[PATCH v4 10/21] powerpc/64s/hash: improve context tracking of hash faults

[Nicholas Piggin]

This moves the 64s/hash context tracking from hash_page_mm() to
__do_hash_fault(), so it's no longer called by OCXL / SPU
accelerators, which was certainly the wrong thing to be doing,
because those callers are not low level interrupt handlers, so
should have entered a kernel context tracking already.

Then remain in kernel context for the duration of the fault,
rather than enter/exit for the hash fault then enter/exit for
the page fault, which is pointless.

Even still, calling exception_enter/exit in __do_hash_fault seems
questionable because that's touching per-cpu variables, tracing,
etc., which might have been interrupted by this hash fault or
themselves cause hash faults. But maybe I miss something because
hash_page_mm very deliberately calls trace_hash_fault too, for
example. So for now go with it, it's no worse than before, in this
regard.

Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 arch/powerpc/include/asm/bug.h        | 1 +
 arch/powerpc/mm/book3s64/hash_utils.c | 7 ++++---
 arch/powerpc/mm/fault.c               | 9 +++++++++
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 4220789b9a97..e048c820ca02 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -112,6 +112,7 @@
 
 struct pt_regs;
 long do_page_fault(struct pt_regs *);
+long hash__do_page_fault(struct pt_regs *);
 void bad_page_fault(struct pt_regs *, int);
 void __bad_page_fault(struct pt_regs *regs, int sig);
 extern void _exception(int, struct pt_regs *, int, unsigned long);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 453afb9ae9b4..801d5e94cd2b 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1289,7 +1289,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		 unsigned long flags)
 {
 	bool is_thp;
-	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
 	unsigned long vsid;
 	pte_t *ptep;
@@ -1491,7 +1490,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 	DBG_LOW(" -> rc=%d\n", rc);
 
 bail:
-	exception_exit(prev_state);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(hash_page_mm);
@@ -1515,6 +1513,7 @@ EXPORT_SYMBOL_GPL(hash_page);
 
 DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 {
+	enum ctx_state prev_state = exception_enter();
 	unsigned long ea = regs->dar;
 	unsigned long dsisr = regs->dsisr;
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
@@ -1563,9 +1562,11 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
 		err = 0;
 
 	} else if (err) {
-		err = do_page_fault(regs);
+		err = hash__do_page_fault(regs);
 	}
 
+	exception_exit(prev_state);
+
 	return err;
 }
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 81dbce473726..cc71c93cceaf 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -589,6 +589,15 @@ DEFINE_INTERRUPT_HANDLER_RET(do_page_fault)
 }
 NOKPROBE_SYMBOL(do_page_fault);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/* Same as do_page_fault but interrupt entry has already run in do_hash_fault */
+long hash__do_page_fault(struct pt_regs *regs)
+{
+	return __do_page_fault(regs);
+}
+NOKPROBE_SYMBOL(hash__do_page_fault);
+#endif
+
 /*
  * bad_page_fault is called when we have a bad access from the kernel.
  * It is called from the DSI and ISI handlers in head.S and from some
-- 
2.23.0