From b5413156bad91dc2995a5c4eab1b05e56914638a Mon Sep 17 00:00:00 2001 From: Benjamin Segall Date: Fri, 25 Oct 2024 18:35:35 -0700 Subject: posix-cpu-timers: Clear TICK_DEP_BIT_POSIX_TIMER on clone When cloning a new thread, its posix_cputimers are not inherited, and are cleared by posix_cputimers_init(). However, this does not clear the tick dependency it creates in tsk->tick_dep_mask, and the handler does not reach the code to clear the dependency if there were no timers to begin with. Thus if a thread has a cputimer running before clone/fork, all descendants will prevent nohz_full unless they create a cputimer of their own. Fix this by entirely clearing the tick_dep_mask in copy_process(). (There is currently no inherited state that needs a tick dependency) Process-wide timers do not have this problem because fork does not copy signal_struct as a baseline, it creates one from scratch. Fixes: b78783000d5c ("posix-cpu-timers: Migrate to use new tick dependency mask model") Signed-off-by: Ben Segall Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/xm26o737bq8o.fsf@google.com --- kernel/fork.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 89ceb4a68af2..6fa9fe62e01e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -105,6 +105,7 @@ #include #include #include +#include #include #include @@ -2292,6 +2293,7 @@ __latent_entropy struct task_struct *copy_process( acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); + tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); -- cgit v1.2.3 From f64e67e5d3a45a4a04286c47afade4b518acd47b Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 15 Oct 2024 18:56:05 +0100 Subject: fork: do not invoke uffd on fork if error occurs Patch series "fork: do not expose incomplete mm on fork". During fork we may place the virtual memory address space into an inconsistent state before the fork operation is complete. In addition, we may encounter an error during the fork operation that indicates that the virtual memory address space is invalidated. As a result, we should not be exposing it in any way to external machinery that might interact with the mm or VMAs, machinery that is not designed to deal with incomplete state. We specifically update the fork logic to defer khugepaged and ksm to the end of the operation and only to be invoked if no error arose, and disallow uffd from observing fork events should an error have occurred. This patch (of 2): Currently on fork we expose the virtual address space of a process to userland unconditionally if uffd is registered in VMAs, regardless of whether an error arose in the fork. This is performed in dup_userfaultfd_complete() which is invoked unconditionally, and performs two duties - invoking registered handlers for the UFFD_EVENT_FORK event via dup_fctx(), and clearing down userfaultfd_fork_ctx objects established in dup_userfaultfd(). This is problematic, because the virtual address space may not yet be correctly initialised if an error arose. The change in commit d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") makes this more pertinent as we may be in a state where entries in the maple tree are not yet consistent. We address this by, on fork error, ensuring that we roll back state that we would otherwise expect to clean up through the event being handled by userland and perform the memory freeing duty otherwise performed by dup_userfaultfd_complete(). We do this by implementing a new function, dup_userfaultfd_fail(), which performs the same loop, only decrementing reference counts. Note that we perform mmgrab() on the parent and child mm's, however userfaultfd_ctx_put() will mmdrop() this once the reference count drops to zero, so we will avoid memory leaks correctly here. Link: https://lkml.kernel.org/r/cover.1729014377.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/d3691d58bb58712b6fb3df2be441d175bd3cdf07.1729014377.git.lorenzo.stoakes@oracle.com Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Jann Horn Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: Linus Torvalds Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 28 ++++++++++++++++++++++++++++ include/linux/userfaultfd_k.h | 5 +++++ kernel/fork.c | 5 ++++- 3 files changed, 37 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 68cdd89c97a3..7c0bd0b55f88 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -692,6 +692,34 @@ void dup_userfaultfd_complete(struct list_head *fcs) } } +void dup_userfaultfd_fail(struct list_head *fcs) +{ + struct userfaultfd_fork_ctx *fctx, *n; + + /* + * An error has occurred on fork, we will tear memory down, but have + * allocated memory for fctx's and raised reference counts for both the + * original and child contexts (and on the mm for each as a result). + * + * These would ordinarily be taken care of by a user handling the event, + * but we are no longer doing so, so manually clean up here. + * + * mm tear down will take care of cleaning up VMA contexts. + */ + list_for_each_entry_safe(fctx, n, fcs, list) { + struct userfaultfd_ctx *octx = fctx->orig; + struct userfaultfd_ctx *ctx = fctx->new; + + atomic_dec(&octx->mmap_changing); + VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0); + userfaultfd_ctx_put(octx); + userfaultfd_ctx_put(ctx); + + list_del(&fctx->list); + kfree(fctx); + } +} + void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9fc6ce15c499..cb40f1a1d081 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l) { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { diff --git a/kernel/fork.c b/kernel/fork.c index 89ceb4a68af2..597b477dd491 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -775,7 +775,10 @@ out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); - dup_userfaultfd_complete(&uf); + if (!retval) + dup_userfaultfd_complete(&uf); + else + dup_userfaultfd_fail(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; -- cgit v1.2.3 From 985da552a98e27096444508ce5d853244019111f Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 15 Oct 2024 18:56:06 +0100 Subject: fork: only invoke khugepaged, ksm hooks if no error There is no reason to invoke these hooks early against an mm that is in an incomplete state. The change in commit d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") makes this more pertinent as we may be in a state where entries in the maple tree are not yet consistent. Their placement early in dup_mmap() only appears to have been meaningful for early error checking, and since functionally it'd require a very small allocation to fail (in practice 'too small to fail') that'd only occur in the most dire circumstances, meaning the fork would fail or be OOM'd in any case. Since both khugepaged and KSM tracking are there to provide optimisations to memory performance rather than critical functionality, it doesn't really matter all that much if, under such dire memory pressure, we fail to register an mm with these. As a result, we follow the example of commit d2081b2bf819 ("mm: khugepaged: make khugepaged_enter() void function") and make ksm_fork() a void function also. We only expose the mm to these functions once we are done with them and only if no error occurred in the fork operation. Link: https://lkml.kernel.org/r/e0cb8b840c9d1d5a6e84d4f8eff5f3f2022aa10c.1729014377.git.lorenzo.stoakes@oracle.com Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Liam R. Howlett Reviewed-by: Vlastimil Babka Reviewed-by: Jann Horn Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: Linus Torvalds Cc: Signed-off-by: Andrew Morton --- include/linux/ksm.h | 10 ++++------ kernel/fork.c | 7 ++----- 2 files changed, 6 insertions(+), 11 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 11690dacd986..ec9c05044d4f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm) return atomic_long_read(&mm->ksm_zero_pages); } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { + /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); - - return 0; + __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) @@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm) return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline int ksm_execve(struct mm_struct *mm) diff --git a/kernel/fork.c b/kernel/fork.c index 597b477dd491..3bf38d260cb3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -653,11 +653,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; - retval = ksm_fork(mm, oldmm); - if (retval) - goto out; - khugepaged_fork(mm, oldmm); - /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) @@ -760,6 +755,8 @@ loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); + ksm_fork(mm, oldmm); + khugepaged_fork(mm, oldmm); } else if (mpnt) { /* * The entire maple tree has already been duplicated. If the -- cgit v1.2.3