powerpc/mm: Evaluate user_mode(regs) only once in do_page_fault()

Analysis of the assembly code shows that when using user_mode(regs),
at least the 'andi.' is redone all the time, and also
the 'lwz ,132(r31)' most of the time. With the new form, the 'is_user'
is mapped to cr4, then all further use of is_user results in just
things like 'beq cr4,218 <do_page_fault+0x218>'

Without the patch:

  50:	81 1e 00 84 	lwz     r8,132(r30)
  54:	71 09 40 00 	andi.   r9,r8,16384
  58:	40 82 00 0c 	bne     64 <do_page_fault+0x64>

  84:	81 3e 00 84 	lwz     r9,132(r30)
  8c:	71 2a 40 00 	andi.   r10,r9,16384
  90:	41 a2 01 64 	beq     1f4 <do_page_fault+0x1f4>

  d4:	81 3e 00 84 	lwz     r9,132(r30)
  dc:	71 28 40 00 	andi.   r8,r9,16384
  e0:	41 82 02 08 	beq     2e8 <do_page_fault+0x2e8>

 108:	81 3e 00 84 	lwz     r9,132(r30)
 110:	71 28 40 00 	andi.   r8,r9,16384
 118:	41 82 02 28 	beq     340 <do_page_fault+0x340>

 1e4:	81 3e 00 84 	lwz     r9,132(r30)
 1e8:	71 2a 40 00 	andi.   r10,r9,16384
 1ec:	40 82 01 68 	bne     354 <do_page_fault+0x354>

 228:	81 3e 00 84 	lwz     r9,132(r30)
 22c:	71 28 40 00 	andi.   r8,r9,16384
 230:	41 82 ff c4 	beq     1f4 <do_page_fault+0x1f4>

 288:	71 2a 40 00 	andi.   r10,r9,16384
 294:	41 a2 fe 60 	beq     f4 <do_page_fault+0xf4>

 50c:	81 3e 00 84 	lwz     r9,132(r30)
 514:	71 2a 40 00 	andi.   r10,r9,16384
 518:	40 a2 fc e0 	bne     1f8 <do_page_fault+0x1f8>

 534:	81 3e 00 84 	lwz     r9,132(r30)
 53c:	71 2a 40 00 	andi.   r10,r9,16384
 540:	41 82 fc b8 	beq     1f8 <do_page_fault+0x1f8>

This patch creates a local var called 'is_user' which contains the
result of user_mode(regs)

With the patch:

  20:	81 03 00 84 	lwz     r8,132(r3)
  48:	55 09 97 fe 	rlwinm  r9,r8,18,31,31
  58:	2e 09 00 00 	cmpwi   cr4,r9,0
  5c:	40 92 00 0c 	bne     cr4,68 <do_page_fault+0x68>

  88:	41 b2 01 90 	beq     cr4,218 <do_page_fault+0x218>

  d4:	40 92 01 d0 	bne     cr4,2a4 <do_page_fault+0x2a4>

 120:	41 b2 00 f8 	beq     cr4,218 <do_page_fault+0x218>

 138:	41 b2 ff a0 	beq     cr4,d8 <do_page_fault+0xd8>

 1d4:	40 92 00 e0 	bne     cr4,2b4 <do_page_fault+0x2b4>

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit is contained in:
Christophe Leroy 2017-04-19 14:56:30 +02:00 committed by Michael Ellerman
parent 97a011e69b
commit da929f6af4

View file

@ -206,6 +206,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
int is_write = 0;
int trap = TRAP(regs);
int is_exec = trap == 0x400;
int is_user = user_mode(regs);
int fault;
int rc = 0, store_update_sp = 0;
@ -247,7 +248,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
* The kernel should never take an execute fault nor should it
* take a page fault to a kernel address.
*/
if (!user_mode(regs) && (is_exec || (address >= TASK_SIZE))) {
if (!is_user && (is_exec || (address >= TASK_SIZE))) {
rc = SIGSEGV;
goto bail;
}
@ -266,7 +267,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
local_irq_enable();
if (faulthandler_disabled() || mm == NULL) {
if (!user_mode(regs)) {
if (!is_user) {
rc = SIGSEGV;
goto bail;
}
@ -287,10 +288,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
* can result in fault, which will cause a deadlock when called with
* mmap_sem held
*/
if (is_write && user_mode(regs))
if (is_write && is_user)
store_update_sp = store_updates_sp(regs);
if (user_mode(regs))
if (is_user)
flags |= FAULT_FLAG_USER;
/* When running in the kernel we expect faults to occur only to
@ -309,7 +310,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
* thus avoiding the deadlock.
*/
if (!down_read_trylock(&mm->mmap_sem)) {
if (!user_mode(regs) && !search_exception_tables(regs->nip))
if (!is_user && !search_exception_tables(regs->nip))
goto bad_area_nosemaphore;
retry:
@ -509,7 +510,7 @@ bad_area:
bad_area_nosemaphore:
/* User mode accesses cause a SIGSEGV */
if (user_mode(regs)) {
if (is_user) {
_exception(SIGSEGV, regs, code, address);
goto bail;
}