The mutex of the anon pool is one of the most contended global locks in
UVM.  Diff below makes it use a pool cache on MP kernels.  Without this,
running the upper part of the fault handler in parallel doesn't improve
anything.  This change already gives a small boost on its own.

Note that on LP64 "struct vm_anon" needs to grow a little bit...

ok?

Index: uvm/uvm_anon.c
===================================================================
RCS file: /cvs/src/sys/uvm/uvm_anon.c,v
diff -u -p -r1.62 uvm_anon.c
--- uvm/uvm_anon.c	10 Mar 2025 14:13:58 -0000	1.62
+++ uvm/uvm_anon.c	10 Mar 2025 18:45:51 -0000
@@ -50,6 +50,14 @@ uvm_anon_init(void)
 	pool_sethiwat(&uvm_anon_pool, uvmexp.free / 16);
 }
 
+void
+uvm_anon_init_percpu(void)
+{
+#ifdef MULTIPROCESSOR
+	pool_cache_init(&uvm_anon_pool);
+#endif
+}
+
 /*
  * uvm_analloc: allocate a new anon.
  *
Index: uvm/uvm_anon.h
===================================================================
RCS file: /cvs/src/sys/uvm/uvm_anon.h,v
diff -u -p -r1.22 uvm_anon.h
--- uvm/uvm_anon.h	19 Jan 2021 13:21:36 -0000	1.22
+++ uvm/uvm_anon.h	10 Mar 2025 18:46:25 -0000
@@ -47,6 +47,10 @@ struct vm_anon {
 	 * Drum swap slot # (if != 0) [if we hold an_page, PG_BUSY]
 	 */
 	int an_swslot;
+
+#if defined(MULTIPROCESSOR) && defined(__LP64__)
+	long unused;			/* to match pool_cache_item's size */
+#endif
 };
 
 /*
@@ -84,6 +88,7 @@ void		 uvm_anfree_list(struct vm_anon *,
 void		 uvm_anon_release(struct vm_anon *);
 void		 uvm_anwait(void);
 void		 uvm_anon_init(void);
+void		 uvm_anon_init_percpu(void);
 void		 uvm_anon_dropswap(struct vm_anon *);
 boolean_t	 uvm_anon_pagein(struct vm_amap *, struct vm_anon *);
 
Index: uvm/uvm_init.c
===================================================================
RCS file: /cvs/src/sys/uvm/uvm_init.c,v
diff -u -p -r1.42 uvm_init.c
--- uvm/uvm_init.c	20 Mar 2021 10:24:21 -0000	1.42
+++ uvm/uvm_init.c	10 Mar 2025 18:37:33 -0000
@@ -194,4 +194,6 @@ void
 uvm_init_percpu(void)
 {
 	uvmexp_counters = counters_alloc_ncpus(uvmexp_counters, exp_ncounters);
+
+	uvm_anon_init_percpu();
 }