KMALLOC_PARTITION_CACHES creates several copies of each normal kmalloc
cache and spreads allocations across them. That costs a fair bit of
memory: Harry measured about 18 MiB more slab memory after boot on a 64
CPU, 64 GiB VM, mostly from under-used slabs [1]. Like SLAB_BUCKETS, it
can only be chosen at build time.

Add a kmalloc_partition= early parameter, enabled by default on kernels
built with CONFIG_KMALLOC_PARTITION_CACHES=y. When it's off, the copies
alias the normal caches rather than being created.

Let's leave kmalloc_type() unchanged since each index simply resolves to
the same cache when partitioning is off.

Link: https://lore.kernel.org/r/179312451613.474906.1475329637924619088@kernel.org [1]
Signed-off-by: Chris Down <chris@chrisdown.name>
---
 .../admin-guide/kernel-parameters.txt         |  7 ++++++
 mm/Kconfig                                    |  5 ++++
 mm/slab_common.c                              | 23 +++++++++++++++----
 3 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c27bbe205051..91caeef33c3a 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3045,6 +3045,13 @@ Kernel parameters
 			Configure the RouterBoard 532 series on-chip
 			Ethernet adapter MAC address.
 
+	kmalloc_partition= [MM,EARLY]
+			Format: <bool>
+			Enable or disable kmalloc cache partitioning on
+			kernels built with CONFIG_KMALLOC_PARTITION_CACHES=y.
+			Ignored without that option.
+			Default: on.
+
 	kmemleak=	[KNL,EARLY] Boot-time kmemleak enable/disable
 			Valid arguments: on, off
 			Default: on
diff --git a/mm/Kconfig b/mm/Kconfig
index e602ebabd6e4..5bb6e33fab49 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -266,6 +266,11 @@ config KMALLOC_PARTITION_CACHES
 	  limited degree of memory and CPU overhead that relates to hardware
 	  and system workload.
 
+	  The partitioning can be disabled at boot with the
+	  "kmalloc_partition=0" kernel parameter, in which case the copies
+	  are not created and all normal kmalloc allocations use the
+	  regular kmalloc caches.
+
 choice
 	prompt "Partitioned slab cache mode"
 	depends on KMALLOC_PARTITION_CACHES
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 5575706b8938..20b066d61703 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -781,6 +781,17 @@ unsigned long random_kmalloc_seed __ro_after_init;
 EXPORT_SYMBOL(random_kmalloc_seed);
 #endif
 
+static bool kmalloc_partition_enabled __ro_after_init =
+	IS_ENABLED(CONFIG_KMALLOC_PARTITION_CACHES);
+
+static int __init setup_kmalloc_partition(char *str)
+{
+	if (!IS_ENABLED(CONFIG_KMALLOC_PARTITION_CACHES))
+		return 0;
+	return kstrtobool(str, &kmalloc_partition_enabled);
+}
+early_param("kmalloc_partition", setup_kmalloc_partition);
+
 /*
  * Conversion table for small slabs sizes / 8 to the index in the
  * kmalloc array. This is necessary for slabs < 192 since we have non power
@@ -1012,10 +1023,14 @@ new_kmalloc_cache(int idx, enum kmalloc_cache_type type)
 		flags |= SLAB_CACHE_DMA;
 	}
 
-#ifdef CONFIG_KMALLOC_PARTITION_CACHES
-	if (type >= KMALLOC_PARTITION_START && type <= KMALLOC_PARTITION_END)
-		flags |= SLAB_NO_MERGE;
-#endif
+	if (kmalloc_partition_enabled) {
+		if (type >= KMALLOC_PARTITION_START && type <= KMALLOC_PARTITION_END)
+			flags |= SLAB_NO_MERGE;
+	} else if (type > KMALLOC_PARTITION_START && type <= KMALLOC_PARTITION_END) {
+		/* Use the normal caches, which have already been created. */
+		kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx];
+		return;
+	}
 
 	/*
 	 * If memcg_kmem is enabled and this is a KMALLOC_NORMAL cache and not
-- 
2.56.1