From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-8.8 required=3.0 tests=DKIM_SIGNED,DKIM_VALID, DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id C5959C6786F for ; Thu, 1 Nov 2018 09:59:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 731E220820 for ; Thu, 1 Nov 2018 09:59:53 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=efficios.com header.i=@efficios.com header.b="TZVi4HPY" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 731E220820 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=efficios.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728361AbeKATCI (ORCPT ); Thu, 1 Nov 2018 15:02:08 -0400 Received: from mail.efficios.com ([167.114.142.138]:41438 "EHLO mail.efficios.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728345AbeKATCF (ORCPT ); Thu, 1 Nov 2018 15:02:05 -0400 Received: from localhost (ip6-localhost [IPv6:::1]) by mail.efficios.com (Postfix) with ESMTP id 4CC4922769F; Thu, 1 Nov 2018 05:59:47 -0400 (EDT) Received: from mail.efficios.com ([IPv6:::1]) by localhost (mail02.efficios.com [IPv6:::1]) (amavisd-new, port 10032) with ESMTP id rk6ytqnCPzXa; Thu, 1 Nov 2018 05:59:46 -0400 (EDT) Received: from localhost (ip6-localhost [IPv6:::1]) by mail.efficios.com (Postfix) with ESMTP id C6D0A22769B; Thu, 1 Nov 2018 05:59:46 -0400 (EDT) DKIM-Filter: OpenDKIM Filter v2.10.3 mail.efficios.com C6D0A22769B DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=efficios.com; s=default; t=1541066386; bh=GZ26zHkI2uFZ/IFYyb1tNeZTZ6P6e1AF5QW+GHa+31k=; h=From:To:Date:Message-Id; b=TZVi4HPYVBcVwjr/09gUjXROvGQAvSoepcx7GOs8Ay159ZC+OoJF1l6YGKZnDlEqe B0LabxOrCeykjNnOzACB3y1ahtgbAErRU7Vn6Tqf62yCZ5vmJxL5OcoFwic6Rafhfh ChwLJUJlcHT94krE9tdesbAAcf48LuCqMQ/7pnd4hhfeKxqhMIvXxuN7EM5u5fnyP6 9KLQr9lg5WyLv6CSQoDPuE5gbJ6Ttzm5sTW0bIlXmEhsdlI2q87+LRrsqtNqHc0k3K Z4Yv6+RLaNMk/7sesmGmnuY38qNWUgjGG6gs2+Wdr64OuPs5pnTT1DVYo7TWZ0fgAL 0JVlTUokmby9w== X-Virus-Scanned: amavisd-new at efficios.com Received: from mail.efficios.com ([IPv6:::1]) by localhost (mail02.efficios.com [IPv6:::1]) (amavisd-new, port 10026) with ESMTP id DpI1j2AvKyHX; Thu, 1 Nov 2018 05:59:46 -0400 (EDT) Received: from thinkos.etherlink (sessfw99-sesbfw99-92.ericsson.net [192.176.1.92]) by mail.efficios.com (Postfix) with ESMTPSA id D891F22768D; Thu, 1 Nov 2018 05:59:39 -0400 (EDT) From: Mathieu Desnoyers To: Peter Zijlstra , "Paul E . McKenney" , Boqun Feng Cc: linux-kernel@vger.kernel.org, linux-api@vger.kernel.org, Thomas Gleixner , Andy Lutomirski , Dave Watson , Paul Turner , Andrew Morton , Russell King , Ingo Molnar , "H . Peter Anvin" , Andi Kleen , Chris Lameter , Ben Maurer , Steven Rostedt , Josh Triplett , Linus Torvalds , Catalin Marinas , Will Deacon , Michael Kerrisk , Joel Fernandes , Mathieu Desnoyers Subject: [RFC PATCH for 4.21 07/16] cpu_opv: limit amount of virtual address space used by cpu_opv Date: Thu, 1 Nov 2018 10:58:35 +0100 Message-Id: <20181101095844.24462-8-mathieu.desnoyers@efficios.com> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20181101095844.24462-1-mathieu.desnoyers@efficios.com> References: <20181101095844.24462-1-mathieu.desnoyers@efficios.com> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Introduce sysctl cpu_opv_va_max_bytes, which limits the amount of virtual address space that can be used by cpu_opv. Its default value is the maximum amount of virtual address space which can be used by a single cpu_opv system call (e.g. 64 kB on x86). Signed-off-by: Mathieu Desnoyers CC: "Paul E. McKenney" CC: Peter Zijlstra CC: Paul Turner CC: Thomas Gleixner CC: Andy Lutomirski CC: Andi Kleen CC: Dave Watson CC: Chris Lameter CC: Ingo Molnar CC: "H. Peter Anvin" CC: Ben Maurer CC: Steven Rostedt CC: Josh Triplett CC: Linus Torvalds CC: Andrew Morton CC: Russell King CC: Catalin Marinas CC: Will Deacon CC: Michael Kerrisk CC: Boqun Feng CC: linux-api@vger.kernel.org --- kernel/cpu_opv.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++++++++- kernel/sysctl.c | 15 ++++++++++++ 2 files changed, 88 insertions(+), 1 deletion(-) diff --git a/kernel/cpu_opv.c b/kernel/cpu_opv.c index 6ee7ca3376be..309d20a35227 100644 --- a/kernel/cpu_opv.c +++ b/kernel/cpu_opv.c @@ -59,6 +59,16 @@ /* Maximum number of virtual addresses per op. */ #define CPU_OP_VEC_MAX_ADDR (2 * CPU_OP_VEC_LEN_MAX) +/* Maximum address range size (aligned on SHMLBA) per virtual address. */ +#define CPU_OP_RANGE_PER_ADDR_MAX (2 * SHMLBA) + +/* + * Minimum value for sysctl_cpu_opv_va_max_bytes is the maximum virtual memory + * space needed by one cpu_opv system call. + */ +#define CPU_OPV_VA_MAX_BYTES_MIN \ + (CPU_OP_VEC_MAX_ADDR * CPU_OP_RANGE_PER_ADDR_MAX) + union op_fn_data { uint8_t _u8; uint16_t _u16; @@ -96,6 +106,15 @@ struct opv_ipi_args { */ static DEFINE_MUTEX(cpu_opv_offline_lock); +/* Maximum virtual address space which can be used by cpu_opv. */ +int sysctl_cpu_opv_va_max_bytes __read_mostly; +int sysctl_cpu_opv_va_max_bytes_min; + +static atomic_t cpu_opv_va_allocated_bytes; + +/* Waitqueue for cpu_opv blocked on virtual address space reservation. */ +static DECLARE_WAIT_QUEUE_HEAD(cpu_opv_va_wait); + /* * The cpu_opv system call executes a vector of operations on behalf of * user-space on a specific CPU either with interrupts disabled or within @@ -489,6 +508,43 @@ static int cpu_opv_pin_pages_op(struct cpu_op *op, return 0; } +/* + * Approximate the amount of virtual address space required per + * vaddr to a worse-case of CPU_OP_RANGE_PER_ADDR_MAX. + */ +static int cpu_opv_reserve_va(int nr_vaddr, int *reserved_va) +{ + int nr_bytes = nr_vaddr * CPU_OP_RANGE_PER_ADDR_MAX; + int old_bytes, new_bytes; + + WARN_ON_ONCE(*reserved_va != 0); + if (nr_bytes > sysctl_cpu_opv_va_max_bytes) { + WARN_ON_ONCE(1); + return -EINVAL; + } + do { + wait_event(cpu_opv_va_wait, + (old_bytes = atomic_read(&cpu_opv_va_allocated_bytes)) + + nr_bytes <= sysctl_cpu_opv_va_max_bytes); + new_bytes = old_bytes + nr_bytes; + } while (atomic_cmpxchg(&cpu_opv_va_allocated_bytes, + old_bytes, new_bytes) != old_bytes); + + *reserved_va = nr_bytes; + return 0; +} + +static void cpu_opv_unreserve_va(int *reserved_va) +{ + int nr_bytes = *reserved_va; + + if (!nr_bytes) + return; + atomic_sub(nr_bytes, &cpu_opv_va_allocated_bytes); + wake_up(&cpu_opv_va_wait); + *reserved_va = 0; +} + static int cpu_opv_pin_pages(struct cpu_op *cpuop, int cpuopcnt, struct cpu_opv_vaddr *vaddr_ptrs) { @@ -898,7 +954,7 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt, struct cpu_opv_vaddr vaddr_ptrs = { .nr_vaddr = 0, }; - int ret, i, nr_vaddr = 0; + int ret, i, nr_vaddr = 0, reserved_va = 0; bool retry = false; if (unlikely(flags & ~(CPU_OP_NR_FLAG | CPU_OP_VEC_LEN_MAX_FLAG))) @@ -922,6 +978,9 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt, if (nr_vaddr > NR_VADDR) return -EINVAL; again: + ret = cpu_opv_reserve_va(nr_vaddr, &reserved_va); + if (ret) + goto end; ret = cpu_opv_pin_pages(cpuopv, cpuopcnt, &vaddr_ptrs); if (ret) goto end; @@ -946,6 +1005,7 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt, */ if (vaddr_ptrs.nr_vaddr) vm_unmap_aliases(); + cpu_opv_unreserve_va(&reserved_va); if (retry) { retry = false; vaddr_ptrs.nr_vaddr = 0; @@ -953,3 +1013,15 @@ SYSCALL_DEFINE4(cpu_opv, struct cpu_op __user *, ucpuopv, int, cpuopcnt, } return ret; } + +/* + * Dynamic initialization is required on sparc because SHMLBA is not a + * constant. + */ +static int __init cpu_opv_init(void) +{ + sysctl_cpu_opv_va_max_bytes = CPU_OPV_VA_MAX_BYTES_MIN; + sysctl_cpu_opv_va_max_bytes_min = CPU_OPV_VA_MAX_BYTES_MIN; + return 0; +} +core_initcall(cpu_opv_init); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cc02050fd0c4..eb34c6be2aa4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -175,6 +175,11 @@ extern int unaligned_dump_stack; extern int no_unaligned_warning; #endif +#ifdef CONFIG_CPU_OPV +extern int sysctl_cpu_opv_va_max_bytes; +extern int sysctl_cpu_opv_va_max_bytes_min; +#endif + #ifdef CONFIG_PROC_SYSCTL /** @@ -1233,6 +1238,16 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_CPU_OPV + { + .procname = "cpu_opv_va_max_bytes", + .data = &sysctl_cpu_opv_va_max_bytes, + .maxlen = sizeof(sysctl_cpu_opv_va_max_bytes), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &sysctl_cpu_opv_va_max_bytes_min, + }, +#endif { } }; -- 2.11.0