@@ -130,6 +130,9 @@ typedef struct {
u32 pkey_allocation_map;
s16 execute_only_pkey; /* key holding execute-only protection */
#endif
+
+ /* Do not preload SLB entries from thread_info during switch_slb() */
+ bool skip_slb_preload;
} mm_context_t;
static inline u16 mm_ctx_user_psize(mm_context_t *ctx)
@@ -298,6 +298,19 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm,
return 0;
}
+#ifdef CONFIG_PPC_BOOK3S_64
+
+static inline void skip_slb_preload_mm(struct mm_struct *mm)
+{
+ mm->context.skip_slb_preload = true;
+}
+
+#else
+
+static inline void skip_slb_preload_mm(struct mm_struct *mm) {}
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
#include <asm-generic/mmu_context.h>
#endif /* __KERNEL__ */
@@ -202,6 +202,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
atomic_set(&mm->context.active_cpus, 0);
atomic_set(&mm->context.copros, 0);
+ mm->context.skip_slb_preload = false;
+
return 0;
}
@@ -441,10 +441,39 @@ static void slb_cache_slbie_user(unsigned int index)
asm volatile("slbie %0" : : "r" (slbie_data));
}
+static void preload_slb_entries(struct task_struct *tsk, struct mm_struct *mm)
+{
+ struct thread_info *ti = task_thread_info(tsk);
+ unsigned char i;
+
+ /*
+ * We gradually age out SLBs after a number of context switches to
+ * reduce reload overhead of unused entries (like we do with FP/VEC
+ * reload). Each time we wrap 256 switches, take an entry out of the
+ * SLB preload cache.
+ */
+ tsk->thread.load_slb++;
+ if (!tsk->thread.load_slb) {
+ unsigned long pc = KSTK_EIP(tsk);
+
+ preload_age(ti);
+ preload_add(ti, pc);
+ }
+
+ for (i = 0; i < ti->slb_preload_nr; i++) {
+ unsigned char idx;
+ unsigned long ea;
+
+ idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR;
+ ea = (unsigned long)ti->slb_preload_esid[idx] << SID_SHIFT;
+
+ slb_allocate_user(mm, ea);
+ }
+}
+
/* Flush all user entries from the segment table of the current processor. */
void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
{
- struct thread_info *ti = task_thread_info(tsk);
unsigned char i;
/*
@@ -502,29 +531,8 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
copy_mm_to_paca(mm);
- /*
- * We gradually age out SLBs after a number of context switches to
- * reduce reload overhead of unused entries (like we do with FP/VEC
- * reload). Each time we wrap 256 switches, take an entry out of the
- * SLB preload cache.
- */
- tsk->thread.load_slb++;
- if (!tsk->thread.load_slb) {
- unsigned long pc = KSTK_EIP(tsk);
-
- preload_age(ti);
- preload_add(ti, pc);
- }
-
- for (i = 0; i < ti->slb_preload_nr; i++) {
- unsigned char idx;
- unsigned long ea;
-
- idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR;
- ea = (unsigned long)ti->slb_preload_esid[idx] << SID_SHIFT;
-
- slb_allocate_user(mm, ea);
- }
+ if (!mm->context.skip_slb_preload)
+ preload_slb_entries(tsk, mm);
/*
* Synchronize slbmte preloads with possible subsequent user memory
Switching to a different mm with Hash translation causes SLB entries to be preloaded from the current thread_info. This reduces SLB faults, for example when threads share a common mm but operate on different address ranges. Preloading entries from the thread_info struct may not always be appropriate - such as when switching to a temporary mm. Introduce a new boolean in mm_context_t to skip the SLB preload entirely. Also move the SLB preload code into a separate function since switch_slb() is already quite long. The default behavior (preloading SLB entries from the current thread_info struct) remains unchanged. Signed-off-by: Christopher M. Riedl <cmr@bluescreens.de> --- v4: * New to series. --- arch/powerpc/include/asm/book3s/64/mmu.h | 3 ++ arch/powerpc/include/asm/mmu_context.h | 13 ++++++ arch/powerpc/mm/book3s64/mmu_context.c | 2 + arch/powerpc/mm/book3s64/slb.c | 56 ++++++++++++++---------- 4 files changed, 50 insertions(+), 24 deletions(-)