From patchwork Thu Jul 16 12:48:31 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stefano Garzarella X-Patchwork-Id: 11667371 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id A359313B4 for ; Thu, 16 Jul 2020 12:49:20 +0000 (UTC) Received: from mother.openwall.net (mother.openwall.net [195.42.179.200]) by mail.kernel.org (Postfix) with SMTP id 0C68C20739 for ; Thu, 16 Jul 2020 12:49:19 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="P2Tk3NYx" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 0C68C20739 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kernel-hardening-return-19346-patchwork-kernel-hardening=patchwork.kernel.org@lists.openwall.com Received: (qmail 26298 invoked by uid 550); 16 Jul 2020 12:49:12 -0000 Mailing-List: contact kernel-hardening-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-ID: Delivered-To: mailing list kernel-hardening@lists.openwall.com Received: (qmail 26166 invoked from network); 16 Jul 2020 12:49:11 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1594903739; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Odxlq9Ln5GrmGx+aMPEKeiGZ+J1+ZE/sVWWvuPsLyGs=; b=P2Tk3NYxzbjMVMQ6rgH3yWBV+MhzDAUpN275PjR8xSsf3tNtAwky33tXK5D+4jbeU7Uj46 nLRAcmJUp4g5LVitFzenGrX4DpGO4fhSiQc3ug6ytPns/PSJJzLjdYjOEXJf1NQpdkEzsx aivW6UPDljkTrdF2OGmBDFh2GafB/L8= X-MC-Unique: opOtX4U3M22wtJYFkI7UFQ-1 From: Stefano Garzarella To: Jens Axboe Cc: Alexander Viro , Kernel Hardening , Kees Cook , Aleksa Sarai , Stefan Hajnoczi , Christian Brauner , Sargun Dhillon , Jann Horn , io-uring@vger.kernel.org, linux-fsdevel@vger.kernel.org, Jeff Moyer , linux-kernel@vger.kernel.org Subject: [PATCH RFC v2 1/3] io_uring: use an enumeration for io_uring_register(2) opcodes Date: Thu, 16 Jul 2020 14:48:31 +0200 Message-Id: <20200716124833.93667-2-sgarzare@redhat.com> In-Reply-To: <20200716124833.93667-1-sgarzare@redhat.com> References: <20200716124833.93667-1-sgarzare@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 The enumeration allows us to keep track of the last io_uring_register(2) opcode available. Behaviour and opcodes names don't change. Signed-off-by: Stefano Garzarella --- include/uapi/linux/io_uring.h | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 7843742b8b74..efc50bd0af34 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -253,17 +253,22 @@ struct io_uring_params { /* * io_uring_register(2) opcodes and arguments */ -#define IORING_REGISTER_BUFFERS 0 -#define IORING_UNREGISTER_BUFFERS 1 -#define IORING_REGISTER_FILES 2 -#define IORING_UNREGISTER_FILES 3 -#define IORING_REGISTER_EVENTFD 4 -#define IORING_UNREGISTER_EVENTFD 5 -#define IORING_REGISTER_FILES_UPDATE 6 -#define IORING_REGISTER_EVENTFD_ASYNC 7 -#define IORING_REGISTER_PROBE 8 -#define IORING_REGISTER_PERSONALITY 9 -#define IORING_UNREGISTER_PERSONALITY 10 +enum { + IORING_REGISTER_BUFFERS, + IORING_UNREGISTER_BUFFERS, + IORING_REGISTER_FILES, + IORING_UNREGISTER_FILES, + IORING_REGISTER_EVENTFD, + IORING_UNREGISTER_EVENTFD, + IORING_REGISTER_FILES_UPDATE, + IORING_REGISTER_EVENTFD_ASYNC, + IORING_REGISTER_PROBE, + IORING_REGISTER_PERSONALITY, + IORING_UNREGISTER_PERSONALITY, + + /* this goes last */ + IORING_REGISTER_LAST +}; struct io_uring_files_update { __u32 offset; From patchwork Thu Jul 16 12:48:32 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stefano Garzarella X-Patchwork-Id: 11667373 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id AF8AA60D for ; Thu, 16 Jul 2020 12:49:28 +0000 (UTC) Received: from mother.openwall.net (mother.openwall.net [195.42.179.200]) by mail.kernel.org (Postfix) with SMTP id E272120739 for ; Thu, 16 Jul 2020 12:49:27 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="Ax6JKLbM" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org E272120739 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kernel-hardening-return-19347-patchwork-kernel-hardening=patchwork.kernel.org@lists.openwall.com Received: (qmail 27835 invoked by uid 550); 16 Jul 2020 12:49:17 -0000 Mailing-List: contact kernel-hardening-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-ID: Delivered-To: mailing list kernel-hardening@lists.openwall.com Received: (qmail 27743 invoked from network); 16 Jul 2020 12:49:16 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1594903745; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wQZLpoLtzsM5d9s2luOcVBYZTZ6mFy5zueA78VrJwvg=; b=Ax6JKLbMrI/W0Azxh/ara5VthWSC7r6mEKm7Y5+6niMSlfYgblYx6Cbq4TIo6ysPZfPFEY e4YT10g/JJ613rCG/rKwOYuacw/Y0Q2anOUYCwMiXmynqK6TQ9sPwbdVUKXZ6cEpkTxMOY vFiDM9QcmGsYk0fFbVZJS9byGgUo3aw= X-MC-Unique: gXHKOYObP3aRqJwTt1_tlA-1 From: Stefano Garzarella To: Jens Axboe Cc: Alexander Viro , Kernel Hardening , Kees Cook , Aleksa Sarai , Stefan Hajnoczi , Christian Brauner , Sargun Dhillon , Jann Horn , io-uring@vger.kernel.org, linux-fsdevel@vger.kernel.org, Jeff Moyer , linux-kernel@vger.kernel.org Subject: [PATCH RFC v2 2/3] io_uring: add IOURING_REGISTER_RESTRICTIONS opcode Date: Thu, 16 Jul 2020 14:48:32 +0200 Message-Id: <20200716124833.93667-3-sgarzare@redhat.com> In-Reply-To: <20200716124833.93667-1-sgarzare@redhat.com> References: <20200716124833.93667-1-sgarzare@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 The new io_uring_register(2) IOURING_REGISTER_RESTRICTIONS opcode permanently installs a feature allowlist on an io_ring_ctx. The io_ring_ctx can then be passed to untrusted code with the knowledge that only operations present in the allowlist can be executed. The allowlist approach ensures that new features added to io_uring do not accidentally become available when an existing application is launched on a newer kernel version. Currently is it possible to restrict sqe opcodes and register opcodes. It is also possible to allow only fixed files. IOURING_REGISTER_RESTRICTIONS can only be made once. Afterwards it is not possible to change restrictions anymore. This prevents untrusted code from removing restrictions. Suggested-by: Stefan Hajnoczi Signed-off-by: Stefano Garzarella --- RFC v2: - added 'restricted' flag in the ctx [Jens] - added IORING_MAX_RESTRICTIONS define - returned EBUSY instead of EINVAL when restrictions are already registered - reset restrictions if an error happened during the registration --- fs/io_uring.c | 102 +++++++++++++++++++++++++++++++++- include/uapi/linux/io_uring.h | 27 +++++++++ 2 files changed, 128 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 9fd7e69696c3..23a2b03d9528 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -97,6 +97,8 @@ #define IORING_MAX_FILES_TABLE (1U << IORING_FILE_TABLE_SHIFT) #define IORING_FILE_TABLE_MASK (IORING_MAX_FILES_TABLE - 1) #define IORING_MAX_FIXED_FILES (64 * IORING_MAX_FILES_TABLE) +#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ + IORING_REGISTER_LAST + IORING_OP_LAST) struct io_uring { u32 head ____cacheline_aligned_in_smp; @@ -218,6 +220,12 @@ struct io_buffer { __u16 bid; }; +struct io_restriction { + DECLARE_BITMAP(register_op, IORING_REGISTER_LAST); + DECLARE_BITMAP(sqe_op, IORING_OP_LAST); + DECLARE_BITMAP(restriction_op, IORING_RESTRICTION_LAST); +}; + struct io_ring_ctx { struct { struct percpu_ref refs; @@ -230,6 +238,7 @@ struct io_ring_ctx { unsigned int cq_overflow_flushed: 1; unsigned int drain_next: 1; unsigned int eventfd_async: 1; + unsigned int restricted: 1; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -337,6 +346,7 @@ struct io_ring_ctx { struct llist_head file_put_llist; struct work_struct exit_work; + struct io_restriction restrictions; }; /* @@ -5496,6 +5506,11 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, if (unlikely(!fixed && io_async_submit(req->ctx))) return -EBADF; + if (unlikely(!fixed && req->ctx->restricted && + test_bit(IORING_RESTRICTION_FIXED_FILES_ONLY, + req->ctx->restrictions.restriction_op))) + return -EACCES; + return io_file_get(state, req, fd, &req->file, fixed); } @@ -5900,6 +5915,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (unlikely(req->opcode >= IORING_OP_LAST)) return -EINVAL; + if (unlikely(ctx->restricted && + !test_bit(req->opcode, ctx->restrictions.sqe_op))) + return -EACCES; + if (unlikely(io_sq_thread_acquire_mm(ctx, req))) return -EFAULT; @@ -8099,6 +8118,71 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) return -EINVAL; } +static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, + unsigned int nr_args) +{ + struct io_uring_restriction *res; + size_t size; + int i, ret; + + /* We allow only a single restrictions registration */ + if (ctx->restricted) + return -EBUSY; + + if (!arg || nr_args > IORING_MAX_RESTRICTIONS) + return -EINVAL; + + size = array_size(nr_args, sizeof(*res)); + if (size == SIZE_MAX) + return -EOVERFLOW; + + res = kmalloc(size, GFP_KERNEL); + if (!res) + return -ENOMEM; + + if (copy_from_user(res, arg, size)) { + ret = -EFAULT; + goto out; + } + + for (i = 0; i < nr_args; i++) { + if (res[i].opcode >= IORING_RESTRICTION_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].opcode, ctx->restrictions.restriction_op); + + if (res[i].opcode == IORING_RESTRICTION_REGISTER_OP) { + if (res[i].register_op >= IORING_REGISTER_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].register_op, + ctx->restrictions.register_op); + } else if (res[i].opcode == IORING_RESTRICTION_SQE_OP) { + if (res[i].sqe_op >= IORING_OP_LAST) { + ret = -EINVAL; + goto out; + } + + __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op); + } + } + + ctx->restricted = 1; + + ret = 0; +out: + /* Reset all restrictions if an error happened */ + if (ret != 0) + memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); + + kfree(res); + return ret; +} + static bool io_register_op_must_quiesce(int op) { switch (op) { @@ -8145,6 +8229,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, if (ret) { percpu_ref_resurrect(&ctx->refs); ret = -EINTR; + goto out_quiesce; + } + } + + if (ctx->restricted) { + if (opcode >= IORING_REGISTER_LAST) { + ret = -EINVAL; + goto out; + } + + if (!test_bit(opcode, ctx->restrictions.register_op)) { + ret = -EACCES; goto out; } } @@ -8208,15 +8304,19 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_unregister_personality(ctx, nr_args); break; + case IORING_REGISTER_RESTRICTIONS: + ret = io_register_restrictions(ctx, arg, nr_args); + break; default: ret = -EINVAL; break; } +out: if (io_register_op_must_quiesce(opcode)) { /* bring the ctx back to life */ percpu_ref_reinit(&ctx->refs); -out: +out_quiesce: reinit_completion(&ctx->ref_comp); } return ret; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index efc50bd0af34..0774d5382c65 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -265,6 +265,7 @@ enum { IORING_REGISTER_PROBE, IORING_REGISTER_PERSONALITY, IORING_UNREGISTER_PERSONALITY, + IORING_REGISTER_RESTRICTIONS, /* this goes last */ IORING_REGISTER_LAST @@ -293,4 +294,30 @@ struct io_uring_probe { struct io_uring_probe_op ops[0]; }; +struct io_uring_restriction { + __u16 opcode; + union { + __u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */ + __u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */ + }; + __u8 resv; + __u32 resv2[3]; +}; + +/* + * io_uring_restriction->opcode values + */ +enum { + /* Allow an io_uring_register(2) opcode */ + IORING_RESTRICTION_REGISTER_OP, + + /* Allow an sqe opcode */ + IORING_RESTRICTION_SQE_OP, + + /* Only allow fixed files */ + IORING_RESTRICTION_FIXED_FILES_ONLY, + + IORING_RESTRICTION_LAST +}; + #endif From patchwork Thu Jul 16 12:48:33 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stefano Garzarella X-Patchwork-Id: 11667375 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0448E60D for ; Thu, 16 Jul 2020 12:49:38 +0000 (UTC) Received: from mother.openwall.net (mother.openwall.net [195.42.179.200]) by mail.kernel.org (Postfix) with SMTP id 383012076D for ; Thu, 16 Jul 2020 12:49:37 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="BJCvd5uI" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 383012076D Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kernel-hardening-return-19348-patchwork-kernel-hardening=patchwork.kernel.org@lists.openwall.com Received: (qmail 30060 invoked by uid 550); 16 Jul 2020 12:49:31 -0000 Mailing-List: contact kernel-hardening-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-ID: Delivered-To: mailing list kernel-hardening@lists.openwall.com Received: (qmail 29980 invoked from network); 16 Jul 2020 12:49:30 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1594903759; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=3IGotHJLDWHOMS4jfIFhav0o5esf4avDkRICTFAhyCo=; b=BJCvd5uIGtgfTXD3qhMtI2Ae2gsT6eDP6OGRk4Ro9Rs7npfisWbo0mGEu7YR42nwqDfsKS NATV69HYhBETqx+EMxrkfDjh9t+el4rwCSwPL0P0AynduwWlx4qxSNa+a4Cy3cRdrRp5RS ZdpOC6rpEgCXSg4GoY1NVCkTVhFBOpE= X-MC-Unique: wSe4nHhrMv606IQIZUQ-PQ-1 From: Stefano Garzarella To: Jens Axboe Cc: Alexander Viro , Kernel Hardening , Kees Cook , Aleksa Sarai , Stefan Hajnoczi , Christian Brauner , Sargun Dhillon , Jann Horn , io-uring@vger.kernel.org, linux-fsdevel@vger.kernel.org, Jeff Moyer , linux-kernel@vger.kernel.org Subject: [PATCH RFC v2 3/3] io_uring: allow disabling rings during the creation Date: Thu, 16 Jul 2020 14:48:33 +0200 Message-Id: <20200716124833.93667-4-sgarzare@redhat.com> In-Reply-To: <20200716124833.93667-1-sgarzare@redhat.com> References: <20200716124833.93667-1-sgarzare@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 This patch adds a new IORING_SETUP_R_DISABLED flag to start the rings disabled, allowing the user to register restrictions, buffers, files, before to start processing SQEs. When IORING_SETUP_R_DISABLED is set, SQE are not processed and SQPOLL kthread is not started. The restrictions registration are allowed only when the rings are disable to prevent concurrency issue while processing SQEs. The rings can be enabled using IORING_REGISTER_ENABLE_RINGS opcode with io_uring_register(2). Suggested-by: Jens Axboe Signed-off-by: Stefano Garzarella --- RFC v2: - removed return value of io_sq_offload_start() --- fs/io_uring.c | 50 +++++++++++++++++++++++++++++------ include/uapi/linux/io_uring.h | 2 ++ 2 files changed, 44 insertions(+), 8 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 23a2b03d9528..2f2ecfa10c94 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6969,8 +6969,8 @@ static int io_init_wq_offload(struct io_ring_ctx *ctx, return ret; } -static int io_sq_offload_start(struct io_ring_ctx *ctx, - struct io_uring_params *p) +static int io_sq_offload_create(struct io_ring_ctx *ctx, + struct io_uring_params *p) { int ret; @@ -7007,7 +7007,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, ctx->sqo_thread = NULL; goto err; } - wake_up_process(ctx->sqo_thread); } else if (p->flags & IORING_SETUP_SQ_AFF) { /* Can't have SQ_AFF without SQPOLL */ ret = -EINVAL; @@ -7026,6 +7025,12 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, return ret; } +static void io_sq_offload_start(struct io_ring_ctx *ctx) +{ + if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sqo_thread) + wake_up_process(ctx->sqo_thread); +} + static void io_unaccount_mem(struct user_struct *user, unsigned long nr_pages) { atomic_long_sub(nr_pages, &user->locked_vm); @@ -7654,9 +7659,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, int submitted = 0; struct fd f; - if (current->task_works) - task_work_run(); - if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP)) return -EINVAL; @@ -7673,6 +7675,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, if (!percpu_ref_tryget(&ctx->refs)) goto out_fput; + if (ctx->flags & IORING_SETUP_R_DISABLED) + return -EBADF; + + if (current->task_works) + task_work_run(); + /* * For SQ polling, the thread will do all submissions and completions. * Just return the requested submit count, and wake the thread if @@ -7978,10 +7986,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, if (ret) goto err; - ret = io_sq_offload_start(ctx, p); + ret = io_sq_offload_create(ctx, p); if (ret) goto err; + if (!(p->flags & IORING_SETUP_R_DISABLED)) + io_sq_offload_start(ctx); + memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); p->sq_off.tail = offsetof(struct io_rings, sq.tail); @@ -8042,7 +8053,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | - IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ)) + IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | + IORING_SETUP_R_DISABLED)) return -EINVAL; return io_uring_create(entries, &p, params); @@ -8125,6 +8137,10 @@ static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, size_t size; int i, ret; + /* Restrictions allowed only if rings started disabled */ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EINVAL; + /* We allow only a single restrictions registration */ if (ctx->restricted) return -EBUSY; @@ -8183,6 +8199,18 @@ static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, return ret; } +static int io_register_enable_rings(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_R_DISABLED)) + return -EINVAL; + + ctx->flags &= ~IORING_SETUP_R_DISABLED; + + io_sq_offload_start(ctx); + + return 0; +} + static bool io_register_op_must_quiesce(int op) { switch (op) { @@ -8304,6 +8332,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_unregister_personality(ctx, nr_args); break; + case IORING_REGISTER_ENABLE_RINGS: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_register_enable_rings(ctx); + break; case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0774d5382c65..ce52333bdc2b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -94,6 +94,7 @@ enum { #define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */ #define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */ #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ +#define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ enum { IORING_OP_NOP, @@ -266,6 +267,7 @@ enum { IORING_REGISTER_PERSONALITY, IORING_UNREGISTER_PERSONALITY, IORING_REGISTER_RESTRICTIONS, + IORING_REGISTER_ENABLE_RINGS, /* this goes last */ IORING_REGISTER_LAST