x86/mpx: Use the new get_xsave_field_ptr()API

The MPX registers (bndcsr/bndcfgu/bndstatus) are not directly
accessible via normal instructions.  They essentially act as
if they were floating point registers and are saved/restored
along with those registers.

There are two main paths in the MPX code where we care about
the contents of these registers:

	1. #BR (bounds) faults
	2. the prctl() code where we are setting MPX up

Both of those paths _might_ be called without the FPU having
been used.  That means that 'tsk->thread.fpu.state' might
never be allocated.

Also, fpu_save_init() is not preempt-safe.  It was a bug to
call it without disabling preemption.  The new
get_xsave_addr() calls unlazy_fpu() instead and properly
disables preemption.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave@sr71.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Suresh Siddha <sbsiddha@gmail.com>
Cc: bp@alien8.de
Link: http://lkml.kernel.org/r/20150607183701.BC0D37CF@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/mpx.h

@@ -60,8 +60,8 @@
 
 #ifdef CONFIG_X86_INTEL_MPX
 siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xregs_state *xsave_buf);
-int mpx_handle_bd_fault(struct xregs_state *xsave_buf);
+				struct task_struct *tsk);
+int mpx_handle_bd_fault(struct task_struct *tsk);
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
 	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
@@ -78,11 +78,11 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long start, unsigned long end);
 #else
 static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-					      struct xregs_state *xsave_buf)
+					      struct task_struct *tsk)
 {
 	return NULL;
 }
-static inline int mpx_handle_bd_fault(struct xregs_state *xsave_buf)
+static inline int mpx_handle_bd_fault(struct task_struct *tsk)
 {
 	return -EINVAL;
 }

arch/x86/kernel/traps.c

@@ -59,6 +59,7 @@
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
+#include <asm/fpu/xstate.h>
 #include <asm/mpx.h>
 
 #ifdef CONFIG_X86_64
@@ -371,9 +372,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
-	struct xregs_state *xsave_buf;
 	enum ctx_state prev_state;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 	siginfo_t *info;
 
 	prev_state = exception_enter();
@@ -392,12 +392,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 
 	/*
 	 * We need to look at BNDSTATUS to resolve this exception.
-	 * It is not directly accessible, though, so we need to
-	 * do an xsave and then pull it out of the xsave buffer.
+	 * A NULL here might mean that it is in its 'init state',
+	 * which is all zeros which indicates MPX was not
+	 * responsible for the exception.
 	 */
-	copy_fpregs_to_fpstate(&tsk->thread.fpu);
-	xsave_buf = &(tsk->thread.fpu.state.xsave);
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		goto exit_trap;
 
@@ -408,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	 */
 	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
 	case 2:	/* Bound directory has invalid entry. */
-		if (mpx_handle_bd_fault(xsave_buf))
+		if (mpx_handle_bd_fault(tsk))
 			goto exit_trap;
 		break; /* Success, it was handled */
 	case 1: /* Bound violation. */
-		info = mpx_generate_siginfo(regs, xsave_buf);
+		info = mpx_generate_siginfo(regs, tsk);
 		if (IS_ERR(info)) {
 			/*
 			 * We failed to decode the MPX instruction.  Act as if

arch/x86/mm/mpx.c

@@ -272,9 +272,9 @@ bad_opcode:
  * The caller is expected to kfree() the returned siginfo_t.
  */
 siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xregs_state *xsave_buf)
+				struct task_struct *tsk)
 {
-	struct bndreg *bndregs, *bndreg;
+	const struct bndreg *bndregs, *bndreg;
 	siginfo_t *info = NULL;
 	struct insn insn;
 	uint8_t bndregno;
@@ -294,8 +294,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
-	/* get the bndregs _area_ of the xsave structure */
-	bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+	/* get bndregs field from current task's xsave area */
+	bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -342,7 +342,7 @@ err_out:
 
 static __user void *task_get_bounds_dir(struct task_struct *tsk)
 {
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX))
 		return MPX_INVALID_BOUNDS_DIR;
@@ -357,8 +357,7 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	copy_fpregs_to_fpstate(&tsk->thread.fpu);
-	bndcsr = get_xsave_addr(&tsk->thread.fpu.state.xsave, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -389,9 +388,10 @@ int mpx_enable_management(struct task_struct *tsk)
 	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
 	 * XRSTOR instruction.
 	 *
-	 * copy_xregs_to_kernel() is expected to be very expensive. Storing the bounds
-	 * directory here means that we do not have to do xsave in the unmap
-	 * path; we can just use mm->bd_addr instead.
+	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+	 * expected to be relatively expensive. Storing the bounds
+	 * directory here means that we do not have to do xsave in the
+	 * unmap path; we can just use mm->bd_addr instead.
 	 */
 	bd_base = task_get_bounds_dir(tsk);
 	down_write(&mm->mmap_sem);
@@ -497,12 +497,12 @@ out_unmap:
  * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
  * and the size of each bound table is 4MB.
  */
-static int do_mpx_bt_fault(struct xregs_state *xsave_buf)
+static int do_mpx_bt_fault(struct task_struct *tsk)
 {
 	unsigned long bd_entry, bd_base;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*
@@ -525,7 +525,7 @@ static int do_mpx_bt_fault(struct xregs_state *xsave_buf)
 	return allocate_bt((long __user *)bd_entry);
 }
 
-int mpx_handle_bd_fault(struct xregs_state *xsave_buf)
+int mpx_handle_bd_fault(struct task_struct *tsk)
 {
 	/*
 	 * Userspace never asked us to manage the bounds tables,
@@ -534,7 +534,7 @@ int mpx_handle_bd_fault(struct xregs_state *xsave_buf)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault(xsave_buf)) {
+	if (do_mpx_bt_fault(tsk)) {
 		force_sig(SIGSEGV, current);
 		/*
 		 * The force_sig() is essentially "handling" this