(&mgr->mgr);
-
- /* If flush returned 0, there are no more jobs in flight. */
- if (!ctx)
- return NULL;
-
- /*
- * If flush returned a job, resubmit the job to finish
- * processing.
- */
- ctx = sha1_ctx_mgr_resubmit(mgr, ctx);
-
- /*
- * If sha1_ctx_mgr_resubmit returned a job, it is ready to be
- * returned. Otherwise, all jobs currently being managed by the
- * sha1_ctx_mgr still need processing. Loop.
- */
- if (ctx)
- return ctx;
- }
-}
-
-static int sha1_mb_init(struct ahash_request *areq)
-{
- struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
-
- hash_ctx_init(sctx);
- sctx->job.result_digest[0] = SHA1_H0;
- sctx->job.result_digest[1] = SHA1_H1;
- sctx->job.result_digest[2] = SHA1_H2;
- sctx->job.result_digest[3] = SHA1_H3;
- sctx->job.result_digest[4] = SHA1_H4;
- sctx->total_length = 0;
- sctx->partial_block_buffer_length = 0;
- sctx->status = HASH_CTX_STS_IDLE;
-
- return 0;
-}
-
-static int sha1_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
-{
- int i;
- struct sha1_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
- __be32 *dst = (__be32 *) rctx->out;
-
- for (i = 0; i < 5; ++i)
- dst[i] = cpu_to_be32(sctx->job.result_digest[i]);
-
- return 0;
-}
-
-static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
- struct mcryptd_alg_cstate *cstate, bool flush)
-{
- int flag = HASH_UPDATE;
- int nbytes, err = 0;
- struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
- struct sha1_hash_ctx *sha_ctx;
-
- /* more work ? */
- while (!(rctx->flag & HASH_DONE)) {
- nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
- if (nbytes < 0) {
- err = nbytes;
- goto out;
- }
- /* check if the walk is done */
- if (crypto_ahash_walk_last(&rctx->walk)) {
- rctx->flag |= HASH_DONE;
- if (rctx->flag & HASH_FINAL)
- flag |= HASH_LAST;
-
- }
- sha_ctx = (struct sha1_hash_ctx *)
- ahash_request_ctx(&rctx->areq);
- kernel_fpu_begin();
- sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx,
- rctx->walk.data, nbytes, flag);
- if (!sha_ctx) {
- if (flush)
- sha_ctx = sha1_ctx_mgr_flush(cstate->mgr);
- }
- kernel_fpu_end();
- if (sha_ctx)
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- else {
- rctx = NULL;
- goto out;
- }
- }
-
- /* copy the results */
- if (rctx->flag & HASH_FINAL)
- sha1_mb_set_results(rctx);
-
-out:
- *ret_rctx = rctx;
- return err;
-}
-
-static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
- struct mcryptd_alg_cstate *cstate,
- int err)
-{
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha1_hash_ctx *sha_ctx;
- struct mcryptd_hash_request_ctx *req_ctx;
- int ret;
-
- /* remove from work list */
- spin_lock(&cstate->work_lock);
- list_del(&rctx->waiter);
- spin_unlock(&cstate->work_lock);
-
- if (irqs_disabled())
- rctx->complete(&req->base, err);
- else {
- local_bh_disable();
- rctx->complete(&req->base, err);
- local_bh_enable();
- }
-
- /* check to see if there are other jobs that are done */
- sha_ctx = sha1_ctx_mgr_get_comp_ctx(cstate->mgr);
- while (sha_ctx) {
- req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&req_ctx, cstate, false);
- if (req_ctx) {
- spin_lock(&cstate->work_lock);
- list_del(&req_ctx->waiter);
- spin_unlock(&cstate->work_lock);
-
- req = cast_mcryptd_ctx_to_req(req_ctx);
- if (irqs_disabled())
- req_ctx->complete(&req->base, ret);
- else {
- local_bh_disable();
- req_ctx->complete(&req->base, ret);
- local_bh_enable();
- }
- }
- sha_ctx = sha1_ctx_mgr_get_comp_ctx(cstate->mgr);
- }
-
- return 0;
-}
-
-static void sha1_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
- struct mcryptd_alg_cstate *cstate)
-{
- unsigned long next_flush;
- unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
-
- /* initialize tag */
- rctx->tag.arrival = jiffies; /* tag the arrival time */
- rctx->tag.seq_num = cstate->next_seq_num++;
- next_flush = rctx->tag.arrival + delay;
- rctx->tag.expire = next_flush;
-
- spin_lock(&cstate->work_lock);
- list_add_tail(&rctx->waiter, &cstate->work_list);
- spin_unlock(&cstate->work_lock);
-
- mcryptd_arm_flusher(cstate, delay);
-}
-
-static int sha1_mb_update(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx, areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
-
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha1_hash_ctx *sha_ctx;
- int ret = 0, nbytes;
-
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- nbytes = crypto_ahash_walk_first(req, &rctx->walk);
-
- if (nbytes < 0) {
- ret = nbytes;
- goto done;
- }
-
- if (crypto_ahash_walk_last(&rctx->walk))
- rctx->flag |= HASH_DONE;
-
- /* submit */
- sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
- sha1_mb_add_list(rctx, cstate);
- kernel_fpu_begin();
- sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
- nbytes, HASH_UPDATE);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
-
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha1_mb_finup(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx, areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
-
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha1_hash_ctx *sha_ctx;
- int ret = 0, flag = HASH_UPDATE, nbytes;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- nbytes = crypto_ahash_walk_first(req, &rctx->walk);
-
- if (nbytes < 0) {
- ret = nbytes;
- goto done;
- }
-
- if (crypto_ahash_walk_last(&rctx->walk)) {
- rctx->flag |= HASH_DONE;
- flag = HASH_LAST;
- }
-
- /* submit */
- rctx->flag |= HASH_FINAL;
- sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
- sha1_mb_add_list(rctx, cstate);
-
- kernel_fpu_begin();
- sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
- nbytes, flag);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha1_mb_final(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx, areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
-
- struct sha1_hash_ctx *sha_ctx;
- int ret = 0;
- u8 data;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- rctx->flag |= HASH_DONE | HASH_FINAL;
-
- sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
- /* flag HASH_FINAL and 0 data size */
- sha1_mb_add_list(rctx, cstate);
- kernel_fpu_begin();
- sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
- HASH_LAST);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha1_mb_export(struct ahash_request *areq, void *out)
-{
- struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
-
- memcpy(out, sctx, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha1_mb_import(struct ahash_request *areq, const void *in)
-{
- struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
-
- memcpy(sctx, in, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
-{
- struct mcryptd_ahash *mcryptd_tfm;
- struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
- struct mcryptd_hash_ctx *mctx;
-
- mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb",
- CRYPTO_ALG_INTERNAL,
- CRYPTO_ALG_INTERNAL);
- if (IS_ERR(mcryptd_tfm))
- return PTR_ERR(mcryptd_tfm);
- mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
- mctx->alg_state = &sha1_mb_alg_state;
- ctx->mcryptd_tfm = mcryptd_tfm;
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- crypto_ahash_reqsize(&mcryptd_tfm->base));
-
- return 0;
-}
-
-static void sha1_mb_async_exit_tfm(struct crypto_tfm *tfm)
-{
- struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
- mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
-static int sha1_mb_areq_init_tfm(struct crypto_tfm *tfm)
-{
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- sizeof(struct sha1_hash_ctx));
-
- return 0;
-}
-
-static void sha1_mb_areq_exit_tfm(struct crypto_tfm *tfm)
-{
- struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
- mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
-static struct ahash_alg sha1_mb_areq_alg = {
- .init = sha1_mb_init,
- .update = sha1_mb_update,
- .final = sha1_mb_final,
- .finup = sha1_mb_finup,
- .export = sha1_mb_export,
- .import = sha1_mb_import,
- .halg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .statesize = sizeof(struct sha1_hash_ctx),
- .base = {
- .cra_name = "__sha1-mb",
- .cra_driver_name = "__intel_sha1-mb",
- .cra_priority = 100,
- /*
- * use ASYNC flag as some buffers in multi-buffer
- * algo may not have completed before hashing thread
- * sleep
- */
- .cra_flags = CRYPTO_ALG_ASYNC |
- CRYPTO_ALG_INTERNAL,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT
- (sha1_mb_areq_alg.halg.base.cra_list),
- .cra_init = sha1_mb_areq_init_tfm,
- .cra_exit = sha1_mb_areq_exit_tfm,
- .cra_ctxsize = sizeof(struct sha1_hash_ctx),
- }
- }
-};
-
-static int sha1_mb_async_init(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_init(mcryptd_req);
-}
-
-static int sha1_mb_async_update(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_update(mcryptd_req);
-}
-
-static int sha1_mb_async_finup(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_finup(mcryptd_req);
-}
-
-static int sha1_mb_async_final(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_final(mcryptd_req);
-}
-
-static int sha1_mb_async_digest(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_digest(mcryptd_req);
-}
-
-static int sha1_mb_async_export(struct ahash_request *req, void *out)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_export(mcryptd_req, out);
-}
-
-static int sha1_mb_async_import(struct ahash_request *req, const void *in)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
- struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
- struct mcryptd_hash_request_ctx *rctx;
- struct ahash_request *areq;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- rctx = ahash_request_ctx(mcryptd_req);
- areq = &rctx->areq;
-
- ahash_request_set_tfm(areq, child);
- ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
- rctx->complete, req);
-
- return crypto_ahash_import(mcryptd_req, in);
-}
-
-static struct ahash_alg sha1_mb_async_alg = {
- .init = sha1_mb_async_init,
- .update = sha1_mb_async_update,
- .final = sha1_mb_async_final,
- .finup = sha1_mb_async_finup,
- .digest = sha1_mb_async_digest,
- .export = sha1_mb_async_export,
- .import = sha1_mb_async_import,
- .halg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .statesize = sizeof(struct sha1_hash_ctx),
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1_mb",
- /*
- * Low priority, since with few concurrent hash requests
- * this is extremely slow due to the flush delay. Users
- * whose workloads would benefit from this can request
- * it explicitly by driver name, or can increase its
- * priority at runtime using NETLINK_CRYPTO.
- */
- .cra_priority = 50,
- .cra_flags = CRYPTO_ALG_ASYNC,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(sha1_mb_async_alg.halg.base.cra_list),
- .cra_init = sha1_mb_async_init_tfm,
- .cra_exit = sha1_mb_async_exit_tfm,
- .cra_ctxsize = sizeof(struct sha1_mb_ctx),
- .cra_alignmask = 0,
- },
- },
-};
-
-static unsigned long sha1_mb_flusher(struct mcryptd_alg_cstate *cstate)
-{
- struct mcryptd_hash_request_ctx *rctx;
- unsigned long cur_time;
- unsigned long next_flush = 0;
- struct sha1_hash_ctx *sha_ctx;
-
-
- cur_time = jiffies;
-
- while (!list_empty(&cstate->work_list)) {
- rctx = list_entry(cstate->work_list.next,
- struct mcryptd_hash_request_ctx, waiter);
- if (time_before(cur_time, rctx->tag.expire))
- break;
- kernel_fpu_begin();
- sha_ctx = (struct sha1_hash_ctx *)
- sha1_ctx_mgr_flush(cstate->mgr);
- kernel_fpu_end();
- if (!sha_ctx) {
- pr_err("sha1_mb error: nothing got flushed for non-empty list\n");
- break;
- }
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- sha_finish_walk(&rctx, cstate, true);
- sha_complete_job(rctx, cstate, 0);
- }
-
- if (!list_empty(&cstate->work_list)) {
- rctx = list_entry(cstate->work_list.next,
- struct mcryptd_hash_request_ctx, waiter);
- /* get the hash context and then flush time */
- next_flush = rctx->tag.expire;
- mcryptd_arm_flusher(cstate, get_delay(next_flush));
- }
- return next_flush;
-}
-
-static int __init sha1_mb_mod_init(void)
-{
-
- int cpu;
- int err;
- struct mcryptd_alg_cstate *cpu_state;
-
- /* check for dependent cpu features */
- if (!boot_cpu_has(X86_FEATURE_AVX2) ||
- !boot_cpu_has(X86_FEATURE_BMI2))
- return -ENODEV;
-
- /* initialize multibuffer structures */
- sha1_mb_alg_state.alg_cstate = alloc_percpu(struct mcryptd_alg_cstate);
-
- sha1_job_mgr_init = sha1_mb_mgr_init_avx2;
- sha1_job_mgr_submit = sha1_mb_mgr_submit_avx2;
- sha1_job_mgr_flush = sha1_mb_mgr_flush_avx2;
- sha1_job_mgr_get_comp_job = sha1_mb_mgr_get_comp_job_avx2;
-
- if (!sha1_mb_alg_state.alg_cstate)
- return -ENOMEM;
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
- cpu_state->next_flush = 0;
- cpu_state->next_seq_num = 0;
- cpu_state->flusher_engaged = false;
- INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
- cpu_state->cpu = cpu;
- cpu_state->alg_state = &sha1_mb_alg_state;
- cpu_state->mgr = kzalloc(sizeof(struct sha1_ctx_mgr),
- GFP_KERNEL);
- if (!cpu_state->mgr)
- goto err2;
- sha1_ctx_mgr_init(cpu_state->mgr);
- INIT_LIST_HEAD(&cpu_state->work_list);
- spin_lock_init(&cpu_state->work_lock);
- }
- sha1_mb_alg_state.flusher = &sha1_mb_flusher;
-
- err = crypto_register_ahash(&sha1_mb_areq_alg);
- if (err)
- goto err2;
- err = crypto_register_ahash(&sha1_mb_async_alg);
- if (err)
- goto err1;
-
-
- return 0;
-err1:
- crypto_unregister_ahash(&sha1_mb_areq_alg);
-err2:
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
- kfree(cpu_state->mgr);
- }
- free_percpu(sha1_mb_alg_state.alg_cstate);
- return -ENODEV;
-}
-
-static void __exit sha1_mb_mod_fini(void)
-{
- int cpu;
- struct mcryptd_alg_cstate *cpu_state;
-
- crypto_unregister_ahash(&sha1_mb_async_alg);
- crypto_unregister_ahash(&sha1_mb_areq_alg);
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
- kfree(cpu_state->mgr);
- }
- free_percpu(sha1_mb_alg_state.alg_cstate);
-}
-
-module_init(sha1_mb_mod_init);
-module_exit(sha1_mb_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, multi buffer accelerated");
-
-MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
deleted file mode 100644
index 9454bd16f9f8..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * Header file for multi buffer SHA context
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _SHA_MB_CTX_INTERNAL_H
-#define _SHA_MB_CTX_INTERNAL_H
-
-#include "sha1_mb_mgr.h"
-
-#define HASH_UPDATE 0x00
-#define HASH_LAST 0x01
-#define HASH_DONE 0x02
-#define HASH_FINAL 0x04
-
-#define HASH_CTX_STS_IDLE 0x00
-#define HASH_CTX_STS_PROCESSING 0x01
-#define HASH_CTX_STS_LAST 0x02
-#define HASH_CTX_STS_COMPLETE 0x04
-
-enum hash_ctx_error {
- HASH_CTX_ERROR_NONE = 0,
- HASH_CTX_ERROR_INVALID_FLAGS = -1,
- HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
- HASH_CTX_ERROR_ALREADY_COMPLETED = -3,
-
-#ifdef HASH_CTX_DEBUG
- HASH_CTX_ERROR_DEBUG_DIGEST_MISMATCH = -4,
-#endif
-};
-
-
-#define hash_ctx_user_data(ctx) ((ctx)->user_data)
-#define hash_ctx_digest(ctx) ((ctx)->job.result_digest)
-#define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
-#define hash_ctx_complete(ctx) ((ctx)->status == HASH_CTX_STS_COMPLETE)
-#define hash_ctx_status(ctx) ((ctx)->status)
-#define hash_ctx_error(ctx) ((ctx)->error)
-#define hash_ctx_init(ctx) \
- do { \
- (ctx)->error = HASH_CTX_ERROR_NONE; \
- (ctx)->status = HASH_CTX_STS_COMPLETE; \
- } while (0)
-
-
-/* Hash Constants and Typedefs */
-#define SHA1_DIGEST_LENGTH 5
-#define SHA1_LOG2_BLOCK_SIZE 6
-
-#define SHA1_PADLENGTHFIELD_SIZE 8
-
-#ifdef SHA_MB_DEBUG
-#define assert(expr) \
-do { \
- if (unlikely(!(expr))) { \
- printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
- #expr, __FILE__, __func__, __LINE__); \
- } \
-} while (0)
-#else
-#define assert(expr) do {} while (0)
-#endif
-
-struct sha1_ctx_mgr {
- struct sha1_mb_mgr mgr;
-};
-
-/* typedef struct sha1_ctx_mgr sha1_ctx_mgr; */
-
-struct sha1_hash_ctx {
- /* Must be at struct offset 0 */
- struct job_sha1 job;
- /* status flag */
- int status;
- /* error flag */
- int error;
-
- uint64_t total_length;
- const void *incoming_buffer;
- uint32_t incoming_buffer_length;
- uint8_t partial_block_buffer[SHA1_BLOCK_SIZE * 2];
- uint32_t partial_block_buffer_length;
- void *user_data;
-};
-
-#endif
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr.h b/arch/x86/crypto/sha1-mb/sha1_mb_mgr.h
deleted file mode 100644
index 08ad1a9acfd7..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * Header file for multi buffer SHA1 algorithm manager
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * James Guilford <james.guilford@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-#ifndef __SHA_MB_MGR_H
-#define __SHA_MB_MGR_H
-
-
-#include <linux/types.h>
-
-#define NUM_SHA1_DIGEST_WORDS 5
-
-enum job_sts { STS_UNKNOWN = 0,
- STS_BEING_PROCESSED = 1,
- STS_COMPLETED = 2,
- STS_INTERNAL_ERROR = 3,
- STS_ERROR = 4
-};
-
-struct job_sha1 {
- u8 *buffer;
- u32 len;
- u32 result_digest[NUM_SHA1_DIGEST_WORDS] __aligned(32);
- enum job_sts status;
- void *user_data;
-};
-
-/* SHA1 out-of-order scheduler */
-
-/* typedef uint32_t sha1_digest_array[5][8]; */
-
-struct sha1_args_x8 {
- uint32_t digest[5][8];
- uint8_t *data_ptr[8];
-};
-
-struct sha1_lane_data {
- struct job_sha1 *job_in_lane;
-};
-
-struct sha1_mb_mgr {
- struct sha1_args_x8 args;
-
- uint32_t lens[8];
-
- /* each byte is index (0...7) of unused lanes */
- uint64_t unused_lanes;
- /* byte 4 is set to FF as a flag */
- struct sha1_lane_data ldata[8];
-};
-
-
-#define SHA1_MB_MGR_NUM_LANES_AVX2 8
-
-void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state);
-struct job_sha1 *sha1_mb_mgr_submit_avx2(struct sha1_mb_mgr *state,
- struct job_sha1 *job);
-struct job_sha1 *sha1_mb_mgr_flush_avx2(struct sha1_mb_mgr *state);
-struct job_sha1 *sha1_mb_mgr_get_comp_job_avx2(struct sha1_mb_mgr *state);
-
-#endif
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S
deleted file mode 100644
index 86688c6e7a25..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S
+++ /dev/null
@@ -1,287 +0,0 @@
-/*
- * Header file for multi buffer SHA1 algorithm data structure
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * James Guilford <james.guilford@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-# Macros for defining data structures
-
-# Usage example
-
-#START_FIELDS # JOB_AES
-### name size align
-#FIELD _plaintext, 8, 8 # pointer to plaintext
-#FIELD _ciphertext, 8, 8 # pointer to ciphertext
-#FIELD _IV, 16, 8 # IV
-#FIELD _keys, 8, 8 # pointer to keys
-#FIELD _len, 4, 4 # length in bytes
-#FIELD _status, 4, 4 # status enumeration
-#FIELD _user_data, 8, 8 # pointer to user data
-#UNION _union, size1, align1, \
-# size2, align2, \
-# size3, align3, \
-# ...
-#END_FIELDS
-#%assign _JOB_AES_size _FIELD_OFFSET
-#%assign _JOB_AES_align _STRUCT_ALIGN
-
-#########################################################################
-
-# Alternate "struc-like" syntax:
-# STRUCT job_aes2
-# RES_Q .plaintext, 1
-# RES_Q .ciphertext, 1
-# RES_DQ .IV, 1
-# RES_B .nested, _JOB_AES_SIZE, _JOB_AES_ALIGN
-# RES_U .union, size1, align1, \
-# size2, align2, \
-# ...
-# ENDSTRUCT
-# # Following only needed if nesting
-# %assign job_aes2_size _FIELD_OFFSET
-# %assign job_aes2_align _STRUCT_ALIGN
-#
-# RES_* macros take a name, a count and an optional alignment.
-# The count in in terms of the base size of the macro, and the
-# default alignment is the base size.
-# The macros are:
-# Macro Base size
-# RES_B 1
-# RES_W 2
-# RES_D 4
-# RES_Q 8
-# RES_DQ 16
-# RES_Y 32
-# RES_Z 64
-#
-# RES_U defines a union. It's arguments are a name and two or more
-# pairs of "size, alignment"
-#
-# The two assigns are only needed if this structure is being nested
-# within another. Even if the assigns are not done, one can still use
-# STRUCT_NAME_size as the size of the structure.
-#
-# Note that for nesting, you still need to assign to STRUCT_NAME_size.
-#
-# The differences between this and using "struc" directly are that each
-# type is implicitly aligned to its natural length (although this can be
-# over-ridden with an explicit third parameter), and that the structure
-# is padded at the end to its overall alignment.
-#
-
-#########################################################################
-
-#ifndef _SHA1_MB_MGR_DATASTRUCT_ASM_
-#define _SHA1_MB_MGR_DATASTRUCT_ASM_
-
-## START_FIELDS
-.macro START_FIELDS
- _FIELD_OFFSET = 0
- _STRUCT_ALIGN = 0
-.endm
-
-## FIELD name size align
-.macro FIELD name size align
- _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
- \name = _FIELD_OFFSET
- _FIELD_OFFSET = _FIELD_OFFSET + (\size)
-.if (\align > _STRUCT_ALIGN)
- _STRUCT_ALIGN = \align
-.endif
-.endm
-
-## END_FIELDS
-.macro END_FIELDS
- _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
-.endm
-
-########################################################################
-
-.macro STRUCT p1
-START_FIELDS
-.struc \p1
-.endm
-
-.macro ENDSTRUCT
- tmp = _FIELD_OFFSET
- END_FIELDS
- tmp = (_FIELD_OFFSET - %%tmp)
-.if (tmp > 0)
- .lcomm tmp
-.endif
-.endstruc
-.endm
-
-## RES_int name size align
-.macro RES_int p1 p2 p3
- name = \p1
- size = \p2
- align = .\p3
-
- _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
-.align align
-.lcomm name size
- _FIELD_OFFSET = _FIELD_OFFSET + (size)
-.if (align > _STRUCT_ALIGN)
- _STRUCT_ALIGN = align
-.endif
-.endm
-
-
-
-# macro RES_B name, size [, align]
-.macro RES_B _name, _size, _align=1
-RES_int _name _size _align
-.endm
-
-# macro RES_W name, size [, align]
-.macro RES_W _name, _size, _align=2
-RES_int _name 2*(_size) _align
-.endm
-
-# macro RES_D name, size [, align]
-.macro RES_D _name, _size, _align=4
-RES_int _name 4*(_size) _align
-.endm
-
-# macro RES_Q name, size [, align]
-.macro RES_Q _name, _size, _align=8
-RES_int _name 8*(_size) _align
-.endm
-
-# macro RES_DQ name, size [, align]
-.macro RES_DQ _name, _size, _align=16
-RES_int _name 16*(_size) _align
-.endm
-
-# macro RES_Y name, size [, align]
-.macro RES_Y _name, _size, _align=32
-RES_int _name 32*(_size) _align
-.endm
-
-# macro RES_Z name, size [, align]
-.macro RES_Z _name, _size, _align=64
-RES_int _name 64*(_size) _align
-.endm
-
-
-#endif
-
-########################################################################
-#### Define constants
-########################################################################
-
-########################################################################
-#### Define SHA1 Out Of Order Data Structures
-########################################################################
-
-START_FIELDS # LANE_DATA
-### name size align
-FIELD _job_in_lane, 8, 8 # pointer to job object
-END_FIELDS
-
-_LANE_DATA_size = _FIELD_OFFSET
-_LANE_DATA_align = _STRUCT_ALIGN
-
-########################################################################
-
-START_FIELDS # SHA1_ARGS_X8
-### name size align
-FIELD _digest, 4*5*8, 16 # transposed digest
-FIELD _data_ptr, 8*8, 8 # array of pointers to data
-END_FIELDS
-
-_SHA1_ARGS_X4_size = _FIELD_OFFSET
-_SHA1_ARGS_X4_align = _STRUCT_ALIGN
-_SHA1_ARGS_X8_size = _FIELD_OFFSET
-_SHA1_ARGS_X8_align = _STRUCT_ALIGN
-
-########################################################################
-
-START_FIELDS # MB_MGR
-### name size align
-FIELD _args, _SHA1_ARGS_X4_size, _SHA1_ARGS_X4_align
-FIELD _lens, 4*8, 8
-FIELD _unused_lanes, 8, 8
-FIELD _ldata, _LANE_DATA_size*8, _LANE_DATA_align
-END_FIELDS
-
-_MB_MGR_size = _FIELD_OFFSET
-_MB_MGR_align = _STRUCT_ALIGN
-
-_args_digest = _args + _digest
-_args_data_ptr = _args + _data_ptr
-
-
-########################################################################
-#### Define constants
-########################################################################
-
-#define STS_UNKNOWN 0
-#define STS_BEING_PROCESSED 1
-#define STS_COMPLETED 2
-
-########################################################################
-#### Define JOB_SHA1 structure
-########################################################################
-
-START_FIELDS # JOB_SHA1
-
-### name size align
-FIELD _buffer, 8, 8 # pointer to buffer
-FIELD _len, 4, 4 # length in bytes
-FIELD _result_digest, 5*4, 32 # Digest (output)
-FIELD _status, 4, 4
-FIELD _user_data, 8, 8
-END_FIELDS
-
-_JOB_SHA1_size = _FIELD_OFFSET
-_JOB_SHA1_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
deleted file mode 100644
index 7cfba738f104..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
+++ /dev/null
@@ -1,304 +0,0 @@
-/*
- * Flush routine for SHA1 multibuffer
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * James Guilford <james.guilford@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-#include <linux/linkage.h>
-#include <asm/frame.h>
-#include "sha1_mb_mgr_datastruct.S"
-
-
-.extern sha1_x8_avx2
-
-# LINUX register definitions
-#define arg1 %rdi
-#define arg2 %rsi
-
-# Common definitions
-#define state arg1
-#define job arg2
-#define len2 arg2
-
-# idx must be a register not clobbered by sha1_x8_avx2
-#define idx %r8
-#define DWORD_idx %r8d
-
-#define unused_lanes %rbx
-#define lane_data %rbx
-#define tmp2 %rbx
-#define tmp2_w %ebx
-
-#define job_rax %rax
-#define tmp1 %rax
-#define size_offset %rax
-#define tmp %rax
-#define start_offset %rax
-
-#define tmp3 %arg1
-
-#define extra_blocks %arg2
-#define p %arg2
-
-.macro LABEL prefix n
-\prefix\n\():
-.endm
-
-.macro JNE_SKIP i
-jne skip_\i
-.endm
-
-.altmacro
-.macro SET_OFFSET _offset
-offset = \_offset
-.endm
-.noaltmacro
-
-# JOB* sha1_mb_mgr_flush_avx2(MB_MGR *state)
-# arg 1 : rcx : state
-ENTRY(sha1_mb_mgr_flush_avx2)
- FRAME_BEGIN
- push %rbx
-
- # If bit (32+3) is set, then all lanes are empty
- mov _unused_lanes(state), unused_lanes
- bt $32+3, unused_lanes
- jc return_null
-
- # find a lane with a non-null job
- xor idx, idx
- offset = (_ldata + 1 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne one(%rip), idx
- offset = (_ldata + 2 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne two(%rip), idx
- offset = (_ldata + 3 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne three(%rip), idx
- offset = (_ldata + 4 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne four(%rip), idx
- offset = (_ldata + 5 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne five(%rip), idx
- offset = (_ldata + 6 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne six(%rip), idx
- offset = (_ldata + 7 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne seven(%rip), idx
-
- # copy idx to empty lanes
-copy_lane_data:
- offset = (_args + _data_ptr)
- mov offset(state,idx,8), tmp
-
- I = 0
-.rep 8
- offset = (_ldata + I * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
-.altmacro
- JNE_SKIP %I
- offset = (_args + _data_ptr + 8*I)
- mov tmp, offset(state)
- offset = (_lens + 4*I)
- movl $0xFFFFFFFF, offset(state)
-LABEL skip_ %I
- I = (I+1)
-.noaltmacro
-.endr
-
- # Find min length
- vmovdqu _lens+0*16(state), %xmm0
- vmovdqu _lens+1*16(state), %xmm1
-
- vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
- vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
- vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min value in low dword
-
- vmovd %xmm2, DWORD_idx
- mov idx, len2
- and $0xF, idx
- shr $4, len2
- jz len_is_0
-
- vpand clear_low_nibble(%rip), %xmm2, %xmm2
- vpshufd $0, %xmm2, %xmm2
-
- vpsubd %xmm2, %xmm0, %xmm0
- vpsubd %xmm2, %xmm1, %xmm1
-
- vmovdqu %xmm0, _lens+0*16(state)
- vmovdqu %xmm1, _lens+1*16(state)
-
- # "state" and "args" are the same address, arg1
- # len is arg2
- call sha1_x8_avx2
- # state and idx are intact
-
-
-len_is_0:
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- mov _unused_lanes(state), unused_lanes
- shl $4, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens(state, idx, 4)
-
- vmovd _args_digest(state , idx, 4) , %xmm0
- vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
- movl _args_digest+4*32(state, idx, 4), tmp2_w
-
- vmovdqu %xmm0, _result_digest(job_rax)
- offset = (_result_digest + 1*16)
- mov tmp2_w, offset(job_rax)
-
-return:
- pop %rbx
- FRAME_END
- ret
-
-return_null:
- xor job_rax, job_rax
- jmp return
-ENDPROC(sha1_mb_mgr_flush_avx2)
-
-
-#################################################################
-
-.align 16
-ENTRY(sha1_mb_mgr_get_comp_job_avx2)
- push %rbx
-
- ## if bit 32+3 is set, then all lanes are empty
- mov _unused_lanes(state), unused_lanes
- bt $(32+3), unused_lanes
- jc .return_null
-
- # Find min length
- vmovdqu _lens(state), %xmm0
- vmovdqu _lens+1*16(state), %xmm1
-
- vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
- vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
- vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min value in low dword
-
- vmovd %xmm2, DWORD_idx
- test $~0xF, idx
- jnz .return_null
-
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- mov _unused_lanes(state), unused_lanes
- shl $4, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens(state, idx, 4)
-
- vmovd _args_digest(state, idx, 4), %xmm0
- vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
- movl _args_digest+4*32(state, idx, 4), tmp2_w
-
- vmovdqu %xmm0, _result_digest(job_rax)
- movl tmp2_w, _result_digest+1*16(job_rax)
-
- pop %rbx
-
- ret
-
-.return_null:
- xor job_rax, job_rax
- pop %rbx
- ret
-ENDPROC(sha1_mb_mgr_get_comp_job_avx2)
-
-.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16
-.align 16
-clear_low_nibble:
-.octa 0x000000000000000000000000FFFFFFF0
-
-.section .rodata.cst8, "aM", @progbits, 8
-.align 8
-one:
-.quad 1
-two:
-.quad 2
-three:
-.quad 3
-four:
-.quad 4
-five:
-.quad 5
-six:
-.quad 6
-seven:
-.quad 7
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
deleted file mode 100644
index d2add0d35f43..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * Initialization code for multi buffer SHA1 algorithm for AVX2
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "sha1_mb_mgr.h"
-
-void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
-{
- unsigned int j;
- state->unused_lanes = 0xF76543210ULL;
- for (j = 0; j < 8; j++) {
- state->lens[j] = 0xFFFFFFFF;
- state->ldata[j].job_in_lane = NULL;
- }
-}
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S
deleted file mode 100644
index 7a93b1c0d69a..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S
+++ /dev/null
@@ -1,209 +0,0 @@
-/*
- * Buffer submit code for multi buffer SHA1 algorithm
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * James Guilford <james.guilford@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/linkage.h>
-#include <asm/frame.h>
-#include "sha1_mb_mgr_datastruct.S"
-
-
-.extern sha1_x8_avx
-
-# LINUX register definitions
-arg1 = %rdi
-arg2 = %rsi
-size_offset = %rcx
-tmp2 = %rcx
-extra_blocks = %rdx
-
-# Common definitions
-#define state arg1
-#define job %rsi
-#define len2 arg2
-#define p2 arg2
-
-# idx must be a register not clobberred by sha1_x8_avx2
-idx = %r8
-DWORD_idx = %r8d
-last_len = %r8
-
-p = %r11
-start_offset = %r11
-
-unused_lanes = %rbx
-BYTE_unused_lanes = %bl
-
-job_rax = %rax
-len = %rax
-DWORD_len = %eax
-
-lane = %r12
-tmp3 = %r12
-
-tmp = %r9
-DWORD_tmp = %r9d
-
-lane_data = %r10
-
-# JOB* submit_mb_mgr_submit_avx2(MB_MGR *state, job_sha1 *job)
-# arg 1 : rcx : state
-# arg 2 : rdx : job
-ENTRY(sha1_mb_mgr_submit_avx2)
- FRAME_BEGIN
- push %rbx
- push %r12
-
- mov _unused_lanes(state), unused_lanes
- mov unused_lanes, lane
- and $0xF, lane
- shr $4, unused_lanes
- imul $_LANE_DATA_size, lane, lane_data
- movl $STS_BEING_PROCESSED, _status(job)
- lea _ldata(state, lane_data), lane_data
- mov unused_lanes, _unused_lanes(state)
- movl _len(job), DWORD_len
-
- mov job, _job_in_lane(lane_data)
- shl $4, len
- or lane, len
-
- movl DWORD_len, _lens(state , lane, 4)
-
- # Load digest words from result_digest
- vmovdqu _result_digest(job), %xmm0
- mov _result_digest+1*16(job), DWORD_tmp
- vmovd %xmm0, _args_digest(state, lane, 4)
- vpextrd $1, %xmm0, _args_digest+1*32(state , lane, 4)
- vpextrd $2, %xmm0, _args_digest+2*32(state , lane, 4)
- vpextrd $3, %xmm0, _args_digest+3*32(state , lane, 4)
- movl DWORD_tmp, _args_digest+4*32(state , lane, 4)
-
- mov _buffer(job), p
- mov p, _args_data_ptr(state, lane, 8)
-
- cmp $0xF, unused_lanes
- jne return_null
-
-start_loop:
- # Find min length
- vmovdqa _lens(state), %xmm0
- vmovdqa _lens+1*16(state), %xmm1
-
- vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
- vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
- vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min value in low dword
-
- vmovd %xmm2, DWORD_idx
- mov idx, len2
- and $0xF, idx
- shr $4, len2
- jz len_is_0
-
- vpand clear_low_nibble(%rip), %xmm2, %xmm2
- vpshufd $0, %xmm2, %xmm2
-
- vpsubd %xmm2, %xmm0, %xmm0
- vpsubd %xmm2, %xmm1, %xmm1
-
- vmovdqa %xmm0, _lens + 0*16(state)
- vmovdqa %xmm1, _lens + 1*16(state)
-
-
- # "state" and "args" are the same address, arg1
- # len is arg2
- call sha1_x8_avx2
-
- # state and idx are intact
-
-len_is_0:
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- mov _unused_lanes(state), unused_lanes
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- shl $4, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens(state, idx, 4)
-
- vmovd _args_digest(state, idx, 4), %xmm0
- vpinsrd $1, _args_digest+1*32(state , idx, 4), %xmm0, %xmm0
- vpinsrd $2, _args_digest+2*32(state , idx, 4), %xmm0, %xmm0
- vpinsrd $3, _args_digest+3*32(state , idx, 4), %xmm0, %xmm0
- movl _args_digest+4*32(state, idx, 4), DWORD_tmp
-
- vmovdqu %xmm0, _result_digest(job_rax)
- movl DWORD_tmp, _result_digest+1*16(job_rax)
-
-return:
- pop %r12
- pop %rbx
- FRAME_END
- ret
-
-return_null:
- xor job_rax, job_rax
- jmp return
-
-ENDPROC(sha1_mb_mgr_submit_avx2)
-
-.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16
-.align 16
-clear_low_nibble:
- .octa 0x000000000000000000000000FFFFFFF0
diff --git a/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S b/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S
deleted file mode 100644
index 20f77aa633de..000000000000
--- a/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S
+++ /dev/null
@@ -1,492 +0,0 @@
-/*
- * Multi-buffer SHA1 algorithm hash compute routine
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * James Guilford <james.guilford@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/linkage.h>
-#include "sha1_mb_mgr_datastruct.S"
-
-## code to compute oct SHA1 using SSE-256
-## outer calling routine takes care of save and restore of XMM registers
-
-## Function clobbers: rax, rcx, rdx, rbx, rsi, rdi, r9-r15# ymm0-15
-##
-## Linux clobbers: rax rbx rcx rdx rsi r9 r10 r11 r12 r13 r14 r15
-## Linux preserves: rdi rbp r8
-##
-## clobbers ymm0-15
-
-
-# TRANSPOSE8 r0, r1, r2, r3, r4, r5, r6, r7, t0, t1
-# "transpose" data in {r0...r7} using temps {t0...t1}
-# Input looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
-# r0 = {a7 a6 a5 a4 a3 a2 a1 a0}
-# r1 = {b7 b6 b5 b4 b3 b2 b1 b0}
-# r2 = {c7 c6 c5 c4 c3 c2 c1 c0}
-# r3 = {d7 d6 d5 d4 d3 d2 d1 d0}
-# r4 = {e7 e6 e5 e4 e3 e2 e1 e0}
-# r5 = {f7 f6 f5 f4 f3 f2 f1 f0}
-# r6 = {g7 g6 g5 g4 g3 g2 g1 g0}
-# r7 = {h7 h6 h5 h4 h3 h2 h1 h0}
-#
-# Output looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
-# r0 = {h0 g0 f0 e0 d0 c0 b0 a0}
-# r1 = {h1 g1 f1 e1 d1 c1 b1 a1}
-# r2 = {h2 g2 f2 e2 d2 c2 b2 a2}
-# r3 = {h3 g3 f3 e3 d3 c3 b3 a3}
-# r4 = {h4 g4 f4 e4 d4 c4 b4 a4}
-# r5 = {h5 g5 f5 e5 d5 c5 b5 a5}
-# r6 = {h6 g6 f6 e6 d6 c6 b6 a6}
-# r7 = {h7 g7 f7 e7 d7 c7 b7 a7}
-#
-
-.macro TRANSPOSE8 r0 r1 r2 r3 r4 r5 r6 r7 t0 t1
- # process top half (r0..r3) {a...d}
- vshufps $0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4 b1 b0 a1 a0}
- vshufps $0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6 b3 b2 a3 a2}
- vshufps $0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4 d1 d0 c1 c0}
- vshufps $0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6 d3 d2 c3 c2}
- vshufps $0xDD, \t1, \t0, \r3 # r3 = {d5 c5 b5 a5 d1 c1 b1 a1}
- vshufps $0x88, \r2, \r0, \r1 # r1 = {d6 c6 b6 a6 d2 c2 b2 a2}
- vshufps $0xDD, \r2, \r0, \r0 # r0 = {d7 c7 b7 a7 d3 c3 b3 a3}
- vshufps $0x88, \t1, \t0, \t0 # t0 = {d4 c4 b4 a4 d0 c0 b0 a0}
-
- # use r2 in place of t0
- # process bottom half (r4..r7) {e...h}
- vshufps $0x44, \r5, \r4, \r2 # r2 = {f5 f4 e5 e4 f1 f0 e1 e0}
- vshufps $0xEE, \r5, \r4, \r4 # r4 = {f7 f6 e7 e6 f3 f2 e3 e2}
- vshufps $0x44, \r7, \r6, \t1 # t1 = {h5 h4 g5 g4 h1 h0 g1 g0}
- vshufps $0xEE, \r7, \r6, \r6 # r6 = {h7 h6 g7 g6 h3 h2 g3 g2}
- vshufps $0xDD, \t1, \r2, \r7 # r7 = {h5 g5 f5 e5 h1 g1 f1 e1}
- vshufps $0x88, \r6, \r4, \r5 # r5 = {h6 g6 f6 e6 h2 g2 f2 e2}
- vshufps $0xDD, \r6, \r4, \r4 # r4 = {h7 g7 f7 e7 h3 g3 f3 e3}
- vshufps $0x88, \t1, \r2, \t1 # t1 = {h4 g4 f4 e4 h0 g0 f0 e0}
-
- vperm2f128 $0x13, \r1, \r5, \r6 # h6...a6
- vperm2f128 $0x02, \r1, \r5, \r2 # h2...a2
- vperm2f128 $0x13, \r3, \r7, \r5 # h5...a5
- vperm2f128 $0x02, \r3, \r7, \r1 # h1...a1
- vperm2f128 $0x13, \r0, \r4, \r7 # h7...a7
- vperm2f128 $0x02, \r0, \r4, \r3 # h3...a3
- vperm2f128 $0x13, \t0, \t1, \r4 # h4...a4
- vperm2f128 $0x02, \t0, \t1, \r0 # h0...a0
-
-.endm
-##
-## Magic functions defined in FIPS 180-1
-##
-# macro MAGIC_F0 F,B,C,D,T ## F = (D ^ (B & (C ^ D)))
-.macro MAGIC_F0 regF regB regC regD regT
- vpxor \regD, \regC, \regF
- vpand \regB, \regF, \regF
- vpxor \regD, \regF, \regF
-.endm
-
-# macro MAGIC_F1 F,B,C,D,T ## F = (B ^ C ^ D)
-.macro MAGIC_F1 regF regB regC regD regT
- vpxor \regC, \regD, \regF
- vpxor \regB, \regF, \regF
-.endm
-
-# macro MAGIC_F2 F,B,C,D,T ## F = ((B & C) | (B & D) | (C & D))
-.macro MAGIC_F2 regF regB regC regD regT
- vpor \regC, \regB, \regF
- vpand \regC, \regB, \regT
- vpand \regD, \regF, \regF
- vpor \regT, \regF, \regF
-.endm
-
-# macro MAGIC_F3 F,B,C,D,T ## F = (B ^ C ^ D)
-.macro MAGIC_F3 regF regB regC regD regT
- MAGIC_F1 \regF,\regB,\regC,\regD,\regT
-.endm
-
-# PROLD reg, imm, tmp
-.macro PROLD reg imm tmp
- vpsrld $(32-\imm), \reg, \tmp
- vpslld $\imm, \reg, \reg
- vpor \tmp, \reg, \reg
-.endm
-
-.macro PROLD_nd reg imm tmp src
- vpsrld $(32-\imm), \src, \tmp
- vpslld $\imm, \src, \reg
- vpor \tmp, \reg, \reg
-.endm
-
-.macro SHA1_STEP_00_15 regA regB regC regD regE regT regF memW immCNT MAGIC
- vpaddd \immCNT, \regE, \regE
- vpaddd \memW*32(%rsp), \regE, \regE
- PROLD_nd \regT, 5, \regF, \regA
- vpaddd \regT, \regE, \regE
- \MAGIC \regF, \regB, \regC, \regD, \regT
- PROLD \regB, 30, \regT
- vpaddd \regF, \regE, \regE
-.endm
-
-.macro SHA1_STEP_16_79 regA regB regC regD regE regT regF memW immCNT MAGIC
- vpaddd \immCNT, \regE, \regE
- offset = ((\memW - 14) & 15) * 32
- vmovdqu offset(%rsp), W14
- vpxor W14, W16, W16
- offset = ((\memW - 8) & 15) * 32
- vpxor offset(%rsp), W16, W16
- offset = ((\memW - 3) & 15) * 32
- vpxor offset(%rsp), W16, W16
- vpsrld $(32-1), W16, \regF
- vpslld $1, W16, W16
- vpor W16, \regF, \regF
-
- ROTATE_W
-
- offset = ((\memW - 0) & 15) * 32
- vmovdqu \regF, offset(%rsp)
- vpaddd \regF, \regE, \regE
- PROLD_nd \regT, 5, \regF, \regA
- vpaddd \regT, \regE, \regE
- \MAGIC \regF,\regB,\regC,\regD,\regT ## FUN = MAGIC_Fi(B,C,D)
- PROLD \regB,30, \regT
- vpaddd \regF, \regE, \regE
-.endm
-
-########################################################################
-########################################################################
-########################################################################
-
-## FRAMESZ plus pushes must be an odd multiple of 8
-YMM_SAVE = (15-15)*32
-FRAMESZ = 32*16 + YMM_SAVE
-_YMM = FRAMESZ - YMM_SAVE
-
-#define VMOVPS vmovups
-
-IDX = %rax
-inp0 = %r9
-inp1 = %r10
-inp2 = %r11
-inp3 = %r12
-inp4 = %r13
-inp5 = %r14
-inp6 = %r15
-inp7 = %rcx
-arg1 = %rdi
-arg2 = %rsi
-RSP_SAVE = %rdx
-
-# ymm0 A
-# ymm1 B
-# ymm2 C
-# ymm3 D
-# ymm4 E
-# ymm5 F AA
-# ymm6 T0 BB
-# ymm7 T1 CC
-# ymm8 T2 DD
-# ymm9 T3 EE
-# ymm10 T4 TMP
-# ymm11 T5 FUN
-# ymm12 T6 K
-# ymm13 T7 W14
-# ymm14 T8 W15
-# ymm15 T9 W16
-
-
-A = %ymm0
-B = %ymm1
-C = %ymm2
-D = %ymm3
-E = %ymm4
-F = %ymm5
-T0 = %ymm6
-T1 = %ymm7
-T2 = %ymm8
-T3 = %ymm9
-T4 = %ymm10
-T5 = %ymm11
-T6 = %ymm12
-T7 = %ymm13
-T8 = %ymm14
-T9 = %ymm15
-
-AA = %ymm5
-BB = %ymm6
-CC = %ymm7
-DD = %ymm8
-EE = %ymm9
-TMP = %ymm10
-FUN = %ymm11
-K = %ymm12
-W14 = %ymm13
-W15 = %ymm14
-W16 = %ymm15
-
-.macro ROTATE_ARGS
- TMP_ = E
- E = D
- D = C
- C = B
- B = A
- A = TMP_
-.endm
-
-.macro ROTATE_W
-TMP_ = W16
-W16 = W15
-W15 = W14
-W14 = TMP_
-.endm
-
-# 8 streams x 5 32bit words per digest x 4 bytes per word
-#define DIGEST_SIZE (8*5*4)
-
-.align 32
-
-# void sha1_x8_avx2(void **input_data, UINT128 *digest, UINT32 size)
-# arg 1 : pointer to array[4] of pointer to input data
-# arg 2 : size (in blocks) ;; assumed to be >= 1
-#
-ENTRY(sha1_x8_avx2)
-
- # save callee-saved clobbered registers to comply with C function ABI
- push %r12
- push %r13
- push %r14
- push %r15
-
- #save rsp
- mov %rsp, RSP_SAVE
- sub $FRAMESZ, %rsp
-
- #align rsp to 32 Bytes
- and $~0x1F, %rsp
-
- ## Initialize digests
- vmovdqu 0*32(arg1), A
- vmovdqu 1*32(arg1), B
- vmovdqu 2*32(arg1), C
- vmovdqu 3*32(arg1), D
- vmovdqu 4*32(arg1), E
-
- ## transpose input onto stack
- mov _data_ptr+0*8(arg1),inp0
- mov _data_ptr+1*8(arg1),inp1
- mov _data_ptr+2*8(arg1),inp2
- mov _data_ptr+3*8(arg1),inp3
- mov _data_ptr+4*8(arg1),inp4
- mov _data_ptr+5*8(arg1),inp5
- mov _data_ptr+6*8(arg1),inp6
- mov _data_ptr+7*8(arg1),inp7
-
- xor IDX, IDX
-lloop:
- vmovdqu PSHUFFLE_BYTE_FLIP_MASK(%rip), F
- I=0
-.rep 2
- VMOVPS (inp0, IDX), T0
- VMOVPS (inp1, IDX), T1
- VMOVPS (inp2, IDX), T2
- VMOVPS (inp3, IDX), T3
- VMOVPS (inp4, IDX), T4
- VMOVPS (inp5, IDX), T5
- VMOVPS (inp6, IDX), T6
- VMOVPS (inp7, IDX), T7
-
- TRANSPOSE8 T0, T1, T2, T3, T4, T5, T6, T7, T8, T9
- vpshufb F, T0, T0
- vmovdqu T0, (I*8)*32(%rsp)
- vpshufb F, T1, T1
- vmovdqu T1, (I*8+1)*32(%rsp)
- vpshufb F, T2, T2
- vmovdqu T2, (I*8+2)*32(%rsp)
- vpshufb F, T3, T3
- vmovdqu T3, (I*8+3)*32(%rsp)
- vpshufb F, T4, T4
- vmovdqu T4, (I*8+4)*32(%rsp)
- vpshufb F, T5, T5
- vmovdqu T5, (I*8+5)*32(%rsp)
- vpshufb F, T6, T6
- vmovdqu T6, (I*8+6)*32(%rsp)
- vpshufb F, T7, T7
- vmovdqu T7, (I*8+7)*32(%rsp)
- add $32, IDX
- I = (I+1)
-.endr
- # save old digests
- vmovdqu A,AA
- vmovdqu B,BB
- vmovdqu C,CC
- vmovdqu D,DD
- vmovdqu E,EE
-
-##
-## perform 0-79 steps
-##
- vmovdqu K00_19(%rip), K
-## do rounds 0...15
- I = 0
-.rep 16
- SHA1_STEP_00_15 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F0
- ROTATE_ARGS
- I = (I+1)
-.endr
-
-## do rounds 16...19
- vmovdqu ((16 - 16) & 15) * 32 (%rsp), W16
- vmovdqu ((16 - 15) & 15) * 32 (%rsp), W15
-.rep 4
- SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F0
- ROTATE_ARGS
- I = (I+1)
-.endr
-
-## do rounds 20...39
- vmovdqu K20_39(%rip), K
-.rep 20
- SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F1
- ROTATE_ARGS
- I = (I+1)
-.endr
-
-## do rounds 40...59
- vmovdqu K40_59(%rip), K
-.rep 20
- SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F2
- ROTATE_ARGS
- I = (I+1)
-.endr
-
-## do rounds 60...79
- vmovdqu K60_79(%rip), K
-.rep 20
- SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F3
- ROTATE_ARGS
- I = (I+1)
-.endr
-
- vpaddd AA,A,A
- vpaddd BB,B,B
- vpaddd CC,C,C
- vpaddd DD,D,D
- vpaddd EE,E,E
-
- sub $1, arg2
- jne lloop
-
- # write out digests
- vmovdqu A, 0*32(arg1)
- vmovdqu B, 1*32(arg1)
- vmovdqu C, 2*32(arg1)
- vmovdqu D, 3*32(arg1)
- vmovdqu E, 4*32(arg1)
-
- # update input pointers
- add IDX, inp0
- add IDX, inp1
- add IDX, inp2
- add IDX, inp3
- add IDX, inp4
- add IDX, inp5
- add IDX, inp6
- add IDX, inp7
- mov inp0, _data_ptr (arg1)
- mov inp1, _data_ptr + 1*8(arg1)
- mov inp2, _data_ptr + 2*8(arg1)
- mov inp3, _data_ptr + 3*8(arg1)
- mov inp4, _data_ptr + 4*8(arg1)
- mov inp5, _data_ptr + 5*8(arg1)
- mov inp6, _data_ptr + 6*8(arg1)
- mov inp7, _data_ptr + 7*8(arg1)
-
- ################
- ## Postamble
-
- mov RSP_SAVE, %rsp
-
- # restore callee-saved clobbered registers
- pop %r15
- pop %r14
- pop %r13
- pop %r12
-
- ret
-ENDPROC(sha1_x8_avx2)
-
-
-.section .rodata.cst32.K00_19, "aM", @progbits, 32
-.align 32
-K00_19:
-.octa 0x5A8279995A8279995A8279995A827999
-.octa 0x5A8279995A8279995A8279995A827999
-
-.section .rodata.cst32.K20_39, "aM", @progbits, 32
-.align 32
-K20_39:
-.octa 0x6ED9EBA16ED9EBA16ED9EBA16ED9EBA1
-.octa 0x6ED9EBA16ED9EBA16ED9EBA16ED9EBA1
-
-.section .rodata.cst32.K40_59, "aM", @progbits, 32
-.align 32
-K40_59:
-.octa 0x8F1BBCDC8F1BBCDC8F1BBCDC8F1BBCDC
-.octa 0x8F1BBCDC8F1BBCDC8F1BBCDC8F1BBCDC
-
-.section .rodata.cst32.K60_79, "aM", @progbits, 32
-.align 32
-K60_79:
-.octa 0xCA62C1D6CA62C1D6CA62C1D6CA62C1D6
-.octa 0xCA62C1D6CA62C1D6CA62C1D6CA62C1D6
-
-.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32
-.align 32
-PSHUFFLE_BYTE_FLIP_MASK:
-.octa 0x0c0d0e0f08090a0b0405060700010203
-.octa 0x0c0d0e0f08090a0b0405060700010203
diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile
deleted file mode 100644
index 53ad6e7db747..000000000000
--- a/arch/x86/crypto/sha256-mb/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Arch-specific CryptoAPI modules.
-#
-
-OBJECT_FILES_NON_STANDARD := y
-
-avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
- $(comma)4)$(comma)%ymm2,yes,no)
-ifeq ($(avx2_supported),yes)
- obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb.o
- sha256-mb-y := sha256_mb.o sha256_mb_mgr_flush_avx2.o \
- sha256_mb_mgr_init_avx2.o sha256_mb_mgr_submit_avx2.o sha256_x8_avx2.o
-endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
deleted file mode 100644
index 97c5fc43e115..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ /dev/null
@@ -1,1013 +0,0 @@
-/*
- * Multi buffer SHA256 algorithm Glue Code
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
-#include <crypto/mcryptd.h>
-#include <crypto/crypto_wq.h>
-#include <asm/byteorder.h>
-#include <linux/hardirq.h>
-#include <asm/fpu/api.h>
-#include "sha256_mb_ctx.h"
-
-#define FLUSH_INTERVAL 1000 /* in usec */
-
-static struct mcryptd_alg_state sha256_mb_alg_state;
-
-struct sha256_mb_ctx {
- struct mcryptd_ahash *mcryptd_tfm;
-};
-
-static inline struct mcryptd_hash_request_ctx
- *cast_hash_to_mcryptd_ctx(struct sha256_hash_ctx *hash_ctx)
-{
- struct ahash_request *areq;
-
- areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
- return container_of(areq, struct mcryptd_hash_request_ctx, areq);
-}
-
-static inline struct ahash_request
- *cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
-{
- return container_of((void *) ctx, struct ahash_request, __ctx);
-}
-
-static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
- struct ahash_request *areq)
-{
- rctx->flag = HASH_UPDATE;
-}
-
-static asmlinkage void (*sha256_job_mgr_init)(struct sha256_mb_mgr *state);
-static asmlinkage struct job_sha256* (*sha256_job_mgr_submit)
- (struct sha256_mb_mgr *state, struct job_sha256 *job);
-static asmlinkage struct job_sha256* (*sha256_job_mgr_flush)
- (struct sha256_mb_mgr *state);
-static asmlinkage struct job_sha256* (*sha256_job_mgr_get_comp_job)
- (struct sha256_mb_mgr *state);
-
-inline uint32_t sha256_pad(uint8_t padblock[SHA256_BLOCK_SIZE * 2],
- uint64_t total_len)
-{
- uint32_t i = total_len & (SHA256_BLOCK_SIZE - 1);
-
- memset(&padblock[i], 0, SHA256_BLOCK_SIZE);
- padblock[i] = 0x80;
-
- i += ((SHA256_BLOCK_SIZE - 1) &
- (0 - (total_len + SHA256_PADLENGTHFIELD_SIZE + 1)))
- + 1 + SHA256_PADLENGTHFIELD_SIZE;
-
-#if SHA256_PADLENGTHFIELD_SIZE == 16
- *((uint64_t *) &padblock[i - 16]) = 0;
-#endif
-
- *((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
-
- /* Number of extra blocks to hash */
- return i >> SHA256_LOG2_BLOCK_SIZE;
-}
-
-static struct sha256_hash_ctx
- *sha256_ctx_mgr_resubmit(struct sha256_ctx_mgr *mgr,
- struct sha256_hash_ctx *ctx)
-{
- while (ctx) {
- if (ctx->status & HASH_CTX_STS_COMPLETE) {
- /* Clear PROCESSING bit */
- ctx->status = HASH_CTX_STS_COMPLETE;
- return ctx;
- }
-
- /*
- * If the extra blocks are empty, begin hashing what remains
- * in the user's buffer.
- */
- if (ctx->partial_block_buffer_length == 0 &&
- ctx->incoming_buffer_length) {
-
- const void *buffer = ctx->incoming_buffer;
- uint32_t len = ctx->incoming_buffer_length;
- uint32_t copy_len;
-
- /*
- * Only entire blocks can be hashed.
- * Copy remainder to extra blocks buffer.
- */
- copy_len = len & (SHA256_BLOCK_SIZE-1);
-
- if (copy_len) {
- len -= copy_len;
- memcpy(ctx->partial_block_buffer,
- ((const char *) buffer + len),
- copy_len);
- ctx->partial_block_buffer_length = copy_len;
- }
-
- ctx->incoming_buffer_length = 0;
-
- /* len should be a multiple of the block size now */
- assert((len % SHA256_BLOCK_SIZE) == 0);
-
- /* Set len to the number of blocks to be hashed */
- len >>= SHA256_LOG2_BLOCK_SIZE;
-
- if (len) {
-
- ctx->job.buffer = (uint8_t *) buffer;
- ctx->job.len = len;
- ctx = (struct sha256_hash_ctx *)
- sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
- continue;
- }
- }
-
- /*
- * If the extra blocks are not empty, then we are
- * either on the last block(s) or we need more
- * user input before continuing.
- */
- if (ctx->status & HASH_CTX_STS_LAST) {
-
- uint8_t *buf = ctx->partial_block_buffer;
- uint32_t n_extra_blocks =
- sha256_pad(buf, ctx->total_length);
-
- ctx->status = (HASH_CTX_STS_PROCESSING |
- HASH_CTX_STS_COMPLETE);
- ctx->job.buffer = buf;
- ctx->job.len = (uint32_t) n_extra_blocks;
- ctx = (struct sha256_hash_ctx *)
- sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
- continue;
- }
-
- ctx->status = HASH_CTX_STS_IDLE;
- return ctx;
- }
-
- return NULL;
-}
-
-static struct sha256_hash_ctx
- *sha256_ctx_mgr_get_comp_ctx(struct sha256_ctx_mgr *mgr)
-{
- /*
- * If get_comp_job returns NULL, there are no jobs complete.
- * If get_comp_job returns a job, verify that it is safe to return to
- * the user. If it is not ready, resubmit the job to finish processing.
- * If sha256_ctx_mgr_resubmit returned a job, it is ready to be
- * returned. Otherwise, all jobs currently being managed by the
- * hash_ctx_mgr still need processing.
- */
- struct sha256_hash_ctx *ctx;
-
- ctx = (struct sha256_hash_ctx *) sha256_job_mgr_get_comp_job(&mgr->mgr);
- return sha256_ctx_mgr_resubmit(mgr, ctx);
-}
-
-static void sha256_ctx_mgr_init(struct sha256_ctx_mgr *mgr)
-{
- sha256_job_mgr_init(&mgr->mgr);
-}
-
-static struct sha256_hash_ctx *sha256_ctx_mgr_submit(struct sha256_ctx_mgr *mgr,
- struct sha256_hash_ctx *ctx,
- const void *buffer,
- uint32_t len,
- int flags)
-{
- if (flags & ~(HASH_UPDATE | HASH_LAST)) {
- /* User should not pass anything other than UPDATE or LAST */
- ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
- return ctx;
- }
-
- if (ctx->status & HASH_CTX_STS_PROCESSING) {
- /* Cannot submit to a currently processing job. */
- ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
- return ctx;
- }
-
- if (ctx->status & HASH_CTX_STS_COMPLETE) {
- /* Cannot update a finished job. */
- ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
- return ctx;
- }
-
- /* If we made it here, there was no error during this call to submit */
- ctx->error = HASH_CTX_ERROR_NONE;
-
- /* Store buffer ptr info from user */
- ctx->incoming_buffer = buffer;
- ctx->incoming_buffer_length = len;
-
- /*
- * Store the user's request flags and mark this ctx as currently
- * being processed.
- */
- ctx->status = (flags & HASH_LAST) ?
- (HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
- HASH_CTX_STS_PROCESSING;
-
- /* Advance byte counter */
- ctx->total_length += len;
-
- /*
- * If there is anything currently buffered in the extra blocks,
- * append to it until it contains a whole block.
- * Or if the user's buffer contains less than a whole block,
- * append as much as possible to the extra block.
- */
- if (ctx->partial_block_buffer_length || len < SHA256_BLOCK_SIZE) {
- /*
- * Compute how many bytes to copy from user buffer into
- * extra block
- */
- uint32_t copy_len = SHA256_BLOCK_SIZE -
- ctx->partial_block_buffer_length;
- if (len < copy_len)
- copy_len = len;
-
- if (copy_len) {
- /* Copy and update relevant pointers and counters */
- memcpy(
- &ctx->partial_block_buffer[ctx->partial_block_buffer_length],
- buffer, copy_len);
-
- ctx->partial_block_buffer_length += copy_len;
- ctx->incoming_buffer = (const void *)
- ((const char *)buffer + copy_len);
- ctx->incoming_buffer_length = len - copy_len;
- }
-
- /* The extra block should never contain more than 1 block */
- assert(ctx->partial_block_buffer_length <= SHA256_BLOCK_SIZE);
-
- /*
- * If the extra block buffer contains exactly 1 block,
- * it can be hashed.
- */
- if (ctx->partial_block_buffer_length >= SHA256_BLOCK_SIZE) {
- ctx->partial_block_buffer_length = 0;
-
- ctx->job.buffer = ctx->partial_block_buffer;
- ctx->job.len = 1;
- ctx = (struct sha256_hash_ctx *)
- sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
- }
- }
-
- return sha256_ctx_mgr_resubmit(mgr, ctx);
-}
-
-static struct sha256_hash_ctx *sha256_ctx_mgr_flush(struct sha256_ctx_mgr *mgr)
-{
- struct sha256_hash_ctx *ctx;
-
- while (1) {
- ctx = (struct sha256_hash_ctx *)
- sha256_job_mgr_flush(&mgr->mgr);
-
- /* If flush returned 0, there are no more jobs in flight. */
- if (!ctx)
- return NULL;
-
- /*
- * If flush returned a job, resubmit the job to finish
- * processing.
- */
- ctx = sha256_ctx_mgr_resubmit(mgr, ctx);
-
- /*
- * If sha256_ctx_mgr_resubmit returned a job, it is ready to
- * be returned. Otherwise, all jobs currently being managed by
- * the sha256_ctx_mgr still need processing. Loop.
- */
- if (ctx)
- return ctx;
- }
-}
-
-static int sha256_mb_init(struct ahash_request *areq)
-{
- struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
-
- hash_ctx_init(sctx);
- sctx->job.result_digest[0] = SHA256_H0;
- sctx->job.result_digest[1] = SHA256_H1;
- sctx->job.result_digest[2] = SHA256_H2;
- sctx->job.result_digest[3] = SHA256_H3;
- sctx->job.result_digest[4] = SHA256_H4;
- sctx->job.result_digest[5] = SHA256_H5;
- sctx->job.result_digest[6] = SHA256_H6;
- sctx->job.result_digest[7] = SHA256_H7;
- sctx->total_length = 0;
- sctx->partial_block_buffer_length = 0;
- sctx->status = HASH_CTX_STS_IDLE;
-
- return 0;
-}
-
-static int sha256_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
-{
- int i;
- struct sha256_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
- __be32 *dst = (__be32 *) rctx->out;
-
- for (i = 0; i < 8; ++i)
- dst[i] = cpu_to_be32(sctx->job.result_digest[i]);
-
- return 0;
-}
-
-static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
- struct mcryptd_alg_cstate *cstate, bool flush)
-{
- int flag = HASH_UPDATE;
- int nbytes, err = 0;
- struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
- struct sha256_hash_ctx *sha_ctx;
-
- /* more work ? */
- while (!(rctx->flag & HASH_DONE)) {
- nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
- if (nbytes < 0) {
- err = nbytes;
- goto out;
- }
- /* check if the walk is done */
- if (crypto_ahash_walk_last(&rctx->walk)) {
- rctx->flag |= HASH_DONE;
- if (rctx->flag & HASH_FINAL)
- flag |= HASH_LAST;
-
- }
- sha_ctx = (struct sha256_hash_ctx *)
- ahash_request_ctx(&rctx->areq);
- kernel_fpu_begin();
- sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx,
- rctx->walk.data, nbytes, flag);
- if (!sha_ctx) {
- if (flush)
- sha_ctx = sha256_ctx_mgr_flush(cstate->mgr);
- }
- kernel_fpu_end();
- if (sha_ctx)
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- else {
- rctx = NULL;
- goto out;
- }
- }
-
- /* copy the results */
- if (rctx->flag & HASH_FINAL)
- sha256_mb_set_results(rctx);
-
-out:
- *ret_rctx = rctx;
- return err;
-}
-
-static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
- struct mcryptd_alg_cstate *cstate,
- int err)
-{
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha256_hash_ctx *sha_ctx;
- struct mcryptd_hash_request_ctx *req_ctx;
- int ret;
-
- /* remove from work list */
- spin_lock(&cstate->work_lock);
- list_del(&rctx->waiter);
- spin_unlock(&cstate->work_lock);
-
- if (irqs_disabled())
- rctx->complete(&req->base, err);
- else {
- local_bh_disable();
- rctx->complete(&req->base, err);
- local_bh_enable();
- }
-
- /* check to see if there are other jobs that are done */
- sha_ctx = sha256_ctx_mgr_get_comp_ctx(cstate->mgr);
- while (sha_ctx) {
- req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&req_ctx, cstate, false);
- if (req_ctx) {
- spin_lock(&cstate->work_lock);
- list_del(&req_ctx->waiter);
- spin_unlock(&cstate->work_lock);
-
- req = cast_mcryptd_ctx_to_req(req_ctx);
- if (irqs_disabled())
- req_ctx->complete(&req->base, ret);
- else {
- local_bh_disable();
- req_ctx->complete(&req->base, ret);
- local_bh_enable();
- }
- }
- sha_ctx = sha256_ctx_mgr_get_comp_ctx(cstate->mgr);
- }
-
- return 0;
-}
-
-static void sha256_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
- struct mcryptd_alg_cstate *cstate)
-{
- unsigned long next_flush;
- unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
-
- /* initialize tag */
- rctx->tag.arrival = jiffies; /* tag the arrival time */
- rctx->tag.seq_num = cstate->next_seq_num++;
- next_flush = rctx->tag.arrival + delay;
- rctx->tag.expire = next_flush;
-
- spin_lock(&cstate->work_lock);
- list_add_tail(&rctx->waiter, &cstate->work_list);
- spin_unlock(&cstate->work_lock);
-
- mcryptd_arm_flusher(cstate, delay);
-}
-
-static int sha256_mb_update(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx, areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
-
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha256_hash_ctx *sha_ctx;
- int ret = 0, nbytes;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- nbytes = crypto_ahash_walk_first(req, &rctx->walk);
-
- if (nbytes < 0) {
- ret = nbytes;
- goto done;
- }
-
- if (crypto_ahash_walk_last(&rctx->walk))
- rctx->flag |= HASH_DONE;
-
- /* submit */
- sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
- sha256_mb_add_list(rctx, cstate);
- kernel_fpu_begin();
- sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
- nbytes, HASH_UPDATE);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
-
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha256_mb_finup(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx, areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
-
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha256_hash_ctx *sha_ctx;
- int ret = 0, flag = HASH_UPDATE, nbytes;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- nbytes = crypto_ahash_walk_first(req, &rctx->walk);
-
- if (nbytes < 0) {
- ret = nbytes;
- goto done;
- }
-
- if (crypto_ahash_walk_last(&rctx->walk)) {
- rctx->flag |= HASH_DONE;
- flag = HASH_LAST;
- }
-
- /* submit */
- rctx->flag |= HASH_FINAL;
- sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
- sha256_mb_add_list(rctx, cstate);
-
- kernel_fpu_begin();
- sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
- nbytes, flag);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha256_mb_final(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx,
- areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
-
- struct sha256_hash_ctx *sha_ctx;
- int ret = 0;
- u8 data;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- rctx->flag |= HASH_DONE | HASH_FINAL;
-
- sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
- /* flag HASH_FINAL and 0 data size */
- sha256_mb_add_list(rctx, cstate);
- kernel_fpu_begin();
- sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
- HASH_LAST);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha256_mb_export(struct ahash_request *areq, void *out)
-{
- struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
-
- memcpy(out, sctx, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha256_mb_import(struct ahash_request *areq, const void *in)
-{
- struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
-
- memcpy(sctx, in, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha256_mb_async_init_tfm(struct crypto_tfm *tfm)
-{
- struct mcryptd_ahash *mcryptd_tfm;
- struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
- struct mcryptd_hash_ctx *mctx;
-
- mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha256-mb",
- CRYPTO_ALG_INTERNAL,
- CRYPTO_ALG_INTERNAL);
- if (IS_ERR(mcryptd_tfm))
- return PTR_ERR(mcryptd_tfm);
- mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
- mctx->alg_state = &sha256_mb_alg_state;
- ctx->mcryptd_tfm = mcryptd_tfm;
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- crypto_ahash_reqsize(&mcryptd_tfm->base));
-
- return 0;
-}
-
-static void sha256_mb_async_exit_tfm(struct crypto_tfm *tfm)
-{
- struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
- mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
-static int sha256_mb_areq_init_tfm(struct crypto_tfm *tfm)
-{
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- sizeof(struct sha256_hash_ctx));
-
- return 0;
-}
-
-static void sha256_mb_areq_exit_tfm(struct crypto_tfm *tfm)
-{
- struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
- mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
-static struct ahash_alg sha256_mb_areq_alg = {
- .init = sha256_mb_init,
- .update = sha256_mb_update,
- .final = sha256_mb_final,
- .finup = sha256_mb_finup,
- .export = sha256_mb_export,
- .import = sha256_mb_import,
- .halg = {
- .digestsize = SHA256_DIGEST_SIZE,
- .statesize = sizeof(struct sha256_hash_ctx),
- .base = {
- .cra_name = "__sha256-mb",
- .cra_driver_name = "__intel_sha256-mb",
- .cra_priority = 100,
- /*
- * use ASYNC flag as some buffers in multi-buffer
- * algo may not have completed before hashing thread
- * sleep
- */
- .cra_flags = CRYPTO_ALG_ASYNC |
- CRYPTO_ALG_INTERNAL,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT
- (sha256_mb_areq_alg.halg.base.cra_list),
- .cra_init = sha256_mb_areq_init_tfm,
- .cra_exit = sha256_mb_areq_exit_tfm,
- .cra_ctxsize = sizeof(struct sha256_hash_ctx),
- }
- }
-};
-
-static int sha256_mb_async_init(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_init(mcryptd_req);
-}
-
-static int sha256_mb_async_update(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_update(mcryptd_req);
-}
-
-static int sha256_mb_async_finup(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_finup(mcryptd_req);
-}
-
-static int sha256_mb_async_final(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_final(mcryptd_req);
-}
-
-static int sha256_mb_async_digest(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_digest(mcryptd_req);
-}
-
-static int sha256_mb_async_export(struct ahash_request *req, void *out)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_export(mcryptd_req, out);
-}
-
-static int sha256_mb_async_import(struct ahash_request *req, const void *in)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
- struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
- struct mcryptd_hash_request_ctx *rctx;
- struct ahash_request *areq;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- rctx = ahash_request_ctx(mcryptd_req);
- areq = &rctx->areq;
-
- ahash_request_set_tfm(areq, child);
- ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
- rctx->complete, req);
-
- return crypto_ahash_import(mcryptd_req, in);
-}
-
-static struct ahash_alg sha256_mb_async_alg = {
- .init = sha256_mb_async_init,
- .update = sha256_mb_async_update,
- .final = sha256_mb_async_final,
- .finup = sha256_mb_async_finup,
- .export = sha256_mb_async_export,
- .import = sha256_mb_async_import,
- .digest = sha256_mb_async_digest,
- .halg = {
- .digestsize = SHA256_DIGEST_SIZE,
- .statesize = sizeof(struct sha256_hash_ctx),
- .base = {
- .cra_name = "sha256",
- .cra_driver_name = "sha256_mb",
- /*
- * Low priority, since with few concurrent hash requests
- * this is extremely slow due to the flush delay. Users
- * whose workloads would benefit from this can request
- * it explicitly by driver name, or can increase its
- * priority at runtime using NETLINK_CRYPTO.
- */
- .cra_priority = 50,
- .cra_flags = CRYPTO_ALG_ASYNC,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT
- (sha256_mb_async_alg.halg.base.cra_list),
- .cra_init = sha256_mb_async_init_tfm,
- .cra_exit = sha256_mb_async_exit_tfm,
- .cra_ctxsize = sizeof(struct sha256_mb_ctx),
- .cra_alignmask = 0,
- },
- },
-};
-
-static unsigned long sha256_mb_flusher(struct mcryptd_alg_cstate *cstate)
-{
- struct mcryptd_hash_request_ctx *rctx;
- unsigned long cur_time;
- unsigned long next_flush = 0;
- struct sha256_hash_ctx *sha_ctx;
-
-
- cur_time = jiffies;
-
- while (!list_empty(&cstate->work_list)) {
- rctx = list_entry(cstate->work_list.next,
- struct mcryptd_hash_request_ctx, waiter);
- if (time_before(cur_time, rctx->tag.expire))
- break;
- kernel_fpu_begin();
- sha_ctx = (struct sha256_hash_ctx *)
- sha256_ctx_mgr_flush(cstate->mgr);
- kernel_fpu_end();
- if (!sha_ctx) {
- pr_err("sha256_mb error: nothing got"
- " flushed for non-empty list\n");
- break;
- }
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- sha_finish_walk(&rctx, cstate, true);
- sha_complete_job(rctx, cstate, 0);
- }
-
- if (!list_empty(&cstate->work_list)) {
- rctx = list_entry(cstate->work_list.next,
- struct mcryptd_hash_request_ctx, waiter);
- /* get the hash context and then flush time */
- next_flush = rctx->tag.expire;
- mcryptd_arm_flusher(cstate, get_delay(next_flush));
- }
- return next_flush;
-}
-
-static int __init sha256_mb_mod_init(void)
-{
-
- int cpu;
- int err;
- struct mcryptd_alg_cstate *cpu_state;
-
- /* check for dependent cpu features */
- if (!boot_cpu_has(X86_FEATURE_AVX2) ||
- !boot_cpu_has(X86_FEATURE_BMI2))
- return -ENODEV;
-
- /* initialize multibuffer structures */
- sha256_mb_alg_state.alg_cstate = alloc_percpu
- (struct mcryptd_alg_cstate);
-
- sha256_job_mgr_init = sha256_mb_mgr_init_avx2;
- sha256_job_mgr_submit = sha256_mb_mgr_submit_avx2;
- sha256_job_mgr_flush = sha256_mb_mgr_flush_avx2;
- sha256_job_mgr_get_comp_job = sha256_mb_mgr_get_comp_job_avx2;
-
- if (!sha256_mb_alg_state.alg_cstate)
- return -ENOMEM;
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
- cpu_state->next_flush = 0;
- cpu_state->next_seq_num = 0;
- cpu_state->flusher_engaged = false;
- INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
- cpu_state->cpu = cpu;
- cpu_state->alg_state = &sha256_mb_alg_state;
- cpu_state->mgr = kzalloc(sizeof(struct sha256_ctx_mgr),
- GFP_KERNEL);
- if (!cpu_state->mgr)
- goto err2;
- sha256_ctx_mgr_init(cpu_state->mgr);
- INIT_LIST_HEAD(&cpu_state->work_list);
- spin_lock_init(&cpu_state->work_lock);
- }
- sha256_mb_alg_state.flusher = &sha256_mb_flusher;
-
- err = crypto_register_ahash(&sha256_mb_areq_alg);
- if (err)
- goto err2;
- err = crypto_register_ahash(&sha256_mb_async_alg);
- if (err)
- goto err1;
-
-
- return 0;
-err1:
- crypto_unregister_ahash(&sha256_mb_areq_alg);
-err2:
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
- kfree(cpu_state->mgr);
- }
- free_percpu(sha256_mb_alg_state.alg_cstate);
- return -ENODEV;
-}
-
-static void __exit sha256_mb_mod_fini(void)
-{
- int cpu;
- struct mcryptd_alg_cstate *cpu_state;
-
- crypto_unregister_ahash(&sha256_mb_async_alg);
- crypto_unregister_ahash(&sha256_mb_areq_alg);
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
- kfree(cpu_state->mgr);
- }
- free_percpu(sha256_mb_alg_state.alg_cstate);
-}
-
-module_init(sha256_mb_mod_init);
-module_exit(sha256_mb_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, multi buffer accelerated");
-
-MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
deleted file mode 100644
index 7c432543dc7f..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * Header file for multi buffer SHA256 context
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _SHA_MB_CTX_INTERNAL_H
-#define _SHA_MB_CTX_INTERNAL_H
-
-#include "sha256_mb_mgr.h"
-
-#define HASH_UPDATE 0x00
-#define HASH_LAST 0x01
-#define HASH_DONE 0x02
-#define HASH_FINAL 0x04
-
-#define HASH_CTX_STS_IDLE 0x00
-#define HASH_CTX_STS_PROCESSING 0x01
-#define HASH_CTX_STS_LAST 0x02
-#define HASH_CTX_STS_COMPLETE 0x04
-
-enum hash_ctx_error {
- HASH_CTX_ERROR_NONE = 0,
- HASH_CTX_ERROR_INVALID_FLAGS = -1,
- HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
- HASH_CTX_ERROR_ALREADY_COMPLETED = -3,
-
-#ifdef HASH_CTX_DEBUG
- HASH_CTX_ERROR_DEBUG_DIGEST_MISMATCH = -4,
-#endif
-};
-
-
-#define hash_ctx_user_data(ctx) ((ctx)->user_data)
-#define hash_ctx_digest(ctx) ((ctx)->job.result_digest)
-#define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
-#define hash_ctx_complete(ctx) ((ctx)->status == HASH_CTX_STS_COMPLETE)
-#define hash_ctx_status(ctx) ((ctx)->status)
-#define hash_ctx_error(ctx) ((ctx)->error)
-#define hash_ctx_init(ctx) \
- do { \
- (ctx)->error = HASH_CTX_ERROR_NONE; \
- (ctx)->status = HASH_CTX_STS_COMPLETE; \
- } while (0)
-
-
-/* Hash Constants and Typedefs */
-#define SHA256_DIGEST_LENGTH 8
-#define SHA256_LOG2_BLOCK_SIZE 6
-
-#define SHA256_PADLENGTHFIELD_SIZE 8
-
-#ifdef SHA_MB_DEBUG
-#define assert(expr) \
-do { \
- if (unlikely(!(expr))) { \
- printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
- #expr, __FILE__, __func__, __LINE__); \
- } \
-} while (0)
-#else
-#define assert(expr) do {} while (0)
-#endif
-
-struct sha256_ctx_mgr {
- struct sha256_mb_mgr mgr;
-};
-
-/* typedef struct sha256_ctx_mgr sha256_ctx_mgr; */
-
-struct sha256_hash_ctx {
- /* Must be at struct offset 0 */
- struct job_sha256 job;
- /* status flag */
- int status;
- /* error flag */
- int error;
-
- uint64_t total_length;
- const void *incoming_buffer;
- uint32_t incoming_buffer_length;
- uint8_t partial_block_buffer[SHA256_BLOCK_SIZE * 2];
- uint32_t partial_block_buffer_length;
- void *user_data;
-};
-
-#endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h b/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
deleted file mode 100644
index b01ae408c56d..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * Header file for multi buffer SHA256 algorithm manager
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-#ifndef __SHA_MB_MGR_H
-#define __SHA_MB_MGR_H
-
-#include <linux/types.h>
-
-#define NUM_SHA256_DIGEST_WORDS 8
-
-enum job_sts { STS_UNKNOWN = 0,
- STS_BEING_PROCESSED = 1,
- STS_COMPLETED = 2,
- STS_INTERNAL_ERROR = 3,
- STS_ERROR = 4
-};
-
-struct job_sha256 {
- u8 *buffer;
- u32 len;
- u32 result_digest[NUM_SHA256_DIGEST_WORDS] __aligned(32);
- enum job_sts status;
- void *user_data;
-};
-
-/* SHA256 out-of-order scheduler */
-
-/* typedef uint32_t sha8_digest_array[8][8]; */
-
-struct sha256_args_x8 {
- uint32_t digest[8][8];
- uint8_t *data_ptr[8];
-};
-
-struct sha256_lane_data {
- struct job_sha256 *job_in_lane;
-};
-
-struct sha256_mb_mgr {
- struct sha256_args_x8 args;
-
- uint32_t lens[8];
-
- /* each byte is index (0...7) of unused lanes */
- uint64_t unused_lanes;
- /* byte 4 is set to FF as a flag */
- struct sha256_lane_data ldata[8];
-};
-
-
-#define SHA256_MB_MGR_NUM_LANES_AVX2 8
-
-void sha256_mb_mgr_init_avx2(struct sha256_mb_mgr *state);
-struct job_sha256 *sha256_mb_mgr_submit_avx2(struct sha256_mb_mgr *state,
- struct job_sha256 *job);
-struct job_sha256 *sha256_mb_mgr_flush_avx2(struct sha256_mb_mgr *state);
-struct job_sha256 *sha256_mb_mgr_get_comp_job_avx2(struct sha256_mb_mgr *state);
-
-#endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S
deleted file mode 100644
index 5c377bac21d0..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S
+++ /dev/null
@@ -1,304 +0,0 @@
-/*
- * Header file for multi buffer SHA256 algorithm data structure
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-# Macros for defining data structures
-
-# Usage example
-
-#START_FIELDS # JOB_AES
-### name size align
-#FIELD _plaintext, 8, 8 # pointer to plaintext
-#FIELD _ciphertext, 8, 8 # pointer to ciphertext
-#FIELD _IV, 16, 8 # IV
-#FIELD _keys, 8, 8 # pointer to keys
-#FIELD _len, 4, 4 # length in bytes
-#FIELD _status, 4, 4 # status enumeration
-#FIELD _user_data, 8, 8 # pointer to user data
-#UNION _union, size1, align1, \
-# size2, align2, \
-# size3, align3, \
-# ...
-#END_FIELDS
-#%assign _JOB_AES_size _FIELD_OFFSET
-#%assign _JOB_AES_align _STRUCT_ALIGN
-
-#########################################################################
-
-# Alternate "struc-like" syntax:
-# STRUCT job_aes2
-# RES_Q .plaintext, 1
-# RES_Q .ciphertext, 1
-# RES_DQ .IV, 1
-# RES_B .nested, _JOB_AES_SIZE, _JOB_AES_ALIGN
-# RES_U .union, size1, align1, \
-# size2, align2, \
-# ...
-# ENDSTRUCT
-# # Following only needed if nesting
-# %assign job_aes2_size _FIELD_OFFSET
-# %assign job_aes2_align _STRUCT_ALIGN
-#
-# RES_* macros take a name, a count and an optional alignment.
-# The count in in terms of the base size of the macro, and the
-# default alignment is the base size.
-# The macros are:
-# Macro Base size
-# RES_B 1
-# RES_W 2
-# RES_D 4
-# RES_Q 8
-# RES_DQ 16
-# RES_Y 32
-# RES_Z 64
-#
-# RES_U defines a union. It's arguments are a name and two or more
-# pairs of "size, alignment"
-#
-# The two assigns are only needed if this structure is being nested
-# within another. Even if the assigns are not done, one can still use
-# STRUCT_NAME_size as the size of the structure.
-#
-# Note that for nesting, you still need to assign to STRUCT_NAME_size.
-#
-# The differences between this and using "struc" directly are that each
-# type is implicitly aligned to its natural length (although this can be
-# over-ridden with an explicit third parameter), and that the structure
-# is padded at the end to its overall alignment.
-#
-
-#########################################################################
-
-#ifndef _DATASTRUCT_ASM_
-#define _DATASTRUCT_ASM_
-
-#define SZ8 8*SHA256_DIGEST_WORD_SIZE
-#define ROUNDS 64*SZ8
-#define PTR_SZ 8
-#define SHA256_DIGEST_WORD_SIZE 4
-#define MAX_SHA256_LANES 8
-#define SHA256_DIGEST_WORDS 8
-#define SHA256_DIGEST_ROW_SIZE (MAX_SHA256_LANES * SHA256_DIGEST_WORD_SIZE)
-#define SHA256_DIGEST_SIZE (SHA256_DIGEST_ROW_SIZE * SHA256_DIGEST_WORDS)
-#define SHA256_BLK_SZ 64
-
-# START_FIELDS
-.macro START_FIELDS
- _FIELD_OFFSET = 0
- _STRUCT_ALIGN = 0
-.endm
-
-# FIELD name size align
-.macro FIELD name size align
- _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
- \name = _FIELD_OFFSET
- _FIELD_OFFSET = _FIELD_OFFSET + (\size)
-.if (\align > _STRUCT_ALIGN)
- _STRUCT_ALIGN = \align
-.endif
-.endm
-
-# END_FIELDS
-.macro END_FIELDS
- _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
-.endm
-
-########################################################################
-
-.macro STRUCT p1
-START_FIELDS
-.struc \p1
-.endm
-
-.macro ENDSTRUCT
- tmp = _FIELD_OFFSET
- END_FIELDS
- tmp = (_FIELD_OFFSET - %%tmp)
-.if (tmp > 0)
- .lcomm tmp
-.endif
-.endstruc
-.endm
-
-## RES_int name size align
-.macro RES_int p1 p2 p3
- name = \p1
- size = \p2
- align = .\p3
-
- _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
-.align align
-.lcomm name size
- _FIELD_OFFSET = _FIELD_OFFSET + (size)
-.if (align > _STRUCT_ALIGN)
- _STRUCT_ALIGN = align
-.endif
-.endm
-
-# macro RES_B name, size [, align]
-.macro RES_B _name, _size, _align=1
-RES_int _name _size _align
-.endm
-
-# macro RES_W name, size [, align]
-.macro RES_W _name, _size, _align=2
-RES_int _name 2*(_size) _align
-.endm
-
-# macro RES_D name, size [, align]
-.macro RES_D _name, _size, _align=4
-RES_int _name 4*(_size) _align
-.endm
-
-# macro RES_Q name, size [, align]
-.macro RES_Q _name, _size, _align=8
-RES_int _name 8*(_size) _align
-.endm
-
-# macro RES_DQ name, size [, align]
-.macro RES_DQ _name, _size, _align=16
-RES_int _name 16*(_size) _align
-.endm
-
-# macro RES_Y name, size [, align]
-.macro RES_Y _name, _size, _align=32
-RES_int _name 32*(_size) _align
-.endm
-
-# macro RES_Z name, size [, align]
-.macro RES_Z _name, _size, _align=64
-RES_int _name 64*(_size) _align
-.endm
-
-#endif
-
-
-########################################################################
-#### Define SHA256 Out Of Order Data Structures
-########################################################################
-
-START_FIELDS # LANE_DATA
-### name size align
-FIELD _job_in_lane, 8, 8 # pointer to job object
-END_FIELDS
-
- _LANE_DATA_size = _FIELD_OFFSET
- _LANE_DATA_align = _STRUCT_ALIGN
-
-########################################################################
-
-START_FIELDS # SHA256_ARGS_X4
-### name size align
-FIELD _digest, 4*8*8, 4 # transposed digest
-FIELD _data_ptr, 8*8, 8 # array of pointers to data
-END_FIELDS
-
- _SHA256_ARGS_X4_size = _FIELD_OFFSET
- _SHA256_ARGS_X4_align = _STRUCT_ALIGN
- _SHA256_ARGS_X8_size = _FIELD_OFFSET
- _SHA256_ARGS_X8_align = _STRUCT_ALIGN
-
-#######################################################################
-
-START_FIELDS # MB_MGR
-### name size align
-FIELD _args, _SHA256_ARGS_X4_size, _SHA256_ARGS_X4_align
-FIELD _lens, 4*8, 8
-FIELD _unused_lanes, 8, 8
-FIELD _ldata, _LANE_DATA_size*8, _LANE_DATA_align
-END_FIELDS
-
- _MB_MGR_size = _FIELD_OFFSET
- _MB_MGR_align = _STRUCT_ALIGN
-
-_args_digest = _args + _digest
-_args_data_ptr = _args + _data_ptr
-
-#######################################################################
-
-START_FIELDS #STACK_FRAME
-### name size align
-FIELD _data, 16*SZ8, 1 # transposed digest
-FIELD _digest, 8*SZ8, 1 # array of pointers to data
-FIELD _ytmp, 4*SZ8, 1
-FIELD _rsp, 8, 1
-END_FIELDS
-
- _STACK_FRAME_size = _FIELD_OFFSET
- _STACK_FRAME_align = _STRUCT_ALIGN
-
-#######################################################################
-
-########################################################################
-#### Define constants
-########################################################################
-
-#define STS_UNKNOWN 0
-#define STS_BEING_PROCESSED 1
-#define STS_COMPLETED 2
-
-########################################################################
-#### Define JOB_SHA256 structure
-########################################################################
-
-START_FIELDS # JOB_SHA256
-
-### name size align
-FIELD _buffer, 8, 8 # pointer to buffer
-FIELD _len, 8, 8 # length in bytes
-FIELD _result_digest, 8*4, 32 # Digest (output)
-FIELD _status, 4, 4
-FIELD _user_data, 8, 8
-END_FIELDS
-
- _JOB_SHA256_size = _FIELD_OFFSET
- _JOB_SHA256_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
deleted file mode 100644
index d2364c55bbde..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ /dev/null
@@ -1,307 +0,0 @@
-/*
- * Flush routine for SHA256 multibuffer
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-#include <linux/linkage.h>
-#include <asm/frame.h>
-#include "sha256_mb_mgr_datastruct.S"
-
-.extern sha256_x8_avx2
-
-#LINUX register definitions
-#define arg1 %rdi
-#define arg2 %rsi
-
-# Common register definitions
-#define state arg1
-#define job arg2
-#define len2 arg2
-
-# idx must be a register not clobberred by sha1_mult
-#define idx %r8
-#define DWORD_idx %r8d
-
-#define unused_lanes %rbx
-#define lane_data %rbx
-#define tmp2 %rbx
-#define tmp2_w %ebx
-
-#define job_rax %rax
-#define tmp1 %rax
-#define size_offset %rax
-#define tmp %rax
-#define start_offset %rax
-
-#define tmp3 %arg1
-
-#define extra_blocks %arg2
-#define p %arg2
-
-.macro LABEL prefix n
-\prefix\n\():
-.endm
-
-.macro JNE_SKIP i
-jne skip_\i
-.endm
-
-.altmacro
-.macro SET_OFFSET _offset
-offset = \_offset
-.endm
-.noaltmacro
-
-# JOB_SHA256* sha256_mb_mgr_flush_avx2(MB_MGR *state)
-# arg 1 : rcx : state
-ENTRY(sha256_mb_mgr_flush_avx2)
- FRAME_BEGIN
- push %rbx
-
- # If bit (32+3) is set, then all lanes are empty
- mov _unused_lanes(state), unused_lanes
- bt $32+3, unused_lanes
- jc return_null
-
- # find a lane with a non-null job
- xor idx, idx
- offset = (_ldata + 1 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne one(%rip), idx
- offset = (_ldata + 2 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne two(%rip), idx
- offset = (_ldata + 3 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne three(%rip), idx
- offset = (_ldata + 4 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne four(%rip), idx
- offset = (_ldata + 5 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne five(%rip), idx
- offset = (_ldata + 6 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne six(%rip), idx
- offset = (_ldata + 7 * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne seven(%rip), idx
-
- # copy idx to empty lanes
-copy_lane_data:
- offset = (_args + _data_ptr)
- mov offset(state,idx,8), tmp
-
- I = 0
-.rep 8
- offset = (_ldata + I * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
-.altmacro
- JNE_SKIP %I
- offset = (_args + _data_ptr + 8*I)
- mov tmp, offset(state)
- offset = (_lens + 4*I)
- movl $0xFFFFFFFF, offset(state)
-LABEL skip_ %I
- I = (I+1)
-.noaltmacro
-.endr
-
- # Find min length
- vmovdqu _lens+0*16(state), %xmm0
- vmovdqu _lens+1*16(state), %xmm1
-
- vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
- vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
- vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min val in low dword
-
- vmovd %xmm2, DWORD_idx
- mov idx, len2
- and $0xF, idx
- shr $4, len2
- jz len_is_0
-
- vpand clear_low_nibble(%rip), %xmm2, %xmm2
- vpshufd $0, %xmm2, %xmm2
-
- vpsubd %xmm2, %xmm0, %xmm0
- vpsubd %xmm2, %xmm1, %xmm1
-
- vmovdqu %xmm0, _lens+0*16(state)
- vmovdqu %xmm1, _lens+1*16(state)
-
- # "state" and "args" are the same address, arg1
- # len is arg2
- call sha256_x8_avx2
- # state and idx are intact
-
-len_is_0:
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- mov _unused_lanes(state), unused_lanes
- shl $4, unused_lanes
- or idx, unused_lanes
-
- mov unused_lanes, _unused_lanes(state)
- movl $0xFFFFFFFF, _lens(state,idx,4)
-
- vmovd _args_digest(state , idx, 4) , %xmm0
- vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
- vmovd _args_digest+4*32(state, idx, 4), %xmm1
- vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
- vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
- vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
-
- vmovdqu %xmm0, _result_digest(job_rax)
- offset = (_result_digest + 1*16)
- vmovdqu %xmm1, offset(job_rax)
-
-return:
- pop %rbx
- FRAME_END
- ret
-
-return_null:
- xor job_rax, job_rax
- jmp return
-ENDPROC(sha256_mb_mgr_flush_avx2)
-
-##############################################################################
-
-.align 16
-ENTRY(sha256_mb_mgr_get_comp_job_avx2)
- push %rbx
-
- ## if bit 32+3 is set, then all lanes are empty
- mov _unused_lanes(state), unused_lanes
- bt $(32+3), unused_lanes
- jc .return_null
-
- # Find min length
- vmovdqu _lens(state), %xmm0
- vmovdqu _lens+1*16(state), %xmm1
-
- vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
- vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
- vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min val in low dword
-
- vmovd %xmm2, DWORD_idx
- test $~0xF, idx
- jnz .return_null
-
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- mov _unused_lanes(state), unused_lanes
- shl $4, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens(state, idx, 4)
-
- vmovd _args_digest(state, idx, 4), %xmm0
- vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
- vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
- vmovd _args_digest+4*32(state, idx, 4), %xmm1
- vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
- vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
- vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
-
- vmovdqu %xmm0, _result_digest(job_rax)
- offset = (_result_digest + 1*16)
- vmovdqu %xmm1, offset(job_rax)
-
- pop %rbx
-
- ret
-
-.return_null:
- xor job_rax, job_rax
- pop %rbx
- ret
-ENDPROC(sha256_mb_mgr_get_comp_job_avx2)
-
-.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16
-.align 16
-clear_low_nibble:
-.octa 0x000000000000000000000000FFFFFFF0
-
-.section .rodata.cst8, "aM", @progbits, 8
-.align 8
-one:
-.quad 1
-two:
-.quad 2
-three:
-.quad 3
-four:
-.quad 4
-five:
-.quad 5
-six:
-.quad 6
-seven:
-.quad 7
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
deleted file mode 100644
index b0c498371e67..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Initialization code for multi buffer SHA256 algorithm for AVX2
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "sha256_mb_mgr.h"
-
-void sha256_mb_mgr_init_avx2(struct sha256_mb_mgr *state)
-{
- unsigned int j;
-
- state->unused_lanes = 0xF76543210ULL;
- for (j = 0; j < 8; j++) {
- state->lens[j] = 0xFFFFFFFF;
- state->ldata[j].job_in_lane = NULL;
- }
-}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S
deleted file mode 100644
index b36ae7454084..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S
+++ /dev/null
@@ -1,214 +0,0 @@
-/*
- * Buffer submit code for multi buffer SHA256 algorithm
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/linkage.h>
-#include <asm/frame.h>
-#include "sha256_mb_mgr_datastruct.S"
-
-.extern sha256_x8_avx2
-
-# LINUX register definitions
-arg1 = %rdi
-arg2 = %rsi
-size_offset = %rcx
-tmp2 = %rcx
-extra_blocks = %rdx
-
-# Common definitions
-#define state arg1
-#define job %rsi
-#define len2 arg2
-#define p2 arg2
-
-# idx must be a register not clobberred by sha1_x8_avx2
-idx = %r8
-DWORD_idx = %r8d
-last_len = %r8
-
-p = %r11
-start_offset = %r11
-
-unused_lanes = %rbx
-BYTE_unused_lanes = %bl
-
-job_rax = %rax
-len = %rax
-DWORD_len = %eax
-
-lane = %r12
-tmp3 = %r12
-
-tmp = %r9
-DWORD_tmp = %r9d
-
-lane_data = %r10
-
-# JOB* sha256_mb_mgr_submit_avx2(MB_MGR *state, JOB_SHA256 *job)
-# arg 1 : rcx : state
-# arg 2 : rdx : job
-ENTRY(sha256_mb_mgr_submit_avx2)
- FRAME_BEGIN
- push %rbx
- push %r12
-
- mov _unused_lanes(state), unused_lanes
- mov unused_lanes, lane
- and $0xF, lane
- shr $4, unused_lanes
- imul $_LANE_DATA_size, lane, lane_data
- movl $STS_BEING_PROCESSED, _status(job)
- lea _ldata(state, lane_data), lane_data
- mov unused_lanes, _unused_lanes(state)
- movl _len(job), DWORD_len
-
- mov job, _job_in_lane(lane_data)
- shl $4, len
- or lane, len
-
- movl DWORD_len, _lens(state , lane, 4)
-
- # Load digest words from result_digest
- vmovdqu _result_digest(job), %xmm0
- vmovdqu _result_digest+1*16(job), %xmm1
- vmovd %xmm0, _args_digest(state, lane, 4)
- vpextrd $1, %xmm0, _args_digest+1*32(state , lane, 4)
- vpextrd $2, %xmm0, _args_digest+2*32(state , lane, 4)
- vpextrd $3, %xmm0, _args_digest+3*32(state , lane, 4)
- vmovd %xmm1, _args_digest+4*32(state , lane, 4)
-
- vpextrd $1, %xmm1, _args_digest+5*32(state , lane, 4)
- vpextrd $2, %xmm1, _args_digest+6*32(state , lane, 4)
- vpextrd $3, %xmm1, _args_digest+7*32(state , lane, 4)
-
- mov _buffer(job), p
- mov p, _args_data_ptr(state, lane, 8)
-
- cmp $0xF, unused_lanes
- jne return_null
-
-start_loop:
- # Find min length
- vmovdqa _lens(state), %xmm0
- vmovdqa _lens+1*16(state), %xmm1
-
- vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
- vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
- vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
- vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min val in low dword
-
- vmovd %xmm2, DWORD_idx
- mov idx, len2
- and $0xF, idx
- shr $4, len2
- jz len_is_0
-
- vpand clear_low_nibble(%rip), %xmm2, %xmm2
- vpshufd $0, %xmm2, %xmm2
-
- vpsubd %xmm2, %xmm0, %xmm0
- vpsubd %xmm2, %xmm1, %xmm1
-
- vmovdqa %xmm0, _lens + 0*16(state)
- vmovdqa %xmm1, _lens + 1*16(state)
-
- # "state" and "args" are the same address, arg1
- # len is arg2
- call sha256_x8_avx2
-
- # state and idx are intact
-
-len_is_0:
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- mov _unused_lanes(state), unused_lanes
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- shl $4, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens(state,idx,4)
-
- vmovd _args_digest(state, idx, 4), %xmm0
- vpinsrd $1, _args_digest+1*32(state , idx, 4), %xmm0, %xmm0
- vpinsrd $2, _args_digest+2*32(state , idx, 4), %xmm0, %xmm0
- vpinsrd $3, _args_digest+3*32(state , idx, 4), %xmm0, %xmm0
- vmovd _args_digest+4*32(state, idx, 4), %xmm1
-
- vpinsrd $1, _args_digest+5*32(state , idx, 4), %xmm1, %xmm1
- vpinsrd $2, _args_digest+6*32(state , idx, 4), %xmm1, %xmm1
- vpinsrd $3, _args_digest+7*32(state , idx, 4), %xmm1, %xmm1
-
- vmovdqu %xmm0, _result_digest(job_rax)
- vmovdqu %xmm1, _result_digest+1*16(job_rax)
-
-return:
- pop %r12
- pop %rbx
- FRAME_END
- ret
-
-return_null:
- xor job_rax, job_rax
- jmp return
-
-ENDPROC(sha256_mb_mgr_submit_avx2)
-
-.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16
-.align 16
-clear_low_nibble:
- .octa 0x000000000000000000000000FFFFFFF0
diff --git a/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S
deleted file mode 100644
index 1687c80c5995..000000000000
--- a/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S
+++ /dev/null
@@ -1,598 +0,0 @@
-/*
- * Multi-buffer SHA256 algorithm hash compute routine
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/linkage.h>
-#include "sha256_mb_mgr_datastruct.S"
-
-## code to compute oct SHA256 using SSE-256
-## outer calling routine takes care of save and restore of XMM registers
-## Logic designed/laid out by JDG
-
-## Function clobbers: rax, rcx, rdx, rbx, rsi, rdi, r9-r15; %ymm0-15
-## Linux clobbers: rax rbx rcx rdx rsi r9 r10 r11 r12 r13 r14 r15
-## Linux preserves: rdi rbp r8
-##
-## clobbers %ymm0-15
-
-arg1 = %rdi
-arg2 = %rsi
-reg3 = %rcx
-reg4 = %rdx
-
-# Common definitions
-STATE = arg1
-INP_SIZE = arg2
-
-IDX = %rax
-ROUND = %rbx
-TBL = reg3
-
-inp0 = %r9
-inp1 = %r10
-inp2 = %r11
-inp3 = %r12
-inp4 = %r13
-inp5 = %r14
-inp6 = %r15
-inp7 = reg4
-
-a = %ymm0
-b = %ymm1
-c = %ymm2
-d = %ymm3
-e = %ymm4
-f = %ymm5
-g = %ymm6
-h = %ymm7
-
-T1 = %ymm8
-
-a0 = %ymm12
-a1 = %ymm13
-a2 = %ymm14
-TMP = %ymm15
-TMP0 = %ymm6
-TMP1 = %ymm7
-
-TT0 = %ymm8
-TT1 = %ymm9
-TT2 = %ymm10
-TT3 = %ymm11
-TT4 = %ymm12
-TT5 = %ymm13
-TT6 = %ymm14
-TT7 = %ymm15
-
-# Define stack usage
-
-# Assume stack aligned to 32 bytes before call
-# Therefore FRAMESZ mod 32 must be 32-8 = 24
-
-#define FRAMESZ 0x388
-
-#define VMOVPS vmovups
-
-# TRANSPOSE8 r0, r1, r2, r3, r4, r5, r6, r7, t0, t1
-# "transpose" data in {r0...r7} using temps {t0...t1}
-# Input looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
-# r0 = {a7 a6 a5 a4 a3 a2 a1 a0}
-# r1 = {b7 b6 b5 b4 b3 b2 b1 b0}
-# r2 = {c7 c6 c5 c4 c3 c2 c1 c0}
-# r3 = {d7 d6 d5 d4 d3 d2 d1 d0}
-# r4 = {e7 e6 e5 e4 e3 e2 e1 e0}
-# r5 = {f7 f6 f5 f4 f3 f2 f1 f0}
-# r6 = {g7 g6 g5 g4 g3 g2 g1 g0}
-# r7 = {h7 h6 h5 h4 h3 h2 h1 h0}
-#
-# Output looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
-# r0 = {h0 g0 f0 e0 d0 c0 b0 a0}
-# r1 = {h1 g1 f1 e1 d1 c1 b1 a1}
-# r2 = {h2 g2 f2 e2 d2 c2 b2 a2}
-# r3 = {h3 g3 f3 e3 d3 c3 b3 a3}
-# r4 = {h4 g4 f4 e4 d4 c4 b4 a4}
-# r5 = {h5 g5 f5 e5 d5 c5 b5 a5}
-# r6 = {h6 g6 f6 e6 d6 c6 b6 a6}
-# r7 = {h7 g7 f7 e7 d7 c7 b7 a7}
-#
-
-.macro TRANSPOSE8 r0 r1 r2 r3 r4 r5 r6 r7 t0 t1
- # process top half (r0..r3) {a...d}
- vshufps $0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4 b1 b0 a1 a0}
- vshufps $0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6 b3 b2 a3 a2}
- vshufps $0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4 d1 d0 c1 c0}
- vshufps $0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6 d3 d2 c3 c2}
- vshufps $0xDD, \t1, \t0, \r3 # r3 = {d5 c5 b5 a5 d1 c1 b1 a1}
- vshufps $0x88, \r2, \r0, \r1 # r1 = {d6 c6 b6 a6 d2 c2 b2 a2}
- vshufps $0xDD, \r2, \r0, \r0 # r0 = {d7 c7 b7 a7 d3 c3 b3 a3}
- vshufps $0x88, \t1, \t0, \t0 # t0 = {d4 c4 b4 a4 d0 c0 b0 a0}
-
- # use r2 in place of t0
- # process bottom half (r4..r7) {e...h}
- vshufps $0x44, \r5, \r4, \r2 # r2 = {f5 f4 e5 e4 f1 f0 e1 e0}
- vshufps $0xEE, \r5, \r4, \r4 # r4 = {f7 f6 e7 e6 f3 f2 e3 e2}
- vshufps $0x44, \r7, \r6, \t1 # t1 = {h5 h4 g5 g4 h1 h0 g1 g0}
- vshufps $0xEE, \r7, \r6, \r6 # r6 = {h7 h6 g7 g6 h3 h2 g3 g2}
- vshufps $0xDD, \t1, \r2, \r7 # r7 = {h5 g5 f5 e5 h1 g1 f1 e1}
- vshufps $0x88, \r6, \r4, \r5 # r5 = {h6 g6 f6 e6 h2 g2 f2 e2}
- vshufps $0xDD, \r6, \r4, \r4 # r4 = {h7 g7 f7 e7 h3 g3 f3 e3}
- vshufps $0x88, \t1, \r2, \t1 # t1 = {h4 g4 f4 e4 h0 g0 f0 e0}
-
- vperm2f128 $0x13, \r1, \r5, \r6 # h6...a6
- vperm2f128 $0x02, \r1, \r5, \r2 # h2...a2
- vperm2f128 $0x13, \r3, \r7, \r5 # h5...a5
- vperm2f128 $0x02, \r3, \r7, \r1 # h1...a1
- vperm2f128 $0x13, \r0, \r4, \r7 # h7...a7
- vperm2f128 $0x02, \r0, \r4, \r3 # h3...a3
- vperm2f128 $0x13, \t0, \t1, \r4 # h4...a4
- vperm2f128 $0x02, \t0, \t1, \r0 # h0...a0
-
-.endm
-
-.macro ROTATE_ARGS
-TMP_ = h
-h = g
-g = f
-f = e
-e = d
-d = c
-c = b
-b = a
-a = TMP_
-.endm
-
-.macro _PRORD reg imm tmp
- vpslld $(32-\imm),\reg,\tmp
- vpsrld $\imm,\reg, \reg
- vpor \tmp,\reg, \reg
-.endm
-
-# PRORD_nd reg, imm, tmp, src
-.macro _PRORD_nd reg imm tmp src
- vpslld $(32-\imm), \src, \tmp
- vpsrld $\imm, \src, \reg
- vpor \tmp, \reg, \reg
-.endm
-
-# PRORD dst/src, amt
-.macro PRORD reg imm
- _PRORD \reg,\imm,TMP
-.endm
-
-# PRORD_nd dst, src, amt
-.macro PRORD_nd reg tmp imm
- _PRORD_nd \reg, \imm, TMP, \tmp
-.endm
-
-# arguments passed implicitly in preprocessor symbols i, a...h
-.macro ROUND_00_15 _T1 i
- PRORD_nd a0,e,5 # sig1: a0 = (e >> 5)
-
- vpxor g, f, a2 # ch: a2 = f^g
- vpand e,a2, a2 # ch: a2 = (f^g)&e
- vpxor g, a2, a2 # a2 = ch
-
- PRORD_nd a1,e,25 # sig1: a1 = (e >> 25)
-
- vmovdqu \_T1,(SZ8*(\i & 0xf))(%rsp)
- vpaddd (TBL,ROUND,1), \_T1, \_T1 # T1 = W + K
- vpxor e,a0, a0 # sig1: a0 = e ^ (e >> 5)
- PRORD a0, 6 # sig1: a0 = (e >> 6) ^ (e >> 11)
- vpaddd a2, h, h # h = h + ch
- PRORD_nd a2,a,11 # sig0: a2 = (a >> 11)
- vpaddd \_T1,h, h # h = h + ch + W + K
- vpxor a1, a0, a0 # a0 = sigma1
- PRORD_nd a1,a,22 # sig0: a1 = (a >> 22)
- vpxor c, a, \_T1 # maj: T1 = a^c
- add $SZ8, ROUND # ROUND++
- vpand b, \_T1, \_T1 # maj: T1 = (a^c)&b
- vpaddd a0, h, h
- vpaddd h, d, d
- vpxor a, a2, a2 # sig0: a2 = a ^ (a >> 11)
- PRORD a2,2 # sig0: a2 = (a >> 2) ^ (a >> 13)
- vpxor a1, a2, a2 # a2 = sig0
- vpand c, a, a1 # maj: a1 = a&c
- vpor \_T1, a1, a1 # a1 = maj
- vpaddd a1, h, h # h = h + ch + W + K + maj
- vpaddd a2, h, h # h = h + ch + W + K + maj + sigma0
- ROTATE_ARGS
-.endm
-
-# arguments passed implicitly in preprocessor symbols i, a...h
-.macro ROUND_16_XX _T1 i
- vmovdqu (SZ8*((\i-15)&0xf))(%rsp), \_T1
- vmovdqu (SZ8*((\i-2)&0xf))(%rsp), a1
- vmovdqu \_T1, a0
- PRORD \_T1,11
- vmovdqu a1, a2
- PRORD a1,2
- vpxor a0, \_T1, \_T1
- PRORD \_T1, 7
- vpxor a2, a1, a1
- PRORD a1, 17
- vpsrld $3, a0, a0
- vpxor a0, \_T1, \_T1
- vpsrld $10, a2, a2
- vpxor a2, a1, a1
- vpaddd (SZ8*((\i-16)&0xf))(%rsp), \_T1, \_T1
- vpaddd (SZ8*((\i-7)&0xf))(%rsp), a1, a1
- vpaddd a1, \_T1, \_T1
-
- ROUND_00_15 \_T1,\i
-.endm
-
-# SHA256_ARGS:
-# UINT128 digest[8]; // transposed digests
-# UINT8 *data_ptr[4];
-
-# void sha256_x8_avx2(SHA256_ARGS *args, UINT64 bytes);
-# arg 1 : STATE : pointer to array of pointers to input data
-# arg 2 : INP_SIZE : size of input in blocks
- # general registers preserved in outer calling routine
- # outer calling routine saves all the XMM registers
- # save rsp, allocate 32-byte aligned for local variables
-ENTRY(sha256_x8_avx2)
-
- # save callee-saved clobbered registers to comply with C function ABI
- push %r12
- push %r13
- push %r14
- push %r15
-
- mov %rsp, IDX
- sub $FRAMESZ, %rsp
- and $~0x1F, %rsp
- mov IDX, _rsp(%rsp)
-
- # Load the pre-transposed incoming digest.
- vmovdqu 0*SHA256_DIGEST_ROW_SIZE(STATE),a
- vmovdqu 1*SHA256_DIGEST_ROW_SIZE(STATE),b
- vmovdqu 2*SHA256_DIGEST_ROW_SIZE(STATE),c
- vmovdqu 3*SHA256_DIGEST_ROW_SIZE(STATE),d
- vmovdqu 4*SHA256_DIGEST_ROW_SIZE(STATE),e
- vmovdqu 5*SHA256_DIGEST_ROW_SIZE(STATE),f
- vmovdqu 6*SHA256_DIGEST_ROW_SIZE(STATE),g
- vmovdqu 7*SHA256_DIGEST_ROW_SIZE(STATE),h
-
- lea K256_8(%rip),TBL
-
- # load the address of each of the 4 message lanes
- # getting ready to transpose input onto stack
- mov _args_data_ptr+0*PTR_SZ(STATE),inp0
- mov _args_data_ptr+1*PTR_SZ(STATE),inp1
- mov _args_data_ptr+2*PTR_SZ(STATE),inp2
- mov _args_data_ptr+3*PTR_SZ(STATE),inp3
- mov _args_data_ptr+4*PTR_SZ(STATE),inp4
- mov _args_data_ptr+5*PTR_SZ(STATE),inp5
- mov _args_data_ptr+6*PTR_SZ(STATE),inp6
- mov _args_data_ptr+7*PTR_SZ(STATE),inp7
-
- xor IDX, IDX
-lloop:
- xor ROUND, ROUND
-
- # save old digest
- vmovdqu a, _digest(%rsp)
- vmovdqu b, _digest+1*SZ8(%rsp)
- vmovdqu c, _digest+2*SZ8(%rsp)
- vmovdqu d, _digest+3*SZ8(%rsp)
- vmovdqu e, _digest+4*SZ8(%rsp)
- vmovdqu f, _digest+5*SZ8(%rsp)
- vmovdqu g, _digest+6*SZ8(%rsp)
- vmovdqu h, _digest+7*SZ8(%rsp)
- i = 0
-.rep 2
- VMOVPS i*32(inp0, IDX), TT0
- VMOVPS i*32(inp1, IDX), TT1
- VMOVPS i*32(inp2, IDX), TT2
- VMOVPS i*32(inp3, IDX), TT3
- VMOVPS i*32(inp4, IDX), TT4
- VMOVPS i*32(inp5, IDX), TT5
- VMOVPS i*32(inp6, IDX), TT6
- VMOVPS i*32(inp7, IDX), TT7
- vmovdqu g, _ytmp(%rsp)
- vmovdqu h, _ytmp+1*SZ8(%rsp)
- TRANSPOSE8 TT0, TT1, TT2, TT3, TT4, TT5, TT6, TT7, TMP0, TMP1
- vmovdqu PSHUFFLE_BYTE_FLIP_MASK(%rip), TMP1
- vmovdqu _ytmp(%rsp), g
- vpshufb TMP1, TT0, TT0
- vpshufb TMP1, TT1, TT1
- vpshufb TMP1, TT2, TT2
- vpshufb TMP1, TT3, TT3
- vpshufb TMP1, TT4, TT4
- vpshufb TMP1, TT5, TT5
- vpshufb TMP1, TT6, TT6
- vpshufb TMP1, TT7, TT7
- vmovdqu _ytmp+1*SZ8(%rsp), h
- vmovdqu TT4, _ytmp(%rsp)
- vmovdqu TT5, _ytmp+1*SZ8(%rsp)
- vmovdqu TT6, _ytmp+2*SZ8(%rsp)
- vmovdqu TT7, _ytmp+3*SZ8(%rsp)
- ROUND_00_15 TT0,(i*8+0)
- vmovdqu _ytmp(%rsp), TT0
- ROUND_00_15 TT1,(i*8+1)
- vmovdqu _ytmp+1*SZ8(%rsp), TT1
- ROUND_00_15 TT2,(i*8+2)
- vmovdqu _ytmp+2*SZ8(%rsp), TT2
- ROUND_00_15 TT3,(i*8+3)
- vmovdqu _ytmp+3*SZ8(%rsp), TT3
- ROUND_00_15 TT0,(i*8+4)
- ROUND_00_15 TT1,(i*8+5)
- ROUND_00_15 TT2,(i*8+6)
- ROUND_00_15 TT3,(i*8+7)
- i = (i+1)
-.endr
- add $64, IDX
- i = (i*8)
-
- jmp Lrounds_16_xx
-.align 16
-Lrounds_16_xx:
-.rep 16
- ROUND_16_XX T1, i
- i = (i+1)
-.endr
-
- cmp $ROUNDS,ROUND
- jb Lrounds_16_xx
-
- # add old digest
- vpaddd _digest+0*SZ8(%rsp), a, a
- vpaddd _digest+1*SZ8(%rsp), b, b
- vpaddd _digest+2*SZ8(%rsp), c, c
- vpaddd _digest+3*SZ8(%rsp), d, d
- vpaddd _digest+4*SZ8(%rsp), e, e
- vpaddd _digest+5*SZ8(%rsp), f, f
- vpaddd _digest+6*SZ8(%rsp), g, g
- vpaddd _digest+7*SZ8(%rsp), h, h
-
- sub $1, INP_SIZE # unit is blocks
- jne lloop
-
- # write back to memory (state object) the transposed digest
- vmovdqu a, 0*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu b, 1*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu c, 2*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu d, 3*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu e, 4*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu f, 5*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu g, 6*SHA256_DIGEST_ROW_SIZE(STATE)
- vmovdqu h, 7*SHA256_DIGEST_ROW_SIZE(STATE)
-
- # update input pointers
- add IDX, inp0
- mov inp0, _args_data_ptr+0*8(STATE)
- add IDX, inp1
- mov inp1, _args_data_ptr+1*8(STATE)
- add IDX, inp2
- mov inp2, _args_data_ptr+2*8(STATE)
- add IDX, inp3
- mov inp3, _args_data_ptr+3*8(STATE)
- add IDX, inp4
- mov inp4, _args_data_ptr+4*8(STATE)
- add IDX, inp5
- mov inp5, _args_data_ptr+5*8(STATE)
- add IDX, inp6
- mov inp6, _args_data_ptr+6*8(STATE)
- add IDX, inp7
- mov inp7, _args_data_ptr+7*8(STATE)
-
- # Postamble
- mov _rsp(%rsp), %rsp
-
- # restore callee-saved clobbered registers
- pop %r15
- pop %r14
- pop %r13
- pop %r12
-
- ret
-ENDPROC(sha256_x8_avx2)
-
-.section .rodata.K256_8, "a", @progbits
-.align 64
-K256_8:
- .octa 0x428a2f98428a2f98428a2f98428a2f98
- .octa 0x428a2f98428a2f98428a2f98428a2f98
- .octa 0x71374491713744917137449171374491
- .octa 0x71374491713744917137449171374491
- .octa 0xb5c0fbcfb5c0fbcfb5c0fbcfb5c0fbcf
- .octa 0xb5c0fbcfb5c0fbcfb5c0fbcfb5c0fbcf
- .octa 0xe9b5dba5e9b5dba5e9b5dba5e9b5dba5
- .octa 0xe9b5dba5e9b5dba5e9b5dba5e9b5dba5
- .octa 0x3956c25b3956c25b3956c25b3956c25b
- .octa 0x3956c25b3956c25b3956c25b3956c25b
- .octa 0x59f111f159f111f159f111f159f111f1
- .octa 0x59f111f159f111f159f111f159f111f1
- .octa 0x923f82a4923f82a4923f82a4923f82a4
- .octa 0x923f82a4923f82a4923f82a4923f82a4
- .octa 0xab1c5ed5ab1c5ed5ab1c5ed5ab1c5ed5
- .octa 0xab1c5ed5ab1c5ed5ab1c5ed5ab1c5ed5
- .octa 0xd807aa98d807aa98d807aa98d807aa98
- .octa 0xd807aa98d807aa98d807aa98d807aa98
- .octa 0x12835b0112835b0112835b0112835b01
- .octa 0x12835b0112835b0112835b0112835b01
- .octa 0x243185be243185be243185be243185be
- .octa 0x243185be243185be243185be243185be
- .octa 0x550c7dc3550c7dc3550c7dc3550c7dc3
- .octa 0x550c7dc3550c7dc3550c7dc3550c7dc3
- .octa 0x72be5d7472be5d7472be5d7472be5d74
- .octa 0x72be5d7472be5d7472be5d7472be5d74
- .octa 0x80deb1fe80deb1fe80deb1fe80deb1fe
- .octa 0x80deb1fe80deb1fe80deb1fe80deb1fe
- .octa 0x9bdc06a79bdc06a79bdc06a79bdc06a7
- .octa 0x9bdc06a79bdc06a79bdc06a79bdc06a7
- .octa 0xc19bf174c19bf174c19bf174c19bf174
- .octa 0xc19bf174c19bf174c19bf174c19bf174
- .octa 0xe49b69c1e49b69c1e49b69c1e49b69c1
- .octa 0xe49b69c1e49b69c1e49b69c1e49b69c1
- .octa 0xefbe4786efbe4786efbe4786efbe4786
- .octa 0xefbe4786efbe4786efbe4786efbe4786
- .octa 0x0fc19dc60fc19dc60fc19dc60fc19dc6
- .octa 0x0fc19dc60fc19dc60fc19dc60fc19dc6
- .octa 0x240ca1cc240ca1cc240ca1cc240ca1cc
- .octa 0x240ca1cc240ca1cc240ca1cc240ca1cc
- .octa 0x2de92c6f2de92c6f2de92c6f2de92c6f
- .octa 0x2de92c6f2de92c6f2de92c6f2de92c6f
- .octa 0x4a7484aa4a7484aa4a7484aa4a7484aa
- .octa 0x4a7484aa4a7484aa4a7484aa4a7484aa
- .octa 0x5cb0a9dc5cb0a9dc5cb0a9dc5cb0a9dc
- .octa 0x5cb0a9dc5cb0a9dc5cb0a9dc5cb0a9dc
- .octa 0x76f988da76f988da76f988da76f988da
- .octa 0x76f988da76f988da76f988da76f988da
- .octa 0x983e5152983e5152983e5152983e5152
- .octa 0x983e5152983e5152983e5152983e5152
- .octa 0xa831c66da831c66da831c66da831c66d
- .octa 0xa831c66da831c66da831c66da831c66d
- .octa 0xb00327c8b00327c8b00327c8b00327c8
- .octa 0xb00327c8b00327c8b00327c8b00327c8
- .octa 0xbf597fc7bf597fc7bf597fc7bf597fc7
- .octa 0xbf597fc7bf597fc7bf597fc7bf597fc7
- .octa 0xc6e00bf3c6e00bf3c6e00bf3c6e00bf3
- .octa 0xc6e00bf3c6e00bf3c6e00bf3c6e00bf3
- .octa 0xd5a79147d5a79147d5a79147d5a79147
- .octa 0xd5a79147d5a79147d5a79147d5a79147
- .octa 0x06ca635106ca635106ca635106ca6351
- .octa 0x06ca635106ca635106ca635106ca6351
- .octa 0x14292967142929671429296714292967
- .octa 0x14292967142929671429296714292967
- .octa 0x27b70a8527b70a8527b70a8527b70a85
- .octa 0x27b70a8527b70a8527b70a8527b70a85
- .octa 0x2e1b21382e1b21382e1b21382e1b2138
- .octa 0x2e1b21382e1b21382e1b21382e1b2138
- .octa 0x4d2c6dfc4d2c6dfc4d2c6dfc4d2c6dfc
- .octa 0x4d2c6dfc4d2c6dfc4d2c6dfc4d2c6dfc
- .octa 0x53380d1353380d1353380d1353380d13
- .octa 0x53380d1353380d1353380d1353380d13
- .octa 0x650a7354650a7354650a7354650a7354
- .octa 0x650a7354650a7354650a7354650a7354
- .octa 0x766a0abb766a0abb766a0abb766a0abb
- .octa 0x766a0abb766a0abb766a0abb766a0abb
- .octa 0x81c2c92e81c2c92e81c2c92e81c2c92e
- .octa 0x81c2c92e81c2c92e81c2c92e81c2c92e
- .octa 0x92722c8592722c8592722c8592722c85
- .octa 0x92722c8592722c8592722c8592722c85
- .octa 0xa2bfe8a1a2bfe8a1a2bfe8a1a2bfe8a1
- .octa 0xa2bfe8a1a2bfe8a1a2bfe8a1a2bfe8a1
- .octa 0xa81a664ba81a664ba81a664ba81a664b
- .octa 0xa81a664ba81a664ba81a664ba81a664b
- .octa 0xc24b8b70c24b8b70c24b8b70c24b8b70
- .octa 0xc24b8b70c24b8b70c24b8b70c24b8b70
- .octa 0xc76c51a3c76c51a3c76c51a3c76c51a3
- .octa 0xc76c51a3c76c51a3c76c51a3c76c51a3
- .octa 0xd192e819d192e819d192e819d192e819
- .octa 0xd192e819d192e819d192e819d192e819
- .octa 0xd6990624d6990624d6990624d6990624
- .octa 0xd6990624d6990624d6990624d6990624
- .octa 0xf40e3585f40e3585f40e3585f40e3585
- .octa 0xf40e3585f40e3585f40e3585f40e3585
- .octa 0x106aa070106aa070106aa070106aa070
- .octa 0x106aa070106aa070106aa070106aa070
- .octa 0x19a4c11619a4c11619a4c11619a4c116
- .octa 0x19a4c11619a4c11619a4c11619a4c116
- .octa 0x1e376c081e376c081e376c081e376c08
- .octa 0x1e376c081e376c081e376c081e376c08
- .octa 0x2748774c2748774c2748774c2748774c
- .octa 0x2748774c2748774c2748774c2748774c
- .octa 0x34b0bcb534b0bcb534b0bcb534b0bcb5
- .octa 0x34b0bcb534b0bcb534b0bcb534b0bcb5
- .octa 0x391c0cb3391c0cb3391c0cb3391c0cb3
- .octa 0x391c0cb3391c0cb3391c0cb3391c0cb3
- .octa 0x4ed8aa4a4ed8aa4a4ed8aa4a4ed8aa4a
- .octa 0x4ed8aa4a4ed8aa4a4ed8aa4a4ed8aa4a
- .octa 0x5b9cca4f5b9cca4f5b9cca4f5b9cca4f
- .octa 0x5b9cca4f5b9cca4f5b9cca4f5b9cca4f
- .octa 0x682e6ff3682e6ff3682e6ff3682e6ff3
- .octa 0x682e6ff3682e6ff3682e6ff3682e6ff3
- .octa 0x748f82ee748f82ee748f82ee748f82ee
- .octa 0x748f82ee748f82ee748f82ee748f82ee
- .octa 0x78a5636f78a5636f78a5636f78a5636f
- .octa 0x78a5636f78a5636f78a5636f78a5636f
- .octa 0x84c8781484c8781484c8781484c87814
- .octa 0x84c8781484c8781484c8781484c87814
- .octa 0x8cc702088cc702088cc702088cc70208
- .octa 0x8cc702088cc702088cc702088cc70208
- .octa 0x90befffa90befffa90befffa90befffa
- .octa 0x90befffa90befffa90befffa90befffa
- .octa 0xa4506ceba4506ceba4506ceba4506ceb
- .octa 0xa4506ceba4506ceba4506ceba4506ceb
- .octa 0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7
- .octa 0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7
- .octa 0xc67178f2c67178f2c67178f2c67178f2
- .octa 0xc67178f2c67178f2c67178f2c67178f2
-
-.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32
-.align 32
-PSHUFFLE_BYTE_FLIP_MASK:
-.octa 0x0c0d0e0f08090a0b0405060700010203
-.octa 0x0c0d0e0f08090a0b0405060700010203
-
-.section .rodata.cst256.K256, "aM", @progbits, 256
-.align 64
-.global K256
-K256:
- .int 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
- .int 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
- .int 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
- .int 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
- .int 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
- .int 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
- .int 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
- .int 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
- .int 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
- .int 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
- .int 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
- .int 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
- .int 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
- .int 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
- .int 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
- .int 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
diff --git a/arch/x86/crypto/sha512-mb/Makefile b/arch/x86/crypto/sha512-mb/Makefile
deleted file mode 100644
index 90f1ef69152e..000000000000
--- a/arch/x86/crypto/sha512-mb/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Arch-specific CryptoAPI modules.
-#
-
-avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
- $(comma)4)$(comma)%ymm2,yes,no)
-ifeq ($(avx2_supported),yes)
- obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb.o
- sha512-mb-y := sha512_mb.o sha512_mb_mgr_flush_avx2.o \
- sha512_mb_mgr_init_avx2.o sha512_mb_mgr_submit_avx2.o sha512_x4_avx2.o
-endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
deleted file mode 100644
index 26b85678012d..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ /dev/null
@@ -1,1047 +0,0 @@
-/*
- * Multi buffer SHA512 algorithm Glue Code
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
-#include <crypto/mcryptd.h>
-#include <crypto/crypto_wq.h>
-#include <asm/byteorder.h>
-#include <linux/hardirq.h>
-#include <asm/fpu/api.h>
-#include "sha512_mb_ctx.h"
-
-#define FLUSH_INTERVAL 1000 /* in usec */
-
-static struct mcryptd_alg_state sha512_mb_alg_state;
-
-struct sha512_mb_ctx {
- struct mcryptd_ahash *mcryptd_tfm;
-};
-
-static inline struct mcryptd_hash_request_ctx
- *cast_hash_to_mcryptd_ctx(struct sha512_hash_ctx *hash_ctx)
-{
- struct ahash_request *areq;
-
- areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
- return container_of(areq, struct mcryptd_hash_request_ctx, areq);
-}
-
-static inline struct ahash_request
- *cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
-{
- return container_of((void *) ctx, struct ahash_request, __ctx);
-}
-
-static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
- struct ahash_request *areq)
-{
- rctx->flag = HASH_UPDATE;
-}
-
-static asmlinkage void (*sha512_job_mgr_init)(struct sha512_mb_mgr *state);
-static asmlinkage struct job_sha512* (*sha512_job_mgr_submit)
- (struct sha512_mb_mgr *state,
- struct job_sha512 *job);
-static asmlinkage struct job_sha512* (*sha512_job_mgr_flush)
- (struct sha512_mb_mgr *state);
-static asmlinkage struct job_sha512* (*sha512_job_mgr_get_comp_job)
- (struct sha512_mb_mgr *state);
-
-inline uint32_t sha512_pad(uint8_t padblock[SHA512_BLOCK_SIZE * 2],
- uint64_t total_len)
-{
- uint32_t i = total_len & (SHA512_BLOCK_SIZE - 1);
-
- memset(&padblock[i], 0, SHA512_BLOCK_SIZE);
- padblock[i] = 0x80;
-
- i += ((SHA512_BLOCK_SIZE - 1) &
- (0 - (total_len + SHA512_PADLENGTHFIELD_SIZE + 1)))
- + 1 + SHA512_PADLENGTHFIELD_SIZE;
-
-#if SHA512_PADLENGTHFIELD_SIZE == 16
- *((uint64_t *) &padblock[i - 16]) = 0;
-#endif
-
- *((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
-
- /* Number of extra blocks to hash */
- return i >> SHA512_LOG2_BLOCK_SIZE;
-}
-
-static struct sha512_hash_ctx *sha512_ctx_mgr_resubmit
- (struct sha512_ctx_mgr *mgr, struct sha512_hash_ctx *ctx)
-{
- while (ctx) {
- if (ctx->status & HASH_CTX_STS_COMPLETE) {
- /* Clear PROCESSING bit */
- ctx->status = HASH_CTX_STS_COMPLETE;
- return ctx;
- }
-
- /*
- * If the extra blocks are empty, begin hashing what remains
- * in the user's buffer.
- */
- if (ctx->partial_block_buffer_length == 0 &&
- ctx->incoming_buffer_length) {
-
- const void *buffer = ctx->incoming_buffer;
- uint32_t len = ctx->incoming_buffer_length;
- uint32_t copy_len;
-
- /*
- * Only entire blocks can be hashed.
- * Copy remainder to extra blocks buffer.
- */
- copy_len = len & (SHA512_BLOCK_SIZE-1);
-
- if (copy_len) {
- len -= copy_len;
- memcpy(ctx->partial_block_buffer,
- ((const char *) buffer + len),
- copy_len);
- ctx->partial_block_buffer_length = copy_len;
- }
-
- ctx->incoming_buffer_length = 0;
-
- /* len should be a multiple of the block size now */
- assert((len % SHA512_BLOCK_SIZE) == 0);
-
- /* Set len to the number of blocks to be hashed */
- len >>= SHA512_LOG2_BLOCK_SIZE;
-
- if (len) {
-
- ctx->job.buffer = (uint8_t *) buffer;
- ctx->job.len = len;
- ctx = (struct sha512_hash_ctx *)
- sha512_job_mgr_submit(&mgr->mgr,
- &ctx->job);
- continue;
- }
- }
-
- /*
- * If the extra blocks are not empty, then we are
- * either on the last block(s) or we need more
- * user input before continuing.
- */
- if (ctx->status & HASH_CTX_STS_LAST) {
-
- uint8_t *buf = ctx->partial_block_buffer;
- uint32_t n_extra_blocks =
- sha512_pad(buf, ctx->total_length);
-
- ctx->status = (HASH_CTX_STS_PROCESSING |
- HASH_CTX_STS_COMPLETE);
- ctx->job.buffer = buf;
- ctx->job.len = (uint32_t) n_extra_blocks;
- ctx = (struct sha512_hash_ctx *)
- sha512_job_mgr_submit(&mgr->mgr, &ctx->job);
- continue;
- }
-
- if (ctx)
- ctx->status = HASH_CTX_STS_IDLE;
- return ctx;
- }
-
- return NULL;
-}
-
-static struct sha512_hash_ctx
- *sha512_ctx_mgr_get_comp_ctx(struct mcryptd_alg_cstate *cstate)
-{
- /*
- * If get_comp_job returns NULL, there are no jobs complete.
- * If get_comp_job returns a job, verify that it is safe to return to
- * the user.
- * If it is not ready, resubmit the job to finish processing.
- * If sha512_ctx_mgr_resubmit returned a job, it is ready to be
- * returned.
- * Otherwise, all jobs currently being managed by the hash_ctx_mgr
- * still need processing.
- */
- struct sha512_ctx_mgr *mgr;
- struct sha512_hash_ctx *ctx;
- unsigned long flags;
-
- mgr = cstate->mgr;
- spin_lock_irqsave(&cstate->work_lock, flags);
- ctx = (struct sha512_hash_ctx *)
- sha512_job_mgr_get_comp_job(&mgr->mgr);
- ctx = sha512_ctx_mgr_resubmit(mgr, ctx);
- spin_unlock_irqrestore(&cstate->work_lock, flags);
- return ctx;
-}
-
-static void sha512_ctx_mgr_init(struct sha512_ctx_mgr *mgr)
-{
- sha512_job_mgr_init(&mgr->mgr);
-}
-
-static struct sha512_hash_ctx
- *sha512_ctx_mgr_submit(struct mcryptd_alg_cstate *cstate,
- struct sha512_hash_ctx *ctx,
- const void *buffer,
- uint32_t len,
- int flags)
-{
- struct sha512_ctx_mgr *mgr;
- unsigned long irqflags;
-
- mgr = cstate->mgr;
- spin_lock_irqsave(&cstate->work_lock, irqflags);
- if (flags & ~(HASH_UPDATE | HASH_LAST)) {
- /* User should not pass anything other than UPDATE or LAST */
- ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
- goto unlock;
- }
-
- if (ctx->status & HASH_CTX_STS_PROCESSING) {
- /* Cannot submit to a currently processing job. */
- ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
- goto unlock;
- }
-
- if (ctx->status & HASH_CTX_STS_COMPLETE) {
- /* Cannot update a finished job. */
- ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
- goto unlock;
- }
-
- /*
- * If we made it here, there were no errors during this call to
- * submit
- */
- ctx->error = HASH_CTX_ERROR_NONE;
-
- /* Store buffer ptr info from user */
- ctx->incoming_buffer = buffer;
- ctx->incoming_buffer_length = len;
-
- /*
- * Store the user's request flags and mark this ctx as currently being
- * processed.
- */
- ctx->status = (flags & HASH_LAST) ?
- (HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
- HASH_CTX_STS_PROCESSING;
-
- /* Advance byte counter */
- ctx->total_length += len;
-
- /*
- * If there is anything currently buffered in the extra blocks,
- * append to it until it contains a whole block.
- * Or if the user's buffer contains less than a whole block,
- * append as much as possible to the extra block.
- */
- if (ctx->partial_block_buffer_length || len < SHA512_BLOCK_SIZE) {
- /* Compute how many bytes to copy from user buffer into extra
- * block
- */
- uint32_t copy_len = SHA512_BLOCK_SIZE -
- ctx->partial_block_buffer_length;
- if (len < copy_len)
- copy_len = len;
-
- if (copy_len) {
- /* Copy and update relevant pointers and counters */
- memcpy
- (&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
- buffer, copy_len);
-
- ctx->partial_block_buffer_length += copy_len;
- ctx->incoming_buffer = (const void *)
- ((const char *)buffer + copy_len);
- ctx->incoming_buffer_length = len - copy_len;
- }
-
- /* The extra block should never contain more than 1 block
- * here
- */
- assert(ctx->partial_block_buffer_length <= SHA512_BLOCK_SIZE);
-
- /* If the extra block buffer contains exactly 1 block, it can
- * be hashed.
- */
- if (ctx->partial_block_buffer_length >= SHA512_BLOCK_SIZE) {
- ctx->partial_block_buffer_length = 0;
-
- ctx->job.buffer = ctx->partial_block_buffer;
- ctx->job.len = 1;
- ctx = (struct sha512_hash_ctx *)
- sha512_job_mgr_submit(&mgr->mgr, &ctx->job);
- }
- }
-
- ctx = sha512_ctx_mgr_resubmit(mgr, ctx);
-unlock:
- spin_unlock_irqrestore(&cstate->work_lock, irqflags);
- return ctx;
-}
-
-static struct sha512_hash_ctx *sha512_ctx_mgr_flush(struct mcryptd_alg_cstate *cstate)
-{
- struct sha512_ctx_mgr *mgr;
- struct sha512_hash_ctx *ctx;
- unsigned long flags;
-
- mgr = cstate->mgr;
- spin_lock_irqsave(&cstate->work_lock, flags);
- while (1) {
- ctx = (struct sha512_hash_ctx *)
- sha512_job_mgr_flush(&mgr->mgr);
-
- /* If flush returned 0, there are no more jobs in flight. */
- if (!ctx)
- break;
-
- /*
- * If flush returned a job, resubmit the job to finish
- * processing.
- */
- ctx = sha512_ctx_mgr_resubmit(mgr, ctx);
-
- /*
- * If sha512_ctx_mgr_resubmit returned a job, it is ready to
- * be returned. Otherwise, all jobs currently being managed by
- * the sha512_ctx_mgr still need processing. Loop.
- */
- if (ctx)
- break;
- }
- spin_unlock_irqrestore(&cstate->work_lock, flags);
- return ctx;
-}
-
-static int sha512_mb_init(struct ahash_request *areq)
-{
- struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
-
- hash_ctx_init(sctx);
- sctx->job.result_digest[0] = SHA512_H0;
- sctx->job.result_digest[1] = SHA512_H1;
- sctx->job.result_digest[2] = SHA512_H2;
- sctx->job.result_digest[3] = SHA512_H3;
- sctx->job.result_digest[4] = SHA512_H4;
- sctx->job.result_digest[5] = SHA512_H5;
- sctx->job.result_digest[6] = SHA512_H6;
- sctx->job.result_digest[7] = SHA512_H7;
- sctx->total_length = 0;
- sctx->partial_block_buffer_length = 0;
- sctx->status = HASH_CTX_STS_IDLE;
-
- return 0;
-}
-
-static int sha512_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
-{
- int i;
- struct sha512_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
- __be64 *dst = (__be64 *) rctx->out;
-
- for (i = 0; i < 8; ++i)
- dst[i] = cpu_to_be64(sctx->job.result_digest[i]);
-
- return 0;
-}
-
-static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
- struct mcryptd_alg_cstate *cstate, bool flush)
-{
- int flag = HASH_UPDATE;
- int nbytes, err = 0;
- struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
- struct sha512_hash_ctx *sha_ctx;
-
- /* more work ? */
- while (!(rctx->flag & HASH_DONE)) {
- nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
- if (nbytes < 0) {
- err = nbytes;
- goto out;
- }
- /* check if the walk is done */
- if (crypto_ahash_walk_last(&rctx->walk)) {
- rctx->flag |= HASH_DONE;
- if (rctx->flag & HASH_FINAL)
- flag |= HASH_LAST;
-
- }
- sha_ctx = (struct sha512_hash_ctx *)
- ahash_request_ctx(&rctx->areq);
- kernel_fpu_begin();
- sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx,
- rctx->walk.data, nbytes, flag);
- if (!sha_ctx) {
- if (flush)
- sha_ctx = sha512_ctx_mgr_flush(cstate);
- }
- kernel_fpu_end();
- if (sha_ctx)
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- else {
- rctx = NULL;
- goto out;
- }
- }
-
- /* copy the results */
- if (rctx->flag & HASH_FINAL)
- sha512_mb_set_results(rctx);
-
-out:
- *ret_rctx = rctx;
- return err;
-}
-
-static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
- struct mcryptd_alg_cstate *cstate,
- int err)
-{
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha512_hash_ctx *sha_ctx;
- struct mcryptd_hash_request_ctx *req_ctx;
- int ret;
- unsigned long flags;
-
- /* remove from work list */
- spin_lock_irqsave(&cstate->work_lock, flags);
- list_del(&rctx->waiter);
- spin_unlock_irqrestore(&cstate->work_lock, flags);
-
- if (irqs_disabled())
- rctx->complete(&req->base, err);
- else {
- local_bh_disable();
- rctx->complete(&req->base, err);
- local_bh_enable();
- }
-
- /* check to see if there are other jobs that are done */
- sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate);
- while (sha_ctx) {
- req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&req_ctx, cstate, false);
- if (req_ctx) {
- spin_lock_irqsave(&cstate->work_lock, flags);
- list_del(&req_ctx->waiter);
- spin_unlock_irqrestore(&cstate->work_lock, flags);
-
- req = cast_mcryptd_ctx_to_req(req_ctx);
- if (irqs_disabled())
- req_ctx->complete(&req->base, ret);
- else {
- local_bh_disable();
- req_ctx->complete(&req->base, ret);
- local_bh_enable();
- }
- }
- sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate);
- }
-
- return 0;
-}
-
-static void sha512_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
- struct mcryptd_alg_cstate *cstate)
-{
- unsigned long next_flush;
- unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
- unsigned long flags;
-
- /* initialize tag */
- rctx->tag.arrival = jiffies; /* tag the arrival time */
- rctx->tag.seq_num = cstate->next_seq_num++;
- next_flush = rctx->tag.arrival + delay;
- rctx->tag.expire = next_flush;
-
- spin_lock_irqsave(&cstate->work_lock, flags);
- list_add_tail(&rctx->waiter, &cstate->work_list);
- spin_unlock_irqrestore(&cstate->work_lock, flags);
-
- mcryptd_arm_flusher(cstate, delay);
-}
-
-static int sha512_mb_update(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx,
- areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
-
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha512_hash_ctx *sha_ctx;
- int ret = 0, nbytes;
-
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- nbytes = crypto_ahash_walk_first(req, &rctx->walk);
-
- if (nbytes < 0) {
- ret = nbytes;
- goto done;
- }
-
- if (crypto_ahash_walk_last(&rctx->walk))
- rctx->flag |= HASH_DONE;
-
- /* submit */
- sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
- sha512_mb_add_list(rctx, cstate);
- kernel_fpu_begin();
- sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, rctx->walk.data,
- nbytes, HASH_UPDATE);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
-
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha512_mb_finup(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx,
- areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
-
- struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
- struct sha512_hash_ctx *sha_ctx;
- int ret = 0, flag = HASH_UPDATE, nbytes;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- nbytes = crypto_ahash_walk_first(req, &rctx->walk);
-
- if (nbytes < 0) {
- ret = nbytes;
- goto done;
- }
-
- if (crypto_ahash_walk_last(&rctx->walk)) {
- rctx->flag |= HASH_DONE;
- flag = HASH_LAST;
- }
-
- /* submit */
- rctx->flag |= HASH_FINAL;
- sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
- sha512_mb_add_list(rctx, cstate);
-
- kernel_fpu_begin();
- sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, rctx->walk.data,
- nbytes, flag);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha512_mb_final(struct ahash_request *areq)
-{
- struct mcryptd_hash_request_ctx *rctx =
- container_of(areq, struct mcryptd_hash_request_ctx,
- areq);
- struct mcryptd_alg_cstate *cstate =
- this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
-
- struct sha512_hash_ctx *sha_ctx;
- int ret = 0;
- u8 data;
-
- /* sanity check */
- if (rctx->tag.cpu != smp_processor_id()) {
- pr_err("mcryptd error: cpu clash\n");
- goto done;
- }
-
- /* need to init context */
- req_ctx_init(rctx, areq);
-
- rctx->flag |= HASH_DONE | HASH_FINAL;
-
- sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
- /* flag HASH_FINAL and 0 data size */
- sha512_mb_add_list(rctx, cstate);
- kernel_fpu_begin();
- sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, &data, 0, HASH_LAST);
- kernel_fpu_end();
-
- /* check if anything is returned */
- if (!sha_ctx)
- return -EINPROGRESS;
-
- if (sha_ctx->error) {
- ret = sha_ctx->error;
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- goto done;
- }
-
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- ret = sha_finish_walk(&rctx, cstate, false);
- if (!rctx)
- return -EINPROGRESS;
-done:
- sha_complete_job(rctx, cstate, ret);
- return ret;
-}
-
-static int sha512_mb_export(struct ahash_request *areq, void *out)
-{
- struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
-
- memcpy(out, sctx, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha512_mb_import(struct ahash_request *areq, const void *in)
-{
- struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
-
- memcpy(sctx, in, sizeof(*sctx));
-
- return 0;
-}
-
-static int sha512_mb_async_init_tfm(struct crypto_tfm *tfm)
-{
- struct mcryptd_ahash *mcryptd_tfm;
- struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
- struct mcryptd_hash_ctx *mctx;
-
- mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha512-mb",
- CRYPTO_ALG_INTERNAL,
- CRYPTO_ALG_INTERNAL);
- if (IS_ERR(mcryptd_tfm))
- return PTR_ERR(mcryptd_tfm);
- mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
- mctx->alg_state = &sha512_mb_alg_state;
- ctx->mcryptd_tfm = mcryptd_tfm;
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- crypto_ahash_reqsize(&mcryptd_tfm->base));
-
- return 0;
-}
-
-static void sha512_mb_async_exit_tfm(struct crypto_tfm *tfm)
-{
- struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
- mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
-static int sha512_mb_areq_init_tfm(struct crypto_tfm *tfm)
-{
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- sizeof(struct sha512_hash_ctx));
-
- return 0;
-}
-
-static void sha512_mb_areq_exit_tfm(struct crypto_tfm *tfm)
-{
- struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
- mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
-static struct ahash_alg sha512_mb_areq_alg = {
- .init = sha512_mb_init,
- .update = sha512_mb_update,
- .final = sha512_mb_final,
- .finup = sha512_mb_finup,
- .export = sha512_mb_export,
- .import = sha512_mb_import,
- .halg = {
- .digestsize = SHA512_DIGEST_SIZE,
- .statesize = sizeof(struct sha512_hash_ctx),
- .base = {
- .cra_name = "__sha512-mb",
- .cra_driver_name = "__intel_sha512-mb",
- .cra_priority = 100,
- /*
- * use ASYNC flag as some buffers in multi-buffer
- * algo may not have completed before hashing thread
- * sleep
- */
- .cra_flags = CRYPTO_ALG_ASYNC |
- CRYPTO_ALG_INTERNAL,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT
- (sha512_mb_areq_alg.halg.base.cra_list),
- .cra_init = sha512_mb_areq_init_tfm,
- .cra_exit = sha512_mb_areq_exit_tfm,
- .cra_ctxsize = sizeof(struct sha512_hash_ctx),
- }
- }
-};
-
-static int sha512_mb_async_init(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_init(mcryptd_req);
-}
-
-static int sha512_mb_async_update(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_update(mcryptd_req);
-}
-
-static int sha512_mb_async_finup(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_finup(mcryptd_req);
-}
-
-static int sha512_mb_async_final(struct ahash_request *req)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
-
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_final(mcryptd_req);
-}
-
-static int sha512_mb_async_digest(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_digest(mcryptd_req);
-}
-
-static int sha512_mb_async_export(struct ahash_request *req, void *out)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- return crypto_ahash_export(mcryptd_req, out);
-}
-
-static int sha512_mb_async_import(struct ahash_request *req, const void *in)
-{
- struct ahash_request *mcryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
- struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
- struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
- struct mcryptd_hash_request_ctx *rctx;
- struct ahash_request *areq;
-
- memcpy(mcryptd_req, req, sizeof(*req));
- ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
- rctx = ahash_request_ctx(mcryptd_req);
-
- areq = &rctx->areq;
-
- ahash_request_set_tfm(areq, child);
- ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
- rctx->complete, req);
-
- return crypto_ahash_import(mcryptd_req, in);
-}
-
-static struct ahash_alg sha512_mb_async_alg = {
- .init = sha512_mb_async_init,
- .update = sha512_mb_async_update,
- .final = sha512_mb_async_final,
- .finup = sha512_mb_async_finup,
- .digest = sha512_mb_async_digest,
- .export = sha512_mb_async_export,
- .import = sha512_mb_async_import,
- .halg = {
- .digestsize = SHA512_DIGEST_SIZE,
- .statesize = sizeof(struct sha512_hash_ctx),
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512_mb",
- /*
- * Low priority, since with few concurrent hash requests
- * this is extremely slow due to the flush delay. Users
- * whose workloads would benefit from this can request
- * it explicitly by driver name, or can increase its
- * priority at runtime using NETLINK_CRYPTO.
- */
- .cra_priority = 50,
- .cra_flags = CRYPTO_ALG_ASYNC,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT
- (sha512_mb_async_alg.halg.base.cra_list),
- .cra_init = sha512_mb_async_init_tfm,
- .cra_exit = sha512_mb_async_exit_tfm,
- .cra_ctxsize = sizeof(struct sha512_mb_ctx),
- .cra_alignmask = 0,
- },
- },
-};
-
-static unsigned long sha512_mb_flusher(struct mcryptd_alg_cstate *cstate)
-{
- struct mcryptd_hash_request_ctx *rctx;
- unsigned long cur_time;
- unsigned long next_flush = 0;
- struct sha512_hash_ctx *sha_ctx;
-
-
- cur_time = jiffies;
-
- while (!list_empty(&cstate->work_list)) {
- rctx = list_entry(cstate->work_list.next,
- struct mcryptd_hash_request_ctx, waiter);
- if time_before(cur_time, rctx->tag.expire)
- break;
- kernel_fpu_begin();
- sha_ctx = (struct sha512_hash_ctx *)
- sha512_ctx_mgr_flush(cstate);
- kernel_fpu_end();
- if (!sha_ctx) {
- pr_err("sha512_mb error: nothing got flushed for"
- " non-empty list\n");
- break;
- }
- rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
- sha_finish_walk(&rctx, cstate, true);
- sha_complete_job(rctx, cstate, 0);
- }
-
- if (!list_empty(&cstate->work_list)) {
- rctx = list_entry(cstate->work_list.next,
- struct mcryptd_hash_request_ctx, waiter);
- /* get the hash context and then flush time */
- next_flush = rctx->tag.expire;
- mcryptd_arm_flusher(cstate, get_delay(next_flush));
- }
- return next_flush;
-}
-
-static int __init sha512_mb_mod_init(void)
-{
-
- int cpu;
- int err;
- struct mcryptd_alg_cstate *cpu_state;
-
- /* check for dependent cpu features */
- if (!boot_cpu_has(X86_FEATURE_AVX2) ||
- !boot_cpu_has(X86_FEATURE_BMI2))
- return -ENODEV;
-
- /* initialize multibuffer structures */
- sha512_mb_alg_state.alg_cstate =
- alloc_percpu(struct mcryptd_alg_cstate);
-
- sha512_job_mgr_init = sha512_mb_mgr_init_avx2;
- sha512_job_mgr_submit = sha512_mb_mgr_submit_avx2;
- sha512_job_mgr_flush = sha512_mb_mgr_flush_avx2;
- sha512_job_mgr_get_comp_job = sha512_mb_mgr_get_comp_job_avx2;
-
- if (!sha512_mb_alg_state.alg_cstate)
- return -ENOMEM;
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
- cpu_state->next_flush = 0;
- cpu_state->next_seq_num = 0;
- cpu_state->flusher_engaged = false;
- INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
- cpu_state->cpu = cpu;
- cpu_state->alg_state = &sha512_mb_alg_state;
- cpu_state->mgr = kzalloc(sizeof(struct sha512_ctx_mgr),
- GFP_KERNEL);
- if (!cpu_state->mgr)
- goto err2;
- sha512_ctx_mgr_init(cpu_state->mgr);
- INIT_LIST_HEAD(&cpu_state->work_list);
- spin_lock_init(&cpu_state->work_lock);
- }
- sha512_mb_alg_state.flusher = &sha512_mb_flusher;
-
- err = crypto_register_ahash(&sha512_mb_areq_alg);
- if (err)
- goto err2;
- err = crypto_register_ahash(&sha512_mb_async_alg);
- if (err)
- goto err1;
-
-
- return 0;
-err1:
- crypto_unregister_ahash(&sha512_mb_areq_alg);
-err2:
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
- kfree(cpu_state->mgr);
- }
- free_percpu(sha512_mb_alg_state.alg_cstate);
- return -ENODEV;
-}
-
-static void __exit sha512_mb_mod_fini(void)
-{
- int cpu;
- struct mcryptd_alg_cstate *cpu_state;
-
- crypto_unregister_ahash(&sha512_mb_async_alg);
- crypto_unregister_ahash(&sha512_mb_areq_alg);
- for_each_possible_cpu(cpu) {
- cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
- kfree(cpu_state->mgr);
- }
- free_percpu(sha512_mb_alg_state.alg_cstate);
-}
-
-module_init(sha512_mb_mod_init);
-module_exit(sha512_mb_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, multi buffer accelerated");
-
-MODULE_ALIAS("sha512");
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
deleted file mode 100644
index e5c465bd821e..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- * Header file for multi buffer SHA512 context
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _SHA_MB_CTX_INTERNAL_H
-#define _SHA_MB_CTX_INTERNAL_H
-
-#include "sha512_mb_mgr.h"
-
-#define HASH_UPDATE 0x00
-#define HASH_LAST 0x01
-#define HASH_DONE 0x02
-#define HASH_FINAL 0x04
-
-#define HASH_CTX_STS_IDLE 0x00
-#define HASH_CTX_STS_PROCESSING 0x01
-#define HASH_CTX_STS_LAST 0x02
-#define HASH_CTX_STS_COMPLETE 0x04
-
-enum hash_ctx_error {
- HASH_CTX_ERROR_NONE = 0,
- HASH_CTX_ERROR_INVALID_FLAGS = -1,
- HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
- HASH_CTX_ERROR_ALREADY_COMPLETED = -3,
-};
-
-#define hash_ctx_user_data(ctx) ((ctx)->user_data)
-#define hash_ctx_digest(ctx) ((ctx)->job.result_digest)
-#define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
-#define hash_ctx_complete(ctx) ((ctx)->status == HASH_CTX_STS_COMPLETE)
-#define hash_ctx_status(ctx) ((ctx)->status)
-#define hash_ctx_error(ctx) ((ctx)->error)
-#define hash_ctx_init(ctx) \
- do { \
- (ctx)->error = HASH_CTX_ERROR_NONE; \
- (ctx)->status = HASH_CTX_STS_COMPLETE; \
- } while (0)
-
-/* Hash Constants and Typedefs */
-#define SHA512_DIGEST_LENGTH 8
-#define SHA512_LOG2_BLOCK_SIZE 7
-
-#define SHA512_PADLENGTHFIELD_SIZE 16
-
-#ifdef SHA_MB_DEBUG
-#define assert(expr) \
-do { \
- if (unlikely(!(expr))) { \
- printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
- #expr, __FILE__, __func__, __LINE__); \
- } \
-} while (0)
-#else
-#define assert(expr) do {} while (0)
-#endif
-
-struct sha512_ctx_mgr {
- struct sha512_mb_mgr mgr;
-};
-
-/* typedef struct sha512_ctx_mgr sha512_ctx_mgr; */
-
-struct sha512_hash_ctx {
- /* Must be at struct offset 0 */
- struct job_sha512 job;
- /* status flag */
- int status;
- /* error flag */
- int error;
-
- uint64_t total_length;
- const void *incoming_buffer;
- uint32_t incoming_buffer_length;
- uint8_t partial_block_buffer[SHA512_BLOCK_SIZE * 2];
- uint32_t partial_block_buffer_length;
- void *user_data;
-};
-
-#endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h b/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
deleted file mode 100644
index 178f17eef382..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/*
- * Header file for multi buffer SHA512 algorithm manager
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef __SHA_MB_MGR_H
-#define __SHA_MB_MGR_H
-
-#include <linux/types.h>
-
-#define NUM_SHA512_DIGEST_WORDS 8
-
-enum job_sts {STS_UNKNOWN = 0,
- STS_BEING_PROCESSED = 1,
- STS_COMPLETED = 2,
- STS_INTERNAL_ERROR = 3,
- STS_ERROR = 4
-};
-
-struct job_sha512 {
- u8 *buffer;
- u64 len;
- u64 result_digest[NUM_SHA512_DIGEST_WORDS] __aligned(32);
- enum job_sts status;
- void *user_data;
-};
-
-struct sha512_args_x4 {
- uint64_t digest[8][4];
- uint8_t *data_ptr[4];
-};
-
-struct sha512_lane_data {
- struct job_sha512 *job_in_lane;
-};
-
-struct sha512_mb_mgr {
- struct sha512_args_x4 args;
-
- uint64_t lens[4];
-
- /* each byte is index (0...7) of unused lanes */
- uint64_t unused_lanes;
- /* byte 4 is set to FF as a flag */
- struct sha512_lane_data ldata[4];
-};
-
-#define SHA512_MB_MGR_NUM_LANES_AVX2 4
-
-void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state);
-struct job_sha512 *sha512_mb_mgr_submit_avx2(struct sha512_mb_mgr *state,
- struct job_sha512 *job);
-struct job_sha512 *sha512_mb_mgr_flush_avx2(struct sha512_mb_mgr *state);
-struct job_sha512 *sha512_mb_mgr_get_comp_job_avx2(struct sha512_mb_mgr *state);
-
-#endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S
deleted file mode 100644
index cf2636d4c9ba..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Header file for multi buffer SHA256 algorithm data structure
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-# Macros for defining data structures
-
-# Usage example
-
-#START_FIELDS # JOB_AES
-### name size align
-#FIELD _plaintext, 8, 8 # pointer to plaintext
-#FIELD _ciphertext, 8, 8 # pointer to ciphertext
-#FIELD _IV, 16, 8 # IV
-#FIELD _keys, 8, 8 # pointer to keys
-#FIELD _len, 4, 4 # length in bytes
-#FIELD _status, 4, 4 # status enumeration
-#FIELD _user_data, 8, 8 # pointer to user data
-#UNION _union, size1, align1, \
-# size2, align2, \
-# size3, align3, \
-# ...
-#END_FIELDS
-#%assign _JOB_AES_size _FIELD_OFFSET
-#%assign _JOB_AES_align _STRUCT_ALIGN
-
-#########################################################################
-
-# Alternate "struc-like" syntax:
-# STRUCT job_aes2
-# RES_Q .plaintext, 1
-# RES_Q .ciphertext, 1
-# RES_DQ .IV, 1
-# RES_B .nested, _JOB_AES_SIZE, _JOB_AES_ALIGN
-# RES_U .union, size1, align1, \
-# size2, align2, \
-# ...
-# ENDSTRUCT
-# # Following only needed if nesting
-# %assign job_aes2_size _FIELD_OFFSET
-# %assign job_aes2_align _STRUCT_ALIGN
-#
-# RES_* macros take a name, a count and an optional alignment.
-# The count in in terms of the base size of the macro, and the
-# default alignment is the base size.
-# The macros are:
-# Macro Base size
-# RES_B 1
-# RES_W 2
-# RES_D 4
-# RES_Q 8
-# RES_DQ 16
-# RES_Y 32
-# RES_Z 64
-#
-# RES_U defines a union. It's arguments are a name and two or more
-# pairs of "size, alignment"
-#
-# The two assigns are only needed if this structure is being nested
-# within another. Even if the assigns are not done, one can still use
-# STRUCT_NAME_size as the size of the structure.
-#
-# Note that for nesting, you still need to assign to STRUCT_NAME_size.
-#
-# The differences between this and using "struc" directly are that each
-# type is implicitly aligned to its natural length (although this can be
-# over-ridden with an explicit third parameter), and that the structure
-# is padded at the end to its overall alignment.
-#
-
-#########################################################################
-
-#ifndef _DATASTRUCT_ASM_
-#define _DATASTRUCT_ASM_
-
-#define PTR_SZ 8
-#define SHA512_DIGEST_WORD_SIZE 8
-#define SHA512_MB_MGR_NUM_LANES_AVX2 4
-#define NUM_SHA512_DIGEST_WORDS 8
-#define SZ4 4*SHA512_DIGEST_WORD_SIZE
-#define ROUNDS 80*SZ4
-#define SHA512_DIGEST_ROW_SIZE (SHA512_MB_MGR_NUM_LANES_AVX2 * 8)
-
-# START_FIELDS
-.macro START_FIELDS
- _FIELD_OFFSET = 0
- _STRUCT_ALIGN = 0
-.endm
-
-# FIELD name size align
-.macro FIELD name size align
- _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
- \name = _FIELD_OFFSET
- _FIELD_OFFSET = _FIELD_OFFSET + (\size)
-.if (\align > _STRUCT_ALIGN)
- _STRUCT_ALIGN = \align
-.endif
-.endm
-
-# END_FIELDS
-.macro END_FIELDS
- _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
-.endm
-
-.macro STRUCT p1
-START_FIELDS
-.struc \p1
-.endm
-
-.macro ENDSTRUCT
- tmp = _FIELD_OFFSET
- END_FIELDS
- tmp = (_FIELD_OFFSET - ##tmp)
-.if (tmp > 0)
- .lcomm tmp
-.endm
-
-## RES_int name size align
-.macro RES_int p1 p2 p3
- name = \p1
- size = \p2
- align = .\p3
-
- _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
-.align align
-.lcomm name size
- _FIELD_OFFSET = _FIELD_OFFSET + (size)
-.if (align > _STRUCT_ALIGN)
- _STRUCT_ALIGN = align
-.endif
-.endm
-
-# macro RES_B name, size [, align]
-.macro RES_B _name, _size, _align=1
-RES_int _name _size _align
-.endm
-
-# macro RES_W name, size [, align]
-.macro RES_W _name, _size, _align=2
-RES_int _name 2*(_size) _align
-.endm
-
-# macro RES_D name, size [, align]
-.macro RES_D _name, _size, _align=4
-RES_int _name 4*(_size) _align
-.endm
-
-# macro RES_Q name, size [, align]
-.macro RES_Q _name, _size, _align=8
-RES_int _name 8*(_size) _align
-.endm
-
-# macro RES_DQ name, size [, align]
-.macro RES_DQ _name, _size, _align=16
-RES_int _name 16*(_size) _align
-.endm
-
-# macro RES_Y name, size [, align]
-.macro RES_Y _name, _size, _align=32
-RES_int _name 32*(_size) _align
-.endm
-
-# macro RES_Z name, size [, align]
-.macro RES_Z _name, _size, _align=64
-RES_int _name 64*(_size) _align
-.endm
-
-#endif
-
-###################################################################
-### Define SHA512 Out Of Order Data Structures
-###################################################################
-
-START_FIELDS # LANE_DATA
-### name size align
-FIELD _job_in_lane, 8, 8 # pointer to job object
-END_FIELDS
-
- _LANE_DATA_size = _FIELD_OFFSET
- _LANE_DATA_align = _STRUCT_ALIGN
-
-####################################################################
-
-START_FIELDS # SHA512_ARGS_X4
-### name size align
-FIELD _digest, 8*8*4, 4 # transposed digest
-FIELD _data_ptr, 8*4, 8 # array of pointers to data
-END_FIELDS
-
- _SHA512_ARGS_X4_size = _FIELD_OFFSET
- _SHA512_ARGS_X4_align = _STRUCT_ALIGN
-
-#####################################################################
-
-START_FIELDS # MB_MGR
-### name size align
-FIELD _args, _SHA512_ARGS_X4_size, _SHA512_ARGS_X4_align
-FIELD _lens, 8*4, 8
-FIELD _unused_lanes, 8, 8
-FIELD _ldata, _LANE_DATA_size*4, _LANE_DATA_align
-END_FIELDS
-
- _MB_MGR_size = _FIELD_OFFSET
- _MB_MGR_align = _STRUCT_ALIGN
-
-_args_digest = _args + _digest
-_args_data_ptr = _args + _data_ptr
-
-#######################################################################
-
-#######################################################################
-#### Define constants
-#######################################################################
-
-#define STS_UNKNOWN 0
-#define STS_BEING_PROCESSED 1
-#define STS_COMPLETED 2
-
-#######################################################################
-#### Define JOB_SHA512 structure
-#######################################################################
-
-START_FIELDS # JOB_SHA512
-### name size align
-FIELD _buffer, 8, 8 # pointer to buffer
-FIELD _len, 8, 8 # length in bytes
-FIELD _result_digest, 8*8, 32 # Digest (output)
-FIELD _status, 4, 4
-FIELD _user_data, 8, 8
-END_FIELDS
-
- _JOB_SHA512_size = _FIELD_OFFSET
- _JOB_SHA512_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S
deleted file mode 100644
index 7c629caebc05..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S
+++ /dev/null
@@ -1,297 +0,0 @@
-/*
- * Flush routine for SHA512 multibuffer
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/linkage.h>
-#include <asm/frame.h>
-#include "sha512_mb_mgr_datastruct.S"
-
-.extern sha512_x4_avx2
-
-# LINUX register definitions
-#define arg1 %rdi
-#define arg2 %rsi
-
-# idx needs to be other than arg1, arg2, rbx, r12
-#define idx %rdx
-
-# Common definitions
-#define state arg1
-#define job arg2
-#define len2 arg2
-
-#define unused_lanes %rbx
-#define lane_data %rbx
-#define tmp2 %rbx
-
-#define job_rax %rax
-#define tmp1 %rax
-#define size_offset %rax
-#define tmp %rax
-#define start_offset %rax
-
-#define tmp3 arg1
-
-#define extra_blocks arg2
-#define p arg2
-
-#define tmp4 %r8
-#define lens0 %r8
-
-#define lens1 %r9
-#define lens2 %r10
-#define lens3 %r11
-
-.macro LABEL prefix n
-\prefix\n\():
-.endm
-
-.macro JNE_SKIP i
-jne skip_\i
-.endm
-
-.altmacro
-.macro SET_OFFSET _offset
-offset = \_offset
-.endm
-.noaltmacro
-
-# JOB* sha512_mb_mgr_flush_avx2(MB_MGR *state)
-# arg 1 : rcx : state
-ENTRY(sha512_mb_mgr_flush_avx2)
- FRAME_BEGIN
- push %rbx
-
- # If bit (32+3) is set, then all lanes are empty
- mov _unused_lanes(state), unused_lanes
- bt $32+7, unused_lanes
- jc return_null
-
- # find a lane with a non-null job
- xor idx, idx
- offset = (_ldata + 1*_LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne one(%rip), idx
- offset = (_ldata + 2*_LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne two(%rip), idx
- offset = (_ldata + 3*_LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
- cmovne three(%rip), idx
-
- # copy idx to empty lanes
-copy_lane_data:
- offset = (_args + _data_ptr)
- mov offset(state,idx,8), tmp
-
- I = 0
-.rep 4
- offset = (_ldata + I * _LANE_DATA_size + _job_in_lane)
- cmpq $0, offset(state)
-.altmacro
- JNE_SKIP %I
- offset = (_args + _data_ptr + 8*I)
- mov tmp, offset(state)
- offset = (_lens + 8*I +4)
- movl $0xFFFFFFFF, offset(state)
-LABEL skip_ %I
- I = (I+1)
-.noaltmacro
-.endr
-
- # Find min length
- mov _lens + 0*8(state),lens0
- mov lens0,idx
- mov _lens + 1*8(state),lens1
- cmp idx,lens1
- cmovb lens1,idx
- mov _lens + 2*8(state),lens2
- cmp idx,lens2
- cmovb lens2,idx
- mov _lens + 3*8(state),lens3
- cmp idx,lens3
- cmovb lens3,idx
- mov idx,len2
- and $0xF,idx
- and $~0xFF,len2
- jz len_is_0
-
- sub len2, lens0
- sub len2, lens1
- sub len2, lens2
- sub len2, lens3
- shr $32,len2
- mov lens0, _lens + 0*8(state)
- mov lens1, _lens + 1*8(state)
- mov lens2, _lens + 2*8(state)
- mov lens3, _lens + 3*8(state)
-
- # "state" and "args" are the same address, arg1
- # len is arg2
- call sha512_x4_avx2
- # state and idx are intact
-
-len_is_0:
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- mov _unused_lanes(state), unused_lanes
- shl $8, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens+4(state, idx, 8)
-
- vmovq _args_digest+0*32(state, idx, 8), %xmm0
- vpinsrq $1, _args_digest+1*32(state, idx, 8), %xmm0, %xmm0
- vmovq _args_digest+2*32(state, idx, 8), %xmm1
- vpinsrq $1, _args_digest+3*32(state, idx, 8), %xmm1, %xmm1
- vmovq _args_digest+4*32(state, idx, 8), %xmm2
- vpinsrq $1, _args_digest+5*32(state, idx, 8), %xmm2, %xmm2
- vmovq _args_digest+6*32(state, idx, 8), %xmm3
- vpinsrq $1, _args_digest+7*32(state, idx, 8), %xmm3, %xmm3
-
- vmovdqu %xmm0, _result_digest(job_rax)
- vmovdqu %xmm1, _result_digest+1*16(job_rax)
- vmovdqu %xmm2, _result_digest+2*16(job_rax)
- vmovdqu %xmm3, _result_digest+3*16(job_rax)
-
-return:
- pop %rbx
- FRAME_END
- ret
-
-return_null:
- xor job_rax, job_rax
- jmp return
-ENDPROC(sha512_mb_mgr_flush_avx2)
-.align 16
-
-ENTRY(sha512_mb_mgr_get_comp_job_avx2)
- push %rbx
-
- mov _unused_lanes(state), unused_lanes
- bt $(32+7), unused_lanes
- jc .return_null
-
- # Find min length
- mov _lens(state),lens0
- mov lens0,idx
- mov _lens+1*8(state),lens1
- cmp idx,lens1
- cmovb lens1,idx
- mov _lens+2*8(state),lens2
- cmp idx,lens2
- cmovb lens2,idx
- mov _lens+3*8(state),lens3
- cmp idx,lens3
- cmovb lens3,idx
- test $~0xF,idx
- jnz .return_null
- and $0xF,idx
-
- #process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- mov _unused_lanes(state), unused_lanes
- shl $8, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF, _lens+4(state, idx, 8)
-
- vmovq _args_digest(state, idx, 8), %xmm0
- vpinsrq $1, _args_digest+1*32(state, idx, 8), %xmm0, %xmm0
- vmovq _args_digest+2*32(state, idx, 8), %xmm1
- vpinsrq $1, _args_digest+3*32(state, idx, 8), %xmm1, %xmm1
- vmovq _args_digest+4*32(state, idx, 8), %xmm2
- vpinsrq $1, _args_digest+5*32(state, idx, 8), %xmm2, %xmm2
- vmovq _args_digest+6*32(state, idx, 8), %xmm3
- vpinsrq $1, _args_digest+7*32(state, idx, 8), %xmm3, %xmm3
-
- vmovdqu %xmm0, _result_digest+0*16(job_rax)
- vmovdqu %xmm1, _result_digest+1*16(job_rax)
- vmovdqu %xmm2, _result_digest+2*16(job_rax)
- vmovdqu %xmm3, _result_digest+3*16(job_rax)
-
- pop %rbx
-
- ret
-
-.return_null:
- xor job_rax, job_rax
- pop %rbx
- ret
-ENDPROC(sha512_mb_mgr_get_comp_job_avx2)
-
-.section .rodata.cst8.one, "aM", @progbits, 8
-.align 8
-one:
-.quad 1
-
-.section .rodata.cst8.two, "aM", @progbits, 8
-.align 8
-two:
-.quad 2
-
-.section .rodata.cst8.three, "aM", @progbits, 8
-.align 8
-three:
-.quad 3
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
deleted file mode 100644
index d08805032f01..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * Initialization code for multi buffer SHA256 algorithm for AVX2
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "sha512_mb_mgr.h"
-
-void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state)
-{
- unsigned int j;
-
- /* initially all lanes are unused */
- state->lens[0] = 0xFFFFFFFF00000000;
- state->lens[1] = 0xFFFFFFFF00000001;
- state->lens[2] = 0xFFFFFFFF00000002;
- state->lens[3] = 0xFFFFFFFF00000003;
-
- state->unused_lanes = 0xFF03020100;
- for (j = 0; j < 4; j++)
- state->ldata[j].job_in_lane = NULL;
-}
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S
deleted file mode 100644
index 4ba709ba78e5..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- * Buffer submit code for multi buffer SHA512 algorithm
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/linkage.h>
-#include <asm/frame.h>
-#include "sha512_mb_mgr_datastruct.S"
-
-.extern sha512_x4_avx2
-
-#define arg1 %rdi
-#define arg2 %rsi
-
-#define idx %rdx
-#define last_len %rdx
-
-#define size_offset %rcx
-#define tmp2 %rcx
-
-# Common definitions
-#define state arg1
-#define job arg2
-#define len2 arg2
-#define p2 arg2
-
-#define p %r11
-#define start_offset %r11
-
-#define unused_lanes %rbx
-
-#define job_rax %rax
-#define len %rax
-
-#define lane %r12
-#define tmp3 %r12
-#define lens3 %r12
-
-#define extra_blocks %r8
-#define lens0 %r8
-
-#define tmp %r9
-#define lens1 %r9
-
-#define lane_data %r10
-#define lens2 %r10
-
-#define DWORD_len %eax
-
-# JOB* sha512_mb_mgr_submit_avx2(MB_MGR *state, JOB *job)
-# arg 1 : rcx : state
-# arg 2 : rdx : job
-ENTRY(sha512_mb_mgr_submit_avx2)
- FRAME_BEGIN
- push %rbx
- push %r12
-
- mov _unused_lanes(state), unused_lanes
- movzb %bl,lane
- shr $8, unused_lanes
- imul $_LANE_DATA_size, lane,lane_data
- movl $STS_BEING_PROCESSED, _status(job)
- lea _ldata(state, lane_data), lane_data
- mov unused_lanes, _unused_lanes(state)
- movl _len(job), DWORD_len
-
- mov job, _job_in_lane(lane_data)
- movl DWORD_len,_lens+4(state , lane, 8)
-
- # Load digest words from result_digest
- vmovdqu _result_digest+0*16(job), %xmm0
- vmovdqu _result_digest+1*16(job), %xmm1
- vmovdqu _result_digest+2*16(job), %xmm2
- vmovdqu _result_digest+3*16(job), %xmm3
-
- vmovq %xmm0, _args_digest(state, lane, 8)
- vpextrq $1, %xmm0, _args_digest+1*32(state , lane, 8)
- vmovq %xmm1, _args_digest+2*32(state , lane, 8)
- vpextrq $1, %xmm1, _args_digest+3*32(state , lane, 8)
- vmovq %xmm2, _args_digest+4*32(state , lane, 8)
- vpextrq $1, %xmm2, _args_digest+5*32(state , lane, 8)
- vmovq %xmm3, _args_digest+6*32(state , lane, 8)
- vpextrq $1, %xmm3, _args_digest+7*32(state , lane, 8)
-
- mov _buffer(job), p
- mov p, _args_data_ptr(state, lane, 8)
-
- cmp $0xFF, unused_lanes
- jne return_null
-
-start_loop:
-
- # Find min length
- mov _lens+0*8(state),lens0
- mov lens0,idx
- mov _lens+1*8(state),lens1
- cmp idx,lens1
- cmovb lens1, idx
- mov _lens+2*8(state),lens2
- cmp idx,lens2
- cmovb lens2,idx
- mov _lens+3*8(state),lens3
- cmp idx,lens3
- cmovb lens3,idx
- mov idx,len2
- and $0xF,idx
- and $~0xFF,len2
- jz len_is_0
-
- sub len2,lens0
- sub len2,lens1
- sub len2,lens2
- sub len2,lens3
- shr $32,len2
- mov lens0, _lens + 0*8(state)
- mov lens1, _lens + 1*8(state)
- mov lens2, _lens + 2*8(state)
- mov lens3, _lens + 3*8(state)
-
- # "state" and "args" are the same address, arg1
- # len is arg2
- call sha512_x4_avx2
- # state and idx are intact
-
-len_is_0:
-
- # process completed job "idx"
- imul $_LANE_DATA_size, idx, lane_data
- lea _ldata(state, lane_data), lane_data
-
- mov _job_in_lane(lane_data), job_rax
- mov _unused_lanes(state), unused_lanes
- movq $0, _job_in_lane(lane_data)
- movl $STS_COMPLETED, _status(job_rax)
- shl $8, unused_lanes
- or idx, unused_lanes
- mov unused_lanes, _unused_lanes(state)
-
- movl $0xFFFFFFFF,_lens+4(state,idx,8)
- vmovq _args_digest+0*32(state , idx, 8), %xmm0
- vpinsrq $1, _args_digest+1*32(state , idx, 8), %xmm0, %xmm0
- vmovq _args_digest+2*32(state , idx, 8), %xmm1
- vpinsrq $1, _args_digest+3*32(state , idx, 8), %xmm1, %xmm1
- vmovq _args_digest+4*32(state , idx, 8), %xmm2
- vpinsrq $1, _args_digest+5*32(state , idx, 8), %xmm2, %xmm2
- vmovq _args_digest+6*32(state , idx, 8), %xmm3
- vpinsrq $1, _args_digest+7*32(state , idx, 8), %xmm3, %xmm3
-
- vmovdqu %xmm0, _result_digest + 0*16(job_rax)
- vmovdqu %xmm1, _result_digest + 1*16(job_rax)
- vmovdqu %xmm2, _result_digest + 2*16(job_rax)
- vmovdqu %xmm3, _result_digest + 3*16(job_rax)
-
-return:
- pop %r12
- pop %rbx
- FRAME_END
- ret
-
-return_null:
- xor job_rax, job_rax
- jmp return
-ENDPROC(sha512_mb_mgr_submit_avx2)
-
-/* UNUSED?
-.section .rodata.cst16, "aM", @progbits, 16
-.align 16
-H0: .int 0x6a09e667
-H1: .int 0xbb67ae85
-H2: .int 0x3c6ef372
-H3: .int 0xa54ff53a
-H4: .int 0x510e527f
-H5: .int 0x9b05688c
-H6: .int 0x1f83d9ab
-H7: .int 0x5be0cd19
-*/
diff --git a/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S
deleted file mode 100644
index e22e907643a6..000000000000
--- a/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S
+++ /dev/null
@@ -1,531 +0,0 @@
-/*
- * Multi-buffer SHA512 algorithm hash compute routine
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Megha Dey <megha.dey@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-# code to compute quad SHA512 using AVX2
-# use YMMs to tackle the larger digest size
-# outer calling routine takes care of save and restore of XMM registers
-# Logic designed/laid out by JDG
-
-# Function clobbers: rax, rcx, rdx, rbx, rsi, rdi, r9-r15; ymm0-15
-# Stack must be aligned to 32 bytes before call
-# Linux clobbers: rax rbx rcx rsi r8 r9 r10 r11 r12
-# Linux preserves: rcx rdx rdi rbp r13 r14 r15
-# clobbers ymm0-15
-
-#include <linux/linkage.h>
-#include "sha512_mb_mgr_datastruct.S"
-
-arg1 = %rdi
-arg2 = %rsi
-
-# Common definitions
-STATE = arg1
-INP_SIZE = arg2
-
-IDX = %rax
-ROUND = %rbx
-TBL = %r8
-
-inp0 = %r9
-inp1 = %r10
-inp2 = %r11
-inp3 = %r12
-
-a = %ymm0
-b = %ymm1
-c = %ymm2
-d = %ymm3
-e = %ymm4
-f = %ymm5
-g = %ymm6
-h = %ymm7
-
-a0 = %ymm8
-a1 = %ymm9
-a2 = %ymm10
-
-TT0 = %ymm14
-TT1 = %ymm13
-TT2 = %ymm12
-TT3 = %ymm11
-TT4 = %ymm10
-TT5 = %ymm9
-
-T1 = %ymm14
-TMP = %ymm15
-
-# Define stack usage
-STACK_SPACE1 = SZ4*16 + NUM_SHA512_DIGEST_WORDS*SZ4 + 24
-
-#define VMOVPD vmovupd
-_digest = SZ4*16
-
-# transpose r0, r1, r2, r3, t0, t1
-# "transpose" data in {r0..r3} using temps {t0..t3}
-# Input looks like: {r0 r1 r2 r3}
-# r0 = {a7 a6 a5 a4 a3 a2 a1 a0}
-# r1 = {b7 b6 b5 b4 b3 b2 b1 b0}
-# r2 = {c7 c6 c5 c4 c3 c2 c1 c0}
-# r3 = {d7 d6 d5 d4 d3 d2 d1 d0}
-#
-# output looks like: {t0 r1 r0 r3}
-# t0 = {d1 d0 c1 c0 b1 b0 a1 a0}
-# r1 = {d3 d2 c3 c2 b3 b2 a3 a2}
-# r0 = {d5 d4 c5 c4 b5 b4 a5 a4}
-# r3 = {d7 d6 c7 c6 b7 b6 a7 a6}
-
-.macro TRANSPOSE r0 r1 r2 r3 t0 t1
- vshufps $0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4 b1 b0 a1 a0}
- vshufps $0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6 b3 b2 a3 a2}
- vshufps $0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4 d1 d0 c1 c0}
- vshufps $0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6 d3 d2 c3 c2}
-
- vperm2f128 $0x20, \r2, \r0, \r1 # h6...a6
- vperm2f128 $0x31, \r2, \r0, \r3 # h2...a2
- vperm2f128 $0x31, \t1, \t0, \r0 # h5...a5
- vperm2f128 $0x20, \t1, \t0, \t0 # h1...a1
-.endm
-
-.macro ROTATE_ARGS
-TMP_ = h
-h = g
-g = f
-f = e
-e = d
-d = c
-c = b
-b = a
-a = TMP_
-.endm
-
-# PRORQ reg, imm, tmp
-# packed-rotate-right-double
-# does a rotate by doing two shifts and an or
-.macro _PRORQ reg imm tmp
- vpsllq $(64-\imm),\reg,\tmp
- vpsrlq $\imm,\reg, \reg
- vpor \tmp,\reg, \reg
-.endm
-
-# non-destructive
-# PRORQ_nd reg, imm, tmp, src
-.macro _PRORQ_nd reg imm tmp src
- vpsllq $(64-\imm), \src, \tmp
- vpsrlq $\imm, \src, \reg
- vpor \tmp, \reg, \reg
-.endm
-
-# PRORQ dst/src, amt
-.macro PRORQ reg imm
- _PRORQ \reg, \imm, TMP
-.endm
-
-# PRORQ_nd dst, src, amt
-.macro PRORQ_nd reg tmp imm
- _PRORQ_nd \reg, \imm, TMP, \tmp
-.endm
-
-#; arguments passed implicitly in preprocessor symbols i, a...h
-.macro ROUND_00_15 _T1 i
- PRORQ_nd a0, e, (18-14) # sig1: a0 = (e >> 4)
-
- vpxor g, f, a2 # ch: a2 = f^g
- vpand e,a2, a2 # ch: a2 = (f^g)&e
- vpxor g, a2, a2 # a2 = ch
-
- PRORQ_nd a1,e,41 # sig1: a1 = (e >> 25)
-
- offset = SZ4*(\i & 0xf)
- vmovdqu \_T1,offset(%rsp)
- vpaddq (TBL,ROUND,1), \_T1, \_T1 # T1 = W + K
- vpxor e,a0, a0 # sig1: a0 = e ^ (e >> 5)
- PRORQ a0, 14 # sig1: a0 = (e >> 6) ^ (e >> 11)
- vpaddq a2, h, h # h = h + ch
- PRORQ_nd a2,a,6 # sig0: a2 = (a >> 11)
- vpaddq \_T1,h, h # h = h + ch + W + K
- vpxor a1, a0, a0 # a0 = sigma1
- vmovdqu a,\_T1
- PRORQ_nd a1,a,39 # sig0: a1 = (a >> 22)
- vpxor c, \_T1, \_T1 # maj: T1 = a^c
- add $SZ4, ROUND # ROUND++
- vpand b, \_T1, \_T1 # maj: T1 = (a^c)&b
- vpaddq a0, h, h
- vpaddq h, d, d
- vpxor a, a2, a2 # sig0: a2 = a ^ (a >> 11)
- PRORQ a2,28 # sig0: a2 = (a >> 2) ^ (a >> 13)
- vpxor a1, a2, a2 # a2 = sig0
- vpand c, a, a1 # maj: a1 = a&c
- vpor \_T1, a1, a1 # a1 = maj
- vpaddq a1, h, h # h = h + ch + W + K + maj
- vpaddq a2, h, h # h = h + ch + W + K + maj + sigma0
- ROTATE_ARGS
-.endm
-
-
-#; arguments passed implicitly in preprocessor symbols i, a...h
-.macro ROUND_16_XX _T1 i
- vmovdqu SZ4*((\i-15)&0xf)(%rsp), \_T1
- vmovdqu SZ4*((\i-2)&0xf)(%rsp), a1
- vmovdqu \_T1, a0
- PRORQ \_T1,7
- vmovdqu a1, a2
- PRORQ a1,42
- vpxor a0, \_T1, \_T1
- PRORQ \_T1, 1
- vpxor a2, a1, a1
- PRORQ a1, 19
- vpsrlq $7, a0, a0
- vpxor a0, \_T1, \_T1
- vpsrlq $6, a2, a2
- vpxor a2, a1, a1
- vpaddq SZ4*((\i-16)&0xf)(%rsp), \_T1, \_T1
- vpaddq SZ4*((\i-7)&0xf)(%rsp), a1, a1
- vpaddq a1, \_T1, \_T1
-
- ROUND_00_15 \_T1,\i
-.endm
-
-
-# void sha512_x4_avx2(void *STATE, const int INP_SIZE)
-# arg 1 : STATE : pointer to input data
-# arg 2 : INP_SIZE : size of data in blocks (assumed >= 1)
-ENTRY(sha512_x4_avx2)
- # general registers preserved in outer calling routine
- # outer calling routine saves all the XMM registers
- # save callee-saved clobbered registers to comply with C function ABI
- push %r12
- push %r13
- push %r14
- push %r15
-
- sub $STACK_SPACE1, %rsp
-
- # Load the pre-transposed incoming digest.
- vmovdqu 0*SHA512_DIGEST_ROW_SIZE(STATE),a
- vmovdqu 1*SHA512_DIGEST_ROW_SIZE(STATE),b
- vmovdqu 2*SHA512_DIGEST_ROW_SIZE(STATE),c
- vmovdqu 3*SHA512_DIGEST_ROW_SIZE(STATE),d
- vmovdqu 4*SHA512_DIGEST_ROW_SIZE(STATE),e
- vmovdqu 5*SHA512_DIGEST_ROW_SIZE(STATE),f
- vmovdqu 6*SHA512_DIGEST_ROW_SIZE(STATE),g
- vmovdqu 7*SHA512_DIGEST_ROW_SIZE(STATE),h
-
- lea K512_4(%rip),TBL
-
- # load the address of each of the 4 message lanes
- # getting ready to transpose input onto stack
- mov _data_ptr+0*PTR_SZ(STATE),inp0
- mov _data_ptr+1*PTR_SZ(STATE),inp1
- mov _data_ptr+2*PTR_SZ(STATE),inp2
- mov _data_ptr+3*PTR_SZ(STATE),inp3
-
- xor IDX, IDX
-lloop:
- xor ROUND, ROUND
-
- # save old digest
- vmovdqu a, _digest(%rsp)
- vmovdqu b, _digest+1*SZ4(%rsp)
- vmovdqu c, _digest+2*SZ4(%rsp)
- vmovdqu d, _digest+3*SZ4(%rsp)
- vmovdqu e, _digest+4*SZ4(%rsp)
- vmovdqu f, _digest+5*SZ4(%rsp)
- vmovdqu g, _digest+6*SZ4(%rsp)
- vmovdqu h, _digest+7*SZ4(%rsp)
- i = 0
-.rep 4
- vmovdqu PSHUFFLE_BYTE_FLIP_MASK(%rip), TMP
- VMOVPD i*32(inp0, IDX), TT2
- VMOVPD i*32(inp1, IDX), TT1
- VMOVPD i*32(inp2, IDX), TT4
- VMOVPD i*32(inp3, IDX), TT3
- TRANSPOSE TT2, TT1, TT4, TT3, TT0, TT5
- vpshufb TMP, TT0, TT0
- vpshufb TMP, TT1, TT1
- vpshufb TMP, TT2, TT2
- vpshufb TMP, TT3, TT3
- ROUND_00_15 TT0,(i*4+0)
- ROUND_00_15 TT1,(i*4+1)
- ROUND_00_15 TT2,(i*4+2)
- ROUND_00_15 TT3,(i*4+3)
- i = (i+1)
-.endr
- add $128, IDX
-
- i = (i*4)
-
- jmp Lrounds_16_xx
-.align 16
-Lrounds_16_xx:
-.rep 16
- ROUND_16_XX T1, i
- i = (i+1)
-.endr
- cmp $0xa00,ROUND
- jb Lrounds_16_xx
-
- # add old digest
- vpaddq _digest(%rsp), a, a
- vpaddq _digest+1*SZ4(%rsp), b, b
- vpaddq _digest+2*SZ4(%rsp), c, c
- vpaddq _digest+3*SZ4(%rsp), d, d
- vpaddq _digest+4*SZ4(%rsp), e, e
- vpaddq _digest+5*SZ4(%rsp), f, f
- vpaddq _digest+6*SZ4(%rsp), g, g
- vpaddq _digest+7*SZ4(%rsp), h, h
-
- sub $1, INP_SIZE # unit is blocks
- jne lloop
-
- # write back to memory (state object) the transposed digest
- vmovdqu a, 0*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu b, 1*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu c, 2*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu d, 3*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu e, 4*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu f, 5*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu g, 6*SHA512_DIGEST_ROW_SIZE(STATE)
- vmovdqu h, 7*SHA512_DIGEST_ROW_SIZE(STATE)
-
- # update input data pointers
- add IDX, inp0
- mov inp0, _data_ptr+0*PTR_SZ(STATE)
- add IDX, inp1
- mov inp1, _data_ptr+1*PTR_SZ(STATE)
- add IDX, inp2
- mov inp2, _data_ptr+2*PTR_SZ(STATE)
- add IDX, inp3
- mov inp3, _data_ptr+3*PTR_SZ(STATE)
-
- #;;;;;;;;;;;;;;;
- #; Postamble
- add $STACK_SPACE1, %rsp
- # restore callee-saved clobbered registers
-
- pop %r15
- pop %r14
- pop %r13
- pop %r12
-
- # outer calling routine restores XMM and other GP registers
- ret
-ENDPROC(sha512_x4_avx2)
-
-.section .rodata.K512_4, "a", @progbits
-.align 64
-K512_4:
- .octa 0x428a2f98d728ae22428a2f98d728ae22,\
- 0x428a2f98d728ae22428a2f98d728ae22
- .octa 0x7137449123ef65cd7137449123ef65cd,\
- 0x7137449123ef65cd7137449123ef65cd
- .octa 0xb5c0fbcfec4d3b2fb5c0fbcfec4d3b2f,\
- 0xb5c0fbcfec4d3b2fb5c0fbcfec4d3b2f
- .octa 0xe9b5dba58189dbbce9b5dba58189dbbc,\
- 0xe9b5dba58189dbbce9b5dba58189dbbc
- .octa 0x3956c25bf348b5383956c25bf348b538,\
- 0x3956c25bf348b5383956c25bf348b538
- .octa 0x59f111f1b605d01959f111f1b605d019,\
- 0x59f111f1b605d01959f111f1b605d019
- .octa 0x923f82a4af194f9b923f82a4af194f9b,\
- 0x923f82a4af194f9b923f82a4af194f9b
- .octa 0xab1c5ed5da6d8118ab1c5ed5da6d8118,\
- 0xab1c5ed5da6d8118ab1c5ed5da6d8118
- .octa 0xd807aa98a3030242d807aa98a3030242,\
- 0xd807aa98a3030242d807aa98a3030242
- .octa 0x12835b0145706fbe12835b0145706fbe,\
- 0x12835b0145706fbe12835b0145706fbe
- .octa 0x243185be4ee4b28c243185be4ee4b28c,\
- 0x243185be4ee4b28c243185be4ee4b28c
- .octa 0x550c7dc3d5ffb4e2550c7dc3d5ffb4e2,\
- 0x550c7dc3d5ffb4e2550c7dc3d5ffb4e2
- .octa 0x72be5d74f27b896f72be5d74f27b896f,\
- 0x72be5d74f27b896f72be5d74f27b896f
- .octa 0x80deb1fe3b1696b180deb1fe3b1696b1,\
- 0x80deb1fe3b1696b180deb1fe3b1696b1
- .octa 0x9bdc06a725c712359bdc06a725c71235,\
- 0x9bdc06a725c712359bdc06a725c71235
- .octa 0xc19bf174cf692694c19bf174cf692694,\
- 0xc19bf174cf692694c19bf174cf692694
- .octa 0xe49b69c19ef14ad2e49b69c19ef14ad2,\
- 0xe49b69c19ef14ad2e49b69c19ef14ad2
- .octa 0xefbe4786384f25e3efbe4786384f25e3,\
- 0xefbe4786384f25e3efbe4786384f25e3
- .octa 0x0fc19dc68b8cd5b50fc19dc68b8cd5b5,\
- 0x0fc19dc68b8cd5b50fc19dc68b8cd5b5
- .octa 0x240ca1cc77ac9c65240ca1cc77ac9c65,\
- 0x240ca1cc77ac9c65240ca1cc77ac9c65
- .octa 0x2de92c6f592b02752de92c6f592b0275,\
- 0x2de92c6f592b02752de92c6f592b0275
- .octa 0x4a7484aa6ea6e4834a7484aa6ea6e483,\
- 0x4a7484aa6ea6e4834a7484aa6ea6e483
- .octa 0x5cb0a9dcbd41fbd45cb0a9dcbd41fbd4,\
- 0x5cb0a9dcbd41fbd45cb0a9dcbd41fbd4
- .octa 0x76f988da831153b576f988da831153b5,\
- 0x76f988da831153b576f988da831153b5
- .octa 0x983e5152ee66dfab983e5152ee66dfab,\
- 0x983e5152ee66dfab983e5152ee66dfab
- .octa 0xa831c66d2db43210a831c66d2db43210,\
- 0xa831c66d2db43210a831c66d2db43210
- .octa 0xb00327c898fb213fb00327c898fb213f,\
- 0xb00327c898fb213fb00327c898fb213f
- .octa 0xbf597fc7beef0ee4bf597fc7beef0ee4,\
- 0xbf597fc7beef0ee4bf597fc7beef0ee4
- .octa 0xc6e00bf33da88fc2c6e00bf33da88fc2,\
- 0xc6e00bf33da88fc2c6e00bf33da88fc2
- .octa 0xd5a79147930aa725d5a79147930aa725,\
- 0xd5a79147930aa725d5a79147930aa725
- .octa 0x06ca6351e003826f06ca6351e003826f,\
- 0x06ca6351e003826f06ca6351e003826f
- .octa 0x142929670a0e6e70142929670a0e6e70,\
- 0x142929670a0e6e70142929670a0e6e70
- .octa 0x27b70a8546d22ffc27b70a8546d22ffc,\
- 0x27b70a8546d22ffc27b70a8546d22ffc
- .octa 0x2e1b21385c26c9262e1b21385c26c926,\
- 0x2e1b21385c26c9262e1b21385c26c926
- .octa 0x4d2c6dfc5ac42aed4d2c6dfc5ac42aed,\
- 0x4d2c6dfc5ac42aed4d2c6dfc5ac42aed
- .octa 0x53380d139d95b3df53380d139d95b3df,\
- 0x53380d139d95b3df53380d139d95b3df
- .octa 0x650a73548baf63de650a73548baf63de,\
- 0x650a73548baf63de650a73548baf63de
- .octa 0x766a0abb3c77b2a8766a0abb3c77b2a8,\
- 0x766a0abb3c77b2a8766a0abb3c77b2a8
- .octa 0x81c2c92e47edaee681c2c92e47edaee6,\
- 0x81c2c92e47edaee681c2c92e47edaee6
- .octa 0x92722c851482353b92722c851482353b,\
- 0x92722c851482353b92722c851482353b
- .octa 0xa2bfe8a14cf10364a2bfe8a14cf10364,\
- 0xa2bfe8a14cf10364a2bfe8a14cf10364
- .octa 0xa81a664bbc423001a81a664bbc423001,\
- 0xa81a664bbc423001a81a664bbc423001
- .octa 0xc24b8b70d0f89791c24b8b70d0f89791,\
- 0xc24b8b70d0f89791c24b8b70d0f89791
- .octa 0xc76c51a30654be30c76c51a30654be30,\
- 0xc76c51a30654be30c76c51a30654be30
- .octa 0xd192e819d6ef5218d192e819d6ef5218,\
- 0xd192e819d6ef5218d192e819d6ef5218
- .octa 0xd69906245565a910d69906245565a910,\
- 0xd69906245565a910d69906245565a910
- .octa 0xf40e35855771202af40e35855771202a,\
- 0xf40e35855771202af40e35855771202a
- .octa 0x106aa07032bbd1b8106aa07032bbd1b8,\
- 0x106aa07032bbd1b8106aa07032bbd1b8
- .octa 0x19a4c116b8d2d0c819a4c116b8d2d0c8,\
- 0x19a4c116b8d2d0c819a4c116b8d2d0c8
- .octa 0x1e376c085141ab531e376c085141ab53,\
- 0x1e376c085141ab531e376c085141ab53
- .octa 0x2748774cdf8eeb992748774cdf8eeb99,\
- 0x2748774cdf8eeb992748774cdf8eeb99
- .octa 0x34b0bcb5e19b48a834b0bcb5e19b48a8,\
- 0x34b0bcb5e19b48a834b0bcb5e19b48a8
- .octa 0x391c0cb3c5c95a63391c0cb3c5c95a63,\
- 0x391c0cb3c5c95a63391c0cb3c5c95a63
- .octa 0x4ed8aa4ae3418acb4ed8aa4ae3418acb,\
- 0x4ed8aa4ae3418acb4ed8aa4ae3418acb
- .octa 0x5b9cca4f7763e3735b9cca4f7763e373,\
- 0x5b9cca4f7763e3735b9cca4f7763e373
- .octa 0x682e6ff3d6b2b8a3682e6ff3d6b2b8a3,\
- 0x682e6ff3d6b2b8a3682e6ff3d6b2b8a3
- .octa 0x748f82ee5defb2fc748f82ee5defb2fc,\
- 0x748f82ee5defb2fc748f82ee5defb2fc
- .octa 0x78a5636f43172f6078a5636f43172f60,\
- 0x78a5636f43172f6078a5636f43172f60
- .octa 0x84c87814a1f0ab7284c87814a1f0ab72,\
- 0x84c87814a1f0ab7284c87814a1f0ab72
- .octa 0x8cc702081a6439ec8cc702081a6439ec,\
- 0x8cc702081a6439ec8cc702081a6439ec
- .octa 0x90befffa23631e2890befffa23631e28,\
- 0x90befffa23631e2890befffa23631e28
- .octa 0xa4506cebde82bde9a4506cebde82bde9,\
- 0xa4506cebde82bde9a4506cebde82bde9
- .octa 0xbef9a3f7b2c67915bef9a3f7b2c67915,\
- 0xbef9a3f7b2c67915bef9a3f7b2c67915
- .octa 0xc67178f2e372532bc67178f2e372532b,\
- 0xc67178f2e372532bc67178f2e372532b
- .octa 0xca273eceea26619cca273eceea26619c,\
- 0xca273eceea26619cca273eceea26619c
- .octa 0xd186b8c721c0c207d186b8c721c0c207,\
- 0xd186b8c721c0c207d186b8c721c0c207
- .octa 0xeada7dd6cde0eb1eeada7dd6cde0eb1e,\
- 0xeada7dd6cde0eb1eeada7dd6cde0eb1e
- .octa 0xf57d4f7fee6ed178f57d4f7fee6ed178,\
- 0xf57d4f7fee6ed178f57d4f7fee6ed178
- .octa 0x06f067aa72176fba06f067aa72176fba,\
- 0x06f067aa72176fba06f067aa72176fba
- .octa 0x0a637dc5a2c898a60a637dc5a2c898a6,\
- 0x0a637dc5a2c898a60a637dc5a2c898a6
- .octa 0x113f9804bef90dae113f9804bef90dae,\
- 0x113f9804bef90dae113f9804bef90dae
- .octa 0x1b710b35131c471b1b710b35131c471b,\
- 0x1b710b35131c471b1b710b35131c471b
- .octa 0x28db77f523047d8428db77f523047d84,\
- 0x28db77f523047d8428db77f523047d84
- .octa 0x32caab7b40c7249332caab7b40c72493,\
- 0x32caab7b40c7249332caab7b40c72493
- .octa 0x3c9ebe0a15c9bebc3c9ebe0a15c9bebc,\
- 0x3c9ebe0a15c9bebc3c9ebe0a15c9bebc
- .octa 0x431d67c49c100d4c431d67c49c100d4c,\
- 0x431d67c49c100d4c431d67c49c100d4c
- .octa 0x4cc5d4becb3e42b64cc5d4becb3e42b6,\
- 0x4cc5d4becb3e42b64cc5d4becb3e42b6
- .octa 0x597f299cfc657e2a597f299cfc657e2a,\
- 0x597f299cfc657e2a597f299cfc657e2a
- .octa 0x5fcb6fab3ad6faec5fcb6fab3ad6faec,\
- 0x5fcb6fab3ad6faec5fcb6fab3ad6faec
- .octa 0x6c44198c4a4758176c44198c4a475817,\
- 0x6c44198c4a4758176c44198c4a475817
-
-.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32
-.align 32
-PSHUFFLE_BYTE_FLIP_MASK: .octa 0x08090a0b0c0d0e0f0001020304050607
- .octa 0x18191a1b1c1d1e1f1011121314151617
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 352e70cd33e8..708b46a54578 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -338,7 +338,7 @@ For 32-bit we have the following conventions - kernel is built with
.macro CALL_enter_from_user_mode
#ifdef CONFIG_CONTEXT_TRACKING
#ifdef HAVE_JUMP_LABEL
- STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+ STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1
#endif
call enter_from_user_mode
.Lafter_call_\@:
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 2767c625a52c..687e47f8a796 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -389,6 +389,13 @@
* that register for the time this macro runs
*/
+ /*
+ * The high bits of the CS dword (__csh) are used for
+ * CS_FROM_ENTRY_STACK and CS_FROM_USER_CR3. Clear them in case
+ * hardware didn't do this for us.
+ */
+ andl $(0x0000ffff), PT_CS(%esp)
+
/* Are we on the entry stack? Bail out if not! */
movl PER_CPU_VAR(cpu_entry_area), %ecx
addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
@@ -407,12 +414,6 @@
/* Load top of task-stack into %edi */
movl TSS_entry2task_stack(%edi), %edi
- /*
- * Clear unused upper bits of the dword containing the word-sized CS
- * slot in pt_regs in case hardware didn't clear it for us.
- */
- andl $(0x0000ffff), PT_CS(%esp)
-
/* Special case - entry from kernel mode via entry stack */
#ifdef CONFIG_VM86
movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS
@@ -782,7 +783,7 @@ GLOBAL(__begin_SYSENTER_singlestep_region)
* will ignore all of the single-step traps generated in this range.
*/
-#ifdef CONFIG_XEN
+#ifdef CONFIG_XEN_PV
/*
* Xen doesn't set %esp to be precisely what the normal SYSENTER
* entry point expects, so fix it up before using the normal path.
@@ -1240,7 +1241,7 @@ ENTRY(spurious_interrupt_bug)
jmp common_exception
END(spurious_interrupt_bug)
-#ifdef CONFIG_XEN
+#ifdef CONFIG_XEN_PV
ENTRY(xen_hypervisor_callback)
pushl $-1 /* orig_ax = -1 => not a system call */
SAVE_ALL
@@ -1321,11 +1322,13 @@ ENTRY(xen_failsafe_callback)
_ASM_EXTABLE(3b, 8b)
_ASM_EXTABLE(4b, 9b)
ENDPROC(xen_failsafe_callback)
+#endif /* CONFIG_XEN_PV */
+#ifdef CONFIG_XEN_PVHVM
BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
xen_evtchn_do_upcall)
+#endif
-#endif /* CONFIG_XEN */
#if IS_ENABLED(CONFIG_HYPERV)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 957dfb693ecc..4d7a2d9d44cf 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -142,67 +142,6 @@ END(native_usergs_sysret64)
* with them due to bugs in both AMD and Intel CPUs.
*/
- .pushsection .entry_trampoline, "ax"
-
-/*
- * The code in here gets remapped into cpu_entry_area's trampoline. This means
- * that the assembler and linker have the wrong idea as to where this code
- * lives (and, in fact, it's mapped more than once, so it's not even at a
- * fixed address). So we can't reference any symbols outside the entry
- * trampoline and expect it to work.
- *
- * Instead, we carefully abuse %rip-relative addressing.
- * _entry_trampoline(%rip) refers to the start of the remapped) entry
- * trampoline. We can thus find cpu_entry_area with this macro:
- */
-
-#define CPU_ENTRY_AREA \
- _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
-
-/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
-#define RSP_SCRATCH CPU_ENTRY_AREA_entry_stack + \
- SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
-
-ENTRY(entry_SYSCALL_64_trampoline)
- UNWIND_HINT_EMPTY
- swapgs
-
- /* Stash the user RSP. */
- movq %rsp, RSP_SCRATCH
-
- /* Note: using %rsp as a scratch reg. */
- SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
-
- /* Load the top of the task stack into RSP */
- movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
-
- /* Start building the simulated IRET frame. */
- pushq $__USER_DS /* pt_regs->ss */
- pushq RSP_SCRATCH /* pt_regs->sp */
- pushq %r11 /* pt_regs->flags */
- pushq $__USER_CS /* pt_regs->cs */
- pushq %rcx /* pt_regs->ip */
-
- /*
- * x86 lacks a near absolute jump, and we can't jump to the real
- * entry text with a relative jump. We could push the target
- * address and then use retq, but this destroys the pipeline on
- * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead,
- * spill RDI and restore it in a second-stage trampoline.
- */
- pushq %rdi
- movq $entry_SYSCALL_64_stage2, %rdi
- JMP_NOSPEC %rdi
-END(entry_SYSCALL_64_trampoline)
-
- .popsection
-
-ENTRY(entry_SYSCALL_64_stage2)
- UNWIND_HINT_EMPTY
- popq %rdi
- jmp entry_SYSCALL_64_after_hwframe
-END(entry_SYSCALL_64_stage2)
-
ENTRY(entry_SYSCALL_64)
UNWIND_HINT_EMPTY
/*
@@ -212,21 +151,19 @@ ENTRY(entry_SYSCALL_64)
*/
swapgs
- /*
- * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it
- * is not required to switch CR3.
- */
- movq %rsp, PER_CPU_VAR(rsp_scratch)
+ /* tss.sp2 is scratch space. */
+ movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/* Construct struct pt_regs on stack */
- pushq $__USER_DS /* pt_regs->ss */
- pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
- pushq %r11 /* pt_regs->flags */
- pushq $__USER_CS /* pt_regs->cs */
- pushq %rcx /* pt_regs->ip */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
GLOBAL(entry_SYSCALL_64_after_hwframe)
- pushq %rax /* pt_regs->orig_ax */
+ pushq %rax /* pt_regs->orig_ax */
PUSH_AND_CLEAR_REGS rax=$-ENOSYS
@@ -900,6 +837,42 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
*/
#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+/**
+ * idtentry - Generate an IDT entry stub
+ * @sym: Name of the generated entry point
+ * @do_sym: C function to be called
+ * @has_error_code: True if this IDT vector has an error code on the stack
+ * @paranoid: non-zero means that this vector may be invoked from
+ * kernel mode with user GSBASE and/or user CR3.
+ * 2 is special -- see below.
+ * @shift_ist: Set to an IST index if entries from kernel mode should
+ * decrement the IST stack so that nested entries get a
+ * fresh stack. (This is for #DB, which has a nasty habit
+ * of recursing.)
+ *
+ * idtentry generates an IDT stub that sets up a usable kernel context,
+ * creates struct pt_regs, and calls @do_sym. The stub has the following
+ * special behaviors:
+ *
+ * On an entry from user mode, the stub switches from the trampoline or
+ * IST stack to the normal thread stack. On an exit to user mode, the
+ * normal exit-to-usermode path is invoked.
+ *
+ * On an exit to kernel mode, if @paranoid == 0, we check for preemption,
+ * whereas we omit the preemption check if @paranoid != 0. This is purely
+ * because the implementation is simpler this way. The kernel only needs
+ * to check for asynchronous kernel preemption when IRQ handlers return.
+ *
+ * If @paranoid == 0, then the stub will handle IRET faults by pretending
+ * that the fault came from user mode. It will handle gs_change faults by
+ * pretending that the fault happened with kernel GSBASE. Since this handling
+ * is omitted for @paranoid != 0, the #GP, #SS, and #NP stubs must have
+ * @paranoid == 0. This special handling will do the wrong thing for
+ * espfix-induced #DF on IRET, so #DF must not use @paranoid == 0.
+ *
+ * @paranoid == 2 is special: the stub will never switch stacks. This is for
+ * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
+ */
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -1050,7 +1023,7 @@ ENTRY(do_softirq_own_stack)
ret
ENDPROC(do_softirq_own_stack)
-#ifdef CONFIG_XEN
+#ifdef CONFIG_XEN_PV
idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
/*
@@ -1130,11 +1103,13 @@ ENTRY(xen_failsafe_callback)
ENCODE_FRAME_POINTER
jmp error_exit
END(xen_failsafe_callback)
+#endif /* CONFIG_XEN_PV */
+#ifdef CONFIG_XEN_PVHVM
apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
xen_hvm_callback_vector xen_evtchn_do_upcall
+#endif
-#endif /* CONFIG_XEN */
#if IS_ENABLED(CONFIG_HYPERV)
apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
@@ -1151,7 +1126,7 @@ idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
idtentry int3 do_int3 has_error_code=0
idtentry stack_segment do_stack_segment has_error_code=1
-#ifdef CONFIG_XEN
+#ifdef CONFIG_XEN_PV
idtentry xennmi do_nmi has_error_code=0
idtentry xendebug do_debug has_error_code=0
idtentry xenint3 do_int3 has_error_code=0
@@ -1187,6 +1162,16 @@ ENTRY(paranoid_entry)
xorl %ebx, %ebx
1:
+ /*
+ * Always stash CR3 in %r14. This value will be restored,
+ * verbatim, at exit. Needed if paranoid_entry interrupted
+ * another entry that already switched to the user CR3 value
+ * but has not yet returned to userspace.
+ *
+ * This is also why CS (stashed in the "iret frame" by the
+ * hardware at entry) can not be used: this may be a return
+ * to kernel code, but with a user CR3 value.
+ */
SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
ret
@@ -1211,11 +1196,13 @@ ENTRY(paranoid_exit)
testl %ebx, %ebx /* swapgs needed? */
jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
+ /* Always restore stashed CR3 value (see paranoid_entry) */
RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
SWAPGS_UNSAFE_STACK
jmp .Lparanoid_exit_restore
.Lparanoid_exit_no_swapgs:
TRACE_IRQS_IRETQ_DEBUG
+ /* Always restore stashed CR3 value (see paranoid_entry) */
RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
.Lparanoid_exit_restore:
jmp restore_regs_and_return_to_kernel
@@ -1626,6 +1613,7 @@ end_repeat_nmi:
movq $-1, %rsi
call do_nmi
+ /* Always restore stashed CR3 value (see paranoid_entry) */
RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
testl %ebx, %ebx /* swapgs needed? */
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index fa3f439f0a92..141d415a8c80 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -68,7 +68,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
$(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
-fno-omit-frame-pointer -foptimize-sibling-calls \
- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS)
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+ CFL += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
@@ -138,7 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+ KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
$(obj)/vdso32.so.dbg: FORCE \
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index f19856d95c60..007b3fe9d727 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -43,50 +43,26 @@ extern u8 hvclock_page
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
- asm("syscall" : "=a" (ret) :
- "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+ asm ("syscall" : "=a" (ret), "=m" (*ts) :
+ "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
+ "rcx", "r11");
return ret;
}
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
- long ret;
-
- asm("syscall" : "=a" (ret) :
- "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
- return ret;
-}
-
-
#else
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
- asm(
+ asm (
"mov %%ebx, %%edx \n"
- "mov %2, %%ebx \n"
+ "mov %[clock], %%ebx \n"
"call __kernel_vsyscall \n"
"mov %%edx, %%ebx \n"
- : "=a" (ret)
- : "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
- : "memory", "edx");
- return ret;
-}
-
-notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
-{
- long ret;
-
- asm(
- "mov %%ebx, %%edx \n"
- "mov %2, %%ebx \n"
- "call __kernel_vsyscall \n"
- "mov %%edx, %%ebx \n"
- : "=a" (ret)
- : "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
- : "memory", "edx");
+ : "=a" (ret), "=m" (*ts)
+ : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
+ : "edx");
return ret;
}
@@ -98,12 +74,11 @@ static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
}
-static notrace u64 vread_pvclock(int *mode)
+static notrace u64 vread_pvclock(void)
{
const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
- u64 ret;
- u64 last;
u32 version;
+ u64 ret;
/*
* Note: The kernel and hypervisor must guarantee that cpu ID
@@ -130,175 +105,112 @@ static notrace u64 vread_pvclock(int *mode)
do {
version = pvclock_read_begin(pvti);
- if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
- *mode = VCLOCK_NONE;
- return 0;
- }
+ if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
+ return U64_MAX;
ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
} while (pvclock_read_retry(pvti, version));
- /* refer to vread_tsc() comment for rationale */
- last = gtod->cycle_last;
-
- if (likely(ret >= last))
- return ret;
-
- return last;
+ return ret;
}
#endif
#ifdef CONFIG_HYPERV_TSCPAGE
-static notrace u64 vread_hvclock(int *mode)
+static notrace u64 vread_hvclock(void)
{
const struct ms_hyperv_tsc_page *tsc_pg =
(const struct ms_hyperv_tsc_page *)&hvclock_page;
- u64 current_tick = hv_read_tsc_page(tsc_pg);
-
- if (current_tick != U64_MAX)
- return current_tick;
- *mode = VCLOCK_NONE;
- return 0;
+ return hv_read_tsc_page(tsc_pg);
}
#endif
-notrace static u64 vread_tsc(void)
-{
- u64 ret = (u64)rdtsc_ordered();
- u64 last = gtod->cycle_last;
-
- if (likely(ret >= last))
- return ret;
-
- /*
- * GCC likes to generate cmov here, but this branch is extremely
- * predictable (it's just a function of time and the likely is
- * very likely) and there's a data dependence, so force GCC
- * to generate a branch instead. I don't barrier() because
- * we don't actually need a barrier, and if this function
- * ever gets inlined it will generate worse code.
- */
- asm volatile ("");
- return last;
-}
-
-notrace static inline u64 vgetsns(int *mode)
+notrace static inline u64 vgetcyc(int mode)
{
- u64 v;
- cycles_t cycles;
-
- if (gtod->vclock_mode == VCLOCK_TSC)
- cycles = vread_tsc();
+ if (mode == VCLOCK_TSC)
+ return (u64)rdtsc_ordered();
#ifdef CONFIG_PARAVIRT_CLOCK
- else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
- cycles = vread_pvclock(mode);
+ else if (mode == VCLOCK_PVCLOCK)
+ return vread_pvclock();
#endif
#ifdef CONFIG_HYPERV_TSCPAGE
- else if (gtod->vclock_mode == VCLOCK_HVCLOCK)
- cycles = vread_hvclock(mode);
+ else if (mode == VCLOCK_HVCLOCK)
+ return vread_hvclock();
#endif
- else
- return 0;
- v = (cycles - gtod->cycle_last) & gtod->mask;
- return v * gtod->mult;
+ return U64_MAX;
}
-/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
-notrace static int __always_inline do_realtime(struct timespec *ts)
+notrace static int do_hres(clockid_t clk, struct timespec *ts)
{
- unsigned long seq;
- u64 ns;
- int mode;
+ struct vgtod_ts *base = &gtod->basetime[clk];
+ u64 cycles, last, sec, ns;
+ unsigned int seq;
do {
seq = gtod_read_begin(gtod);
- mode = gtod->vclock_mode;
- ts->tv_sec = gtod->wall_time_sec;
- ns = gtod->wall_time_snsec;
- ns += vgetsns(&mode);
+ cycles = vgetcyc(gtod->vclock_mode);
+ ns = base->nsec;
+ last = gtod->cycle_last;
+ if (unlikely((s64)cycles < 0))
+ return vdso_fallback_gettime(clk, ts);
+ if (cycles > last)
+ ns += (cycles - last) * gtod->mult;
ns >>= gtod->shift;
+ sec = base->sec;
} while (unlikely(gtod_read_retry(gtod, seq)));
- ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ /*
+ * Do this outside the loop: a race inside the loop could result
+ * in __iter_div_u64_rem() being extremely slow.
+ */
+ ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
ts->tv_nsec = ns;
- return mode;
+ return 0;
}
-notrace static int __always_inline do_monotonic(struct timespec *ts)
+notrace static void do_coarse(clockid_t clk, struct timespec *ts)
{
- unsigned long seq;
- u64 ns;
- int mode;
+ struct vgtod_ts *base = &gtod->basetime[clk];
+ unsigned int seq;
do {
seq = gtod_read_begin(gtod);
- mode = gtod->vclock_mode;
- ts->tv_sec = gtod->monotonic_time_sec;
- ns = gtod->monotonic_time_snsec;
- ns += vgetsns(&mode);
- ns >>= gtod->shift;
+ ts->tv_sec = base->sec;
+ ts->tv_nsec = base->nsec;
} while (unlikely(gtod_read_retry(gtod, seq)));
-
- ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
- ts->tv_nsec = ns;
-
- return mode;
}
-notrace static void do_realtime_coarse(struct timespec *ts)
+notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
{
- unsigned long seq;
- do {
- seq = gtod_read_begin(gtod);
- ts->tv_sec = gtod->wall_time_coarse_sec;
- ts->tv_nsec = gtod->wall_time_coarse_nsec;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-}
+ unsigned int msk;
-notrace static void do_monotonic_coarse(struct timespec *ts)
-{
- unsigned long seq;
- do {
- seq = gtod_read_begin(gtod);
- ts->tv_sec = gtod->monotonic_time_coarse_sec;
- ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-}
+ /* Sort out negative (CPU/FD) and invalid clocks */
+ if (unlikely((unsigned int) clock >= MAX_CLOCKS))
+ return vdso_fallback_gettime(clock, ts);
-notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
-{
- switch (clock) {
- case CLOCK_REALTIME:
- if (do_realtime(ts) == VCLOCK_NONE)
- goto fallback;
- break;
- case CLOCK_MONOTONIC:
- if (do_monotonic(ts) == VCLOCK_NONE)
- goto fallback;
- break;
- case CLOCK_REALTIME_COARSE:
- do_realtime_coarse(ts);
- break;
- case CLOCK_MONOTONIC_COARSE:
- do_monotonic_coarse(ts);
- break;
- default:
- goto fallback;
+ /*
+ * Convert the clockid to a bitmask and use it to check which
+ * clocks are handled in the VDSO directly.
+ */
+ msk = 1U << clock;
+ if (likely(msk & VGTOD_HRES)) {
+ return do_hres(clock, ts);
+ } else if (msk & VGTOD_COARSE) {
+ do_coarse(clock, ts);
+ return 0;
}
-
- return 0;
-fallback:
return vdso_fallback_gettime(clock, ts);
}
+
int clock_gettime(clockid_t, struct timespec *)
__attribute__((weak, alias("__vdso_clock_gettime")));
notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
{
if (likely(tv != NULL)) {
- if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
- return vdso_fallback_gtod(tv, tz);
+ struct timespec *ts = (struct timespec *) tv;
+
+ do_hres(CLOCK_REALTIME, ts);
tv->tv_usec /= 1000;
}
if (unlikely(tz != NULL)) {
@@ -318,7 +230,7 @@ int gettimeofday(struct timeval *, struct timezone *)
notrace time_t __vdso_time(time_t *t)
{
/* This is atomic on x86 so we don't need any locks. */
- time_t result = READ_ONCE(gtod->wall_time_sec);
+ time_t result = READ_ONCE(gtod->basetime[CLOCK_REALTIME].sec);
if (t)
*t = result;
diff --git a/arch/x86/entry/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c
index 8ec3d1f4ce9a..f86ab0ae1777 100644
--- a/arch/x86/entry/vdso/vgetcpu.c
+++ b/arch/x86/entry/vdso/vgetcpu.c
@@ -13,14 +13,8 @@
notrace long
__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
{
- unsigned int p;
+ vdso_read_cpunode(cpu, node);
- p = __getcpu();
-
- if (cpu)
- *cpu = p & VGETCPU_CPU_MASK;
- if (node)
- *node = p >> 12;
return 0;
}
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 5b8b556dbb12..3f9d43f26f63 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -332,40 +332,6 @@ static __init int vdso_setup(char *s)
return 0;
}
__setup("vdso=", vdso_setup);
-#endif
-
-#ifdef CONFIG_X86_64
-static void vgetcpu_cpu_init(void *arg)
-{
- int cpu = smp_processor_id();
- struct desc_struct d = { };
- unsigned long node = 0;
-#ifdef CONFIG_NUMA
- node = cpu_to_node(cpu);
-#endif
- if (static_cpu_has(X86_FEATURE_RDTSCP))
- write_rdtscp_aux((node << 12) | cpu);
-
- /*
- * Store cpu number in limit so that it can be loaded
- * quickly in user space in vgetcpu. (12 bits for the CPU
- * and 8 bits for the node)
- */
- d.limit0 = cpu | ((node & 0xf) << 12);
- d.limit1 = node >> 4;
- d.type = 5; /* RO data, expand down, accessed */
- d.dpl = 3; /* Visible to user code */
- d.s = 1; /* Not a system segment */
- d.p = 1; /* Present */
- d.d = 1; /* 32-bit */
-
- write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
-}
-
-static int vgetcpu_online(unsigned int cpu)
-{
- return smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
-}
static int __init init_vdso(void)
{
@@ -375,9 +341,7 @@ static int __init init_vdso(void)
init_vdso_image(&vdso_image_x32);
#endif
- /* notifier priority > KVM */
- return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
- "x86/vdso/vma:online", vgetcpu_online, NULL);
+ return 0;
}
subsys_initcall(init_vdso);
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 82ed001e8909..85fd85d52ffd 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -100,20 +100,13 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
*/
if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
- siginfo_t info;
struct thread_struct *thread = &current->thread;
thread->error_code = 6; /* user fault, no page, write */
thread->cr2 = ptr;
thread->trap_nr = X86_TRAP_PF;
- clear_siginfo(&info);
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = SEGV_MAPERR;
- info.si_addr = (void __user *)ptr;
-
- force_sig_info(SIGSEGV, &info, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr, current);
return false;
} else {
return true;
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index e1216dd95c04..cfcdba082feb 100644
--- a/arch/x86/entry/vsyscall/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
@@ -31,6 +31,8 @@ void update_vsyscall(struct timekeeper *tk)
{
int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+ struct vgtod_ts *base;
+ u64 nsec;
/* Mark the new vclock used. */
BUILD_BUG_ON(VCLOCK_MAX >= 32);
@@ -45,34 +47,37 @@ void update_vsyscall(struct timekeeper *tk)
vdata->mult = tk->tkr_mono.mult;
vdata->shift = tk->tkr_mono.shift;
- vdata->wall_time_sec = tk->xtime_sec;
- vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec;
+ base = &vdata->basetime[CLOCK_REALTIME];
+ base->sec = tk->xtime_sec;
+ base->nsec = tk->tkr_mono.xtime_nsec;
- vdata->monotonic_time_sec = tk->xtime_sec
- + tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec
- + ((u64)tk->wall_to_monotonic.tv_nsec
- << tk->tkr_mono.shift);
- while (vdata->monotonic_time_snsec >=
- (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
- vdata->monotonic_time_snsec -=
- ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
- vdata->monotonic_time_sec++;
- }
+ base = &vdata->basetime[CLOCK_TAI];
+ base->sec = tk->xtime_sec + (s64)tk->tai_offset;
+ base->nsec = tk->tkr_mono.xtime_nsec;
- vdata->wall_time_coarse_sec = tk->xtime_sec;
- vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
- tk->tkr_mono.shift);
+ base = &vdata->basetime[CLOCK_MONOTONIC];
+ base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+ nsec = tk->tkr_mono.xtime_nsec;
+ nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
+ while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+ nsec -= ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
+ base->sec++;
+ }
+ base->nsec = nsec;
- vdata->monotonic_time_coarse_sec =
- vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_coarse_nsec =
- vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+ base = &vdata->basetime[CLOCK_REALTIME_COARSE];
+ base->sec = tk->xtime_sec;
+ base->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
- while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
- vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
- vdata->monotonic_time_coarse_sec++;
+ base = &vdata->basetime[CLOCK_MONOTONIC_COARSE];
+ base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+ nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsec += tk->wall_to_monotonic.tv_nsec;
+ while (nsec >= NSEC_PER_SEC) {
+ nsec -= NSEC_PER_SEC;
+ base->sec++;
}
+ base->nsec = nsec;
gtod_write_end(vdata);
}
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index c84584bb9402..7d2d7c801dba 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -669,6 +669,10 @@ static int __init amd_core_pmu_init(void)
* We fallback to using default amd_get_event_constraints.
*/
break;
+ case 0x18:
+ pr_cont("Fam18h ");
+ /* Using default amd_get_event_constraints. */
+ break;
default:
pr_err("core perfctr but no constraints; unknown hardware!\n");
return -ENODEV;
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e8241b..398df6eaa109 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
static int num_counters_llc;
static int num_counters_nb;
+static bool l3_mask;
static HLIST_HEAD(uncore_unused_list);
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
hwc->idx = -1;
+ /*
+ * SliceMask and ThreadMask need to be set for certain L3 events in
+ * Family 17h. For other events, the two fields do not affect the count.
+ */
+ if (l3_mask)
+ hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
if (event->cpu < 0)
return -EINVAL;
@@ -507,17 +515,19 @@ static int __init amd_uncore_init(void)
{
int ret = -ENODEV;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return -ENODEV;
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
return -ENODEV;
- if (boot_cpu_data.x86 == 0x17) {
+ if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) {
/*
- * For F17h, the Northbridge counters are repurposed as Data
- * Fabric counters. Also, L3 counters are supported too. The PMUs
- * are exported based on family as either L2 or L3 and NB or DF.
+ * For F17h or F18h, the Northbridge counters are
+ * repurposed as Data Fabric counters. Also, L3
+ * counters are supported too. The PMUs are exported
+ * based on family as either L2 or L3 and NB or DF.
*/
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L3;
@@ -525,6 +535,7 @@ static int __init amd_uncore_init(void)
amd_llc_pmu.name = "amd_l3";
format_attr_event_df.show = &event_show_df;
format_attr_event_l3.show = &event_show_l3;
+ l3_mask = true;
} else {
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L2;
@@ -532,6 +543,7 @@ static int __init amd_uncore_init(void)
amd_llc_pmu.name = "amd_l2";
format_attr_event_df = format_attr_event;
format_attr_event_l3 = format_attr_event;
+ l3_mask = false;
}
amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
@@ -547,7 +559,9 @@ static int __init amd_uncore_init(void)
if (ret)
goto fail_nb;
- pr_info("AMD NB counters detected\n");
+ pr_info("%s NB counters detected\n",
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?
+ "HYGON" : "AMD");
ret = 0;
}
@@ -561,7 +575,9 @@ static int __init amd_uncore_init(void)
if (ret)
goto fail_llc;
- pr_info("AMD LLC counters detected\n");
+ pr_info("%s LLC counters detected\n",
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?
+ "HYGON" : "AMD");
ret = 0;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index dfb2f7c0d019..106911b603bd 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1033,6 +1033,27 @@ static inline void x86_assign_hw_event(struct perf_event *event,
}
}
+/**
+ * x86_perf_rdpmc_index - Return PMC counter used for event
+ * @event: the perf_event to which the PMC counter was assigned
+ *
+ * The counter assigned to this performance event may change if interrupts
+ * are enabled. This counter should thus never be used while interrupts are
+ * enabled. Before this function is used to obtain the assigned counter the
+ * event should be checked for validity using, for example,
+ * perf_event_read_local(), within the same interrupt disabled section in
+ * which this counter is planned to be used.
+ *
+ * Return: The index of the performance monitoring counter assigned to
+ * @perf_event.
+ */
+int x86_perf_rdpmc_index(struct perf_event *event)
+{
+ lockdep_assert_irqs_disabled();
+
+ return event->hw.event_base_rdpmc;
+}
+
static inline int match_prev_assignment(struct hw_perf_event *hwc,
struct cpu_hw_events *cpuc,
int i)
@@ -1584,7 +1605,7 @@ static void __init pmu_check_apic(void)
}
-static struct attribute_group x86_pmu_format_group = {
+static struct attribute_group x86_pmu_format_group __ro_after_init = {
.name = "format",
.attrs = NULL,
};
@@ -1631,9 +1652,9 @@ __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
struct attribute **new;
int j, i;
- for (j = 0; a[j]; j++)
+ for (j = 0; a && a[j]; j++)
;
- for (i = 0; b[i]; i++)
+ for (i = 0; b && b[i]; i++)
j++;
j++;
@@ -1642,9 +1663,9 @@ __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
return NULL;
j = 0;
- for (i = 0; a[i]; i++)
+ for (i = 0; a && a[i]; i++)
new[j++] = a[i];
- for (i = 0; b[i]; i++)
+ for (i = 0; b && b[i]; i++)
new[j++] = b[i];
new[j] = NULL;
@@ -1715,7 +1736,7 @@ static struct attribute *events_attr[] = {
NULL,
};
-static struct attribute_group x86_pmu_events_group = {
+static struct attribute_group x86_pmu_events_group __ro_after_init = {
.name = "events",
.attrs = events_attr,
};
@@ -1776,6 +1797,10 @@ static int __init init_hw_perf_events(void)
case X86_VENDOR_AMD:
err = amd_pmu_init();
break;
+ case X86_VENDOR_HYGON:
+ err = amd_pmu_init();
+ x86_pmu.name = "HYGON";
+ break;
default:
err = -ENOTSUPP;
}
@@ -2230,7 +2255,7 @@ static struct attribute *x86_pmu_attrs[] = {
NULL,
};
-static struct attribute_group x86_pmu_attr_group = {
+static struct attribute_group x86_pmu_attr_group __ro_after_init = {
.attrs = x86_pmu_attrs,
};
@@ -2248,7 +2273,7 @@ static struct attribute *x86_pmu_caps_attrs[] = {
NULL
};
-static struct attribute_group x86_pmu_caps_group = {
+static struct attribute_group x86_pmu_caps_group __ro_after_init = {
.name = "caps",
.attrs = x86_pmu_caps_attrs,
};
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 035c37481f57..0fb8659b20d8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -242,7 +242,7 @@ EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
-static struct attribute *nhm_events_attrs[] = {
+static struct attribute *nhm_mem_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
NULL,
};
@@ -278,8 +278,6 @@ EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
"4", "2");
static struct attribute *snb_events_attrs[] = {
- EVENT_PTR(mem_ld_snb),
- EVENT_PTR(mem_st_snb),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
@@ -290,6 +288,12 @@ static struct attribute *snb_events_attrs[] = {
NULL,
};
+static struct attribute *snb_mem_events_attrs[] = {
+ EVENT_PTR(mem_ld_snb),
+ EVENT_PTR(mem_st_snb),
+ NULL,
+};
+
static struct event_constraint intel_hsw_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -1995,6 +1999,18 @@ static void intel_pmu_nhm_enable_all(int added)
intel_pmu_enable_all(added);
}
+static void enable_counter_freeze(void)
+{
+ update_debugctlmsr(get_debugctlmsr() |
+ DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
+static void disable_counter_freeze(void)
+{
+ update_debugctlmsr(get_debugctlmsr() &
+ ~DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
static inline u64 intel_pmu_get_status(void)
{
u64 status;
@@ -2200,59 +2216,15 @@ static void intel_pmu_reset(void)
local_irq_restore(flags);
}
-/*
- * This handler is triggered by the local APIC, so the APIC IRQ handling
- * rules apply:
- */
-static int intel_pmu_handle_irq(struct pt_regs *regs)
+static int handle_pmi_common(struct pt_regs *regs, u64 status)
{
struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- int bit, loops;
- u64 status;
- int handled;
- int pmu_enabled;
-
- cpuc = this_cpu_ptr(&cpu_hw_events);
-
- /*
- * Save the PMU state.
- * It needs to be restored when leaving the handler.
- */
- pmu_enabled = cpuc->enabled;
- /*
- * No known reason to not always do late ACK,
- * but just in case do it opt-in.
- */
- if (!x86_pmu.late_ack)
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- intel_bts_disable_local();
- cpuc->enabled = 0;
- __intel_pmu_disable_all();
- handled = intel_pmu_drain_bts_buffer();
- handled += intel_bts_interrupt();
- status = intel_pmu_get_status();
- if (!status)
- goto done;
-
- loops = 0;
-again:
- intel_pmu_lbr_read();
- intel_pmu_ack_status(status);
- if (++loops > 100) {
- static bool warned = false;
- if (!warned) {
- WARN(1, "perfevents: irq loop stuck!\n");
- perf_event_print_debug();
- warned = true;
- }
- intel_pmu_reset();
- goto done;
- }
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int bit;
+ int handled = 0;
inc_irq_stat(apic_perf_irqs);
-
/*
* Ignore a range of extra bits in status that do not indicate
* overflow by themselves.
@@ -2261,7 +2233,7 @@ again:
GLOBAL_STATUS_ASIF |
GLOBAL_STATUS_LBRS_FROZEN);
if (!status)
- goto done;
+ return 0;
/*
* In case multiple PEBS events are sampled at the same time,
* it is possible to have GLOBAL_STATUS bit 62 set indicating
@@ -2331,6 +2303,146 @@ again:
x86_pmu_stop(event, 0);
}
+ return handled;
+}
+
+static bool disable_counter_freezing;
+static int __init intel_perf_counter_freezing_setup(char *s)
+{
+ disable_counter_freezing = true;
+ pr_info("Intel PMU Counter freezing feature disabled\n");
+ return 1;
+}
+__setup("disable_counter_freezing", intel_perf_counter_freezing_setup);
+
+/*
+ * Simplified handler for Arch Perfmon v4:
+ * - We rely on counter freezing/unfreezing to enable/disable the PMU.
+ * This is done automatically on PMU ack.
+ * - Ack the PMU only after the APIC.
+ */
+
+static int intel_pmu_handle_irq_v4(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int handled = 0;
+ bool bts = false;
+ u64 status;
+ int pmu_enabled = cpuc->enabled;
+ int loops = 0;
+
+ /* PMU has been disabled because of counter freezing */
+ cpuc->enabled = 0;
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ bts = true;
+ intel_bts_disable_local();
+ handled = intel_pmu_drain_bts_buffer();
+ handled += intel_bts_interrupt();
+ }
+ status = intel_pmu_get_status();
+ if (!status)
+ goto done;
+again:
+ intel_pmu_lbr_read();
+ if (++loops > 100) {
+ static bool warned;
+
+ if (!warned) {
+ WARN(1, "perfevents: irq loop stuck!\n");
+ perf_event_print_debug();
+ warned = true;
+ }
+ intel_pmu_reset();
+ goto done;
+ }
+
+
+ handled += handle_pmi_common(regs, status);
+done:
+ /* Ack the PMI in the APIC */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
+ /*
+ * The counters start counting immediately while ack the status.
+ * Make it as close as possible to IRET. This avoids bogus
+ * freezing on Skylake CPUs.
+ */
+ if (status) {
+ intel_pmu_ack_status(status);
+ } else {
+ /*
+ * CPU may issues two PMIs very close to each other.
+ * When the PMI handler services the first one, the
+ * GLOBAL_STATUS is already updated to reflect both.
+ * When it IRETs, the second PMI is immediately
+ * handled and it sees clear status. At the meantime,
+ * there may be a third PMI, because the freezing bit
+ * isn't set since the ack in first PMI handlers.
+ * Double check if there is more work to be done.
+ */
+ status = intel_pmu_get_status();
+ if (status)
+ goto again;
+ }
+
+ if (bts)
+ intel_bts_enable_local();
+ cpuc->enabled = pmu_enabled;
+ return handled;
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int intel_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc;
+ int loops;
+ u64 status;
+ int handled;
+ int pmu_enabled;
+
+ cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * Save the PMU state.
+ * It needs to be restored when leaving the handler.
+ */
+ pmu_enabled = cpuc->enabled;
+ /*
+ * No known reason to not always do late ACK,
+ * but just in case do it opt-in.
+ */
+ if (!x86_pmu.late_ack)
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+ intel_bts_disable_local();
+ cpuc->enabled = 0;
+ __intel_pmu_disable_all();
+ handled = intel_pmu_drain_bts_buffer();
+ handled += intel_bts_interrupt();
+ status = intel_pmu_get_status();
+ if (!status)
+ goto done;
+
+ loops = 0;
+again:
+ intel_pmu_lbr_read();
+ intel_pmu_ack_status(status);
+ if (++loops > 100) {
+ static bool warned;
+
+ if (!warned) {
+ WARN(1, "perfevents: irq loop stuck!\n");
+ perf_event_print_debug();
+ warned = true;
+ }
+ intel_pmu_reset();
+ goto done;
+ }
+
+ handled += handle_pmi_common(regs, status);
+
/*
* Repeat if there is more work to be done:
*/
@@ -3350,6 +3462,9 @@ static void intel_pmu_cpu_starting(int cpu)
if (x86_pmu.version > 1)
flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+ if (x86_pmu.counter_freezing)
+ enable_counter_freeze();
+
if (!cpuc->shared_regs)
return;
@@ -3421,6 +3536,9 @@ static void intel_pmu_cpu_dying(int cpu)
free_excl_cntrs(cpu);
fini_debug_store_on_cpu(cpu);
+
+ if (x86_pmu.counter_freezing)
+ disable_counter_freeze();
}
static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3725,6 +3843,40 @@ static __init void intel_nehalem_quirk(void)
}
}
+static bool intel_glp_counter_freezing_broken(int cpu)
+{
+ u32 rev = UINT_MAX; /* default to broken for unknown stepping */
+
+ switch (cpu_data(cpu).x86_stepping) {
+ case 1:
+ rev = 0x28;
+ break;
+ case 8:
+ rev = 0x6;
+ break;
+ }
+
+ return (cpu_data(cpu).microcode < rev);
+}
+
+static __init void intel_glp_counter_freezing_quirk(void)
+{
+ /* Check if it's already disabled */
+ if (disable_counter_freezing)
+ return;
+
+ /*
+ * If the system starts with the wrong ucode, leave the
+ * counter-freezing feature permanently disabled.
+ */
+ if (intel_glp_counter_freezing_broken(raw_smp_processor_id())) {
+ pr_info("PMU counter freezing disabled due to CPU errata,"
+ "please upgrade microcode\n");
+ x86_pmu.counter_freezing = false;
+ x86_pmu.handle_irq = intel_pmu_handle_irq;
+ }
+}
+
/*
* enable software workaround for errata:
* SNB: BJ122
@@ -3764,8 +3916,6 @@ EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1");
EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
- EVENT_PTR(mem_ld_hsw),
- EVENT_PTR(mem_st_hsw),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
@@ -3776,6 +3926,12 @@ static struct attribute *hsw_events_attrs[] = {
NULL
};
+static struct attribute *hsw_mem_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
static struct attribute *hsw_tsx_events_attrs[] = {
EVENT_PTR(tx_start),
EVENT_PTR(tx_commit),
@@ -3792,13 +3948,6 @@ static struct attribute *hsw_tsx_events_attrs[] = {
NULL
};
-static __init struct attribute **get_hsw_events_attrs(void)
-{
- return boot_cpu_has(X86_FEATURE_RTM) ?
- merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
- hsw_events_attrs;
-}
-
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@@ -3875,9 +4024,32 @@ static struct attribute *intel_pmu_attrs[] = {
NULL,
};
+static __init struct attribute **
+get_events_attrs(struct attribute **base,
+ struct attribute **mem,
+ struct attribute **tsx)
+{
+ struct attribute **attrs = base;
+ struct attribute **old;
+
+ if (mem && x86_pmu.pebs)
+ attrs = merge_attr(attrs, mem);
+
+ if (tsx && boot_cpu_has(X86_FEATURE_RTM)) {
+ old = attrs;
+ attrs = merge_attr(attrs, tsx);
+ if (old != base)
+ kfree(old);
+ }
+
+ return attrs;
+}
+
__init int intel_pmu_init(void)
{
struct attribute **extra_attr = NULL;
+ struct attribute **mem_attr = NULL;
+ struct attribute **tsx_attr = NULL;
struct attribute **to_free = NULL;
union cpuid10_edx edx;
union cpuid10_eax eax;
@@ -3935,6 +4107,9 @@ __init int intel_pmu_init(void)
max((int)edx.split.num_counters_fixed, assume);
}
+ if (version >= 4)
+ x86_pmu.counter_freezing = !disable_counter_freezing;
+
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
@@ -3986,7 +4161,7 @@ __init int intel_pmu_init(void)
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
- x86_pmu.cpu_events = nhm_events_attrs;
+ mem_attr = nhm_mem_events_attrs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4004,11 +4179,11 @@ __init int intel_pmu_init(void)
name = "nehalem";
break;
- case INTEL_FAM6_ATOM_PINEVIEW:
- case INTEL_FAM6_ATOM_LINCROFT:
- case INTEL_FAM6_ATOM_PENWELL:
- case INTEL_FAM6_ATOM_CLOVERVIEW:
- case INTEL_FAM6_ATOM_CEDARVIEW:
+ case INTEL_FAM6_ATOM_BONNELL:
+ case INTEL_FAM6_ATOM_BONNELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL:
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -4021,9 +4196,11 @@ __init int intel_pmu_init(void)
name = "bonnell";
break;
- case INTEL_FAM6_ATOM_SILVERMONT1:
- case INTEL_FAM6_ATOM_SILVERMONT2:
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_X:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
case INTEL_FAM6_ATOM_AIRMONT:
+ case INTEL_FAM6_ATOM_AIRMONT_MID:
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -4042,7 +4219,7 @@ __init int intel_pmu_init(void)
break;
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -4068,7 +4245,8 @@ __init int intel_pmu_init(void)
name = "goldmont";
break;
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ x86_add_quirk(intel_glp_counter_freezing_quirk);
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -4112,7 +4290,7 @@ __init int intel_pmu_init(void)
x86_pmu.extra_regs = intel_westmere_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = nhm_events_attrs;
+ mem_attr = nhm_mem_events_attrs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4152,6 +4330,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
x86_pmu.cpu_events = snb_events_attrs;
+ mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4192,6 +4371,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
x86_pmu.cpu_events = snb_events_attrs;
+ mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4226,10 +4406,12 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = get_hsw_events_attrs();
+ x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
pr_cont("Haswell events, ");
name = "haswell";
break;
@@ -4265,10 +4447,12 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = get_hsw_events_attrs();
+ x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
pr_cont("Broadwell events, ");
name = "broadwell";
break;
@@ -4324,7 +4508,9 @@ __init int intel_pmu_init(void)
hsw_format_attr : nhm_format_attr;
extra_attr = merge_attr(extra_attr, skl_format_attr);
to_free = extra_attr;
- x86_pmu.cpu_events = get_hsw_events_attrs();
+ x86_pmu.cpu_events = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
intel_pmu_pebs_data_source_skl(
boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
pr_cont("Skylake events, ");
@@ -4357,6 +4543,9 @@ __init int intel_pmu_init(void)
WARN_ON(!x86_pmu.format_attrs);
}
+ x86_pmu.cpu_events = get_events_attrs(x86_pmu.cpu_events,
+ mem_attr, tsx_attr);
+
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
@@ -4431,6 +4620,13 @@ __init int intel_pmu_init(void)
pr_cont("full-width counters, ");
}
+ /*
+ * For arch perfmon 4 use counter freezing to avoid
+ * several MSR accesses in the PMI.
+ */
+ if (x86_pmu.counter_freezing)
+ x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
+
kfree(to_free);
return 0;
}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f8084f18d58..d2e780705c5a 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -559,8 +559,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_X, slm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE, snb_cstates),
@@ -581,9 +581,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f3e006bed9a7..c88ed39582a1 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void)
x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
x86_pmu.lbr_sel_map = snb_lbr_sel_map;
+
+ /* Knights Landing does have MISPREDICT bit */
+ if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
+ x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
}
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 8d016ce5b80d..3a0aa83cbd07 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -95,7 +95,7 @@ static ssize_t pt_cap_show(struct device *cdev,
return snprintf(buf, PAGE_SIZE, "%x\n", pt_cap_get(cap));
}
-static struct attribute_group pt_cap_group = {
+static struct attribute_group pt_cap_group __ro_after_init = {
.name = "caps",
};
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 32f3e9423e99..91039ffed633 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -777,9 +777,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
{},
};
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 51d7c117e3c7..c07bee31abe8 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
void bdx_uncore_cpu_init(void)
{
- int pkg = topology_phys_to_logical_pkg(0);
+ int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
},
{ /* M3UPI0 Link 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
},
{ /* M3UPI0 Link 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
},
{ /* M3UPI1 Link 2 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
},
{ /* end: all zeroes */ }
};
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b4771a6ddbc1..1b9f85abf9bc 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -69,14 +69,14 @@ static bool test_intel(int idx)
case INTEL_FAM6_BROADWELL_GT3E:
case INTEL_FAM6_BROADWELL_X:
- case INTEL_FAM6_ATOM_SILVERMONT1:
- case INTEL_FAM6_ATOM_SILVERMONT2:
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_X:
case INTEL_FAM6_ATOM_AIRMONT:
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_XEON_PHI_KNL:
case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 156286335351..adae087cecdd 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -560,9 +560,11 @@ struct x86_pmu {
struct event_constraint *event_constraints;
struct x86_pmu_quirk *quirks;
int perfctr_second_write;
- bool late_ack;
u64 (*limit_period)(struct perf_event *event, u64 l);
+ /* PMI handler bits */
+ unsigned int late_ack :1,
+ counter_freezing :1;
/*
* sysfs attrs
*/
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index b21ee65c4101..1c11f9420a82 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,2 +1,6 @@
obj-y := hv_init.o mmu.o nested.o
obj-$(CONFIG_X86_64) += hv_apic.o
+
+ifdef CONFIG_X86_64
+obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o
+endif
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5b0f613428c2..8eb6fbee8e13 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -20,7 +20,6 @@
*/
#include <linux/types.h>
-#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/clockchips.h>
@@ -95,8 +94,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val)
*/
static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
{
- struct ipi_arg_ex **arg;
- struct ipi_arg_ex *ipi_arg;
+ struct hv_send_ipi_ex **arg;
+ struct hv_send_ipi_ex *ipi_arg;
unsigned long flags;
int nr_bank = 0;
int ret = 1;
@@ -105,7 +104,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
return false;
local_irq_save(flags);
- arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+ arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
ipi_arg = *arg;
if (unlikely(!ipi_arg))
@@ -135,7 +134,7 @@ ipi_mask_ex_done:
static bool __send_ipi_mask(const struct cpumask *mask, int vector)
{
int cur_cpu, vcpu;
- struct ipi_arg_non_ex ipi_arg;
+ struct hv_send_ipi ipi_arg;
int ret = 1;
trace_hyperv_send_ipi_mask(mask, vector);
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 20c876c7c5bf..7abb09e2eeb8 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -17,6 +17,7 @@
*
*/
+#include <linux/efi.h>
#include <linux/types.h>
#include <asm/apic.h>
#include <asm/desc.h>
@@ -253,6 +254,22 @@ static int hv_cpu_die(unsigned int cpu)
return 0;
}
+static int __init hv_pci_init(void)
+{
+ int gen2vm = efi_enabled(EFI_BOOT);
+
+ /*
+ * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
+ * The purpose is to suppress the harmless warning:
+ * "PCI: Fatal: No config space access function found"
+ */
+ if (gen2vm)
+ return 0;
+
+ /* For Generation-1 VM, we'll proceed in pci_arch_init(). */
+ return 1;
+}
+
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
@@ -329,6 +346,8 @@ void __init hyperv_init(void)
hv_apic_init();
+ x86_init.pci.arch_init = hv_pci_init;
+
/*
* Register Hyper-V specific clocksource.
*/
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
new file mode 100644
index 000000000000..a861b0456b1a
--- /dev/null
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V specific spinlock code.
+ *
+ * Copyright (C) 2018, Intel, Inc.
+ *
+ * Author : Yi Sun <yi.y.sun@intel.com>
+ */
+
+#define pr_fmt(fmt) "Hyper-V: " fmt
+
+#include <linux/spinlock.h>
+
+#include <asm/mshyperv.h>
+#include <asm/paravirt.h>
+#include <asm/apic.h>
+
+static bool __initdata hv_pvspin = true;
+
+static void hv_qlock_kick(int cpu)
+{
+ apic->send_IPI(cpu, X86_PLATFORM_IPI_VECTOR);
+}
+
+static void hv_qlock_wait(u8 *byte, u8 val)
+{
+ unsigned long msr_val;
+ unsigned long flags;
+
+ if (in_nmi())
+ return;
+
+ /*
+ * Reading HV_X64_MSR_GUEST_IDLE MSR tells the hypervisor that the
+ * vCPU can be put into 'idle' state. This 'idle' state is
+ * terminated by an IPI, usually from hv_qlock_kick(), even if
+ * interrupts are disabled on the vCPU.
+ *
+ * To prevent a race against the unlock path it is required to
+ * disable interrupts before accessing the HV_X64_MSR_GUEST_IDLE
+ * MSR. Otherwise, if the IPI from hv_qlock_kick() arrives between
+ * the lock value check and the rdmsrl() then the vCPU might be put
+ * into 'idle' state by the hypervisor and kept in that state for
+ * an unspecified amount of time.
+ */
+ local_irq_save(flags);
+ /*
+ * Only issue the rdmsrl() when the lock state has not changed.
+ */
+ if (READ_ONCE(*byte) == val)
+ rdmsrl(HV_X64_MSR_GUEST_IDLE, msr_val);
+ local_irq_restore(flags);
+}
+
+/*
+ * Hyper-V does not support this so far.
+ */
+bool hv_vcpu_is_preempted(int vcpu)
+{
+ return false;
+}
+PV_CALLEE_SAVE_REGS_THUNK(hv_vcpu_is_preempted);
+
+void __init hv_init_spinlocks(void)
+{
+ if (!hv_pvspin || !apic ||
+ !(ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) ||
+ !(ms_hyperv.features & HV_X64_MSR_GUEST_IDLE_AVAILABLE)) {
+ pr_info("PV spinlocks disabled\n");
+ return;
+ }
+ pr_info("PV spinlocks enabled\n");
+
+ __pv_init_lock_hash();
+ pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops.lock.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops.lock.wait = hv_qlock_wait;
+ pv_ops.lock.kick = hv_qlock_kick;
+ pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(hv_vcpu_is_preempted);
+}
+
+static __init int hv_parse_nopvspin(char *arg)
+{
+ hv_pvspin = false;
+ return 0;
+}
+early_param("hv_nopvspin", hv_parse_nopvspin);
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index ef5f29f913d7..e65d7fe6489f 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -231,6 +231,6 @@ void hyperv_setup_mmu_ops(void)
return;
pr_info("Using hypercall for remote TLB flush\n");
- pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
- pv_mmu_ops.tlb_remove_table = tlb_remove_table;
+ pv_ops.mmu.flush_tlb_others = hyperv_flush_tlb_others;
+ pv_ops.mmu.tlb_remove_table = tlb_remove_table;
}
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index a303d7b7d763..2f01eb4d6208 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -142,6 +142,8 @@ static inline u64 acpi_arch_get_root_pointer(void)
void acpi_generic_reduced_hw_init(void);
+u64 x86_default_get_root_pointer(void);
+
#else /* !CONFIG_ACPI */
#define acpi_lapic 0
@@ -153,6 +155,11 @@ static inline void disable_acpi(void) { }
static inline void acpi_generic_reduced_hw_init(void) { }
+static inline u64 x86_default_get_root_pointer(void)
+{
+ return 0;
+}
+
#endif /* !CONFIG_ACPI */
#define ARCH_HAS_POWER_INIT 1
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..8e4ea39e55d0 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -7,16 +7,24 @@
#include <asm/asm.h>
#ifdef CONFIG_SMP
- .macro LOCK_PREFIX
-672: lock
+.macro LOCK_PREFIX_HERE
.pushsection .smp_locks,"a"
.balign 4
- .long 672b - .
+ .long 671f - . # offset
.popsection
- .endm
+671:
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+ LOCK_PREFIX_HERE
+ lock \insn
+.endm
#else
- .macro LOCK_PREFIX
- .endm
+.macro LOCK_PREFIX_HERE
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+.endm
#endif
/*
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4cd6a3b71824..d7faa16622d8 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -31,15 +31,8 @@
*/
#ifdef CONFIG_SMP
-#define LOCK_PREFIX_HERE \
- ".pushsection .smp_locks,\"a\"\n" \
- ".balign 4\n" \
- ".long 671f - .\n" /* offset */ \
- ".popsection\n" \
- "671:"
-
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
-
+#define LOCK_PREFIX_HERE "LOCK_PREFIX_HERE\n\t"
+#define LOCK_PREFIX "LOCK_PREFIX "
#else /* ! CONFIG_SMP */
#define LOCK_PREFIX_HERE ""
#define LOCK_PREFIX ""
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index fddb6d26239f..1ae4e5791afa 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -103,6 +103,9 @@ static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev)
static inline bool amd_gart_present(void)
{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ return false;
+
/* GART present only on Fam15h, upto model 0fh */
if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
(boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 990770f9e76b..21b086786404 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -120,16 +120,32 @@
/* Exception table entry */
#ifdef __ASSEMBLY__
# define _ASM_EXTABLE_HANDLE(from, to, handler) \
- .pushsection "__ex_table","a" ; \
- .balign 4 ; \
- .long (from) - . ; \
- .long (to) - . ; \
- .long (handler) - . ; \
+ ASM_EXTABLE_HANDLE from to handler
+
+.macro ASM_EXTABLE_HANDLE from:req to:req handler:req
+ .pushsection "__ex_table","a"
+ .balign 4
+ .long (\from) - .
+ .long (\to) - .
+ .long (\handler) - .
.popsection
+.endm
+#else /* __ASSEMBLY__ */
+
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+ "ASM_EXTABLE_HANDLE from=" #from " to=" #to \
+ " handler=\"" #handler "\"\n\t"
+
+/* For C file, we already have NOKPROBE_SYMBOL macro */
+
+#endif /* __ASSEMBLY__ */
# define _ASM_EXTABLE(from, to) \
_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+# define _ASM_EXTABLE_UA(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
# define _ASM_EXTABLE_FAULT(from, to) \
_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
@@ -145,6 +161,7 @@
_ASM_PTR (entry); \
.popsection
+#ifdef __ASSEMBLY__
.macro ALIGN_DESTINATION
/* check for bad alignment of destination */
movl %edi,%ecx
@@ -165,34 +182,10 @@
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
+ _ASM_EXTABLE_UA(100b, 103b)
+ _ASM_EXTABLE_UA(101b, 103b)
.endm
-
-#else
-# define _EXPAND_EXTABLE_HANDLE(x) #x
-# define _ASM_EXTABLE_HANDLE(from, to, handler) \
- " .pushsection \"__ex_table\",\"a\"\n" \
- " .balign 4\n" \
- " .long (" #from ") - .\n" \
- " .long (" #to ") - .\n" \
- " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \
- " .popsection\n"
-
-# define _ASM_EXTABLE(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_FAULT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
-
-# define _ASM_EXTABLE_EX(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
-
-# define _ASM_EXTABLE_REFCOUNT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
-/* For C file, we already have NOKPROBE_SYMBOL macro */
-#endif
+#endif /* __ASSEMBLY__ */
#ifndef __ASSEMBLY__
/*
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index b143717b92b3..ea3d95275b43 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
* true if the result is zero, or false for all
* other cases.
*/
-#define arch_atomic_sub_and_test arch_atomic_sub_and_test
static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i);
}
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
/**
* arch_atomic_inc - increment atomic variable
@@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
*
* Atomically increments @v by 1.
*/
-#define arch_atomic_inc arch_atomic_inc
static __always_inline void arch_atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
}
+#define arch_atomic_inc arch_atomic_inc
/**
* arch_atomic_dec - decrement atomic variable
@@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
*
* Atomically decrements @v by 1.
*/
-#define arch_atomic_dec arch_atomic_dec
static __always_inline void arch_atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
}
+#define arch_atomic_dec arch_atomic_dec
/**
* arch_atomic_dec_and_test - decrement and test
@@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
* returns true if the result is 0, or false for all other
* cases.
*/
-#define arch_atomic_dec_and_test arch_atomic_dec_and_test
static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e);
}
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
/**
* arch_atomic_inc_and_test - increment and test
@@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
* and returns true if the result is zero, or false for all
* other cases.
*/
-#define arch_atomic_inc_and_test arch_atomic_inc_and_test
static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e);
}
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
/**
* arch_atomic_add_negative - add and test if negative
@@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-#define arch_atomic_add_negative arch_atomic_add_negative
static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i);
}
+#define arch_atomic_add_negative arch_atomic_add_negative
/**
* arch_atomic_add_return - add integer and return
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index ef959f02d070..6a5b0ec460da 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
*
* Atomically increments @v by 1.
*/
-#define arch_atomic64_inc arch_atomic64_inc
static inline void arch_atomic64_inc(atomic64_t *v)
{
__alternative_atomic64(inc, inc_return, /* no output */,
"S" (v) : "memory", "eax", "ecx", "edx");
}
+#define arch_atomic64_inc arch_atomic64_inc
/**
* arch_atomic64_dec - decrement atomic64 variable
@@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v)
*
* Atomically decrements @v by 1.
*/
-#define arch_atomic64_dec arch_atomic64_dec
static inline void arch_atomic64_dec(atomic64_t *v)
{
__alternative_atomic64(dec, dec_return, /* no output */,
"S" (v) : "memory", "eax", "ecx", "edx");
}
+#define arch_atomic64_dec arch_atomic64_dec
/**
* arch_atomic64_add_unless - add unless the number is a given value
@@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
return (int)a;
}
-#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
{
int r;
@@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
"S" (v) : "ecx", "edx", "memory");
return r;
}
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
-#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
{
long long r;
@@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
"S" (v) : "ecx", "memory");
return r;
}
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
#undef alternative_atomic64
#undef __alternative_atomic64
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 4343d9b4f30e..dadc20adba21 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
* true if the result is zero, or false for all
* other cases.
*/
-#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i);
}
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
/**
* arch_atomic64_inc - increment atomic64 variable
@@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
*
* Atomically increments @v by 1.
*/
-#define arch_atomic64_inc arch_atomic64_inc
static __always_inline void arch_atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
: "=m" (v->counter)
: "m" (v->counter));
}
+#define arch_atomic64_inc arch_atomic64_inc
/**
* arch_atomic64_dec - decrement atomic64 variable
@@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
*
* Atomically decrements @v by 1.
*/
-#define arch_atomic64_dec arch_atomic64_dec
static __always_inline void arch_atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
: "=m" (v->counter)
: "m" (v->counter));
}
+#define arch_atomic64_dec arch_atomic64_dec
/**
* arch_atomic64_dec_and_test - decrement and test
@@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
* returns true if the result is 0, or false for all other
* cases.
*/
-#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e);
}
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
/**
* arch_atomic64_inc_and_test - increment and test
@@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
* and returns true if the result is zero, or false for all
* other cases.
*/
-#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e);
}
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
/**
* arch_atomic64_add_negative - add and test if negative
@@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
-#define arch_atomic64_add_negative arch_atomic64_add_negative
static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i);
}
+#define arch_atomic64_add_negative arch_atomic64_add_negative
/**
* arch_atomic64_add_return - add and return
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 9f645ba57dbb..124f9195eb3e 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -217,8 +217,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
*/
static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts),
- *addr, "Ir", nr, "%0", c);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr);
}
/**
@@ -264,8 +263,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
*/
static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr),
- *addr, "Ir", nr, "%0", c);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr);
}
/**
@@ -318,8 +316,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
*/
static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc),
- *addr, "Ir", nr, "%0", c);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
}
static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 6804d6642767..5090035e6d16 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -4,6 +4,8 @@
#include <linux/stringify.h>
+#ifndef __ASSEMBLY__
+
/*
* Despite that some emulators terminate on UD2, we use it for WARN().
*
@@ -20,53 +22,15 @@
#define LEN_UD2 2
-#ifdef CONFIG_GENERIC_BUG
-
-#ifdef CONFIG_X86_32
-# define __BUG_REL(val) ".long " __stringify(val)
-#else
-# define __BUG_REL(val) ".long " __stringify(val) " - 2b"
-#endif
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-
-#define _BUG_FLAGS(ins, flags) \
-do { \
- asm volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \
- "\t.word %c1" "\t# bug_entry::line\n" \
- "\t.word %c2" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c3\n" \
- ".popsection" \
- : : "i" (__FILE__), "i" (__LINE__), \
- "i" (flags), \
- "i" (sizeof(struct bug_entry))); \
-} while (0)
-
-#else /* !CONFIG_DEBUG_BUGVERBOSE */
-
#define _BUG_FLAGS(ins, flags) \
do { \
- asm volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t.word %c0" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c1\n" \
- ".popsection" \
- : : "i" (flags), \
+ asm volatile("ASM_BUG ins=\"" ins "\" file=%c0 line=%c1 " \
+ "flags=%c2 size=%c3" \
+ : : "i" (__FILE__), "i" (__LINE__), \
+ "i" (flags), \
"i" (sizeof(struct bug_entry))); \
} while (0)
-#endif /* CONFIG_DEBUG_BUGVERBOSE */
-
-#else
-
-#define _BUG_FLAGS(ins, flags) asm volatile(ins)
-
-#endif /* CONFIG_GENERIC_BUG */
-
#define HAVE_ARCH_BUG
#define BUG() \
do { \
@@ -82,4 +46,54 @@ do { \
#include <asm-generic/bug.h>
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_GENERIC_BUG
+
+#ifdef CONFIG_X86_32
+.macro __BUG_REL val:req
+ .long \val
+.endm
+#else
+.macro __BUG_REL val:req
+ .long \val - 2b
+.endm
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+1: \ins
+ .pushsection __bug_table,"aw"
+2: __BUG_REL val=1b # bug_entry::bug_addr
+ __BUG_REL val=\file # bug_entry::file
+ .word \line # bug_entry::line
+ .word \flags # bug_entry::flags
+ .org 2b+\size
+ .popsection
+.endm
+
+#else /* !CONFIG_DEBUG_BUGVERBOSE */
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+1: \ins
+ .pushsection __bug_table,"aw"
+2: __BUG_REL val=1b # bug_entry::bug_addr
+ .word \flags # bug_entry::flags
+ .org 2b+\size
+ .popsection
+.endm
+
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
+#else /* CONFIG_GENERIC_BUG */
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+ \ins
+.endm
+
+#endif /* CONFIG_GENERIC_BUG */
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
index e958e28f7ab5..86b63c7feab7 100644
--- a/arch/x86/include/asm/cacheinfo.h
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -3,5 +3,6 @@
#define _ASM_X86_CACHEINFO_H
void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
#endif /* _ASM_X86_CACHEINFO_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index a55d79b233d3..bfb85e5844ab 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -242,10 +242,12 @@ extern void __add_wrong_size(void)
BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long)); \
VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long))); \
VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2)); \
- asm volatile(pfx "cmpxchg%c4b %2; sete %0" \
- : "=a" (__ret), "+d" (__old2), \
- "+m" (*(p1)), "+m" (*(p2)) \
- : "i" (2 * sizeof(long)), "a" (__old1), \
+ asm volatile(pfx "cmpxchg%c5b %1" \
+ CC_SET(e) \
+ : CC_OUT(e) (__ret), \
+ "+m" (*(p1)), "+m" (*(p2)), \
+ "+a" (__old1), "+d" (__old2) \
+ : "i" (2 * sizeof(long)), \
"b" (__new1), "c" (__new2)); \
__ret; \
})
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index fb97cf7c4137..fab4df16a3c4 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -12,38 +12,23 @@
#include <asm/user32.h>
#include <asm/unistd.h>
+#include <asm-generic/compat.h>
+
#define COMPAT_USER_HZ 100
#define COMPAT_UTS_MACHINE "i686\0\0"
-typedef u32 compat_size_t;
-typedef s32 compat_ssize_t;
-typedef s32 compat_clock_t;
-typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
typedef u16 __compat_gid_t;
typedef u32 __compat_uid32_t;
typedef u32 __compat_gid32_t;
typedef u16 compat_mode_t;
-typedef u32 compat_ino_t;
typedef u16 compat_dev_t;
-typedef s32 compat_off_t;
-typedef s64 compat_loff_t;
typedef u16 compat_nlink_t;
typedef u16 compat_ipc_pid_t;
-typedef s32 compat_daddr_t;
typedef u32 compat_caddr_t;
typedef __kernel_fsid_t compat_fsid_t;
-typedef s32 compat_timer_t;
-typedef s32 compat_key_t;
-
-typedef s32 compat_int_t;
-typedef s32 compat_long_t;
typedef s64 __attribute__((aligned(4))) compat_s64;
-typedef u32 compat_uint_t;
-typedef u32 compat_ulong_t;
-typedef u32 compat_u32;
typedef u64 __attribute__((aligned(4))) compat_u64;
-typedef u32 compat_uptr_t;
struct compat_stat {
compat_dev_t st_dev;
@@ -240,6 +225,6 @@ static inline bool in_compat_syscall(void)
struct compat_siginfo;
int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
- const siginfo_t *from, bool x32_ABI);
+ const kernel_siginfo_t *from, bool x32_ABI);
#endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 4a7884b8dca5..29c706415443 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -30,8 +30,6 @@ struct cpu_entry_area {
*/
struct tss_struct tss;
- char entry_trampoline[PAGE_SIZE];
-
#ifdef CONFIG_X86_64
/*
* Exception stacks used for IST entries.
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aced6c9290d6..7d442722ef24 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -2,10 +2,10 @@
#ifndef _ASM_X86_CPUFEATURE_H
#define _ASM_X86_CPUFEATURE_H
-#include <asm/processor.h>
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
#include <asm/asm.h>
#include <linux/bitops.h>
@@ -161,37 +161,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline __pure bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto("1: jmp 6f\n"
- "2:\n"
- ".skip -(((5f-4f) - (2b-1b)) > 0) * "
- "((5f-4f) - (2b-1b)),0x90\n"
- "3:\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 4f - .\n" /* repl offset */
- " .word %P[always]\n" /* always replace */
- " .byte 3b - 1b\n" /* src len */
- " .byte 5f - 4f\n" /* repl len */
- " .byte 3b - 2b\n" /* pad len */
- ".previous\n"
- ".section .altinstr_replacement,\"ax\"\n"
- "4: jmp %l[t_no]\n"
- "5:\n"
- ".previous\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 0\n" /* no replacement */
- " .word %P[feature]\n" /* feature bit */
- " .byte 3b - 1b\n" /* src len */
- " .byte 0\n" /* repl len */
- " .byte 0\n" /* pad len */
- ".previous\n"
- ".section .altinstr_aux,\"ax\"\n"
- "6:\n"
- " testb %[bitnum],%[cap_byte]\n"
- " jnz %l[t_yes]\n"
- " jmp %l[t_no]\n"
- ".previous\n"
+ asm_volatile_goto("STATIC_CPU_HAS bitnum=%[bitnum] "
+ "cap_byte=\"%[cap_byte]\" "
+ "feature=%P[feature] t_yes=%l[t_yes] "
+ "t_no=%l[t_no] always=%P[always]"
: : [feature] "i" (bit),
[always] "i" (X86_FEATURE_ALWAYS),
[bitnum] "i" (1 << (bit & 7)),
@@ -226,5 +199,44 @@ t_no:
#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
boot_cpu_data.x86_model
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#else /* __ASSEMBLY__ */
+
+.macro STATIC_CPU_HAS bitnum:req cap_byte:req feature:req t_yes:req t_no:req always:req
+1:
+ jmp 6f
+2:
+ .skip -(((5f-4f) - (2b-1b)) > 0) * ((5f-4f) - (2b-1b)),0x90
+3:
+ .section .altinstructions,"a"
+ .long 1b - . /* src offset */
+ .long 4f - . /* repl offset */
+ .word \always /* always replace */
+ .byte 3b - 1b /* src len */
+ .byte 5f - 4f /* repl len */
+ .byte 3b - 2b /* pad len */
+ .previous
+ .section .altinstr_replacement,"ax"
+4:
+ jmp \t_no
+5:
+ .previous
+ .section .altinstructions,"a"
+ .long 1b - . /* src offset */
+ .long 0 /* no replacement */
+ .word \feature /* feature bit */
+ .byte 3b - 1b /* src len */
+ .byte 0 /* repl len */
+ .byte 0 /* pad len */
+ .previous
+ .section .altinstr_aux,"ax"
+6:
+ testb \bitnum,\cap_byte
+ jnz \t_yes
+ jmp \t_no
+ .previous
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
#endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 4505ac2735ad..9e5ca30738e5 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -8,7 +8,7 @@
DECLARE_PER_CPU(unsigned long, cpu_dr7);
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
/*
* These special macros can be used to get or set a debugging register
*/
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 13c5ee878a47..68a99d2a5f33 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -108,7 +108,7 @@ static inline int desc_empty(const void *ptr)
return !(desc[0] | desc[1]);
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define load_TR_desc() native_load_tr_desc()
@@ -134,7 +134,7 @@ static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
{
}
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cec5fae23eb3..eea40d52ca78 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -140,6 +140,7 @@ extern void __init efi_apply_memmap_quirks(void);
extern int __init efi_reuse_config(u64 tables, int nr_tables);
extern void efi_delete_dummy_variable(void);
extern void efi_switch_mm(struct mm_struct *mm);
+extern void efi_recover_from_page_fault(unsigned long phys_addr);
struct efi_setup_data {
u64 fw_vendor;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 0d157d2a1e2a..69c0f892e310 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -10,6 +10,7 @@
#include <asm/ptrace.h>
#include <asm/user.h>
#include <asm/auxvec.h>
+#include <asm/fsgsbase.h>
typedef unsigned long elf_greg_t;
@@ -62,8 +63,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
#define R_X86_64_8 14 /* Direct 8 bit sign extended */
#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
+#define R_X86_64_PC64 24 /* Place relative 64-bit signed */
/*
* These are used to set parameters in the core dumps.
@@ -205,7 +205,6 @@ void set_personality_ia32(bool);
#define ELF_CORE_COPY_REGS(pr_reg, regs) \
do { \
- unsigned long base; \
unsigned v; \
(pr_reg)[0] = (regs)->r15; \
(pr_reg)[1] = (regs)->r14; \
@@ -228,8 +227,8 @@ do { \
(pr_reg)[18] = (regs)->flags; \
(pr_reg)[19] = (regs)->sp; \
(pr_reg)[20] = (regs)->ss; \
- rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base; \
- rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base; \
+ (pr_reg)[21] = x86_fsbase_read_cpu(); \
+ (pr_reg)[22] = x86_gsbase_read_cpu_inactive(); \
asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \
asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \
asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index f9c3a5d502f4..d8c2198d543b 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -29,7 +29,8 @@ struct pt_regs;
(b)->handler = (tmp).handler - (delta); \
} while (0)
-extern int fixup_exception(struct pt_regs *regs, int trapnr);
+extern int fixup_exception(struct pt_regs *regs, int trapnr,
+ unsigned long error_code, unsigned long fault_addr);
extern int fixup_bug(struct pt_regs *regs, int trapnr);
extern bool ex_has_fault_handler(unsigned long ip);
extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index e203169931c7..50ba74a34a37 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -14,6 +14,16 @@
#ifndef _ASM_X86_FIXMAP_H
#define _ASM_X86_FIXMAP_H
+/*
+ * Exposed to assembly code for setting up initial page tables. Cannot be
+ * calculated in assembly code (fixmap entries are an enum), but is sanity
+ * checked in the actual fixmap C code to make sure that the fixmap is
+ * covered fully.
+ */
+#define FIXMAP_PMD_NUM 2
+/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
+#define FIXMAP_PMD_TOP 507
+
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
#include <asm/acpi.h>
@@ -152,7 +162,7 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
void native_set_fixmap(enum fixed_addresses idx,
phys_addr_t phys, pgprot_t flags);
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
static inline void __set_fixmap(enum fixed_addresses idx,
phys_addr_t phys, pgprot_t flags)
{
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a38bf5a1e37a..5f7290e6e954 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -226,7 +226,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
"3: movl $-2,%[err]\n\t" \
"jmp 2b\n\t" \
".popsection\n\t" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: [err] "=r" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
@@ -528,7 +528,7 @@ static inline void fpregs_activate(struct fpu *fpu)
static inline void
switch_fpu_prepare(struct fpu *old_fpu, int cpu)
{
- if (old_fpu->initialized) {
+ if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
if (!copy_fpregs_to_fpstate(old_fpu))
old_fpu->last_cpu = -1;
else
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
new file mode 100644
index 000000000000..eb377b6e9eed
--- /dev/null
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_FSGSBASE_H
+#define _ASM_FSGSBASE_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_X86_64
+
+#include <asm/msr-index.h>
+
+/*
+ * Read/write a task's FSBASE or GSBASE. This returns the value that
+ * the FS/GS base would have (if the task were to be resumed). These
+ * work on the current task or on a non-running (typically stopped
+ * ptrace child) task.
+ */
+extern unsigned long x86_fsbase_read_task(struct task_struct *task);
+extern unsigned long x86_gsbase_read_task(struct task_struct *task);
+extern int x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase);
+extern int x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase);
+
+/* Helper functions for reading/writing FS/GS base */
+
+static inline unsigned long x86_fsbase_read_cpu(void)
+{
+ unsigned long fsbase;
+
+ rdmsrl(MSR_FS_BASE, fsbase);
+
+ return fsbase;
+}
+
+static inline unsigned long x86_gsbase_read_cpu_inactive(void)
+{
+ unsigned long gsbase;
+
+ rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+
+ return gsbase;
+}
+
+extern void x86_fsbase_write_cpu(unsigned long fsbase);
+extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_FSGSBASE_H */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index de4d68852d3a..13c83fe97988 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -20,7 +20,7 @@
"3:\tmov\t%3, %1\n" \
"\tjmp\t2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (oldval), "=r" (ret), "+m" (*uaddr) \
: "i" (-EFAULT), "0" (oparg), "1" (0))
@@ -36,8 +36,8 @@
"4:\tmov\t%5, %1\n" \
"\tjmp\t3b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=&a" (oldval), "=&r" (ret), \
"+m" (*uaddr), "=&r" (tem) \
: "r" (oparg), "i" (-EFAULT), "1" (0))
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index e977b6b3a538..4139f7650fe5 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -38,6 +38,8 @@
#define HV_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
/* Partition reference TSC MSR is available */
#define HV_MSR_REFERENCE_TSC_AVAILABLE (1 << 9)
+/* Partition Guest IDLE MSR is available */
+#define HV_X64_MSR_GUEST_IDLE_AVAILABLE (1 << 10)
/* A partition's reference time stamp counter (TSC) page */
#define HV_X64_MSR_REFERENCE_TSC 0x40000021
@@ -246,6 +248,9 @@
#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6
#define HV_X64_MSR_STIMER3_COUNT 0x400000B7
+/* Hyper-V guest idle MSR */
+#define HV_X64_MSR_GUEST_IDLE 0x400000F0
+
/* Hyper-V guest crash notification MSR's */
#define HV_X64_MSR_CRASH_P0 0x40000100
#define HV_X64_MSR_CRASH_P1 0x40000101
@@ -726,19 +731,21 @@ struct hv_enlightened_vmcs {
#define HV_STIMER_AUTOENABLE (1ULL << 3)
#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F)
-struct ipi_arg_non_ex {
- u32 vector;
- u32 reserved;
- u64 cpu_mask;
-};
-
struct hv_vpset {
u64 format;
u64 valid_bank_mask;
u64 bank_contents[];
};
-struct ipi_arg_ex {
+/* HvCallSendSyntheticClusterIpi hypercall */
+struct hv_send_ipi {
+ u32 vector;
+ u32 reserved;
+ u64 cpu_mask;
+};
+
+/* HvCallSendSyntheticClusterIpiEx hypercall */
+struct hv_send_ipi_ex {
u32 vector;
u32 reserved;
struct hv_vpset vp_set;
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 7ed08a7c3398..0dd6b0f4000e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -8,9 +8,6 @@
* The "_X" parts are generally the EP and EX Xeons, or the
* "Extreme" ones, like Broadwell-E.
*
- * Things ending in "2" are usually because we have no better
- * name for them. There's no processor called "SILVERMONT2".
- *
* While adding a new CPUID for a new microarchitecture, add a new
* group to keep logically sorted out in chronological order. Within
* that group keep the CPUID for the variants sorted by model number.
@@ -57,19 +54,23 @@
/* "Small Core" Processors (Atom) */
-#define INTEL_FAM6_ATOM_PINEVIEW 0x1C
-#define INTEL_FAM6_ATOM_LINCROFT 0x26
-#define INTEL_FAM6_ATOM_PENWELL 0x27
-#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35
-#define INTEL_FAM6_ATOM_CEDARVIEW 0x36
-#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */
-#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */
-#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */
-#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
-#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
-#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A
+#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
+#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */
+
+#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */
+#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */
+#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */
+
+#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT_X 0x4D /* Avaton, Rangely */
+#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */
+
+#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */
+#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */
+
+#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
+#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */
+#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
/* Xeon Phi */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 6de64840dd22..832da8229cc7 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -187,11 +187,12 @@ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size)
#define ioremap_nocache ioremap_nocache
extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
#define ioremap_uc ioremap_uc
-
extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
#define ioremap_cache ioremap_cache
extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val);
#define ioremap_prot ioremap_prot
+extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size);
+#define ioremap_encrypted ioremap_encrypted
/**
* ioremap - map bus memory into CPU space
@@ -369,18 +370,6 @@ extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
extern bool is_early_ioremap_ptep(pte_t *ptep);
-#ifdef CONFIG_XEN
-#include <xen/xen.h>
-struct bio_vec;
-
-extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
- const struct bio_vec *vec2);
-
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
- (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \
- (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
-#endif /* CONFIG_XEN */
-
#define IO_SPACE_LIMIT 0xffff
#include <asm-generic/io.h>
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 5f26962eff42..67ed72f31cc2 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -45,6 +45,8 @@ struct vcpu_data {
#ifdef CONFIG_IRQ_REMAP
+extern raw_spinlock_t irq_2_ir_lock;
+
extern bool irq_remapping_cap(enum irq_remap_cap cap);
extern void set_irq_remapping_broken(void);
extern int irq_remapping_prepare(void);
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 15450a675031..058e40fed167 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -64,7 +64,7 @@ static inline __cpuidle void native_halt(void)
#endif
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#ifndef __ASSEMBLY__
@@ -123,6 +123,10 @@ static inline notrace unsigned long arch_local_irq_save(void)
#define DISABLE_INTERRUPTS(x) cli
#ifdef CONFIG_X86_64
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x) pushfq; popq %rax
+#endif
+
#define SWAPGS swapgs
/*
* Currently paravirt can't handle swapgs nicely when we
@@ -135,8 +139,6 @@ static inline notrace unsigned long arch_local_irq_save(void)
*/
#define SWAPGS_UNSAFE_STACK swapgs
-#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */
-
#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
@@ -145,18 +147,12 @@ static inline notrace unsigned long arch_local_irq_save(void)
swapgs; \
sysretl
-#ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x) pushfq; popq %rax
-#endif
#else
#define INTERRUPT_RETURN iret
-#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit
-#define GET_CR0_INTO_EAX movl %cr0, %eax
#endif
-
#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
#ifndef __ASSEMBLY__
static inline int arch_irqs_disabled_flags(unsigned long flags)
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 8c0de4282659..a5fb34fe56a4 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -2,19 +2,6 @@
#ifndef _ASM_X86_JUMP_LABEL_H
#define _ASM_X86_JUMP_LABEL_H
-#ifndef HAVE_JUMP_LABEL
-/*
- * For better or for worse, if jump labels (the gcc extension) are missing,
- * then the entire static branch patching infrastructure is compiled out.
- * If that happens, the code in here will malfunction. Raise a compiler
- * error instead.
- *
- * In theory, jump labels and the static branch patching infrastructure
- * could be decoupled to fix this.
- */
-#error asm/jump_label.h included on a non-jump-label kernel
-#endif
-
#define JUMP_LABEL_NOP_SIZE 5
#ifdef CONFIG_X86_64
@@ -33,14 +20,9 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
- ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
- ".pushsection __jump_table, \"aw\" \n\t"
- _ASM_ALIGN "\n\t"
- _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
- ".popsection \n\t"
- : : "i" (key), "i" (branch) : : l_yes);
-
+ asm_volatile_goto("STATIC_BRANCH_NOP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+ "branch=\"%c1\""
+ : : "i" (key), "i" (branch) : : l_yes);
return false;
l_yes:
return true;
@@ -48,13 +30,8 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
- ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"
- "2:\n\t"
- ".pushsection __jump_table, \"aw\" \n\t"
- _ASM_ALIGN "\n\t"
- _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
- ".popsection \n\t"
+ asm_volatile_goto("STATIC_BRANCH_JMP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+ "branch=\"%c1\""
: : "i" (key), "i" (branch) : : l_yes);
return false;
@@ -62,49 +39,28 @@ l_yes:
return true;
}
-#ifdef CONFIG_X86_64
-typedef u64 jump_label_t;
-#else
-typedef u32 jump_label_t;
-#endif
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#else /* __ASSEMBLY__ */
-.macro STATIC_JUMP_IF_TRUE target, key, def
-.Lstatic_jump_\@:
- .if \def
- /* Equivalent to "jmp.d32 \target" */
- .byte 0xe9
- .long \target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
- .else
- .byte STATIC_KEY_INIT_NOP
- .endif
+.macro STATIC_BRANCH_NOP l_yes:req key:req branch:req
+.Lstatic_branch_nop_\@:
+ .byte STATIC_KEY_INIT_NOP
+.Lstatic_branch_no_after_\@:
.pushsection __jump_table, "aw"
_ASM_ALIGN
- _ASM_PTR .Lstatic_jump_\@, \target, \key
+ .long .Lstatic_branch_nop_\@ - ., \l_yes - .
+ _ASM_PTR \key + \branch - .
.popsection
.endm
-.macro STATIC_JUMP_IF_FALSE target, key, def
-.Lstatic_jump_\@:
- .if \def
- .byte STATIC_KEY_INIT_NOP
- .else
- /* Equivalent to "jmp.d32 \target" */
- .byte 0xe9
- .long \target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
- .endif
+.macro STATIC_BRANCH_JMP l_yes:req key:req branch:req
+.Lstatic_branch_jmp_\@:
+ .byte 0xe9
+ .long \l_yes - .Lstatic_branch_jmp_after_\@
+.Lstatic_branch_jmp_after_\@:
.pushsection __jump_table, "aw"
_ASM_ALIGN
- _ASM_PTR .Lstatic_jump_\@, \target, \key + 1
+ .long .Lstatic_branch_jmp_\@ - ., \l_yes - .
+ _ASM_PTR \key + \branch - .
.popsection
.endm
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 395c9631e000..75f1e35e7c15 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -22,10 +22,20 @@ enum die_val {
DIE_NMIUNKNOWN,
};
+enum show_regs_mode {
+ SHOW_REGS_SHORT,
+ /*
+ * For when userspace crashed, but we don't think it's our fault, and
+ * therefore don't print kernel registers.
+ */
+ SHOW_REGS_USER,
+ SHOW_REGS_ALL
+};
+
extern void die(const char *, struct pt_regs *,long);
extern int __must_check __die(const char *, struct pt_regs *, long);
extern void show_stack_regs(struct pt_regs *regs);
-extern void __show_regs(struct pt_regs *regs, int all);
+extern void __show_regs(struct pt_regs *regs, enum show_regs_mode);
extern void show_iret_regs(struct pt_regs *regs);
extern unsigned long oops_begin(void);
extern void oops_end(unsigned long, struct pt_regs *, int signr);
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index f327236f0fa7..5125fca472bb 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -67,7 +67,7 @@ struct kimage;
/* Memory to backup during crash kdump */
#define KEXEC_BACKUP_SRC_START (0UL)
-#define KEXEC_BACKUP_SRC_END (640 * 1024UL) /* 640K */
+#define KEXEC_BACKUP_SRC_END (640 * 1024UL - 1) /* 640K */
/*
* CPU does not save ss and sp on stack if execution is already
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 0f82cd91cd3c..93c4bf598fb0 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -364,6 +364,10 @@ struct x86_emulate_ctxt {
#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+#define X86EMUL_CPUID_VENDOR_HygonGenuine_ebx 0x6f677948
+#define X86EMUL_CPUID_VENDOR_HygonGenuine_ecx 0x656e6975
+#define X86EMUL_CPUID_VENDOR_HygonGenuine_edx 0x6e65476e
+
#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 00ddb0c9e612..55e51ff7e421 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -102,7 +102,15 @@
#define UNMAPPED_GVA (~(gpa_t)0)
/* KVM Hugepage definitions for x86 */
-#define KVM_NR_PAGE_SIZES 3
+enum {
+ PT_PAGE_TABLE_LEVEL = 1,
+ PT_DIRECTORY_LEVEL = 2,
+ PT_PDPE_LEVEL = 3,
+ /* set max level to the biggest one */
+ PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL,
+};
+#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \
+ PT_PAGE_TABLE_LEVEL + 1)
#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9)
#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
@@ -177,6 +185,7 @@ enum {
#define DR6_BD (1 << 13)
#define DR6_BS (1 << 14)
+#define DR6_BT (1 << 15)
#define DR6_RTM (1 << 16)
#define DR6_FIXED_1 0xfffe0ff0
#define DR6_INIT 0xffff0ff0
@@ -247,7 +256,7 @@ struct kvm_mmu_memory_cache {
* @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
*/
union kvm_mmu_page_role {
- unsigned word;
+ u32 word;
struct {
unsigned level:4;
unsigned cr4_pae:1;
@@ -273,6 +282,34 @@ union kvm_mmu_page_role {
};
};
+union kvm_mmu_extended_role {
+/*
+ * This structure complements kvm_mmu_page_role caching everything needed for
+ * MMU configuration. If nothing in both these structures changed, MMU
+ * re-configuration can be skipped. @valid bit is set on first usage so we don't
+ * treat all-zero structure as valid data.
+ */
+ u32 word;
+ struct {
+ unsigned int valid:1;
+ unsigned int execonly:1;
+ unsigned int cr0_pg:1;
+ unsigned int cr4_pse:1;
+ unsigned int cr4_pke:1;
+ unsigned int cr4_smap:1;
+ unsigned int cr4_smep:1;
+ unsigned int cr4_la57:1;
+ };
+};
+
+union kvm_mmu_role {
+ u64 as_u64;
+ struct {
+ union kvm_mmu_page_role base;
+ union kvm_mmu_extended_role ext;
+ };
+};
+
struct kvm_rmap_head {
unsigned long val;
};
@@ -280,18 +317,18 @@ struct kvm_rmap_head {
struct kvm_mmu_page {
struct list_head link;
struct hlist_node hash_link;
+ bool unsync;
/*
* The following two entries are used to key the shadow page in the
* hash table.
*/
- gfn_t gfn;
union kvm_mmu_page_role role;
+ gfn_t gfn;
u64 *spt;
/* hold the gfn of each spte inside spt */
gfn_t *gfns;
- bool unsync;
int root_count; /* Currently serving as active root */
unsigned int unsync_children;
struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
@@ -360,7 +397,7 @@ struct kvm_mmu {
void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
u64 *spte, const void *pte);
hpa_t root_hpa;
- union kvm_mmu_page_role base_role;
+ union kvm_mmu_role mmu_role;
u8 root_level;
u8 shadow_root_level;
u8 ept_ad;
@@ -490,7 +527,7 @@ struct kvm_vcpu_hv {
struct kvm_hyperv_exit exit;
struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
- cpumask_t tlb_lush;
+ cpumask_t tlb_flush;
};
struct kvm_vcpu_arch {
@@ -534,7 +571,13 @@ struct kvm_vcpu_arch {
* the paging mode of the l1 guest. This context is always used to
* handle faults.
*/
- struct kvm_mmu mmu;
+ struct kvm_mmu *mmu;
+
+ /* Non-nested MMU for L1 */
+ struct kvm_mmu root_mmu;
+
+ /* L1 MMU when running nested */
+ struct kvm_mmu guest_mmu;
/*
* Paging state of an L2 guest (used for nested npt)
@@ -585,6 +628,8 @@ struct kvm_vcpu_arch {
bool has_error_code;
u8 nr;
u32 error_code;
+ unsigned long payload;
+ bool has_payload;
u8 nested_apf;
} exception;
@@ -781,6 +826,9 @@ struct kvm_hv {
u64 hv_reenlightenment_control;
u64 hv_tsc_emulation_control;
u64 hv_tsc_emulation_status;
+
+ /* How many vCPUs have VP index != vCPU index */
+ atomic_t num_mismatched_vp_indexes;
};
enum kvm_irqchip_mode {
@@ -869,6 +917,9 @@ struct kvm_arch {
bool x2apic_format;
bool x2apic_broadcast_quirk_disabled;
+
+ bool guest_can_read_msr_platform_info;
+ bool exception_payload_enabled;
};
struct kvm_vm_stat {
@@ -1022,6 +1073,7 @@ struct kvm_x86_ops {
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
+ bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
@@ -1055,6 +1107,7 @@ struct kvm_x86_ops {
bool (*umip_emulated)(void);
int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
+ void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@@ -1129,6 +1182,9 @@ struct kvm_x86_ops {
int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*get_msr_feature)(struct kvm_msr_entry *entry);
+
+ int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version);
};
struct kvm_arch_async_pf {
@@ -1166,7 +1222,6 @@ void kvm_mmu_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_setup(struct kvm_vcpu *vcpu);
void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
@@ -1237,19 +1292,12 @@ enum emulation_result {
#define EMULTYPE_NO_DECODE (1 << 0)
#define EMULTYPE_TRAP_UD (1 << 1)
#define EMULTYPE_SKIP (1 << 2)
-#define EMULTYPE_RETRY (1 << 3)
-#define EMULTYPE_NO_REEXECUTE (1 << 4)
-#define EMULTYPE_NO_UD_ON_FAIL (1 << 5)
-#define EMULTYPE_VMWARE (1 << 6)
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
- int emulation_type, void *insn, int insn_len);
-
-static inline int emulate_instruction(struct kvm_vcpu *vcpu,
- int emulation_type)
-{
- return x86_emulate_instruction(vcpu, 0,
- emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
-}
+#define EMULTYPE_ALLOW_RETRY (1 << 3)
+#define EMULTYPE_NO_UD_ON_FAIL (1 << 4)
+#define EMULTYPE_VMWARE (1 << 5)
+int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
+int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
+ void *insn, int insn_len);
void kvm_enable_efer_bits(u64);
bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
@@ -1327,7 +1375,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free);
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ ulong roots_to_free);
gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
@@ -1450,7 +1499,6 @@ asmlinkage void kvm_spurious_fault(void);
____kvm_handle_fault_on_reboot(insn, "")
#define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
@@ -1463,7 +1511,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
- unsigned long ipi_bitmap_high, int min,
+ unsigned long ipi_bitmap_high, u32 min,
unsigned long icr, int op_64_bit);
u64 kvm_get_arch_capabilities(void);
@@ -1490,6 +1538,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
int kvm_is_in_guest(void);
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index c91083c59845..349a47acaa4a 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -53,7 +53,7 @@ static inline void local_sub(long i, local_t *l)
*/
static inline bool local_sub_and_test(long i, local_t *l)
{
- GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e);
+ return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i);
}
/**
@@ -66,7 +66,7 @@ static inline bool local_sub_and_test(long i, local_t *l)
*/
static inline bool local_dec_and_test(local_t *l)
{
- GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e);
+ return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e);
}
/**
@@ -79,7 +79,7 @@ static inline bool local_dec_and_test(local_t *l)
*/
static inline bool local_inc_and_test(local_t *l)
{
- GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e);
+ return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e);
}
/**
@@ -93,7 +93,7 @@ static inline bool local_inc_and_test(local_t *l)
*/
static inline bool local_add_negative(long i, local_t *l)
{
- GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s);
+ return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i);
}
/**
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 3a17107594c8..4da9b1c58d28 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -10,41 +10,44 @@
/* MCG_CAP register defines */
#define MCG_BANKCNT_MASK 0xff /* Number of Banks */
-#define MCG_CTL_P (1ULL<<8) /* MCG_CTL register available */
-#define MCG_EXT_P (1ULL<<9) /* Extended registers available */
-#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */
+#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */
+#define MCG_EXT_P BIT_ULL(9) /* Extended registers available */
+#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */
#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */
#define MCG_EXT_CNT_SHIFT 16
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
-#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
-#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */
-#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */
+#define MCG_SER_P BIT_ULL(24) /* MCA recovery/new status bits */
+#define MCG_ELOG_P BIT_ULL(26) /* Extended error log supported */
+#define MCG_LMCE_P BIT_ULL(27) /* Local machine check supported */
/* MCG_STATUS register defines */
-#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
-#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */
-#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */
-#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */
+#define MCG_STATUS_RIPV BIT_ULL(0) /* restart ip valid */
+#define MCG_STATUS_EIPV BIT_ULL(1) /* ip points to correct instruction */
+#define MCG_STATUS_MCIP BIT_ULL(2) /* machine check in progress */
+#define MCG_STATUS_LMCES BIT_ULL(3) /* LMCE signaled */
/* MCG_EXT_CTL register defines */
-#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
+#define MCG_EXT_CTL_LMCE_EN BIT_ULL(0) /* Enable LMCE */
/* MCi_STATUS register defines */
-#define MCI_STATUS_VAL (1ULL<<63) /* valid error */
-#define MCI_STATUS_OVER (1ULL<<62) /* previous errors lost */
-#define MCI_STATUS_UC (1ULL<<61) /* uncorrected error */
-#define MCI_STATUS_EN (1ULL<<60) /* error enabled */
-#define MCI_STATUS_MISCV (1ULL<<59) /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1ULL<<58) /* addr reg. valid */
-#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */
-#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
-#define MCI_STATUS_AR (1ULL<<55) /* Action required */
+#define MCI_STATUS_VAL BIT_ULL(63) /* valid error */
+#define MCI_STATUS_OVER BIT_ULL(62) /* previous errors lost */
+#define MCI_STATUS_UC BIT_ULL(61) /* uncorrected error */
+#define MCI_STATUS_EN BIT_ULL(60) /* error enabled */
+#define MCI_STATUS_MISCV BIT_ULL(59) /* misc error reg. valid */
+#define MCI_STATUS_ADDRV BIT_ULL(58) /* addr reg. valid */
+#define MCI_STATUS_PCC BIT_ULL(57) /* processor context corrupt */
+#define MCI_STATUS_S BIT_ULL(56) /* Signaled machine check */
+#define MCI_STATUS_AR BIT_ULL(55) /* Action required */
+#define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */
+#define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38)
+#define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT)
/* AMD-specific bits */
-#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */
-#define MCI_STATUS_SYNDV (1ULL<<53) /* synd reg. valid */
-#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */
-#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
+#define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */
+#define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */
+#define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */
+#define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */
/*
* McaX field if set indicates a given bank supports MCA extensions:
@@ -84,7 +87,7 @@
#define MCI_MISC_ADDR_GENERIC 7 /* generic */
/* CTL2 register defines */
-#define MCI_CTL2_CMCI_EN (1ULL << 30)
+#define MCI_CTL2_CMCI_EN BIT_ULL(30)
#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL
#define MCJ_CTX_MASK 3
@@ -214,6 +217,8 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
#endif
+static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
+
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c0643831706e..616f8e637bc3 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void);
+void __init mem_encrypt_free_decrypted_mem(void);
bool sme_active(void);
bool sev_active(void);
+#define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
+
#else /* !CONFIG_AMD_MEM_ENCRYPT */
#define sme_me_mask 0ULL
@@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0;
static inline int __init
early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
+#define __bss_decrypted
+
#endif /* CONFIG_AMD_MEM_ENCRYPT */
/*
@@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0;
#define __sme_pa(x) (__pa(x) | sme_me_mask)
#define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask)
+extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
+
#endif /* __ASSEMBLY__ */
#endif /* __X86_MEM_ENCRYPT_H__ */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index eeeb9289c764..0ca50611e8ce 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -16,12 +16,12 @@
extern atomic64_t last_mm_ctx_id;
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
}
-#endif /* !CONFIG_PARAVIRT */
+#endif /* !CONFIG_PARAVIRT_XXL */
#ifdef CONFIG_PERF_EVENTS
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index 61eb4b63c5ec..d0b1434fb0b6 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -57,8 +57,14 @@
#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
#define MPX_BNDSTA_ERROR_CODE 0x3
+struct mpx_fault_info {
+ void __user *addr;
+ void __user *lower;
+ void __user *upper;
+};
+
#ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs);
int mpx_handle_bd_fault(void);
static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
{
@@ -78,9 +84,9 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
unsigned long flags);
#else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
+static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
{
- return NULL;
+ return -EINVAL;
}
static inline int mpx_handle_bd_fault(void)
{
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f37704497d8f..0d6271cce198 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -351,6 +351,8 @@ int hyperv_flush_guest_mapping(u64 as);
#ifdef CONFIG_X86_64
void hv_apic_init(void);
+void __init hv_init_spinlocks(void);
+bool hv_vcpu_is_preempted(int vcpu);
#else
static inline void hv_apic_init(void) {}
#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4731f0cf97c5..80f4a4f38c79 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -164,6 +164,7 @@
#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9)
#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
+#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12)
#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14
#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 04addd6e0a4a..91e4cf189914 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -242,7 +242,7 @@ static inline unsigned long long native_read_pmc(int counter)
return EAX_EDX_VAL(val, low, high);
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#include <linux/errno.h>
@@ -305,7 +305,7 @@ do { \
#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
-#endif /* !CONFIG_PARAVIRT */
+#endif /* !CONFIG_PARAVIRT_XXL */
/*
* 64-bit version of wrmsr_safe():
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index fd2a8c1b88bc..80dc14422495 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -170,11 +170,15 @@
*/
# define CALL_NOSPEC \
ANNOTATE_NOSPEC_ALTERNATIVE \
- ALTERNATIVE( \
+ ALTERNATIVE_2( \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
"call __x86_indirect_thunk_%V[thunk_target]\n", \
- X86_FEATURE_RETPOLINE)
+ X86_FEATURE_RETPOLINE, \
+ "lfence;\n" \
+ ANNOTATE_RETPOLINE_SAFE \
+ "call *%[thunk_target]\n", \
+ X86_FEATURE_RETPOLINE_AMD)
# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
@@ -184,7 +188,8 @@
* here, anyway.
*/
# define CALL_NOSPEC \
- ALTERNATIVE( \
+ ANNOTATE_NOSPEC_ALTERNATIVE \
+ ALTERNATIVE_2( \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
" jmp 904f;\n" \
@@ -199,7 +204,11 @@
" ret;\n" \
" .align 16\n" \
"904: call 901b;\n", \
- X86_FEATURE_RETPOLINE)
+ X86_FEATURE_RETPOLINE, \
+ "lfence;\n" \
+ ANNOTATE_RETPOLINE_SAFE \
+ "call *%[thunk_target]\n", \
+ X86_FEATURE_RETPOLINE_AMD)
# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
#else /* No retpoline for C / inline asm */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 6afac386a434..cd0cf1c568b4 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -59,13 +59,16 @@
#endif
/*
- * Kernel image size is limited to 1GiB due to the fixmap living in the
- * next 1GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). Use
- * 512MiB by default, leaving 1.5GiB for modules once the page tables
- * are fully set up. If kernel ASLR is configured, it can extend the
- * kernel page table mapping, reducing the size of the modules area.
+ * Maximum kernel image size is limited to 1 GiB, due to the fixmap living
+ * in the next 1 GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S).
+ *
+ * On KASLR use 1 GiB by default, leaving 1 GiB for modules once the
+ * page tables are fully set up.
+ *
+ * If KASLR is disabled we can shrink it to 0.5 GiB and increase the size
+ * of the modules area to 1.5 GiB.
*/
-#if defined(CONFIG_RANDOMIZE_BASE)
+#ifdef CONFIG_RANDOMIZE_BASE
#define KERNEL_IMAGE_SIZE (1024 * 1024 * 1024)
#else
#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index e375d4266b53..4bf42f9e4eea 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -17,16 +17,73 @@
#include <linux/cpumask.h>
#include <asm/frame.h>
+static inline unsigned long long paravirt_sched_clock(void)
+{
+ return PVOP_CALL0(unsigned long long, time.sched_clock);
+}
+
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+ return PVOP_CALL1(u64, time.steal_clock, cpu);
+}
+
+/* The paravirtualized I/O functions */
+static inline void slow_down_io(void)
+{
+ pv_ops.cpu.io_delay();
+#ifdef REALLY_SLOW_IO
+ pv_ops.cpu.io_delay();
+ pv_ops.cpu.io_delay();
+ pv_ops.cpu.io_delay();
+#endif
+}
+
+static inline void __flush_tlb(void)
+{
+ PVOP_VCALL0(mmu.flush_tlb_user);
+}
+
+static inline void __flush_tlb_global(void)
+{
+ PVOP_VCALL0(mmu.flush_tlb_kernel);
+}
+
+static inline void __flush_tlb_one_user(unsigned long addr)
+{
+ PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
+}
+
+static inline void flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info)
+{
+ PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
+}
+
+static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+ PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
+}
+
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
+{
+ PVOP_VCALL1(mmu.exit_mmap, mm);
+}
+
+#ifdef CONFIG_PARAVIRT_XXL
static inline void load_sp0(unsigned long sp0)
{
- PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0);
+ PVOP_VCALL1(cpu.load_sp0, sp0);
}
/* The paravirtualized CPUID instruction. */
static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
- PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
+ PVOP_VCALL4(cpu.cpuid, eax, ebx, ecx, edx);
}
/*
@@ -34,98 +91,98 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
*/
static inline unsigned long paravirt_get_debugreg(int reg)
{
- return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
+ return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg);
}
#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
static inline void set_debugreg(unsigned long val, int reg)
{
- PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
+ PVOP_VCALL2(cpu.set_debugreg, reg, val);
}
static inline unsigned long read_cr0(void)
{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
+ return PVOP_CALL0(unsigned long, cpu.read_cr0);
}
static inline void write_cr0(unsigned long x)
{
- PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
+ PVOP_VCALL1(cpu.write_cr0, x);
}
static inline unsigned long read_cr2(void)
{
- return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
+ return PVOP_CALL0(unsigned long, mmu.read_cr2);
}
static inline void write_cr2(unsigned long x)
{
- PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
+ PVOP_VCALL1(mmu.write_cr2, x);
}
static inline unsigned long __read_cr3(void)
{
- return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
+ return PVOP_CALL0(unsigned long, mmu.read_cr3);
}
static inline void write_cr3(unsigned long x)
{
- PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
+ PVOP_VCALL1(mmu.write_cr3, x);
}
static inline void __write_cr4(unsigned long x)
{
- PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
+ PVOP_VCALL1(cpu.write_cr4, x);
}
#ifdef CONFIG_X86_64
static inline unsigned long read_cr8(void)
{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr8);
+ return PVOP_CALL0(unsigned long, cpu.read_cr8);
}
static inline void write_cr8(unsigned long x)
{
- PVOP_VCALL1(pv_cpu_ops.write_cr8, x);
+ PVOP_VCALL1(cpu.write_cr8, x);
}
#endif
static inline void arch_safe_halt(void)
{
- PVOP_VCALL0(pv_irq_ops.safe_halt);
+ PVOP_VCALL0(irq.safe_halt);
}
static inline void halt(void)
{
- PVOP_VCALL0(pv_irq_ops.halt);
+ PVOP_VCALL0(irq.halt);
}
static inline void wbinvd(void)
{
- PVOP_VCALL0(pv_cpu_ops.wbinvd);
+ PVOP_VCALL0(cpu.wbinvd);
}
#define get_kernel_rpl() (pv_info.kernel_rpl)
static inline u64 paravirt_read_msr(unsigned msr)
{
- return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr);
+ return PVOP_CALL1(u64, cpu.read_msr, msr);
}
static inline void paravirt_write_msr(unsigned msr,
unsigned low, unsigned high)
{
- PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high);
+ PVOP_VCALL3(cpu.write_msr, msr, low, high);
}
static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
{
- return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err);
+ return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err);
}
static inline int paravirt_write_msr_safe(unsigned msr,
unsigned low, unsigned high)
{
- return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high);
+ return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high);
}
#define rdmsr(msr, val1, val2) \
@@ -170,23 +227,9 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
return err;
}
-static inline unsigned long long paravirt_sched_clock(void)
-{
- return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
-}
-
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
-
-static inline u64 paravirt_steal_clock(int cpu)
-{
- return PVOP_CALL1(u64, pv_time_ops.steal_clock, cpu);
-}
-
static inline unsigned long long paravirt_read_pmc(int counter)
{
- return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
+ return PVOP_CALL1(u64, cpu.read_pmc, counter);
}
#define rdpmc(counter, low, high) \
@@ -200,166 +243,127 @@ do { \
static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
- PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
+ PVOP_VCALL2(cpu.alloc_ldt, ldt, entries);
}
static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
{
- PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
+ PVOP_VCALL2(cpu.free_ldt, ldt, entries);
}
static inline void load_TR_desc(void)
{
- PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
+ PVOP_VCALL0(cpu.load_tr_desc);
}
static inline void load_gdt(const struct desc_ptr *dtr)
{
- PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
+ PVOP_VCALL1(cpu.load_gdt, dtr);
}
static inline void load_idt(const struct desc_ptr *dtr)
{
- PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
+ PVOP_VCALL1(cpu.load_idt, dtr);
}
static inline void set_ldt(const void *addr, unsigned entries)
{
- PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
+ PVOP_VCALL2(cpu.set_ldt, addr, entries);
}
static inline unsigned long paravirt_store_tr(void)
{
- return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
+ return PVOP_CALL0(unsigned long, cpu.store_tr);
}
+
#define store_tr(tr) ((tr) = paravirt_store_tr())
static inline void load_TLS(struct thread_struct *t, unsigned cpu)
{
- PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
+ PVOP_VCALL2(cpu.load_tls, t, cpu);
}
#ifdef CONFIG_X86_64
static inline void load_gs_index(unsigned int gs)
{
- PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
+ PVOP_VCALL1(cpu.load_gs_index, gs);
}
#endif
static inline void write_ldt_entry(struct desc_struct *dt, int entry,
const void *desc)
{
- PVOP_VCALL3(pv_cpu_ops.write_ldt_entry, dt, entry, desc);
+ PVOP_VCALL3(cpu.write_ldt_entry, dt, entry, desc);
}
static inline void write_gdt_entry(struct desc_struct *dt, int entry,
void *desc, int type)
{
- PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, desc, type);
+ PVOP_VCALL4(cpu.write_gdt_entry, dt, entry, desc, type);
}
static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
{
- PVOP_VCALL3(pv_cpu_ops.write_idt_entry, dt, entry, g);
+ PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g);
}
static inline void set_iopl_mask(unsigned mask)
{
- PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
-}
-
-/* The paravirtualized I/O functions */
-static inline void slow_down_io(void)
-{
- pv_cpu_ops.io_delay();
-#ifdef REALLY_SLOW_IO
- pv_cpu_ops.io_delay();
- pv_cpu_ops.io_delay();
- pv_cpu_ops.io_delay();
-#endif
+ PVOP_VCALL1(cpu.set_iopl_mask, mask);
}
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
- PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
+ PVOP_VCALL2(mmu.activate_mm, prev, next);
}
static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
- PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
-}
-
-static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
-{
- PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
-}
-
-static inline void __flush_tlb(void)
-{
- PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
-}
-static inline void __flush_tlb_global(void)
-{
- PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
-}
-static inline void __flush_tlb_one_user(unsigned long addr)
-{
- PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr);
-}
-
-static inline void flush_tlb_others(const struct cpumask *cpumask,
- const struct flush_tlb_info *info)
-{
- PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info);
-}
-
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
- PVOP_VCALL2(pv_mmu_ops.tlb_remove_table, tlb, table);
+ PVOP_VCALL2(mmu.dup_mmap, oldmm, mm);
}
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
{
- return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
+ return PVOP_CALL1(int, mmu.pgd_alloc, mm);
}
static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
- PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
+ PVOP_VCALL2(mmu.pgd_free, mm, pgd);
}
static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_pte, mm, pfn);
}
static inline void paravirt_release_pte(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
+ PVOP_VCALL1(mmu.release_pte, pfn);
}
static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_pmd, mm, pfn);
}
static inline void paravirt_release_pmd(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
+ PVOP_VCALL1(mmu.release_pmd, pfn);
}
static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_pud, mm, pfn);
}
static inline void paravirt_release_pud(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
+ PVOP_VCALL1(mmu.release_pud, pfn);
}
static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)
{
- PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn);
+ PVOP_VCALL2(mmu.alloc_p4d, mm, pfn);
}
static inline void paravirt_release_p4d(unsigned long pfn)
{
- PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn);
+ PVOP_VCALL1(mmu.release_p4d, pfn);
}
static inline pte_t __pte(pteval_t val)
@@ -367,13 +371,9 @@ static inline pte_t __pte(pteval_t val)
pteval_t ret;
if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pteval_t,
- pv_mmu_ops.make_pte,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pteval_t,
- pv_mmu_ops.make_pte,
- val);
+ ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val);
return (pte_t) { .pte = ret };
}
@@ -383,11 +383,10 @@ static inline pteval_t pte_val(pte_t pte)
pteval_t ret;
if (sizeof(pteval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val,
+ ret = PVOP_CALLEE2(pteval_t, mmu.pte_val,
pte.pte, (u64)pte.pte >> 32);
else
- ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val,
- pte.pte);
+ ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
return ret;
}
@@ -397,11 +396,9 @@ static inline pgd_t __pgd(pgdval_t val)
pgdval_t ret;
if (sizeof(pgdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pgdval_t, mmu.make_pgd, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd,
- val);
+ ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val);
return (pgd_t) { ret };
}
@@ -411,11 +408,10 @@ static inline pgdval_t pgd_val(pgd_t pgd)
pgdval_t ret;
if (sizeof(pgdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val,
+ ret = PVOP_CALLEE2(pgdval_t, mmu.pgd_val,
pgd.pgd, (u64)pgd.pgd >> 32);
else
- ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val,
- pgd.pgd);
+ ret = PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
return ret;
}
@@ -426,8 +422,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long a
{
pteval_t ret;
- ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
- mm, addr, ptep);
+ ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep);
return (pte_t) { .pte = ret };
}
@@ -437,20 +432,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long a
{
if (sizeof(pteval_t) > sizeof(long))
/* 5 arg words */
- pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
+ pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte);
else
- PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
+ PVOP_VCALL4(mmu.ptep_modify_prot_commit,
mm, addr, ptep, pte.pte);
}
static inline void set_pte(pte_t *ptep, pte_t pte)
{
if (sizeof(pteval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_pte, ptep,
- pte.pte, (u64)pte.pte >> 32);
+ PVOP_VCALL3(mmu.set_pte, ptep, pte.pte, (u64)pte.pte >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_pte, ptep,
- pte.pte);
+ PVOP_VCALL2(mmu.set_pte, ptep, pte.pte);
}
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -458,9 +451,9 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
{
if (sizeof(pteval_t) > sizeof(long))
/* 5 arg words */
- pv_mmu_ops.set_pte_at(mm, addr, ptep, pte);
+ pv_ops.mmu.set_pte_at(mm, addr, ptep, pte);
else
- PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
+ PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte);
}
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
@@ -468,9 +461,9 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
pmdval_t val = native_pmd_val(pmd);
if (sizeof(pmdval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp, val, (u64)val >> 32);
+ PVOP_VCALL3(mmu.set_pmd, pmdp, val, (u64)val >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val);
+ PVOP_VCALL2(mmu.set_pmd, pmdp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 3
@@ -479,11 +472,9 @@ static inline pmd_t __pmd(pmdval_t val)
pmdval_t ret;
if (sizeof(pmdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd,
- val, (u64)val >> 32);
+ ret = PVOP_CALLEE2(pmdval_t, mmu.make_pmd, val, (u64)val >> 32);
else
- ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd,
- val);
+ ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val);
return (pmd_t) { ret };
}
@@ -493,11 +484,10 @@ static inline pmdval_t pmd_val(pmd_t pmd)
pmdval_t ret;
if (sizeof(pmdval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val,
+ ret = PVOP_CALLEE2(pmdval_t, mmu.pmd_val,
pmd.pmd, (u64)pmd.pmd >> 32);
else
- ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val,
- pmd.pmd);
+ ret = PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
return ret;
}
@@ -507,39 +497,23 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
pudval_t val = native_pud_val(pud);
if (sizeof(pudval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
- val, (u64)val >> 32);
+ PVOP_VCALL3(mmu.set_pud, pudp, val, (u64)val >> 32);
else
- PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
- val);
+ PVOP_VCALL2(mmu.set_pud, pudp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 4
static inline pud_t __pud(pudval_t val)
{
pudval_t ret;
- if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud,
- val, (u64)val >> 32);
- else
- ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud,
- val);
+ ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
return (pud_t) { ret };
}
static inline pudval_t pud_val(pud_t pud)
{
- pudval_t ret;
-
- if (sizeof(pudval_t) > sizeof(long))
- ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val,
- pud.pud, (u64)pud.pud >> 32);
- else
- ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val,
- pud.pud);
-
- return ret;
+ return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
}
static inline void pud_clear(pud_t *pudp)
@@ -551,31 +525,26 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
{
p4dval_t val = native_p4d_val(p4d);
- if (sizeof(p4dval_t) > sizeof(long))
- PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp,
- val, (u64)val >> 32);
- else
- PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp,
- val);
+ PVOP_VCALL2(mmu.set_p4d, p4dp, val);
}
#if CONFIG_PGTABLE_LEVELS >= 5
static inline p4d_t __p4d(p4dval_t val)
{
- p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val);
+ p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
return (p4d_t) { ret };
}
static inline p4dval_t p4d_val(p4d_t p4d)
{
- return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d);
+ return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
}
static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
{
- PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, native_pgd_val(pgd));
+ PVOP_VCALL2(mmu.set_pgd, pgdp, native_pgd_val(pgd));
}
#define set_pgd(pgdp, pgdval) do { \
@@ -606,19 +575,18 @@ static inline void p4d_clear(p4d_t *p4dp)
64-bit pte atomically */
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
{
- PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
- pte.pte, pte.pte >> 32);
+ PVOP_VCALL3(mmu.set_pte_atomic, ptep, pte.pte, pte.pte >> 32);
}
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
- PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
+ PVOP_VCALL3(mmu.pte_clear, mm, addr, ptep);
}
static inline void pmd_clear(pmd_t *pmdp)
{
- PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
+ PVOP_VCALL1(mmu.pmd_clear, pmdp);
}
#else /* !CONFIG_X86_PAE */
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
@@ -641,64 +609,68 @@ static inline void pmd_clear(pmd_t *pmdp)
#define __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(struct task_struct *prev)
{
- PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
+ PVOP_VCALL1(cpu.start_context_switch, prev);
}
static inline void arch_end_context_switch(struct task_struct *next)
{
- PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
+ PVOP_VCALL1(cpu.end_context_switch, next);
}
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
- PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter);
+ PVOP_VCALL0(mmu.lazy_mode.enter);
}
static inline void arch_leave_lazy_mmu_mode(void)
{
- PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
+ PVOP_VCALL0(mmu.lazy_mode.leave);
}
static inline void arch_flush_lazy_mmu_mode(void)
{
- PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+ PVOP_VCALL0(mmu.lazy_mode.flush);
}
static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
phys_addr_t phys, pgprot_t flags)
{
- pv_mmu_ops.set_fixmap(idx, phys, flags);
+ pv_ops.mmu.set_fixmap(idx, phys, flags);
}
+#endif
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
u32 val)
{
- PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+ PVOP_VCALL2(lock.queued_spin_lock_slowpath, lock, val);
}
static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
{
- PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+ PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
}
static __always_inline void pv_wait(u8 *ptr, u8 val)
{
- PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+ PVOP_VCALL2(lock.wait, ptr, val);
}
static __always_inline void pv_kick(int cpu)
{
- PVOP_VCALL1(pv_lock_ops.kick, cpu);
+ PVOP_VCALL1(lock.kick, cpu);
}
static __always_inline bool pv_vcpu_is_preempted(long cpu)
{
- return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu);
+ return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
}
+void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
+bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
+
#endif /* SMP && PARAVIRT_SPINLOCKS */
#ifdef CONFIG_X86_32
@@ -778,24 +750,25 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu)
#define __PV_IS_CALLEE_SAVE(func) \
((struct paravirt_callee_save) { func })
+#ifdef CONFIG_PARAVIRT_XXL
static inline notrace unsigned long arch_local_save_flags(void)
{
- return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
+ return PVOP_CALLEE0(unsigned long, irq.save_fl);
}
static inline notrace void arch_local_irq_restore(unsigned long f)
{
- PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
+ PVOP_VCALLEE1(irq.restore_fl, f);
}
static inline notrace void arch_local_irq_disable(void)
{
- PVOP_VCALLEE0(pv_irq_ops.irq_disable);
+ PVOP_VCALLEE0(irq.irq_disable);
}
static inline notrace void arch_local_irq_enable(void)
{
- PVOP_VCALLEE0(pv_irq_ops.irq_enable);
+ PVOP_VCALLEE0(irq.irq_enable);
}
static inline notrace unsigned long arch_local_irq_save(void)
@@ -806,6 +779,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
arch_local_irq_disable();
return f;
}
+#endif
/* Make sure as little as possible of this mess escapes. */
@@ -827,7 +801,7 @@ extern void default_banner(void);
#else /* __ASSEMBLY__ */
-#define _PVSITE(ptype, clobbers, ops, word, algn) \
+#define _PVSITE(ptype, ops, word, algn) \
771:; \
ops; \
772:; \
@@ -836,7 +810,6 @@ extern void default_banner(void);
word 771b; \
.byte ptype; \
.byte 772b-771b; \
- .short clobbers; \
.popsection
@@ -868,8 +841,8 @@ extern void default_banner(void);
COND_POP(set, CLBR_RCX, rcx); \
COND_POP(set, CLBR_RAX, rax)
-#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8)
-#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
+#define PARA_PATCH(off) ((off) / 8)
+#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
#else
#define PV_SAVE_REGS(set) \
@@ -883,46 +856,41 @@ extern void default_banner(void);
COND_POP(set, CLBR_EDI, edi); \
COND_POP(set, CLBR_EAX, eax)
-#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4)
-#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
+#define PARA_PATCH(off) ((off) / 4)
+#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4)
#define PARA_INDIRECT(addr) *%cs:addr
#endif
+#ifdef CONFIG_PARAVIRT_XXL
#define INTERRUPT_RETURN \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \
- ANNOTATE_RETPOLINE_SAFE; \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
+ PARA_SITE(PARA_PATCH(PV_CPU_iret), \
+ ANNOTATE_RETPOLINE_SAFE; \
+ jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
#define DISABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
+ PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \
+ ANNOTATE_RETPOLINE_SAFE; \
+ call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#define ENABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \
+ PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \
+ ANNOTATE_RETPOLINE_SAFE; \
+ call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
-#ifdef CONFIG_X86_32
-#define GET_CR0_INTO_EAX \
- push %ecx; push %edx; \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \
- pop %edx; pop %ecx
-#else /* !CONFIG_X86_32 */
-
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_PARAVIRT_XXL
/*
* If swapgs is used while the userspace stack is still current,
* there's no way to call a pvop. The PV replacement *must* be
* inlined, or the swapgs instruction must be trapped and emulated.
*/
#define SWAPGS_UNSAFE_STACK \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
- swapgs)
+ PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs)
/*
* Note: swapgs is very special, and in practise is either going to be
@@ -931,44 +899,51 @@ extern void default_banner(void);
* it.
*/
#define SWAPGS \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \
+ PARA_SITE(PARA_PATCH(PV_CPU_swapgs), \
+ ANNOTATE_RETPOLINE_SAFE; \
+ call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \
)
+#endif
#define GET_CR2_INTO_RAX \
ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);
+ call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);
+#ifdef CONFIG_PARAVIRT_XXL
#define USERGS_SYSRET64 \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \
- CLBR_NONE, \
- ANNOTATE_RETPOLINE_SAFE; \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
+ PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \
+ ANNOTATE_RETPOLINE_SAFE; \
+ jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
#ifdef CONFIG_DEBUG_ENTRY
#define SAVE_FLAGS(clobbers) \
- PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \
+ ANNOTATE_RETPOLINE_SAFE; \
+ call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#endif
+#endif
#endif /* CONFIG_X86_32 */
#endif /* __ASSEMBLY__ */
#else /* CONFIG_PARAVIRT */
# define default_banner x86_init_noop
+#endif /* !CONFIG_PARAVIRT */
+
#ifndef __ASSEMBLY__
+#ifndef CONFIG_PARAVIRT_XXL
static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
}
+#endif
+#ifndef CONFIG_PARAVIRT
static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
{
}
+#endif
#endif /* __ASSEMBLY__ */
-#endif /* !CONFIG_PARAVIRT */
#endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4b75acc23b30..fba54ca23b2a 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -66,12 +66,14 @@ struct paravirt_callee_save {
/* general info */
struct pv_info {
+#ifdef CONFIG_PARAVIRT_XXL
unsigned int kernel_rpl;
int shared_kernel_pmd;
#ifdef CONFIG_X86_64
u16 extra_user_64bit_cs; /* __USER_CS if none */
#endif
+#endif
const char *name;
};
@@ -85,17 +87,18 @@ struct pv_init_ops {
* the number of bytes of code generated, as we nop pad the
* rest in generic code.
*/
- unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
+ unsigned (*patch)(u8 type, void *insnbuf,
unsigned long addr, unsigned len);
} __no_randomize_layout;
-
+#ifdef CONFIG_PARAVIRT_XXL
struct pv_lazy_ops {
/* Set deferred update mode, used for batching operations. */
void (*enter)(void);
void (*leave)(void);
void (*flush)(void);
} __no_randomize_layout;
+#endif
struct pv_time_ops {
unsigned long long (*sched_clock)(void);
@@ -104,6 +107,9 @@ struct pv_time_ops {
struct pv_cpu_ops {
/* hooks for various privileged instructions */
+ void (*io_delay)(void);
+
+#ifdef CONFIG_PARAVIRT_XXL
unsigned long (*get_debugreg)(int regno);
void (*set_debugreg)(int regno, unsigned long value);
@@ -141,7 +147,6 @@ struct pv_cpu_ops {
void (*set_iopl_mask)(unsigned mask);
void (*wbinvd)(void);
- void (*io_delay)(void);
/* cpuid emulation, mostly so that caps bits can be disabled */
void (*cpuid)(unsigned int *eax, unsigned int *ebx,
@@ -176,9 +181,11 @@ struct pv_cpu_ops {
void (*start_context_switch)(struct task_struct *prev);
void (*end_context_switch)(struct task_struct *next);
+#endif
} __no_randomize_layout;
struct pv_irq_ops {
+#ifdef CONFIG_PARAVIRT_XXL
/*
* Get/set interrupt state. save_fl and restore_fl are only
* expected to use X86_EFLAGS_IF; all other bits
@@ -195,35 +202,34 @@ struct pv_irq_ops {
void (*safe_halt)(void);
void (*halt)(void);
-
+#endif
} __no_randomize_layout;
struct pv_mmu_ops {
+ /* TLB operations */
+ void (*flush_tlb_user)(void);
+ void (*flush_tlb_kernel)(void);
+ void (*flush_tlb_one_user)(unsigned long addr);
+ void (*flush_tlb_others)(const struct cpumask *cpus,
+ const struct flush_tlb_info *info);
+
+ void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
+
+ /* Hook for intercepting the destruction of an mm_struct. */
+ void (*exit_mmap)(struct mm_struct *mm);
+
+#ifdef CONFIG_PARAVIRT_XXL
unsigned long (*read_cr2)(void);
void (*write_cr2)(unsigned long);
unsigned long (*read_cr3)(void);
void (*write_cr3)(unsigned long);
- /*
- * Hooks for intercepting the creation/use/destruction of an
- * mm_struct.
- */
+ /* Hooks for intercepting the creation/use of an mm_struct. */
void (*activate_mm)(struct mm_struct *prev,
struct mm_struct *next);
void (*dup_mmap)(struct mm_struct *oldmm,
struct mm_struct *mm);
- void (*exit_mmap)(struct mm_struct *mm);
-
-
- /* TLB operations */
- void (*flush_tlb_user)(void);
- void (*flush_tlb_kernel)(void);
- void (*flush_tlb_one_user)(unsigned long addr);
- void (*flush_tlb_others)(const struct cpumask *cpus,
- const struct flush_tlb_info *info);
-
- void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
/* Hooks for allocating and freeing a pagetable top-level */
int (*pgd_alloc)(struct mm_struct *mm);
@@ -298,6 +304,7 @@ struct pv_mmu_ops {
an mfn. We can tell which is which from the index. */
void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
phys_addr_t phys, pgprot_t flags);
+#endif
} __no_randomize_layout;
struct arch_spinlock;
@@ -321,48 +328,31 @@ struct pv_lock_ops {
* number for each function using the offset which we use to indicate
* what to patch. */
struct paravirt_patch_template {
- struct pv_init_ops pv_init_ops;
- struct pv_time_ops pv_time_ops;
- struct pv_cpu_ops pv_cpu_ops;
- struct pv_irq_ops pv_irq_ops;
- struct pv_mmu_ops pv_mmu_ops;
- struct pv_lock_ops pv_lock_ops;
+ struct pv_init_ops init;
+ struct pv_time_ops time;
+ struct pv_cpu_ops cpu;
+ struct pv_irq_ops irq;
+ struct pv_mmu_ops mmu;
+ struct pv_lock_ops lock;
} __no_randomize_layout;
extern struct pv_info pv_info;
-extern struct pv_init_ops pv_init_ops;
-extern struct pv_time_ops pv_time_ops;
-extern struct pv_cpu_ops pv_cpu_ops;
-extern struct pv_irq_ops pv_irq_ops;
-extern struct pv_mmu_ops pv_mmu_ops;
-extern struct pv_lock_ops pv_lock_ops;
+extern struct paravirt_patch_template pv_ops;
#define PARAVIRT_PATCH(x) \
(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
#define paravirt_type(op) \
[paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \
- [paravirt_opptr] "i" (&(op))
+ [paravirt_opptr] "i" (&(pv_ops.op))
#define paravirt_clobber(clobber) \
[paravirt_clobber] "i" (clobber)
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type, clobber) \
- "771:\n\t" insn_string "\n" "772:\n" \
- ".pushsection .parainstructions,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR " 771b\n" \
- " .byte " type "\n" \
- " .byte 772b-771b\n" \
- " .short " clobber "\n" \
- ".popsection\n"
-
/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string) \
- _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
+#define paravirt_call \
+ "PARAVIRT_CALL type=\"%c[paravirt_typenum]\"" \
+ " clobber=\"%c[paravirt_clobber]\"" \
+ " pv_opptr=\"%c[paravirt_opptr]\";"
/* Simple instruction patching code. */
#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
@@ -373,34 +363,17 @@ extern struct pv_lock_ops pv_lock_ops;
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
-unsigned paravirt_patch_call(void *insnbuf,
- const void *target, u16 tgt_clobbers,
- unsigned long addr, u16 site_clobbers,
- unsigned len);
-unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
- unsigned long addr, unsigned len);
-unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
+unsigned paravirt_patch_default(u8 type, void *insnbuf,
unsigned long addr, unsigned len);
unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
const char *start, const char *end);
-unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
- unsigned long addr, unsigned len);
+unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len);
int paravirt_disable_iospace(void);
/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
-#define PARAVIRT_CALL \
- ANNOTATE_RETPOLINE_SAFE \
- "call *%c[paravirt_opptr];"
-
-/*
* These macros are intended to wrap calls through one of the paravirt
* ops structs, so that they can be later identified and patched at
* runtime.
@@ -510,9 +483,9 @@ int paravirt_disable_iospace(void);
#endif /* CONFIG_X86_32 */
#ifdef CONFIG_PARAVIRT_DEBUG
-#define PVOP_TEST_NULL(op) BUG_ON(op == NULL)
+#define PVOP_TEST_NULL(op) BUG_ON(pv_ops.op == NULL)
#else
-#define PVOP_TEST_NULL(op) ((void)op)
+#define PVOP_TEST_NULL(op) ((void)pv_ops.op)
#endif
#define PVOP_RETMASK(rettype) \
@@ -537,7 +510,7 @@ int paravirt_disable_iospace(void);
/* since this condition will never hold */ \
if (sizeof(rettype) > sizeof(unsigned long)) { \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -547,7 +520,7 @@ int paravirt_disable_iospace(void);
__ret = (rettype)((((u64)__edx) << 32) | __eax); \
} else { \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -574,7 +547,7 @@ int paravirt_disable_iospace(void);
PVOP_VCALL_ARGS; \
PVOP_TEST_NULL(op); \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -688,12 +661,31 @@ struct paravirt_patch_site {
u8 *instr; /* original instructions */
u8 instrtype; /* type of this instruction */
u8 len; /* length of original instruction */
- u16 clobbers; /* what registers you may clobber */
};
extern struct paravirt_patch_site __parainstructions[],
__parainstructions_end[];
+#else /* __ASSEMBLY__ */
+
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
+ */
+.macro PARAVIRT_CALL type:req clobber:req pv_opptr:req
+771: ANNOTATE_RETPOLINE_SAFE
+ call *\pv_opptr
+772: .pushsection .parainstructions,"a"
+ _ASM_ALIGN
+ _ASM_PTR 771b
+ .byte \type
+ .byte 772b-771b
+ .short \clobber
+ .popsection
+.endm
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e9202a0de8f0..1a19d11cfbbd 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -185,22 +185,22 @@ do { \
typeof(var) pfo_ret__; \
switch (sizeof(var)) { \
case 1: \
- asm(op "b "__percpu_arg(1)",%0" \
+ asm volatile(op "b "__percpu_arg(1)",%0"\
: "=q" (pfo_ret__) \
: "m" (var)); \
break; \
case 2: \
- asm(op "w "__percpu_arg(1)",%0" \
+ asm volatile(op "w "__percpu_arg(1)",%0"\
: "=r" (pfo_ret__) \
: "m" (var)); \
break; \
case 4: \
- asm(op "l "__percpu_arg(1)",%0" \
+ asm volatile(op "l "__percpu_arg(1)",%0"\
: "=r" (pfo_ret__) \
: "m" (var)); \
break; \
case 8: \
- asm(op "q "__percpu_arg(1)",%0" \
+ asm volatile(op "q "__percpu_arg(1)",%0"\
: "=r" (pfo_ret__) \
: "m" (var)); \
break; \
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f54082f4c8..8bdf74902293 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
#define INTEL_ARCH_EVENT_MASK \
(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
+#define AMD64_L3_SLICE_SHIFT 48
+#define AMD64_L3_SLICE_MASK \
+ ((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT 56
+#define AMD64_L3_THREAD_MASK \
+ ((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
#define X86_RAW_EVENT_MASK \
(ARCH_PERFMON_EVENTSEL_EVENT | \
ARCH_PERFMON_EVENTSEL_UMASK | \
@@ -270,6 +278,7 @@ struct perf_guest_switch_msr {
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
extern void perf_check_microcode(void);
+extern int x86_perf_rdpmc_index(struct perf_event *event);
#else
static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
{
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index fbd578daa66e..ec7f43327033 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -8,7 +8,7 @@
static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm)
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 24c6cf5f16b7..60d0f9015317 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte)
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
-#endif
*pmdp = pmd;
}
@@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
#ifdef CONFIG_SMP
static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
-#endif
return __pmd(xchg((pmdval_t *)xp, 0));
}
#else
@@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
#ifdef CONFIG_SMP
static inline pud_t native_pudp_get_and_clear(pud_t *xp)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
-#endif
return __pud(xchg((pudval_t *)xp, 0));
}
#else
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 858358a82b14..33845d36897c 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -20,7 +20,7 @@ typedef union {
} pte_t;
#endif /* !__ASSEMBLY__ */
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \
(pv_info.shared_kernel_pmd)))
#else
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index e4ffa565a69f..40616e805292 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -55,9 +55,9 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
extern pmdval_t early_pmd_flags;
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
-#else /* !CONFIG_PARAVIRT */
+#else /* !CONFIG_PARAVIRT_XXL */
#define set_pte(ptep, pte) native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
@@ -112,8 +112,7 @@ extern pmdval_t early_pmd_flags;
#define __pte(x) native_make_pte(x)
#define arch_end_context_switch(prev) do {} while(0)
-
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
/*
* The following only work if pte_present() is true.
@@ -1195,7 +1194,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
return xchg(pmdp, pmd);
} else {
pmd_t old = *pmdp;
- *pmdp = pmd;
+ WRITE_ONCE(*pmdp, pmd);
return old;
}
}
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index f773d5e6c8cc..9c85b54bf03c 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -14,6 +14,7 @@
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
+#include <asm/fixmap.h>
extern p4d_t level4_kernel_pgt[512];
extern p4d_t level4_ident_pgt[512];
@@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pmd_t level2_fixmap_pgt[512];
extern pmd_t level2_ident_pgt[512];
-extern pte_t level1_fixmap_pgt[512];
+extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
extern pgd_t init_top_pgt[];
#define swapper_pg_dir init_top_pgt
@@ -55,15 +56,15 @@ struct mm_struct;
void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte);
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
-static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep)
+static inline void native_set_pte(pte_t *ptep, pte_t pte)
{
- *ptep = native_make_pte(0);
+ WRITE_ONCE(*ptep, pte);
}
-static inline void native_set_pte(pte_t *ptep, pte_t pte)
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
{
- *ptep = pte;
+ native_set_pte(ptep, native_make_pte(0));
}
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
@@ -73,7 +74,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
- *pmdp = pmd;
+ WRITE_ONCE(*pmdp, pmd);
}
static inline void native_pmd_clear(pmd_t *pmd)
@@ -109,7 +110,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
- *pudp = pud;
+ WRITE_ONCE(*pudp, pud);
}
static inline void native_pud_clear(pud_t *pud)
@@ -137,13 +138,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
pgd_t pgd;
if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
- *p4dp = p4d;
+ WRITE_ONCE(*p4dp, p4d);
return;
}
pgd = native_make_pgd(native_p4d_val(p4d));
pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd);
- *p4dp = native_make_p4d(native_pgd_val(pgd));
+ WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd)));
}
static inline void native_p4d_clear(p4d_t *p4d)
@@ -153,7 +154,7 @@ static inline void native_p4d_clear(p4d_t *p4d)
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
- *pgdp = pti_set_user_pgtbl(pgdp, pgd);
+ WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd));
}
static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b64acb08a62b..106b7d0e2dae 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -124,7 +124,7 @@
*/
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \
- _PAGE_SOFT_DIRTY)
+ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
/*
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 7f2dbd91fc74..90cb2f36c042 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -88,7 +88,7 @@ static __always_inline void __preempt_count_sub(int val)
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
- GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
+ return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var]));
}
/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d53c54b842da..617805981cce 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -155,7 +155,8 @@ enum cpuid_regs_idx {
#define X86_VENDOR_CENTAUR 5
#define X86_VENDOR_TRANSMETA 7
#define X86_VENDOR_NSC 8
-#define X86_VENDOR_NUM 9
+#define X86_VENDOR_HYGON 9
+#define X86_VENDOR_NUM 10
#define X86_VENDOR_UNKNOWN 0xff
@@ -315,7 +316,13 @@ struct x86_hw_tss {
*/
u64 sp1;
+ /*
+ * Since Linux does not use ring 2, the 'sp2' slot is unused by
+ * hardware. entry_SYSCALL_64 uses it as scratch space to stash
+ * the user RSP value.
+ */
u64 sp2;
+
u64 reserved2;
u64 ist[7];
u32 reserved3;
@@ -578,7 +585,7 @@ static inline bool on_thread_stack(void)
current_stack_pointer) < THREAD_SIZE;
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
#define __cpuid native_cpuid
@@ -589,7 +596,7 @@ static inline void load_sp0(unsigned long sp0)
}
#define set_iopl_mask native_set_iopl_mask
-#endif /* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6de1fd3d0097..143c99499531 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -37,8 +37,10 @@ struct pt_regs {
unsigned short __esh;
unsigned short fs;
unsigned short __fsh;
+ /* On interrupt, gs and __gsh store the vector number. */
unsigned short gs;
unsigned short __gsh;
+ /* On interrupt, this is the error code. */
unsigned long orig_ax;
unsigned long ip;
unsigned short cs;
@@ -144,7 +146,7 @@ static inline int v8086_mode(struct pt_regs *regs)
static inline bool user_64bit_mode(struct pt_regs *regs)
{
#ifdef CONFIG_X86_64
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
/*
* On non-paravirt systems, this is the only long mode CPL 3
* selector. We do not allow long mode selectors in the LDT.
@@ -237,23 +239,51 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs,
}
/**
+ * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack
+ * @regs: pt_regs which contains kernel stack pointer.
+ * @n: stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns the address of the @n th entry of the
+ * kernel stack which is specified by @regs. If the @n th entry is NOT in
+ * the kernel stack, this returns NULL.
+ */
+static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n)
+{
+ unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+ addr += n;
+ if (regs_within_kernel_stack(regs, (unsigned long)addr))
+ return addr;
+ else
+ return NULL;
+}
+
+/* To avoid include hell, we can't include uaccess.h */
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+
+/**
* regs_get_kernel_stack_nth() - get Nth entry of the stack
* @regs: pt_regs which contains kernel stack pointer.
* @n: stack entry number.
*
* regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
- * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack
* this returns 0.
*/
static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
unsigned int n)
{
- unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
- addr += n;
- if (regs_within_kernel_stack(regs, (unsigned long)addr))
- return *addr;
- else
- return 0;
+ unsigned long *addr;
+ unsigned long val;
+ long ret;
+
+ addr = regs_get_kernel_stack_nth_addr(regs, n);
+ if (addr) {
+ ret = probe_kernel_read(&val, addr, sizeof(val));
+ if (!ret)
+ return val;
+ }
+ return 0;
}
#define arch_has_single_step() (1)
@@ -263,7 +293,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
#define arch_has_block_step() (boot_cpu_data.x86 >= 6)
#endif
-#define ARCH_HAS_USER_SINGLE_STEP_INFO
+#define ARCH_HAS_USER_SINGLE_STEP_REPORT
/*
* When hitting ptrace_stop(), we cannot return using SYSRET because
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 3e70bed8a978..87623c6b13db 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -6,9 +6,24 @@
#include <asm/cpufeature.h>
#include <asm-generic/qspinlock_types.h>
#include <asm/paravirt.h>
+#include <asm/rmwcc.h>
#define _Q_PENDING_LOOPS (1 << 9)
+#define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire
+static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
+{
+ u32 val = 0;
+
+ if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c,
+ "I", _Q_PENDING_OFFSET))
+ val |= _Q_PENDING_VAL;
+
+ val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK;
+
+ return val;
+}
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
extern void __pv_init_lock_hash(void);
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 19b90521954c..a8b5e1e13319 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -4,6 +4,41 @@
* x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
* PaX/grsecurity.
*/
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/bug.h>
+
+.macro REFCOUNT_EXCEPTION counter:req
+ .pushsection .text..refcount
+111: lea \counter, %_ASM_CX
+112: ud2
+ ASM_UNREACHABLE
+ .popsection
+113: _ASM_EXTABLE_REFCOUNT(112b, 113b)
+.endm
+
+/* Trigger refcount exception if refcount result is negative. */
+.macro REFCOUNT_CHECK_LT_ZERO counter:req
+ js 111f
+ REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+/* Trigger refcount exception if refcount result is zero or negative. */
+.macro REFCOUNT_CHECK_LE_ZERO counter:req
+ jz 111f
+ REFCOUNT_CHECK_LT_ZERO counter="\counter"
+.endm
+
+/* Trigger refcount exception unconditionally. */
+.macro REFCOUNT_ERROR counter:req
+ jmp 111f
+ REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+#else /* __ASSEMBLY__ */
+
#include <linux/refcount.h>
#include <asm/bug.h>
@@ -15,34 +50,11 @@
* central refcount exception. The fixup address for the exception points
* back to the regular execution flow in .text.
*/
-#define _REFCOUNT_EXCEPTION \
- ".pushsection .text..refcount\n" \
- "111:\tlea %[counter], %%" _ASM_CX "\n" \
- "112:\t" ASM_UD2 "\n" \
- ASM_UNREACHABLE \
- ".popsection\n" \
- "113:\n" \
- _ASM_EXTABLE_REFCOUNT(112b, 113b)
-
-/* Trigger refcount exception if refcount result is negative. */
-#define REFCOUNT_CHECK_LT_ZERO \
- "js 111f\n\t" \
- _REFCOUNT_EXCEPTION
-
-/* Trigger refcount exception if refcount result is zero or negative. */
-#define REFCOUNT_CHECK_LE_ZERO \
- "jz 111f\n\t" \
- REFCOUNT_CHECK_LT_ZERO
-
-/* Trigger refcount exception unconditionally. */
-#define REFCOUNT_ERROR \
- "jmp 111f\n\t" \
- _REFCOUNT_EXCEPTION
static __always_inline void refcount_add(unsigned int i, refcount_t *r)
{
asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
- REFCOUNT_CHECK_LT_ZERO
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: "ir" (i)
: "cc", "cx");
@@ -51,7 +63,7 @@ static __always_inline void refcount_add(unsigned int i, refcount_t *r)
static __always_inline void refcount_inc(refcount_t *r)
{
asm volatile(LOCK_PREFIX "incl %0\n\t"
- REFCOUNT_CHECK_LT_ZERO
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: : "cc", "cx");
}
@@ -59,7 +71,7 @@ static __always_inline void refcount_inc(refcount_t *r)
static __always_inline void refcount_dec(refcount_t *r)
{
asm volatile(LOCK_PREFIX "decl %0\n\t"
- REFCOUNT_CHECK_LE_ZERO
+ "REFCOUNT_CHECK_LE_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: : "cc", "cx");
}
@@ -67,14 +79,17 @@ static __always_inline void refcount_dec(refcount_t *r)
static __always_inline __must_check
bool refcount_sub_and_test(unsigned int i, refcount_t *r)
{
- GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
- r->refs.counter, "er", i, "%0", e, "cx");
+
+ return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[var]\"",
+ r->refs.counter, e, "er", i, "cx");
}
static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
- GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
- r->refs.counter, "%0", e, "cx");
+ return GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[var]\"",
+ r->refs.counter, e, "cx");
}
static __always_inline __must_check
@@ -91,7 +106,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
/* Did we try to increment from/to an undesirable state? */
if (unlikely(c < 0 || c == INT_MAX || result < c)) {
- asm volatile(REFCOUNT_ERROR
+ asm volatile("REFCOUNT_ERROR counter=\"%[counter]\""
: : [counter] "m" (r->refs.counter)
: "cc", "cx");
break;
@@ -107,4 +122,6 @@ static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
return refcount_add_not_zero(1, r);
}
+#endif /* __ASSEMBLY__ */
+
#endif
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4914a3e7c803..46ac84b506f5 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -2,56 +2,69 @@
#ifndef _ASM_X86_RMWcc
#define _ASM_X86_RMWcc
+/* This counts to 12. Any more, it will return 13th argument. */
+#define __RMWcc_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
+#define RMWcc_ARGS(X...) __RMWcc_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __RMWcc_CONCAT(a, b) a ## b
+#define RMWcc_CONCAT(a, b) __RMWcc_CONCAT(a, b)
+
#define __CLOBBERS_MEM(clb...) "memory", ## clb
#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
/* Use asm goto */
-#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \
-do { \
+#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
+({ \
+ bool c = false; \
asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \
- : : [counter] "m" (var), ## __VA_ARGS__ \
+ : : [var] "m" (_var), ## __VA_ARGS__ \
: clobbers : cc_label); \
- return 0; \
-cc_label: \
- return 1; \
-} while (0)
-
-#define __BINARY_RMWcc_ARG " %1, "
-
+ if (0) { \
+cc_label: c = true; \
+ } \
+ c; \
+})
#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
/* Use flags output or a set instruction */
-#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \
-do { \
+#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
+({ \
bool c; \
asm volatile (fullop CC_SET(cc) \
- : [counter] "+m" (var), CC_OUT(cc) (c) \
+ : [var] "+m" (_var), CC_OUT(cc) (c) \
: __VA_ARGS__ : clobbers); \
- return c; \
-} while (0)
-
-#define __BINARY_RMWcc_ARG " %2, "
+ c; \
+})
#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
-#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+#define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \
__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
-#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\
- __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \
- __CLOBBERS_MEM(clobbers))
+#define GEN_UNARY_RMWcc_3(op, var, cc) \
+ GEN_UNARY_RMWcc_4(op, var, cc, "%[var]")
-#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
- __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \
- __CLOBBERS_MEM(), vcon (val))
+#define GEN_UNARY_RMWcc(X...) RMWcc_CONCAT(GEN_UNARY_RMWcc_, RMWcc_ARGS(X))(X)
+
+#define GEN_BINARY_RMWcc_6(op, var, cc, vcon, _val, arg0) \
+ __GEN_RMWcc(op " %[val], " arg0, var, cc, \
+ __CLOBBERS_MEM(), [val] vcon (_val))
+
+#define GEN_BINARY_RMWcc_5(op, var, cc, vcon, val) \
+ GEN_BINARY_RMWcc_6(op, var, cc, vcon, val, "%[var]")
+
+#define GEN_BINARY_RMWcc(X...) RMWcc_CONCAT(GEN_BINARY_RMWcc_, RMWcc_ARGS(X))(X)
+
+#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, cc, clobbers...) \
+ __GEN_RMWcc(op " %[var]\n\t" suffix, var, cc, \
+ __CLOBBERS_MEM(clobbers))
-#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \
- clobbers...) \
- __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \
- __CLOBBERS_MEM(clobbers), vcon (val))
+#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, cc, vcon, _val, clobbers...)\
+ __GEN_RMWcc(op " %[val], %[var]\n\t" suffix, var, cc, \
+ __CLOBBERS_MEM(clobbers), [val] vcon (_val))
#endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 4a911a382ade..8ea1cfdbeabc 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -11,7 +11,6 @@ extern char __end_rodata_aligned[];
#if defined(CONFIG_X86_64)
extern char __end_rodata_hpage_align[];
-extern char __entry_trampoline_start[], __entry_trampoline_end[];
#endif
#endif /* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index e293c122d0d5..ac3892920419 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -186,8 +186,7 @@
#define GDT_ENTRY_TLS_MIN 12
#define GDT_ENTRY_TLS_MAX 14
-/* Abused to load per CPU data from limit */
-#define GDT_ENTRY_PER_CPU 15
+#define GDT_ENTRY_CPUNODE 15
/*
* Number of entries in the GDT table:
@@ -207,11 +206,11 @@
#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3)
#define __USER32_DS __USER_DS
#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3)
-#define __PER_CPU_SEG (GDT_ENTRY_PER_CPU*8 + 3)
+#define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3)
#endif
-#ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PARAVIRT_XXL
# define get_kernel_rpl() 0
#endif
@@ -225,6 +224,47 @@
#define GDT_ENTRY_TLS_ENTRIES 3
#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8)
+#ifdef CONFIG_X86_64
+
+/* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */
+#define VDSO_CPUNODE_BITS 12
+#define VDSO_CPUNODE_MASK 0xfff
+
+#ifndef __ASSEMBLY__
+
+/* Helper functions to store/load CPU and node numbers */
+
+static inline unsigned long vdso_encode_cpunode(int cpu, unsigned long node)
+{
+ return (node << VDSO_CPUNODE_BITS) | cpu;
+}
+
+static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
+{
+ unsigned int p;
+
+ /*
+ * Load CPU and node number from the GDT. LSL is faster than RDTSCP
+ * and works on all CPUs. This is volatile so that it orders
+ * correctly with respect to barrier() and to keep GCC from cleverly
+ * hoisting it out of the calling function.
+ *
+ * If RDPID is available, use it.
+ */
+ alternative_io ("lsl %[seg],%[p]",
+ ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
+ X86_FEATURE_RDPID,
+ [p] "=a" (p), [seg] "r" (__CPUNODE_SEG));
+
+ if (cpu)
+ *cpu = (p & VDSO_CPUNODE_MASK);
+ if (node)
+ *node = (p >> VDSO_CPUNODE_BITS);
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* CONFIG_X86_64 */
+
#ifdef __KERNEL__
/*
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 317fc59b512c..43c029cdc3fe 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -141,7 +141,7 @@ static inline unsigned long __read_cr4(void)
return native_read_cr4();
}
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/paravirt.h>
#else
@@ -208,7 +208,7 @@ static inline void load_gs_index(unsigned selector)
#endif
-#endif/* CONFIG_PARAVIRT */
+#endif /* CONFIG_PARAVIRT_XXL */
static inline void clflush(volatile void *__p)
{
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index d33f92b9fa22..7ad41bfcc16c 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -149,7 +149,25 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt)
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
#define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
-void memcpy_flushcache(void *dst, const void *src, size_t cnt);
+void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
+static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+{
+ if (__builtin_constant_p(cnt)) {
+ switch (cnt) {
+ case 4:
+ asm ("movntil %1, %0" : "=m"(*(u32 *)dst) : "r"(*(u32 *)src));
+ return;
+ case 8:
+ asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
+ return;
+ case 16:
+ asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
+ asm ("movntiq %1, %0" : "=m"(*(u64 *)(dst + 8)) : "r"(*(u64 *)(src + 8)));
+ return;
+ }
+ }
+ __memcpy_flushcache(dst, src, cnt);
+}
#endif
#endif /* __KERNEL__ */
diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h
index ecffe81ff65c..a892494ca5e4 100644
--- a/arch/x86/include/asm/suspend.h
+++ b/arch/x86/include/asm/suspend.h
@@ -4,3 +4,11 @@
#else
# include <asm/suspend_64.h>
#endif
+extern unsigned long restore_jump_address __visible;
+extern unsigned long jump_address_phys;
+extern unsigned long restore_cr3 __visible;
+extern unsigned long temp_pgt __visible;
+extern unsigned long relocated_restore_code __visible;
+extern int relocate_restore_code(void);
+/* Defined in hibernate_asm_32/64.S */
+extern asmlinkage __visible int restore_image(void);
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 8be6afb58471..fdbd9d7b7bca 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -32,4 +32,8 @@ struct saved_context {
unsigned long return_address;
} __attribute__((packed));
+/* routines for saving/restoring kernel state */
+extern char core_restore_code[];
+extern char restore_registers[];
+
#endif /* _ASM_X86_SUSPEND_32_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index cb0a1f470980..404b8b1d44f5 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,16 +6,23 @@
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) \
-{ \
- if (!tlb->fullmm && !tlb->need_flush_all) \
- flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \
- else \
- flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \
-}
+static inline void tlb_flush(struct mmu_gather *tlb);
#include <asm-generic/tlb.h>
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ unsigned long start = 0UL, end = TLB_FLUSH_ALL;
+ unsigned int stride_shift = tlb_get_unmap_shift(tlb);
+
+ if (!tlb->fullmm && !tlb->need_flush_all) {
+ start = tlb->start;
+ end = tlb->end;
+ }
+
+ flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables);
+}
+
/*
* While x86 architecture in general requires an IPI to perform TLB
* shootdown, enablement code for several hypervisors overrides
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 58ce5288878e..323a313947e0 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
#endif
-static inline bool tlb_defer_switch_to_init_mm(void)
-{
- /*
- * If we have PCID, then switching to init_mm is reasonably
- * fast. If we don't have PCID, then switching to init_mm is
- * quite slow, so we try to defer it in the hopes that we can
- * avoid it entirely. The latter approach runs the risk of
- * receiving otherwise unnecessary IPIs.
- *
- * This choice is just a heuristic. The tlb code can handle this
- * function returning true or false regardless of whether we have
- * PCID.
- */
- return !static_cpu_has(X86_FEATURE_PCID);
-}
-
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
@@ -547,23 +531,30 @@ struct flush_tlb_info {
unsigned long start;
unsigned long end;
u64 new_tlb_gen;
+ unsigned int stride_shift;
+ bool freed_tables;
};
#define local_flush_tlb() __flush_tlb()
-#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
+#define flush_tlb_mm(mm) \
+ flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL, true)
-#define flush_tlb_range(vma, start, end) \
- flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
+#define flush_tlb_range(vma, start, end) \
+ flush_tlb_mm_range((vma)->vm_mm, start, end, \
+ ((vma)->vm_flags & VM_HUGETLB) \
+ ? huge_page_shift(hstate_vma(vma)) \
+ : PAGE_SHIFT, false)
extern void flush_tlb_all(void);
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
- unsigned long end, unsigned long vmflag);
+ unsigned long end, unsigned int stride_shift,
+ bool freed_tables);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
{
- flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+ flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
}
void native_flush_tlb_others(const struct cpumask *cpumask,
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
index 7bd92db09e8d..54133017267c 100644
--- a/arch/x86/include/asm/trace/mpx.h
+++ b/arch/x86/include/asm/trace/mpx.h
@@ -11,12 +11,12 @@
TRACE_EVENT(mpx_bounds_register_exception,
- TP_PROTO(void *addr_referenced,
+ TP_PROTO(void __user *addr_referenced,
const struct mpx_bndreg *bndreg),
TP_ARGS(addr_referenced, bndreg),
TP_STRUCT__entry(
- __field(void *, addr_referenced)
+ __field(void __user *, addr_referenced)
__field(u64, lower_bound)
__field(u64, upper_bound)
),
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index aae77eb8491c..b5e58cc0c5e7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -198,8 +198,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
"4: movl %3,%0\n" \
" jmp 3b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=r" (err) \
: "A" (x), "r" (addr), "i" (errret), "0" (err))
@@ -340,8 +340,8 @@ do { \
" xorl %%edx,%%edx\n" \
" jmp 3b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=r" (retval), "=&A"(x) \
: "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
@@ -386,7 +386,7 @@ do { \
" xor"itype" %"rtype"1,%"rtype"1\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
@@ -398,7 +398,7 @@ do { \
"3: mov %3,%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
@@ -474,7 +474,7 @@ struct __large_struct { unsigned long buf[100]; };
"3: mov %3,%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r"(err) \
: ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
@@ -602,7 +602,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "q" (__new), "1" (__old) \
: "memory" \
@@ -618,7 +618,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
@@ -634,7 +634,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
@@ -653,7 +653,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 51c4eee00732..dc4ed8bc2382 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -24,6 +24,7 @@
# include <asm/unistd_64.h>
# include <asm/unistd_64_x32.h>
# define __ARCH_WANT_COMPAT_SYS_TIME
+# define __ARCH_WANT_SYS_UTIME32
# define __ARCH_WANT_COMPAT_SYS_PREADV64
# define __ARCH_WANT_COMPAT_SYS_PWRITEV64
# define __ARCH_WANT_COMPAT_SYS_PREADV64V2
@@ -31,13 +32,13 @@
# endif
+# define __ARCH_WANT_NEW_STAT
# define __ARCH_WANT_OLD_READDIR
# define __ARCH_WANT_OLD_STAT
# define __ARCH_WANT_SYS_ALARM
# define __ARCH_WANT_SYS_FADVISE64
# define __ARCH_WANT_SYS_GETHOSTNAME
# define __ARCH_WANT_SYS_GETPGRP
-# define __ARCH_WANT_SYS_LLSEEK
# define __ARCH_WANT_SYS_NICE
# define __ARCH_WANT_SYS_OLDUMOUNT
# define __ARCH_WANT_SYS_OLD_GETRLIMIT
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index a80c0673798f..e60c45fd3679 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -10,8 +10,13 @@ struct cpumask;
struct mm_struct;
#ifdef CONFIG_X86_UV
+#include <linux/efi.h>
extern enum uv_system_type get_uv_system_type(void);
+static inline bool is_early_uv_system(void)
+{
+ return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab);
+}
extern int is_uv_system(void);
extern int is_uv_hubless(void);
extern void uv_cpu_init(void);
@@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
#else /* X86_UV */
static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline bool is_early_uv_system(void) { return 0; }
static inline int is_uv_system(void) { return 0; }
static inline int is_uv_hubless(void) { return 0; }
static inline void uv_cpu_init(void) { }
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 53748541c487..913a133f8e6f 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -5,33 +5,46 @@
#include <linux/compiler.h>
#include <linux/clocksource.h>
+#include <uapi/linux/time.h>
+
#ifdef BUILD_VDSO32_64
typedef u64 gtod_long_t;
#else
typedef unsigned long gtod_long_t;
#endif
+
+/*
+ * There is one of these objects in the vvar page for each
+ * vDSO-accelerated clockid. For high-resolution clocks, this encodes
+ * the time corresponding to vsyscall_gtod_data.cycle_last. For coarse
+ * clocks, this encodes the actual time.
+ *
+ * To confuse the reader, for high-resolution clocks, nsec is left-shifted
+ * by vsyscall_gtod_data.shift.
+ */
+struct vgtod_ts {
+ u64 sec;
+ u64 nsec;
+};
+
+#define VGTOD_BASES (CLOCK_TAI + 1)
+#define VGTOD_HRES (BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
+#define VGTOD_COARSE (BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
+
/*
* vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
* so be carefull by modifying this structure.
*/
struct vsyscall_gtod_data {
- unsigned seq;
-
- int vclock_mode;
- u64 cycle_last;
- u64 mask;
- u32 mult;
- u32 shift;
-
- /* open coded 'struct timespec' */
- u64 wall_time_snsec;
- gtod_long_t wall_time_sec;
- gtod_long_t monotonic_time_sec;
- u64 monotonic_time_snsec;
- gtod_long_t wall_time_coarse_sec;
- gtod_long_t wall_time_coarse_nsec;
- gtod_long_t monotonic_time_coarse_sec;
- gtod_long_t monotonic_time_coarse_nsec;
+ unsigned int seq;
+
+ int vclock_mode;
+ u64 cycle_last;
+ u64 mask;
+ u32 mult;
+ u32 shift;
+
+ struct vgtod_ts basetime[VGTOD_BASES];
int tz_minuteswest;
int tz_dsttime;
@@ -44,9 +57,9 @@ static inline bool vclock_was_used(int vclock)
return READ_ONCE(vclocks_used) & (1 << vclock);
}
-static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
+static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s)
{
- unsigned ret;
+ unsigned int ret;
repeat:
ret = READ_ONCE(s->seq);
@@ -59,7 +72,7 @@ repeat:
}
static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
- unsigned start)
+ unsigned int start)
{
smp_rmb();
return unlikely(s->seq != start);
@@ -77,30 +90,4 @@ static inline void gtod_write_end(struct vsyscall_gtod_data *s)
++s->seq;
}
-#ifdef CONFIG_X86_64
-
-#define VGETCPU_CPU_MASK 0xfff
-
-static inline unsigned int __getcpu(void)
-{
- unsigned int p;
-
- /*
- * Load per CPU data from GDT. LSL is faster than RDTSCP and
- * works on all CPUs. This is volatile so that it orders
- * correctly wrt barrier() and to keep gcc from cleverly
- * hoisting it out of the calling function.
- *
- * If RDPID is available, use it.
- */
- alternative_io ("lsl %[seg],%[p]",
- ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
- X86_FEATURE_RDPID,
- [p] "=a" (p), [seg] "r" (__PER_CPU_SEG));
-
- return p;
-}
-
-#endif /* CONFIG_X86_64 */
-
#endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 0116b2ee9e64..1fc7a0d1e877 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -40,7 +40,7 @@ static inline int cpu_has_vmx(void)
*/
static inline void cpu_vmxoff(void)
{
- asm volatile (ASM_VMX_VMXOFF : : : "cc");
+ asm volatile ("vmxoff");
cr4_clear_bits(X86_CR4_VMXE);
}
@@ -83,9 +83,10 @@ static inline void cpu_emergency_vmxoff(void)
*/
static inline int cpu_has_svm(const char **msg)
{
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
if (msg)
- *msg = "not amd";
+ *msg = "not amd or hygon";
return 0;
}
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9527ba5d62da..ade0f153947d 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -503,19 +503,6 @@ enum vmcs_field {
#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul
-
-#define ASM_VMX_VMCLEAR_RAX ".byte 0x66, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMLAUNCH ".byte 0x0f, 0x01, 0xc2"
-#define ASM_VMX_VMRESUME ".byte 0x0f, 0x01, 0xc3"
-#define ASM_VMX_VMPTRLD_RAX ".byte 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMREAD_RDX_RAX ".byte 0x0f, 0x78, 0xd0"
-#define ASM_VMX_VMWRITE_RAX_RDX ".byte 0x0f, 0x79, 0xd0"
-#define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4"
-#define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4"
-#define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_INVEPT ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
-#define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
-
struct vmx_msr_entry {
u32 index;
u32 reserved;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index b85a7c54c6a1..0f842104862c 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -303,4 +303,6 @@ extern void x86_init_noop(void);
extern void x86_init_uint_noop(unsigned int unused);
extern bool x86_pnpbios_disabled(void);
+void x86_verify_bootdata_version(void);
+
#endif
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index d383140e1dc8..068d9b067c83 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_XEN_EVENTS_H
#define _ASM_X86_XEN_EVENTS_H
+#include <xen/xen.h>
+
enum ipi_vector {
XEN_RESCHEDULE_VECTOR,
XEN_CALL_FUNCTION_VECTOR,
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index a06cbf019744..22f89d040ddd 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -16,6 +16,9 @@
#define RAMDISK_PROMPT_FLAG 0x8000
#define RAMDISK_LOAD_FLAG 0x4000
+/* version flags */
+#define VERSION_WRITTEN 0x8000
+
/* loadflags */
#define LOADED_HIGH (1<<0)
#define KASLR_FLAG (1<<1)
@@ -86,6 +89,7 @@ struct setup_header {
__u64 pref_address;
__u32 init_size;
__u32 handover_offset;
+ __u64 acpi_rsdp_addr;
} __attribute__((packed));
struct sys_desc_table {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..dabfcf7c3941 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -299,7 +300,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ __u8 pending;
__u32 error_code;
} exception;
struct {
@@ -322,7 +323,9 @@ struct kvm_vcpu_events {
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
- __u32 reserved[9];
+ __u8 reserved[27];
+ __u8 exception_has_payload;
+ __u64 exception_payload;
};
/* for KVM_GET/SET_DEBUGREGS */
@@ -377,9 +380,11 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
+#define KVM_STATE_NESTED_EVMCS 0x00000004
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
diff --git a/arch/x86/include/uapi/asm/siginfo.h b/arch/x86/include/uapi/asm/siginfo.h
index b3d157957177..6642d8be40c4 100644
--- a/arch/x86/include/uapi/asm/siginfo.h
+++ b/arch/x86/include/uapi/asm/siginfo.h
@@ -7,8 +7,6 @@
typedef long long __kernel_si_clock_t __attribute__((aligned(4)));
# define __ARCH_SI_CLOCK_T __kernel_si_clock_t
# define __ARCH_SI_ATTRIBUTES __attribute__((aligned(8)))
-# else /* x86-64 */
-# define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
# endif
#endif
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3b20607d581b..e8fea7ffa306 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -48,6 +48,7 @@
#include <asm/mpspec.h>
#include <asm/smp.h>
#include <asm/i8259.h>
+#include <asm/setup.h>
#include "sleep.h" /* To include x86_acpi_suspend_lowlevel */
static int __initdata acpi_force = 0;
@@ -1771,3 +1772,8 @@ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
e820__range_add(addr, size, E820_TYPE_ACPI);
e820__update_table_print();
}
+
+u64 x86_default_get_root_pointer(void)
+{
+ return boot_params.hdr.acpi_rsdp_addr;
+}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index b9d5e7c9ef43..ebeac487a20c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -222,6 +222,10 @@ void __init arch_init_ideal_nops(void)
}
break;
+ case X86_VENDOR_HYGON:
+ ideal_nops = p6_nops;
+ return;
+
case X86_VENDOR_AMD:
if (boot_cpu_data.x86 > 0xf) {
ideal_nops = p6_nops;
@@ -594,7 +598,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
BUG_ON(p->len > MAX_PATCH_LEN);
/* prep the buffer with the original instructions */
memcpy(insnbuf, p->instr, p->len);
- used = pv_init_ops.patch(p->instrtype, p->clobbers, insnbuf,
+ used = pv_ops.init.patch(p->instrtype, insnbuf,
(unsigned long)p->instr, p->len);
BUG_ON(used > p->len);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index f299d8a479bb..3f9d1b4019bb 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -482,7 +482,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
{
void *vaddr;
- vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
+ vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs);
if (!vaddr ||
!force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24))
return vaddr;
@@ -494,7 +494,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
goto out_free;
return vaddr;
out_free:
- dma_direct_free(dev, size, vaddr, *dma_addr, attrs);
+ dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs);
return NULL;
}
@@ -504,7 +504,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_addr, unsigned long attrs)
{
gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
- dma_direct_free(dev, size, vaddr, dma_addr, attrs);
+ dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
}
static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index b481b95bd8f6..a6eca647bc76 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -61,6 +61,21 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{}
};
+static const struct pci_device_id hygon_root_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_ROOT) },
+ {}
+};
+
+const struct pci_device_id hygon_nb_misc_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ {}
+};
+
+static const struct pci_device_id hygon_nb_link_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+ {}
+};
+
const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
{ 0x00, 0x18, 0x20 },
{ 0xff, 0x00, 0x20 },
@@ -194,15 +209,24 @@ EXPORT_SYMBOL_GPL(amd_df_indirect_read);
int amd_cache_northbridges(void)
{
- u16 i = 0;
- struct amd_northbridge *nb;
+ const struct pci_device_id *misc_ids = amd_nb_misc_ids;
+ const struct pci_device_id *link_ids = amd_nb_link_ids;
+ const struct pci_device_id *root_ids = amd_root_ids;
struct pci_dev *root, *misc, *link;
+ struct amd_northbridge *nb;
+ u16 i = 0;
if (amd_northbridges.num)
return 0;
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ root_ids = hygon_root_ids;
+ misc_ids = hygon_nb_misc_ids;
+ link_ids = hygon_nb_link_ids;
+ }
+
misc = NULL;
- while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
+ while ((misc = next_northbridge(misc, misc_ids)) != NULL)
i++;
if (!i)
@@ -218,11 +242,11 @@ int amd_cache_northbridges(void)
link = misc = root = NULL;
for (i = 0; i != amd_northbridges.num; i++) {
node_to_amd_nb(i)->root = root =
- next_northbridge(root, amd_root_ids);
+ next_northbridge(root, root_ids);
node_to_amd_nb(i)->misc = misc =
- next_northbridge(misc, amd_nb_misc_ids);
+ next_northbridge(misc, misc_ids);
node_to_amd_nb(i)->link = link =
- next_northbridge(link, amd_nb_link_ids);
+ next_northbridge(link, link_ids);
}
if (amd_gart_present())
@@ -261,11 +285,19 @@ EXPORT_SYMBOL_GPL(amd_cache_northbridges);
*/
bool __init early_is_amd_nb(u32 device)
{
+ const struct pci_device_id *misc_ids = amd_nb_misc_ids;
const struct pci_device_id *id;
u32 vendor = device & 0xffff;
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+ return false;
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ misc_ids = hygon_nb_misc_ids;
+
device >>= 16;
- for (id = amd_nb_misc_ids; id->vendor; id++)
+ for (id = misc_ids; id->vendor; id++)
if (vendor == id->vendor && device == id->device)
return true;
return false;
@@ -277,7 +309,8 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
u64 base, msr;
unsigned int segn_busn_bits;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return NULL;
/* assume all cpus from fam10h have mmconfig */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 84132eddb5a8..ab731ab09f06 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -224,6 +224,11 @@ static int modern_apic(void)
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 >= 0xf)
return 1;
+
+ /* Hygon systems use modern APIC */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ return 1;
+
return lapic_get_version() >= 0x14;
}
@@ -1912,6 +1917,8 @@ static int __init detect_init_APIC(void)
(boot_cpu_data.x86 >= 15))
break;
goto no_apic;
+ case X86_VENDOR_HYGON:
+ break;
case X86_VENDOR_INTEL:
if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
(boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 02e8acb134f8..47ff2976c292 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -185,6 +185,7 @@ void __init default_setup_apic_routing(void)
break;
}
/* If P4 and above fall through */
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
def_to_bigsmp = 1;
}
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 9f148e3d45b4..652e7ffa9b9d 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -313,14 +313,13 @@ assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest)
struct apic_chip_data *apicd = apic_chip_data(irqd);
int vector, cpu;
- cpumask_and(vector_searchmask, vector_searchmask, affmsk);
- cpu = cpumask_first(vector_searchmask);
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
+ cpumask_and(vector_searchmask, dest, affmsk);
+
/* set_affinity might call here for nothing */
if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask))
return 0;
- vector = irq_matrix_alloc_managed(vector_matrix, cpu);
+ vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask,
+ &cpu);
trace_vector_alloc_managed(irqd->irq, vector, vector);
if (vector < 0)
return vector;
@@ -413,7 +412,7 @@ static int activate_managed(struct irq_data *irqd)
if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) {
/* Something in the core code broke! Survive gracefully */
pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq);
- return EINVAL;
+ return -EINVAL;
}
ret = assign_managed_vector(irqd, vector_searchmask);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index ec00d1ff5098..f7151cd03cb0 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp)
return 0;
}
+#ifdef CONFIG_PROC_FS
static int proc_apm_show(struct seq_file *m, void *v)
{
unsigned short bx;
@@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v)
units);
return 0;
}
+#endif
static int apm(void *unused)
{
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 01de31db300d..72adf6c335dc 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -64,15 +64,12 @@ void common(void) {
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
#endif
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
BLANK();
- OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
- OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
- OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
- OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
- OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
- OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
- OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
+ OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
+ OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
+ OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
+ OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2);
#endif
#ifdef CONFIG_XEN
@@ -99,13 +96,12 @@ void common(void) {
OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
/* Layout info for cpu_entry_area */
- OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
- OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
- /* Offset for sp0 and sp1 into the tss_struct */
+ /* Offset for fields in tss_struct */
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
+ OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 3b9405e7ba2b..ddced33184b5 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -21,10 +21,13 @@ static char syscalls_ia32[] = {
int main(void)
{
#ifdef CONFIG_PARAVIRT
- OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
- OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+#ifdef CONFIG_PARAVIRT_XXL
+ OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
+ cpu.usergs_sysret64);
+ OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs);
#ifdef CONFIG_DEBUG_ENTRY
- OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+ OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
+#endif
#endif
BLANK();
#endif
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 33399426793e..1979a76bfadd 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -1,4 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/kthread.h>
@@ -31,11 +34,17 @@ static __init int set_corruption_check(char *arg)
ssize_t ret;
unsigned long val;
+ if (!arg) {
+ pr_err("memory_corruption_check config string not provided\n");
+ return -EINVAL;
+ }
+
ret = kstrtoul(arg, 10, &val);
if (ret)
return ret;
memory_corruption_check = val;
+
return 0;
}
early_param("memory_corruption_check", set_corruption_check);
@@ -45,6 +54,11 @@ static __init int set_corruption_check_period(char *arg)
ssize_t ret;
unsigned long val;
+ if (!arg) {
+ pr_err("memory_corruption_check_period config string not provided\n");
+ return -EINVAL;
+ }
+
ret = kstrtoul(arg, 10, &val);
if (ret)
return ret;
@@ -59,6 +73,11 @@ static __init int set_corruption_check_size(char *arg)
char *end;
unsigned size;
+ if (!arg) {
+ pr_err("memory_corruption_check_size config string not provided\n");
+ return -EINVAL;
+ }
+
size = memparse(arg, &end);
if (*end == '\0')
@@ -113,7 +132,7 @@ void __init setup_bios_corruption_check(void)
}
if (num_scan_areas)
- printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas);
+ pr_info("Scanning %d areas for low memory corruption\n", num_scan_areas);
}
@@ -132,8 +151,7 @@ void check_for_bios_corruption(void)
for (; size; addr++, size -= sizeof(unsigned long)) {
if (!*addr)
continue;
- printk(KERN_ERR "Corrupted low memory at %p (%lx phys) = %08lx\n",
- addr, __pa(addr), *addr);
+ pr_err("Corrupted low memory at %p (%lx phys) = %08lx\n", addr, __pa(addr), *addr);
corruption = 1;
*addr = 0;
}
@@ -157,11 +175,11 @@ static int start_periodic_check_for_corruption(void)
if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0)
return 0;
- printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
- corruption_check_period);
+ pr_info("Scanning for low memory corruption every %d seconds\n", corruption_check_period);
/* First time we run the checks right away */
schedule_delayed_work(&bios_check_work, 0);
+
return 0;
}
device_initcall(start_periodic_check_for_corruption);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 347137e80bf5..1f5d2291c31e 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
+obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 22ab408177b2..eeea634bee0a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c)
static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
{
/* AMD errata T13 (order #21922) */
- if ((c->x86 == 6)) {
+ if (c->x86 == 6) {
/* Duron Rev A0 */
if (c->x86_model == 3 && c->x86_stepping == 0)
size = 64;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 40bdaea97fe7..c37e66e493bf 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -35,12 +35,10 @@ static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
-/*
- * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
- * writes to SPEC_CTRL contain whatever reserved bits have been set.
- */
-u64 __ro_after_init x86_spec_ctrl_base;
+/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
+u64 x86_spec_ctrl_base;
EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+static DEFINE_MUTEX(spec_ctrl_mutex);
/*
* The vendor and possibly platform specific bits which can be modified in
@@ -312,6 +310,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
}
if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON &&
boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
return SPECTRE_V2_CMD_AUTO;
@@ -325,6 +324,46 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
return cmd;
}
+static bool stibp_needed(void)
+{
+ if (spectre_v2_enabled == SPECTRE_V2_NONE)
+ return false;
+
+ if (!boot_cpu_has(X86_FEATURE_STIBP))
+ return false;
+
+ return true;
+}
+
+static void update_stibp_msr(void *info)
+{
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+}
+
+void arch_smt_update(void)
+{
+ u64 mask;
+
+ if (!stibp_needed())
+ return;
+
+ mutex_lock(&spec_ctrl_mutex);
+ mask = x86_spec_ctrl_base;
+ if (cpu_smt_control == CPU_SMT_ENABLED)
+ mask |= SPEC_CTRL_STIBP;
+ else
+ mask &= ~SPEC_CTRL_STIBP;
+
+ if (mask != x86_spec_ctrl_base) {
+ pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n",
+ cpu_smt_control == CPU_SMT_ENABLED ?
+ "Enabling" : "Disabling");
+ x86_spec_ctrl_base = mask;
+ on_each_cpu(update_stibp_msr, NULL, 1);
+ }
+ mutex_unlock(&spec_ctrl_mutex);
+}
+
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -371,7 +410,8 @@ static void __init spectre_v2_select_mitigation(void)
return;
retpoline_auto:
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
retpoline_amd:
if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
@@ -424,6 +464,9 @@ specv2_set_mode:
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
+
+ /* Enable STIBP if appropriate */
+ arch_smt_update();
}
#undef pr_fmt
@@ -814,6 +857,8 @@ static ssize_t l1tf_show_state(char *buf)
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
+ int ret;
+
if (!boot_cpu_has_bug(bug))
return sprintf(buf, "Not affected\n");
@@ -831,10 +876,13 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
return sprintf(buf, "Mitigation: __user pointer sanitization\n");
case X86_BUG_SPECTRE_V2:
- return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ ret = sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "",
+ boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
spectre_v2_module_string());
+ return ret;
case X86_BUG_SPEC_STORE_BYPASS:
return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 0c5fcbd998cf..dc1b9342e9c4 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -602,6 +602,10 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
else
amd_cpuid4(index, &eax, &ebx, &ecx);
amd_init_l3_cache(this_leaf, index);
+ } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ cpuid_count(0x8000001d, index, &eax.full,
+ &ebx.full, &ecx.full, &edx);
+ amd_init_l3_cache(this_leaf, index);
} else {
cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
}
@@ -625,7 +629,8 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
union _cpuid4_leaf_eax cache_eax;
int i = -1;
- if (c->x86_vendor == X86_VENDOR_AMD)
+ if (c->x86_vendor == X86_VENDOR_AMD ||
+ c->x86_vendor == X86_VENDOR_HYGON)
op = 0x8000001d;
else
op = 4;
@@ -678,6 +683,22 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
}
}
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+ /*
+ * We may have multiple LLCs if L3 caches exist, so check if we
+ * have an L3 cache by looking at the L3 cache CPUID leaf.
+ */
+ if (!cpuid_edx(0x80000006))
+ return;
+
+ /*
+ * LLC is at the core complex level.
+ * Core complex ID is ApicId[3] for these processors.
+ */
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+}
+
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
{
@@ -691,6 +712,11 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
}
}
+void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
+{
+ num_cache_leaves = find_num_cache_leaves(c);
+}
+
void init_intel_cacheinfo(struct cpuinfo_x86 *c)
{
/* Cache sizes */
@@ -913,7 +939,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
int index_msb, i;
struct cpuinfo_x86 *c = &cpu_data(cpu);
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (c->x86_vendor == X86_VENDOR_AMD ||
+ c->x86_vendor == X86_VENDOR_HYGON) {
if (__cache_amd_cpumap_setup(cpu, index, base))
return;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 44c4ef3d989b..660d0b22e962 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -949,11 +949,11 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
}
static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_TABLET, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL_MID, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_MID, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL, X86_FEATURE_ANY },
{ X86_VENDOR_CENTAUR, 5 },
{ X86_VENDOR_INTEL, 5 },
{ X86_VENDOR_NSC, 5 },
@@ -963,15 +963,16 @@ static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
{ X86_VENDOR_AMD },
+ { X86_VENDOR_HYGON },
{}
};
/* Only list CPUs which speculate but are non susceptible to SSB */
static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
@@ -984,14 +985,14 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
/* in addition to cpu_no_speculation */
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT_MID },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_PLUS },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
{}
@@ -1076,6 +1077,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
memset(&c->x86_capability, 0, sizeof c->x86_capability);
c->extended_cpuid_level = 0;
+ if (!have_cpuid_p())
+ identify_cpu_without_cpuid(c);
+
/* cyrix could have cpuid enabled via c_identify()*/
if (have_cpuid_p()) {
cpu_detect(c);
@@ -1093,7 +1097,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
if (this_cpu->c_bsp_init)
this_cpu->c_bsp_init(c);
} else {
- identify_cpu_without_cpuid(c);
setup_clear_cpu_cap(X86_FEATURE_CPUID);
}
@@ -1240,10 +1243,10 @@ static void generic_identify(struct cpuinfo_x86 *c)
* ESPFIX issue, we can change this.
*/
#ifdef CONFIG_X86_32
-# ifdef CONFIG_PARAVIRT
+# ifdef CONFIG_PARAVIRT_XXL
do {
extern void native_iret(void);
- if (pv_cpu_ops.iret == native_iret)
+ if (pv_ops.cpu.iret == native_iret)
set_cpu_bug(c, X86_BUG_ESPFIX);
} while (0);
# else
@@ -1531,19 +1534,8 @@ EXPORT_PER_CPU_SYMBOL(__preempt_count);
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
- extern char _entry_trampoline[];
- extern char entry_SYSCALL_64_trampoline[];
-
- int cpu = smp_processor_id();
- unsigned long SYSCALL64_entry_trampoline =
- (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
- (entry_SYSCALL_64_trampoline - _entry_trampoline);
-
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
- if (static_cpu_has(X86_FEATURE_PTI))
- wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
- else
- wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+ wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1554,7 +1546,8 @@ void syscall_init(void)
* AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
*/
wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+ (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
#else
wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1669,6 +1662,29 @@ static void wait_for_master_cpu(int cpu)
#endif
}
+#ifdef CONFIG_X86_64
+static void setup_getcpu(int cpu)
+{
+ unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
+ struct desc_struct d = { };
+
+ if (static_cpu_has(X86_FEATURE_RDTSCP))
+ write_rdtscp_aux(cpudata);
+
+ /* Store CPU and node number in limit. */
+ d.limit0 = cpudata;
+ d.limit1 = cpudata >> 16;
+
+ d.type = 5; /* RO data, expand down, accessed */
+ d.dpl = 3; /* Visible to user code */
+ d.s = 1; /* Not a system segment */
+ d.p = 1; /* Present */
+ d.d = 1; /* 32-bit */
+
+ write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S);
+}
+#endif
+
/*
* cpu_init() initializes state that is per-CPU. Some data is already
* initialized (naturally) in the bootstrap process, such as the GDT
@@ -1706,6 +1722,7 @@ void cpu_init(void)
early_cpu_to_node(cpu) != NUMA_NO_NODE)
set_numa_node(early_cpu_to_node(cpu));
#endif
+ setup_getcpu(cpu);
me = current;
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 7b229afa0a37..da5446acc241 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -54,6 +54,7 @@ extern u32 get_scattered_cpuid_leaf(unsigned int level,
enum cpuid_regs_idx reg);
extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
+extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c);
extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 8949b7ae6d92..d12226f60168 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -437,7 +437,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c)
/* enable MAPEN */
setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);
/* enable cpuid */
- setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80);
+ setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80);
/* disable MAPEN */
setCx86(CX86_CCR3, ccr3);
local_irq_restore(flags);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
new file mode 100644
index 000000000000..cf25405444ab
--- /dev/null
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Hygon Processor Support for Linux
+ *
+ * Copyright (C) 2018 Chengdu Haiguang IC Design Co., Ltd.
+ *
+ * Author: Pu Wen <puwen@hygon.cn>
+ */
+#include <linux/io.h>
+
+#include <asm/cpu.h>
+#include <asm/smp.h>
+#include <asm/cacheinfo.h>
+#include <asm/spec-ctrl.h>
+#include <asm/delay.h>
+#ifdef CONFIG_X86_64
+# include <asm/set_memory.h>
+#endif
+
+#include "cpu.h"
+
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config. Read the comment in
+ * srat_detect_node().
+ */
+static int nearby_node(int apicid)
+{
+ int i, node;
+
+ for (i = apicid - 1; i >= 0; i--) {
+ node = __apicid_to_node[i];
+ if (node != NUMA_NO_NODE && node_online(node))
+ return node;
+ }
+ for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+ node = __apicid_to_node[i];
+ if (node != NUMA_NO_NODE && node_online(node))
+ return node;
+ }
+ return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+static void hygon_get_topology_early(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_TOPOEXT))
+ smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+}
+
+/*
+ * Fixup core topology information for
+ * (1) Hygon multi-node processors
+ * Assumption: Number of cores in each internal node is the same.
+ * (2) Hygon processors supporting compute units
+ */
+static void hygon_get_topology(struct cpuinfo_x86 *c)
+{
+ u8 node_id;
+ int cpu = smp_processor_id();
+
+ /* get information required for multi-node processors */
+ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ int err;
+ u32 eax, ebx, ecx, edx;
+
+ cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+ node_id = ecx & 0xff;
+
+ c->cpu_core_id = ebx & 0xff;
+
+ if (smp_num_siblings > 1)
+ c->x86_max_cores /= smp_num_siblings;
+
+ /*
+ * In case leaf B is available, use it to derive
+ * topology information.
+ */
+ err = detect_extended_topology(c);
+ if (!err)
+ c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+ cacheinfo_hygon_init_llc_id(c, cpu, node_id);
+ } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+ u64 value;
+
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+ node_id = value & 7;
+
+ per_cpu(cpu_llc_id, cpu) = node_id;
+ } else
+ return;
+
+ if (nodes_per_socket > 1)
+ set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+}
+
+/*
+ * On Hygon setup the lower bits of the APIC id distinguish the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void hygon_detect_cmp(struct cpuinfo_x86 *c)
+{
+ unsigned int bits;
+ int cpu = smp_processor_id();
+
+ bits = c->x86_coreid_bits;
+ /* Low order bits define the core id (index of core in socket) */
+ c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+ /* Convert the initial APIC ID into the socket ID */
+ c->phys_proc_id = c->initial_apicid >> bits;
+ /* use socket ID also for last level cache */
+ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+}
+
+static void srat_detect_node(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_NUMA
+ int cpu = smp_processor_id();
+ int node;
+ unsigned int apicid = c->apicid;
+
+ node = numa_cpu_node(cpu);
+ if (node == NUMA_NO_NODE)
+ node = per_cpu(cpu_llc_id, cpu);
+
+ /*
+ * On multi-fabric platform (e.g. Numascale NumaChip) a
+ * platform-specific handler needs to be called to fixup some
+ * IDs of the CPU.
+ */
+ if (x86_cpuinit.fixup_cpu_id)
+ x86_cpuinit.fixup_cpu_id(c, node);
+
+ if (!node_online(node)) {
+ /*
+ * Two possibilities here:
+ *
+ * - The CPU is missing memory and no node was created. In
+ * that case try picking one from a nearby CPU.
+ *
+ * - The APIC IDs differ from the HyperTransport node IDs.
+ * Assume they are all increased by a constant offset, but
+ * in the same order as the HT nodeids. If that doesn't
+ * result in a usable node fall back to the path for the
+ * previous case.
+ *
+ * This workaround operates directly on the mapping between
+ * APIC ID and NUMA node, assuming certain relationship
+ * between APIC ID, HT node ID and NUMA topology. As going
+ * through CPU mapping may alter the outcome, directly
+ * access __apicid_to_node[].
+ */
+ int ht_nodeid = c->initial_apicid;
+
+ if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+ node = __apicid_to_node[ht_nodeid];
+ /* Pick a nearby node */
+ if (!node_online(node))
+ node = nearby_node(apicid);
+ }
+ numa_set_node(cpu, node);
+#endif
+}
+
+static void early_init_hygon_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned int bits, ecx;
+
+ /* Multi core CPU? */
+ if (c->extended_cpuid_level < 0x80000008)
+ return;
+
+ ecx = cpuid_ecx(0x80000008);
+
+ c->x86_max_cores = (ecx & 0xff) + 1;
+
+ /* CPU telling us the core id bits shift? */
+ bits = (ecx >> 12) & 0xF;
+
+ /* Otherwise recompute */
+ if (bits == 0) {
+ while ((1 << bits) < c->x86_max_cores)
+ bits++;
+ }
+
+ c->x86_coreid_bits = bits;
+#endif
+}
+
+static void bsp_init_hygon(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+ unsigned long long tseg;
+
+ /*
+ * Split up direct mapping around the TSEG SMM area.
+ * Don't do it for gbpages because there seems very little
+ * benefit in doing so.
+ */
+ if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ unsigned long pfn = tseg >> PAGE_SHIFT;
+
+ pr_debug("tseg: %010llx\n", tseg);
+ if (pfn_range_is_mapped(pfn, pfn + 1))
+ set_memory_4k((unsigned long)__va(tseg), 1);
+ }
+#endif
+
+ if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+ u64 val;
+
+ rdmsrl(MSR_K7_HWCR, val);
+ if (!(val & BIT(24)))
+ pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
+ }
+
+ if (cpu_has(c, X86_FEATURE_MWAITX))
+ use_mwaitx_delay();
+
+ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ u32 ecx;
+
+ ecx = cpuid_ecx(0x8000001e);
+ nodes_per_socket = ((ecx >> 8) & 7) + 1;
+ } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
+ u64 value;
+
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+ nodes_per_socket = ((value >> 3) & 7) + 1;
+ }
+
+ if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
+ !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+ /*
+ * Try to cache the base value so further operations can
+ * avoid RMW. If that faults, do not enable SSBD.
+ */
+ if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+ setup_force_cpu_cap(X86_FEATURE_SSBD);
+ x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
+ }
+ }
+}
+
+static void early_init_hygon(struct cpuinfo_x86 *c)
+{
+ u32 dummy;
+
+ early_init_hygon_mc(c);
+
+ set_cpu_cap(c, X86_FEATURE_K8);
+
+ rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
+
+ /*
+ * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
+ * with P/T states and does not stop in deep C-states
+ */
+ if (c->x86_power & (1 << 8)) {
+ set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+ }
+
+ /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
+ if (c->x86_power & BIT(12))
+ set_cpu_cap(c, X86_FEATURE_ACC_POWER);
+
+#ifdef CONFIG_X86_64
+ set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+#endif
+
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
+ /*
+ * ApicID can always be treated as an 8-bit value for Hygon APIC So, we
+ * can safely set X86_FEATURE_EXTD_APICID unconditionally.
+ */
+ if (boot_cpu_has(X86_FEATURE_APIC))
+ set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+#endif
+
+ /*
+ * This is only needed to tell the kernel whether to use VMCALL
+ * and VMMCALL. VMMCALL is never executed except under virt, so
+ * we can set it unconditionally.
+ */
+ set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
+ hygon_get_topology_early(c);
+}
+
+static void init_hygon(struct cpuinfo_x86 *c)
+{
+ early_init_hygon(c);
+
+ /*
+ * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+ * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+ */
+ clear_cpu_cap(c, 0*32+31);
+
+ set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ /* get apicid instead of initial apic id from cpuid */
+ c->apicid = hard_smp_processor_id();
+
+ set_cpu_cap(c, X86_FEATURE_ZEN);
+ set_cpu_cap(c, X86_FEATURE_CPB);
+
+ cpu_detect_cache_sizes(c);
+
+ hygon_detect_cmp(c);
+ hygon_get_topology(c);
+ srat_detect_node(c);
+
+ init_hygon_cacheinfo(c);
+
+ if (cpu_has(c, X86_FEATURE_XMM2)) {
+ unsigned long long val;
+ int ret;
+
+ /*
+ * A serializing LFENCE has less overhead than MFENCE, so
+ * use it for execution serialization. On families which
+ * don't have that MSR, LFENCE is already serializing.
+ * msr_set_bit() uses the safe accessors, too, even if the MSR
+ * is not present.
+ */
+ msr_set_bit(MSR_F10H_DECFG,
+ MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+ /*
+ * Verify that the MSR write was successful (could be running
+ * under a hypervisor) and only then assume that LFENCE is
+ * serializing.
+ */
+ ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+ if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+ /* A serializing LFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+ } else {
+ /* MFENCE stops RDTSC speculation */
+ set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+ }
+ }
+
+ /*
+ * Hygon processors have APIC timer running in deep C states.
+ */
+ set_cpu_cap(c, X86_FEATURE_ARAT);
+
+ /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */
+ if (!cpu_has(c, X86_FEATURE_XENPV))
+ set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+}
+
+static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
+{
+ u32 ebx, eax, ecx, edx;
+ u16 mask = 0xfff;
+
+ if (c->extended_cpuid_level < 0x80000006)
+ return;
+
+ cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
+
+ tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
+ tlb_lli_4k[ENTRIES] = ebx & mask;
+
+ /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!((eax >> 16) & mask))
+ tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+ else
+ tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+
+ /* a 4M entry uses two 2M entries */
+ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+
+ /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!(eax & mask)) {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ tlb_lli_2m[ENTRIES] = eax & 0xff;
+ } else
+ tlb_lli_2m[ENTRIES] = eax & mask;
+
+ tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+}
+
+static const struct cpu_dev hygon_cpu_dev = {
+ .c_vendor = "Hygon",
+ .c_ident = { "HygonGenuine" },
+ .c_early_init = early_init_hygon,
+ .c_detect_tlb = cpu_detect_tlb_hygon,
+ .c_bsp_init = bsp_init_hygon,
+ .c_init = init_hygon,
+ .c_x86_vendor = X86_VENDOR_HYGON,
+};
+
+cpu_dev_register(hygon_cpu_dev);
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index abb71ac70443..44272b7107ad 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -485,9 +485,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
size_t tsize;
if (is_llc_occupancy_enabled()) {
- d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid),
- sizeof(unsigned long),
- GFP_KERNEL);
+ d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
if (!d->rmid_busy_llc)
return -ENOMEM;
INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
@@ -496,7 +494,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
tsize = sizeof(*d->mbm_total);
d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
if (!d->mbm_total) {
- kfree(d->rmid_busy_llc);
+ bitmap_free(d->rmid_busy_llc);
return -ENOMEM;
}
}
@@ -504,7 +502,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
tsize = sizeof(*d->mbm_local);
d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
if (!d->mbm_local) {
- kfree(d->rmid_busy_llc);
+ bitmap_free(d->rmid_busy_llc);
kfree(d->mbm_total);
return -ENOMEM;
}
@@ -610,9 +608,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
cancel_delayed_work(&d->cqm_limbo);
}
+ /*
+ * rdt_domain "d" is going to be freed below, so clear
+ * its pointer from pseudo_lock_region struct.
+ */
+ if (d->plr)
+ d->plr->d = NULL;
+
kfree(d->ctrl_val);
kfree(d->mbps_val);
- kfree(d->rmid_busy_llc);
+ bitmap_free(d->rmid_busy_llc);
kfree(d->mbm_total);
kfree(d->mbm_local);
kfree(d);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 4e588f36228f..3736f6dc9545 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e)
e <= QOS_L3_MBM_LOCAL_EVENT_ID);
}
+struct rdt_parse_data {
+ struct rdtgroup *rdtgrp;
+ char *buf;
+};
+
/**
* struct rdt_resource - attributes of an RDT resource
* @rid: The index of the resource
@@ -423,16 +428,19 @@ struct rdt_resource {
struct rdt_cache cache;
struct rdt_membw membw;
const char *format_str;
- int (*parse_ctrlval) (void *data, struct rdt_resource *r,
- struct rdt_domain *d);
+ int (*parse_ctrlval)(struct rdt_parse_data *data,
+ struct rdt_resource *r,
+ struct rdt_domain *d);
struct list_head evt_list;
int num_rmid;
unsigned int mon_scale;
unsigned long fflags;
};
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
extern struct mutex rdtgroup_mutex;
@@ -521,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v);
bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
- u32 _cbm, int closid, bool exclusive);
+ unsigned long cbm, int closid, bool exclusive);
unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
- u32 cbm);
+ unsigned long cbm);
enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
int rdtgroup_tasks_assigned(struct rdtgroup *r);
int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm);
bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
int rdt_pseudo_lock_init(void);
void rdt_pseudo_lock_release(void);
@@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
int update_domains(struct rdt_resource *r, int closid);
+int closids_supported(void);
void closid_free(int closid);
int alloc_rmid(void);
void free_rmid(u32 rmid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index af358ca05160..27937458c231 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return true;
}
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
- unsigned long data;
- char *buf = _buf;
+ unsigned long bw_val;
if (d->have_new_ctrl) {
rdt_last_cmd_printf("duplicate domain %d\n", d->id);
return -EINVAL;
}
- if (!bw_validate(buf, &data, r))
+ if (!bw_validate(data->buf, &bw_val, r))
return -EINVAL;
- d->new_ctrl = data;
+ d->new_ctrl = bw_val;
d->have_new_ctrl = true;
return 0;
@@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
return true;
}
-struct rdt_cbm_parse_data {
- struct rdtgroup *rdtgrp;
- char *buf;
-};
-
/*
* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.
*/
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
- struct rdt_cbm_parse_data *data = _data;
struct rdtgroup *rdtgrp = data->rdtgrp;
u32 cbm_val;
@@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
static int parse_line(char *line, struct rdt_resource *r,
struct rdtgroup *rdtgrp)
{
- struct rdt_cbm_parse_data data;
+ struct rdt_parse_data data;
char *dom = NULL, *id;
struct rdt_domain *d;
unsigned long dom_id;
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+ r->rid == RDT_RESOURCE_MBA) {
+ rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
+ return -EINVAL;
+ }
+
next:
if (!line || line[0] == '\0')
return 0;
@@ -403,8 +404,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
for_each_alloc_enabled_rdt_resource(r)
seq_printf(s, "%s:uninitialized\n", r->name);
} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
- rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+ if (!rdtgrp->plr->d) {
+ rdt_last_cmd_clear();
+ rdt_last_cmd_puts("Cache domain offline\n");
+ ret = -ENODEV;
+ } else {
+ seq_printf(s, "%s:%d=%x\n",
+ rdtgrp->plr->r->name,
+ rdtgrp->plr->d->id,
+ rdtgrp->plr->cbm);
+ }
} else {
closid = rdtgrp->closid;
for_each_alloc_enabled_rdt_resource(r) {
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 40f3903ae5d9..815b4e92522c 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -17,6 +17,7 @@
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/mman.h>
+#include <linux/perf_event.h>
#include <linux/pm_qos.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
@@ -26,6 +27,7 @@
#include <asm/intel_rdt_sched.h>
#include <asm/perf_event.h>
+#include "../../events/perf_event.h" /* For X86_CONFIG() */
#include "intel_rdt.h"
#define CREATE_TRACE_POINTS
@@ -91,7 +93,7 @@ static u64 get_prefetch_disable_bits(void)
*/
return 0xF;
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
/*
* SDM defines bits of MSR_MISC_FEATURE_CONTROL register
* as:
@@ -106,16 +108,6 @@ static u64 get_prefetch_disable_bits(void)
return 0;
}
-/*
- * Helper to write 64bit value to MSR without tracing. Used when
- * use of the cache should be restricted and use of registers used
- * for local variables avoided.
- */
-static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
-{
- __wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
-}
-
/**
* pseudo_lock_minor_get - Obtain available minor number
* @minor: Pointer to where new minor number will be stored
@@ -797,25 +789,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
/**
* rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
* @d: RDT domain
- * @_cbm: CBM to test
+ * @cbm: CBM to test
*
- * @d represents a cache instance and @_cbm a capacity bitmask that is
- * considered for it. Determine if @_cbm overlaps with any existing
+ * @d represents a cache instance and @cbm a capacity bitmask that is
+ * considered for it. Determine if @cbm overlaps with any existing
* pseudo-locked region on @d.
*
- * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
+ * Return: true if @cbm overlaps with pseudo-locked region on @d, false
* otherwise.
*/
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
{
- unsigned long *cbm = (unsigned long *)&_cbm;
- unsigned long *cbm_b;
unsigned int cbm_len;
+ unsigned long cbm_b;
if (d->plr) {
cbm_len = d->plr->r->cache.cbm_len;
- cbm_b = (unsigned long *)&d->plr->cbm;
- if (bitmap_intersects(cbm, cbm_b, cbm_len))
+ cbm_b = d->plr->cbm;
+ if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
return true;
}
return false;
@@ -886,31 +880,14 @@ static int measure_cycles_lat_fn(void *_plr)
struct pseudo_lock_region *plr = _plr;
unsigned long i;
u64 start, end;
-#ifdef CONFIG_KASAN
- /*
- * The registers used for local register variables are also used
- * when KASAN is active. When KASAN is active we use a regular
- * variable to ensure we always use a valid pointer to access memory.
- * The cost is that accessing this pointer, which could be in
- * cache, will be included in the measurement of memory read latency.
- */
void *mem_r;
-#else
-#ifdef CONFIG_X86_64
- register void *mem_r asm("rbx");
-#else
- register void *mem_r asm("ebx");
-#endif /* CONFIG_X86_64 */
-#endif /* CONFIG_KASAN */
local_irq_disable();
/*
- * The wrmsr call may be reordered with the assignment below it.
- * Call wrmsr as directly as possible to avoid tracing clobbering
- * local register variable used for memory pointer.
+ * Disable hardware prefetchers.
*/
- __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
- mem_r = plr->kmem;
+ wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ mem_r = READ_ONCE(plr->kmem);
/*
* Dummy execute of the time measurement to load the needed
* instructions into the L1 instruction cache.
@@ -932,157 +909,240 @@ static int measure_cycles_lat_fn(void *_plr)
return 0;
}
-static int measure_cycles_perf_fn(void *_plr)
+/*
+ * Create a perf_event_attr for the hit and miss perf events that will
+ * be used during the performance measurement. A perf_event maintains
+ * a pointer to its perf_event_attr so a unique attribute structure is
+ * created for each perf_event.
+ *
+ * The actual configuration of the event is set right before use in order
+ * to use the X86_CONFIG macro.
+ */
+static struct perf_event_attr perf_miss_attr = {
+ .type = PERF_TYPE_RAW,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 0,
+ .exclude_user = 1,
+};
+
+static struct perf_event_attr perf_hit_attr = {
+ .type = PERF_TYPE_RAW,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 0,
+ .exclude_user = 1,
+};
+
+struct residency_counts {
+ u64 miss_before, hits_before;
+ u64 miss_after, hits_after;
+};
+
+static int measure_residency_fn(struct perf_event_attr *miss_attr,
+ struct perf_event_attr *hit_attr,
+ struct pseudo_lock_region *plr,
+ struct residency_counts *counts)
{
- unsigned long long l3_hits = 0, l3_miss = 0;
- u64 l3_hit_bits = 0, l3_miss_bits = 0;
- struct pseudo_lock_region *plr = _plr;
- unsigned long long l2_hits, l2_miss;
- u64 l2_hit_bits, l2_miss_bits;
- unsigned long i;
-#ifdef CONFIG_KASAN
- /*
- * The registers used for local register variables are also used
- * when KASAN is active. When KASAN is active we use regular variables
- * at the cost of including cache access latency to these variables
- * in the measurements.
- */
+ u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0;
+ struct perf_event *miss_event, *hit_event;
+ int hit_pmcnum, miss_pmcnum;
unsigned int line_size;
unsigned int size;
+ unsigned long i;
void *mem_r;
-#else
- register unsigned int line_size asm("esi");
- register unsigned int size asm("edi");
-#ifdef CONFIG_X86_64
- register void *mem_r asm("rbx");
-#else
- register void *mem_r asm("ebx");
-#endif /* CONFIG_X86_64 */
-#endif /* CONFIG_KASAN */
+ u64 tmp;
+
+ miss_event = perf_event_create_kernel_counter(miss_attr, plr->cpu,
+ NULL, NULL, NULL);
+ if (IS_ERR(miss_event))
+ goto out;
+
+ hit_event = perf_event_create_kernel_counter(hit_attr, plr->cpu,
+ NULL, NULL, NULL);
+ if (IS_ERR(hit_event))
+ goto out_miss;
+
+ local_irq_disable();
+ /*
+ * Check any possible error state of events used by performing
+ * one local read.
+ */
+ if (perf_event_read_local(miss_event, &tmp, NULL, NULL)) {
+ local_irq_enable();
+ goto out_hit;
+ }
+ if (perf_event_read_local(hit_event, &tmp, NULL, NULL)) {
+ local_irq_enable();
+ goto out_hit;
+ }
+
+ /*
+ * Disable hardware prefetchers.
+ */
+ wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+
+ /* Initialize rest of local variables */
+ /*
+ * Performance event has been validated right before this with
+ * interrupts disabled - it is thus safe to read the counter index.
+ */
+ miss_pmcnum = x86_perf_rdpmc_index(miss_event);
+ hit_pmcnum = x86_perf_rdpmc_index(hit_event);
+ line_size = READ_ONCE(plr->line_size);
+ mem_r = READ_ONCE(plr->kmem);
+ size = READ_ONCE(plr->size);
+
+ /*
+ * Read counter variables twice - first to load the instructions
+ * used in L1 cache, second to capture accurate value that does not
+ * include cache misses incurred because of instruction loads.
+ */
+ rdpmcl(hit_pmcnum, hits_before);
+ rdpmcl(miss_pmcnum, miss_before);
+ /*
+ * From SDM: Performing back-to-back fast reads are not guaranteed
+ * to be monotonic.
+ * Use LFENCE to ensure all previous instructions are retired
+ * before proceeding.
+ */
+ rmb();
+ rdpmcl(hit_pmcnum, hits_before);
+ rdpmcl(miss_pmcnum, miss_before);
+ /*
+ * Use LFENCE to ensure all previous instructions are retired
+ * before proceeding.
+ */
+ rmb();
+ for (i = 0; i < size; i += line_size) {
+ /*
+ * Add a barrier to prevent speculative execution of this
+ * loop reading beyond the end of the buffer.
+ */
+ rmb();
+ asm volatile("mov (%0,%1,1), %%eax\n\t"
+ :
+ : "r" (mem_r), "r" (i)
+ : "%eax", "memory");
+ }
+ /*
+ * Use LFENCE to ensure all previous instructions are retired
+ * before proceeding.
+ */
+ rmb();
+ rdpmcl(hit_pmcnum, hits_after);
+ rdpmcl(miss_pmcnum, miss_after);
+ /*
+ * Use LFENCE to ensure all previous instructions are retired
+ * before proceeding.
+ */
+ rmb();
+ /* Re-enable hardware prefetchers */
+ wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ local_irq_enable();
+out_hit:
+ perf_event_release_kernel(hit_event);
+out_miss:
+ perf_event_release_kernel(miss_event);
+out:
+ /*
+ * All counts will be zero on failure.
+ */
+ counts->miss_before = miss_before;
+ counts->hits_before = hits_before;
+ counts->miss_after = miss_after;
+ counts->hits_after = hits_after;
+ return 0;
+}
+
+static int measure_l2_residency(void *_plr)
+{
+ struct pseudo_lock_region *plr = _plr;
+ struct residency_counts counts = {0};
/*
* Non-architectural event for the Goldmont Microarchitecture
* from Intel x86 Architecture Software Developer Manual (SDM):
* MEM_LOAD_UOPS_RETIRED D1H (event number)
* Umask values:
- * L1_HIT 01H
* L2_HIT 02H
- * L1_MISS 08H
* L2_MISS 10H
- *
- * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
- * has two "no fix" errata associated with it: BDM35 and BDM100. On
- * this platform we use the following events instead:
- * L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
- * REFERENCES FFH
- * MISS 3FH
- * LONGEST_LAT_CACHE 2EH (Documented in SDM)
- * REFERENCE 4FH
- * MISS 41H
*/
-
- /*
- * Start by setting flags for IA32_PERFEVTSELx:
- * OS (Operating system mode) 0x2
- * INT (APIC interrupt enable) 0x10
- * EN (Enable counter) 0x40
- *
- * Then add the Umask value and event number to select performance
- * event.
- */
-
switch (boot_cpu_data.x86_model) {
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
- l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
- l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
- break;
- case INTEL_FAM6_BROADWELL_X:
- /* On BDW the l2_hit_bits count references, not hits */
- l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
- l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
- /* On BDW the l3_hit_bits count references, not hits */
- l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
- l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ perf_miss_attr.config = X86_CONFIG(.event = 0xd1,
+ .umask = 0x10);
+ perf_hit_attr.config = X86_CONFIG(.event = 0xd1,
+ .umask = 0x2);
break;
default:
goto out;
}
- local_irq_disable();
+ measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts);
/*
- * Call wrmsr direcly to avoid the local register variables from
- * being overwritten due to reordering of their assignment with
- * the wrmsr calls.
+ * If a failure prevented the measurements from succeeding
+ * tracepoints will still be written and all counts will be zero.
*/
- __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
- /* Disable events and reset counters */
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
- if (l3_hit_bits > 0) {
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
- }
- /* Set and enable the L2 counters */
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
- if (l3_hit_bits > 0) {
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
- l3_hit_bits);
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
- l3_miss_bits);
- }
- mem_r = plr->kmem;
- size = plr->size;
- line_size = plr->line_size;
- for (i = 0; i < size; i += line_size) {
- asm volatile("mov (%0,%1,1), %%eax\n\t"
- :
- : "r" (mem_r), "r" (i)
- : "%eax", "memory");
- }
+ trace_pseudo_lock_l2(counts.hits_after - counts.hits_before,
+ counts.miss_after - counts.miss_before);
+out:
+ plr->thread_done = 1;
+ wake_up_interruptible(&plr->lock_thread_wq);
+ return 0;
+}
+
+static int measure_l3_residency(void *_plr)
+{
+ struct pseudo_lock_region *plr = _plr;
+ struct residency_counts counts = {0};
+
/*
- * Call wrmsr directly (no tracing) to not influence
- * the cache access counters as they are disabled.
+ * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+ * has two "no fix" errata associated with it: BDM35 and BDM100. On
+ * this platform the following events are used instead:
+ * LONGEST_LAT_CACHE 2EH (Documented in SDM)
+ * REFERENCE 4FH
+ * MISS 41H
*/
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
- l2_hit_bits & ~(0x40ULL << 16));
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
- l2_miss_bits & ~(0x40ULL << 16));
- if (l3_hit_bits > 0) {
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
- l3_hit_bits & ~(0x40ULL << 16));
- pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
- l3_miss_bits & ~(0x40ULL << 16));
- }
- l2_hits = native_read_pmc(0);
- l2_miss = native_read_pmc(1);
- if (l3_hit_bits > 0) {
- l3_hits = native_read_pmc(2);
- l3_miss = native_read_pmc(3);
+
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_BROADWELL_X:
+ /* On BDW the hit event counts references, not hits */
+ perf_hit_attr.config = X86_CONFIG(.event = 0x2e,
+ .umask = 0x4f);
+ perf_miss_attr.config = X86_CONFIG(.event = 0x2e,
+ .umask = 0x41);
+ break;
+ default:
+ goto out;
}
- wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
- local_irq_enable();
+
+ measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts);
/*
- * On BDW we count references and misses, need to adjust. Sometimes
- * the "hits" counter is a bit more than the references, for
- * example, x references but x + 1 hits. To not report invalid
- * hit values in this case we treat that as misses eaqual to
- * references.
+ * If a failure prevented the measurements from succeeding
+ * tracepoints will still be written and all counts will be zero.
*/
- if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
- l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
- trace_pseudo_lock_l2(l2_hits, l2_miss);
- if (l3_hit_bits > 0) {
- if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
- l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
- trace_pseudo_lock_l3(l3_hits, l3_miss);
+
+ counts.miss_after -= counts.miss_before;
+ if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) {
+ /*
+ * On BDW references and misses are counted, need to adjust.
+ * Sometimes the "hits" counter is a bit more than the
+ * references, for example, x references but x + 1 hits.
+ * To not report invalid hit values in this case we treat
+ * that as misses equal to references.
+ */
+ /* First compute the number of cache references measured */
+ counts.hits_after -= counts.hits_before;
+ /* Next convert references to cache hits */
+ counts.hits_after -= min(counts.miss_after, counts.hits_after);
+ } else {
+ counts.hits_after -= counts.hits_before;
}
+ trace_pseudo_lock_l3(counts.hits_after, counts.miss_after);
out:
plr->thread_done = 1;
wake_up_interruptible(&plr->lock_thread_wq);
@@ -1114,6 +1174,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
goto out;
}
+ if (!plr->d) {
+ ret = -ENODEV;
+ goto out;
+ }
+
plr->thread_done = 0;
cpu = cpumask_first(&plr->d->cpu_mask);
if (!cpu_online(cpu)) {
@@ -1121,13 +1186,20 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
goto out;
}
+ plr->cpu = cpu;
+
if (sel == 1)
thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
cpu_to_node(cpu),
"pseudo_lock_measure/%u",
cpu);
else if (sel == 2)
- thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
+ thread = kthread_create_on_node(measure_l2_residency, plr,
+ cpu_to_node(cpu),
+ "pseudo_lock_measure/%u",
+ cpu);
+ else if (sel == 3)
+ thread = kthread_create_on_node(measure_l3_residency, plr,
cpu_to_node(cpu),
"pseudo_lock_measure/%u",
cpu);
@@ -1171,7 +1243,7 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file,
buf[buf_size] = '\0';
ret = kstrtoint(buf, 10, &sel);
if (ret == 0) {
- if (sel != 1)
+ if (sel != 1 && sel != 2 && sel != 3)
return -EINVAL;
ret = debugfs_file_get(file->f_path.dentry);
if (ret)
@@ -1427,6 +1499,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
plr = rdtgrp->plr;
+ if (!plr->d) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENODEV;
+ }
+
/*
* Task is required to run with affinity to the cpus associated
* with the pseudo-locked region. If this is not the case the task
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index b799c00bef09..f27b8115ffa2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...)
* limited as the number of resources grows.
*/
static int closid_free_map;
+static int closid_free_map_len;
+
+int closids_supported(void)
+{
+ return closid_free_map_len;
+}
static void closid_init(void)
{
@@ -111,6 +117,7 @@ static void closid_init(void)
/* CLOSID 0 is always reserved for the default group */
closid_free_map &= ~1;
+ closid_free_map_len = rdt_min_closid;
}
static int closid_alloc(void)
@@ -261,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct rdtgroup *rdtgrp;
+ struct cpumask *mask;
int ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
- seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
- cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
- else
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+ if (!rdtgrp->plr->d) {
+ rdt_last_cmd_clear();
+ rdt_last_cmd_puts("Cache domain offline\n");
+ ret = -ENODEV;
+ } else {
+ mask = &rdtgrp->plr->d->cpu_mask;
+ seq_printf(s, is_cpu_list(of) ?
+ "%*pbl\n" : "%*pb\n",
+ cpumask_pr_args(mask));
+ }
+ } else {
seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
cpumask_pr_args(&rdtgrp->cpu_mask));
+ }
} else {
ret = -ENOENT;
}
@@ -802,7 +819,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
sw_shareable = 0;
exclusive = 0;
seq_printf(seq, "%d=", dom->id);
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
if (!closid_allocated(i))
continue;
mode = rdtgroup_mode_by_closid(i);
@@ -954,7 +971,78 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
}
/**
- * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * rdt_cdp_peer_get - Retrieve CDP peer if it exists
+ * @r: RDT resource to which RDT domain @d belongs
+ * @d: Cache instance for which a CDP peer is requested
+ * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer)
+ * Used to return the result.
+ * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer)
+ * Used to return the result.
+ *
+ * RDT resources are managed independently and by extension the RDT domains
+ * (RDT resource instances) are managed independently also. The Code and
+ * Data Prioritization (CDP) RDT resources, while managed independently,
+ * could refer to the same underlying hardware. For example,
+ * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache.
+ *
+ * When provided with an RDT resource @r and an instance of that RDT
+ * resource @d rdt_cdp_peer_get() will return if there is a peer RDT
+ * resource and the exact instance that shares the same hardware.
+ *
+ * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists.
+ * If a CDP peer was found, @r_cdp will point to the peer RDT resource
+ * and @d_cdp will point to the peer RDT domain.
+ */
+static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
+ struct rdt_resource **r_cdp,
+ struct rdt_domain **d_cdp)
+{
+ struct rdt_resource *_r_cdp = NULL;
+ struct rdt_domain *_d_cdp = NULL;
+ int ret = 0;
+
+ switch (r->rid) {
+ case RDT_RESOURCE_L3DATA:
+ _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE];
+ break;
+ case RDT_RESOURCE_L3CODE:
+ _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA];
+ break;
+ case RDT_RESOURCE_L2DATA:
+ _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE];
+ break;
+ case RDT_RESOURCE_L2CODE:
+ _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA];
+ break;
+ default:
+ ret = -ENOENT;
+ goto out;
+ }
+
+ /*
+ * When a new CPU comes online and CDP is enabled then the new
+ * RDT domains (if any) associated with both CDP RDT resources
+ * are added in the same CPU online routine while the
+ * rdtgroup_mutex is held. It should thus not happen for one
+ * RDT domain to exist and be associated with its RDT CDP
+ * resource but there is no RDT domain associated with the
+ * peer RDT CDP resource. Hence the WARN.
+ */
+ _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
+ if (WARN_ON(!_d_cdp)) {
+ _r_cdp = NULL;
+ ret = -EINVAL;
+ }
+
+out:
+ *r_cdp = _r_cdp;
+ *d_cdp = _d_cdp;
+
+ return ret;
+}
+
+/**
+ * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
* @r: Resource to which domain instance @d belongs.
* @d: The domain instance for which @closid is being tested.
* @cbm: Capacity bitmask being tested.
@@ -968,33 +1056,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
* is false then overlaps with any resource group or hardware entities
* will be considered.
*
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
* Return: false if CBM does not overlap, true if it does.
*/
-bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
- u32 _cbm, int closid, bool exclusive)
+static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+ unsigned long cbm, int closid, bool exclusive)
{
- unsigned long *cbm = (unsigned long *)&_cbm;
- unsigned long *ctrl_b;
enum rdtgrp_mode mode;
+ unsigned long ctrl_b;
u32 *ctrl;
int i;
/* Check for any overlap with regions used by hardware directly */
if (!exclusive) {
- if (bitmap_intersects(cbm,
- (unsigned long *)&r->cache.shareable_bits,
- r->cache.cbm_len))
+ ctrl_b = r->cache.shareable_bits;
+ if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
return true;
}
/* Check for overlap with other resource groups */
ctrl = d->ctrl_val;
- for (i = 0; i < r->num_closid; i++, ctrl++) {
- ctrl_b = (unsigned long *)ctrl;
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
+ ctrl_b = *ctrl;
mode = rdtgroup_mode_by_closid(i);
if (closid_allocated(i) && i != closid &&
mode != RDT_MODE_PSEUDO_LOCKSETUP) {
- if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+ if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
if (exclusive) {
if (mode == RDT_MODE_EXCLUSIVE)
return true;
@@ -1009,6 +1098,41 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
}
/**
+ * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Resources that can be allocated using a CBM can use the CBM to control
+ * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
+ * for overlap. Overlap test is not limited to the specific resource for
+ * which the CBM is intended though - when dealing with CDP resources that
+ * share the underlying hardware the overlap check should be performed on
+ * the CDP resource sharing the hardware also.
+ *
+ * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
+ * overlap test.
+ *
+ * Return: true if CBM overlap detected, false if there is no overlap
+ */
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+ unsigned long cbm, int closid, bool exclusive)
+{
+ struct rdt_resource *r_cdp;
+ struct rdt_domain *d_cdp;
+
+ if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive))
+ return true;
+
+ if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0)
+ return false;
+
+ return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive);
+}
+
+/**
* rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
*
* An exclusive resource group implies that there should be no sharing of
@@ -1024,16 +1148,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
{
int closid = rdtgrp->closid;
struct rdt_resource *r;
+ bool has_cache = false;
struct rdt_domain *d;
for_each_alloc_enabled_rdt_resource(r) {
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
+ has_cache = true;
list_for_each_entry(d, &r->domains, list) {
if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
- rdtgrp->closid, false))
+ rdtgrp->closid, false)) {
+ rdt_last_cmd_puts("schemata overlaps\n");
return false;
+ }
}
}
+ if (!has_cache) {
+ rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n");
+ return false;
+ }
+
return true;
}
@@ -1085,7 +1220,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
rdtgrp->mode = RDT_MODE_SHAREABLE;
} else if (!strcmp(buf, "exclusive")) {
if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
- rdt_last_cmd_printf("schemata overlaps\n");
ret = -EINVAL;
goto out;
}
@@ -1121,15 +1255,18 @@ out:
* computed by first dividing the total cache size by the CBM length to
* determine how many bytes each bit in the bitmask represents. The result
* is multiplied with the number of bits set in the bitmask.
+ *
+ * @cbm is unsigned long, even if only 32 bits are used to make the
+ * bitmap functions work correctly.
*/
unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
- struct rdt_domain *d, u32 cbm)
+ struct rdt_domain *d, unsigned long cbm)
{
struct cpu_cacheinfo *ci;
unsigned int size = 0;
int num_b, i;
- num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+ num_b = bitmap_weight(&cbm, r->cache.cbm_len);
ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
for (i = 0; i < ci->num_leaves; i++) {
if (ci->info_list[i].level == r->cache_level) {
@@ -1155,8 +1292,9 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
struct rdt_resource *r;
struct rdt_domain *d;
unsigned int size;
- bool sep = false;
- u32 cbm;
+ int ret = 0;
+ bool sep;
+ u32 ctrl;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
@@ -1165,15 +1303,23 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
}
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
- size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
- rdtgrp->plr->d,
- rdtgrp->plr->cbm);
- seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+ if (!rdtgrp->plr->d) {
+ rdt_last_cmd_clear();
+ rdt_last_cmd_puts("Cache domain offline\n");
+ ret = -ENODEV;
+ } else {
+ seq_printf(s, "%*s:", max_name_width,
+ rdtgrp->plr->r->name);
+ size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+ rdtgrp->plr->d,
+ rdtgrp->plr->cbm);
+ seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+ }
goto out;
}
for_each_alloc_enabled_rdt_resource(r) {
+ sep = false;
seq_printf(s, "%*s:", max_name_width, r->name);
list_for_each_entry(d, &r->domains, list) {
if (sep)
@@ -1181,8 +1327,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
size = 0;
} else {
- cbm = d->ctrl_val[rdtgrp->closid];
- size = rdtgroup_cbm_to_size(r, d, cbm);
+ ctrl = (!is_mba_sc(r) ?
+ d->ctrl_val[rdtgrp->closid] :
+ d->mbps_val[rdtgrp->closid]);
+ if (r->rid == RDT_RESOURCE_MBA)
+ size = ctrl;
+ else
+ size = rdtgroup_cbm_to_size(r, d, ctrl);
}
seq_printf(s, "%d=%u", d->id, size);
sep = true;
@@ -1193,7 +1344,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
out:
rdtgroup_kn_unlock(of->kn);
- return 0;
+ return ret;
}
/* rdtgroup information files for one cache resource. */
@@ -2327,28 +2478,48 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
*/
static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
{
+ struct rdt_resource *r_cdp = NULL;
+ struct rdt_domain *d_cdp = NULL;
u32 used_b = 0, unused_b = 0;
u32 closid = rdtgrp->closid;
struct rdt_resource *r;
+ unsigned long tmp_cbm;
enum rdtgrp_mode mode;
struct rdt_domain *d;
+ u32 peer_ctl, *ctrl;
int i, ret;
- u32 *ctrl;
for_each_alloc_enabled_rdt_resource(r) {
+ /*
+ * Only initialize default allocations for CBM cache
+ * resources
+ */
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
list_for_each_entry(d, &r->domains, list) {
+ rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
d->have_new_ctrl = false;
d->new_ctrl = r->cache.shareable_bits;
used_b = r->cache.shareable_bits;
ctrl = d->ctrl_val;
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
if (closid_allocated(i) && i != closid) {
mode = rdtgroup_mode_by_closid(i);
if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
break;
- used_b |= *ctrl;
+ /*
+ * If CDP is active include peer
+ * domain's usage to ensure there
+ * is no overlap with an exclusive
+ * group.
+ */
+ if (d_cdp)
+ peer_ctl = d_cdp->ctrl_val[i];
+ else
+ peer_ctl = 0;
+ used_b |= *ctrl | peer_ctl;
if (mode == RDT_MODE_SHAREABLE)
- d->new_ctrl |= *ctrl;
+ d->new_ctrl |= *ctrl | peer_ctl;
}
}
if (d->plr && d->plr->cbm > 0)
@@ -2361,9 +2532,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
* modify the CBM based on system availability.
*/
cbm_ensure_valid(&d->new_ctrl, r);
- if (bitmap_weight((unsigned long *) &d->new_ctrl,
- r->cache.cbm_len) <
- r->cache.min_cbm_bits) {
+ /*
+ * Assign the u32 CBM to an unsigned long to ensure
+ * that bitmap_weight() does not access out-of-bound
+ * memory.
+ */
+ tmp_cbm = d->new_ctrl;
+ if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
+ r->cache.min_cbm_bits) {
rdt_last_cmd_printf("no space on %s:%d\n",
r->name, d->id);
return -ENOSPC;
@@ -2373,6 +2549,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
}
for_each_alloc_enabled_rdt_resource(r) {
+ /*
+ * Only initialize default allocations for CBM cache
+ * resources
+ */
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
ret = update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("failed to initialize allocations\n");
@@ -2760,6 +2942,13 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
{
if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
seq_puts(seq, ",cdp");
+
+ if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
+ seq_puts(seq, ",cdpl2");
+
+ if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA]))
+ seq_puts(seq, ",mba_MBps");
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 97685a0c3175..27f394ac983f 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -38,9 +38,6 @@ static struct mce_log_buffer mcelog = {
static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
-/* User mode helper program triggered by machine check event */
-extern char mce_helper[128];
-
static int dev_mce_log(struct notifier_block *nb, unsigned long val,
void *data)
{
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index c805a06e14c3..1fc424c40a31 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -108,6 +108,9 @@ static void setup_inj_struct(struct mce *m)
memset(m, 0, sizeof(struct mce));
m->cpuvendor = boot_cpu_data.x86_vendor;
+ m->time = ktime_get_real_seconds();
+ m->cpuid = cpuid_eax(1);
+ m->microcode = boot_cpu_data.microcode;
}
/* Update fake mce registers on current CPU. */
@@ -576,6 +579,9 @@ static int inj_bank_set(void *data, u64 val)
m->bank = val;
do_inject();
+ /* Reset injection struct */
+ setup_inj_struct(&i_mce);
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index f34d89c01edc..44396d521987 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -336,7 +336,8 @@ int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) =
void __init mcheck_vendor_init_severity(void)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
mce_severity = mce_severity_amd;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 953b3ce92dcc..8cb3c02980cf 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -270,7 +270,7 @@ static void print_mce(struct mce *m)
{
__print_mce(m);
- if (m->cpuvendor != X86_VENDOR_AMD)
+ if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON)
pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
@@ -508,9 +508,9 @@ static int mce_usable_address(struct mce *m)
bool mce_is_memory_error(struct mce *m)
{
- if (m->cpuvendor == X86_VENDOR_AMD) {
+ if (m->cpuvendor == X86_VENDOR_AMD ||
+ m->cpuvendor == X86_VENDOR_HYGON) {
return amd_mce_is_memory_error(m);
-
} else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -539,6 +539,9 @@ static bool mce_is_correctable(struct mce *m)
if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
return false;
+ if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED)
+ return false;
+
if (m->status & MCI_STATUS_UC)
return false;
@@ -1315,7 +1318,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
local_irq_disable();
ist_end_non_atomic();
} else {
- if (!fixup_exception(regs, X86_TRAP_MC))
+ if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
mce_panic("Failed kernel mode recovery", &m, NULL);
}
@@ -1705,7 +1708,7 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
*/
static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
{
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR);
mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA);
@@ -1746,6 +1749,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
mce_amd_feature_init(c);
break;
}
+
+ case X86_VENDOR_HYGON:
+ mce_hygon_feature_init(c);
+ break;
+
case X86_VENDOR_CENTAUR:
mce_centaur_feature_init(c);
break;
@@ -1971,12 +1979,14 @@ static void mce_disable_error_reporting(void)
static void vendor_disable_error_reporting(void)
{
/*
- * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide.
+ * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
+ * are socket-wide.
* Disabling them for just a single offlined CPU is bad, since it will
* inhibit reporting for all shared resources on the socket like the
* last level cache (LLC), the integrated memory controller (iMC), etc.
*/
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
return;
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,
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index ad12733f6058..1c72f3819eb1 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -199,6 +199,16 @@ static unsigned long hv_get_tsc_khz(void)
return freq / 1000;
}
+#if defined(CONFIG_SMP) && IS_ENABLED(CONFIG_HYPERV)
+static void __init hv_smp_prepare_boot_cpu(void)
+{
+ native_smp_prepare_boot_cpu();
+#if defined(CONFIG_X86_64) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+ hv_init_spinlocks();
+#endif
+}
+#endif
+
static void __init ms_hyperv_init_platform(void)
{
int hv_host_info_eax;
@@ -303,6 +313,10 @@ static void __init ms_hyperv_init_platform(void)
if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
alloc_intr_gate(HYPERV_STIMER0_VECTOR,
hv_stimer0_callback_vector);
+
+# ifdef CONFIG_SMP
+ smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
+# endif
#endif
}
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 765afd599039..3668c5df90c6 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -831,7 +831,8 @@ int __init amd_special_default_mtrr(void)
{
u32 l, h;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return 0;
if (boot_cpu_data.x86 < 0xf)
return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 9a19c800fe40..507039c20128 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -127,7 +127,7 @@ static void __init set_num_var_ranges(void)
if (use_intel())
rdmsr(MSR_MTRRcap, config, dummy);
- else if (is_cpu(AMD))
+ else if (is_cpu(AMD) || is_cpu(HYGON))
config = 2;
else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
config = 8;
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d389083330c5..9556930cd8c1 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -46,6 +46,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the performance counter register */
switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTR)
return (msr - MSR_F15H_PERF_CTR) >> 1;
@@ -74,6 +75,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the event selection register */
switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTL)
return (msr - MSR_F15H_PERF_CTL) >> 1;
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 8e005329648b..d9ab49bed8af 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -97,14 +97,14 @@ static void __init vmware_sched_clock_setup(void)
d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul,
d->cyc2ns_shift);
- pv_time_ops.sched_clock = vmware_sched_clock;
+ pv_ops.time.sched_clock = vmware_sched_clock;
pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset);
}
static void __init vmware_paravirt_ops_setup(void)
{
pv_info.name = "VMware hypervisor";
- pv_cpu_ops.io_delay = paravirt_nop;
+ pv_ops.cpu.io_delay = paravirt_nop;
if (vmware_tsc_khz && vmw_sched_clock)
vmware_sched_clock_setup();
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 4f2e0778feac..eb8ab3915268 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -11,40 +11,62 @@
#include <linux/uaccess.h>
#include <linux/io.h>
-/**
- * copy_oldmem_page - copy one page from "oldmem"
- * @pfn: page frame number to be copied
- * @buf: target memory address for the copy; this can be in kernel address
- * space or user address space (see @userbuf)
- * @csize: number of bytes to copy
- * @offset: offset in bytes into the page (based on pfn) to begin the copy
- * @userbuf: if set, @buf is in user address space, use copy_to_user(),
- * otherwise @buf is in kernel address space, use memcpy().
- *
- * Copy a page from "oldmem". For this page, there is no pte mapped
- * in the current kernel. We stitch up a pte, similar to kmap_atomic.
- */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
- size_t csize, unsigned long offset, int userbuf)
+static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+ unsigned long offset, int userbuf,
+ bool encrypted)
{
void *vaddr;
if (!csize)
return 0;
- vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE);
+ if (encrypted)
+ vaddr = (__force void *)ioremap_encrypted(pfn << PAGE_SHIFT, PAGE_SIZE);
+ else
+ vaddr = (__force void *)ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE);
+
if (!vaddr)
return -ENOMEM;
if (userbuf) {
- if (copy_to_user(buf, vaddr + offset, csize)) {
- iounmap(vaddr);
+ if (copy_to_user((void __user *)buf, vaddr + offset, csize)) {
+ iounmap((void __iomem *)vaddr);
return -EFAULT;
}
} else
memcpy(buf, vaddr + offset, csize);
set_iounmap_nonlazy();
- iounmap(vaddr);
+ iounmap((void __iomem *)vaddr);
return csize;
}
+
+/**
+ * copy_oldmem_page - copy one page of memory
+ * @pfn: page frame number to be copied
+ * @buf: target memory address for the copy; this can be in kernel address
+ * space or user address space (see @userbuf)
+ * @csize: number of bytes to copy
+ * @offset: offset in bytes into the page (based on pfn) to begin the copy
+ * @userbuf: if set, @buf is in user address space, use copy_to_user(),
+ * otherwise @buf is in kernel address space, use memcpy().
+ *
+ * Copy a page from the old kernel's memory. For this page, there is no pte
+ * mapped in the current kernel. We stitch up a pte, similar to kmap_atomic.
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+ unsigned long offset, int userbuf)
+{
+ return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, false);
+}
+
+/**
+ * copy_oldmem_page_encrypted - same as copy_oldmem_page() above but ioremap the
+ * memory with the encryption mask set to accomodate kdump on SME-enabled
+ * machines.
+ */
+ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize,
+ unsigned long offset, int userbuf)
+{
+ return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, true);
+}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index f56895106ccf..2b5886401e5f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -146,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
* they can be printed in the right context.
*/
if (!partial && on_stack(info, regs, sizeof(*regs))) {
- __show_regs(regs, 0);
+ __show_regs(regs, SHOW_REGS_SHORT);
} else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
IRET_FRAME_SIZE)) {
@@ -344,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
oops_exit();
/* Executive summary in case the oops scrolled away */
- __show_regs(&exec_summary_regs, true);
+ __show_regs(&exec_summary_regs, SHOW_REGS_ALL);
if (!signr)
return;
@@ -407,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err)
void show_regs(struct pt_regs *regs)
{
- bool all = true;
-
show_regs_print_info(KERN_DEFAULT);
- if (IS_ENABLED(CONFIG_X86_32))
- all = !user_mode(regs);
-
- __show_regs(regs, all);
+ __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL);
/*
* When in-kernel, we also print out the stack at the time of the fault..
diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c
index f260e452e4f8..e8c8c5d78dbd 100644
--- a/arch/x86/kernel/eisa.c
+++ b/arch/x86/kernel/eisa.c
@@ -7,11 +7,17 @@
#include <linux/eisa.h>
#include <linux/io.h>
+#include <xen/xen.h>
+
static __init int eisa_bus_probe(void)
{
- void __iomem *p = ioremap(0x0FFFD9, 4);
+ void __iomem *p;
+
+ if (xen_pv_domain() && !xen_initial_domain())
+ return 0;
- if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24))
+ p = ioremap(0x0FFFD9, 4);
+ if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24))
EISA_bus = 1;
iounmap(p);
return 0;
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 23f1691670b6..61a949d84dfa 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -314,7 +314,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
* thread's fpu state, reconstruct fxstate from the fsave
* header. Validate and sanitize the copied state.
*/
- struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
int err = 0;
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index ec6fefbfd3c0..76fa3b836598 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -37,6 +37,7 @@ asmlinkage __visible void __init i386_start_kernel(void)
cr4_init_shadow();
sanitize_boot_params(&boot_params);
+ x86_verify_bootdata_version();
x86_early_init_platform_quirks();
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 8047379e575a..5dc377dc9d7b 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -35,6 +35,7 @@
#include <asm/bootparam_utils.h>
#include <asm/microcode.h>
#include <asm/kasan.h>
+#include <asm/fixmap.h>
/*
* Manage page tables very early on.
@@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr)
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
+ unsigned long vaddr, vaddr_end;
unsigned long load_delta, *p;
unsigned long pgtable_flags;
pgdval_t *pgd;
@@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
pud[511] += load_delta;
pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
- pmd[506] += load_delta;
+ for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+ pmd[i] += load_delta;
/*
* Set up the identity mapping for the switchover. These
@@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr,
sme_encrypt_kernel(bp);
/*
+ * Clear the memory encryption mask from the .bss..decrypted section.
+ * The bss section will be memset to zero later in the initialization so
+ * there is no need to zero it after changing the memory encryption
+ * attribute.
+ */
+ if (mem_encrypt_active()) {
+ vaddr = (unsigned long)__start_bss_decrypted;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+ for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+ i = pmd_index(vaddr);
+ pmd[i] -= sme_get_me_mask();
+ }
+ }
+
+ /*
* Return the SME encryption mask (if SME is active) to be used as a
* modifier for the initial pgdir entry programmed into CR3.
*/
@@ -439,6 +457,8 @@ void __init x86_64_start_reservations(char *real_mode_data)
if (!boot_params.hdr.version)
copy_bootdata(__va(real_mode_data));
+ x86_verify_bootdata_version();
+
x86_early_init_platform_quirks();
switch (boot_params.hdr.hardware_subarch) {
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 15ebc2fc166e..747c758f67b7 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -24,8 +24,9 @@
#include "../entry/calling.h"
#include <asm/export.h>
#include <asm/nospec-branch.h>
+#include <asm/fixmap.h>
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
#include <asm/asm-offsets.h>
#include <asm/paravirt.h>
#define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg
@@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt)
KERNEL_IMAGE_SIZE/PMD_SIZE)
NEXT_PAGE(level2_fixmap_pgt)
- .fill 506,8,0
- .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
- /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
- .fill 5,8,0
+ .fill (512 - 4 - FIXMAP_PMD_NUM),8,0
+ pgtno = 0
+ .rept (FIXMAP_PMD_NUM)
+ .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \
+ + _PAGE_TABLE_NOENC;
+ pgtno = pgtno + 1
+ .endr
+ /* 6 MB reserved space + a 2MB hole */
+ .fill 4,8,0
NEXT_PAGE(level1_fixmap_pgt)
+ .rept (FIXMAP_PMD_NUM)
.fill 512,8,0
+ .endr
#undef PMDS
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index eeea935e9bb5..aac0c1f7e354 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -42,55 +42,40 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
void *(*poker)(void *, const void *, size_t),
int init)
{
- union jump_code_union code;
+ union jump_code_union jmp;
const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+ const void *expect, *code;
+ int line;
+
+ jmp.jump = 0xe9;
+ jmp.offset = jump_entry_target(entry) -
+ (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
if (early_boot_irqs_disabled)
poker = text_poke_early;
if (type == JUMP_LABEL_JMP) {
if (init) {
- /*
- * Jump label is enabled for the first time.
- * So we expect a default_nop...
- */
- if (unlikely(memcmp((void *)entry->code, default_nop, 5)
- != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = default_nop; line = __LINE__;
} else {
- /*
- * ...otherwise expect an ideal_nop. Otherwise
- * something went horribly wrong.
- */
- if (unlikely(memcmp((void *)entry->code, ideal_nop, 5)
- != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = ideal_nop; line = __LINE__;
}
- code.jump = 0xe9;
- code.offset = entry->target -
- (entry->code + JUMP_LABEL_NOP_SIZE);
+ code = &jmp.code;
} else {
- /*
- * We are disabling this jump label. If it is not what
- * we think it is, then something must have gone wrong.
- * If this is the first initialization call, then we
- * are converting the default nop to the ideal nop.
- */
if (init) {
- if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = default_nop; line = __LINE__;
} else {
- code.jump = 0xe9;
- code.offset = entry->target -
- (entry->code + JUMP_LABEL_NOP_SIZE);
- if (unlikely(memcmp((void *)entry->code, &code, 5) != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = &jmp.code; line = __LINE__;
}
- memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
+
+ code = ideal_nop;
}
+ if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE))
+ bug_at((void *)jump_entry_code(entry), line);
+
/*
* Make text_poke_bp() a default fallback poker.
*
@@ -99,11 +84,14 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
* always nop being the 'currently valid' instruction
*
*/
- if (poker)
- (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
- else
- text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE,
- (void *)entry->code + JUMP_LABEL_NOP_SIZE);
+ if (poker) {
+ (*poker)((void *)jump_entry_code(entry), code,
+ JUMP_LABEL_NOP_SIZE);
+ return;
+ }
+
+ text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
+ (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
}
void arch_jump_label_transform(struct jump_entry *entry,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index b0d1e81c96bb..c33b06f5faa4 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1020,64 +1020,18 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
*/
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
-
- /*
- * In case the user-specified fault handler returned
- * zero, try to fix up.
- */
- if (fixup_exception(regs, trapnr))
- return 1;
-
- /*
- * fixup routine could not handle it,
- * Let do_page_fault() fix it.
- */
}
return 0;
}
NOKPROBE_SYMBOL(kprobe_fault_handler);
-/*
- * Wrapper routine for handling exceptions.
- */
-int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
- void *data)
-{
- struct die_args *args = data;
- int ret = NOTIFY_DONE;
-
- if (args->regs && user_mode(args->regs))
- return ret;
-
- if (val == DIE_GPF) {
- /*
- * To be potentially processing a kprobe fault and to
- * trust the result from kprobe_running(), we have
- * be non-preemptible.
- */
- if (!preemptible() && kprobe_running() &&
- kprobe_fault_handler(args->regs, args->trapnr))
- ret = NOTIFY_STOP;
- }
- return ret;
-}
-NOKPROBE_SYMBOL(kprobe_exceptions_notify);
-
bool arch_within_kprobe_blacklist(unsigned long addr)
{
- bool is_in_entry_trampoline_section = false;
-
-#ifdef CONFIG_X86_64
- is_in_entry_trampoline_section =
- (addr >= (unsigned long)__entry_trampoline_start &&
- addr < (unsigned long)__entry_trampoline_end);
-#endif
return (addr >= (unsigned long)__kprobes_text_start &&
addr < (unsigned long)__kprobes_text_end) ||
(addr >= (unsigned long)__entry_text_start &&
- addr < (unsigned long)__entry_text_end) ||
- is_in_entry_trampoline_section;
+ addr < (unsigned long)__entry_text_end);
}
int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index eaf02f2e7300..40b16b270656 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -179,7 +179,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
opt_pre_handler(&op->kp, regs);
__this_cpu_write(current_kprobe, NULL);
}
- preempt_enable_no_resched();
+ preempt_enable();
}
NOKPROBE_SYMBOL(optimized_callback);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d9b71924c23c..ba4bfb7f6a36 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -283,7 +283,7 @@ static void __init paravirt_ops_setup(void)
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
- pv_cpu_ops.io_delay = kvm_io_delay;
+ pv_ops.cpu.io_delay = kvm_io_delay;
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
@@ -632,14 +632,14 @@ static void __init kvm_guest_init(void)
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
- pv_time_ops.steal_clock = kvm_steal_clock;
+ pv_ops.time.steal_clock = kvm_steal_clock;
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
- pv_mmu_ops.tlb_remove_table = tlb_remove_table;
+ pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
+ pv_ops.mmu.tlb_remove_table = tlb_remove_table;
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -850,13 +850,14 @@ void __init kvm_spinlock_init(void)
return;
__pv_init_lock_hash();
- pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_lock_ops.wait = kvm_wait;
- pv_lock_ops.kick = kvm_kick_cpu;
+ pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops.lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops.lock.wait = kvm_wait;
+ pv_ops.lock.kick = kvm_kick_cpu;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_lock_ops.vcpu_is_preempted =
+ pv_ops.lock.vcpu_is_preempted =
PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
}
}
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1e6764648af3..30084ecaa20f 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -28,6 +28,7 @@
#include <linux/sched/clock.h>
#include <linux/mm.h>
#include <linux/slab.h>
+#include <linux/set_memory.h>
#include <asm/hypervisor.h>
#include <asm/mem_encrypt.h>
@@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
static struct pvclock_vsyscall_time_info
- hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
-static struct pvclock_wall_clock wall_clock;
+ hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock __bss_decrypted;
static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+static struct pvclock_vsyscall_time_info *hvclock_mem;
static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
{
@@ -116,13 +118,13 @@ static u64 kvm_sched_clock_read(void)
static inline void kvm_sched_clock_init(bool stable)
{
if (!stable) {
- pv_time_ops.sched_clock = kvm_clock_read;
+ pv_ops.time.sched_clock = kvm_clock_read;
clear_sched_clock_stable();
return;
}
kvm_sched_clock_offset = kvm_clock_read();
- pv_time_ops.sched_clock = kvm_sched_clock_read;
+ pv_ops.time.sched_clock = kvm_sched_clock_read;
pr_info("kvm-clock: using sched offset of %llu cycles",
kvm_sched_clock_offset);
@@ -236,6 +238,45 @@ static void kvm_shutdown(void)
native_machine_shutdown();
}
+static void __init kvmclock_init_mem(void)
+{
+ unsigned long ncpus;
+ unsigned int order;
+ struct page *p;
+ int r;
+
+ if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus())
+ return;
+
+ ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE;
+ order = get_order(ncpus * sizeof(*hvclock_mem));
+
+ p = alloc_pages(GFP_KERNEL, order);
+ if (!p) {
+ pr_warn("%s: failed to alloc %d pages", __func__, (1U << order));
+ return;
+ }
+
+ hvclock_mem = page_address(p);
+
+ /*
+ * hvclock is shared between the guest and the hypervisor, must
+ * be mapped decrypted.
+ */
+ if (sev_active()) {
+ r = set_memory_decrypted((unsigned long) hvclock_mem,
+ 1UL << order);
+ if (r) {
+ __free_pages(p, order);
+ hvclock_mem = NULL;
+ pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n");
+ return;
+ }
+ }
+
+ memset(hvclock_mem, 0, PAGE_SIZE << order);
+}
+
static int __init kvm_setup_vsyscall_timeinfo(void)
{
#ifdef CONFIG_X86_64
@@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void)
kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
#endif
+
+ kvmclock_init_mem();
+
return 0;
}
early_initcall(kvm_setup_vsyscall_timeinfo);
@@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu)
/* Use the static page for the first CPUs, allocate otherwise */
if (cpu < HVC_BOOT_ARRAY_SIZE)
p = &hv_clock_boot[cpu];
+ else if (hvclock_mem)
+ p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE;
else
- p = kzalloc(sizeof(*p), GFP_KERNEL);
+ return -ENOMEM;
per_cpu(hv_clock_per_cpu, cpu) = p;
return p ? 0 : -ENOMEM;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 733e6ace0fa4..ab18e0884dc6 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -273,7 +273,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
map_ldt_struct_to_user(mm);
va = (unsigned long)ldt_slot_va(slot);
- flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+ flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false);
ldt->slot = slot;
return 0;
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
new file mode 100644
index 000000000000..161c95059044
--- /dev/null
+++ b/arch/x86/kernel/macros.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file includes headers whose assembly part includes macros which are
+ * commonly used. The macros are precompiled into assmebly file which is later
+ * assembled together with each compiled file.
+ */
+
+#include <linux/compiler.h>
+#include <asm/refcount.h>
+#include <asm/alternative-asm.h>
+#include <asm/bug.h>
+#include <asm/paravirt.h>
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/jump_label.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index f58336af095c..b052e883dd8c 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -201,6 +201,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
goto overflow;
#endif
break;
+ case R_X86_64_PC64:
+ if (*(u64 *)loc != 0)
+ goto invalid_relocation;
+ val -= (u64)loc;
+ *(u64 *)loc = val;
+ break;
default:
pr_err("%s: Unknown rela relocation: %llu\n",
me->name, ELF64_R_TYPE(rel[i].r_info));
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 71f2d1125ec0..4f75d0cf6305 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -17,7 +17,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
bool pv_is_native_spin_unlock(void)
{
- return pv_lock_ops.queued_spin_unlock.func ==
+ return pv_ops.lock.queued_spin_unlock.func ==
__raw_callee_save___native_queued_spin_unlock;
}
@@ -29,17 +29,6 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
bool pv_is_native_vcpu_is_preempted(void)
{
- return pv_lock_ops.vcpu_is_preempted.func ==
+ return pv_ops.lock.vcpu_is_preempted.func ==
__raw_callee_save___native_vcpu_is_preempted;
}
-
-struct pv_lock_ops pv_lock_ops = {
-#ifdef CONFIG_SMP
- .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
- .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
- .wait = paravirt_nop,
- .kick = paravirt_nop,
- .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
-#endif /* SMP */
-};
-EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index afdb303285f8..e4d4df37922a 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -81,17 +81,15 @@ struct branch {
u32 delta;
} __attribute__((packed));
-unsigned paravirt_patch_call(void *insnbuf,
- const void *target, u16 tgt_clobbers,
- unsigned long addr, u16 site_clobbers,
- unsigned len)
+static unsigned paravirt_patch_call(void *insnbuf, const void *target,
+ unsigned long addr, unsigned len)
{
struct branch *b = insnbuf;
unsigned long delta = (unsigned long)target - (addr+5);
if (len < 5) {
#ifdef CONFIG_RETPOLINE
- WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+ WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr);
#endif
return len; /* call too long for patch site */
}
@@ -103,15 +101,16 @@ unsigned paravirt_patch_call(void *insnbuf,
return 5;
}
-unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
- unsigned long addr, unsigned len)
+#ifdef CONFIG_PARAVIRT_XXL
+static unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
+ unsigned long addr, unsigned len)
{
struct branch *b = insnbuf;
unsigned long delta = (unsigned long)target - (addr+5);
if (len < 5) {
#ifdef CONFIG_RETPOLINE
- WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+ WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
#endif
return len; /* call too long for patch site */
}
@@ -121,6 +120,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
return 5;
}
+#endif
DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
@@ -130,29 +130,14 @@ void __init native_pv_lock_init(void)
static_branch_disable(&virt_spin_lock_key);
}
-/*
- * Neat trick to map patch type back to the call within the
- * corresponding structure.
- */
-static void *get_call_destination(u8 type)
-{
- struct paravirt_patch_template tmpl = {
- .pv_init_ops = pv_init_ops,
- .pv_time_ops = pv_time_ops,
- .pv_cpu_ops = pv_cpu_ops,
- .pv_irq_ops = pv_irq_ops,
- .pv_mmu_ops = pv_mmu_ops,
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
- .pv_lock_ops = pv_lock_ops,
-#endif
- };
- return *((void **)&tmpl + type);
-}
-
-unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
+unsigned paravirt_patch_default(u8 type, void *insnbuf,
unsigned long addr, unsigned len)
{
- void *opfunc = get_call_destination(type);
+ /*
+ * Neat trick to map patch type back to the call within the
+ * corresponding structure.
+ */
+ void *opfunc = *((void **)&pv_ops + type);
unsigned ret;
if (opfunc == NULL)
@@ -167,15 +152,15 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
else if (opfunc == _paravirt_ident_64)
ret = paravirt_patch_ident_64(insnbuf, len);
- else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
- type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
+#ifdef CONFIG_PARAVIRT_XXL
+ else if (type == PARAVIRT_PATCH(cpu.iret) ||
+ type == PARAVIRT_PATCH(cpu.usergs_sysret64))
/* If operation requires a jmp, then jmp */
ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
+#endif
else
- /* Otherwise call the function; assume target could
- clobber any caller-save reg */
- ret = paravirt_patch_call(insnbuf, opfunc, CLBR_ANY,
- addr, clobbers, len);
+ /* Otherwise call the function. */
+ ret = paravirt_patch_call(insnbuf, opfunc, addr, len);
return ret;
}
@@ -281,6 +266,7 @@ void paravirt_flush_lazy_mmu(void)
preempt_enable();
}
+#ifdef CONFIG_PARAVIRT_XXL
void paravirt_start_context_switch(struct task_struct *prev)
{
BUG_ON(preemptible());
@@ -301,6 +287,7 @@ void paravirt_end_context_switch(struct task_struct *next)
if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
arch_enter_lazy_mmu_mode();
}
+#endif
enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
{
@@ -312,85 +299,16 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
struct pv_info pv_info = {
.name = "bare hardware",
+#ifdef CONFIG_PARAVIRT_XXL
.kernel_rpl = 0,
.shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
#ifdef CONFIG_X86_64
.extra_user_64bit_cs = __USER_CS,
#endif
-};
-
-struct pv_init_ops pv_init_ops = {
- .patch = native_patch,
-};
-
-struct pv_time_ops pv_time_ops = {
- .sched_clock = native_sched_clock,
- .steal_clock = native_steal_clock,
-};
-
-__visible struct pv_irq_ops pv_irq_ops = {
- .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
- .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
- .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
- .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
- .safe_halt = native_safe_halt,
- .halt = native_halt,
-};
-
-__visible struct pv_cpu_ops pv_cpu_ops = {
- .cpuid = native_cpuid,
- .get_debugreg = native_get_debugreg,
- .set_debugreg = native_set_debugreg,
- .read_cr0 = native_read_cr0,
- .write_cr0 = native_write_cr0,
- .write_cr4 = native_write_cr4,
-#ifdef CONFIG_X86_64
- .read_cr8 = native_read_cr8,
- .write_cr8 = native_write_cr8,
#endif
- .wbinvd = native_wbinvd,
- .read_msr = native_read_msr,
- .write_msr = native_write_msr,
- .read_msr_safe = native_read_msr_safe,
- .write_msr_safe = native_write_msr_safe,
- .read_pmc = native_read_pmc,
- .load_tr_desc = native_load_tr_desc,
- .set_ldt = native_set_ldt,
- .load_gdt = native_load_gdt,
- .load_idt = native_load_idt,
- .store_tr = native_store_tr,
- .load_tls = native_load_tls,
-#ifdef CONFIG_X86_64
- .load_gs_index = native_load_gs_index,
-#endif
- .write_ldt_entry = native_write_ldt_entry,
- .write_gdt_entry = native_write_gdt_entry,
- .write_idt_entry = native_write_idt_entry,
-
- .alloc_ldt = paravirt_nop,
- .free_ldt = paravirt_nop,
-
- .load_sp0 = native_load_sp0,
-
-#ifdef CONFIG_X86_64
- .usergs_sysret64 = native_usergs_sysret64,
-#endif
- .iret = native_iret,
- .swapgs = native_swapgs,
-
- .set_iopl_mask = native_set_iopl_mask,
- .io_delay = native_io_delay,
-
- .start_context_switch = paravirt_nop,
- .end_context_switch = paravirt_nop,
};
-/* At this point, native_get/set_debugreg has real function entries */
-NOKPROBE_SYMBOL(native_get_debugreg);
-NOKPROBE_SYMBOL(native_set_debugreg);
-NOKPROBE_SYMBOL(native_load_idt);
-
#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
/* 32-bit pagetable entries */
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32)
@@ -399,85 +317,171 @@ NOKPROBE_SYMBOL(native_load_idt);
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
#endif
-struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
+struct paravirt_patch_template pv_ops = {
+ /* Init ops. */
+ .init.patch = native_patch,
- .read_cr2 = native_read_cr2,
- .write_cr2 = native_write_cr2,
- .read_cr3 = __native_read_cr3,
- .write_cr3 = native_write_cr3,
+ /* Time ops. */
+ .time.sched_clock = native_sched_clock,
+ .time.steal_clock = native_steal_clock,
- .flush_tlb_user = native_flush_tlb,
- .flush_tlb_kernel = native_flush_tlb_global,
- .flush_tlb_one_user = native_flush_tlb_one_user,
- .flush_tlb_others = native_flush_tlb_others,
- .tlb_remove_table = (void (*)(struct mmu_gather *, void *))tlb_remove_page,
+ /* Cpu ops. */
+ .cpu.io_delay = native_io_delay,
- .pgd_alloc = __paravirt_pgd_alloc,
- .pgd_free = paravirt_nop,
+#ifdef CONFIG_PARAVIRT_XXL
+ .cpu.cpuid = native_cpuid,
+ .cpu.get_debugreg = native_get_debugreg,
+ .cpu.set_debugreg = native_set_debugreg,
+ .cpu.read_cr0 = native_read_cr0,
+ .cpu.write_cr0 = native_write_cr0,
+ .cpu.write_cr4 = native_write_cr4,
+#ifdef CONFIG_X86_64
+ .cpu.read_cr8 = native_read_cr8,
+ .cpu.write_cr8 = native_write_cr8,
+#endif
+ .cpu.wbinvd = native_wbinvd,
+ .cpu.read_msr = native_read_msr,
+ .cpu.write_msr = native_write_msr,
+ .cpu.read_msr_safe = native_read_msr_safe,
+ .cpu.write_msr_safe = native_write_msr_safe,
+ .cpu.read_pmc = native_read_pmc,
+ .cpu.load_tr_desc = native_load_tr_desc,
+ .cpu.set_ldt = native_set_ldt,
+ .cpu.load_gdt = native_load_gdt,
+ .cpu.load_idt = native_load_idt,
+ .cpu.store_tr = native_store_tr,
+ .cpu.load_tls = native_load_tls,
+#ifdef CONFIG_X86_64
+ .cpu.load_gs_index = native_load_gs_index,
+#endif
+ .cpu.write_ldt_entry = native_write_ldt_entry,
+ .cpu.write_gdt_entry = native_write_gdt_entry,
+ .cpu.write_idt_entry = native_write_idt_entry,
- .alloc_pte = paravirt_nop,
- .alloc_pmd = paravirt_nop,
- .alloc_pud = paravirt_nop,
- .alloc_p4d = paravirt_nop,
- .release_pte = paravirt_nop,
- .release_pmd = paravirt_nop,
- .release_pud = paravirt_nop,
- .release_p4d = paravirt_nop,
+ .cpu.alloc_ldt = paravirt_nop,
+ .cpu.free_ldt = paravirt_nop,
- .set_pte = native_set_pte,
- .set_pte_at = native_set_pte_at,
- .set_pmd = native_set_pmd,
+ .cpu.load_sp0 = native_load_sp0,
- .ptep_modify_prot_start = __ptep_modify_prot_start,
- .ptep_modify_prot_commit = __ptep_modify_prot_commit,
+#ifdef CONFIG_X86_64
+ .cpu.usergs_sysret64 = native_usergs_sysret64,
+#endif
+ .cpu.iret = native_iret,
+ .cpu.swapgs = native_swapgs,
+
+ .cpu.set_iopl_mask = native_set_iopl_mask,
+
+ .cpu.start_context_switch = paravirt_nop,
+ .cpu.end_context_switch = paravirt_nop,
+
+ /* Irq ops. */
+ .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
+ .irq.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+ .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
+ .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
+ .irq.safe_halt = native_safe_halt,
+ .irq.halt = native_halt,
+#endif /* CONFIG_PARAVIRT_XXL */
+
+ /* Mmu ops. */
+ .mmu.flush_tlb_user = native_flush_tlb,
+ .mmu.flush_tlb_kernel = native_flush_tlb_global,
+ .mmu.flush_tlb_one_user = native_flush_tlb_one_user,
+ .mmu.flush_tlb_others = native_flush_tlb_others,
+ .mmu.tlb_remove_table =
+ (void (*)(struct mmu_gather *, void *))tlb_remove_page,
+
+ .mmu.exit_mmap = paravirt_nop,
+
+#ifdef CONFIG_PARAVIRT_XXL
+ .mmu.read_cr2 = native_read_cr2,
+ .mmu.write_cr2 = native_write_cr2,
+ .mmu.read_cr3 = __native_read_cr3,
+ .mmu.write_cr3 = native_write_cr3,
+
+ .mmu.pgd_alloc = __paravirt_pgd_alloc,
+ .mmu.pgd_free = paravirt_nop,
+
+ .mmu.alloc_pte = paravirt_nop,
+ .mmu.alloc_pmd = paravirt_nop,
+ .mmu.alloc_pud = paravirt_nop,
+ .mmu.alloc_p4d = paravirt_nop,
+ .mmu.release_pte = paravirt_nop,
+ .mmu.release_pmd = paravirt_nop,
+ .mmu.release_pud = paravirt_nop,
+ .mmu.release_p4d = paravirt_nop,
+
+ .mmu.set_pte = native_set_pte,
+ .mmu.set_pte_at = native_set_pte_at,
+ .mmu.set_pmd = native_set_pmd,
+
+ .mmu.ptep_modify_prot_start = __ptep_modify_prot_start,
+ .mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit,
#if CONFIG_PGTABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
- .set_pte_atomic = native_set_pte_atomic,
- .pte_clear = native_pte_clear,
- .pmd_clear = native_pmd_clear,
+ .mmu.set_pte_atomic = native_set_pte_atomic,
+ .mmu.pte_clear = native_pte_clear,
+ .mmu.pmd_clear = native_pmd_clear,
#endif
- .set_pud = native_set_pud,
+ .mmu.set_pud = native_set_pud,
- .pmd_val = PTE_IDENT,
- .make_pmd = PTE_IDENT,
+ .mmu.pmd_val = PTE_IDENT,
+ .mmu.make_pmd = PTE_IDENT,
#if CONFIG_PGTABLE_LEVELS >= 4
- .pud_val = PTE_IDENT,
- .make_pud = PTE_IDENT,
+ .mmu.pud_val = PTE_IDENT,
+ .mmu.make_pud = PTE_IDENT,
- .set_p4d = native_set_p4d,
+ .mmu.set_p4d = native_set_p4d,
#if CONFIG_PGTABLE_LEVELS >= 5
- .p4d_val = PTE_IDENT,
- .make_p4d = PTE_IDENT,
+ .mmu.p4d_val = PTE_IDENT,
+ .mmu.make_p4d = PTE_IDENT,
- .set_pgd = native_set_pgd,
+ .mmu.set_pgd = native_set_pgd,
#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
#endif /* CONFIG_PGTABLE_LEVELS >= 3 */
- .pte_val = PTE_IDENT,
- .pgd_val = PTE_IDENT,
+ .mmu.pte_val = PTE_IDENT,
+ .mmu.pgd_val = PTE_IDENT,
- .make_pte = PTE_IDENT,
- .make_pgd = PTE_IDENT,
+ .mmu.make_pte = PTE_IDENT,
+ .mmu.make_pgd = PTE_IDENT,
- .dup_mmap = paravirt_nop,
- .exit_mmap = paravirt_nop,
- .activate_mm = paravirt_nop,
+ .mmu.dup_mmap = paravirt_nop,
+ .mmu.activate_mm = paravirt_nop,
- .lazy_mode = {
- .enter = paravirt_nop,
- .leave = paravirt_nop,
- .flush = paravirt_nop,
+ .mmu.lazy_mode = {
+ .enter = paravirt_nop,
+ .leave = paravirt_nop,
+ .flush = paravirt_nop,
},
- .set_fixmap = native_set_fixmap,
+ .mmu.set_fixmap = native_set_fixmap,
+#endif /* CONFIG_PARAVIRT_XXL */
+
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
+ /* Lock ops. */
+#ifdef CONFIG_SMP
+ .lock.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .lock.wait = paravirt_nop,
+ .lock.kick = paravirt_nop,
+ .lock.vcpu_is_preempted =
+ PV_CALLEE_SAVE(__native_vcpu_is_preempted),
+#endif /* SMP */
+#endif
};
-EXPORT_SYMBOL_GPL(pv_time_ops);
-EXPORT_SYMBOL (pv_cpu_ops);
-EXPORT_SYMBOL (pv_mmu_ops);
+#ifdef CONFIG_PARAVIRT_XXL
+/* At this point, native_get/set_debugreg has real function entries */
+NOKPROBE_SYMBOL(native_get_debugreg);
+NOKPROBE_SYMBOL(native_set_debugreg);
+NOKPROBE_SYMBOL(native_load_idt);
+#endif
+
+EXPORT_SYMBOL_GPL(pv_ops);
EXPORT_SYMBOL_GPL(pv_info);
-EXPORT_SYMBOL (pv_irq_ops);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 758e69d72ebf..6368c22fa1fa 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -1,18 +1,20 @@
// SPDX-License-Identifier: GPL-2.0
#include <asm/paravirt.h>
-DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
-DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
-DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
-DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
-DEF_NATIVE(pv_cpu_ops, iret, "iret");
-DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
-DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
-DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
+#ifdef CONFIG_PARAVIRT_XXL
+DEF_NATIVE(irq, irq_disable, "cli");
+DEF_NATIVE(irq, irq_enable, "sti");
+DEF_NATIVE(irq, restore_fl, "push %eax; popf");
+DEF_NATIVE(irq, save_fl, "pushf; pop %eax");
+DEF_NATIVE(cpu, iret, "iret");
+DEF_NATIVE(mmu, read_cr2, "mov %cr2, %eax");
+DEF_NATIVE(mmu, write_cr3, "mov %eax, %cr3");
+DEF_NATIVE(mmu, read_cr3, "mov %cr3, %eax");
+#endif
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
-DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
+DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%eax)");
+DEF_NATIVE(lock, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -30,53 +32,42 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
extern bool pv_is_native_spin_unlock(void);
extern bool pv_is_native_vcpu_is_preempted(void);
-unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
- unsigned long addr, unsigned len)
+unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
{
- const unsigned char *start, *end;
- unsigned ret;
-
#define PATCH_SITE(ops, x) \
- case PARAVIRT_PATCH(ops.x): \
- start = start_##ops##_##x; \
- end = end_##ops##_##x; \
- goto patch_site
+ case PARAVIRT_PATCH(ops.x): \
+ return paravirt_patch_insns(ibuf, len, start_##ops##_##x, end_##ops##_##x)
+
switch (type) {
- PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_irq_ops, irq_enable);
- PATCH_SITE(pv_irq_ops, restore_fl);
- PATCH_SITE(pv_irq_ops, save_fl);
- PATCH_SITE(pv_cpu_ops, iret);
- PATCH_SITE(pv_mmu_ops, read_cr2);
- PATCH_SITE(pv_mmu_ops, read_cr3);
- PATCH_SITE(pv_mmu_ops, write_cr3);
+#ifdef CONFIG_PARAVIRT_XXL
+ PATCH_SITE(irq, irq_disable);
+ PATCH_SITE(irq, irq_enable);
+ PATCH_SITE(irq, restore_fl);
+ PATCH_SITE(irq, save_fl);
+ PATCH_SITE(cpu, iret);
+ PATCH_SITE(mmu, read_cr2);
+ PATCH_SITE(mmu, read_cr3);
+ PATCH_SITE(mmu, write_cr3);
+#endif
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
- case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
- if (pv_is_native_spin_unlock()) {
- start = start_pv_lock_ops_queued_spin_unlock;
- end = end_pv_lock_ops_queued_spin_unlock;
- goto patch_site;
- }
- goto patch_default;
+ case PARAVIRT_PATCH(lock.queued_spin_unlock):
+ if (pv_is_native_spin_unlock())
+ return paravirt_patch_insns(ibuf, len,
+ start_lock_queued_spin_unlock,
+ end_lock_queued_spin_unlock);
+ break;
- case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
- if (pv_is_native_vcpu_is_preempted()) {
- start = start_pv_lock_ops_vcpu_is_preempted;
- end = end_pv_lock_ops_vcpu_is_preempted;
- goto patch_site;
- }
- goto patch_default;
+ case PARAVIRT_PATCH(lock.vcpu_is_preempted):
+ if (pv_is_native_vcpu_is_preempted())
+ return paravirt_patch_insns(ibuf, len,
+ start_lock_vcpu_is_preempted,
+ end_lock_vcpu_is_preempted);
+ break;
#endif
default:
-patch_default: __maybe_unused
- ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
- break;
-
-patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
break;
}
#undef PATCH_SITE
- return ret;
+ return paravirt_patch_default(type, ibuf, addr, len);
}
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 9cb98f7b07c9..7ca9cb726f4d 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -3,24 +3,26 @@
#include <asm/asm-offsets.h>
#include <linux/stringify.h>
-DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
-DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
-DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
-DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
-DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
-DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
+#ifdef CONFIG_PARAVIRT_XXL
+DEF_NATIVE(irq, irq_disable, "cli");
+DEF_NATIVE(irq, irq_enable, "sti");
+DEF_NATIVE(irq, restore_fl, "pushq %rdi; popfq");
+DEF_NATIVE(irq, save_fl, "pushfq; popq %rax");
+DEF_NATIVE(mmu, read_cr2, "movq %cr2, %rax");
+DEF_NATIVE(mmu, read_cr3, "movq %cr3, %rax");
+DEF_NATIVE(mmu, write_cr3, "movq %rdi, %cr3");
+DEF_NATIVE(cpu, wbinvd, "wbinvd");
-DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
-DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
+DEF_NATIVE(cpu, usergs_sysret64, "swapgs; sysretq");
+DEF_NATIVE(cpu, swapgs, "swapgs");
+#endif
DEF_NATIVE(, mov32, "mov %edi, %eax");
DEF_NATIVE(, mov64, "mov %rdi, %rax");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
-DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
+DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%rdi)");
+DEF_NATIVE(lock, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -38,55 +40,44 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
extern bool pv_is_native_spin_unlock(void);
extern bool pv_is_native_vcpu_is_preempted(void);
-unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
- unsigned long addr, unsigned len)
+unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len)
{
- const unsigned char *start, *end;
- unsigned ret;
-
#define PATCH_SITE(ops, x) \
- case PARAVIRT_PATCH(ops.x): \
- start = start_##ops##_##x; \
- end = end_##ops##_##x; \
- goto patch_site
- switch(type) {
- PATCH_SITE(pv_irq_ops, restore_fl);
- PATCH_SITE(pv_irq_ops, save_fl);
- PATCH_SITE(pv_irq_ops, irq_enable);
- PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, usergs_sysret64);
- PATCH_SITE(pv_cpu_ops, swapgs);
- PATCH_SITE(pv_mmu_ops, read_cr2);
- PATCH_SITE(pv_mmu_ops, read_cr3);
- PATCH_SITE(pv_mmu_ops, write_cr3);
- PATCH_SITE(pv_cpu_ops, wbinvd);
-#if defined(CONFIG_PARAVIRT_SPINLOCKS)
- case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
- if (pv_is_native_spin_unlock()) {
- start = start_pv_lock_ops_queued_spin_unlock;
- end = end_pv_lock_ops_queued_spin_unlock;
- goto patch_site;
- }
- goto patch_default;
+ case PARAVIRT_PATCH(ops.x): \
+ return paravirt_patch_insns(ibuf, len, start_##ops##_##x, end_##ops##_##x)
- case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
- if (pv_is_native_vcpu_is_preempted()) {
- start = start_pv_lock_ops_vcpu_is_preempted;
- end = end_pv_lock_ops_vcpu_is_preempted;
- goto patch_site;
- }
- goto patch_default;
+ switch (type) {
+#ifdef CONFIG_PARAVIRT_XXL
+ PATCH_SITE(irq, restore_fl);
+ PATCH_SITE(irq, save_fl);
+ PATCH_SITE(irq, irq_enable);
+ PATCH_SITE(irq, irq_disable);
+ PATCH_SITE(cpu, usergs_sysret64);
+ PATCH_SITE(cpu, swapgs);
+ PATCH_SITE(cpu, wbinvd);
+ PATCH_SITE(mmu, read_cr2);
+ PATCH_SITE(mmu, read_cr3);
+ PATCH_SITE(mmu, write_cr3);
#endif
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
+ case PARAVIRT_PATCH(lock.queued_spin_unlock):
+ if (pv_is_native_spin_unlock())
+ return paravirt_patch_insns(ibuf, len,
+ start_lock_queued_spin_unlock,
+ end_lock_queued_spin_unlock);
+ break;
- default:
-patch_default: __maybe_unused
- ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
+ case PARAVIRT_PATCH(lock.vcpu_is_preempted):
+ if (pv_is_native_vcpu_is_preempted())
+ return paravirt_patch_insns(ibuf, len,
+ start_lock_vcpu_is_preempted,
+ end_lock_vcpu_is_preempted);
break;
+#endif
-patch_site:
- ret = paravirt_patch_insns(ibuf, len, start, end);
+ default:
break;
}
#undef PATCH_SITE
- return ret;
+ return paravirt_patch_default(type, ibuf, addr, len);
}
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 661583662430..71c0b01d93b1 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -42,10 +42,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
int __init pci_swiotlb_detect_4gb(void)
{
/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-#ifdef CONFIG_X86_64
if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
swiotlb = 1;
-#endif
/*
* If SME is active then swiotlb will be set to 1 so that bounce
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 2924fd447e61..5046a3c9dec2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -59,7 +59,7 @@
#include <asm/intel_rdt_sched.h>
#include <asm/proto.h>
-void __show_regs(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
unsigned long d0, d1, d2, d3, d6, d7;
@@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all)
printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n",
(u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags);
- if (!all)
+ if (mode != SHOW_REGS_ALL)
return;
cr0 = read_cr0();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a451bc374b9b..31b4755369f0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -54,15 +54,14 @@
#include <asm/vdso.h>
#include <asm/intel_rdt_sched.h>
#include <asm/unistd.h>
+#include <asm/fsgsbase.h>
#ifdef CONFIG_IA32_EMULATION
/* Not included via unistd.h */
#include <asm/unistd_32_ia32.h>
#endif
-__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
-
/* Prints also some state that isn't saved in the pt_regs */
-void __show_regs(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
unsigned long d0, d1, d2, d3, d6, d7;
@@ -87,9 +86,17 @@ void __show_regs(struct pt_regs *regs, int all)
printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
regs->r13, regs->r14, regs->r15);
- if (!all)
+ if (mode == SHOW_REGS_SHORT)
return;
+ if (mode == SHOW_REGS_USER) {
+ rdmsrl(MSR_FS_BASE, fs);
+ rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+ printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n",
+ fs, shadowgs);
+ return;
+ }
+
asm("movl %%ds,%0" : "=r" (ds));
asm("movl %%cs,%0" : "=r" (cs));
asm("movl %%es,%0" : "=r" (es));
@@ -278,6 +285,138 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
}
}
+static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
+ struct thread_struct *next)
+{
+ load_seg_legacy(prev->fsindex, prev->fsbase,
+ next->fsindex, next->fsbase, FS);
+ load_seg_legacy(prev->gsindex, prev->gsbase,
+ next->gsindex, next->gsbase, GS);
+}
+
+static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
+ unsigned short selector)
+{
+ unsigned short idx = selector >> 3;
+ unsigned long base;
+
+ if (likely((selector & SEGMENT_TI_MASK) == 0)) {
+ if (unlikely(idx >= GDT_ENTRIES))
+ return 0;
+
+ /*
+ * There are no user segments in the GDT with nonzero bases
+ * other than the TLS segments.
+ */
+ if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+ return 0;
+
+ idx -= GDT_ENTRY_TLS_MIN;
+ base = get_desc_base(&task->thread.tls_array[idx]);
+ } else {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ struct ldt_struct *ldt;
+
+ /*
+ * If performance here mattered, we could protect the LDT
+ * with RCU. This is a slow path, though, so we can just
+ * take the mutex.
+ */
+ mutex_lock(&task->mm->context.lock);
+ ldt = task->mm->context.ldt;
+ if (unlikely(idx >= ldt->nr_entries))
+ base = 0;
+ else
+ base = get_desc_base(ldt->entries + idx);
+ mutex_unlock(&task->mm->context.lock);
+#else
+ base = 0;
+#endif
+ }
+
+ return base;
+}
+
+void x86_fsbase_write_cpu(unsigned long fsbase)
+{
+ /*
+ * Set the selector to 0 as a notion, that the segment base is
+ * overwritten, which will be checked for skipping the segment load
+ * during context switch.
+ */
+ loadseg(FS, 0);
+ wrmsrl(MSR_FS_BASE, fsbase);
+}
+
+void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
+{
+ /* Set the selector to 0 for the same reason as %fs above. */
+ loadseg(GS, 0);
+ wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+}
+
+unsigned long x86_fsbase_read_task(struct task_struct *task)
+{
+ unsigned long fsbase;
+
+ if (task == current)
+ fsbase = x86_fsbase_read_cpu();
+ else if (task->thread.fsindex == 0)
+ fsbase = task->thread.fsbase;
+ else
+ fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex);
+
+ return fsbase;
+}
+
+unsigned long x86_gsbase_read_task(struct task_struct *task)
+{
+ unsigned long gsbase;
+
+ if (task == current)
+ gsbase = x86_gsbase_read_cpu_inactive();
+ else if (task->thread.gsindex == 0)
+ gsbase = task->thread.gsbase;
+ else
+ gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex);
+
+ return gsbase;
+}
+
+int x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase)
+{
+ /*
+ * Not strictly needed for %fs, but do it for symmetry
+ * with %gs
+ */
+ if (unlikely(fsbase >= TASK_SIZE_MAX))
+ return -EPERM;
+
+ preempt_disable();
+ task->thread.fsbase = fsbase;
+ if (task == current)
+ x86_fsbase_write_cpu(fsbase);
+ task->thread.fsindex = 0;
+ preempt_enable();
+
+ return 0;
+}
+
+int x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase)
+{
+ if (unlikely(gsbase >= TASK_SIZE_MAX))
+ return -EPERM;
+
+ preempt_disable();
+ task->thread.gsbase = gsbase;
+ if (task == current)
+ x86_gsbase_write_cpu_inactive(gsbase);
+ task->thread.gsindex = 0;
+ preempt_enable();
+
+ return 0;
+}
+
int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p, unsigned long tls)
{
@@ -465,10 +604,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
if (unlikely(next->ds | prev->ds))
loadsegment(ds, next->ds);
- load_seg_legacy(prev->fsindex, prev->fsbase,
- next->fsindex, next->fsbase, FS);
- load_seg_legacy(prev->gsindex, prev->gsbase,
- next->gsindex, next->gsbase, GS);
+ x86_fsgsbase_load(prev, next);
switch_fpu_finish(next_fpu, cpu);
@@ -619,54 +755,25 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
{
int ret = 0;
- int doit = task == current;
- int cpu;
switch (option) {
- case ARCH_SET_GS:
- if (arg2 >= TASK_SIZE_MAX)
- return -EPERM;
- cpu = get_cpu();
- task->thread.gsindex = 0;
- task->thread.gsbase = arg2;
- if (doit) {
- load_gs_index(0);
- ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2);
- }
- put_cpu();
+ case ARCH_SET_GS: {
+ ret = x86_gsbase_write_task(task, arg2);
break;
- case ARCH_SET_FS:
- /* Not strictly needed for fs, but do it for symmetry
- with gs */
- if (arg2 >= TASK_SIZE_MAX)
- return -EPERM;
- cpu = get_cpu();
- task->thread.fsindex = 0;
- task->thread.fsbase = arg2;
- if (doit) {
- /* set the selector to 0 to not confuse __switch_to */
- loadsegment(fs, 0);
- ret = wrmsrl_safe(MSR_FS_BASE, arg2);
- }
- put_cpu();
+ }
+ case ARCH_SET_FS: {
+ ret = x86_fsbase_write_task(task, arg2);
break;
+ }
case ARCH_GET_FS: {
- unsigned long base;
+ unsigned long base = x86_fsbase_read_task(task);
- if (doit)
- rdmsrl(MSR_FS_BASE, base);
- else
- base = task->thread.fsbase;
ret = put_user(base, (unsigned long __user *)arg2);
break;
}
case ARCH_GET_GS: {
- unsigned long base;
+ unsigned long base = x86_gsbase_read_task(task);
- if (doit)
- rdmsrl(MSR_KERNEL_GS_BASE, base);
- else
- base = task->thread.gsbase;
ret = put_user(base, (unsigned long __user *)arg2);
break;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e2ee403865eb..ffae9b9740fd 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -39,6 +39,7 @@
#include <asm/hw_breakpoint.h>
#include <asm/traps.h>
#include <asm/syscall.h>
+#include <asm/fsgsbase.h>
#include "tls.h"
@@ -396,12 +397,11 @@ static int putreg(struct task_struct *child,
if (value >= TASK_SIZE_MAX)
return -EIO;
/*
- * When changing the segment base, use do_arch_prctl_64
- * to set either thread.fs or thread.fsindex and the
- * corresponding GDT slot.
+ * When changing the FS base, use the same
+ * mechanism as for do_arch_prctl_64().
*/
if (child->thread.fsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_FS, value);
+ return x86_fsbase_write_task(child, value);
return 0;
case offsetof(struct user_regs_struct,gs_base):
/*
@@ -410,7 +410,7 @@ static int putreg(struct task_struct *child,
if (value >= TASK_SIZE_MAX)
return -EIO;
if (child->thread.gsbase != value)
- return do_arch_prctl_64(child, ARCH_SET_GS, value);
+ return x86_gsbase_write_task(child, value);
return 0;
#endif
}
@@ -434,20 +434,10 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset)
return get_flags(task);
#ifdef CONFIG_X86_64
- case offsetof(struct user_regs_struct, fs_base): {
- /*
- * XXX: This will not behave as expected if called on
- * current or if fsindex != 0.
- */
- return task->thread.fsbase;
- }
- case offsetof(struct user_regs_struct, gs_base): {
- /*
- * XXX: This will not behave as expected if called on
- * current or if fsindex != 0.
- */
- return task->thread.gsbase;
- }
+ case offsetof(struct user_regs_struct, fs_base):
+ return x86_fsbase_read_task(task);
+ case offsetof(struct user_regs_struct, gs_base):
+ return x86_gsbase_read_task(task);
#endif
}
@@ -1369,33 +1359,18 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
#endif
}
-static void fill_sigtrap_info(struct task_struct *tsk,
- struct pt_regs *regs,
- int error_code, int si_code,
- struct siginfo *info)
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
+ int error_code, int si_code)
{
tsk->thread.trap_nr = X86_TRAP_DB;
tsk->thread.error_code = error_code;
- info->si_signo = SIGTRAP;
- info->si_code = si_code;
- info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL;
-}
-
-void user_single_step_siginfo(struct task_struct *tsk,
- struct pt_regs *regs,
- struct siginfo *info)
-{
- fill_sigtrap_info(tsk, regs, 0, TRAP_BRKPT, info);
+ /* Send us the fake SIGTRAP */
+ force_sig_fault(SIGTRAP, si_code,
+ user_mode(regs) ? (void __user *)regs->ip : NULL, tsk);
}
-void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
- int error_code, int si_code)
+void user_single_step_report(struct pt_regs *regs)
{
- struct siginfo info;
-
- clear_siginfo(&info);
- fill_sigtrap_info(tsk, regs, error_code, si_code, &info);
- /* Send us the fake SIGTRAP */
- force_sig_info(SIGTRAP, &info, tsk);
+ send_sigtrap(current, regs, 0, TRAP_BRKPT);
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4866badb235..7005f89bf3b2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1251,7 +1251,7 @@ void __init setup_arch(char **cmdline_p)
x86_init.hyper.guest_late_init();
e820__reserve_resources();
- e820__register_nosave_regions(max_low_pfn);
+ e820__register_nosave_regions(max_pfn);
x86_init.resources.reserve_resources();
@@ -1281,6 +1281,23 @@ void __init setup_arch(char **cmdline_p)
unwind_init();
}
+/*
+ * From boot protocol 2.14 onwards we expect the bootloader to set the
+ * version to "0x8000 | <used version>". In case we find a version >= 2.14
+ * without the 0x8000 we assume the boot loader supports 2.13 only and
+ * reset the version accordingly. The 0x8000 flag is removed in any case.
+ */
+void __init x86_verify_bootdata_version(void)
+{
+ if (boot_params.hdr.version & VERSION_WRITTEN)
+ boot_params.hdr.version &= ~VERSION_WRITTEN;
+ else if (boot_params.hdr.version >= 0x020e)
+ boot_params.hdr.version = 0x020d;
+
+ if (boot_params.hdr.version < 0x020e)
+ boot_params.hdr.acpi_rsdp_addr = 0;
+}
+
#ifdef CONFIG_X86_32
static struct resource video_ram_resource = {
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f02ecaf97904..5369d7fac797 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -676,6 +676,7 @@ static void __init smp_quirk_init_udelay(void)
/* if modern processor, use no delay */
if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+ ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
init_udelay = 0;
return;
@@ -1592,7 +1593,8 @@ static inline void mwait_play_dead(void)
void *mwait_ptr;
int i;
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
return;
if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index be01328eb755..0e14f6c0d35e 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -10,6 +10,7 @@
*
*/
+#include <linux/clocksource.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
@@ -25,7 +26,7 @@
#include <asm/time.h>
#ifdef CONFIG_X86_64
-__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES;
+__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES;
#endif
unsigned long profile_pc(struct pt_regs *regs)
@@ -105,3 +106,24 @@ void __init time_init(void)
{
late_time_init = x86_late_time_init;
}
+
+/*
+ * Sanity check the vdso related archdata content.
+ */
+void clocksource_arch_init(struct clocksource *cs)
+{
+ if (cs->archdata.vclock_mode == VCLOCK_NONE)
+ return;
+
+ if (cs->archdata.vclock_mode > VCLOCK_MAX) {
+ pr_warn("clocksource %s registered with invalid vclock_mode %d. Disabling vclock.\n",
+ cs->name, cs->archdata.vclock_mode);
+ cs->archdata.vclock_mode = VCLOCK_NONE;
+ }
+
+ if (cs->mask != CLOCKSOURCE_MASK(64)) {
+ pr_warn("clocksource %s registered with invalid mask %016llx. Disabling vclock.\n",
+ cs->name, cs->mask);
+ cs->archdata.vclock_mode = VCLOCK_NONE;
+ }
+}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 12cbe2b88c0f..738bf42b0218 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -111,8 +111,10 @@ int arch_register_cpu(int num)
/*
* Currently CPU0 is only hotpluggable on Intel platforms. Other
* vendors can add hotplug support later.
+ * Xen PV guests don't support CPU0 hotplug at all.
*/
- if (c->x86_vendor != X86_VENDOR_INTEL)
+ if (c->x86_vendor != X86_VENDOR_INTEL ||
+ boot_cpu_has(X86_FEATURE_XENPV))
cpu0_hotpluggable = 0;
/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e6db475164ed..8f6dcd88202e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -189,7 +189,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr)
}
static nokprobe_inline int
-do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
+do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str,
struct pt_regs *regs, long error_code)
{
if (v8086_mode(regs)) {
@@ -202,11 +202,8 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
error_code, trapnr))
return 0;
}
- return -1;
- }
-
- if (!user_mode(regs)) {
- if (fixup_exception(regs, trapnr))
+ } else if (!user_mode(regs)) {
+ if (fixup_exception(regs, trapnr, error_code, 0))
return 0;
tsk->thread.error_code = error_code;
@@ -214,49 +211,6 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
die(str, regs, error_code);
}
- return -1;
-}
-
-static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr,
- siginfo_t *info)
-{
- unsigned long siaddr;
- int sicode;
-
- switch (trapnr) {
- default:
- return SEND_SIG_PRIV;
-
- case X86_TRAP_DE:
- sicode = FPE_INTDIV;
- siaddr = uprobe_get_trap_addr(regs);
- break;
- case X86_TRAP_UD:
- sicode = ILL_ILLOPN;
- siaddr = uprobe_get_trap_addr(regs);
- break;
- case X86_TRAP_AC:
- sicode = BUS_ADRALN;
- siaddr = 0;
- break;
- }
-
- info->si_signo = signr;
- info->si_errno = 0;
- info->si_code = sicode;
- info->si_addr = (void __user *)siaddr;
- return info;
-}
-
-static void
-do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
- long error_code, siginfo_t *info)
-{
- struct task_struct *tsk = current;
-
-
- if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
- return;
/*
* We want error_code and trap_nr set for userspace faults and
* kernelspace faults which result in die(), but not
@@ -269,24 +223,45 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = trapnr;
+ return -1;
+}
+
+static void show_signal(struct task_struct *tsk, int signr,
+ const char *type, const char *desc,
+ struct pt_regs *regs, long error_code)
+{
if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
printk_ratelimit()) {
- pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
- tsk->comm, tsk->pid, str,
+ pr_info("%s[%d] %s%s ip:%lx sp:%lx error:%lx",
+ tsk->comm, task_pid_nr(tsk), type, desc,
regs->ip, regs->sp, error_code);
print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
+}
- force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk);
+static void
+do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
+ long error_code, int sicode, void __user *addr)
+{
+ struct task_struct *tsk = current;
+
+
+ if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
+ return;
+
+ show_signal(tsk, signr, "trap ", str, regs, error_code);
+
+ if (!sicode)
+ force_sig(signr, tsk);
+ else
+ force_sig_fault(signr, sicode, addr, tsk);
}
NOKPROBE_SYMBOL(do_trap);
static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
- unsigned long trapnr, int signr)
+ unsigned long trapnr, int signr, int sicode, void __user *addr)
{
- siginfo_t info;
-
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
/*
@@ -299,26 +274,26 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
NOTIFY_STOP) {
cond_local_irq_enable(regs);
- clear_siginfo(&info);
- do_trap(trapnr, signr, str, regs, error_code,
- fill_trap_info(regs, signr, trapnr, &info));
+ do_trap(trapnr, signr, str, regs, error_code, sicode, addr);
}
}
-#define DO_ERROR(trapnr, signr, str, name) \
-dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
-{ \
- do_error_trap(regs, error_code, str, trapnr, signr); \
+#define IP ((void __user *)uprobe_get_trap_addr(regs))
+#define DO_ERROR(trapnr, signr, sicode, addr, str, name) \
+dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
+{ \
+ do_error_trap(regs, error_code, str, trapnr, signr, sicode, addr); \
}
-DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error)
-DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
-DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op)
-DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun)
-DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
-DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
-DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check)
+DO_ERROR(X86_TRAP_DE, SIGFPE, FPE_INTDIV, IP, "divide error", divide_error)
+DO_ERROR(X86_TRAP_OF, SIGSEGV, 0, NULL, "overflow", overflow)
+DO_ERROR(X86_TRAP_UD, SIGILL, ILL_ILLOPN, IP, "invalid opcode", invalid_op)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, 0, NULL, "coprocessor segment overrun", coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS, SIGSEGV, 0, NULL, "invalid TSS", invalid_TSS)
+DO_ERROR(X86_TRAP_NP, SIGBUS, 0, NULL, "segment not present", segment_not_present)
+DO_ERROR(X86_TRAP_SS, SIGBUS, 0, NULL, "stack segment", stack_segment)
+DO_ERROR(X86_TRAP_AC, SIGBUS, BUS_ADRALN, NULL, "alignment check", alignment_check)
+#undef IP
#ifdef CONFIG_VMAP_STACK
__visible void __noreturn handle_stack_overflow(const char *message,
@@ -383,6 +358,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
* we won't enable interupts or schedule before we invoke
* general_protection, so nothing will clobber the stack
* frame we just set up.
+ *
+ * We will enter general_protection with kernel GSBASE,
+ * which is what the stub expects, given that the faulting
+ * RIP will be the IRET instruction.
*/
regs->ip = (unsigned long)general_protection;
regs->sp = (unsigned long)&gpregs->orig_ax;
@@ -455,7 +434,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
const struct mpx_bndcsr *bndcsr;
- siginfo_t *info;
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
if (notify_die(DIE_TRAP, "bounds", regs, error_code,
@@ -493,8 +471,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
goto exit_trap;
break; /* Success, it was handled */
case 1: /* Bound violation. */
- info = mpx_generate_siginfo(regs);
- if (IS_ERR(info)) {
+ {
+ struct task_struct *tsk = current;
+ struct mpx_fault_info mpx;
+
+ if (mpx_fault_info(&mpx, regs)) {
/*
* We failed to decode the MPX instruction. Act as if
* the exception was not caused by MPX.
@@ -503,14 +484,20 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
}
/*
* Success, we decoded the instruction and retrieved
- * an 'info' containing the address being accessed
+ * an 'mpx' containing the address being accessed
* which caused the exception. This information
* allows and application to possibly handle the
* #BR exception itself.
*/
- do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
- kfree(info);
+ if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs,
+ error_code))
+ break;
+
+ show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code);
+
+ force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper);
break;
+ }
case 0: /* No exception caused by Intel MPX operations. */
goto exit_trap;
default:
@@ -527,12 +514,13 @@ exit_trap:
* up here if the kernel has MPX turned off at compile
* time..
*/
- do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
+ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL);
}
dotraplinkage void
do_general_protection(struct pt_regs *regs, long error_code)
{
+ const char *desc = "general protection fault";
struct task_struct *tsk;
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
@@ -551,30 +539,33 @@ do_general_protection(struct pt_regs *regs, long error_code)
tsk = current;
if (!user_mode(regs)) {
- if (fixup_exception(regs, X86_TRAP_GP))
+ if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
return;
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
- if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+
+ /*
+ * To be potentially processing a kprobe fault and to
+ * trust the result from kprobe_running(), we have to
+ * be non-preemptible.
+ */
+ if (!preemptible() && kprobe_running() &&
+ kprobe_fault_handler(regs, X86_TRAP_GP))
+ return;
+
+ if (notify_die(DIE_GPF, desc, regs, error_code,
X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
- die("general protection fault", regs, error_code);
+ die(desc, regs, error_code);
return;
}
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
- if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
- printk_ratelimit()) {
- pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
- tsk->comm, task_pid_nr(tsk),
- regs->ip, regs->sp, error_code);
- print_vma_addr(KERN_CONT " in ", regs->ip);
- pr_cont("\n");
- }
+ show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
- force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
+ force_sig(SIGSEGV, tsk);
}
NOKPROBE_SYMBOL(do_general_protection);
@@ -617,7 +608,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
goto exit;
cond_local_irq_enable(regs);
- do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
+ do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, 0, NULL);
cond_local_irq_disable(regs);
exit:
@@ -831,14 +822,14 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
{
struct task_struct *task = current;
struct fpu *fpu = &task->thread.fpu;
- siginfo_t info;
+ int si_code;
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
cond_local_irq_enable(regs);
if (!user_mode(regs)) {
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, error_code, 0))
return;
task->thread.error_code = error_code;
@@ -857,18 +848,14 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
- clear_siginfo(&info);
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
-
- info.si_code = fpu__exception_code(fpu, trapnr);
+ si_code = fpu__exception_code(fpu, trapnr);
/* Retry when we get spurious exceptions: */
- if (!info.si_code)
+ if (!si_code)
return;
- force_sig_info(SIGFPE, &info, task);
+ force_sig_fault(SIGFPE, si_code,
+ (void __user *)uprobe_get_trap_addr(regs), task);
}
dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
@@ -928,20 +915,13 @@ NOKPROBE_SYMBOL(do_device_not_available);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
- siginfo_t info;
-
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
local_irq_enable();
- clear_siginfo(&info);
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_BADSTK;
- info.si_addr = NULL;
if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
- &info);
+ ILL_BADSTK, (void __user *)NULL);
}
}
#endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 1463468ba9a0..e9f777bfed40 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -26,6 +26,7 @@
#include <asm/apic.h>
#include <asm/intel-family.h>
#include <asm/i8259.h>
+#include <asm/uv/uv.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
@@ -57,7 +58,7 @@ struct cyc2ns {
static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
-void cyc2ns_read_begin(struct cyc2ns_data *data)
+void __always_inline cyc2ns_read_begin(struct cyc2ns_data *data)
{
int seq, idx;
@@ -74,7 +75,7 @@ void cyc2ns_read_begin(struct cyc2ns_data *data)
} while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
}
-void cyc2ns_read_end(void)
+void __always_inline cyc2ns_read_end(void)
{
preempt_enable_notrace();
}
@@ -103,7 +104,7 @@ void cyc2ns_read_end(void)
* -johnstul@us.ibm.com "math is hard, lets go shopping!"
*/
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc)
{
struct cyc2ns_data data;
unsigned long long ns;
@@ -246,7 +247,7 @@ unsigned long long sched_clock(void)
bool using_native_sched_clock(void)
{
- return pv_time_ops.sched_clock == native_sched_clock;
+ return pv_ops.time.sched_clock == native_sched_clock;
}
#else
unsigned long long
@@ -635,7 +636,7 @@ unsigned long native_calibrate_tsc(void)
case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
crystal_khz = 25000; /* 25.0 MHz */
break;
case INTEL_FAM6_ATOM_GOLDMONT:
@@ -1415,7 +1416,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early)
static unsigned long __init get_loops_per_jiffy(void)
{
- unsigned long lpj = tsc_khz * KHZ;
+ u64 lpj = (u64)tsc_khz * KHZ;
do_div(lpj, HZ);
return lpj;
@@ -1433,6 +1434,9 @@ void __init tsc_early_init(void)
{
if (!boot_cpu_has(X86_FEATURE_TSC))
return;
+ /* Don't change UV TSC multi-chassis synchronization */
+ if (is_early_uv_system())
+ return;
if (!determine_cpu_tsc_frequencies(true))
return;
loops_per_jiffy = get_loops_per_jiffy();
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 27ef714d886c..3d0e9aeea7c8 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -59,12 +59,12 @@ static const struct freq_desc freq_desc_ann = {
};
static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
- INTEL_CPU_FAM6(ATOM_PENWELL, freq_desc_pnw),
- INTEL_CPU_FAM6(ATOM_CLOVERVIEW, freq_desc_clv),
- INTEL_CPU_FAM6(ATOM_SILVERMONT1, freq_desc_byt),
+ INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw),
+ INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv),
+ INTEL_CPU_FAM6(ATOM_SILVERMONT, freq_desc_byt),
+ INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng),
INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht),
- INTEL_CPU_FAM6(ATOM_MERRIFIELD, freq_desc_tng),
- INTEL_CPU_FAM6(ATOM_MOOREFIELD, freq_desc_ann),
+ INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann),
{}
};
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index ff20b35e98dd..f8f3cfda01ae 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -271,19 +271,13 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
*/
static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
{
- siginfo_t info;
struct task_struct *tsk = current;
tsk->thread.cr2 = (unsigned long)addr;
tsk->thread.error_code = X86_PF_USER | X86_PF_WRITE;
tsk->thread.trap_nr = X86_TRAP_PF;
- clear_siginfo(&info);
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = SEGV_MAPERR;
- info.si_addr = addr;
- force_sig_info(SIGSEGV, &info, tsk);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR, addr, tsk);
if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV)))
return;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index deb576b23b7c..843feb94a950 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1086,7 +1086,7 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
current->pid, regs->sp, regs->ip);
- force_sig_info(SIGSEGV, SEND_SIG_FORCED, current);
+ force_sig(SIGSEGV, current);
}
return -1;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 1c03e4aa6474..c2fd39752da8 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -199,7 +199,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
pte_unmap_unlock(pte, ptl);
out:
up_write(&mm->mmap_sem);
- flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL);
+ flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT, false);
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8bde0a419f86..0d618ee634ac 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -65,6 +65,23 @@ jiffies_64 = jiffies;
#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+/*
+ * This section contains data which will be mapped as decrypted. Memory
+ * encryption operates on a page basis. Make this section PMD-aligned
+ * to avoid splitting the pages while mapping the section early.
+ *
+ * Note: We use a separate section so that only this section gets
+ * decrypted to avoid exposing more than we wish.
+ */
+#define BSS_DECRYPTED \
+ . = ALIGN(PMD_SIZE); \
+ __start_bss_decrypted = .; \
+ *(.bss..decrypted); \
+ . = ALIGN(PAGE_SIZE); \
+ __start_bss_decrypted_unused = .; \
+ . = ALIGN(PMD_SIZE); \
+ __end_bss_decrypted = .; \
+
#else
#define X86_ALIGN_RODATA_BEGIN
@@ -74,6 +91,7 @@ jiffies_64 = jiffies;
#define ALIGN_ENTRY_TEXT_BEGIN
#define ALIGN_ENTRY_TEXT_END
+#define BSS_DECRYPTED
#endif
@@ -118,16 +136,6 @@ SECTIONS
*(.fixup)
*(.gnu.warning)
-#ifdef CONFIG_X86_64
- . = ALIGN(PAGE_SIZE);
- __entry_trampoline_start = .;
- _entry_trampoline = .;
- *(.entry_trampoline)
- . = ALIGN(PAGE_SIZE);
- __entry_trampoline_end = .;
- ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
-#endif
-
#ifdef CONFIG_RETPOLINE
__indirect_thunk_start = .;
*(.text.__x86.indirect_thunk)
@@ -355,6 +363,7 @@ SECTIONS
__bss_start = .;
*(.bss..page_aligned)
*(.bss)
+ BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;
}
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 44685fb2a192..1eae5af491c2 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -26,7 +26,7 @@
#define TOPOLOGY_REGISTER_OFFSET 0x10
-#if defined CONFIG_PCI && defined CONFIG_PARAVIRT
+#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL
/*
* Interrupt control on vSMPowered systems:
* ~AC is a shadow of IF. If IF is 'on' AC should be 'off'
@@ -69,17 +69,17 @@ asmlinkage __visible void vsmp_irq_enable(void)
}
PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
-static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf,
+static unsigned __init vsmp_patch(u8 type, void *ibuf,
unsigned long addr, unsigned len)
{
switch (type) {
- case PARAVIRT_PATCH(pv_irq_ops.irq_enable):
- case PARAVIRT_PATCH(pv_irq_ops.irq_disable):
- case PARAVIRT_PATCH(pv_irq_ops.save_fl):
- case PARAVIRT_PATCH(pv_irq_ops.restore_fl):
- return paravirt_patch_default(type, clobbers, ibuf, addr, len);
+ case PARAVIRT_PATCH(irq.irq_enable):
+ case PARAVIRT_PATCH(irq.irq_disable):
+ case PARAVIRT_PATCH(irq.save_fl):
+ case PARAVIRT_PATCH(irq.restore_fl):
+ return paravirt_patch_default(type, ibuf, addr, len);
default:
- return native_patch(type, clobbers, ibuf, addr, len);
+ return native_patch(type, ibuf, addr, len);
}
}
@@ -111,11 +111,11 @@ static void __init set_vsmp_pv_ops(void)
if (cap & ctl & (1 << 4)) {
/* Setup irq ops and turn on vSMP IRQ fastpath handling */
- pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
- pv_irq_ops.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
- pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
- pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
- pv_init_ops.patch = vsmp_patch;
+ pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
+ pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
+ pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
+ pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
+ pv_ops.init.patch = vsmp_patch;
ctl &= ~(1 << 4);
}
writel(ctl, address + 4);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 2792b5573818..50a2b492fdd6 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -31,7 +31,6 @@ static int __init iommu_init_noop(void) { return 0; }
static void iommu_shutdown_noop(void) { }
static bool __init bool_x86_init_noop(void) { return false; }
static void x86_op_int_noop(int cpu) { }
-static u64 u64_x86_init_noop(void) { return 0; }
/*
* The platform setup functions are preset with the default functions
@@ -96,7 +95,7 @@ struct x86_init_ops x86_init __initdata = {
},
.acpi = {
- .get_root_pointer = u64_x86_init_noop,
+ .get_root_pointer = x86_default_get_root_pointer,
.reduced_hw_early_init = acpi_generic_reduced_hw_init,
},
};
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 106482da6388..34edf198708f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2711,7 +2711,16 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
return true;
- /* default: (not Intel, not AMD), apply Intel's stricter rules... */
+ /* Hygon ("HygonGenuine") */
+ if (ebx == X86EMUL_CPUID_VENDOR_HygonGenuine_ebx &&
+ ecx == X86EMUL_CPUID_VENDOR_HygonGenuine_ecx &&
+ edx == X86EMUL_CPUID_VENDOR_HygonGenuine_edx)
+ return true;
+
+ /*
+ * default: (not Intel, not AMD, not Hygon), apply Intel's
+ * stricter rules...
+ */
return false;
}
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 01d209ab5481..4e80080f277a 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -36,6 +36,8 @@
#include "trace.h"
+#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
+
static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint)
{
return atomic64_read(&synic->sint[sint]);
@@ -132,8 +134,10 @@ static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx)
struct kvm_vcpu *vcpu = NULL;
int i;
- if (vpidx < KVM_MAX_VCPUS)
- vcpu = kvm_get_vcpu(kvm, vpidx);
+ if (vpidx >= KVM_MAX_VCPUS)
+ return NULL;
+
+ vcpu = kvm_get_vcpu(kvm, vpidx);
if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
return vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
@@ -689,6 +693,24 @@ void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu)
stimer_cleanup(&hv_vcpu->stimer[i]);
}
+bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE))
+ return false;
+ return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED;
+}
+EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled);
+
+bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
+ struct hv_vp_assist_page *assist_page)
+{
+ if (!kvm_hv_assist_page_enabled(vcpu))
+ return false;
+ return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
+ assist_page, sizeof(*assist_page));
+}
+EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page);
+
static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
{
struct hv_message *msg = &stimer->msg;
@@ -1040,21 +1062,41 @@ static u64 current_task_runtime_100ns(void)
static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
{
- struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
switch (msr) {
- case HV_X64_MSR_VP_INDEX:
- if (!host)
+ case HV_X64_MSR_VP_INDEX: {
+ struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+ int vcpu_idx = kvm_vcpu_get_idx(vcpu);
+ u32 new_vp_index = (u32)data;
+
+ if (!host || new_vp_index >= KVM_MAX_VCPUS)
return 1;
- hv->vp_index = (u32)data;
+
+ if (new_vp_index == hv_vcpu->vp_index)
+ return 0;
+
+ /*
+ * The VP index is initialized to vcpu_index by
+ * kvm_hv_vcpu_postcreate so they initially match. Now the
+ * VP index is changing, adjust num_mismatched_vp_indexes if
+ * it now matches or no longer matches vcpu_idx.
+ */
+ if (hv_vcpu->vp_index == vcpu_idx)
+ atomic_inc(&hv->num_mismatched_vp_indexes);
+ else if (new_vp_index == vcpu_idx)
+ atomic_dec(&hv->num_mismatched_vp_indexes);
+
+ hv_vcpu->vp_index = new_vp_index;
break;
+ }
case HV_X64_MSR_VP_ASSIST_PAGE: {
u64 gfn;
unsigned long addr;
if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
- hv->hv_vapic = data;
- if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+ hv_vcpu->hv_vapic = data;
+ if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0))
return 1;
break;
}
@@ -1062,12 +1104,19 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
if (kvm_is_error_hva(addr))
return 1;
- if (__clear_user((void __user *)addr, PAGE_SIZE))
+
+ /*
+ * Clear apic_assist portion of f(struct hv_vp_assist_page
+ * only, there can be valuable data in the rest which needs
+ * to be preserved e.g. on migration.
+ */
+ if (__clear_user((void __user *)addr, sizeof(u32)))
return 1;
- hv->hv_vapic = data;
+ hv_vcpu->hv_vapic = data;
kvm_vcpu_mark_page_dirty(vcpu, gfn);
if (kvm_lapic_enable_pv_eoi(vcpu,
- gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+ gfn_to_gpa(gfn) | KVM_MSR_ENABLED,
+ sizeof(struct hv_vp_assist_page)))
return 1;
break;
}
@@ -1080,7 +1129,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
case HV_X64_MSR_VP_RUNTIME:
if (!host)
return 1;
- hv->runtime_offset = data - current_task_runtime_100ns();
+ hv_vcpu->runtime_offset = data - current_task_runtime_100ns();
break;
case HV_X64_MSR_SCONTROL:
case HV_X64_MSR_SVERSION:
@@ -1172,11 +1221,11 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
bool host)
{
u64 data = 0;
- struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
switch (msr) {
case HV_X64_MSR_VP_INDEX:
- data = hv->vp_index;
+ data = hv_vcpu->vp_index;
break;
case HV_X64_MSR_EOI:
return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
@@ -1185,10 +1234,10 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
case HV_X64_MSR_TPR:
return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
case HV_X64_MSR_VP_ASSIST_PAGE:
- data = hv->hv_vapic;
+ data = hv_vcpu->hv_vapic;
break;
case HV_X64_MSR_VP_RUNTIME:
- data = current_task_runtime_100ns() + hv->runtime_offset;
+ data = current_task_runtime_100ns() + hv_vcpu->runtime_offset;
break;
case HV_X64_MSR_SCONTROL:
case HV_X64_MSR_SVERSION:
@@ -1255,32 +1304,47 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
return kvm_hv_get_msr(vcpu, msr, pdata, host);
}
-static __always_inline int get_sparse_bank_no(u64 valid_bank_mask, int bank_no)
+static __always_inline unsigned long *sparse_set_to_vcpu_mask(
+ struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask,
+ u64 *vp_bitmap, unsigned long *vcpu_bitmap)
{
- int i = 0, j;
+ struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_vcpu *vcpu;
+ int i, bank, sbank = 0;
- if (!(valid_bank_mask & BIT_ULL(bank_no)))
- return -1;
+ memset(vp_bitmap, 0,
+ KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap));
+ for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
+ KVM_HV_MAX_SPARSE_VCPU_SET_BITS)
+ vp_bitmap[bank] = sparse_banks[sbank++];
- for (j = 0; j < bank_no; j++)
- if (valid_bank_mask & BIT_ULL(j))
- i++;
+ if (likely(!atomic_read(&hv->num_mismatched_vp_indexes))) {
+ /* for all vcpus vp_index == vcpu_idx */
+ return (unsigned long *)vp_bitmap;
+ }
- return i;
+ bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (test_bit(vcpu_to_hv_vcpu(vcpu)->vp_index,
+ (unsigned long *)vp_bitmap))
+ __set_bit(i, vcpu_bitmap);
+ }
+ return vcpu_bitmap;
}
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
u16 rep_cnt, bool ex)
{
struct kvm *kvm = current_vcpu->kvm;
- struct kvm_vcpu_hv *hv_current = &current_vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = &current_vcpu->arch.hyperv;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- struct kvm_vcpu *vcpu;
- unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] = {0};
- unsigned long valid_bank_mask = 0;
+ u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+ DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+ unsigned long *vcpu_mask;
+ u64 valid_bank_mask;
u64 sparse_banks[64];
- int sparse_banks_len, i;
+ int sparse_banks_len;
bool all_cpus;
if (!ex) {
@@ -1290,6 +1354,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
trace_kvm_hv_flush_tlb(flush.processor_mask,
flush.address_space, flush.flags);
+ valid_bank_mask = BIT_ULL(0);
sparse_banks[0] = flush.processor_mask;
all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
} else {
@@ -1306,7 +1371,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
all_cpus = flush_ex.hv_vp_set.format !=
HV_GENERIC_SET_SPARSE_4K;
- sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+ sparse_banks_len =
+ bitmap_weight((unsigned long *)&valid_bank_mask, 64) *
sizeof(sparse_banks[0]);
if (!sparse_banks_len && !all_cpus)
@@ -1321,48 +1387,19 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
return HV_STATUS_INVALID_HYPERCALL_INPUT;
}
- cpumask_clear(&hv_current->tlb_lush);
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
- int bank = hv->vp_index / 64, sbank = 0;
-
- if (!all_cpus) {
- /* Banks >64 can't be represented */
- if (bank >= 64)
- continue;
-
- /* Non-ex hypercalls can only address first 64 vCPUs */
- if (!ex && bank)
- continue;
-
- if (ex) {
- /*
- * Check is the bank of this vCPU is in sparse
- * set and get the sparse bank number.
- */
- sbank = get_sparse_bank_no(valid_bank_mask,
- bank);
-
- if (sbank < 0)
- continue;
- }
-
- if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64)))
- continue;
- }
+ cpumask_clear(&hv_vcpu->tlb_flush);
- /*
- * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we
- * can't analyze it here, flush TLB regardless of the specified
- * address space.
- */
- __set_bit(i, vcpu_bitmap);
- }
+ vcpu_mask = all_cpus ? NULL :
+ sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
+ vp_bitmap, vcpu_bitmap);
+ /*
+ * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
+ * analyze it here, flush TLB regardless of the specified address space.
+ */
kvm_make_vcpus_request_mask(kvm,
KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
- vcpu_bitmap, &hv_current->tlb_lush);
+ vcpu_mask, &hv_vcpu->tlb_flush);
ret_success:
/* We always do full TLB flush, set rep_done = rep_cnt. */
@@ -1370,6 +1407,99 @@ ret_success:
((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
}
+static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
+ unsigned long *vcpu_bitmap)
+{
+ struct kvm_lapic_irq irq = {
+ .delivery_mode = APIC_DM_FIXED,
+ .vector = vector
+ };
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+ continue;
+
+ /* We fail only when APIC is disabled */
+ kvm_apic_set_irq(vcpu, &irq, NULL);
+ }
+}
+
+static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa,
+ bool ex, bool fast)
+{
+ struct kvm *kvm = current_vcpu->kvm;
+ struct hv_send_ipi_ex send_ipi_ex;
+ struct hv_send_ipi send_ipi;
+ u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+ DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+ unsigned long *vcpu_mask;
+ unsigned long valid_bank_mask;
+ u64 sparse_banks[64];
+ int sparse_banks_len;
+ u32 vector;
+ bool all_cpus;
+
+ if (!ex) {
+ if (!fast) {
+ if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi,
+ sizeof(send_ipi))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ sparse_banks[0] = send_ipi.cpu_mask;
+ vector = send_ipi.vector;
+ } else {
+ /* 'reserved' part of hv_send_ipi should be 0 */
+ if (unlikely(ingpa >> 32 != 0))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ sparse_banks[0] = outgpa;
+ vector = (u32)ingpa;
+ }
+ all_cpus = false;
+ valid_bank_mask = BIT_ULL(0);
+
+ trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
+ } else {
+ if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi_ex,
+ sizeof(send_ipi_ex))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector,
+ send_ipi_ex.vp_set.format,
+ send_ipi_ex.vp_set.valid_bank_mask);
+
+ vector = send_ipi_ex.vector;
+ valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
+ sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+ sizeof(sparse_banks[0]);
+
+ all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
+
+ if (!sparse_banks_len)
+ goto ret_success;
+
+ if (!all_cpus &&
+ kvm_read_guest(kvm,
+ ingpa + offsetof(struct hv_send_ipi_ex,
+ vp_set.bank_contents),
+ sparse_banks,
+ sparse_banks_len))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ }
+
+ if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ vcpu_mask = all_cpus ? NULL :
+ sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
+ vp_bitmap, vcpu_bitmap);
+
+ kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
+
+ret_success:
+ return HV_STATUS_SUCCESS;
+}
+
bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
@@ -1539,6 +1669,20 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
}
ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
break;
+ case HVCALL_SEND_IPI:
+ if (unlikely(rep)) {
+ ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+ break;
+ }
+ ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, false, fast);
+ break;
+ case HVCALL_SEND_IPI_EX:
+ if (unlikely(fast || rep)) {
+ ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+ break;
+ }
+ ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false);
+ break;
default:
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
break;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index d6aa969e20f1..0e66c12ed2c3 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -62,6 +62,10 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
+bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
+bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
+ struct hv_vp_assist_page *assist_page);
+
static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu,
int timer_index)
{
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0cefba28c864..3cd227ff807f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,6 +70,11 @@
#define APIC_BROADCAST 0xFF
#define X2APIC_BROADCAST 0xFFFFFFFFul
+static bool lapic_timer_advance_adjust_done = false;
+#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
+/* step-by-step approximation to mitigate fluctuation */
+#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+
static inline int apic_test_vector(int vec, void *bitmap)
{
return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -548,7 +553,7 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
}
int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
- unsigned long ipi_bitmap_high, int min,
+ unsigned long ipi_bitmap_high, u32 min,
unsigned long icr, int op_64_bit)
{
int i;
@@ -571,18 +576,31 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
rcu_read_lock();
map = rcu_dereference(kvm->arch.apic_map);
+ if (min > map->max_apic_id)
+ goto out;
/* Bits above cluster_size are masked in the caller. */
- for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) {
- vcpu = map->phys_map[min + i]->vcpu;
- count += kvm_apic_set_irq(vcpu, &irq, NULL);
+ for_each_set_bit(i, &ipi_bitmap_low,
+ min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+ if (map->phys_map[min + i]) {
+ vcpu = map->phys_map[min + i]->vcpu;
+ count += kvm_apic_set_irq(vcpu, &irq, NULL);
+ }
}
min += cluster_size;
- for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) {
- vcpu = map->phys_map[min + i]->vcpu;
- count += kvm_apic_set_irq(vcpu, &irq, NULL);
+
+ if (min > map->max_apic_id)
+ goto out;
+
+ for_each_set_bit(i, &ipi_bitmap_high,
+ min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+ if (map->phys_map[min + i]) {
+ vcpu = map->phys_map[min + i]->vcpu;
+ count += kvm_apic_set_irq(vcpu, &irq, NULL);
+ }
}
+out:
rcu_read_unlock();
return count;
}
@@ -942,14 +960,14 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
map = rcu_dereference(kvm->arch.apic_map);
ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap);
- if (ret)
+ if (ret) {
+ *r = 0;
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
continue;
- if (*r < 0)
- *r = 0;
*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
}
+ }
rcu_read_unlock();
return ret;
@@ -1331,9 +1349,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read);
static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
{
- return kvm_apic_hw_enabled(apic) &&
- addr >= apic->base_address &&
- addr < apic->base_address + LAPIC_MMIO_LENGTH;
+ return addr >= apic->base_address &&
+ addr < apic->base_address + LAPIC_MMIO_LENGTH;
}
static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
@@ -1345,6 +1362,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
if (!apic_mmio_in_range(apic, address))
return -EOPNOTSUPP;
+ if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) {
+ if (!kvm_check_has_quirk(vcpu->kvm,
+ KVM_X86_QUIRK_LAPIC_MMIO_HOLE))
+ return -EOPNOTSUPP;
+
+ memset(data, 0xff, len);
+ return 0;
+ }
+
kvm_lapic_reg_read(apic, offset, len, data);
return 0;
@@ -1451,7 +1477,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
void wait_lapic_expire(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- u64 guest_tsc, tsc_deadline;
+ u64 guest_tsc, tsc_deadline, ns;
if (!lapic_in_kernel(vcpu))
return;
@@ -1471,6 +1497,24 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
if (guest_tsc < tsc_deadline)
__delay(min(tsc_deadline - guest_tsc,
nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+
+ if (!lapic_timer_advance_adjust_done) {
+ /* too early */
+ if (guest_tsc < tsc_deadline) {
+ ns = (tsc_deadline - guest_tsc) * 1000000ULL;
+ do_div(ns, vcpu->arch.virtual_tsc_khz);
+ lapic_timer_advance_ns -= min((unsigned int)ns,
+ lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ } else {
+ /* too late */
+ ns = (guest_tsc - tsc_deadline) * 1000000ULL;
+ do_div(ns, vcpu->arch.virtual_tsc_khz);
+ lapic_timer_advance_ns += min((unsigned int)ns,
+ lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ }
+ if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
+ lapic_timer_advance_adjust_done = true;
+ }
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
@@ -1904,6 +1948,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
if (!apic_mmio_in_range(apic, address))
return -EOPNOTSUPP;
+ if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) {
+ if (!kvm_check_has_quirk(vcpu->kvm,
+ KVM_X86_QUIRK_LAPIC_MMIO_HOLE))
+ return -EOPNOTSUPP;
+
+ return 0;
+ }
+
/*
* APIC register must be aligned on 128-bits boundary.
* 32/64/128 bits registers must be accessed thru 32 bits.
@@ -2592,17 +2644,25 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
return 0;
}
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
{
u64 addr = data & ~KVM_MSR_ENABLED;
+ struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data;
+ unsigned long new_len;
+
if (!IS_ALIGNED(addr, 4))
return 1;
vcpu->arch.pv_eoi.msr_val = data;
if (!pv_eoi_enabled(vcpu))
return 0;
- return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
- addr, sizeof(u8));
+
+ if (addr == ghc->gpa && len <= ghc->len)
+ new_len = ghc->len;
+ else
+ new_len = len;
+
+ return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
}
void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index ed0ed39abd36..ff6ef9c3d760 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -120,7 +120,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
}
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
void kvm_lapic_init(void);
void kvm_lapic_exit(void);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index a282321329b5..cf5f572f2305 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
*/
static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts. This mask covers the lower bits of the GFN.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+
static void mmu_spte_set(u64 *sptep, u64 spte);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
@@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte)
static gfn_t get_mmio_spte_gfn(u64 spte)
{
- u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask |
- shadow_nonpresent_or_rsvd_mask;
- u64 gpa = spte & ~mask;
+ u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
& shadow_nonpresent_or_rsvd_mask;
@@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
static void kvm_mmu_reset_all_pte_masks(void)
{
+ u8 low_phys_bits;
+
shadow_user_mask = 0;
shadow_accessed_mask = 0;
shadow_dirty_mask = 0;
@@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void)
* appropriate mask to guard against L1TF attacks. Otherwise, it is
* assumed that the CPU is not vulnerable to L1TF.
*/
+ low_phys_bits = boot_cpu_data.x86_phys_bits;
if (boot_cpu_data.x86_phys_bits <
- 52 - shadow_nonpresent_or_rsvd_mask_len)
+ 52 - shadow_nonpresent_or_rsvd_mask_len) {
shadow_nonpresent_or_rsvd_mask =
rsvd_bits(boot_cpu_data.x86_phys_bits -
shadow_nonpresent_or_rsvd_mask_len,
boot_cpu_data.x86_phys_bits - 1);
+ low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+ }
+ shadow_nonpresent_or_rsvd_lower_gfn_mask =
+ GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
}
static int is_cpuid_PSE36(void)
@@ -899,7 +915,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
{
/*
* Make sure the write to vcpu->mode is not reordered in front of
- * reads to sptes. If it does, kvm_commit_zap_page() can see us
+ * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us
* OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
*/
smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
@@ -916,7 +932,7 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
obj = kmem_cache_zalloc(base_cache, GFP_KERNEL);
if (!obj)
- return -ENOMEM;
+ return cache->nobjs >= min ? 0 : -ENOMEM;
cache->objects[cache->nobjs++] = obj;
}
return 0;
@@ -944,7 +960,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
if (!page)
- return -ENOMEM;
+ return cache->nobjs >= min ? 0 : -ENOMEM;
cache->objects[cache->nobjs++] = page;
}
return 0;
@@ -1249,24 +1265,24 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
mmu_free_pte_list_desc(desc);
}
-static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
+static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc;
struct pte_list_desc *prev_desc;
int i;
if (!rmap_head->val) {
- printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
+ pr_err("%s: %p 0->BUG\n", __func__, spte);
BUG();
} else if (!(rmap_head->val & 1)) {
- rmap_printk("pte_list_remove: %p 1->0\n", spte);
+ rmap_printk("%s: %p 1->0\n", __func__, spte);
if ((u64 *)rmap_head->val != spte) {
- printk(KERN_ERR "pte_list_remove: %p 1->BUG\n", spte);
+ pr_err("%s: %p 1->BUG\n", __func__, spte);
BUG();
}
rmap_head->val = 0;
} else {
- rmap_printk("pte_list_remove: %p many->many\n", spte);
+ rmap_printk("%s: %p many->many\n", __func__, spte);
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
prev_desc = NULL;
while (desc) {
@@ -1280,11 +1296,17 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
prev_desc = desc;
desc = desc->more;
}
- pr_err("pte_list_remove: %p many->many\n", spte);
+ pr_err("%s: %p many->many\n", __func__, spte);
BUG();
}
}
+static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep)
+{
+ mmu_spte_clear_track_bits(sptep);
+ __pte_list_remove(sptep, rmap_head);
+}
+
static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
struct kvm_memory_slot *slot)
{
@@ -1333,7 +1355,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
sp = page_header(__pa(spte));
gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
rmap_head = gfn_to_rmap(kvm, gfn, sp);
- pte_list_remove(spte, rmap_head);
+ __pte_list_remove(spte, rmap_head);
}
/*
@@ -1669,7 +1691,7 @@ static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
while ((sptep = rmap_get_first(rmap_head, &iter))) {
rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
- drop_spte(kvm, sptep);
+ pte_list_remove(rmap_head, sptep);
flush = true;
}
@@ -1705,7 +1727,7 @@ restart:
need_flush = 1;
if (pte_write(*ptep)) {
- drop_spte(kvm, sptep);
+ pte_list_remove(rmap_head, sptep);
goto restart;
} else {
new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
@@ -1853,11 +1875,6 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
}
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
- return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
-}
-
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
{
return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
@@ -1977,7 +1994,7 @@ static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
u64 *parent_pte)
{
- pte_list_remove(parent_pte, &sp->parent_ptes);
+ __pte_list_remove(parent_pte, &sp->parent_ptes);
}
static void drop_parent_pte(struct kvm_mmu_page *sp,
@@ -2170,7 +2187,7 @@ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
if (sp->role.cr4_pae != !!is_pae(vcpu)
- || vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
+ || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
return false;
}
@@ -2364,14 +2381,14 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
int collisions = 0;
LIST_HEAD(invalid_list);
- role = vcpu->arch.mmu.base_role;
+ role = vcpu->arch.mmu->mmu_role.base;
role.level = level;
role.direct = direct;
if (role.direct)
role.cr4_pae = 0;
role.access = access;
- if (!vcpu->arch.mmu.direct_map
- && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
+ if (!vcpu->arch.mmu->direct_map
+ && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
@@ -2446,11 +2463,11 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
{
iterator->addr = addr;
iterator->shadow_addr = root;
- iterator->level = vcpu->arch.mmu.shadow_root_level;
+ iterator->level = vcpu->arch.mmu->shadow_root_level;
if (iterator->level == PT64_ROOT_4LEVEL &&
- vcpu->arch.mmu.root_level < PT64_ROOT_4LEVEL &&
- !vcpu->arch.mmu.direct_map)
+ vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
+ !vcpu->arch.mmu->direct_map)
--iterator->level;
if (iterator->level == PT32E_ROOT_LEVEL) {
@@ -2458,10 +2475,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
* prev_root is currently only used for 64-bit hosts. So only
* the active root_hpa is valid here.
*/
- BUG_ON(root != vcpu->arch.mmu.root_hpa);
+ BUG_ON(root != vcpu->arch.mmu->root_hpa);
iterator->shadow_addr
- = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+ = vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
--iterator->level;
if (!iterator->shadow_addr)
@@ -2472,7 +2489,7 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
struct kvm_vcpu *vcpu, u64 addr)
{
- shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu.root_hpa,
+ shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root_hpa,
addr);
}
@@ -3084,7 +3101,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
int emulate = 0;
gfn_t pseudo_gfn;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return 0;
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
@@ -3114,16 +3131,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
{
- siginfo_t info;
-
- clear_siginfo(&info);
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_MCEERR_AR;
- info.si_addr = (void __user *)address;
- info.si_addr_lsb = PAGE_SHIFT;
-
- send_sig_info(SIGBUS, &info, tsk);
+ send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
}
static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
@@ -3299,7 +3307,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
u64 spte = 0ull;
uint retry_count = 0;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return false;
if (!page_fault_can_be_fast(error_code))
@@ -3469,11 +3477,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
}
/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free)
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ ulong roots_to_free)
{
int i;
LIST_HEAD(invalid_list);
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);
@@ -3533,20 +3541,20 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
struct kvm_mmu_page *sp;
unsigned i;
- if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
+ if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
spin_lock(&vcpu->kvm->mmu_lock);
if(make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, 0, 0,
- vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
+ vcpu->arch.mmu->shadow_root_level, 1, ACC_ALL);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.root_hpa = __pa(sp->spt);
- } else if (vcpu->arch.mmu.shadow_root_level == PT32E_ROOT_LEVEL) {
+ vcpu->arch.mmu->root_hpa = __pa(sp->spt);
+ } else if (vcpu->arch.mmu->shadow_root_level == PT32E_ROOT_LEVEL) {
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
MMU_WARN_ON(VALID_PAGE(root));
spin_lock(&vcpu->kvm->mmu_lock);
@@ -3559,9 +3567,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
+ vcpu->arch.mmu->pae_root[i] = root | PT_PRESENT_MASK;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
} else
BUG();
@@ -3575,7 +3583,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
gfn_t root_gfn;
int i;
- root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> PAGE_SHIFT;
+ root_gfn = vcpu->arch.mmu->get_cr3(vcpu) >> PAGE_SHIFT;
if (mmu_check_root(vcpu, root_gfn))
return 1;
@@ -3584,8 +3592,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* Do we shadow a long mode page table? If so we need to
* write-protect the guests page table root.
*/
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
MMU_WARN_ON(VALID_PAGE(root));
@@ -3595,11 +3603,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
- vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
+ vcpu->arch.mmu->shadow_root_level, 0, ACC_ALL);
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.root_hpa = root;
+ vcpu->arch.mmu->root_hpa = root;
return 0;
}
@@ -3609,17 +3617,17 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* the shadow page table may be a PAE or a long mode page table.
*/
pm_mask = PT_PRESENT_MASK;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL)
+ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
MMU_WARN_ON(VALID_PAGE(root));
- if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
- pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
+ if (vcpu->arch.mmu->root_level == PT32E_ROOT_LEVEL) {
+ pdptr = vcpu->arch.mmu->get_pdptr(vcpu, i);
if (!(pdptr & PT_PRESENT_MASK)) {
- vcpu->arch.mmu.pae_root[i] = 0;
+ vcpu->arch.mmu->pae_root[i] = 0;
continue;
}
root_gfn = pdptr >> PAGE_SHIFT;
@@ -3637,16 +3645,16 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.pae_root[i] = root | pm_mask;
+ vcpu->arch.mmu->pae_root[i] = root | pm_mask;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
/*
* If we shadow a 32 bit page table with a long mode page
* table we enter this path.
*/
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL) {
- if (vcpu->arch.mmu.lm_root == NULL) {
+ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
+ if (vcpu->arch.mmu->lm_root == NULL) {
/*
* The additional page necessary for this is only
* allocated on demand.
@@ -3658,12 +3666,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
if (lm_root == NULL)
return 1;
- lm_root[0] = __pa(vcpu->arch.mmu.pae_root) | pm_mask;
+ lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;
- vcpu->arch.mmu.lm_root = lm_root;
+ vcpu->arch.mmu->lm_root = lm_root;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.lm_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
}
return 0;
@@ -3671,7 +3679,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return mmu_alloc_direct_roots(vcpu);
else
return mmu_alloc_shadow_roots(vcpu);
@@ -3682,17 +3690,16 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
int i;
struct kvm_mmu_page *sp;
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
-
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
sp = page_header(root);
/*
@@ -3723,7 +3730,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
@@ -3797,7 +3804,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
int root, leaf;
bool reserved = false;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
goto exit;
walk_shadow_page_lockless_begin(vcpu);
@@ -3814,7 +3821,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
if (!is_shadow_present_pte(spte))
break;
- reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+ reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte,
iterator.level);
}
@@ -3893,7 +3900,7 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
struct kvm_shadow_walk_iterator iterator;
u64 spte;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
walk_shadow_page_lockless_begin(vcpu);
@@ -3920,7 +3927,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
if (r)
return r;
- MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
return nonpaging_map(vcpu, gva & PAGE_MASK,
@@ -3933,8 +3940,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
arch.gfn = gfn;
- arch.direct_map = vcpu->arch.mmu.direct_map;
- arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
+ arch.direct_map = vcpu->arch.mmu->direct_map;
+ arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
@@ -4040,7 +4047,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
int write = error_code & PFERR_WRITE_MASK;
bool map_writable;
- MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
if (page_fault_handle_page_track(vcpu, error_code, gfn))
return RET_PF_EMULATE;
@@ -4116,7 +4123,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3,
{
uint i;
struct kvm_mmu_root_info root;
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
root.cr3 = mmu->get_cr3(vcpu);
root.hpa = mmu->root_hpa;
@@ -4139,7 +4146,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
union kvm_mmu_page_role new_role,
bool skip_tlb_flush)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
/*
* For now, limit the fast switch to 64-bit hosts+VMs in order to avoid
@@ -4190,7 +4197,8 @@ static void __kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3,
bool skip_tlb_flush)
{
if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush))
- kvm_mmu_free_roots(vcpu, KVM_MMU_ROOT_CURRENT);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu,
+ KVM_MMU_ROOT_CURRENT);
}
void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush)
@@ -4208,7 +4216,7 @@ static unsigned long get_cr3(struct kvm_vcpu *vcpu)
static void inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
- vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+ vcpu->arch.mmu->inject_page_fault(vcpu, fault);
}
static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
@@ -4412,7 +4420,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
- bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+ bool uses_nx = context->nx ||
+ context->mmu_role.base.smep_andnot_wp;
struct rsvd_bits_validate *shadow_zero_check;
int i;
@@ -4551,7 +4560,7 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
* SMAP:kernel-mode data accesses from user-mode
* mappings should fault. A fault is considered
* as a SMAP violation if all of the following
- * conditions are ture:
+ * conditions are true:
* - X86_CR4_SMAP is set in CR4
* - A user page is accessed
* - The access is not a fetch
@@ -4712,27 +4721,65 @@ static void paging32E_init_context(struct kvm_vcpu *vcpu,
paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
}
-static union kvm_mmu_page_role
-kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu)
+static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
{
- union kvm_mmu_page_role role = {0};
+ union kvm_mmu_extended_role ext = {0};
- role.guest_mode = is_guest_mode(vcpu);
- role.smm = is_smm(vcpu);
- role.ad_disabled = (shadow_accessed_mask == 0);
- role.level = kvm_x86_ops->get_tdp_level(vcpu);
- role.direct = true;
- role.access = ACC_ALL;
+ ext.cr0_pg = !!is_paging(vcpu);
+ ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
+ ext.cr4_pse = !!is_pse(vcpu);
+ ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE);
+ ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
+
+ ext.valid = 1;
+
+ return ext;
+}
+
+static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
+ bool base_only)
+{
+ union kvm_mmu_role role = {0};
+
+ role.base.access = ACC_ALL;
+ role.base.nxe = !!is_nx(vcpu);
+ role.base.cr4_pae = !!is_pae(vcpu);
+ role.base.cr0_wp = is_write_protection(vcpu);
+ role.base.smm = is_smm(vcpu);
+ role.base.guest_mode = is_guest_mode(vcpu);
+
+ if (base_only)
+ return role;
+
+ role.ext = kvm_calc_mmu_role_ext(vcpu);
+
+ return role;
+}
+
+static union kvm_mmu_role
+kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
+{
+ union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
+
+ role.base.ad_disabled = (shadow_accessed_mask == 0);
+ role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
+ role.base.direct = true;
return role;
}
static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
+ union kvm_mmu_role new_role =
+ kvm_calc_tdp_mmu_root_page_role(vcpu, false);
+
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == context->mmu_role.as_u64)
+ return;
- context->base_role.word = mmu_base_role_mask.word &
- kvm_calc_tdp_mmu_root_page_role(vcpu).word;
+ context->mmu_role.as_u64 = new_role.as_u64;
context->page_fault = tdp_page_fault;
context->sync_page = nonpaging_sync_page;
context->invlpg = nonpaging_invlpg;
@@ -4772,36 +4819,36 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
reset_tdp_shadow_zero_bits_mask(vcpu, context);
}
-static union kvm_mmu_page_role
-kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu)
-{
- union kvm_mmu_page_role role = {0};
- bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
- bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
-
- role.nxe = is_nx(vcpu);
- role.cr4_pae = !!is_pae(vcpu);
- role.cr0_wp = is_write_protection(vcpu);
- role.smep_andnot_wp = smep && !is_write_protection(vcpu);
- role.smap_andnot_wp = smap && !is_write_protection(vcpu);
- role.guest_mode = is_guest_mode(vcpu);
- role.smm = is_smm(vcpu);
- role.direct = !is_paging(vcpu);
- role.access = ACC_ALL;
+static union kvm_mmu_role
+kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
+{
+ union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
+
+ role.base.smep_andnot_wp = role.ext.cr4_smep &&
+ !is_write_protection(vcpu);
+ role.base.smap_andnot_wp = role.ext.cr4_smap &&
+ !is_write_protection(vcpu);
+ role.base.direct = !is_paging(vcpu);
if (!is_long_mode(vcpu))
- role.level = PT32E_ROOT_LEVEL;
+ role.base.level = PT32E_ROOT_LEVEL;
else if (is_la57_mode(vcpu))
- role.level = PT64_ROOT_5LEVEL;
+ role.base.level = PT64_ROOT_5LEVEL;
else
- role.level = PT64_ROOT_4LEVEL;
+ role.base.level = PT64_ROOT_4LEVEL;
return role;
}
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
+ union kvm_mmu_role new_role =
+ kvm_calc_shadow_mmu_root_page_role(vcpu, false);
+
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == context->mmu_role.as_u64)
+ return;
if (!is_paging(vcpu))
nonpaging_init_context(vcpu, context);
@@ -4812,22 +4859,28 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
else
paging32_init_context(vcpu, context);
- context->base_role.word = mmu_base_role_mask.word &
- kvm_calc_shadow_mmu_root_page_role(vcpu).word;
+ context->mmu_role.as_u64 = new_role.as_u64;
reset_shadow_zero_bits_mask(vcpu, context);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
-static union kvm_mmu_page_role
-kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
+static union kvm_mmu_role
+kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
+ bool execonly)
{
- union kvm_mmu_page_role role = vcpu->arch.mmu.base_role;
+ union kvm_mmu_role role;
+
+ /* Base role is inherited from root_mmu */
+ role.base.word = vcpu->arch.root_mmu.mmu_role.base.word;
+ role.ext = kvm_calc_mmu_role_ext(vcpu);
+
+ role.base.level = PT64_ROOT_4LEVEL;
+ role.base.direct = false;
+ role.base.ad_disabled = !accessed_dirty;
+ role.base.guest_mode = true;
+ role.base.access = ACC_ALL;
- role.level = PT64_ROOT_4LEVEL;
- role.direct = false;
- role.ad_disabled = !accessed_dirty;
- role.guest_mode = true;
- role.access = ACC_ALL;
+ role.ext.execonly = execonly;
return role;
}
@@ -4835,11 +4888,17 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty, gpa_t new_eptp)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
- union kvm_mmu_page_role root_page_role =
- kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty);
+ struct kvm_mmu *context = vcpu->arch.mmu;
+ union kvm_mmu_role new_role =
+ kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
+ execonly);
+
+ __kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);
+
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == context->mmu_role.as_u64)
+ return;
- __kvm_mmu_new_cr3(vcpu, new_eptp, root_page_role, false);
context->shadow_root_level = PT64_ROOT_4LEVEL;
context->nx = true;
@@ -4851,7 +4910,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
context->update_pte = ept_update_pte;
context->root_level = PT64_ROOT_4LEVEL;
context->direct_map = false;
- context->base_role.word = root_page_role.word & mmu_base_role_mask.word;
+ context->mmu_role.as_u64 = new_role.as_u64;
+
update_permission_bitmask(vcpu, context, true);
update_pkru_bitmask(vcpu, context, true);
update_last_nonleaf_level(vcpu, context);
@@ -4862,7 +4922,7 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
kvm_init_shadow_mmu(vcpu);
context->set_cr3 = kvm_x86_ops->set_cr3;
@@ -4873,14 +4933,20 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
+ union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == g_context->mmu_role.as_u64)
+ return;
+
+ g_context->mmu_role.as_u64 = new_role.as_u64;
g_context->get_cr3 = get_cr3;
g_context->get_pdptr = kvm_pdptr_read;
g_context->inject_page_fault = kvm_inject_page_fault;
/*
- * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using
+ * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using
* L1's nested page tables (e.g. EPT12). The nested translation
* of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
* L2's page tables as the first level of translation and L1's
@@ -4919,10 +4985,10 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots)
if (reset_roots) {
uint i;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.mmu->root_hpa = INVALID_PAGE;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+ vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
}
if (mmu_is_nested(vcpu))
@@ -4937,10 +5003,14 @@ EXPORT_SYMBOL_GPL(kvm_init_mmu);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu)
{
+ union kvm_mmu_role role;
+
if (tdp_enabled)
- return kvm_calc_tdp_mmu_root_page_role(vcpu);
+ role = kvm_calc_tdp_mmu_root_page_role(vcpu, true);
else
- return kvm_calc_shadow_mmu_root_page_role(vcpu);
+ role = kvm_calc_shadow_mmu_root_page_role(vcpu, true);
+
+ return role.base;
}
void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -4970,8 +5040,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load);
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
- kvm_mmu_free_roots(vcpu, KVM_MMU_ROOTS_ALL);
- WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa));
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);
@@ -4985,7 +5057,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
}
++vcpu->kvm->stat.mmu_pte_updated;
- vcpu->arch.mmu.update_pte(vcpu, sp, spte, new);
+ vcpu->arch.mmu->update_pte(vcpu, sp, spte, new);
}
static bool need_remote_flush(u64 old, u64 new)
@@ -5162,10 +5234,12 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
local_flush = true;
while (npte--) {
+ u32 base_role = vcpu->arch.mmu->mmu_role.base.word;
+
entry = *spte;
mmu_page_zap_pte(vcpu->kvm, sp, spte);
if (gentry &&
- !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
+ !((sp->role.word ^ base_role)
& mmu_base_role_mask.word) && rmap_can_add(vcpu))
mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
if (need_remote_flush(entry, *spte))
@@ -5183,7 +5257,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
gpa_t gpa;
int r;
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return 0;
gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
@@ -5217,12 +5291,12 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
void *insn, int insn_len)
{
- int r, emulation_type = EMULTYPE_RETRY;
+ int r, emulation_type = 0;
enum emulation_result er;
- bool direct = vcpu->arch.mmu.direct_map;
+ bool direct = vcpu->arch.mmu->direct_map;
/* With shadow page tables, fault_address contains a GVA or nGPA. */
- if (vcpu->arch.mmu.direct_map) {
+ if (vcpu->arch.mmu->direct_map) {
vcpu->arch.gpa_available = true;
vcpu->arch.gpa_val = cr2;
}
@@ -5230,15 +5304,14 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
r = RET_PF_INVALID;
if (unlikely(error_code & PFERR_RSVD_MASK)) {
r = handle_mmio_page_fault(vcpu, cr2, direct);
- if (r == RET_PF_EMULATE) {
- emulation_type = 0;
+ if (r == RET_PF_EMULATE)
goto emulate;
- }
}
if (r == RET_PF_INVALID) {
- r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
- false);
+ r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+ lower_32_bits(error_code),
+ false);
WARN_ON(r == RET_PF_INVALID);
}
@@ -5254,14 +5327,25 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
* paging in both guests. If true, we simply unprotect the page
* and resume the guest.
*/
- if (vcpu->arch.mmu.direct_map &&
+ if (vcpu->arch.mmu->direct_map &&
(error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
return 1;
}
- if (mmio_info_in_cache(vcpu, cr2, direct))
- emulation_type = 0;
+ /*
+ * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still
+ * optimistically try to just unprotect the page and let the processor
+ * re-execute the instruction that caused the page fault. Do not allow
+ * retrying MMIO emulation, as it's not only pointless but could also
+ * cause us to enter an infinite loop because the processor will keep
+ * faulting on the non-existent MMIO address. Retrying an instruction
+ * from a nested guest is also pointless and dangerous as we are only
+ * explicitly shadowing L1's page tables, i.e. unprotecting something
+ * for L1 isn't going to magically fix whatever issue cause L2 to fail.
+ */
+ if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu))
+ emulation_type = EMULTYPE_ALLOW_RETRY;
emulate:
/*
* On AMD platforms, under certain conditions insn_len may be zero on #NPF.
@@ -5291,7 +5375,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
int i;
/* INVLPG on a * non-canonical address is a NOP according to the SDM. */
@@ -5322,7 +5406,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
bool tlb_flush = false;
uint i;
@@ -5366,8 +5450,8 @@ EXPORT_SYMBOL_GPL(kvm_disable_tdp);
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
- free_page((unsigned long)vcpu->arch.mmu.pae_root);
- free_page((unsigned long)vcpu->arch.mmu.lm_root);
+ free_page((unsigned long)vcpu->arch.mmu->pae_root);
+ free_page((unsigned long)vcpu->arch.mmu->lm_root);
}
static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
@@ -5387,9 +5471,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
if (!page)
return -ENOMEM;
- vcpu->arch.mmu.pae_root = page_address(page);
+ vcpu->arch.mmu->pae_root = page_address(page);
for (i = 0; i < 4; ++i)
- vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
+ vcpu->arch.mmu->pae_root[i] = INVALID_PAGE;
return 0;
}
@@ -5398,22 +5482,21 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
{
uint i;
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
- vcpu->arch.mmu.translate_gpa = translate_gpa;
- vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.root_mmu.translate_gpa = translate_gpa;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-
- return alloc_mmu_pages(vcpu);
-}
+ vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-void kvm_mmu_setup(struct kvm_vcpu *vcpu)
-{
- MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
- kvm_init_mmu(vcpu, true);
+ vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
+ return alloc_mmu_pages(vcpu);
}
static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
@@ -5596,7 +5679,7 @@ restart:
if (sp->role.direct &&
!kvm_is_reserved_pfn(pfn) &&
PageTransCompoundMap(pfn_to_page(pfn))) {
- drop_spte(kvm, sptep);
+ pte_list_remove(rmap_head, sptep);
need_tlb_flush = 1;
goto restart;
}
@@ -5853,6 +5936,16 @@ int kvm_mmu_module_init(void)
{
int ret = -ENOMEM;
+ /*
+ * MMU roles use union aliasing which is, generally speaking, an
+ * undefined behavior. However, we supposedly know how compilers behave
+ * and the current status quo is unlikely to change. Guardians below are
+ * supposed to let us know if the assumption becomes false.
+ */
+ BUILD_BUG_ON(sizeof(union kvm_mmu_page_role) != sizeof(u32));
+ BUILD_BUG_ON(sizeof(union kvm_mmu_extended_role) != sizeof(u32));
+ BUILD_BUG_ON(sizeof(union kvm_mmu_role) != sizeof(u64));
+
kvm_mmu_reset_all_pte_masks();
pte_list_desc_cache = kmem_cache_create("pte_list_desc",
@@ -5882,7 +5975,7 @@ out:
}
/*
- * Caculate mmu pages needed for kvm.
+ * Calculate mmu pages needed for kvm.
*/
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
{
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 1fab69c0b2f3..c7b333147c4a 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,11 +43,6 @@
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3
-#define PT_PDPE_LEVEL 3
-#define PT_DIRECTORY_LEVEL 2
-#define PT_PAGE_TABLE_LEVEL 1
-#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1)
-
static inline u64 rsvd_bits(int s, int e)
{
if (e < s)
@@ -80,7 +75,7 @@ static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
- if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE))
+ if (likely(vcpu->arch.mmu->root_hpa != INVALID_PAGE))
return 0;
return kvm_mmu_load(vcpu);
@@ -102,9 +97,9 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu)
{
- if (VALID_PAGE(vcpu->arch.mmu.root_hpa))
- vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa |
- kvm_get_active_pcid(vcpu));
+ if (VALID_PAGE(vcpu->arch.mmu->root_hpa))
+ vcpu->arch.mmu->set_cr3(vcpu, vcpu->arch.mmu->root_hpa |
+ kvm_get_active_pcid(vcpu));
}
/*
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 1272861e77b9..abac7e208853 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -59,19 +59,19 @@ static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
int i;
struct kvm_mmu_page *sp;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
sp = page_header(root);
- __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu.root_level);
+ __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu->root_level);
return;
}
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
@@ -122,7 +122,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
hpa = pfn << PAGE_SHIFT;
if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
audit_printk(vcpu->kvm, "levels %d pfn %llx hpa %llx "
- "ent %llxn", vcpu->arch.mmu.root_level, pfn,
+ "ent %llxn", vcpu->arch.mmu->root_level, pfn,
hpa, *sptep);
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 14ffd973df54..7cf2185b7eb5 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -158,14 +158,15 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *spte,
u64 gpte)
{
- if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+ if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
goto no_present;
if (!FNAME(is_present_gpte)(gpte))
goto no_present;
/* if accessed bit is not supported prefetch non accessed gpte */
- if (PT_HAVE_ACCESSED_DIRTY(&vcpu->arch.mmu) && !(gpte & PT_GUEST_ACCESSED_MASK))
+ if (PT_HAVE_ACCESSED_DIRTY(vcpu->arch.mmu) &&
+ !(gpte & PT_GUEST_ACCESSED_MASK))
goto no_present;
return false;
@@ -480,7 +481,7 @@ error:
static int FNAME(walk_addr)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, gva_t addr, u32 access)
{
- return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.mmu, addr,
+ return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
access);
}
@@ -509,7 +510,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access & FNAME(gpte_access)(gpte);
- FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
no_dirty_log && (pte_access & ACC_WRITE_MASK));
if (is_error_pfn(pfn))
@@ -604,7 +605,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
direct_access = gw->pte_access;
- top_level = vcpu->arch.mmu.root_level;
+ top_level = vcpu->arch.mmu->root_level;
if (top_level == PT32E_ROOT_LEVEL)
top_level = PT32_ROOT_LEVEL;
/*
@@ -616,7 +617,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
if (FNAME(gpte_changed)(vcpu, gw, top_level))
goto out_gpte_changed;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
goto out_gpte_changed;
for (shadow_walk_init(&it, vcpu, addr);
@@ -1004,7 +1005,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access;
pte_access &= FNAME(gpte_access)(gpte);
- FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
&nr_present))
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 6276140044d0..0e21ccc46792 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -436,14 +436,18 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
static inline bool svm_sev_enabled(void)
{
- return max_sev_asid;
+ return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0;
}
static inline bool sev_guest(struct kvm *kvm)
{
+#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
return sev->active;
+#else
+ return false;
+#endif
}
static inline int sev_get_asid(struct kvm *kvm)
@@ -776,7 +780,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
}
if (!svm->next_rip) {
- if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
+ if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) !=
EMULATE_DONE)
printk(KERN_DEBUG "%s: NOP\n", __func__);
return;
@@ -805,6 +809,8 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
nested_svm_check_exception(svm, nr, has_error_code, error_code))
return;
+ kvm_deliver_exception_payload(&svm->vcpu);
+
if (nr == BP_VECTOR && !static_cpu_has(X86_FEATURE_NRIPS)) {
unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
@@ -1226,8 +1232,7 @@ static __init int sev_hardware_setup(void)
min_sev_asid = cpuid_edx(0x8000001F);
/* Initialize SEV ASID bitmap */
- sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid),
- sizeof(unsigned long), GFP_KERNEL);
+ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
if (!sev_asid_bitmap)
return 1;
@@ -1405,7 +1410,7 @@ static __exit void svm_hardware_unsetup(void)
int cpu;
if (svm_sev_enabled())
- kfree(sev_asid_bitmap);
+ bitmap_free(sev_asid_bitmap);
for_each_possible_cpu(cpu)
svm_cpu_uninit(cpu);
@@ -2715,7 +2720,7 @@ static int gp_interception(struct vcpu_svm *svm)
WARN_ON_ONCE(!enable_vmware_backdoor);
- er = emulate_instruction(vcpu,
+ er = kvm_emulate_instruction(vcpu,
EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
if (er == EMULATE_USER_EXIT)
return 0;
@@ -2819,7 +2824,7 @@ static int io_interception(struct vcpu_svm *svm)
string = (io_info & SVM_IOIO_STR_MASK) != 0;
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
if (string)
- return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
port = io_info >> 16;
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
@@ -2919,18 +2924,18 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
{
WARN_ON(mmu_is_nested(vcpu));
kvm_init_shadow_mmu(vcpu);
- vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3;
- vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3;
- vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr;
- vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
- vcpu->arch.mmu.shadow_root_level = get_npt_level(vcpu);
- reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
+ vcpu->arch.mmu->set_cr3 = nested_svm_set_tdp_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_svm_get_tdp_cr3;
+ vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr;
+ vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
+ vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu);
+ reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu);
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
}
static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static int nested_svm_check_permissions(struct vcpu_svm *svm)
@@ -2966,16 +2971,13 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
svm->vmcb->control.exit_info_1 = error_code;
/*
- * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception.
- * The fix is to add the ancillary datum (CR2 or DR6) to structs
- * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be
- * written only when inject_pending_event runs (DR6 would written here
- * too). This should be conditional on a new capability---if the
- * capability is disabled, kvm_multiple_exception would write the
- * ancillary information to CR2 or DR6, for backwards ABI-compatibility.
+ * EXITINFO2 is undefined for all exception intercepts other
+ * than #PF.
*/
if (svm->vcpu.arch.exception.nested_apf)
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
+ else if (svm->vcpu.arch.exception.has_payload)
+ svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
else
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
@@ -3861,7 +3863,7 @@ static int iret_interception(struct vcpu_svm *svm)
static int invlpg_interception(struct vcpu_svm *svm)
{
if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
- return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1);
return kvm_skip_emulated_instruction(&svm->vcpu);
@@ -3869,13 +3871,13 @@ static int invlpg_interception(struct vcpu_svm *svm)
static int emulate_on_interception(struct vcpu_svm *svm)
{
- return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
}
static int rsm_interception(struct vcpu_svm *svm)
{
- return x86_emulate_instruction(&svm->vcpu, 0, 0,
- rsm_ins_bytes, 2) == EMULATE_DONE;
+ return kvm_emulate_instruction_from_buffer(&svm->vcpu,
+ rsm_ins_bytes, 2) == EMULATE_DONE;
}
static int rdpmc_interception(struct vcpu_svm *svm)
@@ -4700,7 +4702,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm)
ret = avic_unaccel_trap_write(svm);
} else {
/* Handling Fault */
- ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE);
+ ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE);
}
return ret;
@@ -5639,26 +5641,24 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r13, %c[r13](%[svm]) \n\t"
"mov %%r14, %c[r14](%[svm]) \n\t"
"mov %%r15, %c[r15](%[svm]) \n\t"
-#endif
/*
* Clear host registers marked as clobbered to prevent
* speculative use.
*/
- "xor %%" _ASM_BX ", %%" _ASM_BX " \n\t"
- "xor %%" _ASM_CX ", %%" _ASM_CX " \n\t"
- "xor %%" _ASM_DX ", %%" _ASM_DX " \n\t"
- "xor %%" _ASM_SI ", %%" _ASM_SI " \n\t"
- "xor %%" _ASM_DI ", %%" _ASM_DI " \n\t"
-#ifdef CONFIG_X86_64
- "xor %%r8, %%r8 \n\t"
- "xor %%r9, %%r9 \n\t"
- "xor %%r10, %%r10 \n\t"
- "xor %%r11, %%r11 \n\t"
- "xor %%r12, %%r12 \n\t"
- "xor %%r13, %%r13 \n\t"
- "xor %%r14, %%r14 \n\t"
- "xor %%r15, %%r15 \n\t"
+ "xor %%r8d, %%r8d \n\t"
+ "xor %%r9d, %%r9d \n\t"
+ "xor %%r10d, %%r10d \n\t"
+ "xor %%r11d, %%r11d \n\t"
+ "xor %%r12d, %%r12d \n\t"
+ "xor %%r13d, %%r13d \n\t"
+ "xor %%r14d, %%r14d \n\t"
+ "xor %%r15d, %%r15d \n\t"
#endif
+ "xor %%ebx, %%ebx \n\t"
+ "xor %%ecx, %%ecx \n\t"
+ "xor %%edx, %%edx \n\t"
+ "xor %%esi, %%esi \n\t"
+ "xor %%edi, %%edi \n\t"
"pop %%" _ASM_BP
:
: [svm]"a"(svm),
@@ -6747,7 +6747,7 @@ e_free:
static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
{
unsigned long vaddr, vaddr_end, next_vaddr;
- unsigned long dst_vaddr, dst_vaddr_end;
+ unsigned long dst_vaddr;
struct page **src_p, **dst_p;
struct kvm_sev_dbg debug;
unsigned long n;
@@ -6763,7 +6763,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
size = debug.len;
vaddr_end = vaddr + size;
dst_vaddr = debug.dst_uaddr;
- dst_vaddr_end = dst_vaddr + size;
for (; vaddr < vaddr_end; vaddr = next_vaddr) {
int len, s_off, d_off;
@@ -7038,6 +7037,13 @@ failed:
return ret;
}
+static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version)
+{
+ /* Intel-only feature */
+ return -ENODEV;
+}
+
static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
@@ -7150,6 +7156,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.check_intercept = svm_check_intercept,
.handle_external_intr = svm_handle_external_intr,
+ .request_immediate_exit = __kvm_request_immediate_exit,
+
.sched_in = svm_sched_in,
.pmu_ops = &amd_pmu_ops,
@@ -7165,6 +7173,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.mem_enc_op = svm_mem_enc_op,
.mem_enc_reg_region = svm_register_enc_region,
.mem_enc_unreg_region = svm_unregister_enc_region,
+
+ .nested_enable_evmcs = nested_enable_evmcs,
};
static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 0f997683404f..0659465a745c 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1418,6 +1418,48 @@ TRACE_EVENT(kvm_hv_flush_tlb_ex,
__entry->valid_bank_mask, __entry->format,
__entry->address_space, __entry->flags)
);
+
+/*
+ * Tracepoints for kvm_hv_send_ipi.
+ */
+TRACE_EVENT(kvm_hv_send_ipi,
+ TP_PROTO(u32 vector, u64 processor_mask),
+ TP_ARGS(vector, processor_mask),
+
+ TP_STRUCT__entry(
+ __field(u32, vector)
+ __field(u64, processor_mask)
+ ),
+
+ TP_fast_assign(
+ __entry->vector = vector;
+ __entry->processor_mask = processor_mask;
+ ),
+
+ TP_printk("vector %x processor_mask 0x%llx",
+ __entry->vector, __entry->processor_mask)
+);
+
+TRACE_EVENT(kvm_hv_send_ipi_ex,
+ TP_PROTO(u32 vector, u64 format, u64 valid_bank_mask),
+ TP_ARGS(vector, format, valid_bank_mask),
+
+ TP_STRUCT__entry(
+ __field(u32, vector)
+ __field(u64, format)
+ __field(u64, valid_bank_mask)
+ ),
+
+ TP_fast_assign(
+ __entry->vector = vector;
+ __entry->format = format;
+ __entry->valid_bank_mask = valid_bank_mask;
+ ),
+
+ TP_printk("vector %x format %llx valid_bank_mask 0x%llx",
+ __entry->vector, __entry->format,
+ __entry->valid_bank_mask)
+);
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1d26f3c4985b..4555077d69ce 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -20,6 +20,7 @@
#include "mmu.h"
#include "cpuid.h"
#include "lapic.h"
+#include "hyperv.h"
#include <linux/kvm_host.h>
#include <linux/module.h>
@@ -61,7 +62,7 @@
#define __ex(x) __kvm_handle_fault_on_reboot(x)
#define __ex_clear(x, reg) \
- ____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg)
+ ____kvm_handle_fault_on_reboot(x, "xor " reg ", " reg)
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -107,9 +108,12 @@ module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
* VMX and be a hypervisor for its own guests. If nested=0, guests may not
* use VMX instructions.
*/
-static bool __read_mostly nested = 0;
+static bool __read_mostly nested = 1;
module_param(nested, bool, S_IRUGO);
+static bool __read_mostly nested_early_check = 0;
+module_param(nested_early_check, bool, S_IRUGO);
+
static u64 __read_mostly host_xss;
static bool __read_mostly enable_pml = 1;
@@ -121,7 +125,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
#define MSR_BITMAP_MODE_X2APIC 1
#define MSR_BITMAP_MODE_X2APIC_APICV 2
-#define MSR_BITMAP_MODE_LM 4
#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
@@ -132,7 +135,7 @@ static bool __read_mostly enable_preemption_timer = 1;
module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
#endif
-#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
+#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
#define KVM_VM_CR0_ALWAYS_ON \
(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \
@@ -188,6 +191,7 @@ static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
module_param(ple_window_max, uint, 0444);
extern const ulong vmx_return;
+extern const ulong vmx_early_consistency_check_return;
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
@@ -397,6 +401,7 @@ struct loaded_vmcs {
int cpu;
bool launched;
bool nmi_known_unmasked;
+ bool hv_timer_armed;
/* Support for vnmi-less CPUs */
int soft_vnmi_blocked;
ktime_t entry_time;
@@ -827,14 +832,28 @@ struct nested_vmx {
*/
struct vmcs12 *cached_shadow_vmcs12;
/*
- * Indicates if the shadow vmcs must be updated with the
- * data hold by vmcs12
+ * Indicates if the shadow vmcs or enlightened vmcs must be updated
+ * with the data held by struct vmcs12.
*/
- bool sync_shadow_vmcs;
+ bool need_vmcs12_sync;
bool dirty_vmcs12;
+ /*
+ * vmcs02 has been initialized, i.e. state that is constant for
+ * vmcs02 has been written to the backing VMCS. Initialization
+ * is delayed until L1 actually attempts to run a nested VM.
+ */
+ bool vmcs02_initialized;
+
bool change_vmcs01_virtual_apic_mode;
+ /*
+ * Enlightened VMCS has been enabled. It does not mean that L1 has to
+ * use it. However, VMX features available to L1 will be limited based
+ * on what the enlightened VMCS supports.
+ */
+ bool enlightened_vmcs_enabled;
+
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
@@ -856,6 +875,7 @@ struct nested_vmx {
/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
u64 vmcs01_debugctl;
+ u64 vmcs01_guest_bndcfgs;
u16 vpid02;
u16 last_vpid;
@@ -869,6 +889,10 @@ struct nested_vmx {
/* in guest mode on SMM entry? */
bool guest_mode;
} smm;
+
+ gpa_t hv_evmcs_vmptr;
+ struct page *hv_evmcs_page;
+ struct hv_enlightened_vmcs *hv_evmcs;
};
#define POSTED_INTR_ON 0
@@ -1019,6 +1043,8 @@ struct vcpu_vmx {
int ple_window;
bool ple_window_dirty;
+ bool req_immediate_exit;
+
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
@@ -1378,6 +1404,49 @@ DEFINE_STATIC_KEY_FALSE(enable_evmcs);
#define KVM_EVMCS_VERSION 1
+/*
+ * Enlightened VMCSv1 doesn't support these:
+ *
+ * POSTED_INTR_NV = 0x00000002,
+ * GUEST_INTR_STATUS = 0x00000810,
+ * APIC_ACCESS_ADDR = 0x00002014,
+ * POSTED_INTR_DESC_ADDR = 0x00002016,
+ * EOI_EXIT_BITMAP0 = 0x0000201c,
+ * EOI_EXIT_BITMAP1 = 0x0000201e,
+ * EOI_EXIT_BITMAP2 = 0x00002020,
+ * EOI_EXIT_BITMAP3 = 0x00002022,
+ * GUEST_PML_INDEX = 0x00000812,
+ * PML_ADDRESS = 0x0000200e,
+ * VM_FUNCTION_CONTROL = 0x00002018,
+ * EPTP_LIST_ADDRESS = 0x00002024,
+ * VMREAD_BITMAP = 0x00002026,
+ * VMWRITE_BITMAP = 0x00002028,
+ *
+ * TSC_MULTIPLIER = 0x00002032,
+ * PLE_GAP = 0x00004020,
+ * PLE_WINDOW = 0x00004022,
+ * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
+ * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
+ * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
+ *
+ * Currently unsupported in KVM:
+ * GUEST_IA32_RTIT_CTL = 0x00002814,
+ */
+#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \
+ PIN_BASED_VMX_PREEMPTION_TIMER)
+#define EVMCS1_UNSUPPORTED_2NDEXEC \
+ (SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \
+ SECONDARY_EXEC_APIC_REGISTER_VIRT | \
+ SECONDARY_EXEC_ENABLE_PML | \
+ SECONDARY_EXEC_ENABLE_VMFUNC | \
+ SECONDARY_EXEC_SHADOW_VMCS | \
+ SECONDARY_EXEC_TSC_SCALING | \
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)
+
#if IS_ENABLED(CONFIG_HYPERV)
static bool __read_mostly enlightened_vmcs = true;
module_param(enlightened_vmcs, bool, 0444);
@@ -1470,69 +1539,12 @@ static void evmcs_load(u64 phys_addr)
static void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
{
- /*
- * Enlightened VMCSv1 doesn't support these:
- *
- * POSTED_INTR_NV = 0x00000002,
- * GUEST_INTR_STATUS = 0x00000810,
- * APIC_ACCESS_ADDR = 0x00002014,
- * POSTED_INTR_DESC_ADDR = 0x00002016,
- * EOI_EXIT_BITMAP0 = 0x0000201c,
- * EOI_EXIT_BITMAP1 = 0x0000201e,
- * EOI_EXIT_BITMAP2 = 0x00002020,
- * EOI_EXIT_BITMAP3 = 0x00002022,
- */
- vmcs_conf->pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
- vmcs_conf->cpu_based_2nd_exec_ctrl &=
- ~SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
- vmcs_conf->cpu_based_2nd_exec_ctrl &=
- ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmcs_conf->cpu_based_2nd_exec_ctrl &=
- ~SECONDARY_EXEC_APIC_REGISTER_VIRT;
-
- /*
- * GUEST_PML_INDEX = 0x00000812,
- * PML_ADDRESS = 0x0000200e,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_ENABLE_PML;
-
- /* VM_FUNCTION_CONTROL = 0x00002018, */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_ENABLE_VMFUNC;
-
- /*
- * EPTP_LIST_ADDRESS = 0x00002024,
- * VMREAD_BITMAP = 0x00002026,
- * VMWRITE_BITMAP = 0x00002028,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_SHADOW_VMCS;
-
- /*
- * TSC_MULTIPLIER = 0x00002032,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_TSC_SCALING;
-
- /*
- * PLE_GAP = 0x00004020,
- * PLE_WINDOW = 0x00004022,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-
- /*
- * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
- */
- vmcs_conf->pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
- /*
- * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
- * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
- */
- vmcs_conf->vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
- vmcs_conf->vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
- /*
- * Currently unsupported in KVM:
- * GUEST_IA32_RTIT_CTL = 0x00002814,
- */
}
/* check_ept_pointer() should be under protection of ept_pointer_lock. */
@@ -1557,22 +1569,27 @@ static void check_ept_pointer_match(struct kvm *kvm)
static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
{
- int ret;
+ struct kvm_vcpu *vcpu;
+ int ret = -ENOTSUPP, i;
spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK)
check_ept_pointer_match(kvm);
+ /*
+ * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the
+ * base of EPT PML4 table, strip off EPT configuration information.
+ */
if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) {
- ret = -ENOTSUPP;
- goto out;
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ ret |= hyperv_flush_guest_mapping(
+ to_vmx(kvm_get_vcpu(kvm, i))->ept_pointer & PAGE_MASK);
+ } else {
+ ret = hyperv_flush_guest_mapping(
+ to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK);
}
- ret = hyperv_flush_guest_mapping(
- to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer);
-
-out:
spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
return ret;
}
@@ -1588,6 +1605,35 @@ static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
static inline void evmcs_touch_msr_bitmap(void) {}
#endif /* IS_ENABLED(CONFIG_HYPERV) */
+static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /* We don't support disabling the feature for simplicity. */
+ if (vmx->nested.enlightened_vmcs_enabled)
+ return 0;
+
+ vmx->nested.enlightened_vmcs_enabled = true;
+
+ /*
+ * vmcs_version represents the range of supported Enlightened VMCS
+ * versions: lower 8 bits is the minimal version, higher 8 bits is the
+ * maximum supported version. KVM supports versions from 1 to
+ * KVM_EVMCS_VERSION.
+ */
+ if (vmcs_version)
+ *vmcs_version = (KVM_EVMCS_VERSION << 8) | 1;
+
+ vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
+ vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ vmx->nested.msrs.secondary_ctls_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+ vmx->nested.msrs.vmfunc_controls &= ~EVMCS1_UNSUPPORTED_VMFUNC;
+
+ return 0;
+}
+
static inline bool is_exception_n(u32 intr_info, u8 vector)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
@@ -1610,11 +1656,6 @@ static inline bool is_page_fault(u32 intr_info)
return is_exception_n(intr_info, PF_VECTOR);
}
-static inline bool is_no_device(u32 intr_info)
-{
- return is_exception_n(intr_info, NM_VECTOR);
-}
-
static inline bool is_invalid_opcode(u32 intr_info)
{
return is_exception_n(intr_info, UD_VECTOR);
@@ -1625,12 +1666,6 @@ static inline bool is_gp_fault(u32 intr_info)
return is_exception_n(intr_info, GP_VECTOR);
}
-static inline bool is_external_interrupt(u32 intr_info)
-{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
- == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
-}
-
static inline bool is_machine_check(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
@@ -2056,9 +2091,6 @@ static inline bool is_nmi(u32 intr_info)
static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
u32 exit_intr_info,
unsigned long exit_qualification);
-static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12,
- u32 reason, unsigned long qualification);
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
@@ -2070,7 +2102,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
return -1;
}
-static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva)
{
struct {
u64 vpid : 16;
@@ -2079,22 +2111,20 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva)
} operand = { vpid, 0, gva };
bool error;
- asm volatile (__ex(ASM_VMX_INVVPID) CC_SET(na)
- : CC_OUT(na) (error) : "a"(&operand), "c"(ext)
- : "memory");
+ asm volatile (__ex("invvpid %2, %1") CC_SET(na)
+ : CC_OUT(na) (error) : "r"(ext), "m"(operand));
BUG_ON(error);
}
-static inline void __invept(int ext, u64 eptp, gpa_t gpa)
+static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa)
{
struct {
u64 eptp, gpa;
} operand = {eptp, gpa};
bool error;
- asm volatile (__ex(ASM_VMX_INVEPT) CC_SET(na)
- : CC_OUT(na) (error) : "a" (&operand), "c" (ext)
- : "memory");
+ asm volatile (__ex("invept %2, %1") CC_SET(na)
+ : CC_OUT(na) (error) : "r"(ext), "m"(operand));
BUG_ON(error);
}
@@ -2113,9 +2143,8 @@ static void vmcs_clear(struct vmcs *vmcs)
u64 phys_addr = __pa(vmcs);
bool error;
- asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) CC_SET(na)
- : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr)
- : "memory");
+ asm volatile (__ex("vmclear %1") CC_SET(na)
+ : CC_OUT(na) (error) : "m"(phys_addr));
if (unlikely(error))
printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
vmcs, phys_addr);
@@ -2138,9 +2167,8 @@ static void vmcs_load(struct vmcs *vmcs)
if (static_branch_unlikely(&enable_evmcs))
return evmcs_load(phys_addr);
- asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) CC_SET(na)
- : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr)
- : "memory");
+ asm volatile (__ex("vmptrld %1") CC_SET(na)
+ : CC_OUT(na) (error) : "m"(phys_addr));
if (unlikely(error))
printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n",
vmcs, phys_addr);
@@ -2316,8 +2344,8 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
{
unsigned long value;
- asm volatile (__ex_clear(ASM_VMX_VMREAD_RDX_RAX, "%0")
- : "=a"(value) : "d"(field) : "cc");
+ asm volatile (__ex_clear("vmread %1, %0", "%k0")
+ : "=r"(value) : "r"(field));
return value;
}
@@ -2368,8 +2396,8 @@ static __always_inline void __vmcs_writel(unsigned long field, unsigned long val
{
bool error;
- asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) CC_SET(na)
- : CC_OUT(na) (error) : "a"(value), "d"(field));
+ asm volatile (__ex("vmwrite %2, %1") CC_SET(na)
+ : CC_OUT(na) (error) : "r"(field), "rm"(value));
if (unlikely(error))
vmwrite_error(field, value);
}
@@ -2700,7 +2728,8 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
u64 guest_val, u64 host_val)
{
vmcs_write64(guest_val_vmcs, guest_val);
- vmcs_write64(host_val_vmcs, host_val);
+ if (host_val_vmcs != HOST_IA32_EFER)
+ vmcs_write64(host_val_vmcs, host_val);
vm_entry_controls_setbit(vmx, entry);
vm_exit_controls_setbit(vmx, exit);
}
@@ -2798,8 +2827,6 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- clear_atomic_switch_msr(vmx, MSR_EFER);
-
/*
* On EPT, we can't emulate NX, so we must switch EFER atomically.
* On CPUs that support "load IA32_EFER", always switch EFER
@@ -2812,8 +2839,12 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer, false);
+ else
+ clear_atomic_switch_msr(vmx, MSR_EFER);
return false;
} else {
+ clear_atomic_switch_msr(vmx, MSR_EFER);
+
guest_efer &= ~ignore_bits;
guest_efer |= host_efer & ignore_bits;
@@ -2864,6 +2895,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
u16 fs_sel, gs_sel;
int i;
+ vmx->req_immediate_exit = false;
+
if (vmx->loaded_cpu_state)
return;
@@ -2894,8 +2927,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
}
- if (is_long_mode(&vmx->vcpu))
- wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#else
savesegment(fs, fs_sel);
savesegment(gs, gs_sel);
@@ -2946,8 +2978,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
vmx->loaded_cpu_state = NULL;
#ifdef CONFIG_X86_64
- if (is_long_mode(&vmx->vcpu))
- rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
kvm_load_ldt(host_state->ldt_sel);
@@ -2975,24 +3006,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
#ifdef CONFIG_X86_64
static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
{
- if (is_long_mode(&vmx->vcpu)) {
- preempt_disable();
- if (vmx->loaded_cpu_state)
- rdmsrl(MSR_KERNEL_GS_BASE,
- vmx->msr_guest_kernel_gs_base);
- preempt_enable();
- }
+ preempt_disable();
+ if (vmx->loaded_cpu_state)
+ rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ preempt_enable();
return vmx->msr_guest_kernel_gs_base;
}
static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
{
- if (is_long_mode(&vmx->vcpu)) {
- preempt_disable();
- if (vmx->loaded_cpu_state)
- wrmsrl(MSR_KERNEL_GS_BASE, data);
- preempt_enable();
- }
+ preempt_disable();
+ if (vmx->loaded_cpu_state)
+ wrmsrl(MSR_KERNEL_GS_BASE, data);
+ preempt_enable();
vmx->msr_guest_kernel_gs_base = data;
}
#endif
@@ -3270,34 +3296,30 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
unsigned int nr = vcpu->arch.exception.nr;
+ bool has_payload = vcpu->arch.exception.has_payload;
+ unsigned long payload = vcpu->arch.exception.payload;
if (nr == PF_VECTOR) {
if (vcpu->arch.exception.nested_apf) {
*exit_qual = vcpu->arch.apf.nested_apf_token;
return 1;
}
- /*
- * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
- * The fix is to add the ancillary datum (CR2 or DR6) to structs
- * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
- * can be written only when inject_pending_event runs. This should be
- * conditional on a new capability---if the capability is disabled,
- * kvm_multiple_exception would write the ancillary information to
- * CR2 or DR6, for backwards ABI-compatibility.
- */
if (nested_vmx_is_page_fault_vmexit(vmcs12,
vcpu->arch.exception.error_code)) {
- *exit_qual = vcpu->arch.cr2;
- return 1;
- }
- } else {
- if (vmcs12->exception_bitmap & (1u << nr)) {
- if (nr == DB_VECTOR)
- *exit_qual = vcpu->arch.dr6;
- else
- *exit_qual = 0;
+ *exit_qual = has_payload ? payload : vcpu->arch.cr2;
return 1;
}
+ } else if (vmcs12->exception_bitmap & (1u << nr)) {
+ if (nr == DB_VECTOR) {
+ if (!has_payload) {
+ payload = vcpu->arch.dr6;
+ payload &= ~(DR6_FIXED_1 | DR6_BT);
+ payload ^= DR6_RTM;
+ }
+ *exit_qual = payload;
+ } else
+ *exit_qual = 0;
+ return 1;
}
return 0;
@@ -3324,6 +3346,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
u32 error_code = vcpu->arch.exception.error_code;
u32 intr_info = nr | INTR_INFO_VALID_MASK;
+ kvm_deliver_exception_payload(vcpu);
+
if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
@@ -3528,9 +3552,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
- if (kvm_mpx_supported())
- msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
-
/* We support free control of debug control saving. */
msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
@@ -3547,8 +3568,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
VM_ENTRY_LOAD_IA32_PAT;
msrs->entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
- if (kvm_mpx_supported())
- msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
/* We support free control of debug control loading. */
msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
@@ -3596,12 +3615,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
msrs->secondary_ctls_high);
msrs->secondary_ctls_low = 0;
msrs->secondary_ctls_high &=
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING;
+
/*
* We can emulate "VMCS shadowing," even if the hardware
* doesn't support it.
@@ -3658,6 +3677,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
msrs->secondary_ctls_high |=
SECONDARY_EXEC_UNRESTRICTED_GUEST;
+ if (flexpriority_enabled)
+ msrs->secondary_ctls_high |=
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+
/* miscellaneous data */
rdmsr(MSR_IA32_VMX_MISC,
msrs->misc_low,
@@ -4396,9 +4419,7 @@ static void kvm_cpu_vmxon(u64 addr)
cr4_set_bits(X86_CR4_VMXE);
intel_pt_handle_vmx(1);
- asm volatile (ASM_VMX_VMXON_RAX
- : : "a"(&addr), "m"(addr)
- : "memory", "cc");
+ asm volatile ("vmxon %0" : : "m"(addr));
}
static int hardware_enable(void)
@@ -4467,7 +4488,7 @@ static void vmclear_local_loaded_vmcss(void)
*/
static void kvm_cpu_vmxoff(void)
{
- asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
+ asm volatile (__ex("vmxoff"));
intel_pt_handle_vmx(0);
cr4_clear_bits(X86_CR4_VMXE);
@@ -5068,19 +5089,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
if (!msr)
return;
- /*
- * MSR_KERNEL_GS_BASE is not intercepted when the guest is in
- * 64-bit mode as a 64-bit kernel may frequently access the
- * MSR. This means we need to manually save/restore the MSR
- * when switching between guest and host state, but only if
- * the guest is in 64-bit mode. Sync our cached value if the
- * guest is transitioning to 32-bit mode and the CPU contains
- * guest state, i.e. the cache is stale.
- */
-#ifdef CONFIG_X86_64
- if (!(efer & EFER_LMA))
- (void)vmx_read_guest_kernel_gs_base(vmx);
-#endif
vcpu->arch.efer = efer;
if (efer & EFER_LMA) {
vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
@@ -5124,9 +5132,10 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
bool invalidate_gpa)
{
if (enable_ept && (invalidate_gpa || !enable_vpid)) {
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
+ ept_sync_context(construct_eptp(vcpu,
+ vcpu->arch.mmu->root_hpa));
} else {
vpid_sync_context(vpid);
}
@@ -5276,7 +5285,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long hw_cr0;
- hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK);
+ hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF);
if (enable_unrestricted_guest)
hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
else {
@@ -5393,9 +5402,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
* To use VMXON (and later other VMX instructions), a guest
* must first be able to turn on cr4.VMXE (see handle_vmon()).
* So basically the check on whether to allow nested VMX
- * is here.
+ * is here. We operate under the default treatment of SMM,
+ * so VMX cannot be enabled under SMM.
*/
- if (!nested_vmx_allowed(vcpu))
+ if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
return 1;
}
@@ -6072,9 +6082,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
mode |= MSR_BITMAP_MODE_X2APIC_APICV;
}
- if (is_long_mode(vcpu))
- mode |= MSR_BITMAP_MODE_LM;
-
return mode;
}
@@ -6115,9 +6122,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
if (!changed)
return;
- vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
- !(mode & MSR_BITMAP_MODE_LM));
-
if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
@@ -6183,6 +6187,32 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
nested_mark_vmcs12_pages_dirty(vcpu);
}
+static u8 vmx_get_rvi(void)
+{
+ return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+}
+
+static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ void *vapic_page;
+ u32 vppr;
+ int rvi;
+
+ if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
+ !nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+ WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
+ return false;
+
+ rvi = vmx_get_rvi();
+
+ vapic_page = kmap(vmx->nested.virtual_apic_page);
+ vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
+ kunmap(vmx->nested.virtual_apic_page);
+
+ return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
bool nested)
{
@@ -6330,6 +6360,9 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
rdmsr(MSR_IA32_CR_PAT, low32, high32);
vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32));
}
+
+ if (cpu_has_load_ia32_efer)
+ vmcs_write64(HOST_IA32_EFER, host_efer);
}
static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
@@ -6657,7 +6690,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
if (enable_pml) {
- ASSERT(vmx->pml_pg);
vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
}
@@ -6983,7 +7015,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
* Cause the #SS fault with 0 error code in VM86 mode.
*/
if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
- if (emulate_instruction(vcpu, 0) == EMULATE_DONE) {
+ if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) {
if (vcpu->arch.halt_request) {
vcpu->arch.halt_request = 0;
return kvm_vcpu_halt(vcpu);
@@ -7054,7 +7086,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) {
WARN_ON_ONCE(!enable_vmware_backdoor);
- er = emulate_instruction(vcpu,
+ er = kvm_emulate_instruction(vcpu,
EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
if (er == EMULATE_USER_EXIT)
return 0;
@@ -7157,7 +7189,7 @@ static int handle_io(struct kvm_vcpu *vcpu)
++vcpu->stat.io_exits;
if (string)
- return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
port = exit_qualification >> 16;
size = (exit_qualification & 7) + 1;
@@ -7231,7 +7263,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
static int handle_desc(struct kvm_vcpu *vcpu)
{
WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
- return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
}
static int handle_cr(struct kvm_vcpu *vcpu)
@@ -7480,7 +7512,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu)
static int handle_invd(struct kvm_vcpu *vcpu)
{
- return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
}
static int handle_invlpg(struct kvm_vcpu *vcpu)
@@ -7547,7 +7579,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
return kvm_skip_emulated_instruction(vcpu);
}
}
- return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
}
static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
@@ -7704,8 +7736,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
return kvm_skip_emulated_instruction(vcpu);
else
- return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
- NULL, 0) == EMULATE_DONE;
+ return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) ==
+ EMULATE_DONE;
}
return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
@@ -7748,7 +7780,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
if (kvm_test_request(KVM_REQ_EVENT, vcpu))
return 1;
- err = emulate_instruction(vcpu, 0);
+ err = kvm_emulate_instruction(vcpu, 0);
if (err == EMULATE_USER_EXIT) {
++vcpu->stat.mmio_exits;
@@ -7966,6 +7998,9 @@ static __init int hardware_setup(void)
kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
}
+ if (!cpu_has_vmx_preemption_timer())
+ kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;
+
if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
u64 vmx_msr;
@@ -8055,35 +8090,39 @@ static int handle_monitor(struct kvm_vcpu *vcpu)
/*
* The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
+ * set the success or error code of an emulated VMX instruction (as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
+ * instruction.
*/
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
+static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
{
vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+ return kvm_skip_emulated_instruction(vcpu);
}
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
{
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
| X86_EFLAGS_CF);
+ return kvm_skip_emulated_instruction(vcpu);
}
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
- u32 vm_instruction_error)
+static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
+ u32 vm_instruction_error)
{
- if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
- /*
- * failValid writes the error number to the current VMCS, which
- * can't be done there isn't a current VMCS.
- */
- nested_vmx_failInvalid(vcpu);
- return;
- }
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * failValid writes the error number to the current VMCS, which
+ * can't be done if there isn't a current VMCS.
+ */
+ if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
+ return nested_vmx_failInvalid(vcpu);
+
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
@@ -8093,6 +8132,7 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
* We don't need to force a shadow sync because
* VM_INSTRUCTION_ERROR is not shadowed
*/
+ return kvm_skip_emulated_instruction(vcpu);
}
static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
@@ -8280,6 +8320,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
vmx->nested.vpid02 = allocate_vpid();
+ vmx->nested.vmcs02_initialized = false;
vmx->nested.vmxon = true;
return 0;
@@ -8333,10 +8374,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
return 1;
}
- if (vmx->nested.vmxon) {
- nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmx->nested.vmxon)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
!= VMXON_NEEDED_FEATURES) {
@@ -8355,21 +8395,17 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
* Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
* which replaces physical address width with 32
*/
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failInvalid(vcpu);
page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
- if (is_error_page(page)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (is_error_page(page))
+ return nested_vmx_failInvalid(vcpu);
+
if (*(u32 *)kmap(page) != VMCS12_REVISION) {
kunmap(page);
kvm_release_page_clean(page);
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_failInvalid(vcpu);
}
kunmap(page);
kvm_release_page_clean(page);
@@ -8379,8 +8415,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
if (ret)
return ret;
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/*
@@ -8411,8 +8446,24 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
vmcs_write64(VMCS_LINK_POINTER, -1ull);
}
-static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
+static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!vmx->nested.hv_evmcs)
+ return;
+
+ kunmap(vmx->nested.hv_evmcs_page);
+ kvm_release_page_dirty(vmx->nested.hv_evmcs_page);
+ vmx->nested.hv_evmcs_vmptr = -1ull;
+ vmx->nested.hv_evmcs_page = NULL;
+ vmx->nested.hv_evmcs = NULL;
+}
+
+static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (vmx->nested.current_vmptr == -1ull)
return;
@@ -8420,16 +8471,18 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
/* copy to memory all shadowed fields in case
they were modified */
copy_shadow_to_vmcs12(vmx);
- vmx->nested.sync_shadow_vmcs = false;
+ vmx->nested.need_vmcs12_sync = false;
vmx_disable_shadow_vmcs(vmx);
}
vmx->nested.posted_intr_nv = -1;
/* Flush VMCS12 to guest memory */
- kvm_vcpu_write_guest_page(&vmx->vcpu,
+ kvm_vcpu_write_guest_page(vcpu,
vmx->nested.current_vmptr >> PAGE_SHIFT,
vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
vmx->nested.current_vmptr = -1ull;
}
@@ -8437,8 +8490,10 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
* Free whatever needs to be freed from vmx->nested when L1 goes down, or
* just stops using VMX.
*/
-static void free_nested(struct vcpu_vmx *vmx)
+static void free_nested(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
@@ -8471,6 +8526,10 @@ static void free_nested(struct vcpu_vmx *vmx)
vmx->nested.pi_desc = NULL;
}
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
+ nested_release_evmcs(vcpu);
+
free_loaded_vmcs(&vmx->nested.vmcs02);
}
@@ -8479,9 +8538,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
{
if (!nested_vmx_check_permission(vcpu))
return 1;
- free_nested(to_vmx(vcpu));
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ free_nested(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the VMCLEAR instruction */
@@ -8497,25 +8555,28 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMCLEAR_INVALID_ADDRESS);
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmptr == vmx->nested.vmxon_ptr)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMCLEAR_VMXON_POINTER);
- if (vmptr == vmx->nested.current_vmptr)
- nested_release_vmcs12(vmx);
+ if (vmx->nested.hv_evmcs_page) {
+ if (vmptr == vmx->nested.hv_evmcs_vmptr)
+ nested_release_evmcs(vcpu);
+ } else {
+ if (vmptr == vmx->nested.current_vmptr)
+ nested_release_vmcs12(vcpu);
- kvm_vcpu_write_guest(vcpu,
- vmptr + offsetof(struct vmcs12, launch_state),
- &zero, sizeof(zero));
+ kvm_vcpu_write_guest(vcpu,
+ vmptr + offsetof(struct vmcs12,
+ launch_state),
+ &zero, sizeof(zero));
+ }
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
@@ -8598,6 +8659,395 @@ static inline int vmcs12_write_any(struct vmcs12 *vmcs12,
}
+static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
+{
+ struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
+ struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+ vmcs12->hdr.revision_id = evmcs->revision_id;
+
+ /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
+ vmcs12->tpr_threshold = evmcs->tpr_threshold;
+ vmcs12->guest_rip = evmcs->guest_rip;
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
+ vmcs12->guest_rsp = evmcs->guest_rsp;
+ vmcs12->guest_rflags = evmcs->guest_rflags;
+ vmcs12->guest_interruptibility_info =
+ evmcs->guest_interruptibility_info;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
+ vmcs12->cpu_based_vm_exec_control =
+ evmcs->cpu_based_vm_exec_control;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
+ vmcs12->exception_bitmap = evmcs->exception_bitmap;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) {
+ vmcs12->vm_entry_controls = evmcs->vm_entry_controls;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) {
+ vmcs12->vm_entry_intr_info_field =
+ evmcs->vm_entry_intr_info_field;
+ vmcs12->vm_entry_exception_error_code =
+ evmcs->vm_entry_exception_error_code;
+ vmcs12->vm_entry_instruction_len =
+ evmcs->vm_entry_instruction_len;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
+ vmcs12->host_ia32_pat = evmcs->host_ia32_pat;
+ vmcs12->host_ia32_efer = evmcs->host_ia32_efer;
+ vmcs12->host_cr0 = evmcs->host_cr0;
+ vmcs12->host_cr3 = evmcs->host_cr3;
+ vmcs12->host_cr4 = evmcs->host_cr4;
+ vmcs12->host_ia32_sysenter_esp = evmcs->host_ia32_sysenter_esp;
+ vmcs12->host_ia32_sysenter_eip = evmcs->host_ia32_sysenter_eip;
+ vmcs12->host_rip = evmcs->host_rip;
+ vmcs12->host_ia32_sysenter_cs = evmcs->host_ia32_sysenter_cs;
+ vmcs12->host_es_selector = evmcs->host_es_selector;
+ vmcs12->host_cs_selector = evmcs->host_cs_selector;
+ vmcs12->host_ss_selector = evmcs->host_ss_selector;
+ vmcs12->host_ds_selector = evmcs->host_ds_selector;
+ vmcs12->host_fs_selector = evmcs->host_fs_selector;
+ vmcs12->host_gs_selector = evmcs->host_gs_selector;
+ vmcs12->host_tr_selector = evmcs->host_tr_selector;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
+ vmcs12->pin_based_vm_exec_control =
+ evmcs->pin_based_vm_exec_control;
+ vmcs12->vm_exit_controls = evmcs->vm_exit_controls;
+ vmcs12->secondary_vm_exec_control =
+ evmcs->secondary_vm_exec_control;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) {
+ vmcs12->io_bitmap_a = evmcs->io_bitmap_a;
+ vmcs12->io_bitmap_b = evmcs->io_bitmap_b;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) {
+ vmcs12->msr_bitmap = evmcs->msr_bitmap;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) {
+ vmcs12->guest_es_base = evmcs->guest_es_base;
+ vmcs12->guest_cs_base = evmcs->guest_cs_base;
+ vmcs12->guest_ss_base = evmcs->guest_ss_base;
+ vmcs12->guest_ds_base = evmcs->guest_ds_base;
+ vmcs12->guest_fs_base = evmcs->guest_fs_base;
+ vmcs12->guest_gs_base = evmcs->guest_gs_base;
+ vmcs12->guest_ldtr_base = evmcs->guest_ldtr_base;
+ vmcs12->guest_tr_base = evmcs->guest_tr_base;
+ vmcs12->guest_gdtr_base = evmcs->guest_gdtr_base;
+ vmcs12->guest_idtr_base = evmcs->guest_idtr_base;
+ vmcs12->guest_es_limit = evmcs->guest_es_limit;
+ vmcs12->guest_cs_limit = evmcs->guest_cs_limit;
+ vmcs12->guest_ss_limit = evmcs->guest_ss_limit;
+ vmcs12->guest_ds_limit = evmcs->guest_ds_limit;
+ vmcs12->guest_fs_limit = evmcs->guest_fs_limit;
+ vmcs12->guest_gs_limit = evmcs->guest_gs_limit;
+ vmcs12->guest_ldtr_limit = evmcs->guest_ldtr_limit;
+ vmcs12->guest_tr_limit = evmcs->guest_tr_limit;
+ vmcs12->guest_gdtr_limit = evmcs->guest_gdtr_limit;
+ vmcs12->guest_idtr_limit = evmcs->guest_idtr_limit;
+ vmcs12->guest_es_ar_bytes = evmcs->guest_es_ar_bytes;
+ vmcs12->guest_cs_ar_bytes = evmcs->guest_cs_ar_bytes;
+ vmcs12->guest_ss_ar_bytes = evmcs->guest_ss_ar_bytes;
+ vmcs12->guest_ds_ar_bytes = evmcs->guest_ds_ar_bytes;
+ vmcs12->guest_fs_ar_bytes = evmcs->guest_fs_ar_bytes;
+ vmcs12->guest_gs_ar_bytes = evmcs->guest_gs_ar_bytes;
+ vmcs12->guest_ldtr_ar_bytes = evmcs->guest_ldtr_ar_bytes;
+ vmcs12->guest_tr_ar_bytes = evmcs->guest_tr_ar_bytes;
+ vmcs12->guest_es_selector = evmcs->guest_es_selector;
+ vmcs12->guest_cs_selector = evmcs->guest_cs_selector;
+ vmcs12->guest_ss_selector = evmcs->guest_ss_selector;
+ vmcs12->guest_ds_selector = evmcs->guest_ds_selector;
+ vmcs12->guest_fs_selector = evmcs->guest_fs_selector;
+ vmcs12->guest_gs_selector = evmcs->guest_gs_selector;
+ vmcs12->guest_ldtr_selector = evmcs->guest_ldtr_selector;
+ vmcs12->guest_tr_selector = evmcs->guest_tr_selector;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) {
+ vmcs12->tsc_offset = evmcs->tsc_offset;
+ vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
+ vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) {
+ vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask;
+ vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask;
+ vmcs12->cr0_read_shadow = evmcs->cr0_read_shadow;
+ vmcs12->cr4_read_shadow = evmcs->cr4_read_shadow;
+ vmcs12->guest_cr0 = evmcs->guest_cr0;
+ vmcs12->guest_cr3 = evmcs->guest_cr3;
+ vmcs12->guest_cr4 = evmcs->guest_cr4;
+ vmcs12->guest_dr7 = evmcs->guest_dr7;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) {
+ vmcs12->host_fs_base = evmcs->host_fs_base;
+ vmcs12->host_gs_base = evmcs->host_gs_base;
+ vmcs12->host_tr_base = evmcs->host_tr_base;
+ vmcs12->host_gdtr_base = evmcs->host_gdtr_base;
+ vmcs12->host_idtr_base = evmcs->host_idtr_base;
+ vmcs12->host_rsp = evmcs->host_rsp;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) {
+ vmcs12->ept_pointer = evmcs->ept_pointer;
+ vmcs12->virtual_processor_id = evmcs->virtual_processor_id;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) {
+ vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer;
+ vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl;
+ vmcs12->guest_ia32_pat = evmcs->guest_ia32_pat;
+ vmcs12->guest_ia32_efer = evmcs->guest_ia32_efer;
+ vmcs12->guest_pdptr0 = evmcs->guest_pdptr0;
+ vmcs12->guest_pdptr1 = evmcs->guest_pdptr1;
+ vmcs12->guest_pdptr2 = evmcs->guest_pdptr2;
+ vmcs12->guest_pdptr3 = evmcs->guest_pdptr3;
+ vmcs12->guest_pending_dbg_exceptions =
+ evmcs->guest_pending_dbg_exceptions;
+ vmcs12->guest_sysenter_esp = evmcs->guest_sysenter_esp;
+ vmcs12->guest_sysenter_eip = evmcs->guest_sysenter_eip;
+ vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs;
+ vmcs12->guest_activity_state = evmcs->guest_activity_state;
+ vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs;
+ }
+
+ /*
+ * Not used?
+ * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr;
+ * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr;
+ * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr;
+ * vmcs12->cr3_target_value0 = evmcs->cr3_target_value0;
+ * vmcs12->cr3_target_value1 = evmcs->cr3_target_value1;
+ * vmcs12->cr3_target_value2 = evmcs->cr3_target_value2;
+ * vmcs12->cr3_target_value3 = evmcs->cr3_target_value3;
+ * vmcs12->page_fault_error_code_mask =
+ * evmcs->page_fault_error_code_mask;
+ * vmcs12->page_fault_error_code_match =
+ * evmcs->page_fault_error_code_match;
+ * vmcs12->cr3_target_count = evmcs->cr3_target_count;
+ * vmcs12->vm_exit_msr_store_count = evmcs->vm_exit_msr_store_count;
+ * vmcs12->vm_exit_msr_load_count = evmcs->vm_exit_msr_load_count;
+ * vmcs12->vm_entry_msr_load_count = evmcs->vm_entry_msr_load_count;
+ */
+
+ /*
+ * Read only fields:
+ * vmcs12->guest_physical_address = evmcs->guest_physical_address;
+ * vmcs12->vm_instruction_error = evmcs->vm_instruction_error;
+ * vmcs12->vm_exit_reason = evmcs->vm_exit_reason;
+ * vmcs12->vm_exit_intr_info = evmcs->vm_exit_intr_info;
+ * vmcs12->vm_exit_intr_error_code = evmcs->vm_exit_intr_error_code;
+ * vmcs12->idt_vectoring_info_field = evmcs->idt_vectoring_info_field;
+ * vmcs12->idt_vectoring_error_code = evmcs->idt_vectoring_error_code;
+ * vmcs12->vm_exit_instruction_len = evmcs->vm_exit_instruction_len;
+ * vmcs12->vmx_instruction_info = evmcs->vmx_instruction_info;
+ * vmcs12->exit_qualification = evmcs->exit_qualification;
+ * vmcs12->guest_linear_address = evmcs->guest_linear_address;
+ *
+ * Not present in struct vmcs12:
+ * vmcs12->exit_io_instruction_ecx = evmcs->exit_io_instruction_ecx;
+ * vmcs12->exit_io_instruction_esi = evmcs->exit_io_instruction_esi;
+ * vmcs12->exit_io_instruction_edi = evmcs->exit_io_instruction_edi;
+ * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip;
+ */
+
+ return 0;
+}
+
+static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
+{
+ struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
+ struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+ /*
+ * Should not be changed by KVM:
+ *
+ * evmcs->host_es_selector = vmcs12->host_es_selector;
+ * evmcs->host_cs_selector = vmcs12->host_cs_selector;
+ * evmcs->host_ss_selector = vmcs12->host_ss_selector;
+ * evmcs->host_ds_selector = vmcs12->host_ds_selector;
+ * evmcs->host_fs_selector = vmcs12->host_fs_selector;
+ * evmcs->host_gs_selector = vmcs12->host_gs_selector;
+ * evmcs->host_tr_selector = vmcs12->host_tr_selector;
+ * evmcs->host_ia32_pat = vmcs12->host_ia32_pat;
+ * evmcs->host_ia32_efer = vmcs12->host_ia32_efer;
+ * evmcs->host_cr0 = vmcs12->host_cr0;
+ * evmcs->host_cr3 = vmcs12->host_cr3;
+ * evmcs->host_cr4 = vmcs12->host_cr4;
+ * evmcs->host_ia32_sysenter_esp = vmcs12->host_ia32_sysenter_esp;
+ * evmcs->host_ia32_sysenter_eip = vmcs12->host_ia32_sysenter_eip;
+ * evmcs->host_rip = vmcs12->host_rip;
+ * evmcs->host_ia32_sysenter_cs = vmcs12->host_ia32_sysenter_cs;
+ * evmcs->host_fs_base = vmcs12->host_fs_base;
+ * evmcs->host_gs_base = vmcs12->host_gs_base;
+ * evmcs->host_tr_base = vmcs12->host_tr_base;
+ * evmcs->host_gdtr_base = vmcs12->host_gdtr_base;
+ * evmcs->host_idtr_base = vmcs12->host_idtr_base;
+ * evmcs->host_rsp = vmcs12->host_rsp;
+ * sync_vmcs12() doesn't read these:
+ * evmcs->io_bitmap_a = vmcs12->io_bitmap_a;
+ * evmcs->io_bitmap_b = vmcs12->io_bitmap_b;
+ * evmcs->msr_bitmap = vmcs12->msr_bitmap;
+ * evmcs->ept_pointer = vmcs12->ept_pointer;
+ * evmcs->xss_exit_bitmap = vmcs12->xss_exit_bitmap;
+ * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr;
+ * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr;
+ * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr;
+ * evmcs->cr3_target_value0 = vmcs12->cr3_target_value0;
+ * evmcs->cr3_target_value1 = vmcs12->cr3_target_value1;
+ * evmcs->cr3_target_value2 = vmcs12->cr3_target_value2;
+ * evmcs->cr3_target_value3 = vmcs12->cr3_target_value3;
+ * evmcs->tpr_threshold = vmcs12->tpr_threshold;
+ * evmcs->virtual_processor_id = vmcs12->virtual_processor_id;
+ * evmcs->exception_bitmap = vmcs12->exception_bitmap;
+ * evmcs->vmcs_link_pointer = vmcs12->vmcs_link_pointer;
+ * evmcs->pin_based_vm_exec_control = vmcs12->pin_based_vm_exec_control;
+ * evmcs->vm_exit_controls = vmcs12->vm_exit_controls;
+ * evmcs->secondary_vm_exec_control = vmcs12->secondary_vm_exec_control;
+ * evmcs->page_fault_error_code_mask =
+ * vmcs12->page_fault_error_code_mask;
+ * evmcs->page_fault_error_code_match =
+ * vmcs12->page_fault_error_code_match;
+ * evmcs->cr3_target_count = vmcs12->cr3_target_count;
+ * evmcs->virtual_apic_page_addr = vmcs12->virtual_apic_page_addr;
+ * evmcs->tsc_offset = vmcs12->tsc_offset;
+ * evmcs->guest_ia32_debugctl = vmcs12->guest_ia32_debugctl;
+ * evmcs->cr0_guest_host_mask = vmcs12->cr0_guest_host_mask;
+ * evmcs->cr4_guest_host_mask = vmcs12->cr4_guest_host_mask;
+ * evmcs->cr0_read_shadow = vmcs12->cr0_read_shadow;
+ * evmcs->cr4_read_shadow = vmcs12->cr4_read_shadow;
+ * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count;
+ * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count;
+ * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count;
+ *
+ * Not present in struct vmcs12:
+ * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx;
+ * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi;
+ * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi;
+ * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip;
+ */
+
+ evmcs->guest_es_selector = vmcs12->guest_es_selector;
+ evmcs->guest_cs_selector = vmcs12->guest_cs_selector;
+ evmcs->guest_ss_selector = vmcs12->guest_ss_selector;
+ evmcs->guest_ds_selector = vmcs12->guest_ds_selector;
+ evmcs->guest_fs_selector = vmcs12->guest_fs_selector;
+ evmcs->guest_gs_selector = vmcs12->guest_gs_selector;
+ evmcs->guest_ldtr_selector = vmcs12->guest_ldtr_selector;
+ evmcs->guest_tr_selector = vmcs12->guest_tr_selector;
+
+ evmcs->guest_es_limit = vmcs12->guest_es_limit;
+ evmcs->guest_cs_limit = vmcs12->guest_cs_limit;
+ evmcs->guest_ss_limit = vmcs12->guest_ss_limit;
+ evmcs->guest_ds_limit = vmcs12->guest_ds_limit;
+ evmcs->guest_fs_limit = vmcs12->guest_fs_limit;
+ evmcs->guest_gs_limit = vmcs12->guest_gs_limit;
+ evmcs->guest_ldtr_limit = vmcs12->guest_ldtr_limit;
+ evmcs->guest_tr_limit = vmcs12->guest_tr_limit;
+ evmcs->guest_gdtr_limit = vmcs12->guest_gdtr_limit;
+ evmcs->guest_idtr_limit = vmcs12->guest_idtr_limit;
+
+ evmcs->guest_es_ar_bytes = vmcs12->guest_es_ar_bytes;
+ evmcs->guest_cs_ar_bytes = vmcs12->guest_cs_ar_bytes;
+ evmcs->guest_ss_ar_bytes = vmcs12->guest_ss_ar_bytes;
+ evmcs->guest_ds_ar_bytes = vmcs12->guest_ds_ar_bytes;
+ evmcs->guest_fs_ar_bytes = vmcs12->guest_fs_ar_bytes;
+ evmcs->guest_gs_ar_bytes = vmcs12->guest_gs_ar_bytes;
+ evmcs->guest_ldtr_ar_bytes = vmcs12->guest_ldtr_ar_bytes;
+ evmcs->guest_tr_ar_bytes = vmcs12->guest_tr_ar_bytes;
+
+ evmcs->guest_es_base = vmcs12->guest_es_base;
+ evmcs->guest_cs_base = vmcs12->guest_cs_base;
+ evmcs->guest_ss_base = vmcs12->guest_ss_base;
+ evmcs->guest_ds_base = vmcs12->guest_ds_base;
+ evmcs->guest_fs_base = vmcs12->guest_fs_base;
+ evmcs->guest_gs_base = vmcs12->guest_gs_base;
+ evmcs->guest_ldtr_base = vmcs12->guest_ldtr_base;
+ evmcs->guest_tr_base = vmcs12->guest_tr_base;
+ evmcs->guest_gdtr_base = vmcs12->guest_gdtr_base;
+ evmcs->guest_idtr_base = vmcs12->guest_idtr_base;
+
+ evmcs->guest_ia32_pat = vmcs12->guest_ia32_pat;
+ evmcs->guest_ia32_efer = vmcs12->guest_ia32_efer;
+
+ evmcs->guest_pdptr0 = vmcs12->guest_pdptr0;
+ evmcs->guest_pdptr1 = vmcs12->guest_pdptr1;
+ evmcs->guest_pdptr2 = vmcs12->guest_pdptr2;
+ evmcs->guest_pdptr3 = vmcs12->guest_pdptr3;
+
+ evmcs->guest_pending_dbg_exceptions =
+ vmcs12->guest_pending_dbg_exceptions;
+ evmcs->guest_sysenter_esp = vmcs12->guest_sysenter_esp;
+ evmcs->guest_sysenter_eip = vmcs12->guest_sysenter_eip;
+
+ evmcs->guest_activity_state = vmcs12->guest_activity_state;
+ evmcs->guest_sysenter_cs = vmcs12->guest_sysenter_cs;
+
+ evmcs->guest_cr0 = vmcs12->guest_cr0;
+ evmcs->guest_cr3 = vmcs12->guest_cr3;
+ evmcs->guest_cr4 = vmcs12->guest_cr4;
+ evmcs->guest_dr7 = vmcs12->guest_dr7;
+
+ evmcs->guest_physical_address = vmcs12->guest_physical_address;
+
+ evmcs->vm_instruction_error = vmcs12->vm_instruction_error;
+ evmcs->vm_exit_reason = vmcs12->vm_exit_reason;
+ evmcs->vm_exit_intr_info = vmcs12->vm_exit_intr_info;
+ evmcs->vm_exit_intr_error_code = vmcs12->vm_exit_intr_error_code;
+ evmcs->idt_vectoring_info_field = vmcs12->idt_vectoring_info_field;
+ evmcs->idt_vectoring_error_code = vmcs12->idt_vectoring_error_code;
+ evmcs->vm_exit_instruction_len = vmcs12->vm_exit_instruction_len;
+ evmcs->vmx_instruction_info = vmcs12->vmx_instruction_info;
+
+ evmcs->exit_qualification = vmcs12->exit_qualification;
+
+ evmcs->guest_linear_address = vmcs12->guest_linear_address;
+ evmcs->guest_rsp = vmcs12->guest_rsp;
+ evmcs->guest_rflags = vmcs12->guest_rflags;
+
+ evmcs->guest_interruptibility_info =
+ vmcs12->guest_interruptibility_info;
+ evmcs->cpu_based_vm_exec_control = vmcs12->cpu_based_vm_exec_control;
+ evmcs->vm_entry_controls = vmcs12->vm_entry_controls;
+ evmcs->vm_entry_intr_info_field = vmcs12->vm_entry_intr_info_field;
+ evmcs->vm_entry_exception_error_code =
+ vmcs12->vm_entry_exception_error_code;
+ evmcs->vm_entry_instruction_len = vmcs12->vm_entry_instruction_len;
+
+ evmcs->guest_rip = vmcs12->guest_rip;
+
+ evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;
+
+ return 0;
+}
+
/*
* Copy the writable VMCS shadow fields back to the VMCS12, in case
* they have been modified by the L1 guest. Note that the "read-only"
@@ -8671,20 +9121,6 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
vmcs_load(vmx->loaded_vmcs->vmcs);
}
-/*
- * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was
- * used before) all generate the same failure when it is missing.
- */
-static int nested_vmx_check_vmcs12(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (vmx->nested.current_vmptr == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return 0;
- }
- return 1;
-}
-
static int handle_vmread(struct kvm_vcpu *vcpu)
{
unsigned long field;
@@ -8697,8 +9133,8 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- return kvm_skip_emulated_instruction(vcpu);
+ if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
if (!is_guest_mode(vcpu))
vmcs12 = get_vmcs12(vcpu);
@@ -8707,20 +9143,18 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
* When vmcs->vmcs_link_pointer is -1ull, any VMREAD
* to shadowed-field sets the ALU flags for VMfailInvalid.
*/
- if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_shadow_vmcs12(vcpu);
}
/* Decode instruction info and find the field to read */
field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
/* Read the field, zero-extended to a u64 field_value */
- if (vmcs12_read_any(vmcs12, field, &field_value) < 0) {
- nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmcs12_read_any(vmcs12, field, &field_value) < 0)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
/*
* Now copy part of this value to register or memory, as requested.
* Note that the number of bits actually copied is 32 or 64 depending
@@ -8738,8 +9172,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
(is_long_mode(vcpu) ? 8 : 4), NULL);
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
@@ -8764,8 +9197,8 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- return kvm_skip_emulated_instruction(vcpu);
+ if (vmx->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
if (vmx_instruction_info & (1u << 10))
field_value = kvm_register_readl(vcpu,
@@ -8788,11 +9221,9 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
* VMCS," then the "read-only" fields are actually read/write.
*/
if (vmcs_field_readonly(field) &&
- !nested_cpu_has_vmwrite_any_field(vcpu)) {
- nested_vmx_failValid(vcpu,
+ !nested_cpu_has_vmwrite_any_field(vcpu))
+ return nested_vmx_failValid(vcpu,
VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
if (!is_guest_mode(vcpu))
vmcs12 = get_vmcs12(vcpu);
@@ -8801,18 +9232,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
* When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
* to shadowed-field sets the ALU flags for VMfailInvalid.
*/
- if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_shadow_vmcs12(vcpu);
-
}
- if (vmcs12_write_any(vmcs12, field, field_value) < 0) {
- nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmcs12_write_any(vmcs12, field, field_value) < 0)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_UNSUPPORTED_VMCS_COMPONENT);
/*
* Do not track vmcs12 dirty-state if in guest-mode
@@ -8834,8 +9261,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
}
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
@@ -8846,7 +9272,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
SECONDARY_EXEC_SHADOW_VMCS);
vmcs_write64(VMCS_LINK_POINTER,
__pa(vmx->vmcs01.shadow_vmcs));
- vmx->nested.sync_shadow_vmcs = true;
+ vmx->nested.need_vmcs12_sync = true;
}
vmx->nested.dirty_vmcs12 = true;
}
@@ -8863,36 +9289,37 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMPTRLD_INVALID_ADDRESS);
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmptr == vmx->nested.vmxon_ptr)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMPTRLD_VMXON_POINTER);
+
+ /* Forbid normal VMPTRLD if Enlightened version was used */
+ if (vmx->nested.hv_evmcs)
+ return 1;
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
- if (is_error_page(page)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (is_error_page(page))
+ return nested_vmx_failInvalid(vcpu);
+
new_vmcs12 = kmap(page);
if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
(new_vmcs12->hdr.shadow_vmcs &&
!nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
kunmap(page);
kvm_release_page_clean(page);
- nested_vmx_failValid(vcpu,
+ return nested_vmx_failValid(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
- return kvm_skip_emulated_instruction(vcpu);
}
- nested_release_vmcs12(vmx);
+ nested_release_vmcs12(vcpu);
+
/*
* Load VMCS12 from guest memory since it is not already
* cached.
@@ -8904,8 +9331,71 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
set_current_vmptr(vmx, vmptr);
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
+}
+
+/*
+ * This is an equivalent of the nested hypervisor executing the vmptrld
+ * instruction.
+ */
+static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
+ bool from_launch)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct hv_vp_assist_page assist_page;
+
+ if (likely(!vmx->nested.enlightened_vmcs_enabled))
+ return 1;
+
+ if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page)))
+ return 1;
+
+ if (unlikely(!assist_page.enlighten_vmentry))
+ return 1;
+
+ if (unlikely(assist_page.current_nested_vmcs !=
+ vmx->nested.hv_evmcs_vmptr)) {
+
+ if (!vmx->nested.hv_evmcs)
+ vmx->nested.current_vmptr = -1ull;
+
+ nested_release_evmcs(vcpu);
+
+ vmx->nested.hv_evmcs_page = kvm_vcpu_gpa_to_page(
+ vcpu, assist_page.current_nested_vmcs);
+
+ if (unlikely(is_error_page(vmx->nested.hv_evmcs_page)))
+ return 0;
+
+ vmx->nested.hv_evmcs = kmap(vmx->nested.hv_evmcs_page);
+
+ if (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION) {
+ nested_release_evmcs(vcpu);
+ return 0;
+ }
+
+ vmx->nested.dirty_vmcs12 = true;
+ /*
+ * As we keep L2 state for one guest only 'hv_clean_fields' mask
+ * can't be used when we switch between them. Reset it here for
+ * simplicity.
+ */
+ vmx->nested.hv_evmcs->hv_clean_fields &=
+ ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ vmx->nested.hv_evmcs_vmptr = assist_page.current_nested_vmcs;
+
+ /*
+ * Unlike normal vmcs12, enlightened vmcs12 is not fully
+ * reloaded from guest's memory (read only fields, fields not
+ * present in struct hv_enlightened_vmcs, ...). Make sure there
+ * are no leftovers.
+ */
+ if (from_launch)
+ memset(vmx->nested.cached_vmcs12, 0,
+ sizeof(*vmx->nested.cached_vmcs12));
+
+ }
+ return 1;
}
/* Emulate the VMPTRST instruction */
@@ -8920,6 +9410,9 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
+ if (unlikely(to_vmx(vcpu)->nested.hv_evmcs))
+ return 1;
+
if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
return 1;
/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
@@ -8928,8 +9421,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the INVEPT instruction */
@@ -8959,11 +9451,9 @@ static int handle_invept(struct kvm_vcpu *vcpu)
types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
- if (type >= 32 || !(types & (1 << type))) {
- nested_vmx_failValid(vcpu,
+ if (type >= 32 || !(types & (1 << type)))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
/* According to the Intel VMX instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
@@ -8985,14 +9475,20 @@ static int handle_invept(struct kvm_vcpu *vcpu)
case VMX_EPT_EXTENT_CONTEXT:
kvm_mmu_sync_roots(vcpu);
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- nested_vmx_succeed(vcpu);
break;
default:
BUG_ON(1);
break;
}
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
+}
+
+static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
}
static int handle_invvpid(struct kvm_vcpu *vcpu)
@@ -9006,6 +9502,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
u64 vpid;
u64 gla;
} operand;
+ u16 vpid02;
if (!(vmx->nested.msrs.secondary_ctls_high &
SECONDARY_EXEC_ENABLE_VPID) ||
@@ -9023,11 +9520,9 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
types = (vmx->nested.msrs.vpid_caps &
VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
- if (type >= 32 || !(types & (1 << type))) {
- nested_vmx_failValid(vcpu,
+ if (type >= 32 || !(types & (1 << type)))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
/* according to the intel vmx instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
@@ -9039,47 +9534,39 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- if (operand.vpid >> 16) {
- nested_vmx_failValid(vcpu,
+ if (operand.vpid >> 16)
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ vpid02 = nested_get_vpid02(vcpu);
switch (type) {
case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
if (!operand.vpid ||
- is_noncanonical_address(operand.gla, vcpu)) {
- nested_vmx_failValid(vcpu,
+ is_noncanonical_address(operand.gla, vcpu))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
- if (cpu_has_vmx_invvpid_individual_addr() &&
- vmx->nested.vpid02) {
+ if (cpu_has_vmx_invvpid_individual_addr()) {
__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
- vmx->nested.vpid02, operand.gla);
+ vpid02, operand.gla);
} else
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vpid02, false);
break;
case VMX_VPID_EXTENT_SINGLE_CONTEXT:
case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
- if (!operand.vpid) {
- nested_vmx_failValid(vcpu,
+ if (!operand.vpid)
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vpid02, false);
break;
case VMX_VPID_EXTENT_ALL_CONTEXT:
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vpid02, false);
break;
default:
WARN_ON_ONCE(1);
return kvm_skip_emulated_instruction(vcpu);
}
- nested_vmx_succeed(vcpu);
-
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static int handle_invpcid(struct kvm_vcpu *vcpu)
@@ -9150,11 +9637,11 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
}
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- if (kvm_get_pcid(vcpu, vcpu->arch.mmu.prev_roots[i].cr3)
+ if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3)
== operand.pcid)
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
- kvm_mmu_free_roots(vcpu, roots_to_free);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
/*
* If neither the current cr3 nor any of the prev_roots use the
* given PCID, then nothing needs to be done here because a
@@ -9208,7 +9695,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
static int handle_preemption_timer(struct kvm_vcpu *vcpu)
{
- kvm_lapic_expired_hv_timer(vcpu);
+ if (!to_vmx(vcpu)->req_immediate_exit)
+ kvm_lapic_expired_hv_timer(vcpu);
return 1;
}
@@ -9280,7 +9768,7 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
kvm_mmu_unload(vcpu);
mmu->ept_ad = accessed_dirty;
- mmu->base_role.ad_disabled = !accessed_dirty;
+ mmu->mmu_role.base.ad_disabled = !accessed_dirty;
vmcs12->ept_pointer = address;
/*
* TODO: Check what's the correct approach in case
@@ -9639,9 +10127,6 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
return false;
else if (is_page_fault(intr_info))
return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
- else if (is_no_device(intr_info) &&
- !(vmcs12->guest_cr0 & X86_CR0_TS))
- return false;
else if (is_debug(intr_info) &&
vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
@@ -10214,15 +10699,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
if (!lapic_in_kernel(vcpu))
return;
+ if (!flexpriority_enabled &&
+ !cpu_has_vmx_virtualize_x2apic_mode())
+ return;
+
/* Postpone execution until vmcs01 is the current VMCS. */
if (is_guest_mode(vcpu)) {
to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
return;
}
- if (!cpu_need_tpr_shadow(vcpu))
- return;
-
sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -10344,6 +10830,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
return max_irr;
}
+static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
+{
+ u8 rvi = vmx_get_rvi();
+ u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);
+
+ return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
{
if (!kvm_vcpu_apicv_active(vcpu))
@@ -10595,24 +11089,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
msrs[i].host, false);
}
-static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
+{
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
+ if (!vmx->loaded_vmcs->hv_timer_armed)
+ vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ vmx->loaded_vmcs->hv_timer_armed = true;
+}
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 tscl;
u32 delta_tsc;
- if (vmx->hv_deadline_tsc == -1)
+ if (vmx->req_immediate_exit) {
+ vmx_arm_hv_timer(vmx, 0);
return;
+ }
- tscl = rdtsc();
- if (vmx->hv_deadline_tsc > tscl)
- /* sure to be 32 bit only because checked on set_hv_timer */
- delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
- cpu_preemption_timer_multi);
- else
- delta_tsc = 0;
+ if (vmx->hv_deadline_tsc != -1) {
+ tscl = rdtsc();
+ if (vmx->hv_deadline_tsc > tscl)
+ /* set_hv_timer ensures the delta fits in 32-bits */
+ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+ cpu_preemption_timer_multi);
+ else
+ delta_tsc = 0;
- vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+ vmx_arm_hv_timer(vmx, delta_tsc);
+ return;
+ }
+
+ if (vmx->loaded_vmcs->hv_timer_armed)
+ vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ vmx->loaded_vmcs->hv_timer_armed = false;
}
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
@@ -10635,9 +11148,25 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmcs_write32(PLE_WINDOW, vmx->ple_window);
}
- if (vmx->nested.sync_shadow_vmcs) {
- copy_vmcs12_to_shadow(vmx);
- vmx->nested.sync_shadow_vmcs = false;
+ if (vmx->nested.need_vmcs12_sync) {
+ /*
+ * hv_evmcs may end up being not mapped after migration (when
+ * L2 was running), map it here to make sure vmcs12 changes are
+ * properly reflected.
+ */
+ if (vmx->nested.enlightened_vmcs_enabled &&
+ !vmx->nested.hv_evmcs)
+ nested_vmx_handle_enlightened_vmptrld(vcpu, false);
+
+ if (vmx->nested.hv_evmcs) {
+ copy_vmcs12_to_enlightened(vmx);
+ /* All fields are clean */
+ vmx->nested.hv_evmcs->hv_clean_fields |=
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ } else {
+ copy_vmcs12_to_shadow(vmx);
+ }
+ vmx->nested.need_vmcs12_sync = false;
}
if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
@@ -10672,7 +11201,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
atomic_switch_perf_msrs(vmx);
- vmx_arm_hv_timer(vcpu);
+ vmx_update_hv_timer(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -10704,7 +11233,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%" _ASM_SP ", (%%" _ASM_SI ") \n\t"
"jmp 1f \n\t"
"2: \n\t"
- __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
+ __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t"
"1: \n\t"
/* Reload cr2 if changed */
"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
@@ -10736,9 +11265,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
/* Enter guest mode */
"jne 1f \n\t"
- __ex(ASM_VMX_VMLAUNCH) "\n\t"
+ __ex("vmlaunch") "\n\t"
"jmp 2f \n\t"
- "1: " __ex(ASM_VMX_VMRESUME) "\n\t"
+ "1: " __ex("vmresume") "\n\t"
"2: "
/* Save guest registers, load host registers, keep flags */
"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
@@ -10760,6 +11289,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r13, %c[r13](%0) \n\t"
"mov %%r14, %c[r14](%0) \n\t"
"mov %%r15, %c[r15](%0) \n\t"
+ /*
+ * Clear host registers marked as clobbered to prevent
+ * speculative use.
+ */
"xor %%r8d, %%r8d \n\t"
"xor %%r9d, %%r9d \n\t"
"xor %%r10d, %%r10d \n\t"
@@ -10917,6 +11450,10 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
vmx->loaded_vmcs = vmcs;
vmx_vcpu_load(vcpu, cpu);
put_cpu();
+
+ vm_entry_controls_reset_shadow(vmx);
+ vm_exit_controls_reset_shadow(vmx);
+ vmx_segment_cache_clear(vmx);
}
/*
@@ -10925,12 +11462,10 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
*/
static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- vcpu_load(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- free_nested(vmx);
- vcpu_put(vcpu);
+ vcpu_load(vcpu);
+ vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
+ free_nested(vcpu);
+ vcpu_put(vcpu);
}
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
@@ -11214,6 +11749,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
#undef cr4_fixed1_update
}
+static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (kvm_mpx_supported()) {
+ bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);
+
+ if (mpx_enabled) {
+ vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
+ vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
+ } else {
+ vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
+ vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
+ }
+ }
+}
+
static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -11230,8 +11782,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
- if (nested_vmx_allowed(vcpu))
+ if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
+ nested_vmx_entry_exit_ctls_update(vcpu);
+ }
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -11274,28 +11828,28 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
return get_vmcs12(vcpu)->ept_pointer;
}
-static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
{
WARN_ON(mmu_is_nested(vcpu));
- if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu)))
- return 1;
+ vcpu->arch.mmu = &vcpu->arch.guest_mmu;
kvm_init_shadow_ept_mmu(vcpu,
to_vmx(vcpu)->nested.msrs.ept_caps &
VMX_EPT_EXECUTE_ONLY_BIT,
nested_ept_ad_enabled(vcpu),
nested_ept_get_cr3(vcpu));
- vcpu->arch.mmu.set_cr3 = vmx_set_cr3;
- vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3;
- vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->set_cr3 = vmx_set_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3;
+ vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->get_pdptr = kvm_pdptr_read;
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
- return 0;
}
static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
@@ -11427,16 +11981,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (vcpu->arch.virtual_tsc_khz == 0)
- return;
-
- /* Make sure short timeouts reliably trigger an immediate vmexit.
- * hrtimer_start does not guarantee this. */
- if (preemption_timeout <= 1) {
+ /*
+ * A timer value of zero is architecturally guaranteed to cause
+ * a VMExit prior to executing any instructions in the guest.
+ */
+ if (preemption_timeout == 0) {
vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
return;
}
+ if (vcpu->arch.virtual_tsc_khz == 0)
+ return;
+
preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
preemption_timeout *= 1000000;
do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
@@ -11646,11 +12202,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
* bits 15:8 should be zero in posted_intr_nv,
* the descriptor address has been already checked
* in nested_get_vmcs12_pages.
+ *
+ * bits 5:0 of posted_intr_desc_addr should be zero.
*/
if (nested_cpu_has_posted_intr(vmcs12) &&
(!nested_cpu_has_vid(vmcs12) ||
!nested_exit_intr_ack_set(vcpu) ||
- vmcs12->posted_intr_nv & 0xff00))
+ (vmcs12->posted_intr_nv & 0xff00) ||
+ (vmcs12->posted_intr_desc_addr & 0x3f) ||
+ (vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))
return -EINVAL;
/* tpr shadow is needed by all apicv features. */
@@ -11706,15 +12266,12 @@ static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- u64 address = vmcs12->pml_address;
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
+ if (!nested_cpu_has_pml(vmcs12))
+ return 0;
- if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
- if (!nested_cpu_has_ept(vmcs12) ||
- !IS_ALIGNED(address, 4096) ||
- address >> maxphyaddr)
- return -EINVAL;
- }
+ if (!nested_cpu_has_ept(vmcs12) ||
+ !page_address_valid(vcpu, vmcs12->pml_address))
+ return -EINVAL;
return 0;
}
@@ -11894,107 +12451,87 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
return 0;
}
-static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+/*
+ * Returns if KVM is able to config CPU to tag TLB entries
+ * populated by L2 differently than TLB entries populated
+ * by L1.
+ *
+ * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ *
+ * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
+ * with different VPID (L1 entries are tagged with vmx->vpid
+ * while L2 entries are tagged with vmx->nested.vpid02).
+ */
+static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
- vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
- vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
- vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
- vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
- vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
- vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
- vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
- vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
- vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
- vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
- vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
- vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
- vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
- vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
- vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
- vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
- vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
- vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
- vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
- vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
- vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
- vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
- vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
- vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
- vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
- vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
- vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
- vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
- vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
- vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
-
- vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
- vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
- vmcs12->guest_pending_dbg_exceptions);
- vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
- vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+ return nested_cpu_has_ept(vmcs12) ||
+ (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
+}
- if (nested_cpu_has_xsaves(vmcs12))
- vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
- vmcs_write64(VMCS_LINK_POINTER, -1ull);
+static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
+ return vmcs12->guest_ia32_efer;
+ else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
+ return vmx->vcpu.arch.efer | (EFER_LMA | EFER_LME);
+ else
+ return vmx->vcpu.arch.efer & ~(EFER_LMA | EFER_LME);
+}
- if (cpu_has_vmx_posted_intr())
- vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
+static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
+{
+ /*
+ * If vmcs02 hasn't been initialized, set the constant vmcs02 state
+ * according to L0's settings (vmcs12 is irrelevant here). Host
+ * fields that come from L0 and are not constant, e.g. HOST_CR3,
+ * will be set as needed prior to VMLAUNCH/VMRESUME.
+ */
+ if (vmx->nested.vmcs02_initialized)
+ return;
+ vmx->nested.vmcs02_initialized = true;
/*
- * Whether page-faults are trapped is determined by a combination of
- * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
- * If enable_ept, L0 doesn't care about page faults and we should
- * set all of these to L1's desires. However, if !enable_ept, L0 does
- * care about (at least some) page faults, and because it is not easy
- * (if at all possible?) to merge L0 and L1's desires, we simply ask
- * to exit on each and every L2 page fault. This is done by setting
- * MASK=MATCH=0 and (see below) EB.PF=1.
- * Note that below we don't need special code to set EB.PF beyond the
- * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
- * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
- * !enable_ept, EB.PF is 1, so the "or" will always be 1.
+ * We don't care what the EPTP value is we just need to guarantee
+ * it's valid so we don't get a false positive when doing early
+ * consistency checks.
*/
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
- enable_ept ? vmcs12->page_fault_error_code_mask : 0);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
- enable_ept ? vmcs12->page_fault_error_code_match : 0);
+ if (enable_ept && nested_early_check)
+ vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));
/* All VMFUNCs are currently emulated through L0 vmexits. */
if (cpu_has_vmx_vmfunc())
vmcs_write64(VM_FUNCTION_CONTROL, 0);
- if (cpu_has_vmx_apicv()) {
- vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
- vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
- vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
- vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
- }
+ if (cpu_has_vmx_posted_intr())
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
- /*
- * Set host-state according to L0's settings (vmcs12 is irrelevant here)
- * Some constant fields are set here by vmx_set_constant_host_state().
- * Other fields are different per CPU, and will be set later when
- * vmx_vcpu_load() is called, and when vmx_prepare_switch_to_guest()
- * is called.
- */
- vmx_set_constant_host_state(vmx);
+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
+ if (enable_pml)
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
/*
- * Set the MSR load/store lists to match L0's settings.
+ * Set the MSR load/store lists to match L0's settings. Only the
+ * addresses are constant (for vmcs02), the counts can change based
+ * on L2's behavior, e.g. switching to/from long mode.
*/
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
- set_cr4_guest_host_mask(vmx);
+ vmx_set_constant_host_state(vmx);
+}
- if (vmx_mpx_supported())
- vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+static void prepare_vmcs02_early_full(struct vcpu_vmx *vmx,
+ struct vmcs12 *vmcs12)
+{
+ prepare_vmcs02_constant_state(vmx);
+
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
if (enable_vpid) {
if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
@@ -12002,85 +12539,36 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
else
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
}
-
- /*
- * L1 may access the L2's PDPTR, so save them to construct vmcs12
- */
- if (enable_ept) {
- vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
- vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
- vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
- vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
- }
-
- if (cpu_has_vmx_msr_bitmap())
- vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
}
-/*
- * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
- * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
- * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
- * guest in a way that will both be appropriate to L1's requests, and our
- * needs. In addition to modifying the active vmcs (which is vmcs02), this
- * function also has additional necessary side-effects, like setting various
- * vcpu->arch fields.
- * Returns 0 on success, 1 on failure. Invalid state exit qualification code
- * is assigned to entry_failure_code on failure.
- */
-static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- u32 *entry_failure_code)
+static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control, vmcs12_exec_ctrl;
+ u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);
- if (vmx->nested.dirty_vmcs12) {
- prepare_vmcs02_full(vcpu, vmcs12);
- vmx->nested.dirty_vmcs12 = false;
- }
+ if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs)
+ prepare_vmcs02_early_full(vmx, vmcs12);
/*
- * First, the fields that are shadowed. This must be kept in sync
- * with vmx_shadow_fields.h.
+ * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
+ * entry, but only if the current (host) sp changed from the value
+ * we wrote last (vmx->host_rsp). This cache is no longer relevant
+ * if we switch vmcs, and rather than hold a separate cache per vmcs,
+ * here we just force the write to happen on entry. host_rsp will
+ * also be written unconditionally by nested_vmx_check_vmentry_hw()
+ * if we are doing early consistency checks via hardware.
*/
+ vmx->host_rsp = 0;
- vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
- vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
- vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
- vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
- vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
-
- if (vmx->nested.nested_run_pending &&
- (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
- kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
- } else {
- kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
- }
- if (vmx->nested.nested_run_pending) {
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
- vmcs12->vm_entry_intr_info_field);
- vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
- vmcs12->vm_entry_exception_error_code);
- vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
- vmcs12->vm_entry_instruction_len);
- vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
- vmcs12->guest_interruptibility_info);
- vmx->loaded_vmcs->nmi_known_unmasked =
- !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
- } else {
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
- }
- vmx_set_rflags(vcpu, vmcs12->guest_rflags);
-
+ /*
+ * PIN CONTROLS
+ */
exec_control = vmcs12->pin_based_vm_exec_control;
- /* Preemption timer setting is only taken from vmcs01. */
- exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ /* Preemption timer setting is computed directly in vmx_vcpu_run. */
exec_control |= vmcs_config.pin_based_exec_ctrl;
- if (vmx->hv_deadline_tsc == -1)
- exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ vmx->loaded_vmcs->hv_timer_armed = false;
/* Posted interrupts setting is only taken from vmcs12. */
if (nested_cpu_has_posted_intr(vmcs12)) {
@@ -12089,13 +12577,43 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
} else {
exec_control &= ~PIN_BASED_POSTED_INTR;
}
-
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
- vmx->nested.preemption_timer_expired = false;
- if (nested_cpu_has_preemption_timer(vmcs12))
- vmx_start_preemption_timer(vcpu);
+ /*
+ * EXEC CONTROLS
+ */
+ exec_control = vmx_exec_control(vmx); /* L0's desires */
+ exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+ exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
+ exec_control &= ~CPU_BASED_TPR_SHADOW;
+ exec_control |= vmcs12->cpu_based_vm_exec_control;
+
+ /*
+ * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if
+ * nested_get_vmcs12_pages can't fix it up, the illegal value
+ * will result in a VM entry failure.
+ */
+ if (exec_control & CPU_BASED_TPR_SHADOW) {
+ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
+ vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ } else {
+#ifdef CONFIG_X86_64
+ exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+ CPU_BASED_CR8_STORE_EXITING;
+#endif
+ }
+ /*
+ * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
+ * for I/O port accesses.
+ */
+ exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
+ exec_control |= CPU_BASED_UNCOND_IO_EXITING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
+
+ /*
+ * SECONDARY EXEC CONTROLS
+ */
if (cpu_has_secondary_exec_ctrls()) {
exec_control = vmx->secondary_exec_control;
@@ -12136,43 +12654,214 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
}
/*
- * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
- * entry, but only if the current (host) sp changed from the value
- * we wrote last (vmx->host_rsp). This cache is no longer relevant
- * if we switch vmcs, and rather than hold a separate cache per vmcs,
- * here we just force the write to happen on entry.
+ * ENTRY CONTROLS
+ *
+ * vmcs12's VM_{ENTRY,EXIT}_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE
+ * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
+ * on the related bits (if supported by the CPU) in the hope that
+ * we can avoid VMWrites during vmx_set_efer().
+ */
+ exec_control = (vmcs12->vm_entry_controls | vmcs_config.vmentry_ctrl) &
+ ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER;
+ if (cpu_has_load_ia32_efer) {
+ if (guest_efer & EFER_LMA)
+ exec_control |= VM_ENTRY_IA32E_MODE;
+ if (guest_efer != host_efer)
+ exec_control |= VM_ENTRY_LOAD_IA32_EFER;
+ }
+ vm_entry_controls_init(vmx, exec_control);
+
+ /*
+ * EXIT CONTROLS
+ *
+ * L2->L1 exit controls are emulated - the hardware exit is to L0 so
+ * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
+ * bits may be modified by vmx_set_efer() in prepare_vmcs02().
*/
- vmx->host_rsp = 0;
+ exec_control = vmcs_config.vmexit_ctrl;
+ if (cpu_has_load_ia32_efer && guest_efer != host_efer)
+ exec_control |= VM_EXIT_LOAD_IA32_EFER;
+ vm_exit_controls_init(vmx, exec_control);
- exec_control = vmx_exec_control(vmx); /* L0's desires */
- exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
- exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
- exec_control &= ~CPU_BASED_TPR_SHADOW;
- exec_control |= vmcs12->cpu_based_vm_exec_control;
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit and never change
+ * the PML address (once set), this happens to be equivalent to
+ * simply resetting the index in vmcs02.
+ */
+ if (enable_pml)
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
/*
- * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if
- * nested_get_vmcs12_pages can't fix it up, the illegal value
- * will result in a VM entry failure.
+ * Interrupt/Exception Fields
*/
- if (exec_control & CPU_BASED_TPR_SHADOW) {
- vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
- vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ if (vmx->nested.nested_run_pending) {
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ vmcs12->vm_entry_intr_info_field);
+ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
+ vmcs12->vm_entry_exception_error_code);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+ vmcs12->vm_entry_instruction_len);
+ vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
+ vmcs12->guest_interruptibility_info);
+ vmx->loaded_vmcs->nmi_known_unmasked =
+ !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
} else {
-#ifdef CONFIG_X86_64
- exec_control |= CPU_BASED_CR8_LOAD_EXITING |
- CPU_BASED_CR8_STORE_EXITING;
-#endif
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
+ }
+}
+
+static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+ struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+
+ if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+ vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
+ vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
+ vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
+ vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
+ vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
+ vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
+ vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
+ vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
+ vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
+ vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
+ vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
+ vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
+ vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
+ vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
+ vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
+ vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
+ vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
+ vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
+ vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
+ vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
+ vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
+ vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
+ vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
+ vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
+ vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
+ vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
+ vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
+ vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
+ vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
+ vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
+ vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
+ vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
+ vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
+ vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+ }
+
+ if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) {
+ vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+ vmcs12->guest_pending_dbg_exceptions);
+ vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
+ vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+
+ /*
+ * L1 may access the L2's PDPTR, so save them to construct
+ * vmcs12
+ */
+ if (enable_ept) {
+ vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+ vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+ vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+ vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ }
}
+ if (nested_cpu_has_xsaves(vmcs12))
+ vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
+
/*
- * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
- * for I/O port accesses.
+ * Whether page-faults are trapped is determined by a combination of
+ * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
+ * If enable_ept, L0 doesn't care about page faults and we should
+ * set all of these to L1's desires. However, if !enable_ept, L0 does
+ * care about (at least some) page faults, and because it is not easy
+ * (if at all possible?) to merge L0 and L1's desires, we simply ask
+ * to exit on each and every L2 page fault. This is done by setting
+ * MASK=MATCH=0 and (see below) EB.PF=1.
+ * Note that below we don't need special code to set EB.PF beyond the
+ * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
+ * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
+ * !enable_ept, EB.PF is 1, so the "or" will always be 1.
*/
- exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
- exec_control |= CPU_BASED_UNCOND_IO_EXITING;
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
+ enable_ept ? vmcs12->page_fault_error_code_mask : 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
+ enable_ept ? vmcs12->page_fault_error_code_match : 0);
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
+ if (cpu_has_vmx_apicv()) {
+ vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
+ vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
+ vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
+ vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
+ }
+
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+ set_cr4_guest_host_mask(vmx);
+
+ if (kvm_mpx_supported()) {
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+ vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+ else
+ vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+ }
+}
+
+/*
+ * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
+ * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
+ * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
+ * guest in a way that will both be appropriate to L1's requests, and our
+ * needs. In addition to modifying the active vmcs (which is vmcs02), this
+ * function also has additional necessary side-effects, like setting various
+ * vcpu->arch fields.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+ u32 *entry_failure_code)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+
+ if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) {
+ prepare_vmcs02_full(vmx, vmcs12);
+ vmx->nested.dirty_vmcs12 = false;
+ }
+
+ /*
+ * First, the fields that are shadowed. This must be kept in sync
+ * with vmx_shadow_fields.h.
+ */
+ if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+ vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
+ vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
+ }
+
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
+ kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ } else {
+ kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
+ }
+ vmx_set_rflags(vcpu, vmcs12->guest_rflags);
+
+ vmx->nested.preemption_timer_expired = false;
+ if (nested_cpu_has_preemption_timer(vmcs12))
+ vmx_start_preemption_timer(vcpu);
/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
* bitwise-or of what L1 wants to trap for L2, and what we want to
@@ -12182,20 +12871,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- /* L2->L1 exit controls are emulated - the hardware exit is to L0 so
- * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
- * bits are further modified by vmx_set_efer() below.
- */
- vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
-
- /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
- * emulated by vmx_set_efer(), below.
- */
- vm_entry_controls_init(vmx,
- (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
- ~VM_ENTRY_IA32E_MODE) |
- (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
-
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
@@ -12218,37 +12893,29 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
* influence global bitmap(for vpid01 and vpid02 allocation)
* even if spawn a lot of nested vCPUs.
*/
- if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
+ if (nested_cpu_has_vpid(vmcs12) && nested_has_guest_tlb_tag(vcpu)) {
if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
vmx->nested.last_vpid = vmcs12->virtual_processor_id;
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, nested_get_vpid02(vcpu), false);
}
} else {
- vmx_flush_tlb(vcpu, true);
+ /*
+ * If L1 use EPT, then L0 needs to execute INVEPT on
+ * EPTP02 instead of EPTP01. Therefore, delay TLB
+ * flush until vmcs02->eptp is fully updated by
+ * KVM_REQ_LOAD_CR3. Note that this assumes
+ * KVM_REQ_TLB_FLUSH is evaluated after
+ * KVM_REQ_LOAD_CR3 in vcpu_enter_guest().
+ */
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
}
- if (enable_pml) {
- /*
- * Conceptually we want to copy the PML address and index from
- * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
- * since we always flush the log on each vmexit, this happens
- * to be equivalent to simply resetting the fields in vmcs02.
- */
- ASSERT(vmx->pml_pg);
- vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
- vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
- }
-
- if (nested_cpu_has_ept(vmcs12)) {
- if (nested_ept_init_mmu_context(vcpu)) {
- *entry_failure_code = ENTRY_FAIL_DEFAULT;
- return 1;
- }
- } else if (nested_cpu_has2(vmcs12,
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ if (nested_cpu_has_ept(vmcs12))
+ nested_ept_init_mmu_context(vcpu);
+ else if (nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
vmx_flush_tlb(vcpu, true);
- }
/*
* This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
@@ -12264,14 +12931,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmx_set_cr4(vcpu, vmcs12->guest_cr4);
vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
- if (vmx->nested.nested_run_pending &&
- (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
- vcpu->arch.efer = vmcs12->guest_ia32_efer;
- else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
- vcpu->arch.efer |= (EFER_LMA | EFER_LME);
- else
- vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
- /* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
+ vcpu->arch.efer = nested_vmx_calc_efer(vmx, vmcs12);
+ /* Note: may modify VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
vmx_set_efer(vcpu, vcpu->arch.efer);
/*
@@ -12313,11 +12974,15 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool ia32e;
if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
@@ -12384,6 +13049,21 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
/*
+ * If the load IA32_EFER VM-exit control is 1, bits reserved in the
+ * IA32_EFER MSR must be 0 in the field for that register. In addition,
+ * the values of the LMA and LME bits in the field must each be that of
+ * the host address-space size VM-exit control.
+ */
+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
+ ia32e = (vmcs12->vm_exit_controls &
+ VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;
+ if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
+ ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
+ ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
+ return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
+ }
+
+ /*
* From the Intel SDM, volume 3:
* Fields relevant to VM-entry event injection must be set properly.
* These fields are the VM-entry interruption-information field, the
@@ -12439,6 +13119,10 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
}
}
+ if (nested_cpu_has_ept(vmcs12) &&
+ !valid_ept_address(vcpu, vmcs12->ept_pointer))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
return 0;
}
@@ -12504,21 +13188,6 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
return 1;
}
- /*
- * If the load IA32_EFER VM-exit control is 1, bits reserved in the
- * IA32_EFER MSR must be 0 in the field for that register. In addition,
- * the values of the LMA and LME bits in the field must each be that of
- * the host address-space size VM-exit control.
- */
- if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
- ia32e = (vmcs12->vm_exit_controls &
- VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;
- if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
- ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
- ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
- return 1;
- }
-
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
(vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
@@ -12527,42 +13196,175 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
return 0;
}
+static int __noclone nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long cr3, cr4;
+
+ if (!nested_early_check)
+ return 0;
+
+ if (vmx->msr_autoload.host.nr)
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+ if (vmx->msr_autoload.guest.nr)
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+
+ preempt_disable();
+
+ vmx_prepare_switch_to_guest(vcpu);
+
+ /*
+ * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
+ * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to
+ * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e.
+ * there is no need to preserve other bits or save/restore the field.
+ */
+ vmcs_writel(GUEST_RFLAGS, 0);
+
+ vmcs_writel(HOST_RIP, vmx_early_consistency_check_return);
+
+ cr3 = __get_current_cr3_fast();
+ if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+ vmcs_writel(HOST_CR3, cr3);
+ vmx->loaded_vmcs->host_state.cr3 = cr3;
+ }
+
+ cr4 = cr4_read_shadow();
+ if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->loaded_vmcs->host_state.cr4 = cr4;
+ }
+
+ vmx->__launched = vmx->loaded_vmcs->launched;
+
+ asm(
+ /* Set HOST_RSP */
+ __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t"
+ "mov %%" _ASM_SP ", %c[host_rsp](%0)\n\t"
+
+ /* Check if vmlaunch of vmresume is needed */
+ "cmpl $0, %c[launched](%0)\n\t"
+ "je 1f\n\t"
+ __ex("vmresume") "\n\t"
+ "jmp 2f\n\t"
+ "1: " __ex("vmlaunch") "\n\t"
+ "jmp 2f\n\t"
+ "2: "
+
+ /* Set vmx->fail accordingly */
+ "setbe %c[fail](%0)\n\t"
+
+ ".pushsection .rodata\n\t"
+ ".global vmx_early_consistency_check_return\n\t"
+ "vmx_early_consistency_check_return: " _ASM_PTR " 2b\n\t"
+ ".popsection"
+ :
+ : "c"(vmx), "d"((unsigned long)HOST_RSP),
+ [launched]"i"(offsetof(struct vcpu_vmx, __launched)),
+ [fail]"i"(offsetof(struct vcpu_vmx, fail)),
+ [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp))
+ : "rax", "cc", "memory"
+ );
+
+ vmcs_writel(HOST_RIP, vmx_return);
+
+ preempt_enable();
+
+ if (vmx->msr_autoload.host.nr)
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ if (vmx->msr_autoload.guest.nr)
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+ if (vmx->fail) {
+ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ vmx->fail = 0;
+ return 1;
+ }
+
+ /*
+ * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
+ */
+ local_irq_enable();
+ if (hw_breakpoint_active())
+ set_debugreg(__this_cpu_read(cpu_dr7), 7);
+
+ /*
+ * A non-failing VMEntry means we somehow entered guest mode with
+ * an illegal RIP, and that's just the tip of the iceberg. There
+ * is no telling what memory has been modified or what state has
+ * been exposed to unknown code. Hitting this all but guarantees
+ * a (very critical) hardware issue.
+ */
+ WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
+ VMX_EXIT_REASONS_FAILED_VMENTRY));
+
+ return 0;
+}
+STACK_FRAME_NON_STANDARD(nested_vmx_check_vmentry_hw);
+
+static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12);
+
/*
- * If exit_qual is NULL, this is being called from state restore (either RSM
+ * If from_vmentry is false, this is being called from state restore (either RSM
* or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume.
++ *
++ * Returns:
++ * 0 - success, i.e. proceed with actual VMEnter
++ * 1 - consistency check VMExit
++ * -1 - consistency check VMFail
*/
-static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
+static int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+ bool from_vmentry)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- bool from_vmentry = !!exit_qual;
- u32 dummy_exit_qual;
- int r = 0;
+ bool evaluate_pending_interrupts;
+ u32 exit_reason = EXIT_REASON_INVALID_STATE;
+ u32 exit_qual;
- enter_guest_mode(vcpu);
+ evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
+ (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+ if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
+ evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ if (kvm_mpx_supported() &&
+ !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+ vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
- vmx_segment_cache_clear(vmx);
+ prepare_vmcs02_early(vmx, vmcs12);
+
+ if (from_vmentry) {
+ nested_get_vmcs12_pages(vcpu);
+
+ if (nested_vmx_check_vmentry_hw(vcpu)) {
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ return -1;
+ }
+
+ if (check_vmentry_postreqs(vcpu, vmcs12, &exit_qual))
+ goto vmentry_fail_vmexit;
+ }
+
+ enter_guest_mode(vcpu);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vcpu->arch.tsc_offset += vmcs12->tsc_offset;
- r = EXIT_REASON_INVALID_STATE;
- if (prepare_vmcs02(vcpu, vmcs12, from_vmentry ? exit_qual : &dummy_exit_qual))
- goto fail;
+ if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
+ goto vmentry_fail_vmexit_guest_mode;
if (from_vmentry) {
- nested_get_vmcs12_pages(vcpu);
-
- r = EXIT_REASON_MSR_LOAD_FAIL;
- *exit_qual = nested_vmx_load_msr(vcpu,
- vmcs12->vm_entry_msr_load_addr,
- vmcs12->vm_entry_msr_load_count);
- if (*exit_qual)
- goto fail;
+ exit_reason = EXIT_REASON_MSR_LOAD_FAIL;
+ exit_qual = nested_vmx_load_msr(vcpu,
+ vmcs12->vm_entry_msr_load_addr,
+ vmcs12->vm_entry_msr_load_count);
+ if (exit_qual)
+ goto vmentry_fail_vmexit_guest_mode;
} else {
/*
* The MMU is not initialized to point at the right entities yet and
@@ -12575,6 +13377,23 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
}
/*
+ * If L1 had a pending IRQ/NMI until it executed
+ * VMLAUNCH/VMRESUME which wasn't delivered because it was
+ * disallowed (e.g. interrupts disabled), L0 needs to
+ * evaluate if this pending event should cause an exit from L2
+ * to L1 or delivered directly to L2 (e.g. In case L1 don't
+ * intercept EXTERNAL_INTERRUPT).
+ *
+ * Usually this would be handled by the processor noticing an
+ * IRQ/NMI window request, or checking RVI during evaluation of
+ * pending virtual interrupts. However, this setting was done
+ * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
+ * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
+ */
+ if (unlikely(evaluate_pending_interrupts))
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+ /*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
* we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
* returned as far as L1 is concerned. It will only return (and set
@@ -12582,12 +13401,28 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
*/
return 0;
-fail:
+ /*
+ * A failed consistency check that leads to a VMExit during L1's
+ * VMEnter to L2 is a variation of a normal VMexit, as explained in
+ * 26.7 "VM-entry failures during or after loading guest state".
+ */
+vmentry_fail_vmexit_guest_mode:
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
leave_guest_mode(vcpu);
+
+vmentry_fail_vmexit:
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- return r;
+
+ if (!from_vmentry)
+ return 1;
+
+ load_vmcs12_host_state(vcpu, vmcs12);
+ vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
+ vmcs12->exit_qualification = exit_qual;
+ if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
+ vmx->nested.need_vmcs12_sync = true;
+ return 1;
}
/*
@@ -12599,14 +13434,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
struct vmcs12 *vmcs12;
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
- u32 exit_qual;
int ret;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- goto out;
+ if (!nested_vmx_handle_enlightened_vmptrld(vcpu, true))
+ return 1;
+
+ if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_vmcs12(vcpu);
@@ -12616,13 +13453,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
* rather than RFLAGS.ZF, and no error number is stored to the
* VM-instruction error field.
*/
- if (vmcs12->hdr.shadow_vmcs) {
- nested_vmx_failInvalid(vcpu);
- goto out;
- }
+ if (vmcs12->hdr.shadow_vmcs)
+ return nested_vmx_failInvalid(vcpu);
- if (enable_shadow_vmcs)
+ if (vmx->nested.hv_evmcs) {
+ copy_enlightened_to_vmcs12(vmx);
+ /* Enlightened VMCS doesn't have launch state */
+ vmcs12->launch_state = !launch;
+ } else if (enable_shadow_vmcs) {
copy_shadow_to_vmcs12(vmx);
+ }
/*
* The nested entry process starts with enforcing various prerequisites
@@ -12634,59 +13474,37 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
* for misconfigurations which will anyway be caught by the processor
* when using the merged vmcs02.
*/
- if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) {
- nested_vmx_failValid(vcpu,
- VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- goto out;
- }
+ if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- if (vmcs12->launch_state == launch) {
- nested_vmx_failValid(vcpu,
+ if (vmcs12->launch_state == launch)
+ return nested_vmx_failValid(vcpu,
launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
: VMXERR_VMRESUME_NONLAUNCHED_VMCS);
- goto out;
- }
ret = check_vmentry_prereqs(vcpu, vmcs12);
- if (ret) {
- nested_vmx_failValid(vcpu, ret);
- goto out;
- }
-
- /*
- * After this point, the trap flag no longer triggers a singlestep trap
- * on the vm entry instructions; don't call kvm_skip_emulated_instruction.
- * This is not 100% correct; for performance reasons, we delegate most
- * of the checks on host state to the processor. If those fail,
- * the singlestep trap is missed.
- */
- skip_emulated_instruction(vcpu);
-
- ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual);
- if (ret) {
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_INVALID_STATE, exit_qual);
- return 1;
- }
+ if (ret)
+ return nested_vmx_failValid(vcpu, ret);
/*
* We're finally done with prerequisite checking, and can start with
* the nested entry.
*/
-
vmx->nested.nested_run_pending = 1;
- ret = enter_vmx_non_root_mode(vcpu, &exit_qual);
- if (ret) {
- nested_vmx_entry_failure(vcpu, vmcs12, ret, exit_qual);
- vmx->nested.nested_run_pending = 0;
+ ret = nested_vmx_enter_non_root_mode(vcpu, true);
+ vmx->nested.nested_run_pending = !ret;
+ if (ret > 0)
return 1;
- }
+ else if (ret)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/* Hide L1D cache contents from the nested guest. */
vmx->vcpu.arch.l1tf_flush_l1d = true;
/*
- * Must happen outside of enter_vmx_non_root_mode() as it will
+ * Must happen outside of nested_vmx_enter_non_root_mode() as it will
* also be used as part of restoring nVMX state for
* snapshot restore (migration).
*
@@ -12707,9 +13525,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
return kvm_vcpu_halt(vcpu);
}
return 1;
-
-out:
- return kvm_skip_emulated_instruction(vcpu);
}
/*
@@ -12841,6 +13656,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
return 0;
}
+static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+ to_vmx(vcpu)->req_immediate_exit = true;
+}
+
static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
{
ktime_t remaining =
@@ -13018,24 +13838,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
kvm_clear_interrupt_queue(vcpu);
}
-static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12)
-{
- u32 entry_failure_code;
-
- nested_ept_uninit_mmu_context(vcpu);
-
- /*
- * Only PDPTE load can fail as the value of cr3 was checked on entry and
- * couldn't have changed.
- */
- if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
- nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
- if (!enable_ept)
- vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
-}
-
/*
* A part of what we need to when the nested L2 guest exits and we want to
* run its L1 parent, is to reset L1's guest state to the host state specified
@@ -13049,6 +13851,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
struct kvm_segment seg;
+ u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -13061,6 +13864,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
+ vmx_set_interrupt_shadow(vcpu, 0);
+
/*
* Note that calling vmx_set_cr0 is important, even if cr0 hasn't
* actually changed, because vmx_set_cr0 refers to efer set above.
@@ -13075,23 +13880,35 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
vmx_set_cr4(vcpu, vmcs12->host_cr4);
- load_vmcs12_mmu_host_state(vcpu, vmcs12);
+ nested_ept_uninit_mmu_context(vcpu);
+
+ /*
+ * Only PDPTE load can fail as the value of cr3 was checked on entry and
+ * couldn't have changed.
+ */
+ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+ if (!enable_ept)
+ vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
/*
- * If vmcs01 don't use VPID, CPU flushes TLB on every
+ * If vmcs01 doesn't use VPID, CPU flushes TLB on every
* VMEntry/VMExit. Thus, no need to flush TLB.
*
- * If vmcs12 uses VPID, TLB entries populated by L2 are
- * tagged with vmx->nested.vpid02 while L1 entries are tagged
- * with vmx->vpid. Thus, no need to flush TLB.
+ * If vmcs12 doesn't use VPID, L1 expects TLB to be
+ * flushed on every VMEntry/VMExit.
*
- * Therefore, flush TLB only in case vmcs01 uses VPID and
- * vmcs12 don't use VPID as in this case L1 & L2 TLB entries
- * are both tagged with vmx->vpid.
+ * Otherwise, we can preserve TLB entries as long as we are
+ * able to tag L1 TLB entries differently than L2 TLB entries.
+ *
+ * If vmcs12 uses EPT, we need to execute this flush on EPTP01
+ * and therefore we request the TLB flush to happen only after VMCS EPTP
+ * has been set by KVM_REQ_LOAD_CR3.
*/
if (enable_vpid &&
- !(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02)) {
- vmx_flush_tlb(vcpu, true);
+ (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) {
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
@@ -13171,6 +13988,140 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
}
+static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
+{
+ struct shared_msr_entry *efer_msr;
+ unsigned int i;
+
+ if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER)
+ return vmcs_read64(GUEST_IA32_EFER);
+
+ if (cpu_has_load_ia32_efer)
+ return host_efer;
+
+ for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) {
+ if (vmx->msr_autoload.guest.val[i].index == MSR_EFER)
+ return vmx->msr_autoload.guest.val[i].value;
+ }
+
+ efer_msr = find_msr_entry(vmx, MSR_EFER);
+ if (efer_msr)
+ return efer_msr->data;
+
+ return host_efer;
+}
+
+static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmx_msr_entry g, h;
+ struct msr_data msr;
+ gpa_t gpa;
+ u32 i, j;
+
+ vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT);
+
+ if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+ /*
+ * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set
+ * as vmcs01.GUEST_DR7 contains a userspace defined value
+ * and vcpu->arch.dr7 is not squirreled away before the
+ * nested VMENTER (not worth adding a variable in nested_vmx).
+ */
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+ kvm_set_dr(vcpu, 7, DR7_FIXED_1);
+ else
+ WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
+ }
+
+ /*
+ * Note that calling vmx_set_{efer,cr0,cr4} is important as they
+ * handle a variety of side effects to KVM's software model.
+ */
+ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
+
+ vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
+
+ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
+ vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
+
+ nested_ept_uninit_mmu_context(vcpu);
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
+ * from vmcs01 (if necessary). The PDPTRs are not loaded on
+ * VMFail, like everything else we just need to ensure our
+ * software model is up-to-date.
+ */
+ ept_save_pdptrs(vcpu);
+
+ kvm_mmu_reset_context(vcpu);
+
+ if (cpu_has_vmx_msr_bitmap())
+ vmx_update_msr_bitmap(vcpu);
+
+ /*
+ * This nasty bit of open coding is a compromise between blindly
+ * loading L1's MSRs using the exit load lists (incorrect emulation
+ * of VMFail), leaving the nested VM's MSRs in the software model
+ * (incorrect behavior) and snapshotting the modified MSRs (too
+ * expensive since the lists are unbound by hardware). For each
+ * MSR that was (prematurely) loaded from the nested VMEntry load
+ * list, reload it from the exit load list if it exists and differs
+ * from the guest value. The intent is to stuff host state as
+ * silently as possible, not to fully process the exit load list.
+ */
+ msr.host_initiated = false;
+ for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) {
+ gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g));
+ if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) {
+ pr_debug_ratelimited(
+ "%s read MSR index failed (%u, 0x%08llx)\n",
+ __func__, i, gpa);
+ goto vmabort;
+ }
+
+ for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) {
+ gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h));
+ if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) {
+ pr_debug_ratelimited(
+ "%s read MSR failed (%u, 0x%08llx)\n",
+ __func__, j, gpa);
+ goto vmabort;
+ }
+ if (h.index != g.index)
+ continue;
+ if (h.value == g.value)
+ break;
+
+ if (nested_vmx_load_msr_check(vcpu, &h)) {
+ pr_debug_ratelimited(
+ "%s check failed (%u, 0x%x, 0x%x)\n",
+ __func__, j, h.index, h.reserved);
+ goto vmabort;
+ }
+
+ msr.index = h.index;
+ msr.data = h.value;
+ if (kvm_set_msr(vcpu, &msr)) {
+ pr_debug_ratelimited(
+ "%s WRMSR failed (%u, 0x%x, 0x%llx)\n",
+ __func__, j, h.index, h.value);
+ goto vmabort;
+ }
+ }
+ }
+
+ return;
+
+vmabort:
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+}
+
/*
* Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1
* and modify vmcs12 to make it see what it would expect to see there if
@@ -13186,14 +14137,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
- /*
- * The only expected VM-instruction error is "VM entry with
- * invalid control field(s)." Anything else indicates a
- * problem with L0.
- */
- WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) !=
- VMXERR_ENTRY_INVALID_CONTROL_FIELD));
-
leave_guest_mode(vcpu);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
@@ -13220,23 +14163,25 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr,
vmcs12->vm_exit_msr_store_count))
nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
+ } else {
+ /*
+ * The only expected VM-instruction error is "VM entry with
+ * invalid control field(s)." Anything else indicates a
+ * problem with L0. And we should never get here with a
+ * VMFail of any type if early consistency checks are enabled.
+ */
+ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ WARN_ON_ONCE(nested_early_check);
}
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- vm_entry_controls_reset_shadow(vmx);
- vm_exit_controls_reset_shadow(vmx);
- vmx_segment_cache_clear(vmx);
/* Update any VMCS fields that might have changed while L2 ran */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
- if (vmx->hv_deadline_tsc == -1)
- vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
- else
- vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
+
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
@@ -13274,8 +14219,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
*/
kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
- if (enable_shadow_vmcs && exit_reason != -1)
- vmx->nested.sync_shadow_vmcs = true;
+ if ((exit_reason != -1) && (enable_shadow_vmcs || vmx->nested.hv_evmcs))
+ vmx->nested.need_vmcs12_sync = true;
/* in case we halted in L2 */
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -13310,24 +14255,24 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
return;
}
-
+
/*
* After an early L2 VM-entry failure, we're now back
* in L1 which thinks it just finished a VMLAUNCH or
* VMRESUME instruction, so we need to set the failure
* flag and the VM-instruction error field of the VMCS
- * accordingly.
+ * accordingly, and skip the emulated instruction.
*/
- nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-
- load_vmcs12_mmu_host_state(vcpu, vmcs12);
+ (void)nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/*
- * The emulated instruction was already skipped in
- * nested_vmx_run, but the updated RIP was never
- * written back to the vmcs01.
+ * Restore L1's host state to KVM's software model. We're here
+ * because a consistency check was caught by hardware, which
+ * means some amount of guest state has been propagated to KVM's
+ * model and needs to be unwound to the host's state.
*/
- skip_emulated_instruction(vcpu);
+ nested_vmx_restore_host_state(vcpu);
+
vmx->fail = 0;
}
@@ -13340,26 +14285,7 @@ static void vmx_leave_nested(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
}
- free_nested(to_vmx(vcpu));
-}
-
-/*
- * L1's failure to enter L2 is a subset of a normal exit, as explained in
- * 23.7 "VM-entry failures during or after loading guest state" (this also
- * lists the acceptable exit-reason and exit-qualification parameters).
- * It should only be called before L2 actually succeeded to run, and when
- * vmcs01 is current (it doesn't leave_guest_mode() or switch vmcss).
- */
-static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12,
- u32 reason, unsigned long qualification)
-{
- load_vmcs12_host_state(vcpu, vmcs12);
- vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
- vmcs12->exit_qualification = qualification;
- nested_vmx_succeed(vcpu);
- if (enable_shadow_vmcs)
- to_vmx(vcpu)->nested.sync_shadow_vmcs = true;
+ free_nested(vcpu);
}
static int vmx_check_intercept(struct kvm_vcpu *vcpu,
@@ -13440,18 +14366,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
return -ERANGE;
vmx->hv_deadline_tsc = tscl + delta_tsc;
- vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
-
return delta_tsc == 0;
}
static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->hv_deadline_tsc = -1;
- vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
+ to_vmx(vcpu)->hv_deadline_tsc = -1;
}
#endif
@@ -13791,7 +14711,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
if (vmx->nested.smm.guest_mode) {
vcpu->arch.hflags &= ~HF_SMM_MASK;
- ret = enter_vmx_non_root_mode(vcpu, NULL);
+ ret = nested_vmx_enter_non_root_mode(vcpu, false);
vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
@@ -13806,6 +14726,20 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
return 0;
}
+static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * In case we do two consecutive get/set_nested_state()s while L2 was
+ * running hv_evmcs may end up not being mapped (we map it from
+ * nested_vmx_run()/vmx_vcpu_run()). Check is_guest_mode() as we always
+ * have vmcs12 if it is true.
+ */
+ return is_guest_mode(vcpu) || vmx->nested.current_vmptr != -1ull ||
+ vmx->nested.hv_evmcs;
+}
+
static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
u32 user_data_size)
@@ -13825,12 +14759,16 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
vmx = to_vmx(vcpu);
vmcs12 = get_vmcs12(vcpu);
+
+ if (nested_vmx_allowed(vcpu) && vmx->nested.enlightened_vmcs_enabled)
+ kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
+
if (nested_vmx_allowed(vcpu) &&
(vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
kvm_state.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
kvm_state.vmx.vmcs_pa = vmx->nested.current_vmptr;
- if (vmx->nested.current_vmptr != -1ull) {
+ if (vmx_has_valid_vmcs12(vcpu)) {
kvm_state.size += VMCS12_SIZE;
if (is_guest_mode(vcpu) &&
@@ -13859,20 +14797,24 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
return -EFAULT;
- if (vmx->nested.current_vmptr == -1ull)
+ if (!vmx_has_valid_vmcs12(vcpu))
goto out;
/*
* When running L2, the authoritative vmcs12 state is in the
* vmcs02. When running L1, the authoritative vmcs12 state is
- * in the shadow vmcs linked to vmcs01, unless
- * sync_shadow_vmcs is set, in which case, the authoritative
+ * in the shadow or enlightened vmcs linked to vmcs01, unless
+ * need_vmcs12_sync is set, in which case, the authoritative
* vmcs12 state is in the vmcs12 already.
*/
- if (is_guest_mode(vcpu))
+ if (is_guest_mode(vcpu)) {
sync_vmcs12(vcpu, vmcs12);
- else if (enable_shadow_vmcs && !vmx->nested.sync_shadow_vmcs)
- copy_shadow_to_vmcs12(vmx);
+ } else if (!vmx->nested.need_vmcs12_sync) {
+ if (vmx->nested.hv_evmcs)
+ copy_enlightened_to_vmcs12(vmx);
+ else if (enable_shadow_vmcs)
+ copy_shadow_to_vmcs12(vmx);
+ }
if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12)))
return -EFAULT;
@@ -13900,6 +14842,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (kvm_state->format != 0)
return -EINVAL;
+ if (kvm_state->flags & KVM_STATE_NESTED_EVMCS)
+ nested_enable_evmcs(vcpu, NULL);
+
if (!nested_vmx_allowed(vcpu))
return kvm_state->vmx.vmxon_pa == -1ull ? 0 : -EINVAL;
@@ -13917,13 +14862,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (!page_address_valid(vcpu, kvm_state->vmx.vmxon_pa))
return -EINVAL;
- if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
- return -EINVAL;
-
- if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa ||
- !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa))
- return -EINVAL;
-
if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
return -EINVAL;
@@ -13932,6 +14870,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
+ /*
+ * SMM temporarily disables VMX, so we cannot be in guest mode,
+ * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags
+ * must be zero.
+ */
+ if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags)
+ return -EINVAL;
+
if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
!(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
@@ -13945,7 +14891,25 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (ret)
return ret;
- set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa);
+ /* Empty 'VMXON' state is permitted */
+ if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+ return 0;
+
+ if (kvm_state->vmx.vmcs_pa != -1ull) {
+ if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa ||
+ !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa))
+ return -EINVAL;
+
+ set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa);
+ } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
+ /*
+ * Sync eVMCS upon entry as we may not have
+ * HV_X64_MSR_VP_ASSIST_PAGE set up yet.
+ */
+ vmx->nested.need_vmcs12_sync = true;
+ } else {
+ return -EINVAL;
+ }
if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
vmx->nested.smm.vmxon = true;
@@ -13988,11 +14952,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
check_vmentry_postreqs(vcpu, vmcs12, &exit_qual))
return -EINVAL;
- if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING)
- vmx->nested.nested_run_pending = 1;
-
vmx->nested.dirty_vmcs12 = true;
- ret = enter_vmx_non_root_mode(vcpu, NULL);
+ ret = nested_vmx_enter_non_root_mode(vcpu, false);
if (ret)
return -EINVAL;
@@ -14078,6 +15039,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.apicv_post_state_restore = vmx_apicv_post_state_restore,
.hwapic_irr_update = vmx_hwapic_irr_update,
.hwapic_isr_update = vmx_hwapic_isr_update,
+ .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
.sync_pir_to_irr = vmx_sync_pir_to_irr,
.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
@@ -14111,6 +15073,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.umip_emulated = vmx_umip_emulated,
.check_nested_events = vmx_check_nested_events,
+ .request_immediate_exit = vmx_request_immediate_exit,
.sched_in = vmx_sched_in,
@@ -14142,6 +15105,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.pre_enter_smm = vmx_pre_enter_smm,
.pre_leave_smm = vmx_pre_leave_smm,
.enable_smi_window = enable_smi_window,
+
+ .nested_enable_evmcs = nested_enable_evmcs,
};
static void vmx_cleanup_l1d_flush(void)
diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx_shadow_fields.h
index cd0c75f6d037..132432f375c2 100644
--- a/arch/x86/kvm/vmx_shadow_fields.h
+++ b/arch/x86/kvm/vmx_shadow_fields.h
@@ -28,7 +28,6 @@
*/
/* 16-bits */
-SHADOW_FIELD_RW(GUEST_CS_SELECTOR)
SHADOW_FIELD_RW(GUEST_INTR_STATUS)
SHADOW_FIELD_RW(GUEST_PML_INDEX)
SHADOW_FIELD_RW(HOST_FS_SELECTOR)
@@ -47,8 +46,8 @@ SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE)
SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD)
SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN)
SHADOW_FIELD_RW(TPR_THRESHOLD)
-SHADOW_FIELD_RW(GUEST_CS_LIMIT)
SHADOW_FIELD_RW(GUEST_CS_AR_BYTES)
+SHADOW_FIELD_RW(GUEST_SS_AR_BYTES)
SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO)
SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE)
@@ -61,8 +60,6 @@ SHADOW_FIELD_RW(GUEST_CR0)
SHADOW_FIELD_RW(GUEST_CR3)
SHADOW_FIELD_RW(GUEST_CR4)
SHADOW_FIELD_RW(GUEST_RFLAGS)
-SHADOW_FIELD_RW(GUEST_CS_BASE)
-SHADOW_FIELD_RW(GUEST_ES_BASE)
SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK)
SHADOW_FIELD_RW(CR0_READ_SHADOW)
SHADOW_FIELD_RW(CR4_READ_SHADOW)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 506bd2b4b8bb..66d66d77caee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 0;
+unsigned int __read_mostly lapic_timer_advance_ns = 1000;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
@@ -400,9 +400,51 @@ static int exception_type(int vector)
return EXCPT_FAULT;
}
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
+{
+ unsigned nr = vcpu->arch.exception.nr;
+ bool has_payload = vcpu->arch.exception.has_payload;
+ unsigned long payload = vcpu->arch.exception.payload;
+
+ if (!has_payload)
+ return;
+
+ switch (nr) {
+ case DB_VECTOR:
+ /*
+ * "Certain debug exceptions may clear bit 0-3. The
+ * remaining contents of the DR6 register are never
+ * cleared by the processor".
+ */
+ vcpu->arch.dr6 &= ~DR_TRAP_BITS;
+ /*
+ * DR6.RTM is set by all #DB exceptions that don't clear it.
+ */
+ vcpu->arch.dr6 |= DR6_RTM;
+ vcpu->arch.dr6 |= payload;
+ /*
+ * Bit 16 should be set in the payload whenever the #DB
+ * exception should clear DR6.RTM. This makes the payload
+ * compatible with the pending debug exceptions under VMX.
+ * Though not currently documented in the SDM, this also
+ * makes the payload compatible with the exit qualification
+ * for #DB exceptions under VMX.
+ */
+ vcpu->arch.dr6 ^= payload & DR6_RTM;
+ break;
+ case PF_VECTOR:
+ vcpu->arch.cr2 = payload;
+ break;
+ }
+
+ vcpu->arch.exception.has_payload = false;
+ vcpu->arch.exception.payload = 0;
+}
+EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload);
+
static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
unsigned nr, bool has_error, u32 error_code,
- bool reinject)
+ bool has_payload, unsigned long payload, bool reinject)
{
u32 prev_nr;
int class1, class2;
@@ -424,6 +466,14 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
*/
WARN_ON_ONCE(vcpu->arch.exception.pending);
vcpu->arch.exception.injected = true;
+ if (WARN_ON_ONCE(has_payload)) {
+ /*
+ * A reinjected event has already
+ * delivered its payload.
+ */
+ has_payload = false;
+ payload = 0;
+ }
} else {
vcpu->arch.exception.pending = true;
vcpu->arch.exception.injected = false;
@@ -431,6 +481,22 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.has_error_code = has_error;
vcpu->arch.exception.nr = nr;
vcpu->arch.exception.error_code = error_code;
+ vcpu->arch.exception.has_payload = has_payload;
+ vcpu->arch.exception.payload = payload;
+ /*
+ * In guest mode, payload delivery should be deferred,
+ * so that the L1 hypervisor can intercept #PF before
+ * CR2 is modified (or intercept #DB before DR6 is
+ * modified under nVMX). However, for ABI
+ * compatibility with KVM_GET_VCPU_EVENTS and
+ * KVM_SET_VCPU_EVENTS, we can't delay payload
+ * delivery unless userspace has enabled this
+ * functionality via the per-VM capability,
+ * KVM_CAP_EXCEPTION_PAYLOAD.
+ */
+ if (!vcpu->kvm->arch.exception_payload_enabled ||
+ !is_guest_mode(vcpu))
+ kvm_deliver_exception_payload(vcpu);
return;
}
@@ -455,6 +521,8 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.has_error_code = true;
vcpu->arch.exception.nr = DF_VECTOR;
vcpu->arch.exception.error_code = 0;
+ vcpu->arch.exception.has_payload = false;
+ vcpu->arch.exception.payload = 0;
} else
/* replace previous exception with a new one in a hope
that instruction re-execution will regenerate lost
@@ -464,16 +532,29 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_multiple_exception(vcpu, nr, false, 0, false);
+ kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_multiple_exception(vcpu, nr, false, 0, true);
+ kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
+ unsigned long payload)
+{
+ kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
+}
+
+static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
+ u32 error_code, unsigned long payload)
+{
+ kvm_multiple_exception(vcpu, nr, true, error_code,
+ true, payload, false);
+}
+
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
if (err)
@@ -490,11 +571,13 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
++vcpu->stat.pf_guest;
vcpu->arch.exception.nested_apf =
is_guest_mode(vcpu) && fault->async_page_fault;
- if (vcpu->arch.exception.nested_apf)
+ if (vcpu->arch.exception.nested_apf) {
vcpu->arch.apf.nested_apf_token = fault->address;
- else
- vcpu->arch.cr2 = fault->address;
- kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
+ kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
+ } else {
+ kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
+ fault->address);
+ }
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
@@ -503,7 +586,7 @@ static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fau
if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
else
- vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+ vcpu->arch.mmu->inject_page_fault(vcpu, fault);
return fault->nested_page_fault;
}
@@ -517,13 +600,13 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- kvm_multiple_exception(vcpu, nr, true, error_code, false);
+ kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- kvm_multiple_exception(vcpu, nr, true, error_code, true);
+ kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
@@ -602,7 +685,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if ((pdpte[i] & PT_PRESENT_MASK) &&
(pdpte[i] &
- vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+ vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) {
ret = 0;
goto out;
}
@@ -628,7 +711,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
gfn_t gfn;
int r;
- if (is_long_mode(vcpu) || !is_pae(vcpu))
+ if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
return false;
if (!test_bit(VCPU_EXREG_PDPTR,
@@ -2477,7 +2560,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_KVM_PV_EOI_EN:
- if (kvm_lapic_enable_pv_eoi(vcpu, data))
+ if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8)))
return 1;
break;
@@ -2537,7 +2620,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_PLATFORM_INFO:
if (!msr_info->host_initiated ||
- data & ~MSR_PLATFORM_INFO_CPUID_FAULT ||
(!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
cpuid_fault_enabled(vcpu)))
return 1;
@@ -2780,6 +2862,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vcpu->arch.osvw.status;
break;
case MSR_PLATFORM_INFO:
+ if (!msr_info->host_initiated &&
+ !vcpu->kvm->arch.guest_can_read_msr_platform_info)
+ return 1;
msr_info->data = vcpu->arch.msr_platform_info;
break;
case MSR_MISC_FEATURES_ENABLES:
@@ -2910,6 +2995,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_HYPERV_VP_INDEX:
case KVM_CAP_HYPERV_EVENTFD:
case KVM_CAP_HYPERV_TLBFLUSH:
+ case KVM_CAP_HYPERV_SEND_IPI:
+ case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
case KVM_CAP_PCI_SEGMENT:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -2927,6 +3014,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_SPLIT_IRQCHIP:
case KVM_CAP_IMMEDIATE_EXIT:
case KVM_CAP_GET_MSR_FEATURES:
+ case KVM_CAP_MSR_PLATFORM_INFO:
+ case KVM_CAP_EXCEPTION_PAYLOAD:
r = 1;
break;
case KVM_CAP_SYNC_REGS:
@@ -3359,19 +3448,33 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
process_nmi(vcpu);
+
/*
- * FIXME: pass injected and pending separately. This is only
- * needed for nested virtualization, whose state cannot be
- * migrated yet. For now we can combine them.
+ * The API doesn't provide the instruction length for software
+ * exceptions, so don't report them. As long as the guest RIP
+ * isn't advanced, we should expect to encounter the exception
+ * again.
*/
- events->exception.injected =
- (vcpu->arch.exception.pending ||
- vcpu->arch.exception.injected) &&
- !kvm_exception_is_soft(vcpu->arch.exception.nr);
+ if (kvm_exception_is_soft(vcpu->arch.exception.nr)) {
+ events->exception.injected = 0;
+ events->exception.pending = 0;
+ } else {
+ events->exception.injected = vcpu->arch.exception.injected;
+ events->exception.pending = vcpu->arch.exception.pending;
+ /*
+ * For ABI compatibility, deliberately conflate
+ * pending and injected exceptions when
+ * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
+ */
+ if (!vcpu->kvm->arch.exception_payload_enabled)
+ events->exception.injected |=
+ vcpu->arch.exception.pending;
+ }
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
- events->exception.pad = 0;
events->exception.error_code = vcpu->arch.exception.error_code;
+ events->exception_has_payload = vcpu->arch.exception.has_payload;
+ events->exception_payload = vcpu->arch.exception.payload;
events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -3395,6 +3498,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SHADOW
| KVM_VCPUEVENT_VALID_SMM);
+ if (vcpu->kvm->arch.exception_payload_enabled)
+ events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+
memset(&events->reserved, 0, sizeof(events->reserved));
}
@@ -3406,12 +3512,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW
- | KVM_VCPUEVENT_VALID_SMM))
+ | KVM_VCPUEVENT_VALID_SMM
+ | KVM_VCPUEVENT_VALID_PAYLOAD))
return -EINVAL;
- if (events->exception.injected &&
- (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR ||
- is_guest_mode(vcpu)))
+ if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
+ if (!vcpu->kvm->arch.exception_payload_enabled)
+ return -EINVAL;
+ if (events->exception.pending)
+ events->exception.injected = 0;
+ else
+ events->exception_has_payload = 0;
+ } else {
+ events->exception.pending = 0;
+ events->exception_has_payload = 0;
+ }
+
+ if ((events->exception.injected || events->exception.pending) &&
+ (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
return -EINVAL;
/* INITs are latched while in SMM */
@@ -3421,11 +3539,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return -EINVAL;
process_nmi(vcpu);
- vcpu->arch.exception.injected = false;
- vcpu->arch.exception.pending = events->exception.injected;
+ vcpu->arch.exception.injected = events->exception.injected;
+ vcpu->arch.exception.pending = events->exception.pending;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
vcpu->arch.exception.error_code = events->exception.error_code;
+ vcpu->arch.exception.has_payload = events->exception_has_payload;
+ vcpu->arch.exception.payload = events->exception_payload;
vcpu->arch.interrupt.injected = events->interrupt.injected;
vcpu->arch.interrupt.nr = events->interrupt.nr;
@@ -3691,6 +3811,10 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
struct kvm_enable_cap *cap)
{
+ int r;
+ uint16_t vmcs_version;
+ void __user *user_ptr;
+
if (cap->flags)
return -EINVAL;
@@ -3703,6 +3827,16 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
return -EINVAL;
return kvm_hv_activate_synic(vcpu, cap->cap ==
KVM_CAP_HYPERV_SYNIC2);
+ case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
+ r = kvm_x86_ops->nested_enable_evmcs(vcpu, &vmcs_version);
+ if (!r) {
+ user_ptr = (void __user *)(uintptr_t)cap->args[0];
+ if (copy_to_user(user_ptr, &vmcs_version,
+ sizeof(vmcs_version)))
+ r = -EFAULT;
+ }
+ return r;
+
default:
return -EINVAL;
}
@@ -4007,19 +4141,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size));
+ r = -EFAULT;
if (get_user(user_data_size, &user_kvm_nested_state->size))
- return -EFAULT;
+ break;
r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state,
user_data_size);
if (r < 0)
- return r;
+ break;
if (r > user_data_size) {
if (put_user(r, &user_kvm_nested_state->size))
- return -EFAULT;
- return -E2BIG;
+ r = -EFAULT;
+ else
+ r = -E2BIG;
+ break;
}
+
r = 0;
break;
}
@@ -4031,19 +4169,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (!kvm_x86_ops->set_nested_state)
break;
+ r = -EFAULT;
if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state)))
- return -EFAULT;
+ break;
+ r = -EINVAL;
if (kvm_state.size < sizeof(kvm_state))
- return -EINVAL;
+ break;
if (kvm_state.flags &
- ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE))
- return -EINVAL;
+ ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE
+ | KVM_STATE_NESTED_EVMCS))
+ break;
/* nested_run_pending implies guest_mode. */
- if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING)
- return -EINVAL;
+ if ((kvm_state.flags & KVM_STATE_NESTED_RUN_PENDING)
+ && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
+ break;
r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
break;
@@ -4350,6 +4492,14 @@ split_irqchip_unlock:
kvm->arch.pause_in_guest = true;
r = 0;
break;
+ case KVM_CAP_MSR_PLATFORM_INFO:
+ kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
+ r = 0;
+ break;
+ case KVM_CAP_EXCEPTION_PAYLOAD:
+ kvm->arch.exception_payload_enabled = cap->args[0];
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -4685,7 +4835,7 @@ static void kvm_init_msr_list(void)
*/
switch (msrs_to_save[i]) {
case MSR_IA32_BNDCFGS:
- if (!kvm_x86_ops->mpx_supported())
+ if (!kvm_mpx_supported())
continue;
break;
case MSR_TSC_AUX:
@@ -4790,7 +4940,7 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
/* NPT walks are always user-walks */
access |= PFERR_USER_MASK;
- t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
+ t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception);
return t_gpa;
}
@@ -4987,7 +5137,7 @@ int handle_ud(struct kvm_vcpu *vcpu)
emul_type = 0;
}
- er = emulate_instruction(vcpu, emul_type);
+ er = kvm_emulate_instruction(vcpu, emul_type);
if (er == EMULATE_USER_EXIT)
return 0;
if (er != EMULATE_DONE)
@@ -5870,10 +6020,13 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
gpa_t gpa = cr2;
kvm_pfn_t pfn;
- if (emulation_type & EMULTYPE_NO_REEXECUTE)
+ if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
+ return false;
+
+ if (WARN_ON_ONCE(is_guest_mode(vcpu)))
return false;
- if (!vcpu->arch.mmu.direct_map) {
+ if (!vcpu->arch.mmu->direct_map) {
/*
* Write permission should be allowed since only
* write access need to be emulated.
@@ -5906,7 +6059,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
kvm_release_pfn_clean(pfn);
/* The instructions are well-emulated on direct mmu. */
- if (vcpu->arch.mmu.direct_map) {
+ if (vcpu->arch.mmu->direct_map) {
unsigned int indirect_shadow_pages;
spin_lock(&vcpu->kvm->mmu_lock);
@@ -5958,7 +6111,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
*/
vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0;
- if (!(emulation_type & EMULTYPE_RETRY))
+ if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
+ return false;
+
+ if (WARN_ON_ONCE(is_guest_mode(vcpu)))
return false;
if (x86_page_table_writing_insn(ctxt))
@@ -5970,7 +6126,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
vcpu->arch.last_retry_eip = ctxt->eip;
vcpu->arch.last_retry_addr = cr2;
- if (!vcpu->arch.mmu.direct_map)
+ if (!vcpu->arch.mmu->direct_map)
gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
@@ -6030,14 +6186,7 @@ static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
kvm_run->exit_reason = KVM_EXIT_DEBUG;
*r = EMULATE_USER_EXIT;
} else {
- /*
- * "Certain debug exceptions may clear bit 0-3. The
- * remaining contents of the DR6 register are never
- * cleared by the processor".
- */
- vcpu->arch.dr6 &= ~15;
- vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
- kvm_queue_exception(vcpu, DB_VECTOR);
+ kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS);
}
}
@@ -6276,7 +6425,19 @@ restart:
return r;
}
-EXPORT_SYMBOL_GPL(x86_emulate_instruction);
+
+int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type)
+{
+ return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_instruction);
+
+int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
+ void *insn, int insn_len)
+{
+ return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
unsigned short port)
@@ -6964,10 +7125,22 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
X86_EFLAGS_RF);
- if (vcpu->arch.exception.nr == DB_VECTOR &&
- (vcpu->arch.dr7 & DR7_GD)) {
- vcpu->arch.dr7 &= ~DR7_GD;
- kvm_update_dr7(vcpu);
+ if (vcpu->arch.exception.nr == DB_VECTOR) {
+ /*
+ * This code assumes that nSVM doesn't use
+ * check_nested_events(). If it does, the
+ * DR6/DR7 changes should happen before L1
+ * gets a #VMEXIT for an intercepted #DB in
+ * L2. (Under VMX, on the other hand, the
+ * DR6/DR7 changes should not happen in the
+ * event of a VM-exit to L1 for an intercepted
+ * #DB in L2.)
+ */
+ kvm_deliver_exception_payload(vcpu);
+ if (vcpu->arch.dr7 & DR7_GD) {
+ vcpu->arch.dr7 &= ~DR7_GD;
+ kvm_update_dr7(vcpu);
+ }
}
kvm_x86_ops->queue_exception(vcpu);
@@ -7343,6 +7516,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+ smp_send_reschedule(vcpu->cpu);
+}
+EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit);
+
/*
* Returns 1 to let vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
@@ -7547,7 +7726,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
- smp_send_reschedule(vcpu->cpu);
+ kvm_x86_ops->request_immediate_exit(vcpu);
}
trace_kvm_entry(vcpu->vcpu_id);
@@ -7734,7 +7913,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
{
int r;
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
+ r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (r != EMULATE_DONE)
return 0;
@@ -7811,6 +7990,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
return 0;
}
+/* Swap (qemu) user FPU context for the guest FPU context. */
+static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
+{
+ preempt_disable();
+ copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
+ /* PKRU is separately restored in kvm_x86_ops->run. */
+ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+ ~XFEATURE_MASK_PKRU);
+ preempt_enable();
+ trace_kvm_fpu(1);
+}
+
+/* When vcpu_run ends, restore user space FPU context. */
+static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
+{
+ preempt_disable();
+ copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
+ copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+ preempt_enable();
+ ++vcpu->stat.fpu_reload;
+ trace_kvm_fpu(0);
+}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
@@ -8159,7 +8361,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
- if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+ if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
mmu_reset_needed = 1;
}
@@ -8388,29 +8590,6 @@ static void fx_init(struct kvm_vcpu *vcpu)
vcpu->arch.cr0 |= X86_CR0_ET;
}
-/* Swap (qemu) user FPU context for the guest FPU context. */
-void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
-{
- preempt_disable();
- copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
- /* PKRU is separately restored in kvm_x86_ops->run. */
- __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
- ~XFEATURE_MASK_PKRU);
- preempt_enable();
- trace_kvm_fpu(1);
-}
-
-/* When vcpu_run ends, restore user space FPU context. */
-void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
-{
- preempt_disable();
- copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
- copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
- preempt_enable();
- ++vcpu->stat.fpu_reload;
- trace_kvm_fpu(0);
-}
-
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
@@ -8441,7 +8620,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
kvm_vcpu_mtrr_init(vcpu);
vcpu_load(vcpu);
kvm_vcpu_reset(vcpu, false);
- kvm_mmu_setup(vcpu);
+ kvm_init_mmu(vcpu, false);
vcpu_put(vcpu);
return 0;
}
@@ -8834,6 +9013,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
pvclock_update_vm_gtod_copy(kvm);
+ kvm->arch.guest_can_read_msr_platform_info = true;
+
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
@@ -9182,6 +9363,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
kvm_page_track_flush_slot(kvm, slot);
}
+static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ return (is_guest_mode(vcpu) &&
+ kvm_x86_ops->guest_apic_has_interrupt &&
+ kvm_x86_ops->guest_apic_has_interrupt(vcpu));
+}
+
static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
if (!list_empty_careful(&vcpu->async_pf.done))
@@ -9206,7 +9394,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
return true;
if (kvm_arch_interrupt_allowed(vcpu) &&
- kvm_cpu_has_interrupt(vcpu))
+ (kvm_cpu_has_interrupt(vcpu) ||
+ kvm_guest_apic_has_interrupt(vcpu)))
return true;
if (kvm_hv_has_stimer_pending(vcpu))
@@ -9280,7 +9469,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
{
int r;
- if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
+ if ((vcpu->arch.mmu->direct_map != work->arch.direct_map) ||
work->wakeup_all)
return;
@@ -9288,11 +9477,11 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
if (unlikely(r))
return;
- if (!vcpu->arch.mmu.direct_map &&
- work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu))
+ if (!vcpu->arch.mmu->direct_map &&
+ work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
return;
- vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true);
+ vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
}
static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -9416,6 +9605,8 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
vcpu->arch.exception.nr = 0;
vcpu->arch.exception.has_error_code = false;
vcpu->arch.exception.error_code = 0;
+ vcpu->arch.exception.has_payload = false;
+ vcpu->arch.exception.payload = 0;
} else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
fault.vector = PF_VECTOR;
fault.error_code_valid = true;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 257f27620bc2..224cd0a47568 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -266,6 +266,8 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu,
int handle_ud(struct kvm_vcpu *vcpu);
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu);
+
void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
@@ -274,6 +276,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
int page_num);
bool kvm_vector_hashing_enabled(void);
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+ int emulation_type, void *insn, int insn_len);
#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 46e71a74e612..ad8e0906d1ea 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -273,11 +273,11 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
#define SRC(y...) \
9999: y; \
- _ASM_EXTABLE(9999b, 6001f)
+ _ASM_EXTABLE_UA(9999b, 6001f)
#define DST(y...) \
9999: y; \
- _ASM_EXTABLE(9999b, 6002f)
+ _ASM_EXTABLE_UA(9999b, 6002f)
#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 020f75cc8cf6..db4e5aa0858b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -92,26 +92,26 @@ ENTRY(copy_user_generic_unrolled)
60: jmp copy_user_handle_tail /* ecx is zerorest also */
.previous
- _ASM_EXTABLE(1b,30b)
- _ASM_EXTABLE(2b,30b)
- _ASM_EXTABLE(3b,30b)
- _ASM_EXTABLE(4b,30b)
- _ASM_EXTABLE(5b,30b)
- _ASM_EXTABLE(6b,30b)
- _ASM_EXTABLE(7b,30b)
- _ASM_EXTABLE(8b,30b)
- _ASM_EXTABLE(9b,30b)
- _ASM_EXTABLE(10b,30b)
- _ASM_EXTABLE(11b,30b)
- _ASM_EXTABLE(12b,30b)
- _ASM_EXTABLE(13b,30b)
- _ASM_EXTABLE(14b,30b)
- _ASM_EXTABLE(15b,30b)
- _ASM_EXTABLE(16b,30b)
- _ASM_EXTABLE(18b,40b)
- _ASM_EXTABLE(19b,40b)
- _ASM_EXTABLE(21b,50b)
- _ASM_EXTABLE(22b,50b)
+ _ASM_EXTABLE_UA(1b, 30b)
+ _ASM_EXTABLE_UA(2b, 30b)
+ _ASM_EXTABLE_UA(3b, 30b)
+ _ASM_EXTABLE_UA(4b, 30b)
+ _ASM_EXTABLE_UA(5b, 30b)
+ _ASM_EXTABLE_UA(6b, 30b)
+ _ASM_EXTABLE_UA(7b, 30b)
+ _ASM_EXTABLE_UA(8b, 30b)
+ _ASM_EXTABLE_UA(9b, 30b)
+ _ASM_EXTABLE_UA(10b, 30b)
+ _ASM_EXTABLE_UA(11b, 30b)
+ _ASM_EXTABLE_UA(12b, 30b)
+ _ASM_EXTABLE_UA(13b, 30b)
+ _ASM_EXTABLE_UA(14b, 30b)
+ _ASM_EXTABLE_UA(15b, 30b)
+ _ASM_EXTABLE_UA(16b, 30b)
+ _ASM_EXTABLE_UA(18b, 40b)
+ _ASM_EXTABLE_UA(19b, 40b)
+ _ASM_EXTABLE_UA(21b, 50b)
+ _ASM_EXTABLE_UA(22b, 50b)
ENDPROC(copy_user_generic_unrolled)
EXPORT_SYMBOL(copy_user_generic_unrolled)
@@ -156,8 +156,8 @@ ENTRY(copy_user_generic_string)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,11b)
- _ASM_EXTABLE(3b,12b)
+ _ASM_EXTABLE_UA(1b, 11b)
+ _ASM_EXTABLE_UA(3b, 12b)
ENDPROC(copy_user_generic_string)
EXPORT_SYMBOL(copy_user_generic_string)
@@ -189,7 +189,7 @@ ENTRY(copy_user_enhanced_fast_string)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,12b)
+ _ASM_EXTABLE_UA(1b, 12b)
ENDPROC(copy_user_enhanced_fast_string)
EXPORT_SYMBOL(copy_user_enhanced_fast_string)
@@ -319,27 +319,27 @@ ENTRY(__copy_user_nocache)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(20b,.L_fixup_8b_copy)
- _ASM_EXTABLE(21b,.L_fixup_8b_copy)
- _ASM_EXTABLE(30b,.L_fixup_4b_copy)
- _ASM_EXTABLE(31b,.L_fixup_4b_copy)
- _ASM_EXTABLE(40b,.L_fixup_1b_copy)
- _ASM_EXTABLE(41b,.L_fixup_1b_copy)
+ _ASM_EXTABLE_UA(1b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(2b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(3b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(4b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(5b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(6b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(7b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(8b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(9b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(10b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(11b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(12b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(13b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(14b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(15b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(16b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(20b, .L_fixup_8b_copy)
+ _ASM_EXTABLE_UA(21b, .L_fixup_8b_copy)
+ _ASM_EXTABLE_UA(30b, .L_fixup_4b_copy)
+ _ASM_EXTABLE_UA(31b, .L_fixup_4b_copy)
+ _ASM_EXTABLE_UA(40b, .L_fixup_1b_copy)
+ _ASM_EXTABLE_UA(41b, .L_fixup_1b_copy)
ENDPROC(__copy_user_nocache)
EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 45a53dfe1859..a4a379e79259 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -31,14 +31,18 @@
.macro source
10:
- _ASM_EXTABLE(10b, .Lbad_source)
+ _ASM_EXTABLE_UA(10b, .Lbad_source)
.endm
.macro dest
20:
- _ASM_EXTABLE(20b, .Lbad_dest)
+ _ASM_EXTABLE_UA(20b, .Lbad_dest)
.endm
+ /*
+ * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
+ * potentially unmapped kernel address.
+ */
.macro ignore L=.Lignore
30:
_ASM_EXTABLE(30b, \L)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 49b167f73215..74fdff968ea3 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -132,12 +132,12 @@ bad_get_user_8:
END(bad_get_user_8)
#endif
- _ASM_EXTABLE(1b,bad_get_user)
- _ASM_EXTABLE(2b,bad_get_user)
- _ASM_EXTABLE(3b,bad_get_user)
+ _ASM_EXTABLE_UA(1b, bad_get_user)
+ _ASM_EXTABLE_UA(2b, bad_get_user)
+ _ASM_EXTABLE_UA(3b, bad_get_user)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(4b,bad_get_user)
+ _ASM_EXTABLE_UA(4b, bad_get_user)
#else
- _ASM_EXTABLE(4b,bad_get_user_8)
- _ASM_EXTABLE(5b,bad_get_user_8)
+ _ASM_EXTABLE_UA(4b, bad_get_user_8)
+ _ASM_EXTABLE_UA(5b, bad_get_user_8)
#endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 96dce5fe2a35..d2e5c9c39601 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -94,10 +94,10 @@ bad_put_user:
EXIT
END(bad_put_user)
- _ASM_EXTABLE(1b,bad_put_user)
- _ASM_EXTABLE(2b,bad_put_user)
- _ASM_EXTABLE(3b,bad_put_user)
- _ASM_EXTABLE(4b,bad_put_user)
+ _ASM_EXTABLE_UA(1b, bad_put_user)
+ _ASM_EXTABLE_UA(2b, bad_put_user)
+ _ASM_EXTABLE_UA(3b, bad_put_user)
+ _ASM_EXTABLE_UA(4b, bad_put_user)
#ifdef CONFIG_X86_32
- _ASM_EXTABLE(5b,bad_put_user)
+ _ASM_EXTABLE_UA(5b, bad_put_user)
#endif
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7add8ba06887..71fb58d44d58 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -47,8 +47,8 @@ do { \
"3: lea 0(%2,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,2b) \
+ _ASM_EXTABLE_UA(0b, 3b) \
+ _ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0) \
: "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
} while (0)
@@ -153,44 +153,44 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
"101: lea 0(%%eax,%0,4),%0\n"
" jmp 100b\n"
".previous\n"
- _ASM_EXTABLE(1b,100b)
- _ASM_EXTABLE(2b,100b)
- _ASM_EXTABLE(3b,100b)
- _ASM_EXTABLE(4b,100b)
- _ASM_EXTABLE(5b,100b)
- _ASM_EXTABLE(6b,100b)
- _ASM_EXTABLE(7b,100b)
- _ASM_EXTABLE(8b,100b)
- _ASM_EXTABLE(9b,100b)
- _ASM_EXTABLE(10b,100b)
- _ASM_EXTABLE(11b,100b)
- _ASM_EXTABLE(12b,100b)
- _ASM_EXTABLE(13b,100b)
- _ASM_EXTABLE(14b,100b)
- _ASM_EXTABLE(15b,100b)
- _ASM_EXTABLE(16b,100b)
- _ASM_EXTABLE(17b,100b)
- _ASM_EXTABLE(18b,100b)
- _ASM_EXTABLE(19b,100b)
- _ASM_EXTABLE(20b,100b)
- _ASM_EXTABLE(21b,100b)
- _ASM_EXTABLE(22b,100b)
- _ASM_EXTABLE(23b,100b)
- _ASM_EXTABLE(24b,100b)
- _ASM_EXTABLE(25b,100b)
- _ASM_EXTABLE(26b,100b)
- _ASM_EXTABLE(27b,100b)
- _ASM_EXTABLE(28b,100b)
- _ASM_EXTABLE(29b,100b)
- _ASM_EXTABLE(30b,100b)
- _ASM_EXTABLE(31b,100b)
- _ASM_EXTABLE(32b,100b)
- _ASM_EXTABLE(33b,100b)
- _ASM_EXTABLE(34b,100b)
- _ASM_EXTABLE(35b,100b)
- _ASM_EXTABLE(36b,100b)
- _ASM_EXTABLE(37b,100b)
- _ASM_EXTABLE(99b,101b)
+ _ASM_EXTABLE_UA(1b, 100b)
+ _ASM_EXTABLE_UA(2b, 100b)
+ _ASM_EXTABLE_UA(3b, 100b)
+ _ASM_EXTABLE_UA(4b, 100b)
+ _ASM_EXTABLE_UA(5b, 100b)
+ _ASM_EXTABLE_UA(6b, 100b)
+ _ASM_EXTABLE_UA(7b, 100b)
+ _ASM_EXTABLE_UA(8b, 100b)
+ _ASM_EXTABLE_UA(9b, 100b)
+ _ASM_EXTABLE_UA(10b, 100b)
+ _ASM_EXTABLE_UA(11b, 100b)
+ _ASM_EXTABLE_UA(12b, 100b)
+ _ASM_EXTABLE_UA(13b, 100b)
+ _ASM_EXTABLE_UA(14b, 100b)
+ _ASM_EXTABLE_UA(15b, 100b)
+ _ASM_EXTABLE_UA(16b, 100b)
+ _ASM_EXTABLE_UA(17b, 100b)
+ _ASM_EXTABLE_UA(18b, 100b)
+ _ASM_EXTABLE_UA(19b, 100b)
+ _ASM_EXTABLE_UA(20b, 100b)
+ _ASM_EXTABLE_UA(21b, 100b)
+ _ASM_EXTABLE_UA(22b, 100b)
+ _ASM_EXTABLE_UA(23b, 100b)
+ _ASM_EXTABLE_UA(24b, 100b)
+ _ASM_EXTABLE_UA(25b, 100b)
+ _ASM_EXTABLE_UA(26b, 100b)
+ _ASM_EXTABLE_UA(27b, 100b)
+ _ASM_EXTABLE_UA(28b, 100b)
+ _ASM_EXTABLE_UA(29b, 100b)
+ _ASM_EXTABLE_UA(30b, 100b)
+ _ASM_EXTABLE_UA(31b, 100b)
+ _ASM_EXTABLE_UA(32b, 100b)
+ _ASM_EXTABLE_UA(33b, 100b)
+ _ASM_EXTABLE_UA(34b, 100b)
+ _ASM_EXTABLE_UA(35b, 100b)
+ _ASM_EXTABLE_UA(36b, 100b)
+ _ASM_EXTABLE_UA(37b, 100b)
+ _ASM_EXTABLE_UA(99b, 101b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
@@ -259,26 +259,26 @@ static unsigned long __copy_user_intel_nocache(void *to,
"9: lea 0(%%eax,%0,4),%0\n"
"16: jmp 8b\n"
".previous\n"
- _ASM_EXTABLE(0b,16b)
- _ASM_EXTABLE(1b,16b)
- _ASM_EXTABLE(2b,16b)
- _ASM_EXTABLE(21b,16b)
- _ASM_EXTABLE(3b,16b)
- _ASM_EXTABLE(31b,16b)
- _ASM_EXTABLE(4b,16b)
- _ASM_EXTABLE(41b,16b)
- _ASM_EXTABLE(10b,16b)
- _ASM_EXTABLE(51b,16b)
- _ASM_EXTABLE(11b,16b)
- _ASM_EXTABLE(61b,16b)
- _ASM_EXTABLE(12b,16b)
- _ASM_EXTABLE(71b,16b)
- _ASM_EXTABLE(13b,16b)
- _ASM_EXTABLE(81b,16b)
- _ASM_EXTABLE(14b,16b)
- _ASM_EXTABLE(91b,16b)
- _ASM_EXTABLE(6b,9b)
- _ASM_EXTABLE(7b,16b)
+ _ASM_EXTABLE_UA(0b, 16b)
+ _ASM_EXTABLE_UA(1b, 16b)
+ _ASM_EXTABLE_UA(2b, 16b)
+ _ASM_EXTABLE_UA(21b, 16b)
+ _ASM_EXTABLE_UA(3b, 16b)
+ _ASM_EXTABLE_UA(31b, 16b)
+ _ASM_EXTABLE_UA(4b, 16b)
+ _ASM_EXTABLE_UA(41b, 16b)
+ _ASM_EXTABLE_UA(10b, 16b)
+ _ASM_EXTABLE_UA(51b, 16b)
+ _ASM_EXTABLE_UA(11b, 16b)
+ _ASM_EXTABLE_UA(61b, 16b)
+ _ASM_EXTABLE_UA(12b, 16b)
+ _ASM_EXTABLE_UA(71b, 16b)
+ _ASM_EXTABLE_UA(13b, 16b)
+ _ASM_EXTABLE_UA(81b, 16b)
+ _ASM_EXTABLE_UA(14b, 16b)
+ _ASM_EXTABLE_UA(91b, 16b)
+ _ASM_EXTABLE_UA(6b, 9b)
+ _ASM_EXTABLE_UA(7b, 16b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
@@ -321,9 +321,9 @@ do { \
"3: lea 0(%3,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(4b,5b) \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,2b) \
+ _ASM_EXTABLE_UA(4b, 5b) \
+ _ASM_EXTABLE_UA(0b, 3b) \
+ _ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
: "3"(size), "0"(size), "1"(to), "2"(from) \
: "memory"); \
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 9c5606d88f61..1bd837cdc4b1 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -37,8 +37,8 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
"3: lea 0(%[size1],%[size8],8),%[size8]\n"
" jmp 2b\n"
".previous\n"
- _ASM_EXTABLE(0b,3b)
- _ASM_EXTABLE(1b,2b)
+ _ASM_EXTABLE_UA(0b, 3b)
+ _ASM_EXTABLE_UA(1b, 2b)
: [size8] "=&c"(size), [dst] "=&D" (__d0)
: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
clac();
@@ -153,7 +153,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
return rc;
}
-void memcpy_flushcache(void *_dst, const void *_src, size_t size)
+void __memcpy_flushcache(void *_dst, const void *_src, size_t size)
{
unsigned long dest = (unsigned long) _dst;
unsigned long source = (unsigned long) _src;
@@ -216,7 +216,7 @@ void memcpy_flushcache(void *_dst, const void *_src, size_t size)
clean_cache_range((void *) dest, size);
}
}
-EXPORT_SYMBOL_GPL(memcpy_flushcache);
+EXPORT_SYMBOL_GPL(__memcpy_flushcache);
void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
size_t len)
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 076ebdce9bd4..12d7e7fb4efd 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -15,7 +15,6 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage)
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-static DEFINE_PER_CPU(struct kcore_list, kcore_entry_trampoline);
#endif
struct cpu_entry_area *get_cpu_entry_area(int cpu)
@@ -83,8 +82,6 @@ static void percpu_setup_debug_store(int cpu)
static void __init setup_cpu_entry_area(int cpu)
{
#ifdef CONFIG_X86_64
- extern char _entry_trampoline[];
-
/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
pgprot_t gdt_prot = PAGE_KERNEL_RO;
pgprot_t tss_prot = PAGE_KERNEL_RO;
@@ -146,43 +143,10 @@ static void __init setup_cpu_entry_area(int cpu)
cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
&per_cpu(exception_stacks, cpu),
sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
-
- cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
- __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
- /*
- * The cpu_entry_area alias addresses are not in the kernel binary
- * so they do not show up in /proc/kcore normally. This adds entries
- * for them manually.
- */
- kclist_add_remap(&per_cpu(kcore_entry_trampoline, cpu),
- _entry_trampoline,
- &get_cpu_entry_area(cpu)->entry_trampoline, PAGE_SIZE);
#endif
percpu_setup_debug_store(cpu);
}
-#ifdef CONFIG_X86_64
-int arch_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
- char *name)
-{
- unsigned int cpu, ncpu = 0;
-
- if (symnum >= num_possible_cpus())
- return -EINVAL;
-
- for_each_possible_cpu(cpu) {
- if (ncpu++ >= symnum)
- break;
- }
-
- *value = (unsigned long)&get_cpu_entry_area(cpu)->entry_trampoline;
- *type = 't';
- strlcpy(name, "__entry_SYSCALL_64_trampoline", KSYM_NAME_LEN);
-
- return 0;
-}
-#endif
-
static __init void setup_cpu_entry_area_ptes(void)
{
#ifdef CONFIG_X86_32
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index a12afff146d1..fc37bbd23eb8 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -19,7 +19,9 @@
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
+#include <linux/pci.h>
+#include <asm/e820/types.h>
#include <asm/pgtable.h>
/*
@@ -241,6 +243,29 @@ static unsigned long normalize_addr(unsigned long u)
return (signed long)(u << shift) >> shift;
}
+static void note_wx(struct pg_state *st)
+{
+ unsigned long npages;
+
+ npages = (st->current_address - st->start_address) / PAGE_SIZE;
+
+#ifdef CONFIG_PCI_BIOS
+ /*
+ * If PCI BIOS is enabled, the PCI BIOS area is forced to WX.
+ * Inform about it, but avoid the warning.
+ */
+ if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN &&
+ st->current_address <= PAGE_OFFSET + BIOS_END) {
+ pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages);
+ return;
+ }
+#endif
+ /* Account the WX pages */
+ st->wx_pages += npages;
+ WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n",
+ (void *)st->start_address);
+}
+
/*
* This function gets called on a break in a continuous series
* of PTE entries; the next one is different so we need to
@@ -276,14 +301,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
unsigned long delta;
int width = sizeof(unsigned long) * 2;
- if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX)) {
- WARN_ONCE(1,
- "x86/mm: Found insecure W+X mapping at address %p/%pS\n",
- (void *)st->start_address,
- (void *)st->start_address);
- st->wx_pages += (st->current_address -
- st->start_address) / PAGE_SIZE;
- }
+ if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX))
+ note_wx(st);
/*
* Now print the actual finished series
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 45f5d6cf65ae..6521134057e8 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -8,7 +8,8 @@
#include <asm/kdebug.h>
typedef bool (*ex_handler_t)(const struct exception_table_entry *,
- struct pt_regs *, int);
+ struct pt_regs *, int, unsigned long,
+ unsigned long);
static inline unsigned long
ex_fixup_addr(const struct exception_table_entry *x)
@@ -22,7 +23,9 @@ ex_fixup_handler(const struct exception_table_entry *x)
}
__visible bool ex_handler_default(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
return true;
@@ -30,7 +33,9 @@ __visible bool ex_handler_default(const struct exception_table_entry *fixup,
EXPORT_SYMBOL(ex_handler_default);
__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
@@ -43,7 +48,9 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
* result of a refcount inc/dec/add/sub.
*/
__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
/* First unconditionally saturate the refcount. */
*(int *)regs->cx = INT_MIN / 2;
@@ -96,7 +103,9 @@ EXPORT_SYMBOL(ex_handler_refcount);
* out all the FPU registers) if we can't restore from the task's FPU state.
*/
__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
@@ -108,9 +117,79 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+/* Helper to check whether a uaccess fault indicates a kernel bug. */
+static bool bogus_uaccess(struct pt_regs *regs, int trapnr,
+ unsigned long fault_addr)
+{
+ /* This is the normal case: #PF with a fault address in userspace. */
+ if (trapnr == X86_TRAP_PF && fault_addr < TASK_SIZE_MAX)
+ return false;
+
+ /*
+ * This code can be reached for machine checks, but only if the #MC
+ * handler has already decided that it looks like a candidate for fixup.
+ * This e.g. happens when attempting to access userspace memory which
+ * the CPU can't access because of uncorrectable bad memory.
+ */
+ if (trapnr == X86_TRAP_MC)
+ return false;
+
+ /*
+ * There are two remaining exception types we might encounter here:
+ * - #PF for faulting accesses to kernel addresses
+ * - #GP for faulting accesses to noncanonical addresses
+ * Complain about anything else.
+ */
+ if (trapnr != X86_TRAP_PF && trapnr != X86_TRAP_GP) {
+ WARN(1, "unexpected trap %d in uaccess\n", trapnr);
+ return false;
+ }
+
+ /*
+ * This is a faulting memory access in kernel space, on a kernel
+ * address, in a usercopy function. This can e.g. be caused by improper
+ * use of helpers like __put_user and by improper attempts to access
+ * userspace addresses in KERNEL_DS regions.
+ * The one (semi-)legitimate exception are probe_kernel_{read,write}(),
+ * which can be invoked from places like kgdb, /dev/mem (for reading)
+ * and privileged BPF code (for reading).
+ * The probe_kernel_*() functions set the kernel_uaccess_faults_ok flag
+ * to tell us that faulting on kernel addresses, and even noncanonical
+ * addresses, in a userspace accessor does not necessarily imply a
+ * kernel bug, root might just be doing weird stuff.
+ */
+ if (current->kernel_uaccess_faults_ok)
+ return false;
+
+ /* This is bad. Refuse the fixup so that we go into die(). */
+ if (trapnr == X86_TRAP_PF) {
+ pr_emerg("BUG: pagefault on kernel address 0x%lx in non-whitelisted uaccess\n",
+ fault_addr);
+ } else {
+ pr_emerg("BUG: GPF in non-whitelisted uaccess (non-canonical address?)\n");
+ }
+ return true;
+}
+
+__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
+{
+ if (bogus_uaccess(regs, trapnr, fault_addr))
+ return false;
+ regs->ip = ex_fixup_addr(fixup);
+ return true;
+}
+EXPORT_SYMBOL(ex_handler_uaccess);
+
__visible bool ex_handler_ext(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
+ if (bogus_uaccess(regs, trapnr, fault_addr))
+ return false;
/* Special hack for uaccess_err */
current->thread.uaccess_err = 1;
regs->ip = ex_fixup_addr(fixup);
@@ -119,7 +198,9 @@ __visible bool ex_handler_ext(const struct exception_table_entry *fixup,
EXPORT_SYMBOL(ex_handler_ext);
__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
@@ -134,7 +215,9 @@ __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup
EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, (unsigned int)regs->dx,
@@ -148,12 +231,14 @@ __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup
EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (static_cpu_has(X86_BUG_NULL_SEG))
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
asm volatile ("mov %0, %%fs" : : "rm" (0));
- return ex_handler_default(fixup, regs, trapnr);
+ return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr);
}
EXPORT_SYMBOL(ex_handler_clear_fs);
@@ -170,7 +255,8 @@ __visible bool ex_has_fault_handler(unsigned long ip)
return handler == ex_handler_fault;
}
-int fixup_exception(struct pt_regs *regs, int trapnr)
+int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
+ unsigned long fault_addr)
{
const struct exception_table_entry *e;
ex_handler_t handler;
@@ -194,7 +280,7 @@ int fixup_exception(struct pt_regs *regs, int trapnr)
return 0;
handler = ex_fixup_handler(e);
- return handler(e, regs, trapnr);
+ return handler(e, regs, trapnr, error_code, fault_addr);
}
extern unsigned int early_recursion_flag;
@@ -230,9 +316,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
* result in a hard-to-debug panic.
*
* Keep in mind that not all vectors actually get here. Early
- * fage faults, for example, are special.
+ * page faults, for example, are special.
*/
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, regs->orig_ax, 0))
return;
if (fixup_bug(regs, trapnr))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 47bebfe6efa7..b24eb4eb9984 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -16,6 +16,7 @@
#include <linux/prefetch.h> /* prefetchw */
#include <linux/context_tracking.h> /* exception_enter(), ... */
#include <linux/uaccess.h> /* faulthandler_disabled() */
+#include <linux/efi.h> /* efi_recover_from_page_fault()*/
#include <linux/mm_types.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
@@ -25,6 +26,7 @@
#include <asm/vsyscall.h> /* emulate_vsyscall */
#include <asm/vm86.h> /* struct vm86 */
#include <asm/mmu_context.h> /* vma_pkey() */
+#include <asm/efi.h> /* efi_recover_from_page_fault()*/
#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>
@@ -44,17 +46,19 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
static nokprobe_inline int kprobes_fault(struct pt_regs *regs)
{
- int ret = 0;
-
- /* kprobe_running() needs smp_processor_id() */
- if (kprobes_built_in() && !user_mode(regs)) {
- preempt_disable();
- if (kprobe_running() && kprobe_fault_handler(regs, 14))
- ret = 1;
- preempt_enable();
- }
-
- return ret;
+ if (!kprobes_built_in())
+ return 0;
+ if (user_mode(regs))
+ return 0;
+ /*
+ * To be potentially processing a kprobe fault and to be allowed to call
+ * kprobe_running(), we have to be non-preemptible.
+ */
+ if (preemptible())
+ return 0;
+ if (!kprobe_running())
+ return 0;
+ return kprobe_fault_handler(regs, X86_TRAP_PF);
}
/*
@@ -153,79 +157,6 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
return prefetch;
}
-/*
- * A protection key fault means that the PKRU value did not allow
- * access to some PTE. Userspace can figure out what PKRU was
- * from the XSAVE state, and this function fills out a field in
- * siginfo so userspace can discover which protection key was set
- * on the PTE.
- *
- * If we get here, we know that the hardware signaled a X86_PF_PK
- * fault and that there was a VMA once we got in the fault
- * handler. It does *not* guarantee that the VMA we find here
- * was the one that we faulted on.
- *
- * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4);
- * 2. T1 : set PKRU to deny access to pkey=4, touches page
- * 3. T1 : faults...
- * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
- * 5. T1 : enters fault handler, takes mmap_sem, etc...
- * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
- * faulted on a pte with its pkey=4.
- */
-static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info,
- u32 *pkey)
-{
- /* This is effectively an #ifdef */
- if (!boot_cpu_has(X86_FEATURE_OSPKE))
- return;
-
- /* Fault not from Protection Keys: nothing to do */
- if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV))
- return;
- /*
- * force_sig_info_fault() is called from a number of
- * contexts, some of which have a VMA and some of which
- * do not. The X86_PF_PK handing happens after we have a
- * valid VMA, so we should never reach this without a
- * valid VMA.
- */
- if (!pkey) {
- WARN_ONCE(1, "PKU fault with no VMA passed in");
- info->si_pkey = 0;
- return;
- }
- /*
- * si_pkey should be thought of as a strong hint, but not
- * absolutely guranteed to be 100% accurate because of
- * the race explained above.
- */
- info->si_pkey = *pkey;
-}
-
-static void
-force_sig_info_fault(int si_signo, int si_code, unsigned long address,
- struct task_struct *tsk, u32 *pkey, int fault)
-{
- unsigned lsb = 0;
- siginfo_t info;
-
- clear_siginfo(&info);
- info.si_signo = si_signo;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *)address;
- if (fault & VM_FAULT_HWPOISON_LARGE)
- lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
- if (fault & VM_FAULT_HWPOISON)
- lsb = PAGE_SHIFT;
- info.si_addr_lsb = lsb;
-
- fill_sig_info_pkey(si_signo, si_code, &info, pkey);
-
- force_sig_info(si_signo, &info, tsk);
-}
-
DEFINE_SPINLOCK(pgd_lock);
LIST_HEAD(pgd_list);
@@ -709,7 +640,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
int sig;
/* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs, X86_TRAP_PF)) {
+ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
/*
* Any interrupt that takes a fault gets the fixup. This makes
* the below recursive fault logic only apply to a faults from
@@ -730,8 +661,8 @@ no_context(struct pt_regs *regs, unsigned long error_code,
tsk->thread.cr2 = address;
/* XXX: hwpoison faults will set the wrong code. */
- force_sig_info_fault(signal, si_code, address,
- tsk, NULL, 0);
+ force_sig_fault(signal, si_code, (void __user *)address,
+ tsk);
}
/*
@@ -789,6 +720,13 @@ no_context(struct pt_regs *regs, unsigned long error_code,
return;
/*
+ * Buggy firmware could access regions which might page fault, try to
+ * recover from such faults.
+ */
+ if (IS_ENABLED(CONFIG_EFI))
+ efi_recover_from_page_fault(address);
+
+ /*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice:
*/
@@ -840,9 +778,18 @@ 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)
+ unsigned long address, u32 pkey, int si_code)
{
struct task_struct *tsk = current;
@@ -863,18 +810,6 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
if (is_errata100(regs, address))
return;
-#ifdef CONFIG_X86_64
- /*
- * Instruction fetch faults in the vsyscall page might need
- * emulation.
- */
- if (unlikely((error_code & X86_PF_INSTR) &&
- ((address & ~0xfff) == VSYSCALL_ADDR))) {
- if (emulate_vsyscall(regs, address))
- return;
- }
-#endif
-
/*
* To avoid leaking information about the kernel page table
* layout, pretend that user-mode accesses to kernel addresses
@@ -890,7 +825,10 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_PF;
- force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
+ if (si_code == SEGV_PKUERR)
+ force_sig_pkuerr((void __user *)address, pkey);
+
+ force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
return;
}
@@ -903,35 +841,29 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
static noinline void
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, u32 *pkey)
+ unsigned long address)
{
- __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
+ __bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR);
}
static void
__bad_area(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma, int si_code)
+ unsigned long address, u32 pkey, int si_code)
{
struct mm_struct *mm = current->mm;
- u32 pkey;
-
- if (vma)
- pkey = vma_pkey(vma);
-
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
up_read(&mm->mmap_sem);
- __bad_area_nosemaphore(regs, error_code, address,
- (vma) ? &pkey : NULL, si_code);
+ __bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
}
static noinline void
bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
- __bad_area(regs, error_code, address, NULL, SEGV_MAPERR);
+ __bad_area(regs, error_code, address, 0, SEGV_MAPERR);
}
static inline bool bad_area_access_from_pkeys(unsigned long error_code,
@@ -960,18 +892,40 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
* But, doing it this way allows compiler optimizations
* if pkeys are compiled out.
*/
- if (bad_area_access_from_pkeys(error_code, vma))
- __bad_area(regs, error_code, address, vma, SEGV_PKUERR);
- else
- __bad_area(regs, error_code, address, vma, SEGV_ACCERR);
+ if (bad_area_access_from_pkeys(error_code, vma)) {
+ /*
+ * A protection key fault means that the PKRU value did not allow
+ * access to some PTE. Userspace can figure out what PKRU was
+ * from the XSAVE state. This function captures the pkey from
+ * the vma and passes it to userspace so userspace can discover
+ * which protection key was set on the PTE.
+ *
+ * If we get here, we know that the hardware signaled a X86_PF_PK
+ * fault and that there was a VMA once we got in the fault
+ * handler. It does *not* guarantee that the VMA we find here
+ * was the one that we faulted on.
+ *
+ * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4);
+ * 2. T1 : set PKRU to deny access to pkey=4, touches page
+ * 3. T1 : faults...
+ * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
+ * 5. T1 : enters fault handler, takes mmap_sem, etc...
+ * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
+ * faulted on a pte with its pkey=4.
+ */
+ u32 pkey = vma_pkey(vma);
+
+ __bad_area(regs, error_code, address, pkey, SEGV_PKUERR);
+ } else {
+ __bad_area(regs, error_code, address, 0, SEGV_ACCERR);
+ }
}
static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
- u32 *pkey, unsigned int fault)
+ unsigned int fault)
{
struct task_struct *tsk = current;
- int code = BUS_ADRERR;
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & X86_PF_USER)) {
@@ -989,18 +943,25 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
#ifdef CONFIG_MEMORY_FAILURE
if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
- printk(KERN_ERR
+ unsigned lsb = 0;
+
+ pr_err(
"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
tsk->comm, tsk->pid, address);
- code = BUS_MCEERR_AR;
+ if (fault & VM_FAULT_HWPOISON_LARGE)
+ lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+ if (fault & VM_FAULT_HWPOISON)
+ lsb = PAGE_SHIFT;
+ force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, tsk);
+ return;
}
#endif
- force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
}
static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, u32 *pkey, vm_fault_t fault)
+ unsigned long address, vm_fault_t fault)
{
if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) {
no_context(regs, error_code, address, 0, 0);
@@ -1024,27 +985,21 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
- do_sigbus(regs, error_code, address, pkey, fault);
+ do_sigbus(regs, error_code, address, fault);
else if (fault & VM_FAULT_SIGSEGV)
- bad_area_nosemaphore(regs, error_code, address, pkey);
+ bad_area_nosemaphore(regs, error_code, address);
else
BUG();
}
}
-static int spurious_fault_check(unsigned long error_code, pte_t *pte)
+static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte)
{
if ((error_code & X86_PF_WRITE) && !pte_write(*pte))
return 0;
if ((error_code & X86_PF_INSTR) && !pte_exec(*pte))
return 0;
- /*
- * Note: We do not do lazy flushing on protection key
- * changes, so no spurious fault will ever set X86_PF_PK.
- */
- if ((error_code & X86_PF_PK))
- return 1;
return 1;
}
@@ -1071,7 +1026,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
* (Optional Invalidation).
*/
static noinline int
-spurious_fault(unsigned long error_code, unsigned long address)
+spurious_kernel_fault(unsigned long error_code, unsigned long address)
{
pgd_t *pgd;
p4d_t *p4d;
@@ -1102,27 +1057,27 @@ spurious_fault(unsigned long error_code, unsigned long address)
return 0;
if (p4d_large(*p4d))
- return spurious_fault_check(error_code, (pte_t *) p4d);
+ return spurious_kernel_fault_check(error_code, (pte_t *) p4d);
pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return 0;
if (pud_large(*pud))
- return spurious_fault_check(error_code, (pte_t *) pud);
+ return spurious_kernel_fault_check(error_code, (pte_t *) pud);
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return 0;
if (pmd_large(*pmd))
- return spurious_fault_check(error_code, (pte_t *) pmd);
+ return spurious_kernel_fault_check(error_code, (pte_t *) pmd);
pte = pte_offset_kernel(pmd, address);
if (!pte_present(*pte))
return 0;
- ret = spurious_fault_check(error_code, pte);
+ ret = spurious_kernel_fault_check(error_code, pte);
if (!ret)
return 0;
@@ -1130,12 +1085,12 @@ spurious_fault(unsigned long error_code, unsigned long address)
* Make sure we have permissions in PMD.
* If not, then there's a bug in the page tables:
*/
- ret = spurious_fault_check(error_code, (pte_t *) pmd);
+ ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd);
WARN_ONCE(!ret, "PMD has incorrect permission bits\n");
return ret;
}
-NOKPROBE_SYMBOL(spurious_fault);
+NOKPROBE_SYMBOL(spurious_kernel_fault);
int show_unhandled_signals = 1;
@@ -1182,6 +1137,14 @@ access_error(unsigned long error_code, struct vm_area_struct *vma)
static int fault_in_kernel_space(unsigned long address)
{
+ /*
+ * On 64-bit systems, the vsyscall page is at an address above
+ * TASK_SIZE_MAX, but is not considered part of the kernel
+ * address space.
+ */
+ if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address))
+ return false;
+
return address >= TASK_SIZE_MAX;
}
@@ -1203,31 +1166,23 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
}
/*
- * This routine handles page faults. It determines the address,
- * and the problem, and then passes it off to one of the appropriate
- * routines.
+ * Called for all faults where 'address' is part of the kernel address
+ * space. Might get called for faults that originate from *code* that
+ * ran in userspace or the kernel.
*/
-static noinline void
-__do_page_fault(struct pt_regs *regs, unsigned long error_code,
- unsigned long address)
+static void
+do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
+ unsigned long address)
{
- struct vm_area_struct *vma;
- struct task_struct *tsk;
- struct mm_struct *mm;
- vm_fault_t fault, major = 0;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
- u32 pkey;
-
- tsk = current;
- mm = tsk->mm;
-
- prefetchw(&mm->mmap_sem);
-
- if (unlikely(kmmio_fault(regs, address)))
- return;
+ /*
+ * Protection keys exceptions only happen on user pages. We
+ * have no user pages in the kernel portion of the address
+ * space, so do not expect them here.
+ */
+ WARN_ON_ONCE(hw_error_code & X86_PF_PK);
/*
- * We fault-in kernel-space virtual memory on-demand. The
+ * We can fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
@@ -1235,41 +1190,73 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
* only copy the information from the master page table,
* nothing more.
*
- * This verifies that the fault happens in kernel space
- * (error_code & 4) == 0, and that the fault was not a
- * protection error (error_code & 9) == 0.
+ * Before doing this on-demand faulting, ensure that the
+ * fault is not any of the following:
+ * 1. A fault on a PTE with a reserved bit set.
+ * 2. A fault caused by a user-mode access. (Do not demand-
+ * fault kernel memory due to user-mode accesses).
+ * 3. A fault caused by a page-level protection violation.
+ * (A demand fault would be on a non-present page which
+ * would have X86_PF_PROT==0).
*/
- if (unlikely(fault_in_kernel_space(address))) {
- if (!(error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
- if (vmalloc_fault(address) >= 0)
- return;
- }
-
- /* Can handle a stale RO->RW TLB: */
- if (spurious_fault(error_code, address))
+ if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
+ if (vmalloc_fault(address) >= 0)
return;
+ }
- /* kprobes don't want to hook the spurious faults: */
- if (kprobes_fault(regs))
- return;
- /*
- * Don't take the mm semaphore here. If we fixup a prefetch
- * fault we could otherwise deadlock:
- */
- bad_area_nosemaphore(regs, error_code, address, NULL);
+ /* Was the fault spurious, caused by lazy TLB invalidation? */
+ if (spurious_kernel_fault(hw_error_code, address))
+ return;
+ /* kprobes don't want to hook the spurious faults: */
+ if (kprobes_fault(regs))
return;
- }
+
+ /*
+ * Note, despite being a "bad area", there are quite a few
+ * acceptable reasons to get here, such as erratum fixups
+ * and handling kernel code that can fault, like get_user().
+ *
+ * Don't take the mm semaphore here. If we fixup a prefetch
+ * fault we could otherwise deadlock:
+ */
+ bad_area_nosemaphore(regs, hw_error_code, address);
+}
+NOKPROBE_SYMBOL(do_kern_addr_fault);
+
+/* Handle faults in the user portion of the address space */
+static inline
+void do_user_addr_fault(struct pt_regs *regs,
+ unsigned long hw_error_code,
+ unsigned long address)
+{
+ unsigned long sw_error_code;
+ struct vm_area_struct *vma;
+ struct task_struct *tsk;
+ struct mm_struct *mm;
+ vm_fault_t fault, major = 0;
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+
+ tsk = current;
+ mm = tsk->mm;
/* kprobes don't want to hook the spurious faults: */
if (unlikely(kprobes_fault(regs)))
return;
- if (unlikely(error_code & X86_PF_RSVD))
- pgtable_bad(regs, error_code, address);
+ /*
+ * Reserved bits are never expected to be set on
+ * entries in the user portion of the page tables.
+ */
+ if (unlikely(hw_error_code & X86_PF_RSVD))
+ pgtable_bad(regs, hw_error_code, address);
- if (unlikely(smap_violation(error_code, regs))) {
- bad_area_nosemaphore(regs, error_code, address, NULL);
+ /*
+ * Check for invalid kernel (supervisor) access to user
+ * pages in the user address space.
+ */
+ if (unlikely(smap_violation(hw_error_code, regs))) {
+ bad_area_nosemaphore(regs, hw_error_code, address);
return;
}
@@ -1278,11 +1265,18 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
* in a region with pagefaults disabled then we must not take the fault
*/
if (unlikely(faulthandler_disabled() || !mm)) {
- bad_area_nosemaphore(regs, error_code, address, NULL);
+ bad_area_nosemaphore(regs, hw_error_code, address);
return;
}
/*
+ * hw_error_code is literally the "page fault error code" passed to
+ * the kernel directly from the hardware. But, we will shortly be
+ * modifying it in software, so give it a new name.
+ */
+ sw_error_code = hw_error_code;
+
+ /*
* It's safe to allow irq's after cr2 has been saved and the
* vmalloc fault has been handled.
*
@@ -1291,7 +1285,26 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
*/
if (user_mode(regs)) {
local_irq_enable();
- error_code |= X86_PF_USER;
+ /*
+ * Up to this point, X86_PF_USER set in hw_error_code
+ * indicated a user-mode access. But, after this,
+ * X86_PF_USER in sw_error_code will indicate either
+ * that, *or* an implicit kernel(supervisor)-mode access
+ * which originated from user mode.
+ */
+ if (!(hw_error_code & X86_PF_USER)) {
+ /*
+ * The CPU was in user mode, but the CPU says
+ * the fault was not a user-mode access.
+ * Must be an implicit kernel-mode access,
+ * which we do not expect to happen in the
+ * user address space.
+ */
+ pr_warn_once("kernel-mode error from user-mode: %lx\n",
+ hw_error_code);
+
+ sw_error_code |= X86_PF_USER;
+ }
flags |= FAULT_FLAG_USER;
} else {
if (regs->flags & X86_EFLAGS_IF)
@@ -1300,31 +1313,49 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
- if (error_code & X86_PF_WRITE)
+ if (sw_error_code & X86_PF_WRITE)
flags |= FAULT_FLAG_WRITE;
- if (error_code & X86_PF_INSTR)
+ if (sw_error_code & X86_PF_INSTR)
flags |= FAULT_FLAG_INSTRUCTION;
+#ifdef CONFIG_X86_64
+ /*
+ * Instruction fetch faults in the vsyscall page might need
+ * emulation. The vsyscall page is at a high address
+ * (>PAGE_OFFSET), but is considered to be part of the user
+ * address space.
+ *
+ * The vsyscall page does not have a "real" VMA, so do this
+ * emulation before we go searching for VMAs.
+ */
+ if ((sw_error_code & X86_PF_INSTR) && is_vsyscall_vaddr(address)) {
+ if (emulate_vsyscall(regs, address))
+ return;
+ }
+#endif
+
/*
- * When running in the kernel we expect faults to occur only to
- * addresses in user space. All other faults represent errors in
- * the kernel and should generate an OOPS. Unfortunately, in the
- * case of an erroneous fault occurring in a code path which already
- * holds mmap_sem we will deadlock attempting to validate the fault
- * against the address space. Luckily the kernel only validly
- * references user space from well defined areas of code, which are
- * listed in the exceptions table.
+ * Kernel-mode access to the user address space should only occur
+ * on well-defined single instructions listed in the exception
+ * tables. But, an erroneous kernel fault occurring outside one of
+ * those areas which also holds mmap_sem might deadlock attempting
+ * to validate the fault against the address space.
*
- * As the vast majority of faults will be valid we will only perform
- * the source reference check when there is a possibility of a
- * deadlock. Attempt to lock the address space, if we cannot we then
- * validate the source. If this is invalid we can skip the address
- * space check, thus avoiding the deadlock:
+ * Only do the expensive exception table search when we might be at
+ * risk of a deadlock. This happens if we
+ * 1. Failed to acquire mmap_sem, and
+ * 2. The access did not originate in userspace. Note: either the
+ * hardware or earlier page fault code may set X86_PF_USER
+ * in sw_error_code.
*/
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
- if (!(error_code & X86_PF_USER) &&
+ if (!(sw_error_code & X86_PF_USER) &&
!search_exception_tables(regs->ip)) {
- bad_area_nosemaphore(regs, error_code, address, NULL);
+ /*
+ * Fault from code in kernel from
+ * which we do not expect faults.
+ */
+ bad_area_nosemaphore(regs, sw_error_code, address);
return;
}
retry:
@@ -1340,16 +1371,16 @@ retry:
vma = find_vma(mm, address);
if (unlikely(!vma)) {
- bad_area(regs, error_code, address);
+ bad_area(regs, sw_error_code, address);
return;
}
if (likely(vma->vm_start <= address))
goto good_area;
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
- bad_area(regs, error_code, address);
+ bad_area(regs, sw_error_code, address);
return;
}
- if (error_code & X86_PF_USER) {
+ if (sw_error_code & X86_PF_USER) {
/*
* Accessing the stack below %sp is always a bug.
* The large cushion allows instructions like enter
@@ -1357,12 +1388,12 @@ retry:
* 32 pointers and then decrements %sp by 65535.)
*/
if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
- bad_area(regs, error_code, address);
+ bad_area(regs, sw_error_code, address);
return;
}
}
if (unlikely(expand_stack(vma, address))) {
- bad_area(regs, error_code, address);
+ bad_area(regs, sw_error_code, address);
return;
}
@@ -1371,8 +1402,8 @@ retry:
* we can handle it..
*/
good_area:
- if (unlikely(access_error(error_code, vma))) {
- bad_area_access_error(regs, error_code, address, vma);
+ if (unlikely(access_error(sw_error_code, vma))) {
+ bad_area_access_error(regs, sw_error_code, address, vma);
return;
}
@@ -1388,10 +1419,7 @@ good_area:
* (potentially after handling any pending signal during the return to
* userland). The return to userland is identified whenever
* FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
- * Thus we have to be careful about not touching vma after handling the
- * fault, so we read the pkey beforehand.
*/
- pkey = vma_pkey(vma);
fault = handle_mm_fault(vma, address, flags);
major |= fault & VM_FAULT_MAJOR;
@@ -1414,13 +1442,13 @@ good_area:
return;
/* Not returning to user mode? Handle exceptions or die: */
- no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
+ no_context(regs, sw_error_code, address, SIGBUS, BUS_ADRERR);
return;
}
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
- mm_fault_error(regs, error_code, address, &pkey, fault);
+ mm_fault_error(regs, sw_error_code, address, fault);
return;
}
@@ -1438,6 +1466,28 @@ good_area:
check_v8086_mode(regs, address, tsk);
}
+NOKPROBE_SYMBOL(do_user_addr_fault);
+
+/*
+ * This routine handles page faults. It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ */
+static noinline void
+__do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
+ unsigned long address)
+{
+ prefetchw(&current->mm->mmap_sem);
+
+ if (unlikely(kmmio_fault(regs, address)))
+ return;
+
+ /* Was the fault on kernel-controlled part of the address space? */
+ if (unlikely(fault_in_kernel_space(address)))
+ do_kern_addr_fault(regs, hw_error_code, address);
+ else
+ do_user_addr_fault(regs, hw_error_code, address);
+}
NOKPROBE_SYMBOL(__do_page_fault);
static nokprobe_inline void
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 7a8fc26c1115..faca978ebf9d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end)
set_memory_np_noalias(begin_ul, len_pages);
}
+void __weak mem_encrypt_free_decrypted_mem(void) { }
+
void __ref free_initmem(void)
{
e820__reallocate_tables();
+ mem_encrypt_free_decrypted_mem();
+
free_kernel_image_pages(&__init_begin, &__init_end);
}
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 979e0a02cbe1..142c7d9f89cc 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -923,34 +923,19 @@ static void mark_nxdata_nx(void)
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
- unsigned long size = PFN_ALIGN(_etext) - start;
+ unsigned long size = (unsigned long)__end_rodata - start;
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
- printk(KERN_INFO "Write protecting the kernel text: %luk\n",
+ pr_info("Write protecting kernel text and read-only data: %luk\n",
size >> 10);
kernel_set_to_readonly = 1;
#ifdef CONFIG_CPA_DEBUG
- printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
- start, start+size);
- set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT);
-
- printk(KERN_INFO "Testing CPA: write protecting again\n");
- set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
-#endif
-
- start += size;
- size = (unsigned long)__end_rodata - start;
- set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
- printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
- size >> 10);
-
-#ifdef CONFIG_CPA_DEBUG
- printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, start + size);
+ pr_info("Testing CPA: Reverting %lx-%lx\n", start, start + size);
set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
- printk(KERN_INFO "Testing CPA: write protecting again\n");
+ pr_info("Testing CPA: write protecting again\n");
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
#endif
mark_nxdata_nx();
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index c63a545ec199..24e0920a9b25 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -131,7 +131,8 @@ static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
* caller shouldn't need to know that small detail.
*/
static void __iomem *__ioremap_caller(resource_size_t phys_addr,
- unsigned long size, enum page_cache_mode pcm, void *caller)
+ unsigned long size, enum page_cache_mode pcm,
+ void *caller, bool encrypted)
{
unsigned long offset, vaddr;
resource_size_t last_addr;
@@ -199,7 +200,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
* resulting mapping.
*/
prot = PAGE_KERNEL_IO;
- if (sev_active() && mem_flags.desc_other)
+ if ((sev_active() && mem_flags.desc_other) || encrypted)
prot = pgprot_encrypted(prot);
switch (pcm) {
@@ -291,7 +292,7 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
return __ioremap_caller(phys_addr, size, pcm,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_nocache);
@@ -324,7 +325,7 @@ void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
return __ioremap_caller(phys_addr, size, pcm,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL_GPL(ioremap_uc);
@@ -341,7 +342,7 @@ EXPORT_SYMBOL_GPL(ioremap_uc);
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_wc);
@@ -358,14 +359,21 @@ EXPORT_SYMBOL(ioremap_wc);
void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_wt);
+void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size)
+{
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
+ __builtin_return_address(0), true);
+}
+EXPORT_SYMBOL(ioremap_encrypted);
+
void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_cache);
@@ -374,7 +382,7 @@ void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
{
return __ioremap_caller(phys_addr, size,
pgprot2cachemode(__pgprot(prot_val)),
- __builtin_return_address(0));
+ __builtin_return_address(0), false);
}
EXPORT_SYMBOL(ioremap_prot);
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index b2de398d1fd3..006f373f54ab 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -348,6 +348,30 @@ bool sev_active(void)
EXPORT_SYMBOL(sev_active);
/* Architecture __weak replacement functions */
+void __init mem_encrypt_free_decrypted_mem(void)
+{
+ unsigned long vaddr, vaddr_end, npages;
+ int r;
+
+ vaddr = (unsigned long)__start_bss_decrypted_unused;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+ npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
+
+ /*
+ * The unused memory range was mapped decrypted, change the encryption
+ * attribute from decrypted to encrypted before freeing it.
+ */
+ if (mem_encrypt_active()) {
+ r = set_memory_encrypted(vaddr, npages);
+ if (r) {
+ pr_warn("failed to free unused decrypted pages\n");
+ return;
+ }
+ }
+
+ free_init_pages("unused decrypted", vaddr, vaddr_end);
+}
+
void __init mem_encrypt_init(void)
{
if (!sme_me_mask)
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 7ae36868aed2..a19ef1a416ff 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -27,6 +27,7 @@
* be extended when new paravirt and debugging variants are added.)
*/
#undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_XXL
#undef CONFIG_PARAVIRT_SPINLOCKS
#include <linux/kernel.h>
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index e500949bae24..2385538e8065 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -118,14 +118,11 @@ bad_opcode:
* anything it wants in to the instructions. We can not
* trust anything about it. They might not be valid
* instructions or might encode invalid registers, etc...
- *
- * The caller is expected to kfree() the returned siginfo_t.
*/
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
+int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
{
const struct mpx_bndreg_state *bndregs;
const struct mpx_bndreg *bndreg;
- siginfo_t *info = NULL;
struct insn insn;
uint8_t bndregno;
int err;
@@ -153,11 +150,6 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
/* now go select the individual register in the set of 4 */
bndreg = &bndregs->bndreg[bndregno];
- info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info) {
- err = -ENOMEM;
- goto err_out;
- }
/*
* The registers are always 64-bit, but the upper 32
* bits are ignored in 32-bit mode. Also, note that the
@@ -168,27 +160,23 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
* complains when casting from integers to different-size
* pointers.
*/
- info->si_lower = (void __user *)(unsigned long)bndreg->lower_bound;
- info->si_upper = (void __user *)(unsigned long)~bndreg->upper_bound;
- info->si_addr_lsb = 0;
- info->si_signo = SIGSEGV;
- info->si_errno = 0;
- info->si_code = SEGV_BNDERR;
- info->si_addr = insn_get_addr_ref(&insn, regs);
+ info->lower = (void __user *)(unsigned long)bndreg->lower_bound;
+ info->upper = (void __user *)(unsigned long)~bndreg->upper_bound;
+ info->addr = insn_get_addr_ref(&insn, regs);
+
/*
* We were not able to extract an address from the instruction,
* probably because there was something invalid in it.
*/
- if (info->si_addr == (void __user *)-1) {
+ if (info->addr == (void __user *)-1) {
err = -EINVAL;
goto err_out;
}
- trace_mpx_bounds_register_exception(info->si_addr, bndreg);
- return info;
+ trace_mpx_bounds_register_exception(info->addr, bndreg);
+ return 0;
err_out:
/* info might be NULL, but kfree() handles that */
- kfree(info);
- return ERR_PTR(err);
+ return err;
}
static __user void *mpx_get_bounds_dir(void)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 51a5a69ecac9..62bb30b4bd2a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -37,11 +37,20 @@ struct cpa_data {
unsigned long numpages;
int flags;
unsigned long pfn;
- unsigned force_split : 1;
+ unsigned force_split : 1,
+ force_static_prot : 1;
int curpage;
struct page **pages;
};
+enum cpa_warn {
+ CPA_CONFLICT,
+ CPA_PROTECT,
+ CPA_DETECT,
+};
+
+static const int cpa_warn_level = CPA_PROTECT;
+
/*
* Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings)
* using cpa_lock. So that we don't allow any other cpu, with stale large tlb
@@ -94,6 +103,87 @@ void arch_report_meminfo(struct seq_file *m)
static inline void split_page_count(int level) { }
#endif
+#ifdef CONFIG_X86_CPA_STATISTICS
+
+static unsigned long cpa_1g_checked;
+static unsigned long cpa_1g_sameprot;
+static unsigned long cpa_1g_preserved;
+static unsigned long cpa_2m_checked;
+static unsigned long cpa_2m_sameprot;
+static unsigned long cpa_2m_preserved;
+static unsigned long cpa_4k_install;
+
+static inline void cpa_inc_1g_checked(void)
+{
+ cpa_1g_checked++;
+}
+
+static inline void cpa_inc_2m_checked(void)
+{
+ cpa_2m_checked++;
+}
+
+static inline void cpa_inc_4k_install(void)
+{
+ cpa_4k_install++;
+}
+
+static inline void cpa_inc_lp_sameprot(int level)
+{
+ if (level == PG_LEVEL_1G)
+ cpa_1g_sameprot++;
+ else
+ cpa_2m_sameprot++;
+}
+
+static inline void cpa_inc_lp_preserved(int level)
+{
+ if (level == PG_LEVEL_1G)
+ cpa_1g_preserved++;
+ else
+ cpa_2m_preserved++;
+}
+
+static int cpastats_show(struct seq_file *m, void *p)
+{
+ seq_printf(m, "1G pages checked: %16lu\n", cpa_1g_checked);
+ seq_printf(m, "1G pages sameprot: %16lu\n", cpa_1g_sameprot);
+ seq_printf(m, "1G pages preserved: %16lu\n", cpa_1g_preserved);
+ seq_printf(m, "2M pages checked: %16lu\n", cpa_2m_checked);
+ seq_printf(m, "2M pages sameprot: %16lu\n", cpa_2m_sameprot);
+ seq_printf(m, "2M pages preserved: %16lu\n", cpa_2m_preserved);
+ seq_printf(m, "4K pages set-checked: %16lu\n", cpa_4k_install);
+ return 0;
+}
+
+static int cpastats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, cpastats_show, NULL);
+}
+
+static const struct file_operations cpastats_fops = {
+ .open = cpastats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init cpa_stats_init(void)
+{
+ debugfs_create_file("cpa_stats", S_IRUSR, arch_debugfs_dir, NULL,
+ &cpastats_fops);
+ return 0;
+}
+late_initcall(cpa_stats_init);
+#else
+static inline void cpa_inc_1g_checked(void) { }
+static inline void cpa_inc_2m_checked(void) { }
+static inline void cpa_inc_4k_install(void) { }
+static inline void cpa_inc_lp_sameprot(int level) { }
+static inline void cpa_inc_lp_preserved(int level) { }
+#endif
+
+
static inline int
within(unsigned long addr, unsigned long start, unsigned long end)
{
@@ -195,14 +285,20 @@ static void cpa_flush_all(unsigned long cache)
on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}
-static void __cpa_flush_range(void *arg)
+static bool __cpa_flush_range(unsigned long start, int numpages, int cache)
{
- /*
- * We could optimize that further and do individual per page
- * tlb invalidates for a low number of pages. Caveat: we must
- * flush the high aliases on 64bit as well.
- */
- __flush_tlb_all();
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
+
+ WARN_ON(PAGE_ALIGN(start) != start);
+
+ if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
+ cpa_flush_all(cache);
+ return true;
+ }
+
+ flush_tlb_kernel_range(start, start + PAGE_SIZE * numpages);
+
+ return !cache;
}
static void cpa_flush_range(unsigned long start, int numpages, int cache)
@@ -210,12 +306,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache)
unsigned int i, level;
unsigned long addr;
- BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
- WARN_ON(PAGE_ALIGN(start) != start);
-
- on_each_cpu(__cpa_flush_range, NULL, 1);
-
- if (!cache)
+ if (__cpa_flush_range(start, numpages, cache))
return;
/*
@@ -235,30 +326,13 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache)
}
}
-static void cpa_flush_array(unsigned long *start, int numpages, int cache,
+static void cpa_flush_array(unsigned long baddr, unsigned long *start,
+ int numpages, int cache,
int in_flags, struct page **pages)
{
unsigned int i, level;
-#ifdef CONFIG_PREEMPT
- /*
- * Avoid wbinvd() because it causes latencies on all CPUs,
- * regardless of any CPU isolation that may be in effect.
- *
- * This should be extended for CAT enabled systems independent of
- * PREEMPT because wbinvd() does not respect the CAT partitions and
- * this is exposed to unpriviledged users through the graphics
- * subsystem.
- */
- unsigned long do_wbinvd = 0;
-#else
- unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
-#endif
-
- BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
- on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
-
- if (!cache || do_wbinvd)
+ if (__cpa_flush_range(baddr, numpages, cache))
return;
/*
@@ -286,84 +360,179 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
}
}
-/*
- * Certain areas of memory on x86 require very specific protection flags,
- * for example the BIOS area or kernel text. Callers don't always get this
- * right (again, ioremap() on BIOS memory is not uncommon) so this function
- * checks and fixes these known static required protection bits.
- */
-static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
- unsigned long pfn)
+static bool overlaps(unsigned long r1_start, unsigned long r1_end,
+ unsigned long r2_start, unsigned long r2_end)
{
- pgprot_t forbidden = __pgprot(0);
+ return (r1_start <= r2_end && r1_end >= r2_start) ||
+ (r2_start <= r1_end && r2_end >= r1_start);
+}
- /*
- * The BIOS area between 640k and 1Mb needs to be executable for
- * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
- */
#ifdef CONFIG_PCI_BIOS
- if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
- pgprot_val(forbidden) |= _PAGE_NX;
+/*
+ * The BIOS area between 640k and 1Mb needs to be executable for PCI BIOS
+ * based config access (CONFIG_PCI_GOBIOS) support.
+ */
+#define BIOS_PFN PFN_DOWN(BIOS_BEGIN)
+#define BIOS_PFN_END PFN_DOWN(BIOS_END - 1)
+
+static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn)
+{
+ if (pcibios_enabled && overlaps(spfn, epfn, BIOS_PFN, BIOS_PFN_END))
+ return _PAGE_NX;
+ return 0;
+}
+#else
+static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn)
+{
+ return 0;
+}
#endif
- /*
- * The kernel text needs to be executable for obvious reasons
- * Does not cover __inittext since that is gone later on. On
- * 64bit we do not enforce !NX on the low mapping
- */
- if (within(address, (unsigned long)_text, (unsigned long)_etext))
- pgprot_val(forbidden) |= _PAGE_NX;
+/*
+ * The .rodata section needs to be read-only. Using the pfn catches all
+ * aliases. This also includes __ro_after_init, so do not enforce until
+ * kernel_set_to_readonly is true.
+ */
+static pgprotval_t protect_rodata(unsigned long spfn, unsigned long epfn)
+{
+ unsigned long epfn_ro, spfn_ro = PFN_DOWN(__pa_symbol(__start_rodata));
/*
- * The .rodata section needs to be read-only. Using the pfn
- * catches all aliases. This also includes __ro_after_init,
- * so do not enforce until kernel_set_to_readonly is true.
+ * Note: __end_rodata is at page aligned and not inclusive, so
+ * subtract 1 to get the last enforced PFN in the rodata area.
*/
- if (kernel_set_to_readonly &&
- within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT,
- __pa_symbol(__end_rodata) >> PAGE_SHIFT))
- pgprot_val(forbidden) |= _PAGE_RW;
+ epfn_ro = PFN_DOWN(__pa_symbol(__end_rodata)) - 1;
+
+ if (kernel_set_to_readonly && overlaps(spfn, epfn, spfn_ro, epfn_ro))
+ return _PAGE_RW;
+ return 0;
+}
+
+/*
+ * Protect kernel text against becoming non executable by forbidding
+ * _PAGE_NX. This protects only the high kernel mapping (_text -> _etext)
+ * out of which the kernel actually executes. Do not protect the low
+ * mapping.
+ *
+ * This does not cover __inittext since that is gone after boot.
+ */
+static pgprotval_t protect_kernel_text(unsigned long start, unsigned long end)
+{
+ unsigned long t_end = (unsigned long)_etext - 1;
+ unsigned long t_start = (unsigned long)_text;
+
+ if (overlaps(start, end, t_start, t_end))
+ return _PAGE_NX;
+ return 0;
+}
#if defined(CONFIG_X86_64)
+/*
+ * Once the kernel maps the text as RO (kernel_set_to_readonly is set),
+ * kernel text mappings for the large page aligned text, rodata sections
+ * will be always read-only. For the kernel identity mappings covering the
+ * holes caused by this alignment can be anything that user asks.
+ *
+ * This will preserve the large page mappings for kernel text/data at no
+ * extra cost.
+ */
+static pgprotval_t protect_kernel_text_ro(unsigned long start,
+ unsigned long end)
+{
+ unsigned long t_end = (unsigned long)__end_rodata_hpage_align - 1;
+ unsigned long t_start = (unsigned long)_text;
+ unsigned int level;
+
+ if (!kernel_set_to_readonly || !overlaps(start, end, t_start, t_end))
+ return 0;
/*
- * Once the kernel maps the text as RO (kernel_set_to_readonly is set),
- * kernel text mappings for the large page aligned text, rodata sections
- * will be always read-only. For the kernel identity mappings covering
- * the holes caused by this alignment can be anything that user asks.
+ * Don't enforce the !RW mapping for the kernel text mapping, if
+ * the current mapping is already using small page mapping. No
+ * need to work hard to preserve large page mappings in this case.
*
- * This will preserve the large page mappings for kernel text/data
- * at no extra cost.
+ * This also fixes the Linux Xen paravirt guest boot failure caused
+ * by unexpected read-only mappings for kernel identity
+ * mappings. In this paravirt guest case, the kernel text mapping
+ * and the kernel identity mapping share the same page-table pages,
+ * so the protections for kernel text and identity mappings have to
+ * be the same.
*/
- if (kernel_set_to_readonly &&
- within(address, (unsigned long)_text,
- (unsigned long)__end_rodata_hpage_align)) {
- unsigned int level;
-
- /*
- * Don't enforce the !RW mapping for the kernel text mapping,
- * if the current mapping is already using small page mapping.
- * No need to work hard to preserve large page mappings in this
- * case.
- *
- * This also fixes the Linux Xen paravirt guest boot failure
- * (because of unexpected read-only mappings for kernel identity
- * mappings). In this paravirt guest case, the kernel text
- * mapping and the kernel identity mapping share the same
- * page-table pages. Thus we can't really use different
- * protections for the kernel text and identity mappings. Also,
- * these shared mappings are made of small page mappings.
- * Thus this don't enforce !RW mapping for small page kernel
- * text mapping logic will help Linux Xen parvirt guest boot
- * as well.
- */
- if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
- pgprot_val(forbidden) |= _PAGE_RW;
- }
+ if (lookup_address(start, &level) && (level != PG_LEVEL_4K))
+ return _PAGE_RW;
+ return 0;
+}
+#else
+static pgprotval_t protect_kernel_text_ro(unsigned long start,
+ unsigned long end)
+{
+ return 0;
+}
#endif
- prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
+static inline bool conflicts(pgprot_t prot, pgprotval_t val)
+{
+ return (pgprot_val(prot) & ~val) != pgprot_val(prot);
+}
- return prot;
+static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val,
+ unsigned long start, unsigned long end,
+ unsigned long pfn, const char *txt)
+{
+ static const char *lvltxt[] = {
+ [CPA_CONFLICT] = "conflict",
+ [CPA_PROTECT] = "protect",
+ [CPA_DETECT] = "detect",
+ };
+
+ if (warnlvl > cpa_warn_level || !conflicts(prot, val))
+ return;
+
+ pr_warn("CPA %8s %10s: 0x%016lx - 0x%016lx PFN %lx req %016llx prevent %016llx\n",
+ lvltxt[warnlvl], txt, start, end, pfn, (unsigned long long)pgprot_val(prot),
+ (unsigned long long)val);
+}
+
+/*
+ * Certain areas of memory on x86 require very specific protection flags,
+ * for example the BIOS area or kernel text. Callers don't always get this
+ * right (again, ioremap() on BIOS memory is not uncommon) so this function
+ * checks and fixes these known static required protection bits.
+ */
+static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
+ unsigned long pfn, unsigned long npg,
+ int warnlvl)
+{
+ pgprotval_t forbidden, res;
+ unsigned long end;
+
+ /*
+ * There is no point in checking RW/NX conflicts when the requested
+ * mapping is setting the page !PRESENT.
+ */
+ if (!(pgprot_val(prot) & _PAGE_PRESENT))
+ return prot;
+
+ /* Operate on the virtual address */
+ end = start + npg * PAGE_SIZE - 1;
+
+ res = protect_kernel_text(start, end);
+ check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX");
+ forbidden = res;
+
+ res = protect_kernel_text_ro(start, end);
+ check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
+ forbidden |= res;
+
+ /* Check the PFN directly */
+ res = protect_pci_bios(pfn, pfn + npg - 1);
+ check_conflict(warnlvl, prot, res, start, end, pfn, "PCIBIOS NX");
+ forbidden |= res;
+
+ res = protect_rodata(pfn, pfn + npg - 1);
+ check_conflict(warnlvl, prot, res, start, end, pfn, "Rodata RO");
+ forbidden |= res;
+
+ return __pgprot(pgprot_val(prot) & ~forbidden);
}
/*
@@ -421,18 +590,18 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
*/
pte_t *lookup_address(unsigned long address, unsigned int *level)
{
- return lookup_address_in_pgd(pgd_offset_k(address), address, level);
+ return lookup_address_in_pgd(pgd_offset_k(address), address, level);
}
EXPORT_SYMBOL_GPL(lookup_address);
static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
unsigned int *level)
{
- if (cpa->pgd)
+ if (cpa->pgd)
return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
address, level);
- return lookup_address(address, level);
+ return lookup_address(address, level);
}
/*
@@ -549,40 +718,35 @@ static pgprot_t pgprot_clear_protnone_bits(pgprot_t prot)
return prot;
}
-static int
-try_preserve_large_page(pte_t *kpte, unsigned long address,
- struct cpa_data *cpa)
+static int __should_split_large_page(pte_t *kpte, unsigned long address,
+ struct cpa_data *cpa)
{
- unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn, old_pfn;
+ unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn;
+ pgprot_t old_prot, new_prot, req_prot, chk_prot;
pte_t new_pte, old_pte, *tmp;
- pgprot_t old_prot, new_prot, req_prot;
- int i, do_split = 1;
enum pg_level level;
- if (cpa->force_split)
- return 1;
-
- spin_lock(&pgd_lock);
/*
* Check for races, another CPU might have split this page
* up already:
*/
tmp = _lookup_address_cpa(cpa, address, &level);
if (tmp != kpte)
- goto out_unlock;
+ return 1;
switch (level) {
case PG_LEVEL_2M:
old_prot = pmd_pgprot(*(pmd_t *)kpte);
old_pfn = pmd_pfn(*(pmd_t *)kpte);
+ cpa_inc_2m_checked();
break;
case PG_LEVEL_1G:
old_prot = pud_pgprot(*(pud_t *)kpte);
old_pfn = pud_pfn(*(pud_t *)kpte);
+ cpa_inc_1g_checked();
break;
default:
- do_split = -EINVAL;
- goto out_unlock;
+ return -EINVAL;
}
psize = page_level_size(level);
@@ -592,8 +756,8 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
* Calculate the number of pages, which fit into this large
* page starting at address:
*/
- nextpage_addr = (address + psize) & pmask;
- numpages = (nextpage_addr - address) >> PAGE_SHIFT;
+ lpaddr = (address + psize) & pmask;
+ numpages = (lpaddr - address) >> PAGE_SHIFT;
if (numpages < cpa->numpages)
cpa->numpages = numpages;
@@ -620,71 +784,142 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
pgprot_val(req_prot) |= _PAGE_PSE;
/*
- * old_pfn points to the large page base pfn. So we need
- * to add the offset of the virtual address:
+ * old_pfn points to the large page base pfn. So we need to add the
+ * offset of the virtual address:
*/
pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT);
cpa->pfn = pfn;
- new_prot = static_protections(req_prot, address, pfn);
+ /*
+ * Calculate the large page base address and the number of 4K pages
+ * in the large page
+ */
+ lpaddr = address & pmask;
+ numpages = psize >> PAGE_SHIFT;
/*
- * We need to check the full range, whether
- * static_protection() requires a different pgprot for one of
- * the pages in the range we try to preserve:
+ * Sanity check that the existing mapping is correct versus the static
+ * protections. static_protections() guards against !PRESENT, so no
+ * extra conditional required here.
*/
- addr = address & pmask;
- pfn = old_pfn;
- for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) {
- pgprot_t chk_prot = static_protections(req_prot, addr, pfn);
+ chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages,
+ CPA_CONFLICT);
- if (pgprot_val(chk_prot) != pgprot_val(new_prot))
- goto out_unlock;
+ if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) {
+ /*
+ * Split the large page and tell the split code to
+ * enforce static protections.
+ */
+ cpa->force_static_prot = 1;
+ return 1;
}
/*
- * If there are no changes, return. maxpages has been updated
- * above:
+ * Optimization: If the requested pgprot is the same as the current
+ * pgprot, then the large page can be preserved and no updates are
+ * required independent of alignment and length of the requested
+ * range. The above already established that the current pgprot is
+ * correct, which in consequence makes the requested pgprot correct
+ * as well if it is the same. The static protection scan below will
+ * not come to a different conclusion.
*/
- if (pgprot_val(new_prot) == pgprot_val(old_prot)) {
- do_split = 0;
- goto out_unlock;
+ if (pgprot_val(req_prot) == pgprot_val(old_prot)) {
+ cpa_inc_lp_sameprot(level);
+ return 0;
}
/*
- * We need to change the attributes. Check, whether we can
- * change the large page in one go. We request a split, when
- * the address is not aligned and the number of pages is
- * smaller than the number of pages in the large page. Note
- * that we limited the number of possible pages already to
- * the number of pages in the large page.
+ * If the requested range does not cover the full page, split it up
*/
- if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) {
- /*
- * The address is aligned and the number of pages
- * covers the full page.
- */
- new_pte = pfn_pte(old_pfn, new_prot);
- __set_pmd_pte(kpte, address, new_pte);
- cpa->flags |= CPA_FLUSHTLB;
- do_split = 0;
- }
+ if (address != lpaddr || cpa->numpages != numpages)
+ return 1;
-out_unlock:
+ /*
+ * Check whether the requested pgprot is conflicting with a static
+ * protection requirement in the large page.
+ */
+ new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
+ CPA_DETECT);
+
+ /*
+ * If there is a conflict, split the large page.
+ *
+ * There used to be a 4k wise evaluation trying really hard to
+ * preserve the large pages, but experimentation has shown, that this
+ * does not help at all. There might be corner cases which would
+ * preserve one large page occasionally, but it's really not worth the
+ * extra code and cycles for the common case.
+ */
+ if (pgprot_val(req_prot) != pgprot_val(new_prot))
+ return 1;
+
+ /* All checks passed. Update the large page mapping. */
+ new_pte = pfn_pte(old_pfn, new_prot);
+ __set_pmd_pte(kpte, address, new_pte);
+ cpa->flags |= CPA_FLUSHTLB;
+ cpa_inc_lp_preserved(level);
+ return 0;
+}
+
+static int should_split_large_page(pte_t *kpte, unsigned long address,
+ struct cpa_data *cpa)
+{
+ int do_split;
+
+ if (cpa->force_split)
+ return 1;
+
+ spin_lock(&pgd_lock);
+ do_split = __should_split_large_page(kpte, address, cpa);
spin_unlock(&pgd_lock);
return do_split;
}
+static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn,
+ pgprot_t ref_prot, unsigned long address,
+ unsigned long size)
+{
+ unsigned int npg = PFN_DOWN(size);
+ pgprot_t prot;
+
+ /*
+ * If should_split_large_page() discovered an inconsistent mapping,
+ * remove the invalid protection in the split mapping.
+ */
+ if (!cpa->force_static_prot)
+ goto set;
+
+ prot = static_protections(ref_prot, address, pfn, npg, CPA_PROTECT);
+
+ if (pgprot_val(prot) == pgprot_val(ref_prot))
+ goto set;
+
+ /*
+ * If this is splitting a PMD, fix it up. PUD splits cannot be
+ * fixed trivially as that would require to rescan the newly
+ * installed PMD mappings after returning from split_large_page()
+ * so an eventual further split can allocate the necessary PTE
+ * pages. Warn for now and revisit it in case this actually
+ * happens.
+ */
+ if (size == PAGE_SIZE)
+ ref_prot = prot;
+ else
+ pr_warn_once("CPA: Cannot fixup static protections for PUD split\n");
+set:
+ set_pte(pte, pfn_pte(pfn, ref_prot));
+}
+
static int
__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
struct page *base)
{
+ unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1;
pte_t *pbase = (pte_t *)page_address(base);
- unsigned long ref_pfn, pfn, pfninc = 1;
unsigned int i, level;
- pte_t *tmp;
pgprot_t ref_prot;
+ pte_t *tmp;
spin_lock(&pgd_lock);
/*
@@ -707,15 +942,17 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
* PAT bit to correct position.
*/
ref_prot = pgprot_large_2_4k(ref_prot);
-
ref_pfn = pmd_pfn(*(pmd_t *)kpte);
+ lpaddr = address & PMD_MASK;
+ lpinc = PAGE_SIZE;
break;
case PG_LEVEL_1G:
ref_prot = pud_pgprot(*(pud_t *)kpte);
ref_pfn = pud_pfn(*(pud_t *)kpte);
pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
-
+ lpaddr = address & PUD_MASK;
+ lpinc = PMD_SIZE;
/*
* Clear the PSE flags if the PRESENT flag is not set
* otherwise pmd_present/pmd_huge will return true
@@ -736,8 +973,8 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
* Get the target pfn from the original entry:
*/
pfn = ref_pfn;
- for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
- set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
+ for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc, lpaddr += lpinc)
+ split_set_pte(cpa, pbase + i, pfn, ref_prot, lpaddr, lpinc);
if (virt_addr_valid(address)) {
unsigned long pfn = PFN_DOWN(__pa(address));
@@ -756,14 +993,24 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
/*
- * Intel Atom errata AAH41 workaround.
+ * Do a global flush tlb after splitting the large page
+ * and before we do the actual change page attribute in the PTE.
+ *
+ * Without this, we violate the TLB application note, that says:
+ * "The TLBs may contain both ordinary and large-page
+ * translations for a 4-KByte range of linear addresses. This
+ * may occur if software modifies the paging structures so that
+ * the page size used for the address range changes. If the two
+ * translations differ with respect to page frame or attributes
+ * (e.g., permissions), processor behavior is undefined and may
+ * be implementation-specific."
*
- * The real fix should be in hw or in a microcode update, but
- * we also probabilistically try to reduce the window of having
- * a large TLB mixed with 4K TLBs while instruction fetches are
- * going on.
+ * We do this global tlb flush inside the cpa_lock, so that we
+ * don't allow any other cpu, with stale tlb entries change the
+ * page attribute in parallel, that also falls into the
+ * just split large page entry.
*/
- __flush_tlb_all();
+ flush_tlb_all();
spin_unlock(&pgd_lock);
return 0;
@@ -1247,7 +1494,9 @@ repeat:
pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
- new_prot = static_protections(new_prot, address, pfn);
+ cpa_inc_4k_install();
+ new_prot = static_protections(new_prot, address, pfn, 1,
+ CPA_PROTECT);
new_prot = pgprot_clear_protnone_bits(new_prot);
@@ -1273,7 +1522,7 @@ repeat:
* Check, whether we can keep the large page intact
* and just change the pte:
*/
- do_split = try_preserve_large_page(kpte, address, cpa);
+ do_split = should_split_large_page(kpte, address, cpa);
/*
* When the range fits into the existing large page,
* return. cp->numpages and cpa->tlbflush have been updated in
@@ -1286,28 +1535,8 @@ repeat:
* We have to split the large page:
*/
err = split_large_page(cpa, kpte, address);
- if (!err) {
- /*
- * Do a global flush tlb after splitting the large page
- * and before we do the actual change page attribute in the PTE.
- *
- * With out this, we violate the TLB application note, that says
- * "The TLBs may contain both ordinary and large-page
- * translations for a 4-KByte range of linear addresses. This
- * may occur if software modifies the paging structures so that
- * the page size used for the address range changes. If the two
- * translations differ with respect to page frame or attributes
- * (e.g., permissions), processor behavior is undefined and may
- * be implementation-specific."
- *
- * We do this global tlb flush inside the cpa_lock, so that we
- * don't allow any other cpu, with stale tlb entries change the
- * page attribute in parallel, that also falls into the
- * just split large page entry.
- */
- flush_tlb_all();
+ if (!err)
goto repeat;
- }
return err;
}
@@ -1529,19 +1758,19 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
cache = !!pgprot2cachemode(mask_set);
/*
- * On success we use CLFLUSH, when the CPU supports it to
- * avoid the WBINVD. If the CPU does not support it and in the
- * error case we fall back to cpa_flush_all (which uses
- * WBINVD):
+ * On error; flush everything to be sure.
*/
- if (!ret && boot_cpu_has(X86_FEATURE_CLFLUSH)) {
- if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
- cpa_flush_array(addr, numpages, cache,
- cpa.flags, pages);
- } else
- cpa_flush_range(baddr, numpages, cache);
- } else
+ if (ret) {
cpa_flush_all(cache);
+ goto out;
+ }
+
+ if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+ cpa_flush_array(baddr, addr, numpages, cache,
+ cpa.flags, pages);
+ } else {
+ cpa_flush_range(baddr, numpages, cache);
+ }
out:
return ret;
@@ -1856,10 +2085,7 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
/*
* Before changing the encryption attribute, we need to flush caches.
*/
- if (static_cpu_has(X86_FEATURE_CLFLUSH))
- cpa_flush_range(start, numpages, 1);
- else
- cpa_flush_all(1);
+ cpa_flush_range(start, numpages, 1);
ret = __change_page_attr_set_clr(&cpa, 1);
@@ -1870,10 +2096,7 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
* in case TLB flushing gets optimized in the cpa_flush_range()
* path use the same logic as above.
*/
- if (static_cpu_has(X86_FEATURE_CLFLUSH))
- cpa_flush_range(start, numpages, 0);
- else
- cpa_flush_all(0);
+ cpa_flush_range(start, numpages, 0);
return ret;
}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index e848a4811785..59274e2c1ac4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -115,6 +115,8 @@ static inline void pgd_list_del(pgd_t *pgd)
#define UNSHARED_PTRS_PER_PGD \
(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
+#define MAX_UNSHARED_PTRS_PER_PGD \
+ max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
@@ -181,6 +183,7 @@ static void pgd_dtor(pgd_t *pgd)
* and initialize the kernel pmds here.
*/
#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD
+#define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD
/*
* We allocate separate PMDs for the kernel part of the user page-table
@@ -189,6 +192,7 @@ static void pgd_dtor(pgd_t *pgd)
*/
#define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \
KERNEL_PGD_PTRS : 0)
+#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
{
@@ -210,7 +214,9 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
/* No need to prepopulate any pagetable entries in non-PAE modes. */
#define PREALLOCATED_PMDS 0
+#define MAX_PREALLOCATED_PMDS 0
#define PREALLOCATED_USER_PMDS 0
+#define MAX_PREALLOCATED_USER_PMDS 0
#endif /* CONFIG_X86_PAE */
static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
@@ -269,7 +275,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
if (pgd_val(pgd) != 0) {
pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
- *pgdp = native_make_pgd(0);
+ pgd_clear(pgdp);
paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
pmd_free(mm, pmd);
@@ -428,8 +434,8 @@ static inline void _pgd_free(pgd_t *pgd)
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
- pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
- pmd_t *pmds[PREALLOCATED_PMDS];
+ pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
+ pmd_t *pmds[MAX_PREALLOCATED_PMDS];
pgd = _pgd_alloc();
@@ -494,7 +500,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
int changed = !pte_same(*ptep, entry);
if (changed && dirty)
- *ptep = entry;
+ set_pte(ptep, entry);
return changed;
}
@@ -509,7 +515,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
if (changed && dirty) {
- *pmdp = entry;
+ set_pmd(pmdp, entry);
/*
* We had a write-protection fault here and changed the pmd
* to to more permissive. No need to flush the TLB for that,
@@ -529,7 +535,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
VM_BUG_ON(address & ~HPAGE_PUD_MASK);
if (changed && dirty) {
- *pudp = entry;
+ set_pud(pudp, entry);
/*
* We had a write-protection fault here and changed the pud
* to to more permissive. No need to flush the TLB for that,
@@ -637,6 +643,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
{
unsigned long address = __fix_to_virt(idx);
+#ifdef CONFIG_X86_64
+ /*
+ * Ensure that the static initial page tables are covering the
+ * fixmap completely.
+ */
+ BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
+ (FIXMAP_PMD_NUM * PTRS_PER_PTE));
+#endif
+
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index c1fc1ae6b429..4fee5c3003ed 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -434,11 +434,42 @@ static void __init pti_clone_p4d(unsigned long addr)
}
/*
- * Clone the CPU_ENTRY_AREA into the user space visible page table.
+ * Clone the CPU_ENTRY_AREA and associated data into the user space visible
+ * page table.
*/
static void __init pti_clone_user_shared(void)
{
+ unsigned int cpu;
+
pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+
+ for_each_possible_cpu(cpu) {
+ /*
+ * The SYSCALL64 entry code needs to be able to find the
+ * thread stack and needs one word of scratch space in which
+ * to spill a register. All of this lives in the TSS, in
+ * the sp1 and sp2 slots.
+ *
+ * This is done for all possible CPUs during boot to ensure
+ * that it's propagated to all mms. If we were to add one of
+ * these mappings during CPU hotplug, we would need to take
+ * some measure to make sure that every mm that subsequently
+ * ran on that CPU would have the relevant PGD entry in its
+ * pagetables. The usual vmalloc_fault() mechanism would not
+ * work for page faults taken in entry_SYSCALL_64 before RSP
+ * is set up.
+ */
+
+ unsigned long va = (unsigned long)&per_cpu(cpu_tss_rw, cpu);
+ phys_addr_t pa = per_cpu_ptr_to_phys((void *)va);
+ pte_t *target_pte;
+
+ target_pte = pti_user_pagetable_walk_pte(va);
+ if (WARN_ON(!target_pte))
+ return;
+
+ *target_pte = pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL);
+ }
}
#else /* CONFIG_X86_64 */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e96b99eb800c..bddd6b3cee1d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -7,6 +7,7 @@
#include <linux/export.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
+#include <linux/ptrace.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
@@ -180,13 +181,29 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
}
}
+static bool ibpb_needed(struct task_struct *tsk, u64 last_ctx_id)
+{
+ /*
+ * Check if the current (previous) task has access to the memory
+ * of the @tsk (next) task. If access is denied, make sure to
+ * issue a IBPB to stop user->user Spectre-v2 attacks.
+ *
+ * Note: __ptrace_may_access() returns 0 or -ERRNO.
+ */
+ return (tsk && tsk->mm && tsk->mm->context.ctx_id != last_ctx_id &&
+ ptrace_may_access_sched(tsk, PTRACE_MODE_SPEC_IBPB));
+}
+
void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+ bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
unsigned cpu = smp_processor_id();
u64 next_tlb_gen;
+ bool need_flush;
+ u16 new_asid;
/*
* NB: The scheduler will call us with prev == next when switching
@@ -240,20 +257,41 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
next->context.ctx_id);
/*
- * We don't currently support having a real mm loaded without
- * our cpu set in mm_cpumask(). We have all the bookkeeping
- * in place to figure out whether we would need to flush
- * if our cpu were cleared in mm_cpumask(), but we don't
- * currently use it.
+ * Even in lazy TLB mode, the CPU should stay set in the
+ * mm_cpumask. The TLB shootdown code can figure out from
+ * from cpu_tlbstate.is_lazy whether or not to send an IPI.
*/
if (WARN_ON_ONCE(real_prev != &init_mm &&
!cpumask_test_cpu(cpu, mm_cpumask(next))))
cpumask_set_cpu(cpu, mm_cpumask(next));
- return;
+ /*
+ * If the CPU is not in lazy TLB mode, we are just switching
+ * from one thread in a process to another thread in the same
+ * process. No TLB flush required.
+ */
+ if (!was_lazy)
+ return;
+
+ /*
+ * Read the tlb_gen to check whether a flush is needed.
+ * If the TLB is up to date, just use it.
+ * The barrier synchronizes with the tlb_gen increment in
+ * the TLB shootdown code.
+ */
+ smp_mb();
+ next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+ if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
+ next_tlb_gen)
+ return;
+
+ /*
+ * TLB contents went out of date while we were in lazy
+ * mode. Fall through to the TLB switching code below.
+ */
+ new_asid = prev_asid;
+ need_flush = true;
} else {
- u16 new_asid;
- bool need_flush;
u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
/*
@@ -262,18 +300,13 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* one process from doing Spectre-v2 attacks on another.
*
* As an optimization, flush indirect branches only when
- * switching into processes that disable dumping. This
- * protects high value processes like gpg, without having
- * too high performance overhead. IBPB is *expensive*!
- *
- * This will not flush branches when switching into kernel
- * threads. It will also not flush if we switch to idle
- * thread and back to the same process. It will flush if we
- * switch to a different non-dumpable process.
+ * switching into a processes that can't be ptrace by the
+ * current one (as in such case, attacker has much more
+ * convenient way how to tamper with the next process than
+ * branch buffer poisoning).
*/
- if (tsk && tsk->mm &&
- tsk->mm->context.ctx_id != last_ctx_id &&
- get_dumpable(tsk->mm) != SUID_DUMP_USER)
+ if (static_cpu_has(X86_FEATURE_USE_IBPB) &&
+ ibpb_needed(tsk, last_ctx_id))
indirect_branch_prediction_barrier();
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
@@ -308,46 +341,48 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
/* Let nmi_uaccess_okay() know that we're changing CR3. */
this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
barrier();
+ }
- if (need_flush) {
- this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
- this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- load_new_mm_cr3(next->pgd, new_asid, true);
-
- /*
- * NB: This gets called via leave_mm() in the idle path
- * where RCU functions differently. Tracing normally
- * uses RCU, so we need to use the _rcuidle variant.
- *
- * (There is no good reason for this. The idle code should
- * be rearranged to call this before rcu_idle_enter().)
- */
- trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
- } else {
- /* The new ASID is already up to date. */
- load_new_mm_cr3(next->pgd, new_asid, false);
-
- /* See above wrt _rcuidle. */
- trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
- }
+ if (need_flush) {
+ this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+ this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
+ load_new_mm_cr3(next->pgd, new_asid, true);
/*
- * Record last user mm's context id, so we can avoid
- * flushing branch buffer with IBPB if we switch back
- * to the same user.
+ * NB: This gets called via leave_mm() in the idle path
+ * where RCU functions differently. Tracing normally
+ * uses RCU, so we need to use the _rcuidle variant.
+ *
+ * (There is no good reason for this. The idle code should
+ * be rearranged to call this before rcu_idle_enter().)
*/
- if (next != &init_mm)
- this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
-
- /* Make sure we write CR3 before loaded_mm. */
- barrier();
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+ } else {
+ /* The new ASID is already up to date. */
+ load_new_mm_cr3(next->pgd, new_asid, false);
- this_cpu_write(cpu_tlbstate.loaded_mm, next);
- this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+ /* See above wrt _rcuidle. */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
- load_mm_cr4(next);
- switch_ldt(real_prev, next);
+ /*
+ * Record last user mm's context id, so we can avoid
+ * flushing branch buffer with IBPB if we switch back
+ * to the same user.
+ */
+ if (next != &init_mm)
+ this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
+ /* Make sure we write CR3 before loaded_mm. */
+ barrier();
+
+ this_cpu_write(cpu_tlbstate.loaded_mm, next);
+ this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
+ if (next != real_prev) {
+ load_mm_cr4(next);
+ switch_ldt(real_prev, next);
+ }
}
/*
@@ -368,20 +403,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
return;
- if (tlb_defer_switch_to_init_mm()) {
- /*
- * There's a significant optimization that may be possible
- * here. We have accurate enough TLB flush tracking that we
- * don't need to maintain coherence of TLB per se when we're
- * lazy. We do, however, need to maintain coherence of
- * paging-structure caches. We could, in principle, leave our
- * old mm loaded and only switch to init_mm when
- * tlb_remove_page() happens.
- */
- this_cpu_write(cpu_tlbstate.is_lazy, true);
- } else {
- switch_mm(NULL, &init_mm, NULL);
- }
+ this_cpu_write(cpu_tlbstate.is_lazy, true);
}
/*
@@ -468,6 +490,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
* paging-structure cache to avoid speculatively reading
* garbage into our TLB. Since switching to init_mm is barely
* slower than a minimal flush, just switch to init_mm.
+ *
+ * This should be rare, with native_flush_tlb_others skipping
+ * IPIs to lazy TLB mode CPUs.
*/
switch_mm_irqs_off(NULL, &init_mm, NULL);
return;
@@ -528,17 +553,16 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
f->new_tlb_gen == local_tlb_gen + 1 &&
f->new_tlb_gen == mm_tlb_gen) {
/* Partial flush */
- unsigned long addr;
- unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT;
+ unsigned long nr_invalidate = (f->end - f->start) >> f->stride_shift;
+ unsigned long addr = f->start;
- addr = f->start;
while (addr < f->end) {
__flush_tlb_one_user(addr);
- addr += PAGE_SIZE;
+ addr += 1UL << f->stride_shift;
}
if (local)
- count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages);
- trace_tlb_flush(reason, nr_pages);
+ count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate);
+ trace_tlb_flush(reason, nr_invalidate);
} else {
/* Full flush. */
local_flush_tlb();
@@ -571,6 +595,11 @@ static void flush_tlb_func_remote(void *info)
flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
}
+static bool tlb_is_not_lazy(int cpu, void *data)
+{
+ return !per_cpu(cpu_tlbstate.is_lazy, cpu);
+}
+
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
@@ -606,8 +635,23 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
(void *)info, 1);
return;
}
- smp_call_function_many(cpumask, flush_tlb_func_remote,
+
+ /*
+ * If no page tables were freed, we can skip sending IPIs to
+ * CPUs in lazy TLB mode. They will flush the CPU themselves
+ * at the next context switch.
+ *
+ * However, if page tables are getting freed, we need to send the
+ * IPI everywhere, to prevent CPUs in lazy TLB mode from tripping
+ * up on the new contents of what used to be page tables, while
+ * doing a speculative memory access.
+ */
+ if (info->freed_tables)
+ smp_call_function_many(cpumask, flush_tlb_func_remote,
(void *)info, 1);
+ else
+ on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote,
+ (void *)info, 1, GFP_ATOMIC, cpumask);
}
/*
@@ -623,12 +667,15 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
- unsigned long end, unsigned long vmflag)
+ unsigned long end, unsigned int stride_shift,
+ bool freed_tables)
{
int cpu;
struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
.mm = mm,
+ .stride_shift = stride_shift,
+ .freed_tables = freed_tables,
};
cpu = get_cpu();
@@ -638,8 +685,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
/* Should we flush just the requested range? */
if ((end != TLB_FLUSH_ALL) &&
- !(vmflag & VM_HUGETLB) &&
- ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) {
+ ((end - start) >> stride_shift) <= tlb_single_page_flush_ceiling) {
info.start = start;
info.end = end;
} else {
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 5559dcaddd5e..948656069cdd 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -356,7 +356,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
} else {
struct pci_root_info *info;
- info = kzalloc_node(sizeof(*info), GFP_KERNEL, node);
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info)
dev_err(&root->device->dev,
"pci_bus %04x:%02x: ignored (out of memory)\n",
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 649bdde63e32..bfa50e65ef6c 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -93,7 +93,8 @@ static int __init early_root_info_init(void)
vendor = id & 0xffff;
device = (id>>16) & 0xffff;
- if (vendor != PCI_VENDOR_ID_AMD)
+ if (vendor != PCI_VENDOR_ID_AMD &&
+ vendor != PCI_VENDOR_ID_HYGON)
continue;
if (hb_probes[i].device == device) {
@@ -390,7 +391,8 @@ static int __init pci_io_ecs_init(void)
static int __init amd_postcore_init(void)
{
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return 0;
early_root_info_init();
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 13f4485ca388..30a5111ae5fd 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -629,17 +629,11 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8c10, quirk_apple_mbp_poweroff);
static void quirk_no_aersid(struct pci_dev *pdev)
{
/* VMD Domain */
- if (is_vmd(pdev->bus))
+ if (is_vmd(pdev->bus) && pci_is_root_bus(pdev->bus))
pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2031, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2032, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x334a, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x334b, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x334c, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x334d, quirk_no_aersid);
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+ PCI_CLASS_BRIDGE_PCI, 8, quirk_no_aersid);
#ifdef CONFIG_PHYS_ADDR_T_64BIT
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index 034813d4ab1e..6cb6076223ba 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -115,7 +115,7 @@ static struct dentry *punit_dbg_file;
static int punit_dbgfs_register(struct punit_device *punit_device)
{
- static struct dentry *dev_state;
+ struct dentry *dev_state;
punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
if (!punit_dbg_file)
@@ -143,8 +143,8 @@ static void punit_dbgfs_unregister(void)
(kernel_ulong_t)&drv_data }
static const struct x86_cpu_id intel_punit_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt),
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD, punit_device_tng),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, punit_device_tng),
ICPU(INTEL_FAM6_ATOM_AIRMONT, punit_device_cht),
{}
};
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 5fdacb322ceb..7476b3b097e1 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -26,12 +26,14 @@ static bool early_efi_keep;
*/
static __init int early_efi_map_fb(void)
{
- unsigned long base, size;
+ u64 base, size;
if (!early_efi_keep)
return 0;
base = boot_params.screen_info.lfb_base;
+ if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)boot_params.screen_info.ext_lfb_base << 32;
size = boot_params.screen_info.lfb_size;
efi_fb = ioremap(base, size);
@@ -46,9 +48,11 @@ early_initcall(early_efi_map_fb);
*/
static __ref void *early_efi_map(unsigned long start, unsigned long len)
{
- unsigned long base;
+ u64 base;
base = boot_params.screen_info.lfb_base;
+ if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)boot_params.screen_info.ext_lfb_base << 32;
if (efi_fb)
return (efi_fb + start);
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 05ca14222463..9959657127f4 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -85,10 +85,9 @@ pgd_t * __init efi_call_phys_prolog(void)
void __init efi_call_phys_epilog(pgd_t *save_pgd)
{
+ load_fixmap_gdt(0);
load_cr3(save_pgd);
__flush_tlb_all();
-
- load_fixmap_gdt(0);
}
void __init efi_runtime_update_mappings(void)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ee5d08f25ce4..e8da7f492970 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void)
/*
* Makes the calling thread switch to/from efi_mm context. Can be used
- * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well
- * as during efi runtime calls i.e current->active_mm == current_mm.
- * We are not mm_dropping()/mm_grabbing() any mm, because we are not
- * losing/creating any references.
+ * in a kernel thread and user context. Preemption needs to remain disabled
+ * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm
+ * can not change under us.
+ * It should be ensured that there are no concurent calls to this function.
*/
void efi_switch_mm(struct mm_struct *mm)
{
- task_lock(current);
efi_scratch.prev_mm = current->active_mm;
current->active_mm = mm;
switch_mm(efi_scratch.prev_mm, mm, NULL);
- task_unlock(current);
}
#ifdef CONFIG_EFI_MIXED
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 844d31cb8a0c..669babcaf245 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -16,6 +16,7 @@
#include <asm/efi.h>
#include <asm/uv/uv.h>
#include <asm/cpu_device_id.h>
+#include <asm/reboot.h>
#define EFI_MIN_RESERVE 5120
@@ -654,3 +655,80 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
}
#endif
+
+/*
+ * If any access by any efi runtime service causes a page fault, then,
+ * 1. If it's efi_reset_system(), reboot through BIOS.
+ * 2. If any other efi runtime service, then
+ * a. Return error status to the efi caller process.
+ * b. Disable EFI Runtime Services forever and
+ * c. Freeze efi_rts_wq and schedule new process.
+ *
+ * @return: Returns, if the page fault is not handled. This function
+ * will never return if the page fault is handled successfully.
+ */
+void efi_recover_from_page_fault(unsigned long phys_addr)
+{
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ /*
+ * Make sure that an efi runtime service caused the page fault.
+ * "efi_mm" cannot be used to check if the page fault had occurred
+ * in the firmware context because efi=old_map doesn't use efi_pgd.
+ */
+ if (efi_rts_work.efi_rts_id == NONE)
+ return;
+
+ /*
+ * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so
+ * page faulting on these addresses isn't expected.
+ */
+ if (phys_addr >= 0x0000 && phys_addr <= 0x0fff)
+ return;
+
+ /*
+ * Print stack trace as it might be useful to know which EFI Runtime
+ * Service is buggy.
+ */
+ WARN(1, FW_BUG "Page fault caused by firmware at PA: 0x%lx\n",
+ phys_addr);
+
+ /*
+ * Buggy efi_reset_system() is handled differently from other EFI
+ * Runtime Services as it doesn't use efi_rts_wq. Although,
+ * native_machine_emergency_restart() says that machine_real_restart()
+ * could fail, it's better not to compilcate this fault handler
+ * because this case occurs *very* rarely and hence could be improved
+ * on a need by basis.
+ */
+ if (efi_rts_work.efi_rts_id == RESET_SYSTEM) {
+ pr_info("efi_reset_system() buggy! Reboot through BIOS\n");
+ machine_real_restart(MRR_BIOS);
+ return;
+ }
+
+ /*
+ * Before calling EFI Runtime Service, the kernel has switched the
+ * calling process to efi_mm. Hence, switch back to task_mm.
+ */
+ arch_efi_call_virt_teardown();
+
+ /* Signal error status to the efi caller process */
+ efi_rts_work.status = EFI_ABORTED;
+ complete(&efi_rts_work.efi_rts_comp);
+
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ pr_info("Froze efi_rts_wq and disabled EFI Runtime Services\n");
+
+ /*
+ * Call schedule() in an infinite loop, so that any spurious wake ups
+ * will never run efi_rts_wq again.
+ */
+ for (;;) {
+ set_current_state(TASK_IDLE);
+ schedule();
+ }
+
+ return;
+}
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
index 4392c15ed9e0..dbfc5cf2aa93 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
@@ -10,7 +10,7 @@
* of the License.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/machine.h>
#include <linux/platform_device.h>
#include <linux/regulator/machine.h>
#include <linux/regulator/fixed.h>
@@ -43,7 +43,6 @@ static struct fixed_voltage_config bcm43xx_vmmc = {
* real voltage and signaling are still 1.8V.
*/
.microvolts = 2000000, /* 1.8V */
- .gpio = -EINVAL,
.startup_delay = 250 * 1000, /* 250ms */
.enable_high = 1, /* active high */
.enabled_at_boot = 0, /* disabled at boot */
@@ -58,11 +57,23 @@ static struct platform_device bcm43xx_vmmc_regulator = {
},
};
+static struct gpiod_lookup_table bcm43xx_vmmc_gpio_table = {
+ .dev_id = "reg-fixed-voltage.0",
+ .table = {
+ GPIO_LOOKUP("0000:00:0c.0", -1, NULL, GPIO_ACTIVE_LOW),
+ {}
+ },
+};
+
static int __init bcm43xx_regulator_register(void)
{
+ struct gpiod_lookup_table *table = &bcm43xx_vmmc_gpio_table;
+ struct gpiod_lookup *lookup = table->table;
int ret;
- bcm43xx_vmmc.gpio = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME);
+ lookup[0].chip_hwnum = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME);
+ gpiod_add_lookup_table(table);
+
ret = platform_device_register(&bcm43xx_vmmc_regulator);
if (ret) {
pr_err("%s: vmmc regulator register failed\n", __func__);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index 5a0483e7bf66..31dce781364c 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -68,7 +68,7 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = {
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
static const struct x86_cpu_id bt_sfi_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data),
{}
};
diff --git a/arch/x86/platform/olpc/olpc-xo1-rtc.c b/arch/x86/platform/olpc/olpc-xo1-rtc.c
index a2b4efddd61a..8e7ddd7e313a 100644
--- a/arch/x86/platform/olpc/olpc-xo1-rtc.c
+++ b/arch/x86/platform/olpc/olpc-xo1-rtc.c
@@ -16,6 +16,7 @@
#include <asm/msr.h>
#include <asm/olpc.h>
+#include <asm/x86_init.h>
static void rtc_wake_on(struct device *dev)
{
@@ -75,6 +76,8 @@ static int __init xo1_rtc_init(void)
if (r)
return r;
+ x86_platform.legacy.rtc = 0;
+
device_init_wakeup(&xo1_rtc_device.dev, 1);
return 0;
}
diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c
index fd39301f25ac..7e56fc74093c 100644
--- a/arch/x86/platform/ts5500/ts5500.c
+++ b/arch/x86/platform/ts5500/ts5500.c
@@ -24,7 +24,6 @@
#include <linux/kernel.h>
#include <linux/leds.h>
#include <linux/init.h>
-#include <linux/platform_data/gpio-ts5500.h>
#include <linux/platform_data/max197.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index a4701389562c..37923d715741 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -7,4 +7,4 @@ nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_cpu.o := $(nostackp)
obj-$(CONFIG_PM_SLEEP) += cpu.o
-obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o
+obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
new file mode 100644
index 000000000000..bcddf09b5aa3
--- /dev/null
+++ b/arch/x86/power/hibernate.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hibernation support for x86
+ *
+ * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
+ * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
+ */
+#include <linux/gfp.h>
+#include <linux/smp.h>
+#include <linux/suspend.h>
+#include <linux/scatterlist.h>
+#include <linux/kdebug.h>
+
+#include <crypto/hash.h>
+
+#include <asm/e820/api.h>
+#include <asm/init.h>
+#include <asm/proto.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/mtrr.h>
+#include <asm/sections.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Address to jump to in the last phase of restore in order to get to the image
+ * kernel's text (this value is passed in the image header).
+ */
+unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
+
+/*
+ * Value of the cr3 register from before the hibernation (this value is passed
+ * in the image header).
+ */
+unsigned long restore_cr3 __visible;
+unsigned long temp_pgt __visible;
+unsigned long relocated_restore_code __visible;
+
+/**
+ * pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+int pfn_is_nosave(unsigned long pfn)
+{
+ unsigned long nosave_begin_pfn;
+ unsigned long nosave_end_pfn;
+
+ nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+ nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+
+ return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn;
+}
+
+
+#define MD5_DIGEST_SIZE 16
+
+struct restore_data_record {
+ unsigned long jump_address;
+ unsigned long jump_address_phys;
+ unsigned long cr3;
+ unsigned long magic;
+ u8 e820_digest[MD5_DIGEST_SIZE];
+};
+
+#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
+/**
+ * get_e820_md5 - calculate md5 according to given e820 table
+ *
+ * @table: the e820 table to be calculated
+ * @buf: the md5 result to be stored to
+ */
+static int get_e820_md5(struct e820_table *table, void *buf)
+{
+ struct crypto_shash *tfm;
+ struct shash_desc *desc;
+ int size;
+ int ret = 0;
+
+ tfm = crypto_alloc_shash("md5", 0, 0);
+ if (IS_ERR(tfm))
+ return -ENOMEM;
+
+ desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+ GFP_KERNEL);
+ if (!desc) {
+ ret = -ENOMEM;
+ goto free_tfm;
+ }
+
+ desc->tfm = tfm;
+ desc->flags = 0;
+
+ size = offsetof(struct e820_table, entries) +
+ sizeof(struct e820_entry) * table->nr_entries;
+
+ if (crypto_shash_digest(desc, (u8 *)table, size, buf))
+ ret = -EINVAL;
+
+ kzfree(desc);
+
+free_tfm:
+ crypto_free_shash(tfm);
+ return ret;
+}
+
+static int hibernation_e820_save(void *buf)
+{
+ return get_e820_md5(e820_table_firmware, buf);
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+ int ret;
+ u8 result[MD5_DIGEST_SIZE];
+
+ memset(result, 0, MD5_DIGEST_SIZE);
+ /* If there is no digest in suspend kernel, let it go. */
+ if (!memcmp(result, buf, MD5_DIGEST_SIZE))
+ return false;
+
+ ret = get_e820_md5(e820_table_firmware, result);
+ if (ret)
+ return true;
+
+ return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
+}
+#else
+static int hibernation_e820_save(void *buf)
+{
+ return 0;
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+ /* If md5 is not builtin for restore kernel, let it go. */
+ return false;
+}
+#endif
+
+#ifdef CONFIG_X86_64
+#define RESTORE_MAGIC 0x23456789ABCDEF01UL
+#else
+#define RESTORE_MAGIC 0x12345678UL
+#endif
+
+/**
+ * arch_hibernation_header_save - populate the architecture specific part
+ * of a hibernation image header
+ * @addr: address to save the data at
+ */
+int arch_hibernation_header_save(void *addr, unsigned int max_size)
+{
+ struct restore_data_record *rdr = addr;
+
+ if (max_size < sizeof(struct restore_data_record))
+ return -EOVERFLOW;
+ rdr->magic = RESTORE_MAGIC;
+ rdr->jump_address = (unsigned long)restore_registers;
+ rdr->jump_address_phys = __pa_symbol(restore_registers);
+
+ /*
+ * The restore code fixes up CR3 and CR4 in the following sequence:
+ *
+ * [in hibernation asm]
+ * 1. CR3 <= temporary page tables
+ * 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
+ * 3. CR3 <= rdr->cr3
+ * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
+ * [in restore_processor_state()]
+ * 5. CR4 <= saved CR4
+ * 6. CR3 <= saved CR3
+ *
+ * Our mmu_cr4_features has CR4.PCIDE=0, and toggling
+ * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
+ * rdr->cr3 needs to point to valid page tables but must not
+ * have any of the PCID bits set.
+ */
+ rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
+
+ return hibernation_e820_save(rdr->e820_digest);
+}
+
+/**
+ * arch_hibernation_header_restore - read the architecture specific data
+ * from the hibernation image header
+ * @addr: address to read the data from
+ */
+int arch_hibernation_header_restore(void *addr)
+{
+ struct restore_data_record *rdr = addr;
+
+ if (rdr->magic != RESTORE_MAGIC) {
+ pr_crit("Unrecognized hibernate image header format!\n");
+ return -EINVAL;
+ }
+
+ restore_jump_address = rdr->jump_address;
+ jump_address_phys = rdr->jump_address_phys;
+ restore_cr3 = rdr->cr3;
+
+ if (hibernation_e820_mismatch(rdr->e820_digest)) {
+ pr_crit("Hibernate inconsistent memory map detected!\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+int relocate_restore_code(void)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ relocated_restore_code = get_safe_page(GFP_ATOMIC);
+ if (!relocated_restore_code)
+ return -ENOMEM;
+
+ memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
+
+ /* Make the page containing the relocated code executable */
+ pgd = (pgd_t *)__va(read_cr3_pa()) +
+ pgd_index(relocated_restore_code);
+ p4d = p4d_offset(pgd, relocated_restore_code);
+ if (p4d_large(*p4d)) {
+ set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
+ goto out;
+ }
+ pud = pud_offset(p4d, relocated_restore_code);
+ if (pud_large(*pud)) {
+ set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+ goto out;
+ }
+ pmd = pmd_offset(pud, relocated_restore_code);
+ if (pmd_large(*pmd)) {
+ set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+ goto out;
+ }
+ pte = pte_offset_kernel(pmd, relocated_restore_code);
+ set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+out:
+ __flush_tlb_all();
+ return 0;
+}
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index afc4ed7b1578..15695e30f982 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -14,9 +14,7 @@
#include <asm/pgtable.h>
#include <asm/mmzone.h>
#include <asm/sections.h>
-
-/* Defined in hibernate_asm_32.S */
-extern int restore_image(void);
+#include <asm/suspend.h>
/* Pointer to the temporary resume page tables */
pgd_t *resume_pg_dir;
@@ -145,6 +143,32 @@ static inline void resume_init_first_level_page_table(pgd_t *pg_dir)
#endif
}
+static int set_up_temporary_text_mapping(pgd_t *pgd_base)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_base + pgd_index(restore_jump_address);
+
+ pmd = resume_one_md_table_init(pgd);
+ if (!pmd)
+ return -ENOMEM;
+
+ if (boot_cpu_has(X86_FEATURE_PSE)) {
+ set_pmd(pmd + pmd_index(restore_jump_address),
+ __pmd((jump_address_phys & PMD_MASK) | pgprot_val(PAGE_KERNEL_LARGE_EXEC)));
+ } else {
+ pte = resume_one_page_table_init(pmd);
+ if (!pte)
+ return -ENOMEM;
+ set_pte(pte + pte_index(restore_jump_address),
+ __pte((jump_address_phys & PAGE_MASK) | pgprot_val(PAGE_KERNEL_EXEC)));
+ }
+
+ return 0;
+}
+
asmlinkage int swsusp_arch_resume(void)
{
int error;
@@ -154,22 +178,22 @@ asmlinkage int swsusp_arch_resume(void)
return -ENOMEM;
resume_init_first_level_page_table(resume_pg_dir);
+
+ error = set_up_temporary_text_mapping(resume_pg_dir);
+ if (error)
+ return error;
+
error = resume_physical_mapping_init(resume_pg_dir);
if (error)
return error;
+ temp_pgt = __pa(resume_pg_dir);
+
+ error = relocate_restore_code();
+ if (error)
+ return error;
+
/* We have got enough memory and from now on we cannot recover */
restore_image();
return 0;
}
-
-/*
- * pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-int pfn_is_nosave(unsigned long pfn)
-{
- unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
- unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
- return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index f8e3b668d20b..239f424ccb29 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -26,26 +26,6 @@
#include <asm/suspend.h>
#include <asm/tlbflush.h>
-/* Defined in hibernate_asm_64.S */
-extern asmlinkage __visible int restore_image(void);
-
-/*
- * Address to jump to in the last phase of restore in order to get to the image
- * kernel's text (this value is passed in the image header).
- */
-unsigned long restore_jump_address __visible;
-unsigned long jump_address_phys;
-
-/*
- * Value of the cr3 register from before the hibernation (this value is passed
- * in the image header).
- */
-unsigned long restore_cr3 __visible;
-
-unsigned long temp_level4_pgt __visible;
-
-unsigned long relocated_restore_code __visible;
-
static int set_up_temporary_text_mapping(pgd_t *pgd)
{
pmd_t *pmd;
@@ -141,46 +121,7 @@ static int set_up_temporary_mappings(void)
return result;
}
- temp_level4_pgt = __pa(pgd);
- return 0;
-}
-
-static int relocate_restore_code(void)
-{
- pgd_t *pgd;
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
-
- relocated_restore_code = get_safe_page(GFP_ATOMIC);
- if (!relocated_restore_code)
- return -ENOMEM;
-
- memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
-
- /* Make the page containing the relocated code executable */
- pgd = (pgd_t *)__va(read_cr3_pa()) +
- pgd_index(relocated_restore_code);
- p4d = p4d_offset(pgd, relocated_restore_code);
- if (p4d_large(*p4d)) {
- set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
- goto out;
- }
- pud = pud_offset(p4d, relocated_restore_code);
- if (pud_large(*pud)) {
- set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
- goto out;
- }
- pmd = pmd_offset(pud, relocated_restore_code);
- if (pmd_large(*pmd)) {
- set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
- goto out;
- }
- pte = pte_offset_kernel(pmd, relocated_restore_code);
- set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
-out:
- __flush_tlb_all();
+ temp_pgt = __pa(pgd);
return 0;
}
@@ -200,166 +141,3 @@ asmlinkage int swsusp_arch_resume(void)
restore_image();
return 0;
}
-
-/*
- * pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-int pfn_is_nosave(unsigned long pfn)
-{
- unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
- unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
- return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
-
-#define MD5_DIGEST_SIZE 16
-
-struct restore_data_record {
- unsigned long jump_address;
- unsigned long jump_address_phys;
- unsigned long cr3;
- unsigned long magic;
- u8 e820_digest[MD5_DIGEST_SIZE];
-};
-
-#define RESTORE_MAGIC 0x23456789ABCDEF01UL
-
-#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
-/**
- * get_e820_md5 - calculate md5 according to given e820 table
- *
- * @table: the e820 table to be calculated
- * @buf: the md5 result to be stored to
- */
-static int get_e820_md5(struct e820_table *table, void *buf)
-{
- struct crypto_shash *tfm;
- struct shash_desc *desc;
- int size;
- int ret = 0;
-
- tfm = crypto_alloc_shash("md5", 0, 0);
- if (IS_ERR(tfm))
- return -ENOMEM;
-
- desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
- GFP_KERNEL);
- if (!desc) {
- ret = -ENOMEM;
- goto free_tfm;
- }
-
- desc->tfm = tfm;
- desc->flags = 0;
-
- size = offsetof(struct e820_table, entries) +
- sizeof(struct e820_entry) * table->nr_entries;
-
- if (crypto_shash_digest(desc, (u8 *)table, size, buf))
- ret = -EINVAL;
-
- kzfree(desc);
-
-free_tfm:
- crypto_free_shash(tfm);
- return ret;
-}
-
-static void hibernation_e820_save(void *buf)
-{
- get_e820_md5(e820_table_firmware, buf);
-}
-
-static bool hibernation_e820_mismatch(void *buf)
-{
- int ret;
- u8 result[MD5_DIGEST_SIZE];
-
- memset(result, 0, MD5_DIGEST_SIZE);
- /* If there is no digest in suspend kernel, let it go. */
- if (!memcmp(result, buf, MD5_DIGEST_SIZE))
- return false;
-
- ret = get_e820_md5(e820_table_firmware, result);
- if (ret)
- return true;
-
- return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
-}
-#else
-static void hibernation_e820_save(void *buf)
-{
-}
-
-static bool hibernation_e820_mismatch(void *buf)
-{
- /* If md5 is not builtin for restore kernel, let it go. */
- return false;
-}
-#endif
-
-/**
- * arch_hibernation_header_save - populate the architecture specific part
- * of a hibernation image header
- * @addr: address to save the data at
- */
-int arch_hibernation_header_save(void *addr, unsigned int max_size)
-{
- struct restore_data_record *rdr = addr;
-
- if (max_size < sizeof(struct restore_data_record))
- return -EOVERFLOW;
- rdr->jump_address = (unsigned long)restore_registers;
- rdr->jump_address_phys = __pa_symbol(restore_registers);
-
- /*
- * The restore code fixes up CR3 and CR4 in the following sequence:
- *
- * [in hibernation asm]
- * 1. CR3 <= temporary page tables
- * 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
- * 3. CR3 <= rdr->cr3
- * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
- * [in restore_processor_state()]
- * 5. CR4 <= saved CR4
- * 6. CR3 <= saved CR3
- *
- * Our mmu_cr4_features has CR4.PCIDE=0, and toggling
- * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
- * rdr->cr3 needs to point to valid page tables but must not
- * have any of the PCID bits set.
- */
- rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
-
- rdr->magic = RESTORE_MAGIC;
-
- hibernation_e820_save(rdr->e820_digest);
-
- return 0;
-}
-
-/**
- * arch_hibernation_header_restore - read the architecture specific data
- * from the hibernation image header
- * @addr: address to read the data from
- */
-int arch_hibernation_header_restore(void *addr)
-{
- struct restore_data_record *rdr = addr;
-
- restore_jump_address = rdr->jump_address;
- jump_address_phys = rdr->jump_address_phys;
- restore_cr3 = rdr->cr3;
-
- if (rdr->magic != RESTORE_MAGIC) {
- pr_crit("Unrecognized hibernate image header format!\n");
- return -EINVAL;
- }
-
- if (hibernation_e820_mismatch(rdr->e820_digest)) {
- pr_crit("Hibernate inconsistent memory map detected!\n");
- return -ENODEV;
- }
-
- return 0;
-}
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 6e56815e13a0..6fe383002125 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -12,6 +12,7 @@
#include <asm/page_types.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
+#include <asm/frame.h>
.text
@@ -24,13 +25,30 @@ ENTRY(swsusp_arch_suspend)
pushfl
popl saved_context_eflags
+ /* save cr3 */
+ movl %cr3, %eax
+ movl %eax, restore_cr3
+
+ FRAME_BEGIN
call swsusp_save
+ FRAME_END
ret
+ENDPROC(swsusp_arch_suspend)
ENTRY(restore_image)
+ /* prepare to jump to the image kernel */
+ movl restore_jump_address, %ebx
+ movl restore_cr3, %ebp
+
movl mmu_cr4_features, %ecx
- movl resume_pg_dir, %eax
- subl $__PAGE_OFFSET, %eax
+
+ /* jump to relocated restore code */
+ movl relocated_restore_code, %eax
+ jmpl *%eax
+
+/* code below has been relocated to a safe page */
+ENTRY(core_restore_code)
+ movl temp_pgt, %eax
movl %eax, %cr3
jecxz 1f # cr4 Pentium and higher, skip if zero
@@ -49,7 +67,7 @@ copy_loop:
movl pbe_address(%edx), %esi
movl pbe_orig_address(%edx), %edi
- movl $1024, %ecx
+ movl $(PAGE_SIZE >> 2), %ecx
rep
movsl
@@ -58,10 +76,13 @@ copy_loop:
.p2align 4,,7
done:
+ jmpl *%ebx
+
+ /* code below belongs to the image kernel */
+ .align PAGE_SIZE
+ENTRY(restore_registers)
/* go back to the original page tables */
- movl $swapper_pg_dir, %eax
- subl $__PAGE_OFFSET, %eax
- movl %eax, %cr3
+ movl %ebp, %cr3
movl mmu_cr4_features, %ecx
jecxz 1f # cr4 Pentium and higher, skip if zero
movl %ecx, %cr4; # turn PGE back on
@@ -82,4 +103,8 @@ done:
xorl %eax, %eax
+ /* tell the hibernation core that we've just restored the memory */
+ movl %eax, in_suspend
+
ret
+ENDPROC(restore_registers)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index fd369a6e9ff8..3008baa2fa95 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -59,7 +59,7 @@ ENTRY(restore_image)
movq restore_cr3(%rip), %r9
/* prepare to switch to temporary page tables */
- movq temp_level4_pgt(%rip), %rax
+ movq temp_pgt(%rip), %rax
movq mmu_cr4_features(%rip), %rbx
/* prepare to copy image data to their original locations */
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 3a6c8ebc8032..0b08067c45f3 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -196,6 +196,7 @@ static const char *rel_type(unsigned type)
#if ELF_BITS == 64
REL_TYPE(R_X86_64_NONE),
REL_TYPE(R_X86_64_64),
+ REL_TYPE(R_X86_64_PC64),
REL_TYPE(R_X86_64_PC32),
REL_TYPE(R_X86_64_GOT32),
REL_TYPE(R_X86_64_PLT32),
@@ -782,6 +783,15 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
add_reloc(&relocs32neg, offset);
break;
+ case R_X86_64_PC64:
+ /*
+ * Only used by jump labels
+ */
+ if (is_percpu_sym(sym, symname))
+ die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n",
+ symname);
+ break;
+
case R_X86_64_32:
case R_X86_64_32S:
case R_X86_64_64:
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index 548197212a45..413f3519d9a1 100644
--- a/arch/x86/um/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -116,8 +116,7 @@ do { \
#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
#define R_X86_64_8 14 /* Direct 8 bit sign extended */
#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
+#define R_X86_64_PC64 24 /* Place relative 64-bit signed */
/*
* This is used to ensure we don't load something for the wrong architecture.
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index c1f98f32c45f..1ef391aa184d 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -18,6 +18,7 @@ config XEN_PV
bool "Xen PV guest support"
default y
depends on XEN
+ select PARAVIRT_XXL
select XEN_HAVE_PVMMU
select XEN_HAVE_VPMU
help
@@ -68,7 +69,6 @@ config XEN_SAVE_RESTORE
config XEN_DEBUG_FS
bool "Enable Xen debug and tuning parameters in debugfs"
depends on XEN && DEBUG_FS
- default n
help
Enable statistics output and various tuning options in debugfs.
Enabling this option may incur a significant performance overhead.
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index d83cb5478f54..dd2550d33b38 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -12,25 +12,46 @@ endif
# Make sure early boot has no stackprotector
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_enlighten_pv.o := $(nostackp)
-CFLAGS_mmu_pv.o := $(nostackp)
+CFLAGS_mmu_pv.o := $(nostackp)
-obj-y := enlighten.o multicalls.o mmu.o irq.o \
- time.o xen-asm.o xen-asm_$(BITS).o \
- grant-table.o suspend.o platform-pci-unplug.o
+obj-y += enlighten.o
+obj-y += mmu.o
+obj-y += time.o
+obj-y += grant-table.o
+obj-y += suspend.o
-obj-$(CONFIG_XEN_PVHVM) += enlighten_hvm.o mmu_hvm.o suspend_hvm.o
-obj-$(CONFIG_XEN_PV) += setup.o apic.o pmu.o suspend_pv.o \
- p2m.o enlighten_pv.o mmu_pv.o
-obj-$(CONFIG_XEN_PVH) += enlighten_pvh.o
+obj-$(CONFIG_XEN_PVHVM) += enlighten_hvm.o
+obj-$(CONFIG_XEN_PVHVM) += mmu_hvm.o
+obj-$(CONFIG_XEN_PVHVM) += suspend_hvm.o
+obj-$(CONFIG_XEN_PVHVM) += platform-pci-unplug.o
-obj-$(CONFIG_EVENT_TRACING) += trace.o
+obj-$(CONFIG_XEN_PV) += setup.o
+obj-$(CONFIG_XEN_PV) += apic.o
+obj-$(CONFIG_XEN_PV) += pmu.o
+obj-$(CONFIG_XEN_PV) += suspend_pv.o
+obj-$(CONFIG_XEN_PV) += p2m.o
+obj-$(CONFIG_XEN_PV) += enlighten_pv.o
+obj-$(CONFIG_XEN_PV) += mmu_pv.o
+obj-$(CONFIG_XEN_PV) += irq.o
+obj-$(CONFIG_XEN_PV) += multicalls.o
+obj-$(CONFIG_XEN_PV) += xen-asm.o
+obj-$(CONFIG_XEN_PV) += xen-asm_$(BITS).o
+
+obj-$(CONFIG_XEN_PVH) += enlighten_pvh.o
+obj-$(CONFIG_XEN_PVH) += xen-pvh.o
+
+obj-$(CONFIG_EVENT_TRACING) += trace.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_XEN_PV_SMP) += smp_pv.o
obj-$(CONFIG_XEN_PVHVM_SMP) += smp_hvm.o
+
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
+
obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
+
obj-$(CONFIG_XEN_DOM0) += vga.o
+
obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o
+
obj-$(CONFIG_XEN_EFI) += efi.o
-obj-$(CONFIG_XEN_PVH) += xen-pvh.o
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 1804b27f9632..1fbb629a9d78 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2014 Oracle Co., Daniel Kiper
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/bitops.h>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2eeddd814653..67b2f31a1265 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
#include <linux/bootmem.h>
#endif
@@ -5,6 +7,7 @@
#include <linux/kexec.h>
#include <linux/slab.h>
+#include <xen/xen.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/interface/memory.h>
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 19c1ff542387..0e75642d42a3 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/kexec.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 52a7c3faee0c..ec7a4209f310 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -995,11 +995,14 @@ void __init xen_setup_vcpu_info_placement(void)
* percpu area for all cpus, so make use of it.
*/
if (xen_have_vcpu_info_placement) {
- pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
- pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
- pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
- pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
- pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
+ pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
+ pv_ops.irq.restore_fl =
+ __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
+ pv_ops.irq.irq_disable =
+ __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
+ pv_ops.irq.irq_enable =
+ __PV_IS_CALLEE_SAVE(xen_irq_enable_direct);
+ pv_ops.mmu.read_cr2 = xen_read_cr2_direct;
}
}
@@ -1174,14 +1177,14 @@ static void __init xen_boot_params_init_edd(void)
*/
static void __init xen_setup_gdt(int cpu)
{
- pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
- pv_cpu_ops.load_gdt = xen_load_gdt_boot;
+ pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot;
+ pv_ops.cpu.load_gdt = xen_load_gdt_boot;
setup_stack_canary_segment(cpu);
switch_to_new_gdt(cpu);
- pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry;
- pv_cpu_ops.load_gdt = xen_load_gdt;
+ pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry;
+ pv_ops.cpu.load_gdt = xen_load_gdt;
}
static void __init xen_dom0_set_legacy_features(void)
@@ -1206,8 +1209,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
/* Install Xen paravirt ops */
pv_info = xen_info;
- pv_init_ops.patch = paravirt_patch_default;
- pv_cpu_ops = xen_cpu_ops;
+ pv_ops.init.patch = paravirt_patch_default;
+ pv_ops.cpu = xen_cpu_ops;
xen_init_irq_ops();
/*
@@ -1276,8 +1279,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
#endif
if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
- pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
- pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
+ pv_ops.mmu.ptep_modify_prot_start =
+ xen_ptep_modify_prot_start;
+ pv_ops.mmu.ptep_modify_prot_commit =
+ xen_ptep_modify_prot_commit;
}
machine_ops = xen_machine_ops;
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index c85d1a88f476..02e3ab7ff242 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -11,6 +11,7 @@
#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>
+#include <xen/xen.h>
#include <xen/interface/memory.h>
#include <xen/interface/hvm/start_info.h>
@@ -75,7 +76,7 @@ static void __init init_pvh_bootparams(void)
* Version 2.12 supports Xen entry point but we will use default x86/PC
* environment (i.e. hardware_subarch 0).
*/
- pvh_bootparams.hdr.version = 0x212;
+ pvh_bootparams.hdr.version = (2 << 8) | 12;
pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
x86_init.acpi.get_root_pointer = pvh_get_root_pointer;
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 92ccc718152d..ecb0d5450334 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
/******************************************************************************
* grant_table.c
* x86 specific part
@@ -8,30 +9,6 @@
* Copyright (c) 2004-2005, K A Fraser
* Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
* VA Linux Systems Japan. Split out x86 specific part.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation; or, when distributed
- * separately from the Linux kernel or incorporated into other
- * software packages, subject to the following license:
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this source file (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy, modify,
- * merge, publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
*/
#include <linux/sched.h>
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 7515a19fd324..850c93f346c7 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -128,6 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = {
void __init xen_init_irq_ops(void)
{
- pv_irq_ops = xen_irq_ops;
+ pv_ops.irq = xen_irq_ops;
x86_init.irqs.intr_init = xen_init_IRQ;
}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 96fc2f0fdbfe..60e9c37fd79f 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
#include <linux/pfn.h>
#include <asm/xen/page.h>
#include <asm/xen/hypercall.h>
@@ -6,12 +8,6 @@
#include "multicalls.h"
#include "mmu.h"
-/*
- * Protects atomic reservation decrease/increase against concurrent increases.
- * Also protects non-atomic updates of current_pages and balloon lists.
- */
-DEFINE_SPINLOCK(xen_reservation_lock);
-
unsigned long arbitrary_virt_to_mfn(void *vaddr)
{
xmaddr_t maddr = arbitrary_virt_to_machine(vaddr);
@@ -42,186 +38,6 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
}
EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
-static noinline void xen_flush_tlb_all(void)
-{
- struct mmuext_op *op;
- struct multicall_space mcs;
-
- preempt_disable();
-
- mcs = xen_mc_entry(sizeof(*op));
-
- op = mcs.args;
- op->cmd = MMUEXT_TLB_FLUSH_ALL;
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
-
- preempt_enable();
-}
-
-#define REMAP_BATCH_SIZE 16
-
-struct remap_data {
- xen_pfn_t *pfn;
- bool contiguous;
- bool no_translate;
- pgprot_t prot;
- struct mmu_update *mmu_update;
-};
-
-static int remap_area_pfn_pte_fn(pte_t *ptep, pgtable_t token,
- unsigned long addr, void *data)
-{
- struct remap_data *rmd = data;
- pte_t pte = pte_mkspecial(mfn_pte(*rmd->pfn, rmd->prot));
-
- /*
- * If we have a contiguous range, just update the pfn itself,
- * else update pointer to be "next pfn".
- */
- if (rmd->contiguous)
- (*rmd->pfn)++;
- else
- rmd->pfn++;
-
- rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
- rmd->mmu_update->ptr |= rmd->no_translate ?
- MMU_PT_UPDATE_NO_TRANSLATE :
- MMU_NORMAL_PT_UPDATE;
- rmd->mmu_update->val = pte_val_ma(pte);
- rmd->mmu_update++;
-
- return 0;
-}
-
-static int do_remap_pfn(struct vm_area_struct *vma,
- unsigned long addr,
- xen_pfn_t *pfn, int nr,
- int *err_ptr, pgprot_t prot,
- unsigned int domid,
- bool no_translate,
- struct page **pages)
-{
- int err = 0;
- struct remap_data rmd;
- struct mmu_update mmu_update[REMAP_BATCH_SIZE];
- unsigned long range;
- int mapped = 0;
-
- BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
-
- rmd.pfn = pfn;
- rmd.prot = prot;
- /*
- * We use the err_ptr to indicate if there we are doing a contiguous
- * mapping or a discontigious mapping.
- */
- rmd.contiguous = !err_ptr;
- rmd.no_translate = no_translate;
-
- while (nr) {
- int index = 0;
- int done = 0;
- int batch = min(REMAP_BATCH_SIZE, nr);
- int batch_left = batch;
- range = (unsigned long)batch << PAGE_SHIFT;
-
- rmd.mmu_update = mmu_update;
- err = apply_to_page_range(vma->vm_mm, addr, range,
- remap_area_pfn_pte_fn, &rmd);
- if (err)
- goto out;
-
- /* We record the error for each page that gives an error, but
- * continue mapping until the whole set is done */
- do {
- int i;
-
- err = HYPERVISOR_mmu_update(&mmu_update[index],
- batch_left, &done, domid);
-
- /*
- * @err_ptr may be the same buffer as @gfn, so
- * only clear it after each chunk of @gfn is
- * used.
- */
- if (err_ptr) {
- for (i = index; i < index + done; i++)
- err_ptr[i] = 0;
- }
- if (err < 0) {
- if (!err_ptr)
- goto out;
- err_ptr[i] = err;
- done++; /* Skip failed frame. */
- } else
- mapped += done;
- batch_left -= done;
- index += done;
- } while (batch_left);
-
- nr -= batch;
- addr += range;
- if (err_ptr)
- err_ptr += batch;
- cond_resched();
- }
-out:
-
- xen_flush_tlb_all();
-
- return err < 0 ? err : mapped;
-}
-
-int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
- unsigned long addr,
- xen_pfn_t gfn, int nr,
- pgprot_t prot, unsigned domid,
- struct page **pages)
-{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return -EOPNOTSUPP;
-
- return do_remap_pfn(vma, addr, &gfn, nr, NULL, prot, domid, false,
- pages);
-}
-EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range);
-
-int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
- unsigned long addr,
- xen_pfn_t *gfn, int nr,
- int *err_ptr, pgprot_t prot,
- unsigned domid, struct page **pages)
-{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
- prot, domid, pages);
-
- /* We BUG_ON because it's a programmer error to pass a NULL err_ptr,
- * and the consequences later is quite hard to detect what the actual
- * cause of "wrong memory was mapped in".
- */
- BUG_ON(err_ptr == NULL);
- return do_remap_pfn(vma, addr, gfn, nr, err_ptr, prot, domid,
- false, pages);
-}
-EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array);
-
-int xen_remap_domain_mfn_array(struct vm_area_struct *vma,
- unsigned long addr,
- xen_pfn_t *mfn, int nr,
- int *err_ptr, pgprot_t prot,
- unsigned int domid, struct page **pages)
-{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return -EOPNOTSUPP;
-
- return do_remap_pfn(vma, addr, mfn, nr, err_ptr, prot, domid,
- true, pages);
-}
-EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array);
-
/* Returns: 0 success */
int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
int nr, struct page **pages)
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index dd2ad82eee80..57409373750f 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -73,7 +73,7 @@ static int is_pagetable_dying_supported(void)
void __init xen_hvm_init_mmu_ops(void)
{
if (is_pagetable_dying_supported())
- pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
+ pv_ops.mmu.exit_mmap = xen_hvm_exit_mmap;
#ifdef CONFIG_PROC_VMCORE
WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
#endif
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2fe5c9b1816b..70ea598a37d2 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
/*
* Xen mmu operations
*
@@ -99,6 +101,12 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
#endif /* CONFIG_X86_64 */
/*
+ * Protects atomic reservation decrease/increase against concurrent increases.
+ * Also protects non-atomic updates of current_pages and balloon lists.
+ */
+static DEFINE_SPINLOCK(xen_reservation_lock);
+
+/*
* Note about cr3 (pagetable base) values:
*
* xen_cr3 contains the current logical cr3 value; it contains the
@@ -1907,7 +1915,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
/* L3_k[511] -> level2_fixmap_pgt */
convert_pfn_mfn(level3_kernel_pgt);
- /* L3_k[511][506] -> level1_fixmap_pgt */
+ /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */
convert_pfn_mfn(level2_fixmap_pgt);
/* We get [511][511] and have Xen's version of level2_kernel_pgt */
@@ -1952,7 +1960,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
- set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+ for (i = 0; i < FIXMAP_PMD_NUM; i++) {
+ set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE,
+ PAGE_KERNEL_RO);
+ }
/* Pin down new L4 */
pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
@@ -2205,7 +2217,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
set_page_prot(initial_page_table, PAGE_KERNEL);
set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
- pv_mmu_ops.write_cr3 = &xen_write_cr3;
+ pv_ops.mmu.write_cr3 = &xen_write_cr3;
}
/*
@@ -2354,27 +2366,27 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
static void __init xen_post_allocator_init(void)
{
- pv_mmu_ops.set_pte = xen_set_pte;
- pv_mmu_ops.set_pmd = xen_set_pmd;
- pv_mmu_ops.set_pud = xen_set_pud;
+ pv_ops.mmu.set_pte = xen_set_pte;
+ pv_ops.mmu.set_pmd = xen_set_pmd;
+ pv_ops.mmu.set_pud = xen_set_pud;
#ifdef CONFIG_X86_64
- pv_mmu_ops.set_p4d = xen_set_p4d;
+ pv_ops.mmu.set_p4d = xen_set_p4d;
#endif
/* This will work as long as patching hasn't happened yet
(which it hasn't) */
- pv_mmu_ops.alloc_pte = xen_alloc_pte;
- pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
- pv_mmu_ops.release_pte = xen_release_pte;
- pv_mmu_ops.release_pmd = xen_release_pmd;
+ pv_ops.mmu.alloc_pte = xen_alloc_pte;
+ pv_ops.mmu.alloc_pmd = xen_alloc_pmd;
+ pv_ops.mmu.release_pte = xen_release_pte;
+ pv_ops.mmu.release_pmd = xen_release_pmd;
#ifdef CONFIG_X86_64
- pv_mmu_ops.alloc_pud = xen_alloc_pud;
- pv_mmu_ops.release_pud = xen_release_pud;
+ pv_ops.mmu.alloc_pud = xen_alloc_pud;
+ pv_ops.mmu.release_pud = xen_release_pud;
#endif
- pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
+ pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte);
#ifdef CONFIG_X86_64
- pv_mmu_ops.write_cr3 = &xen_write_cr3;
+ pv_ops.mmu.write_cr3 = &xen_write_cr3;
#endif
}
@@ -2462,7 +2474,7 @@ void __init xen_init_mmu_ops(void)
x86_init.paging.pagetable_init = xen_pagetable_init;
x86_init.hyper.init_after_bootmem = xen_after_bootmem;
- pv_mmu_ops = xen_mmu_ops;
+ pv_ops.mmu = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
}
@@ -2662,6 +2674,138 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
}
EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
+static noinline void xen_flush_tlb_all(void)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
+
+ op = mcs.args;
+ op->cmd = MMUEXT_TLB_FLUSH_ALL;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
+}
+
+#define REMAP_BATCH_SIZE 16
+
+struct remap_data {
+ xen_pfn_t *pfn;
+ bool contiguous;
+ bool no_translate;
+ pgprot_t prot;
+ struct mmu_update *mmu_update;
+};
+
+static int remap_area_pfn_pte_fn(pte_t *ptep, pgtable_t token,
+ unsigned long addr, void *data)
+{
+ struct remap_data *rmd = data;
+ pte_t pte = pte_mkspecial(mfn_pte(*rmd->pfn, rmd->prot));
+
+ /*
+ * If we have a contiguous range, just update the pfn itself,
+ * else update pointer to be "next pfn".
+ */
+ if (rmd->contiguous)
+ (*rmd->pfn)++;
+ else
+ rmd->pfn++;
+
+ rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
+ rmd->mmu_update->ptr |= rmd->no_translate ?
+ MMU_PT_UPDATE_NO_TRANSLATE :
+ MMU_NORMAL_PT_UPDATE;
+ rmd->mmu_update->val = pte_val_ma(pte);
+ rmd->mmu_update++;
+
+ return 0;
+}
+
+int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
+ xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
+ unsigned int domid, bool no_translate, struct page **pages)
+{
+ int err = 0;
+ struct remap_data rmd;
+ struct mmu_update mmu_update[REMAP_BATCH_SIZE];
+ unsigned long range;
+ int mapped = 0;
+
+ BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
+
+ rmd.pfn = pfn;
+ rmd.prot = prot;
+ /*
+ * We use the err_ptr to indicate if there we are doing a contiguous
+ * mapping or a discontigious mapping.
+ */
+ rmd.contiguous = !err_ptr;
+ rmd.no_translate = no_translate;
+
+ while (nr) {
+ int index = 0;
+ int done = 0;
+ int batch = min(REMAP_BATCH_SIZE, nr);
+ int batch_left = batch;
+
+ range = (unsigned long)batch << PAGE_SHIFT;
+
+ rmd.mmu_update = mmu_update;
+ err = apply_to_page_range(vma->vm_mm, addr, range,
+ remap_area_pfn_pte_fn, &rmd);
+ if (err)
+ goto out;
+
+ /*
+ * We record the error for each page that gives an error, but
+ * continue mapping until the whole set is done
+ */
+ do {
+ int i;
+
+ err = HYPERVISOR_mmu_update(&mmu_update[index],
+ batch_left, &done, domid);
+
+ /*
+ * @err_ptr may be the same buffer as @gfn, so
+ * only clear it after each chunk of @gfn is
+ * used.
+ */
+ if (err_ptr) {
+ for (i = index; i < index + done; i++)
+ err_ptr[i] = 0;
+ }
+ if (err < 0) {
+ if (!err_ptr)
+ goto out;
+ err_ptr[i] = err;
+ done++; /* Skip failed frame. */
+ } else
+ mapped += done;
+ batch_left -= done;
+ index += done;
+ } while (batch_left);
+
+ nr -= batch;
+ addr += range;
+ if (err_ptr)
+ err_ptr += batch;
+ cond_resched();
+ }
+out:
+
+ xen_flush_tlb_all();
+
+ return err < 0 ? err : mapped;
+}
+EXPORT_SYMBOL_GPL(xen_remap_pfn);
+
#ifdef CONFIG_KEXEC_CORE
phys_addr_t paddr_vmcoreinfo_note(void)
{
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 159a897151d6..d6d74efd8912 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
/*
* Xen leaves the responsibility for maintaining p2m mappings to the
* guests themselves, but it must also access and update the p2m array
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 37c6056a7bba..33293ce01d8d 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
/* Glue code to lib/swiotlb-xen.c */
#include <linux/dma-mapping.h>
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 33a783c77d96..66ab96a4e2b3 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -1,28 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+
/******************************************************************************
* platform-pci-unplug.c
*
* Xen platform PCI device driver
* Copyright (c) 2010, Citrix
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
*/
#include <linux/init.h>
#include <linux/io.h>
#include <linux/export.h>
+#include <xen/xen.h>
#include <xen/platform_pci.h>
#include "xen-ops.h"
@@ -30,7 +19,6 @@
#define XEN_PLATFORM_ERR_PROTOCOL -2
#define XEN_PLATFORM_ERR_BLACKLIST -3
-#ifdef CONFIG_XEN_PVHVM
/* store the value of xen_emul_unplug after the unplug is done */
static int xen_platform_pci_unplug;
static int xen_emul_unplug;
@@ -214,4 +202,3 @@ static int __init parse_xen_emul_unplug(char *arg)
return 0;
}
early_param("xen_emul_unplug", parse_xen_emul_unplug);
-#endif
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 7d00d4ad44d4..e13b0b49fcdf 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -3,6 +3,7 @@
#include <linux/interrupt.h>
#include <asm/xen/hypercall.h>
+#include <xen/xen.h>
#include <xen/page.h>
#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>
@@ -90,6 +91,12 @@ static void xen_pmu_arch_init(void)
k7_counters_mirrored = 0;
break;
}
+ } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ amd_num_counters = F10H_NUM_COUNTERS;
+ amd_counters_base = MSR_K7_PERFCTR0;
+ amd_ctrls_base = MSR_K7_EVNTSEL0;
+ amd_msr_step = 1;
+ k7_counters_mirrored = 0;
} else {
uint32_t eax, ebx, ecx, edx;
@@ -285,7 +292,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
if (is_amd_pmu_msr(msr)) {
if (!xen_amd_pmu_emulate(msr, val, 1))
*val = native_read_msr_safe(msr, err);
@@ -308,7 +315,7 @@ bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
{
uint64_t val = ((uint64_t)high << 32) | low;
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
if (is_amd_pmu_msr(msr)) {
if (!xen_amd_pmu_emulate(msr, &val, 0))
*err = native_write_msr_safe(msr, low, high);
@@ -379,7 +386,7 @@ static unsigned long long xen_intel_read_pmc(int counter)
unsigned long long xen_read_pmc(int counter)
{
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return xen_amd_read_pmc(counter);
else
return xen_intel_read_pmc(counter);
@@ -478,7 +485,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs,
irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
{
int err, ret = IRQ_NONE;
- struct pt_regs regs;
+ struct pt_regs regs = {0};
const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
uint8_t xenpmu_flags = get_xenpmu_flags();
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index e3b18ad49889..145506f9fdbe 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -22,6 +22,7 @@
#include <linux/tick.h>
#include <linux/nmi.h>
#include <linux/cpuhotplug.h>
+#include <linux/stackprotector.h>
#include <asm/paravirt.h>
#include <asm/desc.h>
@@ -88,6 +89,7 @@ static void cpu_bringup(void)
asmlinkage __visible void cpu_bringup_and_idle(void)
{
cpu_bringup();
+ boot_init_stack_canary();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 973f10e05211..23f6793af88a 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -141,11 +141,12 @@ void __init xen_init_spinlocks(void)
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
__pv_init_lock_hash();
- pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_lock_ops.wait = xen_qlock_wait;
- pv_lock_ops.kick = xen_qlock_kick;
- pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
+ pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops.lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops.lock.wait = xen_qlock_wait;
+ pv_ops.lock.kick = xen_qlock_kick;
+ pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
static __init int xen_parse_nopvspin(char *arg)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c84f1e039d84..72bf446c3fee 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -513,7 +513,7 @@ static void __init xen_time_init(void)
void __init xen_init_time_ops(void)
{
xen_sched_clock_offset = xen_clocksource_read();
- pv_time_ops = xen_time_ops;
+ pv_ops.time = xen_time_ops;
x86_init.timers.timer_init = xen_time_init;
x86_init.timers.setup_percpu_clockev = x86_init_noop;
@@ -555,7 +555,7 @@ void __init xen_hvm_init_time_ops(void)
}
xen_sched_clock_offset = xen_clocksource_read();
- pv_time_ops = xen_time_ops;
+ pv_ops.time = xen_time_ops;
x86_init.timers.setup_percpu_clockev = xen_time_init;
x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
diff --git a/arch/x86/xen/vdso.h b/arch/x86/xen/vdso.h
index 861fedfe5230..873c54c488fe 100644
--- a/arch/x86/xen/vdso.h
+++ b/arch/x86/xen/vdso.h
@@ -1,3 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
/* Bit used for the pseudo-hwcap for non-negative segments. We use
bit 1 to avoid bugs in some versions of glibc when bit 0 is
used; the choice is otherwise arbitrary. */
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 417b339e5c8e..bb1c2da0381d 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -91,13 +91,15 @@ ENTRY(xen_iret)
ENTRY(xen_sysret64)
/*
* We're already on the usermode stack at this point, but
- * still with the kernel gs, so we can easily switch back
+ * still with the kernel gs, so we can easily switch back.
+ *
+ * tss.sp2 is scratch space.
*/
- movq %rsp, PER_CPU_VAR(rsp_scratch)
+ movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER_DS
- pushq PER_CPU_VAR(rsp_scratch)
+ pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
pushq %r11
pushq $__USER_CS
pushq %rcx
diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S
index ca2d3b2bf2af..b0e471506cd8 100644
--- a/arch/x86/xen/xen-pvh.S
+++ b/arch/x86/xen/xen-pvh.S
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
/*
* Copyright C 2016, Oracle and/or its affiliates. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program. If not, see <http://www.gnu.org/licenses/>.
*/
.code32