From 2ac02e5ecec0cc2484d60a73b1bc6394aa2fad28 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Wed, 3 Feb 2021 10:28:12 +0530
Subject: [PATCH] powerpc/mm: Remove dcache flush from memory remove.

References: bsc#1196433 ltc#196449
Patch-mainline: v5.12-rc1
Git-commit: 2ac02e5ecec0cc2484d60a73b1bc6394aa2fad28

We added dcache flush on memory add/remove in commit
fb5924fddf9e ("powerpc/mm: Flush cache on memory hot(un)plug") to
handle crashes on GPU hotplug. Instead of adding dcache flush in
generic memory add/remove routine which is used even for regular
memory, we should handle these devices specific flush in the device
driver code.

memtrace did handle this in the driver and that was removed by commit
7fd6641de28f ("powerpc/powernv/memtrace: Let the arch hotunplug code
flush cache"). This patch reverts that commit.

The dcache flush in memory add was removed by commit
ea458effa88e ("powerpc: Don't flush caches when adding memory") which
I don't think is correct. The reason why we require dcache flush in
memtrace is to make sure we don't have a dirty cache when we remap a
pfn to cache inhibited. We should do that when the memtrace module
removes the memory and make the pfn available for HTM traces to map it
as cache inhibited.

The other device mentioned in commit fb5924fddf9e ("powerpc/mm: Flush
cache on memory hot(un)plug") is nvlink device with coherent memory.
The support for that was removed in commit
7eb3cf761927 ("powerpc/powernv: remove unused NPU DMA code") and
commit 25b2995a35b6 ("mm: remove MEMORY_DEVICE_PUBLIC support")

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210203045812.234439-3-aneesh.kumar@linux.ibm.com
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/mm/mem.c                     | 22 -----------------
 arch/powerpc/platforms/powernv/memtrace.c | 29 +++++++++++++++++++++++
 2 files changed, 29 insertions(+), 22 deletions(-)

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -107,27 +107,6 @@ int __weak remove_section_mapping(unsign
 	return -ENODEV;
 }
 
-#define FLUSH_CHUNK_SIZE SZ_1G
-/**
- * flush_dcache_range_chunked(): Write any modified data cache blocks out to
- * memory and invalidate them, in chunks of up to FLUSH_CHUNK_SIZE
- * Does not invalidate the corresponding instruction cache blocks.
- *
- * @start: the start address
- * @stop: the stop address (exclusive)
- * @chunk: the max size of the chunks
- */
-static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
-				       unsigned long chunk)
-{
-	unsigned long i;
-
-	for (i = start; i < stop; i += chunk) {
-		flush_dcache_range(i, min(stop, i + chunk));
-		cond_resched();
-	}
-}
-
 int __ref arch_add_memory(int nid, u64 start, u64 size,
 			  struct mhp_params *params)
 {
@@ -158,7 +137,6 @@ void __ref arch_remove_memory(int nid, u
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
-	flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE);
 
 	ret = remove_section_mapping(start, start + size);
 	WARN_ON_ONCE(ret);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -19,6 +19,7 @@
 #include <linux/numa.h>
 #include <asm/machdep.h>
 #include <asm/debugfs.h>
+#include <asm/cacheflush.h>
 
 /* This enables us to keep track of the memory removed from each node. */
 struct memtrace_entry {
@@ -68,6 +69,27 @@ static int change_memblock_state(struct
 	return 0;
 }
 
+#define FLUSH_CHUNK_SIZE SZ_1G
+/**
+ * flush_dcache_range_chunked(): Write any modified data cache blocks out to
+ * memory and invalidate them, in chunks of up to FLUSH_CHUNK_SIZE
+ * Does not invalidate the corresponding instruction cache blocks.
+ *
+ * @start: the start address
+ * @stop: the stop address (exclusive)
+ * @chunk: the max size of the chunks
+ */
+static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
+				       unsigned long chunk)
+{
+	unsigned long i;
+
+	for (i = start; i < stop; i += chunk) {
+		flush_dcache_range(i, min(stop, i + chunk));
+		cond_resched();
+	}
+}
+
 static void memtrace_clear_range(unsigned long start_pfn,
 				 unsigned long nr_pages)
 {
@@ -83,6 +105,13 @@ static void memtrace_clear_range(unsigne
 			cond_resched();
 		clear_page(__va(PFN_PHYS(pfn)));
 	}
+	/*
+	 * Before we go ahead and use this range as cache inhibited range
+	 * flush the cache.
+	 */
+	flush_dcache_range_chunked(PFN_PHYS(start_pfn),
+				   PFN_PHYS(start_pfn + nr_pages),
+				   FLUSH_CHUNK_SIZE);
 }
 
 /* called with device_hotplug_lock held */