Thread (79 messages) 79 messages, 4 authors, 2016-06-24
STALE3670d REVIEWED: 1 (0M)

[PATCH 4.4 57/75] sparc64: Take ctx_alloc_lock properly in hugetlb_setup().

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: 2016-06-22 23:13:56
Also in: lkml

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "David S. Miller" <davem@davemloft.net>

[ Upstream commit 9ea46abe22550e3366ff7cee2f8391b35b12f730 ]

On cheetahplus chips we take the ctx_alloc_lock in order to
modify the TLB lookup parameters for the indexed TLBs, which
are stored in the context register.

This is called with interrupts disabled, however ctx_alloc_lock
is an IRQ safe lock, therefore we must take acquire/release it
properly with spin_{lock,unlock}_irq().

Reported-by: Meelis Roos <redacted>
Tested-by: Meelis Roos <redacted>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/sparc/mm/init_64.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2821,9 +2821,10 @@ void hugetlb_setup(struct pt_regs *regs)
 	 * the Data-TLB for huge pages.
 	 */
 	if (tlb_type == cheetah_plus) {
+		bool need_context_reload = false;
 		unsigned long ctx;
 
-		spin_lock(&ctx_alloc_lock);
+		spin_lock_irq(&ctx_alloc_lock);
 		ctx = mm->context.sparc64_ctx_val;
 		ctx &= ~CTX_PGSZ_MASK;
 		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@@ -2842,9 +2843,12 @@ void hugetlb_setup(struct pt_regs *regs)
 			 * also executing in this address space.
 			 */
 			mm->context.sparc64_ctx_val = ctx;
-			on_each_cpu(context_reload, mm, 0);
+			need_context_reload = true;
 		}
-		spin_unlock(&ctx_alloc_lock);
+		spin_unlock_irq(&ctx_alloc_lock);
+
+		if (need_context_reload)
+			on_each_cpu(context_reload, mm, 0);
 	}
 }
 #endif

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help