2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 20:53:53 +08:00
linux-next/arch/x86
Sean Christopherson 5a8781607e KVM: nVMX: Cache host_rsp on a per-VMCS basis
Currently, host_rsp is cached on a per-vCPU basis, i.e. it's stored in
struct vcpu_vmx.  In non-nested usage the caching is for all intents
and purposes 100% effective, e.g. only the first VMLAUNCH needs to
synchronize VMCS.HOST_RSP since the call stack to vmx_vcpu_run() is
identical each and every time.  But when running a nested guest, KVM
must invalidate the cache when switching the current VMCS as it can't
guarantee the new VMCS has the same HOST_RSP as the previous VMCS.  In
other words, the cache loses almost all of its efficacy when running a
nested VM.

Move host_rsp to struct vmcs_host_state, which is per-VMCS, so that it
is cached on a per-VMCS basis and restores its 100% hit rate when
nested VMs are in play.

Note that the host_rsp cache for vmcs02 essentially "breaks" when
nested early checks are enabled as nested_vmx_check_vmentry_hw() will
see a different RSP at the time of its VM-Enter.  While it's possible
to avoid even that VMCS.HOST_RSP synchronization, e.g. by employing a
dedicated VM-Exit stack, there is little motivation for doing so as
the overhead of two VMWRITEs (~55 cycles) is dwarfed by the overhead
of the extra VMX transition (600+ cycles) and is a proverbial drop in
the ocean relative to the total cost of a nested transtion (10s of
thousands of cycles).

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2019-02-12 13:12:22 +01:00
..
boot x86/boot/compressed/64: Do not corrupt EDX on EFER.LME=1 setting 2019-02-06 18:56:18 +01:00
configs PCI: consolidate PCI config entry in drivers/pci 2018-11-23 11:45:34 +09:00
crypto Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2018-12-27 13:53:32 -08:00
entry x86/entry/64/compat: Fix stack switching for XEN PV 2019-01-18 00:39:33 +01:00
events perf/x86/intel: Delay memory deallocation until x86_pmu_dead_cpu() 2019-02-04 08:44:51 +01:00
hyperv x86/hyper-v: Add HvFlushGuestAddressList hypercall support 2018-12-21 11:28:39 +01:00
ia32 Remove 'type' argument from access_ok() function 2019-01-03 18:57:57 -08:00
include Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2019-02-10 09:57:42 -08:00
kernel Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2019-02-10 09:57:42 -08:00
kvm KVM: nVMX: Cache host_rsp on a per-VMCS basis 2019-02-12 13:12:22 +01:00
lib x86: explicitly align IO accesses in memcpy_{to,from}io 2019-02-01 09:07:48 -08:00
math-emu Remove 'type' argument from access_ok() function 2019-01-03 18:57:57 -08:00
mm x86/mm/cpa: Fix set_mce_nospec() 2019-02-08 14:31:56 +01:00
net bpf: Add bpf_line_info support 2018-12-09 13:54:38 -08:00
oprofile
pci pci-v4.21-changes 2019-01-05 17:57:34 -08:00
platform Merge branch 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2018-12-26 18:42:51 -08:00
power mm: remove include/linux/bootmem.h 2018-10-31 08:54:16 -07:00
purgatory kbuild: move bin2c back to scripts/ from scripts/basic/ 2018-07-18 01:18:05 +09:00
ras
realmode
tools x86: Clean up 'sizeof x' => 'sizeof(x)' 2018-10-29 07:13:28 +01:00
um Remove 'type' argument from access_ok() function 2019-01-03 18:57:57 -08:00
video
xen xen: fixes for 5.0-rc3 2019-01-19 05:53:41 +12:00
.gitignore
Kbuild KVM: x86: Allow Qemu/KVM to use PVH entry point 2018-12-13 13:41:49 -05:00
Kconfig x86/resctrl: Avoid confusion over the new X86_RESCTRL config 2019-02-02 10:34:52 +01:00
Kconfig.cpu x86/cpu: Create Hygon Dhyana architecture support file 2018-09-27 16:14:05 +02:00
Kconfig.debug x86/kconfig: Remove redundant 'default n' lines from all x86 Kconfig's 2018-10-17 08:39:42 +02:00
Makefile jump_label: move 'asm goto' support test to Kconfig 2019-01-06 09:46:51 +09:00
Makefile_32.cpu
Makefile.um x86, powerpc: Remove -funit-at-a-time compiler option entirely 2018-12-09 11:55:32 +01:00