diff mbox series

[v1,23/55] KVM: PPC: Book3S HV P9: Reduce mtmsrd instructions required to save host SPRs

Message ID 20210726035036.739609-24-npiggin@gmail.com
State New
Headers show
Series [v1,01/55] KVM: PPC: Book3S HV: Remove TM emulation from POWER7/8 path | expand

Commit Message

Nicholas Piggin July 26, 2021, 3:50 a.m. UTC
This reduces the number of mtmsrd required to enable facility bits when
saving/restoring registers, by having the KVM code set all bits up front
rather than using individual facility functions that set their particular
MSR bits.

-42 cycles (7803) POWER9 virt-mode NULL hcall

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/process.c         | 24 +++++++++++
 arch/powerpc/kvm/book3s_hv.c          | 61 ++++++++++++++++++---------
 arch/powerpc/kvm/book3s_hv_p9_entry.c |  1 +
 3 files changed, 67 insertions(+), 19 deletions(-)

Comments

kernel test robot July 26, 2021, 6:57 a.m. UTC | #1
Hi Nicholas,

I love your patch! Perhaps something to improve:

[auto build test WARNING on linus/master]
[also build test WARNING on v5.14-rc3 next-20210723]
[cannot apply to powerpc/next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Nicholas-Piggin/KVM-PPC-Book3S-HV-P9-entry-exit-optimisations/20210726-115329
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git ff1176468d368232b684f75e82563369208bc371
config: powerpc-randconfig-r022-20210726 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project c63dbd850182797bc4b76124d08e1c320ab2365d)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install powerpc cross compiling tool for clang build
        # apt-get install binutils-powerpc-linux-gnu
        # https://github.com/0day-ci/linux/commit/d173e4690cf13578686dbbce48e1f81e925b96af
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Nicholas-Piggin/KVM-PPC-Book3S-HV-P9-entry-exit-optimisations/20210726-115329
        git checkout d173e4690cf13578686dbbce48e1f81e925b96af
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=powerpc 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

   arch/powerpc/kernel/process.c:612:33: error: no member named 'tm_tfhar' in 'struct thread_struct'
                   current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
                   ~~~~~~~~~~~~~~~ ^
   arch/powerpc/kernel/process.c:613:33: error: no member named 'tm_tfiar' in 'struct thread_struct'
                   current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
                   ~~~~~~~~~~~~~~~ ^
   arch/powerpc/kernel/process.c:614:33: error: no member named 'tm_texasr' in 'struct thread_struct'
                   current->thread.tm_texasr = mfspr(SPRN_TEXASR);
                   ~~~~~~~~~~~~~~~ ^
>> arch/powerpc/kernel/process.c:596:6: warning: no previous prototype for function 'save_user_regs_kvm' [-Wmissing-prototypes]
   void save_user_regs_kvm(void)
        ^
   arch/powerpc/kernel/process.c:596:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
   void save_user_regs_kvm(void)
   ^
   static 
>> arch/powerpc/kernel/process.c:611:16: warning: shift count >= width of type [-Wshift-count-overflow]
           if (usermsr & MSR_TM) {
                         ^~~~~~
   arch/powerpc/include/asm/reg.h:115:17: note: expanded from macro 'MSR_TM'
   #define MSR_TM          __MASK(MSR_TM_LG)       /* Transactional Mem Available */
                           ^~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/reg.h:66:23: note: expanded from macro '__MASK'
   #define __MASK(X)       (1UL<<(X))
                               ^ ~~~
   arch/powerpc/kernel/process.c:615:47: warning: shift count >= width of type [-Wshift-count-overflow]
                   current->thread.regs->msr &= ~MSR_TM;
                                                 ^~~~~~
   arch/powerpc/include/asm/reg.h:115:17: note: expanded from macro 'MSR_TM'
   #define MSR_TM          __MASK(MSR_TM_LG)       /* Transactional Mem Available */
                           ^~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/reg.h:66:23: note: expanded from macro '__MASK'
   #define __MASK(X)       (1UL<<(X))
                               ^ ~~~
   3 warnings and 3 errors generated.


vim +/save_user_regs_kvm +596 arch/powerpc/kernel/process.c

   595	
 > 596	void save_user_regs_kvm(void)
   597	{
   598		unsigned long usermsr;
   599	
   600		if (!current->thread.regs)
   601			return;
   602	
   603		usermsr = current->thread.regs->msr;
   604	
   605		if (usermsr & MSR_FP)
   606			save_fpu(current);
   607	
   608		if (usermsr & MSR_VEC)
   609			save_altivec(current);
   610	
 > 611		if (usermsr & MSR_TM) {
   612	                current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
   613	                current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
   614	                current->thread.tm_texasr = mfspr(SPRN_TEXASR);
   615	                current->thread.regs->msr &= ~MSR_TM;
   616		}
   617	}
   618	EXPORT_SYMBOL_GPL(save_user_regs_kvm);
   619	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
kernel test robot July 26, 2021, 7:01 a.m. UTC | #2
Hi Nicholas,

I love your patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on v5.14-rc3 next-20210723]
[cannot apply to powerpc/next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Nicholas-Piggin/KVM-PPC-Book3S-HV-P9-entry-exit-optimisations/20210726-115329
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git ff1176468d368232b684f75e82563369208bc371
config: powerpc64-randconfig-r024-20210726 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project c63dbd850182797bc4b76124d08e1c320ab2365d)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install powerpc64 cross compiling tool for clang build
        # apt-get install binutils-powerpc64-linux-gnu
        # https://github.com/0day-ci/linux/commit/d173e4690cf13578686dbbce48e1f81e925b96af
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Nicholas-Piggin/KVM-PPC-Book3S-HV-P9-entry-exit-optimisations/20210726-115329
        git checkout d173e4690cf13578686dbbce48e1f81e925b96af
        # save the attached .config to linux build tree
        mkdir build_dir
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross O=build_dir ARCH=powerpc SHELL=/bin/bash arch/powerpc/kernel/

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   arch/powerpc/include/asm/io-defs.h:45:1: error: performing pointer arithmetic on a null pointer has undefined behavior [-Werror,-Wnull-pointer-arithmetic]
   DEF_PCI_AC_NORET(insw, (unsigned long p, void *b, unsigned long c),
   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/io.h:616:3: note: expanded from macro 'DEF_PCI_AC_NORET'
                   __do_##name al;                                 \
                   ^~~~~~~~~~~~~~
   <scratch space>:121:1: note: expanded from here
   __do_insw
   ^
   arch/powerpc/include/asm/io.h:557:56: note: expanded from macro '__do_insw'
   #define __do_insw(p, b, n)      readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
                                          ~~~~~~~~~~~~~~~~~~~~~^
   In file included from arch/powerpc/kernel/process.c:28:
   In file included from include/linux/init_task.h:9:
   In file included from include/linux/ftrace.h:10:
   In file included from include/linux/trace_recursion.h:5:
   In file included from include/linux/interrupt.h:11:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/powerpc/include/asm/hardirq.h:6:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/powerpc/include/asm/io.h:619:
   arch/powerpc/include/asm/io-defs.h:47:1: error: performing pointer arithmetic on a null pointer has undefined behavior [-Werror,-Wnull-pointer-arithmetic]
   DEF_PCI_AC_NORET(insl, (unsigned long p, void *b, unsigned long c),
   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/io.h:616:3: note: expanded from macro 'DEF_PCI_AC_NORET'
                   __do_##name al;                                 \
                   ^~~~~~~~~~~~~~
   <scratch space>:123:1: note: expanded from here
   __do_insl
   ^
   arch/powerpc/include/asm/io.h:558:56: note: expanded from macro '__do_insl'
   #define __do_insl(p, b, n)      readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
                                          ~~~~~~~~~~~~~~~~~~~~~^
   In file included from arch/powerpc/kernel/process.c:28:
   In file included from include/linux/init_task.h:9:
   In file included from include/linux/ftrace.h:10:
   In file included from include/linux/trace_recursion.h:5:
   In file included from include/linux/interrupt.h:11:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/powerpc/include/asm/hardirq.h:6:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/powerpc/include/asm/io.h:619:
   arch/powerpc/include/asm/io-defs.h:49:1: error: performing pointer arithmetic on a null pointer has undefined behavior [-Werror,-Wnull-pointer-arithmetic]
   DEF_PCI_AC_NORET(outsb, (unsigned long p, const void *b, unsigned long c),
   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/io.h:616:3: note: expanded from macro 'DEF_PCI_AC_NORET'
                   __do_##name al;                                 \
                   ^~~~~~~~~~~~~~
   <scratch space>:125:1: note: expanded from here
   __do_outsb
   ^
   arch/powerpc/include/asm/io.h:559:58: note: expanded from macro '__do_outsb'
   #define __do_outsb(p, b, n)     writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
                                           ~~~~~~~~~~~~~~~~~~~~~^
   In file included from arch/powerpc/kernel/process.c:28:
   In file included from include/linux/init_task.h:9:
   In file included from include/linux/ftrace.h:10:
   In file included from include/linux/trace_recursion.h:5:
   In file included from include/linux/interrupt.h:11:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/powerpc/include/asm/hardirq.h:6:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/powerpc/include/asm/io.h:619:
   arch/powerpc/include/asm/io-defs.h:51:1: error: performing pointer arithmetic on a null pointer has undefined behavior [-Werror,-Wnull-pointer-arithmetic]
   DEF_PCI_AC_NORET(outsw, (unsigned long p, const void *b, unsigned long c),
   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/io.h:616:3: note: expanded from macro 'DEF_PCI_AC_NORET'
                   __do_##name al;                                 \
                   ^~~~~~~~~~~~~~
   <scratch space>:127:1: note: expanded from here
   __do_outsw
   ^
   arch/powerpc/include/asm/io.h:560:58: note: expanded from macro '__do_outsw'
   #define __do_outsw(p, b, n)     writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
                                           ~~~~~~~~~~~~~~~~~~~~~^
   In file included from arch/powerpc/kernel/process.c:28:
   In file included from include/linux/init_task.h:9:
   In file included from include/linux/ftrace.h:10:
   In file included from include/linux/trace_recursion.h:5:
   In file included from include/linux/interrupt.h:11:
   In file included from include/linux/hardirq.h:11:
   In file included from arch/powerpc/include/asm/hardirq.h:6:
   In file included from include/linux/irq.h:20:
   In file included from include/linux/io.h:13:
   In file included from arch/powerpc/include/asm/io.h:619:
   arch/powerpc/include/asm/io-defs.h:53:1: error: performing pointer arithmetic on a null pointer has undefined behavior [-Werror,-Wnull-pointer-arithmetic]
   DEF_PCI_AC_NORET(outsl, (unsigned long p, const void *b, unsigned long c),
   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   arch/powerpc/include/asm/io.h:616:3: note: expanded from macro 'DEF_PCI_AC_NORET'
                   __do_##name al;                                 \
                   ^~~~~~~~~~~~~~
   <scratch space>:129:1: note: expanded from here
   __do_outsl
   ^
   arch/powerpc/include/asm/io.h:561:58: note: expanded from macro '__do_outsl'
   #define __do_outsl(p, b, n)     writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
                                           ~~~~~~~~~~~~~~~~~~~~~^
>> arch/powerpc/kernel/process.c:612:33: error: no member named 'tm_tfhar' in 'struct thread_struct'
                   current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
                   ~~~~~~~~~~~~~~~ ^
>> arch/powerpc/kernel/process.c:613:33: error: no member named 'tm_tfiar' in 'struct thread_struct'
                   current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
                   ~~~~~~~~~~~~~~~ ^
>> arch/powerpc/kernel/process.c:614:33: error: no member named 'tm_texasr' in 'struct thread_struct'
                   current->thread.tm_texasr = mfspr(SPRN_TEXASR);
                   ~~~~~~~~~~~~~~~ ^
>> arch/powerpc/kernel/process.c:596:6: error: no previous prototype for function 'save_user_regs_kvm' [-Werror,-Wmissing-prototypes]
   void save_user_regs_kvm(void)
        ^
   arch/powerpc/kernel/process.c:596:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
   void save_user_regs_kvm(void)
   ^
   static 
   16 errors generated.


vim +612 arch/powerpc/kernel/process.c

   595	
 > 596	void save_user_regs_kvm(void)
   597	{
   598		unsigned long usermsr;
   599	
   600		if (!current->thread.regs)
   601			return;
   602	
   603		usermsr = current->thread.regs->msr;
   604	
   605		if (usermsr & MSR_FP)
   606			save_fpu(current);
   607	
   608		if (usermsr & MSR_VEC)
   609			save_altivec(current);
   610	
   611		if (usermsr & MSR_TM) {
 > 612	                current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
 > 613	                current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
 > 614	                current->thread.tm_texasr = mfspr(SPRN_TEXASR);
   615	                current->thread.regs->msr &= ~MSR_TM;
   616		}
   617	}
   618	EXPORT_SYMBOL_GPL(save_user_regs_kvm);
   619	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff mbox series

Patch

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 185beb290580..00b55b38a460 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -593,6 +593,30 @@  static void save_all(struct task_struct *tsk)
 	msr_check_and_clear(msr_all_available);
 }
 
+void save_user_regs_kvm(void)
+{
+	unsigned long usermsr;
+
+	if (!current->thread.regs)
+		return;
+
+	usermsr = current->thread.regs->msr;
+
+	if (usermsr & MSR_FP)
+		save_fpu(current);
+
+	if (usermsr & MSR_VEC)
+		save_altivec(current);
+
+	if (usermsr & MSR_TM) {
+                current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+                current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+                current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+                current->thread.regs->msr &= ~MSR_TM;
+	}
+}
+EXPORT_SYMBOL_GPL(save_user_regs_kvm);
+
 void flush_all_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2e966d62a583..dedcf3ddba3b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4103,6 +4103,7 @@  static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	struct p9_host_os_sprs host_os_sprs;
 	s64 dec;
 	u64 tb, next_timer;
+	unsigned long msr;
 	int trap;
 
 	WARN_ON_ONCE(vcpu->arch.ceded);
@@ -4114,8 +4115,23 @@  static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (next_timer < time_limit)
 		time_limit = next_timer;
 
+	vcpu->arch.ceded = 0;
+
 	save_p9_host_os_sprs(&host_os_sprs);
 
+	/* MSR bits may have been cleared by context switch */
+	msr = 0;
+	if (IS_ENABLED(CONFIG_PPC_FPU))
+		msr |= MSR_FP;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		msr |= MSR_VEC;
+	if (cpu_has_feature(CPU_FTR_VSX))
+		msr |= MSR_VSX;
+	if (cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+		msr |= MSR_TM;
+	msr = msr_check_and_set(msr);
+
 	kvmppc_subcore_enter_guest();
 
 	vc->entry_exit_map = 1;
@@ -4124,12 +4140,13 @@  static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	vcpu_vpa_increment_dispatch(vcpu);
 
 	if (cpu_has_feature(CPU_FTR_TM) ||
-	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) {
 		kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
+		msr = mfmsr(); /* TM restore can update msr */
+	}
 
 	switch_pmu_to_guest(vcpu, &host_os_sprs);
 
-	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
 	load_fp_state(&vcpu->arch.fp);
 #ifdef CONFIG_ALTIVEC
 	load_vr_state(&vcpu->arch.vr);
@@ -4238,7 +4255,6 @@  static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	restore_p9_host_os_sprs(vcpu, &host_os_sprs);
 
-	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
 	store_fp_state(&vcpu->arch.fp);
 #ifdef CONFIG_ALTIVEC
 	store_vr_state(&vcpu->arch.vr);
@@ -4767,6 +4783,8 @@  int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	goto done;
 }
 
+void save_user_regs_kvm(void);
+
 static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
@@ -4776,19 +4794,24 @@  static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 	unsigned long user_tar = 0;
 	unsigned int user_vrsave;
 	struct kvm *kvm;
+	unsigned long msr;
 
 	if (!vcpu->arch.sane) {
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		return -EINVAL;
 	}
 
+	/* No need to go into the guest when all we'll do is come back out */
+	if (signal_pending(current)) {
+		run->exit_reason = KVM_EXIT_INTR;
+		return -EINTR;
+	}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	/*
 	 * Don't allow entry with a suspended transaction, because
 	 * the guest entry/exit code will lose it.
-	 * If the guest has TM enabled, save away their TM-related SPRs
-	 * (they will get restored by the TM unavailable interrupt).
 	 */
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
 	    (current->thread.regs->msr & MSR_TM)) {
 		if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
@@ -4796,12 +4819,6 @@  static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 			run->fail_entry.hardware_entry_failure_reason = 0;
 			return -EINVAL;
 		}
-		/* Enable TM so we can read the TM SPRs */
-		mtmsr(mfmsr() | MSR_TM);
-		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
-		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
-		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
-		current->thread.regs->msr &= ~MSR_TM;
 	}
 #endif
 
@@ -4816,18 +4833,24 @@  static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 
 	kvmppc_core_prepare_to_enter(vcpu);
 
-	/* No need to go into the guest when all we'll do is come back out */
-	if (signal_pending(current)) {
-		run->exit_reason = KVM_EXIT_INTR;
-		return -EINTR;
-	}
-
 	kvm = vcpu->kvm;
 	atomic_inc(&kvm->arch.vcpus_running);
 	/* Order vcpus_running vs. mmu_ready, see kvmppc_alloc_reset_hpt */
 	smp_mb();
 
-	flush_all_to_thread(current);
+	msr = 0;
+	if (IS_ENABLED(CONFIG_PPC_FPU))
+		msr |= MSR_FP;
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		msr |= MSR_VEC;
+	if (cpu_has_feature(CPU_FTR_VSX))
+		msr |= MSR_VSX;
+	if (cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+		msr |= MSR_TM;
+	msr = msr_check_and_set(msr);
+
+	save_user_regs_kvm();
 
 	/* Save userspace EBB and other register values */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index a7f63082b4e3..fb9cb34445ea 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -224,6 +224,7 @@  int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
 		vc->tb_offset_applied = vc->tb_offset;
 	}
 
+	/* Could avoid mfmsr by passing around, but probably no big deal */
 	msr = mfmsr();
 
 	host_hfscr = mfspr(SPRN_HFSCR);