@@ -26,6 +26,8 @@
#include <linux/atomic.h>
#include <linux/uaccess.h>
+#include <kunit/visibility.h>
+
#define MEMORY_CLASS_NAME "memory"
static const char *const online_type_to_str[] = {
@@ -183,7 +185,7 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem)
/*
* Must acquire mem_hotplug_lock in write mode.
*/
-static int memory_block_online(struct memory_block *mem)
+VISIBLE_IF_KUNIT int memory_block_online(struct memory_block *mem)
{
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
@@ -250,6 +252,7 @@ static int memory_block_online(struct memory_block *mem)
mem_hotplug_done();
return ret;
}
+EXPORT_SYMBOL_IF_KUNIT(memory_block_online);
/*
* Must acquire mem_hotplug_lock in write mode.
@@ -177,6 +177,10 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
register_memory_notifier(&fn##_mem_nb); \
})
+#ifdef CONFIG_KUNIT
+int memory_block_online(struct memory_block *mem);
+#endif
+
#ifdef CONFIG_NUMA
void memory_block_add_nid(struct memory_block *mem, int nid,
enum meminit_context context);
@@ -536,6 +536,19 @@ static __always_inline int node_random(const nodemask_t *maskp)
#define for_each_node(node) for_each_node_state(node, N_POSSIBLE)
#define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
+
+#ifdef CONFIG_PAGE_ALLOC_KUNIT_TEST
+/*
+ * An isolated node is a fake node for testing, that boots with no memory and no
+ * attached CPUs, and nothing should touch it except for test code.
+ */
+extern bool node_isolated(int node);
+/* Only one isolated node is supported at present and it cannot be un-isolated. */
+extern void node_set_isolated(int node);
+#else
+static inline bool node_isolated(int node) { return false; }
+#endif /* CONFIG_PAGE_ALLOC_KUNIT_TEST */
+
/*
* For nodemask scratch area.
* NODEMASK_ALLOC(type, name) allocates an object with a specified type and
@@ -9,6 +9,7 @@
*/
#include <uapi/linux/sched/types.h>
#include <linux/mm.h>
+#include <linux/mmdebug.h>
#include <linux/mmu_context.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
@@ -511,6 +512,8 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
struct kthread_create_info *create = kmalloc(sizeof(*create),
GFP_KERNEL);
+ VM_WARN_ON(node != NUMA_NO_NODE && node_isolated(node));
+
if (!create)
return ERR_PTR(-ENOMEM);
create->threadfn = threadfn;
@@ -1,2 +1,10 @@
CONFIG_KUNIT=y
-CONFIG_PAGE_ALLOC_KUNIT_TEST=y
\ No newline at end of file
+CONFIG_PAGE_ALLOC_KUNIT_TEST=y
+
+# Required for NUMA
+CONFIG_SMP=y
+# Used by tests to carve out fake node for isolating page_alloc data.
+CONFIG_NUMA=y
+CONFIG_NUMA_EMU=y
+CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTREMOVE=y
\ No newline at end of file
@@ -1360,7 +1360,7 @@ config PT_RECLAIM
config PAGE_ALLOC_KUNIT_TEST
tristate "KUnit test for page allocator" if !KUNIT_ALL_TESTS
- depends on KUNIT
+ depends on KUNIT && NUMA && MEMORY_HOTREMOVE
default KUNIT_ALL_TESTS
help
Builds unit tests for page allocator.
@@ -1545,5 +1545,16 @@ static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
}
#endif /* CONFIG_PT_RECLAIM */
+#ifdef CONFIG_PAGE_ALLOC_KUNIT_TEST
+/*
+ * Note that node_isolated() is separate, that's a "public API". But only
+ * test code needs to look up which node is isolated.
+ */
+extern int isolated_node;
+#endif
+
+#ifdef CONFIG_KUNIT
+void drain_pages(unsigned int cpu);
+#endif
#endif /* __MM_INTERNAL_H */
@@ -1198,10 +1198,12 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
arg.nr_pages = nr_pages;
node_states_check_changes_online(nr_pages, zone, &arg);
- ret = memory_notify(MEM_GOING_ONLINE, &arg);
- ret = notifier_to_errno(ret);
- if (ret)
- goto failed_addition;
+ if (!node_isolated(nid)) {
+ ret = memory_notify(MEM_GOING_ONLINE, &arg);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ goto failed_addition;
+ }
/*
* Fixup the number of isolated pageblocks before marking the sections
@@ -1242,19 +1244,27 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
/* reinitialise watermarks and update pcp limits */
init_per_zone_wmark_min();
- kswapd_run(nid);
- kcompactd_run(nid);
+ /*
+ * Don't run daemons on the special test node, if that needs to be
+ * tested the test should run it.
+ */
+ if (!node_isolated(nid)) {
+ kswapd_run(nid);
+ kcompactd_run(nid);
+ }
writeback_set_ratelimit();
- memory_notify(MEM_ONLINE, &arg);
+ if (!node_isolated(nid))
+ memory_notify(MEM_ONLINE, &arg);
return 0;
failed_addition:
pr_debug("online_pages [mem %#010llx-%#010llx] failed\n",
(unsigned long long) pfn << PAGE_SHIFT,
(((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
- memory_notify(MEM_CANCEL_ONLINE, &arg);
+ if (!node_isolated(nid))
+ memory_notify(MEM_CANCEL_ONLINE, &arg);
remove_pfn_range_from_zone(zone, pfn, nr_pages);
return ret;
}
@@ -7,6 +7,8 @@
#include <linux/numa.h>
#include <linux/numa_memblks.h>
+#include "internal.h"
+
int numa_distance_cnt;
static u8 *numa_distance;
@@ -371,6 +373,24 @@ static void __init numa_clear_kernel_node_hotplug(void)
}
}
+#ifdef CONFIG_PAGE_ALLOC_KUNIT_TEST
+static inline void make_isolated_node(void)
+{
+ int node;
+
+ node = num_possible_nodes();
+ if (!numa_valid_node(node)) {
+ pr_err("All node IDs used, can't fake another.\n");
+ } else {
+ node_set(num_possible_nodes(), node_possible_map);
+ node_set_isolated(node);
+ }
+}
+#else
+static inline void make_isolated_node(void) { }
+#endif
+
+
static int __init numa_register_meminfo(struct numa_meminfo *mi)
{
int i;
@@ -381,6 +401,8 @@ static int __init numa_register_meminfo(struct numa_meminfo *mi)
if (WARN_ON(nodes_empty(node_possible_map)))
return -EINVAL;
+ make_isolated_node();
+
for (i = 0; i < mi->nr_blks; i++) {
struct numa_memblk *mb = &mi->blk[i];
@@ -56,6 +56,7 @@
#include <linux/cacheinfo.h>
#include <linux/pgalloc_tag.h>
#include <asm/div64.h>
+#include <kunit/visibility.h>
#include "internal.h"
#include "shuffle.h"
#include "page_reporting.h"
@@ -291,6 +292,26 @@ static bool __free_unaccepted(struct page *page);
int page_group_by_mobility_disabled __read_mostly;
+/*
+ * Test harness for KUnit - pick a node that we will never allocate from, except
+ * for in the page allocator tests.
+ */
+#ifdef CONFIG_PAGE_ALLOC_KUNIT_TEST
+int isolated_node = NUMA_NO_NODE;
+EXPORT_SYMBOL(isolated_node);
+
+void node_set_isolated(int node)
+{
+ WARN_ON(isolated_node != NUMA_NO_NODE);
+ isolated_node = node;
+}
+
+bool node_isolated(int node)
+{
+ return node == isolated_node;
+}
+#endif /* CONFIG_POAGE_ALLOC_KUNIT_TEST */
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* During boot we initialize deferred pages on-demand, as needed, but once
@@ -2410,7 +2431,7 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
/*
* Drain pcplists of all zones on the indicated processor.
*/
-static void drain_pages(unsigned int cpu)
+VISIBLE_IF_KUNIT void drain_pages(unsigned int cpu)
{
struct zone *zone;
@@ -2418,6 +2439,7 @@ static void drain_pages(unsigned int cpu)
drain_pages_zone(cpu, zone);
}
}
+EXPORT_SYMBOL_IF_KUNIT(drain_pages);
/*
* Spill all of this CPU's per-cpu pages back into the buddy allocator.
@@ -5087,6 +5109,8 @@ int find_next_best_node(int node, nodemask_t *used_node_mask)
}
for_each_node_state(n, N_MEMORY) {
+ if (node_isolated(n))
+ continue;
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
@@ -5134,8 +5158,17 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
for (i = 0; i < nr_nodes; i++) {
int nr_zones;
+ int other_nid = node_order[i];
+ pg_data_t *node = NODE_DATA(other_nid);
- pg_data_t *node = NODE_DATA(node_order[i]);
+ /*
+ * Never fall back to the isolated node. The isolated node has
+ * to be able to fall back to other nodes because that fallback
+ * is relied on for allocating data structures that describe the
+ * node.
+ */
+ if (node_isolated(other_nid) && other_nid != pgdat->node_id)
+ continue;
nr_zones = build_zonerefs_node(node, zonerefs);
zonerefs += nr_zones;
@@ -3,19 +3,157 @@
#include <linux/list.h>
#include <linux/gfp.h>
#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/percpu.h>
#include <linux/smp.h>
#include <kunit/test.h>
+#include "internal.h"
+
+#define EXPECT_PCPLIST_EMPTY(test, zone, cpu, pindex) ({ \
+ struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); \
+ struct page *page; \
+ \
+ lockdep_assert_held(&pcp->lock); \
+ page = list_first_entry_or_null( \
+ &pcp->lists[pindex], struct page, pcp_list); \
+ \
+ if (page) { \
+ KUNIT_FAIL(test, "PCPlist %d on CPU %d wasn't empty", i, cpu); \
+ dump_page(page, "unexpectedly on pcplist"); \
+ } \
+})
+
+static void action_drain_pages_all(void *unused)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ drain_pages(cpu);
+}
+
+/* Runs before each test. */
+static int test_init(struct kunit *test)
+{
+ struct zone *zone_normal;
+ int cpu;
+
+ if (isolated_node == NUMA_NO_NODE)
+ kunit_skip(test, "No fake NUMA node ID allocated");
+
+ zone_normal = &NODE_DATA(isolated_node)->node_zones[ZONE_NORMAL];
+
+ /*
+ * Nothing except these tests should be allocating from the fake node so
+ * the pcplists should be empty. Obviously this is racy but at least it
+ * can probabilistically detect issues that would otherwise make for
+ * really confusing test results.
+ */
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pages *pcp = per_cpu_ptr(zone_normal->per_cpu_pageset, cpu);
+ unsigned long flags;
+ int i;
+
+ spin_lock_irqsave(&pcp->lock, flags);
+ for (i = 0; i < ARRAY_SIZE(pcp->lists); i++)
+ EXPECT_PCPLIST_EMPTY(test, zone_normal, cpu, i);
+ spin_unlock_irqrestore(&pcp->lock, flags);
+ }
+
+ /* Also ensure we don't leave a mess for the next test. */
+ kunit_add_action(test, action_drain_pages_all, NULL);
+
+ return 0;
+}
+
+static int memory_block_online_cb(struct memory_block *mem, void *unused)
+{
+ return memory_block_online(mem);
+}
+
+struct region {
+ int node;
+ unsigned long start;
+ unsigned long size;
+};
+
+/*
+ * Unplug some memory from a "real" node and plug it into the isolated node, for
+ * use during the tests.
+ */
+static int populate_isolated_node(struct kunit_suite *suite)
+{
+ struct zone *zone_movable = &NODE_DATA(0)->node_zones[ZONE_MOVABLE];
+ phys_addr_t zone_start = zone_movable->zone_start_pfn << PAGE_SHIFT;
+ phys_addr_t zone_size = zone_movable->spanned_pages << PAGE_SHIFT;
+ unsigned long bs = memory_block_size_bytes();
+ u64 start = round_up(zone_start, bs);
+ /* Plug a memory block if we can find it. */
+ unsigned long size = round_down(min(zone_size, bs), bs);
+ int err;
+
+ if (!size) {
+ pr_err("Couldn't find ZONE_MOVABLE block to offline\n");
+ pr_err("Try setting/expanding movablecore=\n");
+ return -1;
+ }
+
+ err = offline_and_remove_memory(start, size);
+ if (err) {
+ pr_notice("Couldn't offline PFNs 0x%llx - 0x%llx\n",
+ start >> PAGE_SHIFT, (start + size) >> PAGE_SHIFT);
+ return err;
+ }
+ err = add_memory(isolated_node, start, size, MMOP_ONLINE);
+ if (err) {
+ pr_notice("Couldn't add PFNs 0x%llx - 0x%llx\n",
+ start >> PAGE_SHIFT, (start + size) >> PAGE_SHIFT);
+ goto add_and_online_memory;
+ }
+ err = walk_memory_blocks(start, size, NULL, memory_block_online_cb);
+ if (err) {
+ pr_notice("Couldn't online PFNs 0x%llx - 0x%llx\n",
+ start >> PAGE_SHIFT, (start + size) >> PAGE_SHIFT);
+ goto remove_memory;
+ }
+
+ return 0;
+
+remove_memory:
+ if (WARN_ON(remove_memory(start, size)))
+ return err;
+add_and_online_memory:
+ if (WARN_ON(add_memory(0, start, size, MMOP_ONLINE)))
+ return err;
+ WARN_ON(walk_memory_blocks(start, size, NULL, memory_block_online_cb));
+ return err;
+}
+
+static void depopulate_isolated_node(struct kunit_suite *suite)
+{
+ unsigned long start, size = memory_block_size_bytes();
+
+ if (suite->suite_init_err)
+ return;
+
+ start = NODE_DATA(isolated_node)->node_start_pfn << PAGE_SHIFT;
+
+ WARN_ON(remove_memory(start, size));
+ WARN_ON(add_memory(0, start, size, MMOP_ONLINE));
+ WARN_ON(walk_memory_blocks(start, size, NULL, memory_block_online_cb));
+}
static struct kunit_case test_cases[] = { {} };
-static struct kunit_suite test_suite = {
+struct kunit_suite page_alloc_test_suite = {
.name = "page_alloc",
.test_cases = test_cases,
+ .suite_init = populate_isolated_node,
+ .suite_exit = depopulate_isolated_node,
+ .init = test_init,
};
-kunit_test_suite(test_suite);
+kunit_test_suite(page_alloc_test_suite);
MODULE_LICENSE("GPL");
MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
In order to test the page allocator, we need an "instance" of the page allocator that is not subject to unpredictable perturbation by the live system. The closest thing that we have to an "instance" of the allocator is a NUMA node. So, introduce a new concept of an "isolated" node. This is an extension of the existing concept of a "fake" node, with the addition that nothing else in the system will touch it unless instructed to by the test code. The node is created during boot but has no memory nor any CPUs attached. It is not on any other node's fallback lists. Any code that pays general attention to NODE_DATA in such a way that might cause the page allocator data structures to be modified asynchronously to the test, is enlightened to ignore it via the node_isolated() helper. Then, during initialization of the allocator test suite, hotplug out some memory and then plug it back in to the isolated node. The node can then be used for testing. Because it's easy to miss code that needs enlightenment, which can lead to confusing test behaviour, also add some defensive checks to try and interference with the isolated node before the start of the test. Signed-off-by: Brendan Jackman <jackmanb@google.com> --- drivers/base/memory.c | 5 +- include/linux/memory.h | 4 ++ include/linux/nodemask.h | 13 +++++ kernel/kthread.c | 3 + mm/.kunitconfig | 10 +++- mm/Kconfig | 2 +- mm/internal.h | 11 ++++ mm/memory_hotplug.c | 26 ++++++--- mm/numa_memblks.c | 22 ++++++++ mm/page_alloc.c | 37 +++++++++++- mm/page_alloc_test.c | 142 ++++++++++++++++++++++++++++++++++++++++++++++- 11 files changed, 260 insertions(+), 15 deletions(-)