* [PATCH]: MIPS: Adjust set_pte() SMP fix to handle R10000_LLSC_WAR
@ 2015-09-07 10:42 Joshua Kinard
0 siblings, 0 replies; only message in thread
From: Joshua Kinard @ 2015-09-07 10:42 UTC (permalink / raw)
To: Ralf Baechle; +Cc: Linux/MIPS, Markos Chandras, David Daney
From: Joshua Kinard <kumba@gentoo.org>
Update the recent changes to set_pte() that were added in 46011e6ea392
to handle R10000_LLSC_WAR, and format the assembly to match other areas
of the MIPS tree using the same WAR.
This also incorporates a patch recently sent in my Markos Chandras,
"Remove local LL/SC preprocessor variants", so that patch doesn't need
to be applied if this one is accepted.
Signed-off-by: Joshua Kinard <kumba@gentoo.org>
Fixes: 46011e6ea392 ("MIPS: Make set_pte() SMP safe.)
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: David Daney <david.daney@cavium.com>
---
arch/mips/include/asm/pgtable.h | 52 ++++++++++++++++++------------
1 file changed, 32 insertions(+), 20 deletions(-)
Not sure if 'kernel_uses_llsc' or 'cpu_has_llsc' is appropriate for the
if conditional. I've seen both used in the tree w/ the R10000_LLSC_WAR
construct.
Note: The set_pte() fix appears to be needed for IP27 to boot, so the
original patch and this one may need to be backported. Otherwise, the
heavy disk I/O lockup bug I've mentioned in the past has a higher chance
of triggering and freezing the machine solid, especially if mdraid is
rebuilding a disk. The set_pte() fix won't address that bug, but at
least mdraid was able to finish the rebuild after it was applied.
linux-mips-set_pte-smp-r10k-war.patch
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 8957f15..560bc74 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -187,30 +187,42 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
* For SMP, multiple CPUs can race, so we need to do
* this atomically.
*/
-#ifdef CONFIG_64BIT
-#define LL_INSN "lld"
-#define SC_INSN "scd"
-#else /* CONFIG_32BIT */
-#define LL_INSN "ll"
-#define SC_INSN "sc"
-#endif
unsigned long page_global = _PAGE_GLOBAL;
unsigned long tmp;
- __asm__ __volatile__ (
- " .set push\n"
- " .set noreorder\n"
- "1: " LL_INSN " %[tmp], %[buddy]\n"
- " bnez %[tmp], 2f\n"
- " or %[tmp], %[tmp], %[global]\n"
- " " SC_INSN " %[tmp], %[buddy]\n"
- " beqz %[tmp], 1b\n"
- " nop\n"
- "2:\n"
- " .set pop"
- : [buddy] "+m" (buddy->pte),
- [tmp] "=&r" (tmp)
+ if (kernel_uses_llsc && R10000_LLSC_WAR) {
+ __asm__ __volatile__ (
+ " .set arch=r4000 \n"
+ " .set push \n"
+ " .set noreorder \n"
+ "1:" __LL "%[tmp], %[buddy] \n"
+ " bnez %[tmp], 2f \n"
+ " or %[tmp], %[tmp], %[global] \n"
+ __SC "%[tmp], %[buddy] \n"
+ " beqzl %[tmp], 1b \n"
+ " nop \n"
+ "2: \n"
+ " .set pop \n"
+ " .set mips0 \n"
+ : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
+ : [global] "r" (page_global));
+ } else if (kernel_uses_llsc) {
+ __asm__ __volatile__ (
+ " .set "MIPS_ISA_ARCH_LEVEL" \n"
+ " .set push \n"
+ " .set noreorder \n"
+ "1:" __LL "%[tmp], %[buddy] \n"
+ " bnez %[tmp], 2f \n"
+ " or %[tmp], %[tmp], %[global] \n"
+ __SC "%[tmp], %[buddy] \n"
+ " beqz %[tmp], 1b \n"
+ " nop \n"
+ "2: \n"
+ " .set pop \n"
+ " .set mips0 \n"
+ : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
: [global] "r" (page_global));
+ }
#else /* !CONFIG_SMP */
if (pte_none(*buddy))
pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2015-09-07 10:42 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-09-07 10:42 [PATCH]: MIPS: Adjust set_pte() SMP fix to handle R10000_LLSC_WAR Joshua Kinard
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.