Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 FPU state handling updates from Borislav Petkov:
 "This contains work started by Rik van Riel and brought to fruition by
  Sebastian Andrzej Siewior with the main goal to optimize when to load
  FPU registers: only when returning to userspace and not on every
  context switch (while the task remains in the kernel).

  In addition, this optimization makes kernel_fpu_begin() cheaper by
  requiring registers saving only on the first invocation and skipping
  that in following ones.

  What is more, this series cleans up and streamlines many aspects of
  the already complex FPU code, hopefully making it more palatable for
  future improvements and simplifications.

  Finally, there's a __user annotations fix from Jann Horn"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  x86/fpu: Fault-in user stack if copy_fpstate_to_sigframe() fails
  x86/pkeys: Add PKRU value to init_fpstate
  x86/fpu: Restore regs in copy_fpstate_to_sigframe() in order to use the fastpath
  x86/fpu: Add a fastpath to copy_fpstate_to_sigframe()
  x86/fpu: Add a fastpath to __fpu__restore_sig()
  x86/fpu: Defer FPU state load until return to userspace
  x86/fpu: Merge the two code paths in __fpu__restore_sig()
  x86/fpu: Restore from kernel memory on the 64-bit path too
  x86/fpu: Inline copy_user_to_fpregs_zeroing()
  x86/fpu: Update xstate's PKRU value on write_pkru()
  x86/fpu: Prepare copy_fpstate_to_sigframe() for TIF_NEED_FPU_LOAD
  x86/fpu: Always store the registers in copy_fpstate_to_sigframe()
  x86/entry: Add TIF_NEED_FPU_LOAD
  x86/fpu: Eager switch PKRU state
  x86/pkeys: Don't check if PKRU is zero before writing it
  x86/fpu: Only write PKRU if it is different from current
  x86/pkeys: Provide *pkru() helpers
  x86/fpu: Use a feature number instead of mask in two more helpers
  x86/fpu: Make __raw_xsave_addr() use a feature number instead of mask
  x86/fpu: Add an __fpregs_load_activate() internal helper
  ...

1 files changed, 125 insertions, 77 deletions

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index f6a1d299627c..5a8d118bc423 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -92,13 +92,13 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 		return err;
 
 	err |= __put_user(FP_XSTATE_MAGIC2,
-			  (__u32 *)(buf + fpu_user_xstate_size));
+			  (__u32 __user *)(buf + fpu_user_xstate_size));
 
 	/*
 	 * Read the xfeatures which we copied (directly from the cpu or
 	 * from the state in task struct) to the user buffers.
 	 */
-	err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+	err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
 
 	/*
 	 * For legacy compatible, we always set FP/SSE bits in the bit
@@ -113,7 +113,7 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 	 */
 	xfeatures |= XFEATURE_MASK_FPSSE;
 
-	err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+	err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
 
 	return err;
 }
@@ -144,9 +144,10 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
  *	buf != buf_fx for 32-bit frames with fxstate.
  *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ * Try to save it directly to the user frame with disabled page fault handler.
+ * If this fails then do the slow path where the FPU state is first saved to
+ * task's fpu->state and then copy it to the user frame pointed to by the
+ * aligned pointer 'buf_fx'.
  *
  * If this is a 32-bit frame with fxstate, put a fsave header before
  * the aligned state at 'buf_fx'.
@@ -156,10 +157,9 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  */
 int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 {
-	struct fpu *fpu = &current->thread.fpu;
-	struct xregs_state *xsave = &fpu->state.xsave;
 	struct task_struct *tsk = current;
 	int ia32_fxstate = (buf != buf_fx);
+	int ret;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -172,28 +172,34 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 			sizeof(struct user_i387_ia32_struct), NULL,
 			(struct _fpstate_32 __user *) buf) ? -1 : 1;
 
-	if (fpu->initialized || using_compacted_format()) {
-		/* Save the live register state to the user directly. */
-		if (copy_fpregs_to_sigframe(buf_fx))
-			return -1;
-		/* Update the thread's fxstate to save the fsave header. */
-		if (ia32_fxstate)
-			copy_fxregs_to_kernel(fpu);
-	} else {
-		/*
-		 * It is a *bug* if kernel uses compacted-format for xsave
-		 * area and we copy it out directly to a signal frame. It
-		 * should have been handled above by saving the registers
-		 * directly.
-		 */
-		if (boot_cpu_has(X86_FEATURE_XSAVES)) {
-			WARN_ONCE(1, "x86/fpu: saving compacted-format xsave area to a signal frame!\n");
-			return -1;
-		}
-
-		fpstate_sanitize_xstate(fpu);
-		if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
-			return -1;
+retry:
+	/*
+	 * Load the FPU registers if they are not valid for the current task.
+	 * With a valid FPU state we can attempt to save the state directly to
+	 * userland's stack frame which will likely succeed. If it does not,
+	 * resolve the fault in the user memory and try again.
+	 */
+	fpregs_lock();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		__fpregs_load_activate();
+
+	pagefault_disable();
+	ret = copy_fpregs_to_sigframe(buf_fx);
+	pagefault_enable();
+	fpregs_unlock();
+
+	if (ret) {
+		int aligned_size;
+		int nr_pages;
+
+		aligned_size = offset_in_page(buf_fx) + fpu_user_xstate_size;
+		nr_pages = DIV_ROUND_UP(aligned_size, PAGE_SIZE);
+
+		ret = get_user_pages_unlocked((unsigned long)buf_fx, nr_pages,
+					      NULL, FOLL_WRITE);
+		if (ret == nr_pages)
+			goto retry;
+		return -EFAULT;
 	}
 
 	/* Save the fsave header for the 32-bit frames. */
@@ -207,11 +213,11 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 }
 
 static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
+sanitize_restored_xstate(union fpregs_state *state,
 			 struct user_i387_ia32_struct *ia32_env,
 			 u64 xfeatures, int fx_only)
 {
-	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct xregs_state *xsave = &state->xsave;
 	struct xstate_header *header = &xsave->header;
 
 	if (use_xsave()) {
@@ -238,17 +244,18 @@ sanitize_restored_xstate(struct task_struct *tsk,
 		 */
 		xsave->i387.mxcsr &= mxcsr_feature_mask;
 
-		convert_to_fxsr(tsk, ia32_env);
+		if (ia32_env)
+			convert_to_fxsr(&state->fxsave, ia32_env);
 	}
 }
 
 /*
  * Restore the extended state if present. Otherwise, restore the FP/SSE state.
  */
-static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
 {
 	if (use_xsave()) {
-		if ((unsigned long)buf % 64 || fx_only) {
+		if (fx_only) {
 			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 			return copy_user_to_fxregs(buf);
@@ -266,12 +273,15 @@ static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_
 
 static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 {
+	struct user_i387_ia32_struct *envp = NULL;
+	int state_size = fpu_kernel_xstate_size;
 	int ia32_fxstate = (buf != buf_fx);
 	struct task_struct *tsk = current;
 	struct fpu *fpu = &tsk->thread.fpu;
-	int state_size = fpu_kernel_xstate_size;
+	struct user_i387_ia32_struct env;
 	u64 xfeatures = 0;
 	int fx_only = 0;
+	int ret = 0;
 
 	ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
@@ -284,8 +294,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	if (!access_ok(buf, size))
 		return -EACCES;
 
-	fpu__initialize(fpu);
-
 	if (!static_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(current, NULL,
 				       0, sizeof(struct user_i387_ia32_struct),
@@ -308,61 +316,101 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		}
 	}
 
+	/*
+	 * The current state of the FPU registers does not matter. By setting
+	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
+	 * is not modified on context switch and that the xstate is considered
+	 * to be loaded again on return to userland (overriding last_cpu avoids
+	 * the optimisation).
+	 */
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+	__fpu_invalidate_fpregs_state(fpu);
+
+	if ((unsigned long)buf_fx % 64)
+		fx_only = 1;
+	/*
+	 * For 32-bit frames with fxstate, copy the fxstate so it can be
+	 * reconstructed later.
+	 */
 	if (ia32_fxstate) {
+		ret = __copy_from_user(&env, buf, sizeof(env));
+		if (ret)
+			goto err_out;
+		envp = &env;
+	} else {
 		/*
-		 * For 32-bit frames with fxstate, copy the user state to the
-		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Validate and sanitize the copied state.
+		 * Attempt to restore the FPU registers directly from user
+		 * memory. For that to succeed, the user access cannot cause
+		 * page faults. If it does, fall back to the slow path below,
+		 * going through the kernel buffer with the enabled pagefault
+		 * handler.
 		 */
-		struct user_i387_ia32_struct env;
-		int err = 0;
+		fpregs_lock();
+		pagefault_disable();
+		ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only);
+		pagefault_enable();
+		if (!ret) {
+			fpregs_mark_activate();
+			fpregs_unlock();
+			return 0;
+		}
+		fpregs_unlock();
+	}
 
-		/*
-		 * Drop the current fpu which clears fpu->initialized. This ensures
-		 * that any context-switch during the copy of the new state,
-		 * avoids the intermediate state from getting restored/saved.
-		 * Thus avoiding the new restored state from getting corrupted.
-		 * We will be ready to restore/save the state only after
-		 * fpu->initialized is again set.
-		 */
-		fpu__drop(fpu);
+
+	if (use_xsave() && !fx_only) {
+		u64 init_bv = xfeatures_mask & ~xfeatures;
 
 		if (using_compacted_format()) {
-			err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
+			ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
 		} else {
-			err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
+			ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
 
-			if (!err && state_size > offsetof(struct xregs_state, header))
-				err = validate_xstate_header(&fpu->state.xsave.header);
+			if (!ret && state_size > offsetof(struct xregs_state, header))
+				ret = validate_xstate_header(&fpu->state.xsave.header);
 		}
+		if (ret)
+			goto err_out;
 
-		if (err || __copy_from_user(&env, buf, sizeof(env))) {
-			fpstate_init(&fpu->state);
-			trace_x86_fpu_init_state(fpu);
-			err = -1;
-		} else {
-			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+
+		fpregs_lock();
+		if (unlikely(init_bv))
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures);
+
+	} else if (use_fxsr()) {
+		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
+		if (ret) {
+			ret = -EFAULT;
+			goto err_out;
 		}
 
-		local_bh_disable();
-		fpu->initialized = 1;
-		fpu__restore(fpu);
-		local_bh_enable();
+		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
 
-		return err;
-	} else {
-		/*
-		 * For 64-bit frames and 32-bit fsave frames, restore the user
-		 * state to the registers directly (with exceptions handled).
-		 */
-		user_fpu_begin();
-		if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
-			fpu__clear(fpu);
-			return -1;
+		fpregs_lock();
+		if (use_xsave()) {
+			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 		}
+
+		ret = copy_kernel_to_fxregs_err(&fpu->state.fxsave);
+	} else {
+		ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size);
+		if (ret)
+			goto err_out;
+
+		fpregs_lock();
+		ret = copy_kernel_to_fregs_err(&fpu->state.fsave);
 	}
+	if (!ret)
+		fpregs_mark_activate();
+	fpregs_unlock();
 
-	return 0;
+err_out:
+	if (ret)
+		fpu__clear(fpu);
+	return ret;
 }
 
 static inline int xstate_sigframe_size(void)