RFC: fault-injection capabilities

Index: work-failmalloc/include/linux/should_fail.h
===================================================================
@@ -0,0 +1,44 @@
+#ifndef _LINUX_SHOULD_FAIL_H
+#define _LINUX_SHOULD_FAIL_H
+
+#ifdef CONFIG_SHOULD_FAIL
+
+#include <linux/types.h>
+#include <asm/atomic.h>
+
+struct should_fail_data {
+
+	/* how often it should fail in percent. */
+	unsigned long probability;
+
+	/* the interval of failures. */
+	unsigned long interval;
+
+	/*
+	 * how many times failures may happen at most.
+	 * A value of '-1' means infinity.
+	 */
+	atomic_t times;
+
+	/*
+	 * the size of free space where memory can be allocated safely.
+	 * A value of '0' means infinity.
+	 */
+	atomic_t space;
+
+	unsigned long count;
+};
+
+#define DEFINE_SHOULD_FAIL(name) \
+	struct should_fail_data name = { .times = ATOMIC_INIT(-1), }
+
+int should_fail(struct should_fail_data *data, unsigned long size);
+int setup_should_fail(struct should_fail_data *data, char *str);
+
+#else
+
+#define should_fail(data, size)	(0)
+
+#endif /* CONFIG_SHOULD_FAIL */
+
+#endif /* _LINUX_SHOULD_FAIL_H */

69 lines not on this page · raw message

Index: work-failmalloc/mm/slab.c
===================================================================
@@ -108,6 +108,7 @@
 #include	<linux/mempolicy.h>
 #include	<linux/mutex.h>
 #include	<linux/rtmutex.h>
+#include	<linux/should_fail.h>
 
 #include	<asm/uaccess.h>
 #include	<asm/cacheflush.h>

@@ -2963,11 +2964,30 @@ static void *cache_alloc_debugcheck_afte
 #define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
 #endif
 
+#ifdef CONFIG_FAILSLAB
+
+static DEFINE_SHOULD_FAIL(failslab_data);
+
+static int __init setup_failslab(char *str)
+{
+	return setup_should_fail(&failslab_data, str);
+}
+__setup("failslab=", setup_failslab);
+
+struct should_fail_data *failslab = &failslab_data;
+EXPORT_SYMBOL_GPL(failslab);
+
+#endif
+
 static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	void *objp;
 	struct array_cache *ac;
 
+	if (!(flags & __GFP_NOFAIL) && cachep != &cache_cache &&
+	    should_fail(failslab, obj_size(cachep)))
+		return NULL;
+
 #ifdef CONFIG_NUMA
 	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
 		objp = alternate_node_alloc(cachep, flags);

Index: work-failmalloc/include/linux/should_fail.h
===================================================================
@@ -35,6 +35,10 @@ struct should_fail_data {
 int should_fail(struct should_fail_data *data, unsigned long size);
 int setup_should_fail(struct should_fail_data *data, char *str);
 
+#ifdef CONFIG_FAILSLAB
+extern struct should_fail_data *failslab;
+#endif
+
 #else
 
 #define should_fail(data, size)	(0)

Index: work-failmalloc/mm/page_alloc.c
===================================================================
@@ -37,6 +37,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mempolicy.h>
 #include <linux/stop_machine.h>
+#include <linux/should_fail.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>

@@ -903,6 +904,21 @@ get_page_from_freelist(gfp_t gfp_mask, u
 	return page;
 }
 
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+
+static DEFINE_SHOULD_FAIL(fail_page_alloc_data);
+
+static int __init setup_fail_page_alloc(char *str)
+{
+	return setup_should_fail(&fail_page_alloc_data, str);
+}
+__setup("fail_page_alloc=", setup_fail_page_alloc);
+
+struct should_fail_data *fail_page_alloc = &fail_page_alloc_data;
+EXPORT_SYMBOL_GPL(fail_page_alloc);
+
+#endif
+
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */

@@ -921,6 +937,10 @@ __alloc_pages(gfp_t gfp_mask, unsigned i
 
 	might_sleep_if(wait);
 
+	if (!(gfp_mask & __GFP_NOFAIL) &&
+	    should_fail(fail_page_alloc, 1 << order))
+		return NULL;
+
 restart:
 	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
 

Index: work-failmalloc/include/linux/should_fail.h
===================================================================
@@ -39,6 +39,10 @@ int setup_should_fail(struct should_fail
 extern struct should_fail_data *failslab;
 #endif
 
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+extern struct should_fail_data *fail_page_alloc;
+#endif
+
 #else
 
 #define should_fail(data, size)	(0)

Index: work-failmalloc/block/ll_rw_blk.c
===================================================================
@@ -28,6 +28,7 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/blktrace_api.h>
+#include <linux/should_fail.h>
 
 /*
  * for max sense size

@@ -2993,6 +2994,21 @@ static void handle_bad_sector(struct bio
 	set_bit(BIO_EOF, &bio->bi_flags);
 }
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static DEFINE_SHOULD_FAIL(fail_make_request_data);
+
+static int __init setup_fail_make_request(char *str)
+{
+	return setup_should_fail(&fail_make_request_data, str);
+}
+__setup("fail_make_request=", setup_fail_make_request);
+
+struct should_fail_data *fail_make_request = &fail_make_request_data;
+EXPORT_SYMBOL_GPL(fail_make_request);
+
+#endif
+
 /**
  * generic_make_request: hand a buffer to its device driver for I/O
  * @bio:  The bio describing the location in memory and on the device.

@@ -3077,6 +3093,9 @@ end_io:
 		if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
 			goto end_io;
 
+		if (should_fail(fail_make_request, bio->bi_size))
+			goto end_io;
+
 		/*
 		 * If this device has partitions, remap block n
 		 * of partition p to block n+start(p) of the disk.

Index: work-failmalloc/include/linux/should_fail.h
===================================================================
@@ -43,6 +43,10 @@ extern struct should_fail_data *failslab
 extern struct should_fail_data *fail_page_alloc;
 #endif
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+extern struct should_fail_data *fail_make_request;
+#endif
+
 #else
 
 #define should_fail(data, size)	(0)

Index: work-failmalloc/lib/should_fail_knobs.c
===================================================================
@@ -0,0 +1,168 @@
+#include <linux/module.h>
+#include <linux/should_fail.h>
+#include <linux/debugfs.h>
+
+struct should_fail_knobs {
+	struct dentry *dir;
+	struct dentry *probability_file;
+	struct dentry *interval_file;
+	struct dentry *times_file;
+	struct dentry *space_file;
+};
+
+static void debugfs_ul_set(void *data, u64 val)
+{
+	*(unsigned long *)data = val;
+}
+
+static u64 debugfs_ul_get(void *data)
+{
+	return *(unsigned long *)data;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_ul, debugfs_ul_get, debugfs_ul_set, "%llu\n");
+
+static struct dentry *debugfs_create_ul(const char *name, mode_t mode,
+				struct dentry *parent, unsigned long *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_ul);
+}
+
+static void debugfs_atomic_t_set(void *data, u64 val)
+{
+	atomic_set((atomic_t *)data, val);
+}
+
+static u64 debugfs_atomic_t_get(void *data)
+{
+	return atomic_read((atomic_t *)data);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get,
+			debugfs_atomic_t_set, "%lld\n");
+
+static struct dentry *debugfs_create_atomic_t(const char *name, mode_t mode,
+				struct dentry *parent, atomic_t *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_atomic_t);
+}
+
+static void cleanup_should_fail_knobs(struct should_fail_knobs *knobs)
+{
+	if (knobs->dir) {
+		if (knobs->probability_file) {
+			debugfs_remove(knobs->probability_file);
+			knobs->probability_file = NULL;
+		}
+		if (knobs->interval_file) {
+			debugfs_remove(knobs->interval_file);
+			knobs->interval_file = NULL;
+		}
+		if (knobs->times_file) {
+			debugfs_remove(knobs->times_file);
+			knobs->times_file = NULL;
+		}
+		if (knobs->space_file) {
+			debugfs_remove(knobs->space_file);
+			knobs->space_file = NULL;
+		}
+		debugfs_remove(knobs->dir);
+		knobs->dir = NULL;
+	}
+}
+
+static int init_should_fail_knobs(struct should_fail_knobs *knobs,
+			   struct should_fail_data *data, const char *name)
+{
+	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	struct dentry *dir;
+	struct dentry *file;
+
+	memset(knobs, 0, sizeof(*knobs));
+
+	dir = debugfs_create_dir(name, NULL);
+	if (!dir)
+		goto fail;
+	knobs->dir = dir;
+
+	file = debugfs_create_ul("probability", mode, dir, &data->probability);
+	if (!file)
+		goto fail;
+	knobs->probability_file = file;
+
+	file = debugfs_create_ul("interval", mode, dir, &data->interval);
+	if (!file)
+		goto fail;
+	knobs->interval_file = file;
+
+	file = debugfs_create_atomic_t("times", mode, dir, &data->times);
+	if (!file)
+		goto fail;
+	knobs->times_file = file;
+
+	file = debugfs_create_atomic_t("space", mode, dir, &data->space);
+	if (!file)
+		goto fail;
+	knobs->space_file = file;
+
+	return 0;
+fail:
+	cleanup_should_fail_knobs(knobs);
+	return -ENOMEM;
+}
+
+#ifdef CONFIG_FAILSLAB
+static struct should_fail_knobs failslab_knobs;
+#endif
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+static struct should_fail_knobs fail_page_alloc_knobs;
+#endif
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+static struct should_fail_knobs fail_make_request_knobs;
+#endif
+
+static void cleanup_knobs(void)
+{
+#ifdef CONFIG_FAILSLAB
+	cleanup_should_fail_knobs(&fail_make_request_knobs);
+#endif
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+	cleanup_should_fail_knobs(&fail_page_alloc_knobs);
+#endif
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	cleanup_should_fail_knobs(&failslab_knobs);
+#endif
+}
+
+static int init_knobs(void)
+{
+	int err;
+
+#ifdef CONFIG_FAILSLAB
+	err = init_should_fail_knobs(&failslab_knobs, failslab, "failslab");
+	if (err)
+		goto fail;
+#endif
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+	err = init_should_fail_knobs(&fail_page_alloc_knobs, fail_page_alloc,
+				     "fail_page_alloc");
+	if (err)
+		goto fail;
+#endif
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	err = init_should_fail_knobs(&fail_make_request_knobs,
+				     fail_make_request, "fail_make_request");
+	if (err)
+		goto fail;
+#endif
+
+	return 0;
+fail:
+	cleanup_knobs();
+
+	return err;
+}
+
+module_init(init_knobs);
+module_exit(cleanup_knobs);
+MODULE_LICENSE("GPL");