MIPS: tlbex: Fix build_restore_pagemask KScratch restore

commit b42aa3fd upstream.

build_restore_pagemask() will restore the value of register $1/$at when
its restore_scratch argument is non-zero, and aims to do so by filling a
branch delay slot. Commit 0b24cae4 ("MIPS: Add missing EHB in mtc0
-> mfc0 sequence.") added an EHB instruction (Execution Hazard Barrier)
prior to restoring $1 from a KScratch register, in order to resolve a
hazard that can result in stale values of the KScratch register being
observed. In particular, P-class CPUs from MIPS with out of order
execution pipelines such as the P5600 & P6600 are affected.

Unfortunately this EHB instruction was inserted in the branch delay slot
causing the MFC0 instruction which performs the restoration to no longer
execute along with the branch. The result is that the $1 register isn't
actually restored, ie. the TLB refill exception handler clobbers it -
which is exactly the problem the EHB is meant to avoid for the P-class
CPUs.

Similarly build_get_pgd_vmalloc() will restore the value of $1/$at when
its mode argument equals refill_scratch, and suffers from the same
problem.

Fix this by in both cases moving the EHB earlier in the emitted code.
There's no reason it needs to immediately precede the MFC0 - it simply
needs to be between the MTC0 & MFC0.

This bug only affects Cavium Octeon systems which use
build_fast_tlb_refill_handler().
Signed-off-by: Paul Burton <paulburton@kernel.org>
Fixes: 0b24cae4 ("MIPS: Add missing EHB in mtc0 -> mfc0 sequence.")
Cc: Dmitry Korotin <dkorotin@wavecomp.com>
Cc: stable@vger.kernel.org # v3.15+
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/mips/mm/tlbex.c

@@ -654,6 +654,13 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r,
 				   int restore_scratch)
 {
 	if (restore_scratch) {
+		/*
+		 * Ensure the MFC0 below observes the value written to the
+		 * KScratch register by the prior MTC0.
+		 */
+		if (scratch_reg >= 0)
+			uasm_i_ehb(p);
+
 		/* Reset default page size */
 		if (PM_DEFAULT_MASK >> 16) {
 			uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16);
@@ -668,12 +675,10 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r,
 			uasm_i_mtc0(p, 0, C0_PAGEMASK);
 			uasm_il_b(p, r, lid);
 		}
-		if (scratch_reg >= 0) {
-			uasm_i_ehb(p);
+		if (scratch_reg >= 0)
 			UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
-		} else {
+		else
 			UASM_i_LW(p, 1, scratchpad_offset(0), 0);
-		}
 	} else {
 		/* Reset default page size */
 		if (PM_DEFAULT_MASK >> 16) {
@@ -922,6 +927,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 	}
 	if (mode != not_refill && check_for_high_segbits) {
 		uasm_l_large_segbits_fault(l, *p);
+
+		if (mode == refill_scratch && scratch_reg >= 0)
+			uasm_i_ehb(p);
+
 		/*
 		 * We get here if we are an xsseg address, or if we are
 		 * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary.
@@ -938,12 +947,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		uasm_i_jr(p, ptr);
 
 		if (mode == refill_scratch) {
-			if (scratch_reg >= 0) {
-				uasm_i_ehb(p);
+			if (scratch_reg >= 0)
 				UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
-			} else {
+			else
 				UASM_i_LW(p, 1, scratchpad_offset(0), 0);
-			}
 		} else {
 			uasm_i_nop(p);
 		}