From d504bed676caad29a3dba3d3727298c560628f5c Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Mon, 10 May 2010 20:28:26 +0000
Subject: powerpc/kexec: Speedup kexec hash PTE tear down

Currently for kexec the PTE tear down on 1TB segment systems normally
requires 3 hcalls for each PTE removal. On a machine with 32GB of
memory it can take around a minute to remove all the PTEs.

This optimises the path so that we only remove PTEs that are valid.
It also uses the read 4 PTEs at once HCALL.  For the common case where
a PTEs is invalid in a 1TB segment, this turns the 3 HCALLs per PTE
down to 1 HCALL per 4 PTEs.

This gives an > 10x speedup in kexec times on PHYP, taking a 32GB
machine from around 1 minute down to a few seconds.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 0707653..cf79b46 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -367,21 +367,28 @@ static void pSeries_lpar_hptab_clear(void)
 {
 	unsigned long size_bytes = 1UL << ppc64_pft_size;
 	unsigned long hpte_count = size_bytes >> 4;
-	unsigned long dummy1, dummy2, dword0;
+	struct {
+		unsigned long pteh;
+		unsigned long ptel;
+	} ptes[4];
 	long lpar_rc;
-	int i;
+	int i, j;
 
-	/* TODO: Use bulk call */
-	for (i = 0; i < hpte_count; i++) {
-		/* dont remove HPTEs with VRMA mappings */
-		lpar_rc = plpar_pte_remove_raw(H_ANDCOND, i, HPTE_V_1TB_SEG,
-						&dummy1, &dummy2);
-		if (lpar_rc == H_NOT_FOUND) {
-			lpar_rc = plpar_pte_read_raw(0, i, &dword0, &dummy1);
-			if (!lpar_rc && ((dword0 & HPTE_V_VRMA_MASK)
-				!= HPTE_V_VRMA_MASK))
-				/* Can be hpte for 1TB Seg. So remove it */
-				plpar_pte_remove_raw(0, i, 0, &dummy1, &dummy2);
+	/* Read in batches of 4,
+	 * invalidate only valid entries not in the VRMA
+	 * hpte_count will be a multiple of 4
+         */
+	for (i = 0; i < hpte_count; i += 4) {
+		lpar_rc = plpar_pte_read_4_raw(0, i, (void *)ptes);
+		if (lpar_rc != H_SUCCESS)
+			continue;
+		for (j = 0; j < 4; j++){
+			if ((ptes[j].pteh & HPTE_V_VRMA_MASK) ==
+				HPTE_V_VRMA_MASK)
+				continue;
+			if (ptes[j].pteh & HPTE_V_VALID)
+				plpar_pte_remove_raw(0, i + j, 0,
+					&(ptes[j].pteh), &(ptes[j].ptel));
 		}
 	}
 }
-- 
cgit v0.10.2