[PATCH 03/19] x86, mpx: use new tsk_get_xsave_addr()

From: Dave Hansen
Date: Fri May 08 2015 - 14:59:48 EST



From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

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
tsk_get_xsave_addr() calls unlazy_fpu() instead and properly
disables preemption.

Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: bp@xxxxxxxxx
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Suresh Siddha <sbsiddha@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: the arch/x86 maintainers <x86@xxxxxxxxxx>
Cc: linux-kernel <linux-kernel@xxxxxxxxxxxxxxx>
---

b/arch/x86/include/asm/mpx.h | 8 ++++----
b/arch/x86/kernel/traps.c | 15 +++++++--------
b/arch/x86/mm/mpx.c | 23 +++++++++++------------
3 files changed, 22 insertions(+), 24 deletions(-)

diff -puN arch/x86/include/asm/mpx.h~use-new-tsk_get_xsave_addr arch/x86/include/asm/mpx.h
--- a/arch/x86/include/asm/mpx.h~use-new-tsk_get_xsave_addr 2015-05-08 11:46:11.385599446 -0700
+++ b/arch/x86/include/asm/mpx.h 2015-05-08 11:46:11.392599762 -0700
@@ -60,8 +60,8 @@

#ifdef CONFIG_X86_INTEL_MPX
siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf);
-int mpx_handle_bd_fault(struct xsave_struct *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 *
unsigned long start, unsigned long end);
#else
static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf)
+ struct task_struct *tsk)
{
return NULL;
}
-static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+static inline int mpx_handle_bd_fault(struct task_struct *tsk)
{
return -EINVAL;
}
diff -puN arch/x86/kernel/traps.c~use-new-tsk_get_xsave_addr arch/x86/kernel/traps.c
--- a/arch/x86/kernel/traps.c~use-new-tsk_get_xsave_addr 2015-05-08 11:46:11.387599536 -0700
+++ b/arch/x86/kernel/traps.c 2015-05-08 11:46:11.392599762 -0700
@@ -61,6 +61,7 @@
#include <asm/mach_traps.h>
#include <asm/alternative.h>
#include <asm/mpx.h>
+#include <asm/xsave.h>

#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -372,7 +373,6 @@ dotraplinkage void do_double_fault(struc
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk = current;
- struct xsave_struct *xsave_buf;
enum ctx_state prev_state;
struct bndcsr *bndcsr;
siginfo_t *info;
@@ -393,12 +393,11 @@ dotraplinkage void do_bounds(struct pt_r

/*
* 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.
*/
- fpu_save_init(&tsk->thread.fpu);
- xsave_buf = &(tsk->thread.fpu.state->xsave);
- bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field(XSTATE_BNDCSR);
if (!bndcsr)
goto exit_trap;

@@ -409,11 +408,11 @@ dotraplinkage void do_bounds(struct pt_r
*/
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
diff -puN arch/x86/mm/mpx.c~use-new-tsk_get_xsave_addr arch/x86/mm/mpx.c
--- a/arch/x86/mm/mpx.c~use-new-tsk_get_xsave_addr 2015-05-08 11:46:11.388599581 -0700
+++ b/arch/x86/mm/mpx.c 2015-05-08 11:46:11.393599807 -0700
@@ -273,7 +273,7 @@ bad_opcode:
* The caller is expected to kfree() the returned siginfo_t.
*/
siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
- struct xsave_struct *xsave_buf)
+ struct task_struct *tsk)
{
struct bndreg *bndregs, *bndreg;
siginfo_t *info = NULL;
@@ -295,8 +295,8 @@ siginfo_t *mpx_generate_siginfo(struct p
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 urrent task's xsave area */
+ bndregs = get_xsave_field(XSTATE_BNDREGS);
if (!bndregs) {
err = -EINVAL;
goto err_out;
@@ -358,8 +358,7 @@ static __user void *task_get_bounds_dir(
* The bounds directory pointer is stored in a register
* only accessible if we first do an xsave.
*/
- fpu_save_init(&tsk->thread.fpu);
- bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field(XSTATE_BNDCSR);
if (!bndcsr)
return MPX_INVALID_BOUNDS_DIR;

@@ -390,9 +389,9 @@ int mpx_enable_management(struct task_st
* directory into XSAVE/XRSTOR Save Area and enable MPX through
* XRSTOR instruction.
*
- * fpu_xsave() 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.
+ * xsaves are 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.
*/
bd_base = task_get_bounds_dir(tsk);
down_write(&mm->mmap_sem);
@@ -498,12 +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 xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(struct task_struct *tsk)
{
unsigned long bd_entry, bd_base;
struct bndcsr *bndcsr;

- bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ bndcsr = get_xsave_field(XSTATE_BNDCSR);
if (!bndcsr)
return -EINVAL;
/*
@@ -526,7 +525,7 @@ static int do_mpx_bt_fault(struct xsave_
return allocate_bt((long __user *)bd_entry);
}

-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(struct task_struct *tsk)
{
/*
* Userspace never asked us to manage the bounds tables,
@@ -535,7 +534,7 @@ int mpx_handle_bd_fault(struct xsave_str
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
_
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/