From patchwork Tue Jul 12 01:42:01 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: AKASHI Takahiro X-Patchwork-Id: 71765 Delivered-To: patch@linaro.org Received: by 10.140.29.52 with SMTP id a49csp221020qga; Mon, 11 Jul 2016 18:37:55 -0700 (PDT) X-Received: by 10.66.219.105 with SMTP id pn9mr17478931pac.25.1468287475755; Mon, 11 Jul 2016 18:37:55 -0700 (PDT) Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id wo10si1107279pab.206.2016.07.11.18.37.55; Mon, 11 Jul 2016 18:37:55 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE dis=NONE) header.from=linaro.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932664AbcGLBho (ORCPT + 30 others); Mon, 11 Jul 2016 21:37:44 -0400 Received: from mail-pf0-f174.google.com ([209.85.192.174]:34847 "EHLO mail-pf0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932560AbcGLBhl (ORCPT ); Mon, 11 Jul 2016 21:37:41 -0400 Received: by mail-pf0-f174.google.com with SMTP id c2so806120pfa.2 for ; Mon, 11 Jul 2016 18:37:41 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=tlRo2ahBRDfTUl3h8x9SZMaqq8xY/JXEx8/Yc0LzIls=; b=g5tpCDJEjD0vIZ6HEUAqpWVa8k2AyOZVZYlHcvJYIn3gz9QEg4TAxrOGLDT9xB1vXx 8WfHqE1uhXiZb3qMcwdNdY6QL92yEEchPblYC4cpDaXTYREh65AQgAgu/NMV032YjHxV 76AUkvJPm/Q4VYy61LvjfCkfIPzfw5wafju2c= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=tlRo2ahBRDfTUl3h8x9SZMaqq8xY/JXEx8/Yc0LzIls=; b=Itjz3EfBaPWlnrfgISNMJrUqPluGg89mTjlykP+Z+Qb3YnK850UDZjA2+CrGdZhgPo 1kWoK6mZMtPooNtD1Z4sYrvy2RbGWpj8rTjyyZmAkY0FN0CYkz74bmumg889o+zXPCks tsDEoChp5vj5EUP9O0BTeEZIv7cbyaU5WB9anneoUqhfqoIGSpRq116nE6ogQQGU7+0w ASneo/Hn5UlUEkYcbSWKxUbKiXXXmrZeRKLt2u3p7kbP6FZ1sGQLAGcKFxnst/cW/3X6 LUFpaJNYFcxdAKN4okXA3epp8iBUnSCt5denwgwaRosPf/GWtgVPfyavuRaAH8yp8imJ Z8fA== X-Gm-Message-State: ALyK8tLcqvru3FgQpxVPMtJkQ/+woe+IO1BQwEbhNtWexpE8Ddtpzoshrm63l6YCiUtLAaYt X-Received: by 10.98.64.4 with SMTP id n4mr37873571pfa.30.1468287460317; Mon, 11 Jul 2016 18:37:40 -0700 (PDT) Received: from linaro.org ([121.95.100.191]) by smtp.googlemail.com with ESMTPSA id k76sm3949146pfg.53.2016.07.11.18.37.39 (version=TLS1_2 cipher=AES128-SHA bits=128/128); Mon, 11 Jul 2016 18:37:39 -0700 (PDT) From: AKASHI Takahiro To: ebiederm@xmission.com, vgoyal@redhat.com, dyoung@redhat.com, bhe@redhat.com, bauerman@linux.vnet.ibm.com, arnd@arndb.de Cc: kexec@lists.infradead.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linuxppc-dev@lists.ozlabs.org, AKASHI Takahiro Subject: [RFC 3/3] kexec: extend kexec_file_load system call Date: Tue, 12 Jul 2016 10:42:01 +0900 Message-Id: <20160712014201.11456-4-takahiro.akashi@linaro.org> X-Mailer: git-send-email 2.9.0 In-Reply-To: <20160712014201.11456-1-takahiro.akashi@linaro.org> References: <20160712014201.11456-1-takahiro.akashi@linaro.org> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Device tree blob must be passed to a second kernel on DTB-capable archs, like powerpc and arm64, but the current kernel interface lacks this support. This patch extends kexec_file_load system call by adding an extra argument to this syscall so that an arbitrary number of file descriptors can be handed out from user space to the kernel. long sys_kexec_file_load(int kernel_fd, int initrd_fd, unsigned long cmdline_len, const char __user *cmdline_ptr, unsigned long flags, const struct kexec_fdset __user *ufdset); If KEXEC_FILE_EXTRA_FDS is set to the "flags" argument, the "ufdset" argument points to the following struct buffer: struct kexec_fdset { int nr_fds; struct kexec_file_fd fds[0]; } Signed-off-by: AKASHI Takahiro --- include/linux/fs.h | 1 + include/linux/kexec.h | 2 +- include/linux/syscalls.h | 4 +++- include/uapi/linux/kexec.h | 17 ++++++++++++++ kernel/kexec_file.c | 57 ++++++++++++++++++++++++++++++++++++++++------ 5 files changed, 72 insertions(+), 9 deletions(-) -- 2.9.0 diff --git a/include/linux/fs.h b/include/linux/fs.h index dd28814..6dd6fdf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2634,6 +2634,7 @@ extern int do_pipe_flags(int *, int); id(MODULE, kernel-module) \ id(KEXEC_IMAGE, kexec-image) \ id(KEXEC_INITRAMFS, kexec-initramfs) \ + id(KEXEC_DTB, kexec-dtb) \ id(POLICY, security-policy) \ id(MAX_ID, ) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 554c848..5f11bd5 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -277,7 +277,7 @@ extern int kexec_load_disabled; /* List of defined/legal kexec file flags */ #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ - KEXEC_FILE_NO_INITRAMFS) + KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_EXTRA_FDS) #define VMCOREINFO_BYTES (4096) #define VMCOREINFO_NOTE_NAME "VMCOREINFO" diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d022390..fc072bd 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -66,6 +66,7 @@ struct perf_event_attr; struct file_handle; struct sigaltstack; union bpf_attr; +struct kexec_fdset; #include #include @@ -321,7 +322,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, asmlinkage long sys_kexec_file_load(int kernel_fd, int initrd_fd, unsigned long cmdline_len, const char __user *cmdline_ptr, - unsigned long flags); + unsigned long flags, + const struct kexec_fdset __user *ufdset); asmlinkage long sys_exit(int error_code); asmlinkage long sys_exit_group(int error_code); diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index aae5ebf..adf53b6 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -23,6 +23,23 @@ #define KEXEC_FILE_UNLOAD 0x00000001 #define KEXEC_FILE_ON_CRASH 0x00000002 #define KEXEC_FILE_NO_INITRAMFS 0x00000004 +#define KEXEC_FILE_EXTRA_FDS 0x00000008 + +enum kexec_file_type { + KEXEC_FILE_TYPE_KERNEL, + KEXEC_FILE_TYPE_INITRAMFS, + KEXEC_FILE_TYPE_DTB, +}; + +struct kexec_file_fd { + enum kexec_file_type type; + int fd; +}; + +struct kexec_fdset { + int nr_fds; + struct kexec_file_fd fds[0]; +}; /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 7278329..451b4b0 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -137,11 +137,14 @@ void kimage_file_post_load_cleanup(struct kimage *image) static int kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, const char __user *cmdline_ptr, - unsigned long cmdline_len, unsigned flags) + unsigned long cmdline_len, unsigned long flags, + const struct kexec_fdset __user *ufdset) { - int ret = 0; + int ret = 0, nr_fds, i; void *ldata; loff_t size; + struct kexec_fdset *fdset = NULL; + size_t fdset_size; ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf, &size, INT_MAX, READING_KEXEC_IMAGE); @@ -174,6 +177,42 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, image->initrd_buf_len = size; } + if (flags & KEXEC_FILE_EXTRA_FDS) { + ret = copy_from_user(&nr_fds, ufdset, sizeof(int)); + if (ret) { + ret = -EFAULT; + goto out; + } + + fdset_size = sizeof(struct kexec_fdset) + + nr_fds * sizeof(struct kexec_file_fd); + fdset = kmalloc(fdset_size, GFP_KERNEL); + if (!fdset) { + ret = -ENOMEM; + goto out; + } + + ret = copy_from_user(fdset, ufdset, fdset_size); + if (ret) { + ret = -EFAULT; + goto out; + } + + for (i = 0; i < fdset->nr_fds; i++) { + if (fdset->fds[i].type == KEXEC_FILE_TYPE_DTB) { + ret = kernel_read_file_from_fd(fdset->fds[i].fd, + &image->dtb_buf, &size, INT_MAX, + READING_KEXEC_DTB); + if (ret) + goto out; + image->dtb_buf_len = size; + } else { + pr_debug("unknown file type %d failed.\n", + fdset->fds[i].type); + } + } + } + if (cmdline_len) { image->cmdline_buf = kzalloc(cmdline_len, GFP_KERNEL); if (!image->cmdline_buf) { @@ -208,6 +247,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, image->image_loader_data = ldata; out: /* In case of error, free up all allocated memory in this function */ + kfree(fdset); + if (ret) kimage_file_post_load_cleanup(image); return ret; @@ -216,7 +257,8 @@ out: static int kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, int initrd_fd, const char __user *cmdline_ptr, - unsigned long cmdline_len, unsigned long flags) + unsigned long cmdline_len, unsigned long flags, + const struct kexec_fdset __user *ufdset) { int ret; struct kimage *image; @@ -235,7 +277,8 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, } ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd, - cmdline_ptr, cmdline_len, flags); + cmdline_ptr, cmdline_len, flags, + ufdset); if (ret) goto out_free_image; @@ -270,9 +313,9 @@ out_free_image: return ret; } -SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, +SYSCALL_DEFINE6(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, - unsigned long, flags) + unsigned long, flags, const struct kexec_fdset __user *, ufdset) { int ret = 0, i; struct kimage **dest_image, *image; @@ -309,7 +352,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, kimage_free(xchg(&kexec_crash_image, NULL)); ret = kimage_file_alloc_init(&image, kernel_fd, initrd_fd, cmdline_ptr, - cmdline_len, flags); + cmdline_len, flags, ufdset); if (ret) goto out;