From a2fc422ed75748eef2985454e97847fb22f873c2 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Wed, 21 May 2025 17:04:29 +0200 Subject: syscall_user_dispatch: Add PR_SYS_DISPATCH_INCLUSIVE_ON There are two possible scenarios for syscall filtering: - having a trusted/allowed range of PCs, and intercepting everything else - or the opposite: a single untrusted/intercepted range and allowing everything else (this is relevant for any kind of sandboxing scenario, or monitoring behavior of a single library) The current API only allows the former use case due to allowed range wrap-around check. Add PR_SYS_DISPATCH_INCLUSIVE_ON that enables the second use case. Add PR_SYS_DISPATCH_EXCLUSIVE_ON alias for PR_SYS_DISPATCH_ON to make it clear how it's different from the new PR_SYS_DISPATCH_INCLUSIVE_ON. Signed-off-by: Dmitry Vyukov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/97947cc8e205ff49675826d7b0327ef2e2c66eea.1747839857.git.dvyukov@google.com --- kernel/entry/syscall_user_dispatch.c | 36 +++++++++++++++++++++++------------- 1 file changed, 23 insertions(+), 13 deletions(-) (limited to 'kernel/entry/syscall_user_dispatch.c') diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index 5340c5aa89e7..a9055eccb27e 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -78,7 +78,7 @@ static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned lon if (offset || len || selector) return -EINVAL; break; - case PR_SYS_DISPATCH_ON: + case PR_SYS_DISPATCH_EXCLUSIVE_ON: /* * Validate the direct dispatcher region just for basic * sanity against overflow and a 0-sized dispatcher @@ -87,30 +87,40 @@ static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned lon */ if (offset && offset + len <= offset) return -EINVAL; - + break; + case PR_SYS_DISPATCH_INCLUSIVE_ON: + if (len == 0 || offset + len <= offset) + return -EINVAL; /* - * access_ok() will clear memory tags for tagged addresses - * if current has memory tagging enabled. - - * To enable a tracer to set a tracees selector the - * selector address must be untagged for access_ok(), - * otherwise an untagged tracer will always fail to set a - * tagged tracees selector. + * Invert the range, the check in syscall_user_dispatch() + * supports wrap-around. */ - if (selector && !access_ok(untagged_addr(selector), sizeof(*selector))) - return -EFAULT; - + offset = offset + len; + len = -len; break; default: return -EINVAL; } + /* + * access_ok() will clear memory tags for tagged addresses + * if current has memory tagging enabled. + * + * To enable a tracer to set a tracees selector the + * selector address must be untagged for access_ok(), + * otherwise an untagged tracer will always fail to set a + * tagged tracees selector. + */ + if (mode != PR_SYS_DISPATCH_OFF && selector && + !access_ok(untagged_addr(selector), sizeof(*selector))) + return -EFAULT; + task->syscall_dispatch.selector = selector; task->syscall_dispatch.offset = offset; task->syscall_dispatch.len = len; task->syscall_dispatch.on_dispatch = false; - if (mode == PR_SYS_DISPATCH_ON) + if (mode != PR_SYS_DISPATCH_OFF) set_task_syscall_work(task, SYSCALL_USER_DISPATCH); else clear_task_syscall_work(task, SYSCALL_USER_DISPATCH); -- cgit v1.2.3