From db61e6a4eee5a7884b2cafeaf407895f253bbaa7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 1 Aug 2024 15:27:24 +0200 Subject: selftests/bpf: fix uprobe.path leak in bpf_testmod testmod_unregister_uprobe() forgets to path_put(&uprobe.path). Signed-off-by: Jiri Olsa Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240801132724.GA8791@redhat.com --- tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c') diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index fd28c1157bd3..72f565af4f82 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -477,6 +477,7 @@ static void testmod_unregister_uprobe(void) if (uprobe.offset) { uprobe_unregister(d_real_inode(uprobe.path.dentry), uprobe.offset, &uprobe.consumer); + path_put(&uprobe.path); uprobe.offset = 0; } -- cgit From e04332ebc8ac128fa551e83f1161ab1c094d13a9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 1 Aug 2024 15:27:28 +0200 Subject: uprobes: kill uprobe_register_refctr() It doesn't make any sense to have 2 versions of _register(). Note that trace_uprobe_enable(), the only user of uprobe_register(), doesn't need to check tu->ref_ctr_offset to decide which one should be used, it could safely pass ref_ctr_offset == 0 to uprobe_register_refctr(). Add this argument to uprobe_register(), update the callers, and kill uprobe_register_refctr(). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Jiri Olsa Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20240801132728.GA8800@redhat.com --- include/linux/uprobes.h | 9 ++------ kernel/events/uprobes.c | 24 ++++++---------------- kernel/trace/bpf_trace.c | 8 ++++---- kernel/trace/trace_uprobe.c | 7 +------ .../selftests/bpf/bpf_testmod/bpf_testmod.c | 4 ++-- 5 files changed, 15 insertions(+), 37 deletions(-) (limited to 'tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index a270a5892ab4..788813c0b8fc 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -112,8 +112,7 @@ extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); -extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); +extern int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); @@ -154,11 +153,7 @@ static inline void uprobes_init(void) #define uprobe_get_trap_addr(regs) instruction_pointer(regs) static inline int -uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) -{ - return -ENOSYS; -} -static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { return -ENOSYS; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e9b092acc71b..3a80154bc4c7 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1121,25 +1121,26 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume EXPORT_SYMBOL_GPL(uprobe_unregister); /* - * __uprobe_register - register a probe + * uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. + * @ref_ctr_offset: offset of SDT marker / reference counter * @uc: information on howto handle the probe.. * - * Apart from the access refcount, __uprobe_register() takes a creation + * Apart from the access refcount, uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe - * unregisters. Caller of __uprobe_register() is required to keep @inode + * unregisters. Caller of uprobe_register() is required to keep @inode * (and the containing mount) referenced. * * Return errno if it cannot successully install probes * else return 0 (success) */ -static int __uprobe_register(struct inode *inode, loff_t offset, - loff_t ref_ctr_offset, struct uprobe_consumer *uc) +int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, + struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; @@ -1189,21 +1190,8 @@ static int __uprobe_register(struct inode *inode, loff_t offset, goto retry; return ret; } - -int uprobe_register(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc) -{ - return __uprobe_register(inode, offset, 0, uc); -} EXPORT_SYMBOL_GPL(uprobe_register); -int uprobe_register_refctr(struct inode *inode, loff_t offset, - loff_t ref_ctr_offset, struct uprobe_consumer *uc) -{ - return __uprobe_register(inode, offset, ref_ctr_offset, uc); -} -EXPORT_SYMBOL_GPL(uprobe_register_refctr); - /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cd098846e251..afa909e17824 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3480,10 +3480,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr &bpf_uprobe_multi_link_lops, prog); for (i = 0; i < cnt; i++) { - err = uprobe_register_refctr(d_real_inode(link->path.dentry), - uprobes[i].offset, - uprobes[i].ref_ctr_offset, - &uprobes[i].consumer); + err = uprobe_register(d_real_inode(link->path.dentry), + uprobes[i].offset, + uprobes[i].ref_ctr_offset, + &uprobes[i].consumer); if (err) { bpf_uprobe_unregister(&path, uprobes, i); goto error_free; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index c98e3b3386ba..1f590f989c1e 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1089,12 +1089,7 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); - if (tu->ref_ctr_offset) - ret = uprobe_register_refctr(tu->inode, tu->offset, - tu->ref_ctr_offset, &tu->consumer); - else - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); - + ret = uprobe_register(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); if (ret) tu->inode = NULL; diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 72f565af4f82..55f6905de743 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -458,8 +458,8 @@ static int testmod_register_uprobe(loff_t offset) if (err) goto out; - err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); + err = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); if (err) path_put(&uprobe.path); else -- cgit From 3c83a9ad0295eb63bdeb81d821b8c3b9417fbcac Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 1 Aug 2024 15:27:34 +0200 Subject: uprobes: make uprobe_register() return struct uprobe * This way uprobe_unregister() and uprobe_apply() can use "struct uprobe *" rather than inode + offset. This simplifies the code and allows to avoid the unnecessary find_uprobe() + put_uprobe() in these functions. TODO: uprobe_unregister() still needs get_uprobe/put_uprobe to ensure that this uprobe can't be freed before up_write(&uprobe->register_rwsem). Co-developed-by: Andrii Nakryiko Signed-off-by: Andrii Nakryiko Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Jiri Olsa Link: https://lore.kernel.org/r/20240801132734.GA8803@redhat.com --- include/linux/uprobes.h | 15 +++--- kernel/events/uprobes.c | 56 +++++++++------------- kernel/trace/bpf_trace.c | 25 +++++----- kernel/trace/trace_uprobe.c | 26 +++++----- .../selftests/bpf/bpf_testmod/bpf_testmod.c | 25 +++++----- 5 files changed, 67 insertions(+), 80 deletions(-) (limited to 'tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 788813c0b8fc..f50df1fa93e7 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -16,6 +16,7 @@ #include #include +struct uprobe; struct vm_area_struct; struct mm_struct; struct inode; @@ -112,9 +113,9 @@ extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); -extern int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); -extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); -extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); +extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); +extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void uprobe_start_dup_mmap(void); @@ -152,18 +153,18 @@ static inline void uprobes_init(void) #define uprobe_get_trap_addr(regs) instruction_pointer(regs) -static inline int +static inline struct uprobe * uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { - return -ENOSYS; + return ERR_PTR(-ENOSYS); } static inline int -uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) +uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add) { return -ENOSYS; } static inline void -uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { } static inline int uprobe_mmap(struct vm_area_struct *vma) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 3a80154bc4c7..b33f1397dae0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1099,20 +1099,14 @@ __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) delete_uprobe(uprobe); } -/* +/** * uprobe_unregister - unregister an already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. + * @uprobe: uprobe to remove * @uc: identify which probe if multiple probes are colocated. */ -void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { - struct uprobe *uprobe; - - uprobe = find_uprobe(inode, offset); - if (WARN_ON(!uprobe)) - return; - + get_uprobe(uprobe); down_write(&uprobe->register_rwsem); __uprobe_unregister(uprobe, uc); up_write(&uprobe->register_rwsem); @@ -1120,7 +1114,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume } EXPORT_SYMBOL_GPL(uprobe_unregister); -/* +/** * uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. @@ -1136,40 +1130,40 @@ EXPORT_SYMBOL_GPL(uprobe_unregister); * unregisters. Caller of uprobe_register() is required to keep @inode * (and the containing mount) referenced. * - * Return errno if it cannot successully install probes - * else return 0 (success) + * Return: pointer to the new uprobe on success or an ERR_PTR on failure. */ -int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, - struct uprobe_consumer *uc) +struct uprobe *uprobe_register(struct inode *inode, + loff_t offset, loff_t ref_ctr_offset, + struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; /* Uprobe must have at least one set consumer */ if (!uc->handler && !uc->ret_handler) - return -EINVAL; + return ERR_PTR(-EINVAL); /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ if (!inode->i_mapping->a_ops->read_folio && !shmem_mapping(inode->i_mapping)) - return -EIO; + return ERR_PTR(-EIO); /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) - return -EINVAL; + return ERR_PTR(-EINVAL); /* * This ensures that copy_from_page(), copy_to_page() and * __update_ref_ctr() can't cross page boundary. */ if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) - return -EINVAL; + return ERR_PTR(-EINVAL); if (!IS_ALIGNED(ref_ctr_offset, sizeof(short))) - return -EINVAL; + return ERR_PTR(-EINVAL); retry: uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (IS_ERR(uprobe)) - return PTR_ERR(uprobe); + return uprobe; /* * We can race with uprobe_unregister()->delete_uprobe(). @@ -1188,35 +1182,29 @@ int uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, if (unlikely(ret == -EAGAIN)) goto retry; - return ret; + + return ret ? ERR_PTR(ret) : uprobe; } EXPORT_SYMBOL_GPL(uprobe_register); -/* - * uprobe_apply - unregister an already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. +/** + * uprobe_apply - add or remove the breakpoints according to @uc->filter + * @uprobe: uprobe which "owns" the breakpoint * @uc: consumer which wants to add more or remove some breakpoints * @add: add or remove the breakpoints + * Return: 0 on success or negative error code. */ -int uprobe_apply(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc, bool add) +int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool add) { - struct uprobe *uprobe; struct uprobe_consumer *con; int ret = -ENOENT; - uprobe = find_uprobe(inode, offset); - if (WARN_ON(!uprobe)) - return ret; - down_write(&uprobe->register_rwsem); for (con = uprobe->consumers; con && con != uc ; con = con->next) ; if (con) ret = register_for_each_vma(uprobe, add ? uc : NULL); up_write(&uprobe->register_rwsem); - put_uprobe(uprobe); return ret; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index afa909e17824..4e391daafa64 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3160,6 +3160,7 @@ struct bpf_uprobe { loff_t offset; unsigned long ref_ctr_offset; u64 cookie; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -3178,15 +3179,12 @@ struct bpf_uprobe_multi_run_ctx { struct bpf_uprobe *uprobe; }; -static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes, - u32 cnt) +static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt) { u32 i; - for (i = 0; i < cnt; i++) { - uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset, - &uprobes[i].consumer); - } + for (i = 0; i < cnt; i++) + uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer); } static void bpf_uprobe_multi_link_release(struct bpf_link *link) @@ -3194,7 +3192,7 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); - bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); + bpf_uprobe_unregister(umulti_link->uprobes, umulti_link->cnt); if (umulti_link->task) put_task_struct(umulti_link->task); path_put(&umulti_link->path); @@ -3480,12 +3478,13 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr &bpf_uprobe_multi_link_lops, prog); for (i = 0; i < cnt; i++) { - err = uprobe_register(d_real_inode(link->path.dentry), - uprobes[i].offset, - uprobes[i].ref_ctr_offset, - &uprobes[i].consumer); - if (err) { - bpf_uprobe_unregister(&path, uprobes, i); + uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry), + uprobes[i].offset, + uprobes[i].ref_ctr_offset, + &uprobes[i].consumer); + if (IS_ERR(uprobes[i].uprobe)) { + err = PTR_ERR(uprobes[i].uprobe); + bpf_uprobe_unregister(uprobes, i); goto error_free; } } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 1f590f989c1e..52e76a73fa7c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -58,8 +58,8 @@ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; - struct inode *inode; char *filename; + struct uprobe *uprobe; unsigned long offset; unsigned long ref_ctr_offset; unsigned long nhit; @@ -1084,16 +1084,16 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { - int ret; + struct inode *inode = d_real_inode(tu->path.dentry); + struct uprobe *uprobe; tu->consumer.filter = filter; - tu->inode = d_real_inode(tu->path.dentry); - - ret = uprobe_register(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); - if (ret) - tu->inode = NULL; + uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); + if (IS_ERR(uprobe)) + return PTR_ERR(uprobe); - return ret; + tu->uprobe = uprobe; + return 0; } static void __probe_event_disable(struct trace_probe *tp) @@ -1104,11 +1104,11 @@ static void __probe_event_disable(struct trace_probe *tp) WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - if (!tu->inode) + if (!tu->uprobe) continue; - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->inode = NULL; + uprobe_unregister(tu->uprobe, &tu->consumer); + tu->uprobe = NULL; } } @@ -1305,7 +1305,7 @@ static int uprobe_perf_close(struct trace_event_call *call, return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + ret = uprobe_apply(tu->uprobe, &tu->consumer, false); if (ret) break; } @@ -1329,7 +1329,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + err = uprobe_apply(tu->uprobe, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); break; diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 55f6905de743..3c0515a27842 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -432,7 +432,7 @@ uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func, struct testmod_uprobe { struct path path; - loff_t offset; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -446,25 +446,25 @@ static int testmod_register_uprobe(loff_t offset) { int err = -EBUSY; - if (uprobe.offset) + if (uprobe.uprobe) return -EBUSY; mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) + if (uprobe.uprobe) goto out; err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path); if (err) goto out; - err = uprobe_register(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); - if (err) + uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); + if (IS_ERR(uprobe.uprobe)) { + err = PTR_ERR(uprobe.uprobe); path_put(&uprobe.path); - else - uprobe.offset = offset; - + uprobe.uprobe = NULL; + } out: mutex_unlock(&testmod_uprobe_mutex); return err; @@ -474,11 +474,10 @@ static void testmod_unregister_uprobe(void) { mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) { - uprobe_unregister(d_real_inode(uprobe.path.dentry), - uprobe.offset, &uprobe.consumer); + if (uprobe.uprobe) { + uprobe_unregister(uprobe.uprobe, &uprobe.consumer); path_put(&uprobe.path); - uprobe.offset = 0; + uprobe.uprobe = NULL; } mutex_unlock(&testmod_uprobe_mutex); -- cgit From 04b01625da130c7521b768996cd5e48052198b97 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 Sep 2024 10:46:00 -0700 Subject: perf/uprobe: split uprobe_unregister() With uprobe_unregister() having grown a synchronize_srcu(), it becomes fairly slow to call. Esp. since both users of this API call it in a loop. Peel off the sync_srcu() and do it once, after the loop. We also need to add uprobe_unregister_sync() into uprobe_register()'s error handling path, as we need to be careful about returning to the caller before we have a guarantee that partially attached consumer won't be called anymore. This is an unlikely slow path and this should be totally fine to be slow in the case of a failed attach. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: "Peter Zijlstra (Intel)" Co-developed-by: Andrii Nakryiko Signed-off-by: Andrii Nakryiko Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240903174603.3554182-6-andrii@kernel.org --- include/linux/uprobes.h | 8 ++++++-- kernel/events/uprobes.c | 21 +++++++++++++++------ kernel/trace/bpf_trace.c | 5 ++++- kernel/trace/trace_uprobe.c | 6 +++++- .../testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 3 ++- 5 files changed, 32 insertions(+), 11 deletions(-) (limited to 'tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f112b56e9479..2b294bf1881f 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -115,7 +115,8 @@ extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); -extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc); +extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc); +extern void uprobe_unregister_sync(void); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void uprobe_start_dup_mmap(void); @@ -164,7 +165,10 @@ uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add) return -ENOSYS; } static inline void -uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) +uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ +} +static inline void uprobe_unregister_sync(void) { } static inline int uprobe_mmap(struct vm_area_struct *vma) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e15c0306e535..694f6790e848 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1105,11 +1105,11 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) } /** - * uprobe_unregister - unregister an already registered probe. + * uprobe_unregister_nosync - unregister an already registered probe. * @uprobe: uprobe to remove * @uc: identify which probe if multiple probes are colocated. */ -void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) +void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc) { int err; @@ -1121,12 +1121,15 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) /* TODO : cant unregister? schedule a worker thread */ if (unlikely(err)) { uprobe_warn(current, "unregister, leaking uprobe"); - goto out_sync; + return; } put_uprobe(uprobe); +} +EXPORT_SYMBOL_GPL(uprobe_unregister_nosync); -out_sync: +void uprobe_unregister_sync(void) +{ /* * Now that handler_chain() and handle_uretprobe_chain() iterate over * uprobe->consumers list under RCU protection without holding @@ -1138,7 +1141,7 @@ out_sync: */ synchronize_srcu(&uprobes_srcu); } -EXPORT_SYMBOL_GPL(uprobe_unregister); +EXPORT_SYMBOL_GPL(uprobe_unregister_sync); /** * uprobe_register - register a probe @@ -1196,7 +1199,13 @@ struct uprobe *uprobe_register(struct inode *inode, up_write(&uprobe->register_rwsem); if (ret) { - uprobe_unregister(uprobe, uc); + uprobe_unregister_nosync(uprobe, uc); + /* + * Registration might have partially succeeded, so we can have + * this consumer being called right at this time. We need to + * sync here. It's ok, it's unlikely slow path. + */ + uprobe_unregister_sync(); return ERR_PTR(ret); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c99bf0617602..ac0a01cc8634 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3184,7 +3184,10 @@ static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt) u32 i; for (i = 0; i < cnt; i++) - uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer); + uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer); + + if (cnt) + uprobe_unregister_sync(); } static void bpf_uprobe_multi_link_release(struct bpf_link *link) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 7eb79e0a5352..f7443e996b1b 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1097,6 +1097,7 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) static void __probe_event_disable(struct trace_probe *tp) { struct trace_uprobe *tu; + bool sync = false; tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); @@ -1105,9 +1106,12 @@ static void __probe_event_disable(struct trace_probe *tp) if (!tu->uprobe) continue; - uprobe_unregister(tu->uprobe, &tu->consumer); + uprobe_unregister_nosync(tu->uprobe, &tu->consumer); + sync = true; tu->uprobe = NULL; } + if (sync) + uprobe_unregister_sync(); } static int probe_event_enable(struct trace_event_call *call, diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 3c0515a27842..1fc16657cf42 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -475,7 +475,8 @@ static void testmod_unregister_uprobe(void) mutex_lock(&testmod_uprobe_mutex); if (uprobe.uprobe) { - uprobe_unregister(uprobe.uprobe, &uprobe.consumer); + uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer); + uprobe_unregister_sync(); path_put(&uprobe.path); uprobe.uprobe = NULL; } -- cgit