From 8d9fa88edd5e360b71765feeadb915d4066c9684 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 18 May 2018 16:08:51 -0700 Subject: radix tree test suite: fix mapshift build target Commit c6ce3e2fe3da ("radix tree test suite: Add config option for map shift") introduced a phony makefile target called 'mapshift' that ends up generating the file generated/map-shift.h. This phony target was then added as a dependency of the top level 'targets' build target, which is what is run when you go to tools/testing/radix-tree and just type 'make'. Unfortunately, this phony target doesn't actually work as a dependency, so you end up getting: $ make make: *** No rule to make target 'generated/map-shift.h', needed by 'main.o'. Stop. make: *** Waiting for unfinished jobs.... Fix this by making the file generated/map-shift.h our real makefile target, and add this a dependency of the top level build target. Link: http://lkml.kernel.org/r/20180503192430.7582-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Cc: Christoph Hellwig Cc: CR, Sapthagirish Cc: Dan Williams Cc: Dave Chinner Cc: Jan Kara Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/radix-tree/Makefile | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index fa7ee369b3c9..db66f8a0d4be 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -17,7 +17,7 @@ ifeq ($(BUILD), 32) LDFLAGS += -m32 endif -targets: mapshift $(TARGETS) +targets: generated/map-shift.h $(TARGETS) main: $(OFILES) @@ -42,9 +42,7 @@ radix-tree.c: ../../../lib/radix-tree.c idr.c: ../../../lib/idr.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ -.PHONY: mapshift - -mapshift: +generated/map-shift.h: @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ generated/map-shift.h; \ -- cgit v1.3.1 From dcbbf25adb31410c95ce844f80d372ed38b68b24 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 18 May 2018 16:08:54 -0700 Subject: radix tree test suite: fix compilation issue Pulled from a patch from Matthew Wilcox entitled "xarray: Add definition of struct xarray": > From: Matthew Wilcox > Signed-off-by: Matthew Wilcox https://patchwork.kernel.org/patch/10341249/ These defines fix this compilation error: In file included from ./linux/radix-tree.h:6:0, from ./linux/../../../../include/linux/idr.h:15, from ./linux/idr.h:1, from idr.c:4: ./linux/../../../../include/linux/idr.h: In function `idr_init_base': ./linux/../../../../include/linux/radix-tree.h:129:2: warning: implicit declaration of function `spin_lock_init'; did you mean `spinlock_t'? [-Wimplicit-function-declaration] spin_lock_init(&(root)->xa_lock); \ ^ ./linux/../../../../include/linux/idr.h:126:2: note: in expansion of macro `INIT_RADIX_TREE' INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); ^~~~~~~~~~~~~~~ by providing a spin_lock_init() wrapper for the v4.17-rc* version of the radix tree test suite. Link: http://lkml.kernel.org/r/20180503192430.7582-3-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Cc: Christoph Hellwig Cc: CR, Sapthagirish Cc: Dan Williams Cc: Dave Chinner Cc: Jan Kara Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/include/linux/spinlock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index b21b586b9854..1738c0391da4 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -6,8 +6,9 @@ #include #define spinlock_t pthread_mutex_t -#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; +#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER #define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER +#define spin_lock_init(x) pthread_mutex_init(x, NULL) #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) -- cgit v1.3.1 From 3e252fa7d4f711798e7a3f5ff2d7b62f0e2987ce Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 18 May 2018 16:08:58 -0700 Subject: radix tree test suite: add item_delete_rcu() Currently the lifetime of "struct item" entries in the radix tree are not controlled by RCU, but are instead deleted inline as they are removed from the tree. In the following patches we add a test which has threads iterating over items pulled from the tree and verifying them in an rcu_read_lock()/rcu_read_unlock() section. This means that though an item has been removed from the tree it could still be being worked on by other threads until the RCU grace period expires. So, we need to actually free the "struct item" structures at the end of the grace period, just as we do with "struct radix_tree_node" items. Link: http://lkml.kernel.org/r/20180503192430.7582-4-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Cc: Christoph Hellwig Cc: CR, Sapthagirish Cc: Dan Williams Cc: Dave Chinner Cc: Jan Kara Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/radix-tree/test.c | 19 +++++++++++++++++++ tools/testing/radix-tree/test.h | 2 ++ 2 files changed, 21 insertions(+) (limited to 'tools') diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index 5978ab1f403d..def6015570b2 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -75,6 +75,25 @@ int item_delete(struct radix_tree_root *root, unsigned long index) return 0; } +static void item_free_rcu(struct rcu_head *head) +{ + struct item *item = container_of(head, struct item, rcu_head); + + free(item); +} + +int item_delete_rcu(struct radix_tree_root *root, unsigned long index) +{ + struct item *item = radix_tree_delete(root, index); + + if (item) { + item_sanity(item, index); + call_rcu(&item->rcu_head, item_free_rcu); + return 1; + } + return 0; +} + void item_check_present(struct radix_tree_root *root, unsigned long index) { struct item *item; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index d9c031dbeb1a..8cf4a7a7f94c 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -5,6 +5,7 @@ #include struct item { + struct rcu_head rcu_head; unsigned long index; unsigned int order; }; @@ -15,6 +16,7 @@ int item_insert(struct radix_tree_root *root, unsigned long index); int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order); int item_delete(struct radix_tree_root *root, unsigned long index); +int item_delete_rcu(struct radix_tree_root *root, unsigned long index); struct item *item_lookup(struct radix_tree_root *root, unsigned long index); void item_check_present(struct radix_tree_root *root, unsigned long index); -- cgit v1.3.1 From fd8f58c40b703e47697c9f12bc16c31f14c161f1 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 18 May 2018 16:09:01 -0700 Subject: radix tree test suite: multi-order iteration race Add a test which shows a race in the multi-order iteration code. This test reliably hits the race in under a second on my machine, and is the result of a real bug report against kernel a production v4.15 based kernel (4.15.6-300.fc27.x86_64). With a real kernel this issue is hit when using order 9 PMD DAX radix tree entries. The race has to do with how we tear down multi-order sibling entries when we are removing an item from the tree. Remember that an order 2 entry looks like this: struct radix_tree_node.slots[] = [entry][sibling][sibling][sibling] where 'entry' is in some slot in the struct radix_tree_node, and the three slots following 'entry' contain sibling pointers which point back to 'entry.' When we delete 'entry' from the tree, we call : radix_tree_delete() radix_tree_delete_item() __radix_tree_delete() replace_slot() replace_slot() first removes the siblings in order from the first to the last, then at then replaces 'entry' with NULL. This means that for a brief period of time we end up with one or more of the siblings removed, so: struct radix_tree_node.slots[] = [entry][NULL][sibling][sibling] This causes an issue if you have a reader iterating over the slots in the tree via radix_tree_for_each_slot() while only under rcu_read_lock()/rcu_read_unlock() protection. This is a common case in mm/filemap.c. The issue is that when __radix_tree_next_slot() => skip_siblings() tries to skip over the sibling entries in the slots, it currently does so with an exact match on the slot directly preceding our current slot. Normally this works: V preceding slot struct radix_tree_node.slots[] = [entry][sibling][sibling][sibling] ^ current slot This lets you find the first sibling, and you skip them all in order. But in the case where one of the siblings is NULL, that slot is skipped and then our sibling detection is interrupted: V preceding slot struct radix_tree_node.slots[] = [entry][NULL][sibling][sibling] ^ current slot This means that the sibling pointers aren't recognized since they point all the way back to 'entry', so we think that they are normal internal radix tree pointers. This causes us to think we need to walk down to a struct radix_tree_node starting at the address of 'entry'. In a real running kernel this will crash the thread with a GP fault when you try and dereference the slots in your broken node starting at 'entry'. In the radix tree test suite this will be caught by the address sanitizer: ==27063==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x60c0008ae400 at pc 0x00000040ce4f bp 0x7fa89b8fcad0 sp 0x7fa89b8fcac0 READ of size 8 at 0x60c0008ae400 thread T3 #0 0x40ce4e in __radix_tree_next_slot /home/rzwisler/project/linux/tools/testing/radix-tree/radix-tree.c:1660 #1 0x4022cc in radix_tree_next_slot linux/../../../../include/linux/radix-tree.h:567 #2 0x4022cc in iterator_func /home/rzwisler/project/linux/tools/testing/radix-tree/multiorder.c:655 #3 0x7fa8a088d50a in start_thread (/lib64/libpthread.so.0+0x750a) #4 0x7fa8a03bd16e in clone (/lib64/libc.so.6+0xf516e) Link: http://lkml.kernel.org/r/20180503192430.7582-5-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Cc: Christoph Hellwig Cc: CR, Sapthagirish Cc: Dan Williams Cc: Dave Chinner Cc: Jan Kara Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/radix-tree/multiorder.c | 63 +++++++++++++++++++++++++++++++++++ tools/testing/radix-tree/test.h | 1 + 2 files changed, 64 insertions(+) (limited to 'tools') diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 59245b3d587c..7bf405638b0b 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "test.h" @@ -624,6 +625,67 @@ static void multiorder_account(void) item_kill_tree(&tree); } +bool stop_iteration = false; + +static void *creator_func(void *ptr) +{ + /* 'order' is set up to ensure we have sibling entries */ + unsigned int order = RADIX_TREE_MAP_SHIFT - 1; + struct radix_tree_root *tree = ptr; + int i; + + for (i = 0; i < 10000; i++) { + item_insert_order(tree, 0, order); + item_delete_rcu(tree, 0); + } + + stop_iteration = true; + return NULL; +} + +static void *iterator_func(void *ptr) +{ + struct radix_tree_root *tree = ptr; + struct radix_tree_iter iter; + struct item *item; + void **slot; + + while (!stop_iteration) { + rcu_read_lock(); + radix_tree_for_each_slot(slot, tree, &iter, 0) { + item = radix_tree_deref_slot(slot); + + if (!item) + continue; + if (radix_tree_deref_retry(item)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + item_sanity(item, iter.index); + } + rcu_read_unlock(); + } + return NULL; +} + +static void multiorder_iteration_race(void) +{ + const int num_threads = sysconf(_SC_NPROCESSORS_ONLN); + pthread_t worker_thread[num_threads]; + RADIX_TREE(tree, GFP_KERNEL); + int i; + + pthread_create(&worker_thread[0], NULL, &creator_func, &tree); + for (i = 1; i < num_threads; i++) + pthread_create(&worker_thread[i], NULL, &iterator_func, &tree); + + for (i = 0; i < num_threads; i++) + pthread_join(worker_thread[i], NULL); + + item_kill_tree(&tree); +} + void multiorder_checks(void) { int i; @@ -644,6 +706,7 @@ void multiorder_checks(void) multiorder_join(); multiorder_split(); multiorder_account(); + multiorder_iteration_race(); radix_tree_cpu_dead(0); } diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index 8cf4a7a7f94c..31f1d9b6f506 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -13,6 +13,7 @@ struct item { struct item *item_create(unsigned long index, unsigned int order); int __item_insert(struct radix_tree_root *root, struct item *item); int item_insert(struct radix_tree_root *root, unsigned long index); +void item_sanity(struct item *item, unsigned long index); int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order); int item_delete(struct radix_tree_root *root, unsigned long index); -- cgit v1.3.1