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
  ...

arch/x86/mm/mpx.c

@@ -142,7 +142,7 @@ int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
 		goto err_out;
 	}
 	/* get bndregs field from current task's xsave area */
-	bndregs = get_xsave_field_ptr(XFEATURE_MASK_BNDREGS);
+	bndregs = get_xsave_field_ptr(XFEATURE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -190,7 +190,7 @@ static __user void *mpx_get_bounds_dir(void)
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -376,7 +376,7 @@ static int do_mpx_bt_fault(void)
 	const struct mpx_bndcsr *bndcsr;
 	struct mm_struct *mm = current->mm;
 
-	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*

arch/x86/mm/pkeys.c

@@ -18,6 +18,7 @@
 
 #include <asm/cpufeature.h>             /* boot_cpu_has, ...            */
 #include <asm/mmu_context.h>            /* vma_pkey()                   */
+#include <asm/fpu/internal.h>		/* init_fpstate			*/
 
 int __execute_only_pkey(struct mm_struct *mm)
 {
@@ -39,17 +40,12 @@ int __execute_only_pkey(struct mm_struct *mm)
 	 * dance to set PKRU if we do not need to.  Check it
 	 * first and assume that if the execute-only pkey is
 	 * write-disabled that we do not have to set it
-	 * ourselves.  We need preempt off so that nobody
-	 * can make fpregs inactive.
+	 * ourselves.
 	 */
-	preempt_disable();
 	if (!need_to_set_mm_pkey &&
-	    current->thread.fpu.initialized &&
 	    !__pkru_allows_read(read_pkru(), execute_only_pkey)) {
-		preempt_enable();
 		return execute_only_pkey;
 	}
-	preempt_enable();
 
 	/*
 	 * Set up PKRU so that it denies access for everything
@@ -131,7 +127,6 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
  * in the process's lifetime will not accidentally get access
  * to data which is pkey-protected later on.
  */
-static
 u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
 		      PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) |
 		      PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) |
@@ -147,13 +142,6 @@ u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
 void copy_init_pkru_to_fpregs(void)
 {
 	u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value);
-	/*
-	 * Any write to PKRU takes it out of the XSAVE 'init
-	 * state' which increases context switch cost.  Avoid
-	 * writing 0 when PKRU was already 0.
-	 */
-	if (!init_pkru_value_snapshot && !read_pkru())
-		return;
 	/*
 	 * Override the PKRU state that came from 'init_fpstate'
 	 * with the baseline from the process.
@@ -174,6 +162,7 @@ static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
 static ssize_t init_pkru_write_file(struct file *file,
 		 const char __user *user_buf, size_t count, loff_t *ppos)
 {
+	struct pkru_state *pk;
 	char buf[32];
 	ssize_t len;
 	u32 new_init_pkru;
@@ -196,6 +185,10 @@ static ssize_t init_pkru_write_file(struct file *file,
 		return -EINVAL;
 
 	WRITE_ONCE(init_pkru_value, new_init_pkru);
+	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
+	if (!pk)
+		return -EINVAL;
+	pk->pkru = new_init_pkru;
 	return count;
 }