From 3aef2cad5d51ee66d2a614dd2f70cb34c74caf77 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Thu, 6 Dec 2018 11:18:13 -0800 Subject: tools: Update rbtree implementation There have been a number of changes in the kernel's rbrtee implementation, including loose lockless searching guarantees and rb_root_cached, which later patches will use as an optimization. Signed-off-by: Davidlohr Bueso Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20181206191819.30182-2-dave@stgolabs.net Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/rbtree.c | 178 ++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 135 insertions(+), 43 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c index 17c2b596f043..904adb70a4f0 100644 --- a/tools/lib/rbtree.c +++ b/tools/lib/rbtree.c @@ -22,6 +22,7 @@ */ #include +#include /* * red-black trees properties: http://en.wikipedia.org/wiki/Rbtree @@ -43,6 +44,30 @@ * parentheses and have some accompanying text comment. */ +/* + * Notes on lockless lookups: + * + * All stores to the tree structure (rb_left and rb_right) must be done using + * WRITE_ONCE(). And we must not inadvertently cause (temporary) loops in the + * tree structure as seen in program order. + * + * These two requirements will allow lockless iteration of the tree -- not + * correct iteration mind you, tree rotations are not atomic so a lookup might + * miss entire subtrees. + * + * But they do guarantee that any such traversal will only see valid elements + * and that it will indeed complete -- does not get stuck in a loop. + * + * It also guarantees that if the lookup returns an element it is the 'correct' + * one. But not returning an element does _NOT_ mean it's not present. + * + * NOTE: + * + * Stores to __rb_parent_color are not important for simple lookups so those + * are left undone as of now. Nor did I check for loops involving parent + * pointers. + */ + static inline void rb_set_black(struct rb_node *rb) { rb->__rb_parent_color |= RB_BLACK; @@ -70,22 +95,35 @@ __rb_rotate_set_parents(struct rb_node *old, struct rb_node *new, static __always_inline void __rb_insert(struct rb_node *node, struct rb_root *root, + bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) { struct rb_node *parent = rb_red_parent(node), *gparent, *tmp; + if (newleft) + *leftmost = node; + while (true) { /* - * Loop invariant: node is red - * - * If there is a black parent, we are done. - * Otherwise, take some corrective action as we don't - * want a red root or two consecutive red nodes. + * Loop invariant: node is red. */ - if (!parent) { + if (unlikely(!parent)) { + /* + * The inserted node is root. Either this is the + * first node, or we recursed at Case 1 below and + * are no longer violating 4). + */ rb_set_parent_color(node, NULL, RB_BLACK); break; - } else if (rb_is_black(parent)) + } + + /* + * If there is a black parent, we are done. + * Otherwise, take some corrective action as, + * per 4), we don't want a red root or two + * consecutive red nodes. + */ + if(rb_is_black(parent)) break; gparent = rb_red_parent(parent); @@ -94,7 +132,7 @@ __rb_insert(struct rb_node *node, struct rb_root *root, if (parent != tmp) { /* parent == gparent->rb_left */ if (tmp && rb_is_red(tmp)) { /* - * Case 1 - color flips + * Case 1 - node's uncle is red (color flips). * * G g * / \ / \ @@ -117,7 +155,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root, tmp = parent->rb_right; if (node == tmp) { /* - * Case 2 - left rotate at parent + * Case 2 - node's uncle is black and node is + * the parent's right child (left rotate at parent). * * G G * / \ / \ @@ -128,8 +167,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root, * This still leaves us in violation of 4), the * continuation into Case 3 will fix that. */ - parent->rb_right = tmp = node->rb_left; - node->rb_left = parent; + tmp = node->rb_left; + WRITE_ONCE(parent->rb_right, tmp); + WRITE_ONCE(node->rb_left, parent); if (tmp) rb_set_parent_color(tmp, parent, RB_BLACK); @@ -140,7 +180,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root, } /* - * Case 3 - right rotate at gparent + * Case 3 - node's uncle is black and node is + * the parent's left child (right rotate at gparent). * * G P * / \ / \ @@ -148,8 +189,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root, * / \ * n U */ - gparent->rb_left = tmp; /* == parent->rb_right */ - parent->rb_right = gparent; + WRITE_ONCE(gparent->rb_left, tmp); /* == parent->rb_right */ + WRITE_ONCE(parent->rb_right, gparent); if (tmp) rb_set_parent_color(tmp, gparent, RB_BLACK); __rb_rotate_set_parents(gparent, parent, root, RB_RED); @@ -170,8 +211,9 @@ __rb_insert(struct rb_node *node, struct rb_root *root, tmp = parent->rb_left; if (node == tmp) { /* Case 2 - right rotate at parent */ - parent->rb_left = tmp = node->rb_right; - node->rb_right = parent; + tmp = node->rb_right; + WRITE_ONCE(parent->rb_left, tmp); + WRITE_ONCE(node->rb_right, parent); if (tmp) rb_set_parent_color(tmp, parent, RB_BLACK); @@ -182,8 +224,8 @@ __rb_insert(struct rb_node *node, struct rb_root *root, } /* Case 3 - left rotate at gparent */ - gparent->rb_right = tmp; /* == parent->rb_left */ - parent->rb_left = gparent; + WRITE_ONCE(gparent->rb_right, tmp); /* == parent->rb_left */ + WRITE_ONCE(parent->rb_left, gparent); if (tmp) rb_set_parent_color(tmp, gparent, RB_BLACK); __rb_rotate_set_parents(gparent, parent, root, RB_RED); @@ -223,8 +265,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * Sl Sr N Sl */ - parent->rb_right = tmp1 = sibling->rb_left; - sibling->rb_left = parent; + tmp1 = sibling->rb_left; + WRITE_ONCE(parent->rb_right, tmp1); + WRITE_ONCE(sibling->rb_left, parent); rb_set_parent_color(tmp1, parent, RB_BLACK); __rb_rotate_set_parents(parent, sibling, root, RB_RED); @@ -268,15 +311,31 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * * (p) (p) * / \ / \ - * N S --> N Sl + * N S --> N sl * / \ \ - * sl Sr s + * sl Sr S * \ * Sr + * + * Note: p might be red, and then both + * p and sl are red after rotation(which + * breaks property 4). This is fixed in + * Case 4 (in __rb_rotate_set_parents() + * which set sl the color of p + * and set p RB_BLACK) + * + * (p) (sl) + * / \ / \ + * N sl --> P S + * \ / \ + * S N Sr + * \ + * Sr */ - sibling->rb_left = tmp1 = tmp2->rb_right; - tmp2->rb_right = sibling; - parent->rb_right = tmp2; + tmp1 = tmp2->rb_right; + WRITE_ONCE(sibling->rb_left, tmp1); + WRITE_ONCE(tmp2->rb_right, sibling); + WRITE_ONCE(parent->rb_right, tmp2); if (tmp1) rb_set_parent_color(tmp1, sibling, RB_BLACK); @@ -296,8 +355,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * (sl) sr N (sl) */ - parent->rb_right = tmp2 = sibling->rb_left; - sibling->rb_left = parent; + tmp2 = sibling->rb_left; + WRITE_ONCE(parent->rb_right, tmp2); + WRITE_ONCE(sibling->rb_left, parent); rb_set_parent_color(tmp1, sibling, RB_BLACK); if (tmp2) rb_set_parent(tmp2, parent); @@ -309,8 +369,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, sibling = parent->rb_left; if (rb_is_red(sibling)) { /* Case 1 - right rotate at parent */ - parent->rb_left = tmp1 = sibling->rb_right; - sibling->rb_right = parent; + tmp1 = sibling->rb_right; + WRITE_ONCE(parent->rb_left, tmp1); + WRITE_ONCE(sibling->rb_right, parent); rb_set_parent_color(tmp1, parent, RB_BLACK); __rb_rotate_set_parents(parent, sibling, root, RB_RED); @@ -334,10 +395,11 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, } break; } - /* Case 3 - right rotate at sibling */ - sibling->rb_right = tmp1 = tmp2->rb_left; - tmp2->rb_left = sibling; - parent->rb_left = tmp2; + /* Case 3 - left rotate at sibling */ + tmp1 = tmp2->rb_left; + WRITE_ONCE(sibling->rb_right, tmp1); + WRITE_ONCE(tmp2->rb_left, sibling); + WRITE_ONCE(parent->rb_left, tmp2); if (tmp1) rb_set_parent_color(tmp1, sibling, RB_BLACK); @@ -345,9 +407,10 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, tmp1 = sibling; sibling = tmp2; } - /* Case 4 - left rotate at parent + color flips */ - parent->rb_left = tmp2 = sibling->rb_right; - sibling->rb_right = parent; + /* Case 4 - right rotate at parent + color flips */ + tmp2 = sibling->rb_right; + WRITE_ONCE(parent->rb_left, tmp2); + WRITE_ONCE(sibling->rb_right, parent); rb_set_parent_color(tmp1, sibling, RB_BLACK); if (tmp2) rb_set_parent(tmp2, parent); @@ -378,22 +441,41 @@ static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {} static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {} static const struct rb_augment_callbacks dummy_callbacks = { - dummy_propagate, dummy_copy, dummy_rotate + .propagate = dummy_propagate, + .copy = dummy_copy, + .rotate = dummy_rotate }; void rb_insert_color(struct rb_node *node, struct rb_root *root) { - __rb_insert(node, root, dummy_rotate); + __rb_insert(node, root, false, NULL, dummy_rotate); } void rb_erase(struct rb_node *node, struct rb_root *root) { struct rb_node *rebalance; - rebalance = __rb_erase_augmented(node, root, &dummy_callbacks); + rebalance = __rb_erase_augmented(node, root, + NULL, &dummy_callbacks); if (rebalance) ____rb_erase_color(rebalance, root, dummy_rotate); } +void rb_insert_color_cached(struct rb_node *node, + struct rb_root_cached *root, bool leftmost) +{ + __rb_insert(node, &root->rb_root, leftmost, + &root->rb_leftmost, dummy_rotate); +} + +void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) +{ + struct rb_node *rebalance; + rebalance = __rb_erase_augmented(node, &root->rb_root, + &root->rb_leftmost, &dummy_callbacks); + if (rebalance) + ____rb_erase_color(rebalance, &root->rb_root, dummy_rotate); +} + /* * Augmented rbtree manipulation functions. * @@ -402,9 +484,10 @@ void rb_erase(struct rb_node *node, struct rb_root *root) */ void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, + bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) { - __rb_insert(node, root, augment_rotate); + __rb_insert(node, root, newleft, leftmost, augment_rotate); } /* @@ -498,15 +581,24 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new, { struct rb_node *parent = rb_parent(victim); + /* Copy the pointers/colour from the victim to the replacement */ + *new = *victim; + /* Set the surrounding nodes to point to the replacement */ - __rb_change_child(victim, new, parent, root); if (victim->rb_left) rb_set_parent(victim->rb_left, new); if (victim->rb_right) rb_set_parent(victim->rb_right, new); + __rb_change_child(victim, new, parent, root); +} - /* Copy the pointers/colour from the victim to the replacement */ - *new = *victim; +void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, + struct rb_root_cached *root) +{ + rb_replace_node(victim, new, &root->rb_root); + + if (root->rb_leftmost == victim) + root->rb_leftmost = new; } static struct rb_node *rb_left_deepest_node(const struct rb_node *node) -- cgit v1.3-18-gd494 From d93ac78bf7b37db36fa00225f8e9a14c7ed1b2ba Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 14 Feb 2019 15:00:57 -0800 Subject: lockdep/lib/tests: Fix run_tests.sh Apparently the execute bits were set for the tests/*.sh scripts on my test setup but these are not set in the kernel tree. Fix this by adding the interpreter path in front of the script paths. Signed-off-by: Bart Van Assche Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Johannes Berg Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: johannes.berg@intel.com Cc: tj@kernel.org Fixes: 5ecb8e94b494 ("tools/lib/lockdep/tests: Improve testing accuracy") # v5.0-rc1 Link: https://lkml.kernel.org/r/20190214230058.196511-23-bvanassche@acm.org Signed-off-by: Ingo Molnar --- tools/lib/lockdep/run_tests.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index c8fbd0306960..11f425662b43 100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh @@ -11,7 +11,7 @@ find tests -name '*.c' | sort | while read -r i; do testname=$(basename "$i" .c) echo -ne "$testname... " if gcc -o "tests/$testname" -pthread "$i" liblockdep.a -Iinclude -D__USE_LIBLOCKDEP && - timeout 1 "tests/$testname" 2>&1 | "tests/${testname}.sh"; then + timeout 1 "tests/$testname" 2>&1 | /bin/bash "tests/${testname}.sh"; then echo "PASSED!" else echo "FAILED!" @@ -24,7 +24,7 @@ find tests -name '*.c' | sort | while read -r i; do echo -ne "(PRELOAD) $testname... " if gcc -o "tests/$testname" -pthread -Iinclude "$i" && timeout 1 ./lockdep "tests/$testname" 2>&1 | - "tests/${testname}.sh"; then + /bin/bash "tests/${testname}.sh"; then echo "PASSED!" else echo "FAILED!" @@ -37,7 +37,7 @@ find tests -name '*.c' | sort | while read -r i; do echo -ne "(PRELOAD + Valgrind) $testname... " if gcc -o "tests/$testname" -pthread -Iinclude "$i" && { timeout 10 valgrind --read-var-info=yes ./lockdep "./tests/$testname" >& "tests/${testname}.vg.out"; true; } && - "tests/${testname}.sh" < "tests/${testname}.vg.out" && + /bin/bash "tests/${testname}.sh" < "tests/${testname}.vg.out" && ! grep -Eq '(^==[0-9]*== (Invalid |Uninitialised ))|Mismatched free|Source and destination overlap| UME ' "tests/${testname}.vg.out"; then echo "PASSED!" else -- cgit v1.3-18-gd494 From f214737b75b0ee79763b5c058b9d5e83d711348d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 14 Feb 2019 15:00:58 -0800 Subject: lockdep/lib/tests: Test dynamic key registration Make sure that the lockdep_register_key() and lockdep_unregister_key() code is tested when running the lockdep tests. Signed-off-by: Bart Van Assche Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Johannes Berg Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Cc: johannes.berg@intel.com Cc: tj@kernel.org Link: https://lkml.kernel.org/r/20190214230058.196511-24-bvanassche@acm.org Signed-off-by: Ingo Molnar --- tools/lib/lockdep/include/liblockdep/common.h | 2 ++ tools/lib/lockdep/include/liblockdep/mutex.h | 11 ++++++----- tools/lib/lockdep/tests/ABBA.c | 9 +++++++++ 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h index d640a9761f09..a81d91d4fc78 100644 --- a/tools/lib/lockdep/include/liblockdep/common.h +++ b/tools/lib/lockdep/include/liblockdep/common.h @@ -45,6 +45,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); void lockdep_reset_lock(struct lockdep_map *lock); +void lockdep_register_key(struct lock_class_key *key); +void lockdep_unregister_key(struct lock_class_key *key); extern void debug_check_no_locks_freed(const void *from, unsigned long len); #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h index 2073d4e1f2f0..783dd0df06f9 100644 --- a/tools/lib/lockdep/include/liblockdep/mutex.h +++ b/tools/lib/lockdep/include/liblockdep/mutex.h @@ -7,6 +7,7 @@ struct liblockdep_pthread_mutex { pthread_mutex_t mutex; + struct lock_class_key key; struct lockdep_map dep_map; }; @@ -27,11 +28,10 @@ static inline int __mutex_init(liblockdep_pthread_mutex_t *lock, return pthread_mutex_init(&lock->mutex, __mutexattr); } -#define liblockdep_pthread_mutex_init(mutex, mutexattr) \ -({ \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key, (mutexattr)); \ +#define liblockdep_pthread_mutex_init(mutex, mutexattr) \ +({ \ + lockdep_register_key(&(mutex)->key); \ + __mutex_init((mutex), #mutex, &(mutex)->key, (mutexattr)); \ }) static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock) @@ -55,6 +55,7 @@ static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *l static inline int liblockdep_pthread_mutex_destroy(liblockdep_pthread_mutex_t *lock) { lockdep_reset_lock(&lock->dep_map); + lockdep_unregister_key(&lock->key); return pthread_mutex_destroy(&lock->mutex); } diff --git a/tools/lib/lockdep/tests/ABBA.c b/tools/lib/lockdep/tests/ABBA.c index 623313f54720..543789bc3e37 100644 --- a/tools/lib/lockdep/tests/ABBA.c +++ b/tools/lib/lockdep/tests/ABBA.c @@ -14,4 +14,13 @@ void main(void) pthread_mutex_destroy(&b); pthread_mutex_destroy(&a); + + pthread_mutex_init(&a, NULL); + pthread_mutex_init(&b, NULL); + + LOCK_UNLOCK_2(a, b); + LOCK_UNLOCK_2(b, a); + + pthread_mutex_destroy(&b); + pthread_mutex_destroy(&a); } -- cgit v1.3-18-gd494 From 7c5b019e3a638a5a290b0ec020f6ca83d2ec2aaa Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Wed, 27 Feb 2019 17:55:32 -0800 Subject: tools lib traceevent: Fix buffer overflow in arg_eval Fix buffer overflow observed when running perf test. The overflow is when trying to evaluate "1ULL << (64 - 1)" which is resulting in -9223372036854775808 which overflows the 20 character buffer. If is possible this bug has been reported before but I still don't see any fix checked in: See: https://www.spinics.net/lists/linux-perf-users/msg07714.html Reported-by: Michael Sartain Reported-by: Mathias Krause Signed-off-by: Tony Jones Acked-by: Steven Rostedt (VMware) Cc: Frederic Weisbecker Fixes: f7d82350e597 ("tools/events: Add files to create libtraceevent.a") Link: http://lkml.kernel.org/r/20190228015532.8941-1-tonyj@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/lib') diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index abd4fa5d3088..87494c7c619d 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2457,7 +2457,7 @@ static int arg_num_eval(struct tep_print_arg *arg, long long *val) static char *arg_eval (struct tep_print_arg *arg) { long long val; - static char buf[20]; + static char buf[24]; switch (arg->type) { case TEP_PRINT_ATOM: -- cgit v1.3-18-gd494 From f38a1f0a5a5710b14c0e899628c815522c6111cf Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Fri, 8 Mar 2019 15:58:20 -0800 Subject: libbpf: handle BTF parsing and loading properly This patch splits and cleans up error handling logic for loading BTF data. Previously, if BTF data was parsed successfully, but failed to load into kernel, we'd report nonsensical error code, instead of error returned from btf__load(). Now btf__new() and btf__load() are handled separately with proper cleanup and warning reporting. Fixes: d29d87f7e612 ("btf: separate btf creation and loading") Reported-by: Martin KaFai Lau Signed-off-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/lib/bpf/libbpf.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d5b830d60601..5e977d2688da 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -835,12 +835,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.maps_shndx = idx; else if (strcmp(name, BTF_ELF_SEC) == 0) { obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf) || btf__load(obj->btf)) { + if (IS_ERR(obj->btf)) { pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", BTF_ELF_SEC, PTR_ERR(obj->btf)); - if (!IS_ERR(obj->btf)) - btf__free(obj->btf); obj->btf = NULL; + continue; + } + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + err = 0; } } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; -- cgit v1.3-18-gd494 From 6bf21b54a596d60905cfc7e8af8e2fe16d9fe7e9 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 12 Mar 2019 09:59:45 +0100 Subject: libbpf: fix to reject unknown flags in xsk_socket__create() In xsk_socket__create(), the libbpf_flags field was not checked for setting currently unused/unknown flags. This patch fixes that by returning -EINVAL if the user has set any flag that is not in use at this point in time. Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets") Signed-off-by: Magnus Karlsson Reviewed-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- tools/lib/bpf/xsk.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index f98ac82c9aea..8d0078b65486 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->frame_headroom = usr_cfg->frame_headroom; } -static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, - const struct xsk_socket_config *usr_cfg) +static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, + const struct xsk_socket_config *usr_cfg) { if (!usr_cfg) { cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; @@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, cfg->libbpf_flags = 0; cfg->xdp_flags = 0; cfg->bind_flags = 0; - return; + return 0; } + if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD) + return -EINVAL; + cfg->rx_size = usr_cfg->rx_size; cfg->tx_size = usr_cfg->tx_size; cfg->libbpf_flags = usr_cfg->libbpf_flags; cfg->xdp_flags = usr_cfg->xdp_flags; cfg->bind_flags = usr_cfg->bind_flags; + + return 0; } int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, @@ -557,7 +562,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } strncpy(xsk->ifname, ifname, IFNAMSIZ); - xsk_set_xdp_socket_config(&xsk->config, usr_config); + err = xsk_set_xdp_socket_config(&xsk->config, usr_config); + if (err) + goto out_socket; if (rx) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, -- cgit v1.3-18-gd494 From 9768095ba97ce946838e8210f0b44f2fd36ec31d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 10 Mar 2019 17:44:09 -0700 Subject: btf: resolve enum fwds in btf_dedup GCC and clang support enum forward declarations as an extension. Such forward-declared enums will be represented as normal BTF_KIND_ENUM types with vlen=0. This patch adds ability to resolve such enums to their corresponding fully defined enums. This helps to avoid duplicated BTF type graphs which only differ by some types referencing forward-declared enum vs full enum. One such example in kernel is enum irqchip_irq_state, defined in include/linux/interrupt.h and forward-declared in include/linux/irq.h. This causes entire struct task_struct and all referenced types to be duplicated in btf_dedup output. This patch eliminates such duplication cases. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/btf.c | 51 ++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 13 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 1b8d8cdd3575..87e3020ac1bc 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1602,16 +1602,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) /* Calculate type signature hash of ENUM. */ static __u32 btf_hash_enum(struct btf_type *t) { - struct btf_enum *member = (struct btf_enum *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); - __u32 h = btf_hash_common(t); - int i; + __u32 h; - for (i = 0; i < vlen; i++) { - h = hash_combine(h, member->name_off); - h = hash_combine(h, member->val); - member++; - } + /* don't hash vlen and enum members to support enum fwd resolving */ + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info & ~0xffff); + h = hash_combine(h, t->size); return h; } @@ -1637,6 +1633,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) return true; } +static inline bool btf_is_enum_fwd(struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && + BTF_INFO_VLEN(t->info) == 0; +} + +static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum(t1, t2); + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + /* * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, * as referenced type IDs equivalence is established separately during type @@ -1860,6 +1872,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) new_id = cand_node->type_id; break; } + if (d->opts.dont_resolve_fwds) + continue; + if (btf_compat_enum(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_node->type_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_node->type_id] = type_id; + } } break; @@ -2084,15 +2107,15 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return fwd_kind == real_kind; } - if (cand_type->info != canon_type->info) - return 0; - switch (cand_kind) { case BTF_KIND_INT: return btf_equal_int(cand_type, canon_type); case BTF_KIND_ENUM: - return btf_equal_enum(cand_type, canon_type); + if (d->opts.dont_resolve_fwds) + return btf_equal_enum(cand_type, canon_type); + else + return btf_compat_enum(cand_type, canon_type); case BTF_KIND_FWD: return btf_equal_common(cand_type, canon_type); @@ -2103,6 +2126,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + if (cand_type->info != canon_type->info) + return 0; return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { -- cgit v1.3-18-gd494