x86/fpu: Provide infrastructure for KVM FPU cleanup

BugLink: https://bugs.launchpad.net/bugs/1967750
For the upcoming AMX support it's necessary to do a proper integration with
KVM. Currently KVM allocates two FPU structs which are used for saving the user
state of the vCPU thread and restoring the guest state when entering
vcpu_run() and doing the reverse operation before leaving vcpu_run().

With the new fpstate mechanism this can be reduced to one extra buffer by
swapping the fpstate pointer in current::thread::fpu. This makes the
upcoming support for AMX and XFD simpler because then fpstate information
(features, sizes, xfd) are always consistent and it does not require any
nasty workarounds.

Provide:

  - An allocator which initializes the state properly

  - A replacement for the existing FPU swap mechanim

Aside of the reduced memory footprint, this also makes state switching
more efficient when TIF_FPU_NEED_LOAD is set. It does not require a
memcpy as the state is already correct in the to be swapped out fpstate.

The existing interfaces will be removed once KVM is converted over.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20211022185312.954684740@linutronix.de
(cherry picked from commit 69f6ed1d14c6bcf712f4bb22a231c15eeab401e7)
Acked-by: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 9ce83148058fcbb98044788ca62d96bbc59ac1ce..de85bcaae0c309ff78f9d932b2849b6891b94ec5 100644 (file)
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -135,9 +135,22 @@ extern void fpu_init_fpstate_user(struct fpu *fpu);
 extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature);
 
 /* KVM specific functions */
+extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu);
+extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu);
+extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest);
 extern void fpu_swap_kvm_fpu(struct fpu *save, struct fpu *rstor, u64 restore_mask);
 
 extern int fpu_copy_kvm_uabi_to_fpstate(struct fpu *fpu, const void *buf, u64 xcr0, u32 *pkru);
 extern void fpu_copy_fpstate_to_kvm_uabi(struct fpu *fpu, void *buf, unsigned int size, u32 pkru);
 
+static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
+{
+       gfpu->fpstate->is_confidential = true;
+}
+
+static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
+{
+       return gfpu->fpstate->is_confidential;
+}
+
 #endif /* _ASM_X86_FPU_API_H */

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0fb9defaba47641b530f8a3eedaf03533a9d3125..748d7b2fcacb10d0f8e83ccc9705468e94aa3174 100644 (file)
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -176,6 +176,75 @@ void fpu_reset_from_exception_fixup(void)
 }
 
 #if IS_ENABLED(CONFIG_KVM)
+static void __fpstate_reset(struct fpstate *fpstate);
+
+bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
+{
+       struct fpstate *fpstate;
+       unsigned int size;
+
+       size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+       fpstate = vzalloc(size);
+       if (!fpstate)
+               return false;
+
+       __fpstate_reset(fpstate);
+       fpstate_init_user(fpstate);
+       fpstate->is_valloc      = true;
+       fpstate->is_guest       = true;
+
+       gfpu->fpstate = fpstate;
+       return true;
+}
+EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
+
+void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
+{
+       struct fpstate *fps = gfpu->fpstate;
+
+       if (!fps)
+               return;
+
+       if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use))
+               return;
+
+       gfpu->fpstate = NULL;
+       vfree(fps);
+}
+EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
+
+int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
+{
+       struct fpstate *guest_fps = guest_fpu->fpstate;
+       struct fpu *fpu = &current->thread.fpu;
+       struct fpstate *cur_fps = fpu->fpstate;
+
+       fpregs_lock();
+       if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD))
+               save_fpregs_to_fpstate(fpu);
+
+       /* Swap fpstate */
+       if (enter_guest) {
+               fpu->__task_fpstate = cur_fps;
+               fpu->fpstate = guest_fps;
+               guest_fps->in_use = true;
+       } else {
+               guest_fps->in_use = false;
+               fpu->fpstate = fpu->__task_fpstate;
+               fpu->__task_fpstate = NULL;
+       }
+
+       cur_fps = fpu->fpstate;
+
+       if (!cur_fps->is_confidential)
+               restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE);
+
+       fpregs_mark_activate();
+       fpregs_unlock();
+       return 0;
+}
+EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
+
 void fpu_swap_kvm_fpu(struct fpu *save, struct fpu *rstor, u64 restore_mask)
 {
        fpregs_lock();
@@ -352,16 +421,20 @@ void fpstate_init_user(struct fpstate *fpstate)
                fpstate_init_fstate(fpstate);
 }
 
+static void __fpstate_reset(struct fpstate *fpstate)
+{
+       /* Initialize sizes and feature masks */
+       fpstate->size           = fpu_kernel_cfg.default_size;
+       fpstate->user_size      = fpu_user_cfg.default_size;
+       fpstate->xfeatures      = fpu_kernel_cfg.default_features;
+       fpstate->user_xfeatures = fpu_user_cfg.default_features;
+}
+
 void fpstate_reset(struct fpu *fpu)
 {
        /* Set the fpstate pointer to the default fpstate */
        fpu->fpstate = &fpu->__fpstate;
-
-       /* Initialize sizes and feature masks */
-       fpu->fpstate->size              = fpu_kernel_cfg.default_size;
-       fpu->fpstate->user_size         = fpu_user_cfg.default_size;
-       fpu->fpstate->xfeatures         = fpu_kernel_cfg.default_features;
-       fpu->fpstate->user_xfeatures    = fpu_user_cfg.default_features;
+       __fpstate_reset(fpu->fpstate);
 }
 
 #if IS_ENABLED(CONFIG_KVM)