From 4b6b037c15b9463e6e80aa8d346e53f08ecabb34 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Fri, 6 Jun 2014 14:36:09 -0700 Subject: [PATCH 01/53] rtc: rtc-at91rm9200: fix infinite wait for ACKUPD irq commit 2fe121e1f5aa3bf31b418a9790db6c400e922291 upstream. The rtc user must wait at least 1 sec between each time/calandar update (see atmel's datasheet chapter "Updating Time/Calendar"). Use the 1Hz interrupt to update the at91_rtc_upd_rdy flag and wait for the at91_rtc_wait_upd_rdy event if the rtc is not ready. This patch fixes a deadlock in an uninterruptible wait when the RTC is updated more than once every second. AFAICT the bug is here from the beginning, but I think we should at least backport this fix to 3.10 and the following longterm and stable releases. Signed-off-by: Boris BREZILLON Reported-by: Bryan Evenson Tested-by: Bryan Evenson Cc: Andrew Victor Cc: Nicolas Ferre Cc: Jean-Christophe Plagniol-Villard Cc: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/rtc/rtc-at91rm9200.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index 1237c2173c6d..e51cc5fec98a 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -49,6 +49,7 @@ struct at91_rtc_config { static const struct at91_rtc_config *at91_rtc_config; static DECLARE_COMPLETION(at91_rtc_updated); +static DECLARE_COMPLETION(at91_rtc_upd_rdy); static unsigned int at91_alarm_year = AT91_RTC_EPOCH; static void __iomem *at91_rtc_regs; static int irq; @@ -162,6 +163,8 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm) 1900 + tm->tm_year, tm->tm_mon, tm->tm_mday, tm->tm_hour, tm->tm_min, tm->tm_sec); + wait_for_completion(&at91_rtc_upd_rdy); + /* Stop Time/Calendar from counting */ cr = at91_rtc_read(AT91_RTC_CR); at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM); @@ -184,7 +187,9 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm) /* Restart Time/Calendar */ cr = at91_rtc_read(AT91_RTC_CR); + at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV); at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM)); + at91_rtc_write_ier(AT91_RTC_SECEV); return 0; } @@ -291,8 +296,10 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id) if (rtsr) { /* this interrupt is shared! Is it ours? */ if (rtsr & AT91_RTC_ALARM) events |= (RTC_AF | RTC_IRQF); - if (rtsr & AT91_RTC_SECEV) - events |= (RTC_UF | RTC_IRQF); + if (rtsr & AT91_RTC_SECEV) { + complete(&at91_rtc_upd_rdy); + at91_rtc_write_idr(AT91_RTC_SECEV); + } if (rtsr & AT91_RTC_ACKUPD) complete(&at91_rtc_updated); @@ -415,6 +422,11 @@ static int __init at91_rtc_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, rtc); + /* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy + * completion. + */ + at91_rtc_write_ier(AT91_RTC_SECEV); + dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n"); return 0; From 63afedf498ed0971cbb18db542af635d94152f74 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 5 Jun 2014 18:08:57 -0700 Subject: [PATCH 02/53] iscsi-target: Reject mutual authentication with reflected CHAP_C commit 1d2b60a5545942b1376cb48c1d55843d71e3a08f upstream. This patch adds an explicit check in chap_server_compute_md5() to ensure the CHAP_C value received from the initiator during mutual authentication does not match the original CHAP_C provided by the target. This is in line with RFC-3720, section 8.2.1: Originators MUST NOT reuse the CHAP challenge sent by the Responder for the other direction of a bidirectional authentication. Responders MUST check for this condition and close the iSCSI TCP connection if it occurs. Reported-by: Tejas Vaykole Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman --- drivers/target/iscsi/iscsi_target_auth.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index 130a1e4f96a1..3c9a8dfd1c2e 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -315,6 +315,16 @@ static int chap_server_compute_md5( pr_err("Unable to convert incoming challenge\n"); goto out; } + /* + * During mutual authentication, the CHAP_C generated by the + * initiator must not match the original CHAP_C generated by + * the target. + */ + if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) { + pr_err("initiator CHAP_C matches target CHAP_C, failing" + " login attempt\n"); + goto out; + } /* * Generate CHAP_N and CHAP_R for mutual authentication. */ From 8b46db3abbe22919d249e26c26178d70f19b8262 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Thu, 8 May 2014 14:03:22 +0300 Subject: [PATCH 03/53] ima: introduce ima_kernel_read() commit 0430e49b6e7c6b5e076be8fefdee089958c9adad upstream. Commit 8aac62706 "move exit_task_namespaces() outside of exit_notify" introduced the kernel opps since the kernel v3.10, which happens when Apparmor and IMA-appraisal are enabled at the same time. ---------------------------------------------------------------------- [ 106.750167] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 [ 106.750221] IP: [] our_mnt+0x1a/0x30 [ 106.750241] PGD 0 [ 106.750254] Oops: 0000 [#1] SMP [ 106.750272] Modules linked in: cuse parport_pc ppdev bnep rfcomm bluetooth rpcsec_gss_krb5 nfsd auth_rpcgss nfs_acl nfs lockd sunrpc fscache dm_crypt intel_rapl x86_pkg_temp_thermal intel_powerclamp kvm_intel snd_hda_codec_hdmi kvm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd snd_hda_codec_realtek dcdbas snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_page_alloc snd_seq_midi snd_seq_midi_event snd_rawmidi psmouse snd_seq microcode serio_raw snd_timer snd_seq_device snd soundcore video lpc_ich coretemp mac_hid lp parport mei_me mei nbd hid_generic e1000e usbhid ahci ptp hid libahci pps_core [ 106.750658] CPU: 6 PID: 1394 Comm: mysqld Not tainted 3.13.0-rc7-kds+ #15 [ 106.750673] Hardware name: Dell Inc. OptiPlex 9010/0M9KCM, BIOS A08 09/19/2012 [ 106.750689] task: ffff8800de804920 ti: ffff880400fca000 task.ti: ffff880400fca000 [ 106.750704] RIP: 0010:[] [] our_mnt+0x1a/0x30 [ 106.750725] RSP: 0018:ffff880400fcba60 EFLAGS: 00010286 [ 106.750738] RAX: 0000000000000000 RBX: 0000000000000100 RCX: ffff8800d51523e7 [ 106.750764] RDX: ffffffffffffffea RSI: ffff880400fcba34 RDI: ffff880402d20020 [ 106.750791] RBP: ffff880400fcbae0 R08: 0000000000000000 R09: 0000000000000001 [ 106.750817] R10: 0000000000000000 R11: 0000000000000001 R12: ffff8800d5152300 [ 106.750844] R13: ffff8803eb8df510 R14: ffff880400fcbb28 R15: ffff8800d51523e7 [ 106.750871] FS: 0000000000000000(0000) GS:ffff88040d200000(0000) knlGS:0000000000000000 [ 106.750910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 106.750935] CR2: 0000000000000018 CR3: 0000000001c0e000 CR4: 00000000001407e0 [ 106.750962] Stack: [ 106.750981] ffffffff813434eb ffff880400fcbb20 ffff880400fcbb18 0000000000000000 [ 106.751037] ffff8800de804920 ffffffff8101b9b9 0001800000000000 0000000000000100 [ 106.751093] 0000010000000000 0000000000000002 000000000000000e ffff8803eb8df500 [ 106.751149] Call Trace: [ 106.751172] [] ? aa_path_name+0x2ab/0x430 [ 106.751199] [] ? sched_clock+0x9/0x10 [ 106.751225] [] aa_path_perm+0x7d/0x170 [ 106.751250] [] ? native_sched_clock+0x15/0x80 [ 106.751276] [] aa_file_perm+0x33/0x40 [ 106.751301] [] common_file_perm+0x8e/0xb0 [ 106.751327] [] apparmor_file_permission+0x18/0x20 [ 106.751355] [] security_file_permission+0x23/0xa0 [ 106.751382] [] rw_verify_area+0x52/0xe0 [ 106.751407] [] vfs_read+0x6d/0x170 [ 106.751432] [] kernel_read+0x41/0x60 [ 106.751457] [] ima_calc_file_hash+0x225/0x280 [ 106.751483] [] ? ima_calc_file_hash+0x32/0x280 [ 106.751509] [] ima_collect_measurement+0x9d/0x160 [ 106.751536] [] ? trace_hardirqs_on+0xd/0x10 [ 106.751562] [] ? ima_file_free+0x6c/0xd0 [ 106.751587] [] ima_update_xattr+0x34/0x60 [ 106.751612] [] ima_file_free+0xc0/0xd0 [ 106.751637] [] __fput+0xd5/0x300 [ 106.751662] [] ____fput+0xe/0x10 [ 106.751687] [] task_work_run+0xc4/0xe0 [ 106.751712] [] do_exit+0x2bd/0xa90 [ 106.751738] [] ? retint_swapgs+0x13/0x1b [ 106.751763] [] do_group_exit+0x4c/0xc0 [ 106.751788] [] SyS_exit_group+0x14/0x20 [ 106.751814] [] system_call_fastpath+0x1a/0x1f [ 106.751839] Code: c3 0f 1f 44 00 00 55 48 89 e5 e8 22 fe ff ff 5d c3 0f 1f 44 00 00 55 65 48 8b 04 25 c0 c9 00 00 48 8b 80 28 06 00 00 48 89 e5 5d <48> 8b 40 18 48 39 87 c0 00 00 00 0f 94 c0 c3 0f 1f 80 00 00 00 [ 106.752185] RIP [] our_mnt+0x1a/0x30 [ 106.752214] RSP [ 106.752236] CR2: 0000000000000018 [ 106.752258] ---[ end trace 3c520748b4732721 ]--- ---------------------------------------------------------------------- The reason for the oops is that IMA-appraisal uses "kernel_read()" when file is closed. kernel_read() honors LSM security hook which calls Apparmor handler, which uses current->nsproxy->mnt_ns. The 'guilty' commit changed the order of cleanup code so that nsproxy->mnt_ns was not already available for Apparmor. Discussion about the issue with Al Viro and Eric W. Biederman suggested that kernel_read() is too high-level for IMA. Another issue, except security checking, that was identified is mandatory locking. kernel_read honors it as well and it might prevent IMA from calculating necessary hash. It was suggested to use simplified version of the function without security and locking checks. This patch introduces special version ima_kernel_read(), which skips security and mandatory locking checking. It prevents the kernel oops to happen. Signed-off-by: Dmitry Kasatkin Suggested-by: Eric W. Biederman Signed-off-by: Mimi Zohar Signed-off-by: Greg Kroah-Hartman --- security/integrity/ima/ima_crypto.c | 32 ++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index a02e0791cf15..9da974c0f958 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -24,6 +24,36 @@ static struct crypto_shash *ima_shash_tfm; +/** + * ima_kernel_read - read file content + * + * This is a function for reading file content instead of kernel_read(). + * It does not perform locking checks to ensure it cannot be blocked. + * It does not perform security checks because it is irrelevant for IMA. + * + */ +static int ima_kernel_read(struct file *file, loff_t offset, + char *addr, unsigned long count) +{ + mm_segment_t old_fs; + char __user *buf = addr; + ssize_t ret; + + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + if (!file->f_op->read && !file->f_op->aio_read) + return -EINVAL; + + old_fs = get_fs(); + set_fs(get_ds()); + if (file->f_op->read) + ret = file->f_op->read(file, buf, count, &offset); + else + ret = do_sync_read(file, buf, count, &offset); + set_fs(old_fs); + return ret; +} + int ima_init_crypto(void) { long rc; @@ -70,7 +100,7 @@ int ima_calc_file_hash(struct file *file, char *digest) while (offset < i_size) { int rbuf_len; - rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE); + rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE); if (rbuf_len < 0) { rc = rbuf_len; break; From bb7f9e5c384dbd4a1548a12c1e49d8bbfa3913a8 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sun, 11 May 2014 00:05:23 -0400 Subject: [PATCH 04/53] evm: prohibit userspace writing 'security.evm' HMAC value commit 2fb1c9a4f2dbc2f0bd2431c7fa64d0b5483864e4 upstream. Calculating the 'security.evm' HMAC value requires access to the EVM encrypted key. Only the kernel should have access to it. This patch prevents userspace tools(eg. setfattr, cp --preserve=xattr) from setting/modifying the 'security.evm' HMAC value directly. Signed-off-by: Mimi Zohar Signed-off-by: Greg Kroah-Hartman --- security/integrity/evm/evm_main.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index cdbde1762189..b9b2bebeb350 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -275,12 +275,20 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name, * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * - * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that - * the current value is valid. + * Before allowing the 'security.evm' protected xattr to be updated, + * verify the existing value is valid. As only the kernel should have + * access to the EVM encrypted key needed to calculate the HMAC, prevent + * userspace from writing HMAC value. Writing 'security.evm' requires + * requires CAP_SYS_ADMIN privileges. */ int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { + const struct evm_ima_xattr_data *xattr_data = xattr_value; + + if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0) + && (xattr_data->type == EVM_XATTR_HMAC)) + return -EPERM; return evm_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); } From d806b7310e479239441cebdd3fdcdacdb4208db3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:25:48 -0700 Subject: [PATCH 05/53] netlink: Rename netlink_capable netlink_allowed [ Upstream commit 5187cd055b6e81fc6526109456f8b20623148d5f ] netlink_capable is a static internal function in af_netlink.c and we have better uses for the name netlink_capable. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/netlink/af_netlink.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c9c2a8441d32..3f1d67e7cf5b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1219,7 +1219,7 @@ retry: return err; } -static inline int netlink_capable(const struct socket *sock, unsigned int flag) +static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); @@ -1287,7 +1287,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, /* Only superuser is allowed to listen multicasts */ if (nladdr->nl_groups) { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -1349,7 +1349,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; /* Only superuser is allowed to send multicasts */ - if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + if (nladdr->nl_groups && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) @@ -1921,7 +1921,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -2072,7 +2072,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && - !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; } else { dst_portid = nlk->dst_portid; From f0efa2954c20ab833bf99acba0a0817f1deee9e0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:26:25 -0700 Subject: [PATCH 06/53] net: Move the permission check in sock_diag_put_filterinfo to packet_diag_dump [ Upstream commit a53b72c83a4216f2eb883ed45a0cbce014b8e62d ] The permission check in sock_diag_put_filterinfo is wrong, and it is so removed from it's sources it is not clear why it is wrong. Move the computation into packet_diag_dump and pass a bool of the result into sock_diag_filterinfo. This does not yet correct the capability check but instead simply moves it to make it clear what is going on. Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/sock_diag.h | 2 +- net/core/sock_diag.c | 4 ++-- net/packet/diag.c | 7 ++++++- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index 302ab805b0bb..46cca4c06848 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -23,7 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie); void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); -int sock_diag_put_filterinfo(struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); #endif diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 6a7fae228634..c38e7a2b5a8e 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct nlattr *attr; @@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct sock *sk, unsigned int len; int err = 0; - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } diff --git a/net/packet/diag.c b/net/packet/diag.c index ec8b6e8a80b1..01cd1ac44ff5 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -127,6 +127,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, + bool may_report_filterinfo, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { @@ -171,7 +172,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_FILTER) && - sock_diag_put_filterinfo(sk, skb, PACKET_DIAG_FILTER)) + sock_diag_put_filterinfo(may_report_filterinfo, sk, skb, + PACKET_DIAG_FILTER)) goto out_nlmsg_trim; return nlmsg_end(skb, nlh); @@ -187,9 +189,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct packet_diag_req *req; struct net *net; struct sock *sk; + bool may_report_filterinfo; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); + may_report_filterinfo = ns_capable(net->user_ns, CAP_NET_ADMIN); mutex_lock(&net->packet.sklist_lock); sk_for_each(sk, &net->packet.sklist) { @@ -199,6 +203,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (sk_diag_fill(sk, skb, req, + may_report_filterinfo, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, From c35b4e287f5ede32bae6db1aef1ae3e9174bb2ff Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:26:56 -0700 Subject: [PATCH 07/53] net: Add variants of capable for use on on sockets [ Upstream commit a3b299da869d6e78cf42ae0b1b41797bcb8c5e4b ] sk_net_capable - The common case, operations that are safe in a network namespace. sk_capable - Operations that are not known to be safe in a network namespace sk_ns_capable - The general case for special cases. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/sock.h | 5 +++++ net/core/sock.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) diff --git a/include/net/sock.h b/include/net/sock.h index 8f32b779bc83..72f710d2f75a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2248,6 +2248,11 @@ extern void sock_enable_timestamp(struct sock *sk, int flag); extern int sock_get_timestamp(struct sock *, struct timeval __user *); extern int sock_get_timestampns(struct sock *, struct timespec __user *); +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap); +bool sk_capable(const struct sock *sk, int cap); +bool sk_net_capable(const struct sock *sk, int cap); + /* * Enable debug/info messages */ diff --git a/net/core/sock.c b/net/core/sock.c index d743099250f4..af65d17517b8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,6 +142,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { From 738f378d77b04f685f2cd01aa4240d1bce5c9668 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:28:03 -0700 Subject: [PATCH 08/53] net: Add variants of capable for use on netlink messages [ Upstream commit aa4cf9452f469f16cea8c96283b641b4576d4a7b ] netlink_net_capable - The common case use, for operations that are safe on a network namespace netlink_capable - For operations that are only known to be safe for the global root netlink_ns_capable - The general case of capable used to handle special cases __netlink_ns_capable - Same as netlink_ns_capable except taking a netlink_skb_parms instead of the skbuff of a netlink message. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/netlink.h | 7 +++++ net/netlink/af_netlink.c | 65 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 6358da5eeee8..438b312aa050 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -144,4 +144,11 @@ static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, return __netlink_dump_start(ssk, skb, nlh, control); } +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *ns, int cap); +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *ns, int cap); +bool netlink_capable(const struct sk_buff *skb, int cap); +bool netlink_net_capable(const struct sk_buff *skb, int cap); + #endif /* __LINUX_NETLINK_H */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3f1d67e7cf5b..e846e3e361fa 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1219,6 +1219,71 @@ retry: return err; } +/** + * __netlink_ns_capable - General netlink message capability test + * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *user_ns, int cap) +{ + return sk_ns_capable(nsp->sk, user_ns, cap); +} +EXPORT_SYMBOL(__netlink_ns_capable); + +/** + * netlink_ns_capable - General netlink message capability test + * @skb: socket buffer holding a netlink command from userspace + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *user_ns, int cap) +{ + return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); +} +EXPORT_SYMBOL(netlink_ns_capable); + +/** + * netlink_capable - Netlink global message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in all user namespaces. + */ +bool netlink_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, &init_user_ns, cap); +} +EXPORT_SYMBOL(netlink_capable); + +/** + * netlink_net_capable - Netlink network namespace message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap over the network namespace of + * the socket we received the message from. + */ +bool netlink_net_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); +} +EXPORT_SYMBOL(netlink_net_capable); + static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || From 1141a455802884d3bcbcf6b30e1d65d09cf286e1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:29:27 -0700 Subject: [PATCH 09/53] net: Use netlink_ns_capable to verify the permisions of netlink messages [ Upstream commit 90f62cf30a78721641e08737bda787552428061e ] It is possible by passing a netlink socket to a more privileged executable and then to fool that executable into writing to the socket data that happens to be valid netlink message to do something that privileged executable did not intend to do. To keep this from happening replace bare capable and ns_capable calls with netlink_capable, netlink_net_calls and netlink_ns_capable calls. Which act the same as the previous calls except they verify that the opener of the socket had the desired permissions as well. Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- crypto/crypto_user.c | 2 +- drivers/connector/cn_proc.c | 2 +- drivers/scsi/scsi_netlink.c | 2 +- kernel/audit.c | 4 ++-- net/can/gw.c | 4 ++-- net/core/rtnetlink.c | 20 +++++++++++--------- net/dcb/dcbnl.c | 2 +- net/decnet/dn_dev.c | 4 ++-- net/decnet/dn_fib.c | 4 ++-- net/decnet/netfilter/dn_rtmsg.c | 2 +- net/netfilter/nfnetlink.c | 2 +- net/netlink/genetlink.c | 2 +- net/packet/diag.c | 2 +- net/phonet/pn_netlink.c | 8 ++++---- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 2 +- net/sched/sch_api.c | 6 +++--- net/tipc/netlink.c | 2 +- net/xfrm/xfrm_user.c | 2 +- 19 files changed, 38 insertions(+), 36 deletions(-) diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 1512e41cd93d..43665d0d0905 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -466,7 +466,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) type -= CRYPTO_MSG_BASE; link = &crypto_dispatch[type]; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 18c5b9b16645..3165811e2407 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -369,7 +369,7 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, return; /* Can only change if privileged. */ - if (!capable(CAP_NET_ADMIN)) { + if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) { err = EPERM; goto out; } diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c index fe30ea94ffe6..109802f776ed 100644 --- a/drivers/scsi/scsi_netlink.c +++ b/drivers/scsi/scsi_netlink.c @@ -77,7 +77,7 @@ scsi_nl_rcv_msg(struct sk_buff *skb) goto next_msg; } - if (!capable(CAP_SYS_ADMIN)) { + if (!netlink_capable(skb, CAP_SYS_ADMIN)) { err = -EPERM; goto next_msg; } diff --git a/kernel/audit.c b/kernel/audit.c index 6def25f1b351..a6c632757e57 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -593,13 +593,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: - if (!capable(CAP_AUDIT_CONTROL)) + if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: - if (!capable(CAP_AUDIT_WRITE)) + if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ diff --git a/net/can/gw.c b/net/can/gw.c index 3ee690e8c7d3..de25455b4e3e 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -784,7 +784,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) struct cgw_job *gwj; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) @@ -876,7 +876,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh) struct can_can_gw ccgw; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 87ec574ffac8..054ebbf73236 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1294,7 +1294,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1306,7 +1307,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { err = -EPERM; goto errout; } @@ -1560,7 +1561,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1678,7 +1679,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1687,7 +1689,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1789,12 +1791,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -2179,7 +2181,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2635,7 +2637,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 40d5829ed36a..1074ffb6d533 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1670,7 +1670,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; - if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN)) + if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 7d9197063ebb..b5e52100a89a 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -573,7 +573,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr __rcu **ifap; int err = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -617,7 +617,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr *ifa; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 57dc159245ec..d332aefb0846 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 2a7efe388344..f3dc69a41d63 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) return; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); /* Eventually we might send routing messages too */ diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 572d87dc116f..0a03662bfbef 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -147,7 +147,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) const struct nfnetlink_subsystem *ss; int type, err; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; /* All the messages must at least contain nfgenmsg */ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 393f17eea1a2..ade434b8abd8 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -592,7 +592,7 @@ static int genl_family_rcv_msg(struct genl_family *family, return -EOPNOTSUPP; if ((ops->flags & GENL_ADMIN_PERM) && - !capable(CAP_NET_ADMIN)) + !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlh->nlmsg_flags & NLM_F_DUMP) { diff --git a/net/packet/diag.c b/net/packet/diag.c index 01cd1ac44ff5..674b0a65df6c 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -193,7 +193,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); - may_report_filterinfo = ns_capable(net->user_ns, CAP_NET_ADMIN); + may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN); mutex_lock(&net->packet.sklist_lock); sk_for_each(sk, &net->packet.sklist) { diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index dc15f4300808..b64151ade6b3 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 pnaddr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); @@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 dst; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fd7072827a40..15d46b9166de 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -989,7 +989,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; - if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e118af90973..2ea40d1877a6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -138,7 +138,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n) int err; int tp_created = 0; - if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 51b968d3febb..2d2f07945c85 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1024,7 +1024,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *p = NULL; int err; - if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1091,7 +1091,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *q, *p; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: @@ -1431,7 +1431,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n) u32 qid; int err; - if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 8bcd4985d0fb..1e6081fb6078 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN); u16 cmd; - if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN))) + if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN))) cmd = TIPC_CMD_NOT_NET_ADMIN; else cmd = req_userhdr->cmd; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3f565e495ac6..7a70a5a5671a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2362,7 +2362,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || From 8ab02acdf274cbd6b10f7dd990f42c9b40469141 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 May 2014 11:04:00 -0700 Subject: [PATCH 10/53] netlink: Only check file credentials for implicit destinations [ Upstream commit 2d7a85f4b06e9c27ff629f07a524c48074f07f81 ] It was possible to get a setuid root or setcap executable to write to it's stdout or stderr (which has been set made a netlink socket) and inadvertently reconfigure the networking stack. To prevent this we check that both the creator of the socket and the currentl applications has permission to reconfigure the network stack. Unfortunately this breaks Zebra which always uses sendto/sendmsg and creates it's socket without any privileges. To keep Zebra working don't bother checking if the creator of the socket has privilege when a destination address is specified. Instead rely exclusively on the privileges of the sender of the socket. Note from Andy: This is exactly Eric's code except for some comment clarifications and formatting fixes. Neither I nor, I think, anyone else is thrilled with this approach, but I'm hesitant to wait on a better fix since 3.15 is almost here. Note to stable maintainers: This is a mess. An earlier series of patches in 3.15 fix a rather serious security issue (CVE-2014-0181), but they did so in a way that breaks Zebra. The offending series includes: commit aa4cf9452f469f16cea8c96283b641b4576d4a7b Author: Eric W. Biederman Date: Wed Apr 23 14:28:03 2014 -0700 net: Add variants of capable for use on netlink messages If a given kernel version is missing that series of fixes, it's probably worth backporting it and this patch. if that series is present, then this fix is critical if you care about Zebra. Cc: stable@vger.kernel.org Signed-off-by: "Eric W. Biederman" Signed-off-by: Andy Lutomirski Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/netlink.h | 7 ++++--- net/netlink/af_netlink.c | 7 ++++++- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 438b312aa050..9516dad45109 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -16,9 +16,10 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) } enum netlink_skb_flags { - NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ - NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ - NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ + NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ + NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ + NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */ }; struct netlink_skb_parms { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e846e3e361fa..be34adde692f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1232,7 +1232,9 @@ retry: bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { - return sk_ns_capable(nsp->sk, user_ns, cap); + return ((nsp->flags & NETLINK_SKB_DST) || + file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && + ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable); @@ -2118,6 +2120,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; int err; struct scm_cookie scm; + u32 netlink_skb_flags = 0; if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; @@ -2139,6 +2142,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; + netlink_skb_flags |= NETLINK_SKB_DST; } else { dst_portid = nlk->dst_portid; dst_group = nlk->dst_group; @@ -2168,6 +2172,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = siocb->scm->creds; + NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { From 83880480db7b0a59c6304f9b86ae2b7024741045 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Mon, 2 Jun 2014 18:25:02 +0200 Subject: [PATCH 11/53] netlink: rate-limit leftover bytes warning and print process name [ Upstream commit bfc5184b69cf9eeb286137640351c650c27f118a ] Any process is able to send netlink messages with leftover bytes. Make the warning rate-limited to prevent too much log spam. The warning is supposed to help find userspace bugs, so print the triggering command name to implicate the buggy program. [v2: Use pr_warn_ratelimited instead of printk_ratelimited.] Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- lib/nlattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/nlattr.c b/lib/nlattr.c index fc6754720ced..10ad042d01be 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -201,8 +201,8 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, } if (unlikely(rem > 0)) - printk(KERN_WARNING "netlink: %d bytes leftover after parsing " - "attributes.\n", rem); + pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", + rem, current->comm); err = 0; errout: From 57b1ec6058e6633724817c9d001330a9fea9d39c Mon Sep 17 00:00:00 2001 From: Tom Gundersen Date: Thu, 15 May 2014 23:21:30 +0200 Subject: [PATCH 12/53] net: tunnels - enable module autoloading [ Upstream commit f98f89a0104454f35a62d681683c844f6dbf4043 ] Enable the module alias hookup to allow tunnel modules to be autoloaded on demand. This is in line with how most other netdev kinds work, and will allow userspace to create tunnels without having CAP_SYS_MODULE. Signed-off-by: Tom Gundersen Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ipip.c | 1 + net/ipv6/ip6_tunnel.c | 1 + net/ipv6/sit.c | 1 + 3 files changed, 3 insertions(+) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index f5cc7b331511..562ed15318ac 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -483,4 +483,5 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 73d7f68da557..a0ecdf596f2f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -61,6 +61,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 620d326e8fdd..b91179344e74 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1654,4 +1654,5 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); From 25bc3126ccbe553b5cc293ca9c77d44bb40ff62d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 29 May 2014 08:45:14 -0700 Subject: [PATCH 13/53] net: fix inet_getid() and ipv6_select_ident() bugs [ Upstream commit 39c36094d78c39e038c1e499b2364e13bce36f54 ] I noticed we were sending wrong IPv4 ID in TCP flows when MTU discovery is disabled. Note how GSO/TSO packets do not have monotonically incrementing ID. 06:37:41.575531 IP (id 14227, proto: TCP (6), length: 4396) 06:37:41.575534 IP (id 14272, proto: TCP (6), length: 65212) 06:37:41.575544 IP (id 14312, proto: TCP (6), length: 57972) 06:37:41.575678 IP (id 14317, proto: TCP (6), length: 7292) 06:37:41.575683 IP (id 14361, proto: TCP (6), length: 63764) It appears I introduced this bug in linux-3.1. inet_getid() must return the old value of peer->ip_id_count, not the new one. Lets revert this part, and remove the prevention of a null identification field in IPv6 Fragment Extension Header, which is dubious and not even done properly. Fixes: 87c48fa3b463 ("ipv6: make fragment identifications less predictable") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/inetpeer.h | 9 +-------- net/ipv6/output_core.c | 11 +++-------- 2 files changed, 4 insertions(+), 16 deletions(-) diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 53f464d7cddc..6ca347a0717e 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -178,16 +178,9 @@ static inline void inet_peer_refcheck(const struct inet_peer *p) /* can be called with or without local BH being disabled */ static inline int inet_getid(struct inet_peer *p, int more) { - int old, new; more++; inet_peer_refcheck(p); - do { - old = atomic_read(&p->ip_id_count); - new = old + more; - if (!new) - new = 1; - } while (atomic_cmpxchg(&p->ip_id_count, old, new) != old); - return new; + return atomic_add_return(more, &p->ip_id_count) - more; } #endif /* _NET_INETPEER_H */ diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index c2e73e647e44..3d2c81a66d6a 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -9,7 +9,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) { static atomic_t ipv6_fragmentation_id; - int old, new; + int ident; #if IS_ENABLED(CONFIG_IPV6) if (rt && !(rt->dst.flags & DST_NOPEER)) { @@ -25,13 +25,8 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) } } #endif - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); + ident = atomic_inc_return(&ipv6_fragmentation_id); + fhdr->identification = htonl(ident); } EXPORT_SYMBOL(ipv6_select_ident); From 35f8524540ad82b1af784ebd7002753ffb8e953c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 29 May 2014 20:46:17 +0200 Subject: [PATCH 14/53] team: fix mtu setting [ Upstream commit 9d0d68faea6962d62dd501cd6e71ce5cc8ed262b ] Now it is not possible to set mtu to team device which has a port enslaved to it. The reason is that when team_change_mtu() calls dev_set_mtu() for port device, notificator for NETDEV_PRECHANGEMTU event is called and team_device_event() returns NOTIFY_BAD forbidding the change. So fix this by returning NOTIFY_DONE here in case team is changing mtu in team_change_mtu(). Introduced-by: 3d249d4c "net: introduce ethernet teaming device" Signed-off-by: Jiri Pirko Acked-by: Flavio Leitner Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/team/team.c | 7 ++++++- include/linux/if_team.h | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index fe3fd77821bf..12222290c802 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1542,6 +1542,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu) * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); + team->port_mtu_change_allowed = true; list_for_each_entry(port, &team->port_list, list) { err = dev_set_mtu(port->dev, new_mtu); if (err) { @@ -1550,6 +1551,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu) goto unwind; } } + team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); dev->mtu = new_mtu; @@ -1559,6 +1561,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu) unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) dev_set_mtu(port->dev, dev->mtu); + team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); return err; @@ -2678,7 +2681,9 @@ static int team_device_event(struct notifier_block *unused, break; case NETDEV_CHANGEMTU: /* Forbid to change mtu of underlaying device */ - return NOTIFY_BAD; + if (!port->team->port_mtu_change_allowed) + return NOTIFY_BAD; + break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 16fae6436d0e..25b8b15197b0 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -193,6 +193,7 @@ struct team { bool user_carrier_enabled; bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ + bool port_mtu_change_allowed; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; From a597a10af49eefe89cb319054d1c824476d6deec Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 30 May 2014 15:25:59 -0700 Subject: [PATCH 15/53] tcp: fix cwnd undo on DSACK in F-RTO [ Upstream commit 0cfa5c07d6d1d7f8e710fc671c5ba1ce85e09fa4 ] This bug is discovered by an recent F-RTO issue on tcpm list https://www.ietf.org/mail-archive/web/tcpm/current/msg08794.html The bug is that currently F-RTO does not use DSACK to undo cwnd in certain cases: upon receiving an ACK after the RTO retransmission in F-RTO, and the ACK has DSACK indicating the retransmission is spurious, the sender only calls tcp_try_undo_loss() if some never retransmisted data is sacked (FLAG_ORIG_DATA_SACKED). The correct behavior is to unconditionally call tcp_try_undo_loss so the DSACK information is used properly to undo the cwnd reduction. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e15d330919af..ba7d2b7ad9f9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2720,13 +2720,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) bool recovered = !before(tp->snd_una, tp->high_seq); if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ - if (flag & FLAG_ORIG_SACK_ACKED) { - /* Step 3.b. A timeout is spurious if not all data are - * lost, i.e., never-retransmitted data are (s)acked. - */ - tcp_try_undo_loss(sk, true); + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) return; - } + if (after(tp->snd_nxt, tp->high_seq) && (flag & FLAG_DATA_SACKED || is_dupack)) { tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ From 74f6232f454fdee002bb60cc9454330e35b34bfd Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 5 Jun 2014 22:47:44 -0700 Subject: [PATCH 16/53] net: filter: fix typo in sparc BPF JIT [ Upstream commit 569810d1e3278907264f5b115281fca3f0038d53 ] fix typo in sparc codegen for SKF_AD_IFINDEX and SKF_AD_HATYPE classic BPF extensions Fixes: 2809a2087cc4 ("net: filter: Just In Time compiler for sparc") Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- arch/sparc/net/bpf_jit_comp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index fd95862c65aa..e0dffa5abf54 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_) #define BNE (F2(0, 2) | CONDNE) #ifdef CONFIG_SPARC64 -#define BNE_PTR (F2(0, 1) | CONDNE | (2 << 20)) +#define BE_PTR (F2(0, 1) | CONDE | (2 << 20)) #else -#define BNE_PTR BNE +#define BE_PTR BNE #endif #define SETHI(K, REG) \ @@ -600,7 +600,7 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ANC_IFINDEX: emit_skb_loadptr(dev, r_A); emit_cmpi(r_A, 0); - emit_branch(BNE_PTR, cleanup_addr + 4); + emit_branch(BE_PTR, cleanup_addr + 4); emit_nop(); emit_load32(r_A, struct net_device, ifindex, r_A); break; @@ -613,7 +613,7 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ANC_HATYPE: emit_skb_loadptr(dev, r_A); emit_cmpi(r_A, 0); - emit_branch(BNE_PTR, cleanup_addr + 4); + emit_branch(BE_PTR, cleanup_addr + 4); emit_nop(); emit_load16(r_A, struct net_device, type, r_A); break; From 9cc0c780050dfbd1ca7e7206d9593ebe047e30f7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 6 Jun 2014 08:35:59 -0700 Subject: [PATCH 17/53] net: filter: fix sparc32 typo [ Upstream commit 588f5d629b3369aba88f52217d1c473a28fa7723 ] Fixes: 569810d1e327 ("net: filter: fix typo in sparc BPF JIT") Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- arch/sparc/net/bpf_jit_comp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index e0dffa5abf54..224fc0c71b8a 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -85,7 +85,7 @@ static void bpf_flush_icache(void *start_, void *end_) #ifdef CONFIG_SPARC64 #define BE_PTR (F2(0, 1) | CONDE | (2 << 20)) #else -#define BE_PTR BNE +#define BE_PTR BE #endif #define SETHI(K, REG) \ From 9deb5f0852ddb318511605433367fcb02a738dc2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 6 Jun 2014 17:27:59 +0200 Subject: [PATCH 18/53] net: qmi_wwan: add Olivetti Olicard modems MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit ba6de0f5304ccdc45ae260e7e0feb6e0ef2dd558 ] Lars writes: "I'm only 99% sure that the net interfaces are qmi interfaces, nothing to lose by adding them in my opinion." And I tend to agree based on the similarity with the two Olicard modems we already have here. Reported-by: Lars Melin Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/qmi_wwan.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 7be4860ccfd7..6fb0082b3308 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -739,7 +739,12 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ - {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ + {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */ + {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */ + {QMI_FIXED_INTF(0x0b3c, 0xc002, 4)}, /* Olivetti Olicard 140 */ + {QMI_FIXED_INTF(0x0b3c, 0xc004, 6)}, /* Olivetti Olicard 155 */ + {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ + {QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)}, /* Olivetti Olicard 160 */ {QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)}, /* Olivetti Olicard 500 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ From 6a827d8a67f750f3096e668657e16d479363d4b5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Jun 2014 06:44:03 -0700 Subject: [PATCH 19/53] net: force a list_del() in unregister_netdevice_many() [ Upstream commit 87757a917b0b3c0787e0563c679762152be81312 ] unregister_netdevice_many() API is error prone and we had too many bugs because of dangling LIST_HEAD on stacks. See commit f87e6f47933e3e ("net: dont leave active on stack LIST_HEAD") In fact, instead of making sure no caller leaves an active list_head, just force a list_del() in the callee. No one seems to need to access the list after unregister_netdevice_many() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/macvlan.c | 1 - net/core/dev.c | 5 ++++- net/core/rtnetlink.c | 1 - net/mac80211/iface.c | 1 - 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c12aeaee22fa..155ef4bbde91 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -961,7 +961,6 @@ static int macvlan_device_event(struct notifier_block *unused, list_for_each_entry_safe(vlan, next, &port->vlans, list) vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill); unregister_netdevice_many(&list_kill); - list_del(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ diff --git a/net/core/dev.c b/net/core/dev.c index 56383a3e5d71..cca7ae0ba915 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5827,6 +5827,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -5836,6 +5839,7 @@ void unregister_netdevice_many(struct list_head *head) rollback_registered_many(head); list_for_each_entry(dev, head, unreg_list) net_set_todo(dev); + list_del(head); } } EXPORT_SYMBOL(unregister_netdevice_many); @@ -6252,7 +6256,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); - list_del(&dev_kill_list); rtnl_unlock(); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 054ebbf73236..642151c003e4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1601,7 +1601,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) ops->dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); - list_del(&list_kill); return 0; } diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 514e90f470bf..2c64ab27b515 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1746,7 +1746,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } mutex_unlock(&local->iflist_mtx); unregister_netdevice_many(&unreg_list); - list_del(&unreg_list); list_for_each_entry_safe(sdata, tmp, &wdev_list, list) { list_del(&sdata->list); From c581207eda173d5cf3234a579424bbc117b63dd6 Mon Sep 17 00:00:00 2001 From: Dmitry Popov Date: Fri, 6 Jun 2014 23:19:21 +0400 Subject: [PATCH 20/53] ipip, sit: fix ipv4_{update_pmtu,redirect} calls [ Upstream commit 2346829e641b804ece9ac9298136b56d9567c278 ] ipv4_{update_pmtu,redirect} were called with tunnel's ifindex (t->dev is a tunnel netdevice). It caused wrong route lookup and failure of pmtu update or redirect. We should use the same ifindex that we use in ip_route_output_* in *tunnel_xmit code. It is t->parms.link . Signed-off-by: Dmitry Popov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ipip.c | 4 ++-- net/ipv6/sit.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 562ed15318ac..897b784e9c05 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPIP, 0); + t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b91179344e74..540d58921007 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -530,12 +530,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPV6, 0); + t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; From 9138f241fc79c4124b6ce46ff08a6ec8c07c5ed7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Jun 2014 06:43:01 -0700 Subject: [PATCH 21/53] ipv4: fix a race in ip4_datagram_release_cb() [ Upstream commit 9709674e68646cee5a24e3000b3558d25412203a ] Alexey gave a AddressSanitizer[1] report that finally gave a good hint at where was the origin of various problems already reported by Dormando in the past [2] Problem comes from the fact that UDP can have a lockless TX path, and concurrent threads can manipulate sk_dst_cache, while another thread, is holding socket lock and calls __sk_dst_set() in ip4_datagram_release_cb() (this was added in linux-3.8) It seems that all we need to do is to use sk_dst_check() and sk_dst_set() so that all the writers hold same spinlock (sk->sk_dst_lock) to prevent corruptions. TCP stack do not need this protection, as all sk_dst_cache writers hold the socket lock. [1] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel AddressSanitizer: heap-use-after-free in ipv4_dst_check Read of size 2 by thread T15453: [] ipv4_dst_check+0x1a/0x90 ./net/ipv4/route.c:1116 [] __sk_dst_check+0x89/0xe0 ./net/core/sock.c:531 [] ip4_datagram_release_cb+0x46/0x390 ??:0 [] release_sock+0x17a/0x230 ./net/core/sock.c:2413 [] ip4_datagram_connect+0x462/0x5d0 ??:0 [] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [] SyS_connect+0xe/0x10 ./net/socket.c:1682 [] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Freed by thread T15455: [] dst_destroy+0xa8/0x160 ./net/core/dst.c:251 [] dst_release+0x45/0x80 ./net/core/dst.c:280 [] ip4_datagram_connect+0xa1/0x5d0 ??:0 [] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [] SyS_connect+0xe/0x10 ./net/socket.c:1682 [] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Allocated by thread T15453: [] dst_alloc+0x81/0x2b0 ./net/core/dst.c:171 [] rt_dst_alloc+0x47/0x50 ./net/ipv4/route.c:1406 [< inlined >] __ip_route_output_key+0x3e8/0xf70 __mkroute_output ./net/ipv4/route.c:1939 [] __ip_route_output_key+0x3e8/0xf70 ./net/ipv4/route.c:2161 [] ip_route_output_flow+0x14/0x30 ./net/ipv4/route.c:2249 [] ip4_datagram_connect+0x317/0x5d0 ??:0 [] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [] SyS_connect+0xe/0x10 ./net/socket.c:1682 [] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 [2] <4>[196727.311203] general protection fault: 0000 [#1] SMP <4>[196727.311224] Modules linked in: xt_TEE xt_dscp xt_DSCP macvlan bridge coretemp crc32_pclmul ghash_clmulni_intel gpio_ich microcode ipmi_watchdog ipmi_devintf sb_edac edac_core lpc_ich mfd_core tpm_tis tpm tpm_bios ipmi_si ipmi_msghandler isci igb libsas i2c_algo_bit ixgbe ptp pps_core mdio <4>[196727.311333] CPU: 17 PID: 0 Comm: swapper/17 Not tainted 3.10.26 #1 <4>[196727.311344] Hardware name: Supermicro X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.0 07/05/2013 <4>[196727.311364] task: ffff885e6f069700 ti: ffff885e6f072000 task.ti: ffff885e6f072000 <4>[196727.311377] RIP: 0010:[] [] ipv4_dst_destroy+0x4f/0x80 <4>[196727.311399] RSP: 0018:ffff885effd23a70 EFLAGS: 00010282 <4>[196727.311409] RAX: dead000000200200 RBX: ffff8854c398ecc0 RCX: 0000000000000040 <4>[196727.311423] RDX: dead000000100100 RSI: dead000000100100 RDI: dead000000200200 <4>[196727.311437] RBP: ffff885effd23a80 R08: ffffffff815fd9e0 R09: ffff885d5a590800 <4>[196727.311451] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>[196727.311464] R13: ffffffff81c8c280 R14: 0000000000000000 R15: ffff880e85ee16ce <4>[196727.311510] FS: 0000000000000000(0000) GS:ffff885effd20000(0000) knlGS:0000000000000000 <4>[196727.311554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[196727.311581] CR2: 00007a46751eb000 CR3: 0000005e65688000 CR4: 00000000000407e0 <4>[196727.311625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>[196727.311669] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 <4>[196727.311713] Stack: <4>[196727.311733] ffff8854c398ecc0 ffff8854c398ecc0 ffff885effd23ab0 ffffffff815b7f42 <4>[196727.311784] ffff88be6595bc00 ffff8854c398ecc0 0000000000000000 ffff8854c398ecc0 <4>[196727.311834] ffff885effd23ad0 ffffffff815b86c6 ffff885d5a590800 ffff8816827821c0 <4>[196727.311885] Call Trace: <4>[196727.311907] <4>[196727.311912] [] dst_destroy+0x32/0xe0 <4>[196727.311959] [] dst_release+0x56/0x80 <4>[196727.311986] [] tcp_v4_do_rcv+0x2a5/0x4a0 <4>[196727.312013] [] tcp_v4_rcv+0x7da/0x820 <4>[196727.312041] [] ? ip_rcv_finish+0x360/0x360 <4>[196727.312070] [] ? nf_hook_slow+0x7d/0x150 <4>[196727.312097] [] ? ip_rcv_finish+0x360/0x360 <4>[196727.312125] [] ip_local_deliver_finish+0xb2/0x230 <4>[196727.312154] [] ip_local_deliver+0x4a/0x90 <4>[196727.312183] [] ip_rcv_finish+0x119/0x360 <4>[196727.312212] [] ip_rcv+0x22b/0x340 <4>[196727.312242] [] ? macvlan_broadcast+0x160/0x160 [macvlan] <4>[196727.312275] [] __netif_receive_skb_core+0x512/0x640 <4>[196727.312308] [] ? kmem_cache_alloc+0x13b/0x150 <4>[196727.312338] [] __netif_receive_skb+0x21/0x70 <4>[196727.312368] [] netif_receive_skb+0x31/0xa0 <4>[196727.312397] [] napi_gro_receive+0xe8/0x140 <4>[196727.312433] [] ixgbe_poll+0x551/0x11f0 [ixgbe] <4>[196727.312463] [] ? ip_rcv+0x22b/0x340 <4>[196727.312491] [] net_rx_action+0x111/0x210 <4>[196727.312521] [] ? __netif_receive_skb+0x21/0x70 <4>[196727.312552] [] __do_softirq+0xd0/0x270 <4>[196727.312583] [] call_softirq+0x1c/0x30 <4>[196727.312613] [] do_softirq+0x55/0x90 <4>[196727.312640] [] irq_exit+0x55/0x60 <4>[196727.312668] [] do_IRQ+0x63/0xe0 <4>[196727.312696] [] common_interrupt+0x6a/0x6a <4>[196727.312722] <1>[196727.313071] RIP [] ipv4_dst_destroy+0x4f/0x80 <4>[196727.313100] RSP <4>[196727.313377] ---[ end trace 64b3f14fae0f2e29 ]--- <0>[196727.380908] Kernel panic - not syncing: Fatal exception in interrupt Reported-by: Alexey Preobrazhensky Reported-by: dormando Signed-off-by: Eric Dumazet Fixes: 8141ed9fcedb2 ("ipv4: Add a socket release callback for datagram sockets") Cc: Steffen Klassert Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/datagram.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 19e36376d2a0..5f3dc1df04bf 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -86,18 +86,26 @@ out: } EXPORT_SYMBOL(ip4_datagram_connect); +/* Because UDP xmit path can manipulate sk_dst_cache without holding + * socket lock, we need to use sk_dst_set() here, + * even if we own the socket lock. + */ void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; + struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; - if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) - return; - rcu_read_lock(); + + dst = __sk_dst_get(sk); + if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { + rcu_read_unlock(); + return; + } inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; @@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk) inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); - if (!IS_ERR(rt)) - __sk_dst_set(sk, &rt->dst); + + dst = !IS_ERR(rt) ? &rt->dst : NULL; + sk_dst_set(sk, dst); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); From a6987bca8054bf0cf9e90a9b0d42486d7bc53d70 Mon Sep 17 00:00:00 2001 From: Xufeng Zhang Date: Thu, 12 Jun 2014 10:53:36 +0800 Subject: [PATCH 22/53] sctp: Fix sk_ack_backlog wrap-around problem [ Upstream commit d3217b15a19a4779c39b212358a5c71d725822ee ] Consider the scenario: For a TCP-style socket, while processing the COOKIE_ECHO chunk in sctp_sf_do_5_1D_ce(), after it has passed a series of sanity check, a new association would be created in sctp_unpack_cookie(), but afterwards, some processing maybe failed, and sctp_association_free() will be called to free the previously allocated association, in sctp_association_free(), sk_ack_backlog value is decremented for this socket, since the initial value for sk_ack_backlog is 0, after the decrement, it will be 65535, a wrap-around problem happens, and if we want to establish new associations afterward in the same socket, ABORT would be triggered since sctp deem the accept queue as full. Fix this issue by only decrementing sk_ack_backlog for associations in the endpoint's list. Fix-suggested-by: Neil Horman Signed-off-by: Xufeng Zhang Acked-by: Daniel Borkmann Acked-by: Vlad Yasevich Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sctp/associola.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 91cfd8f94a19..229b3c3fb6c9 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -387,7 +387,7 @@ void sctp_association_free(struct sctp_association *asoc) /* Only real associations count against the endpoint, so * don't bother for if this is a temporary association. */ - if (!asoc->temp) { + if (!list_empty(&asoc->asocs)) { list_del(&asoc->asocs); /* Decrement the backlog value for a TCP-style listening From fb0d10bff97d0016a8305d6102699a93afe5011a Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 28 May 2014 14:15:19 +0200 Subject: [PATCH 23/53] rtnetlink: fix userspace API breakage for iproute2 < v3.9.0 [ Upstream commit e5eca6d41f53db48edd8cf88a3f59d2c30227f8e ] When running RHEL6 userspace on a current upstream kernel, "ip link" fails to show VF information. The reason is a kernel<->userspace API change introduced by commit 88c5b5ce5cb57 ("rtnetlink: Call nlmsg_parse() with correct header length"), after which the kernel does not see iproute2's IFLA_EXT_MASK attribute in the netlink request. iproute2 adjusted for the API change in its commit 63338dca4513 ("libnetlink: Use ifinfomsg instead of rtgenmsg in rtnl_wilddump_req_filter"). The problem has been noticed before: http://marc.info/?l=linux-netdev&m=136692296022182&w=2 (Subject: Re: getting VF link info seems to be broken in 3.9-rc8) We can do better than tell those with old userspace to upgrade. We can recognize the old iproute2 in the kernel by checking the netlink message length. Even when including the IFLA_EXT_MASK attribute, its netlink message is shorter than struct ifinfomsg. With this patch "ip link" shows VF information in both old and new iproute2 versions. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/rtnetlink.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 642151c003e4..ae43dd807bb2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1044,6 +1044,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; int err; + int hdrlen; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1051,8 +1052,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + /* A hack to preserve kernel<->userspace interface. + * The correct header is ifinfomsg. It is consistent with rtnl_getlink. + * However, before Linux v3.9 the code here assumed rtgenmsg and that's + * what iproute2 < v3.9.0 used. + * We can detect the old iproute2. Even including the IFLA_EXT_MASK + * attribute, its netlink message is shorter than struct ifinfomsg. + */ + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -1907,9 +1917,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; + int hdrlen; - if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ + hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); } From 1d7716d95bc77b3fa128f1de50900d02b2c0f4d9 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 12 Jun 2014 11:53:10 -0700 Subject: [PATCH 24/53] vxlan: use dev->needed_headroom instead of dev->hard_header_len [ Upstream commit 2853af6a2ea1a8ed09b09dd4fb578e7f435e8d34 ] When we mirror packets from a vxlan tunnel to other device, the mirror device should see the same packets (that is, without outer header). Because vxlan tunnel sets dev->hard_header_len, tcf_mirred() resets mac header back to outer mac, the mirror device actually sees packets with outer headers Vxlan tunnel should set dev->needed_headroom instead of dev->hard_header_len, like what other ip tunnels do. This fixes the above problem. Cc: "David S. Miller" Cc: stephen hemminger Cc: Pravin B Shelar Signed-off-by: Cong Wang Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/vxlan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 9673edfff451..fcbd4eee52cc 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1314,7 +1314,7 @@ static void vxlan_setup(struct net_device *dev) eth_hw_addr_random(dev); ether_setup(dev); - dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM; + dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; dev->netdev_ops = &vxlan_netdev_ops; dev->destructor = vxlan_free; @@ -1454,7 +1454,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev, dev->mtu = lowerdev->mtu - VXLAN_HEADROOM; /* update header length based on lower device */ - dev->hard_header_len = lowerdev->hard_header_len + + dev->needed_headroom = lowerdev->hard_header_len + VXLAN_HEADROOM; } From f2f3e2713849a2f46c593737ed108349a5bcd9f9 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sun, 1 Jun 2014 15:24:59 +0800 Subject: [PATCH 25/53] net/mlx4_core: pass pci_device_id.driver_data to __mlx4_init_one during reset [ No upstream commit, this is a cherry picked backport enabler. ] The second parameter of __mlx4_init_one() is used to identify whether the pci_dev is a PF or VF. Currently, when it is invoked in mlx4_pci_slot_reset() this information is missed. This patch match the pci_dev with mlx4_pci_table and passes the pci_device_id.driver_data to __mlx4_init_one() in mlx4_pci_slot_reset(). Signed-off-by: Wei Yang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 1b195fc7f411..3f15ec82b0f3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2517,7 +2517,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) { - int ret = __mlx4_init_one(pdev, 0); + const struct pci_device_id *id; + int ret; + + id = pci_match_id(mlx4_pci_table, pdev); + ret = __mlx4_init_one(pdev, id->driver_data); return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } From 65df70793e5cce0b72f38172afa9ad32de92bf65 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sun, 1 Jun 2014 15:25:00 +0800 Subject: [PATCH 26/53] net/mlx4_core: Preserve pci_dev_data after __mlx4_remove_one() [ Upstream commit befdf8978accecac2e0739e6b5075afc62db37fe ] pci_match_id() just match the static pci_device_id, which may return NULL if someone binds the driver to a device manually using /sys/bus/pci/drivers/.../new_id. This patch wrap up a helper function __mlx4_remove_one() which does the tear down function but preserve the drv_data. Functions like mlx4_pci_err_detected() and mlx4_restart_one() will call this one with out releasing drvdata. Fixes: 97a5221 "net/mlx4_core: pass pci_device_id.driver_data to __mlx4_init_one during reset". CC: Bjorn Helgaas CC: Amir Vadai CC: Jack Morgenstein CC: Or Gerlitz Signed-off-by: Wei Yang Acked-by: Jack Morgenstein Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/mellanox/mlx4/main.c | 186 ++++++++++++---------- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 1 + 2 files changed, 104 insertions(+), 83 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 3f15ec82b0f3..3fb2643d05b4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2129,13 +2129,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) /* Allow large DMA segments, up to the firmware limit of 1 GB */ dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - err = -ENOMEM; - goto err_release_regions; - } - - dev = &priv->dev; + dev = pci_get_drvdata(pdev); + priv = mlx4_priv(dev); dev->pdev = pdev; INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); @@ -2300,8 +2295,7 @@ slave_start: mlx4_sense_init(dev); mlx4_start_sense(dev); - priv->pci_dev_data = pci_dev_data; - pci_set_drvdata(pdev, dev); + priv->removed = 0; return 0; @@ -2367,84 +2361,110 @@ err_disable_pdev: static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { + struct mlx4_priv *priv; + struct mlx4_dev *dev; + printk_once(KERN_INFO "%s", mlx4_version); + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + dev = &priv->dev; + pci_set_drvdata(pdev, dev); + priv->pci_dev_data = id->driver_data; + return __mlx4_init_one(pdev, id->driver_data); } +static void __mlx4_remove_one(struct pci_dev *pdev) +{ + struct mlx4_dev *dev = pci_get_drvdata(pdev); + struct mlx4_priv *priv = mlx4_priv(dev); + int pci_dev_data; + int p; + + if (priv->removed) + return; + + pci_dev_data = priv->pci_dev_data; + + /* in SRIOV it is not allowed to unload the pf's + * driver while there are alive vf's */ + if (mlx4_is_master(dev)) { + if (mlx4_how_many_lives_vf(dev)) + printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n"); + } + mlx4_stop_sense(dev); + mlx4_unregister_device(dev); + + for (p = 1; p <= dev->caps.num_ports; p++) { + mlx4_cleanup_port_info(&priv->port[p]); + mlx4_CLOSE_PORT(dev, p); + } + + if (mlx4_is_master(dev)) + mlx4_free_resource_tracker(dev, + RES_TR_FREE_SLAVES_ONLY); + + mlx4_cleanup_counters_table(dev); + mlx4_cleanup_qp_table(dev); + mlx4_cleanup_srq_table(dev); + mlx4_cleanup_cq_table(dev); + mlx4_cmd_use_polling(dev); + mlx4_cleanup_eq_table(dev); + mlx4_cleanup_mcg_table(dev); + mlx4_cleanup_mr_table(dev); + mlx4_cleanup_xrcd_table(dev); + mlx4_cleanup_pd_table(dev); + + if (mlx4_is_master(dev)) + mlx4_free_resource_tracker(dev, + RES_TR_FREE_STRUCTS_ONLY); + + iounmap(priv->kar); + mlx4_uar_free(dev, &priv->driver_uar); + mlx4_cleanup_uar_table(dev); + if (!mlx4_is_slave(dev)) + mlx4_clear_steering(dev); + mlx4_free_eq_table(dev); + if (mlx4_is_master(dev)) + mlx4_multi_func_cleanup(dev); + mlx4_close_hca(dev); + if (mlx4_is_slave(dev)) + mlx4_multi_func_cleanup(dev); + mlx4_cmd_cleanup(dev); + + if (dev->flags & MLX4_FLAG_MSI_X) + pci_disable_msix(pdev); + if (dev->flags & MLX4_FLAG_SRIOV) { + mlx4_warn(dev, "Disabling SR-IOV\n"); + pci_disable_sriov(pdev); + } + + if (!mlx4_is_slave(dev)) + mlx4_free_ownership(dev); + + kfree(dev->caps.qp0_tunnel); + kfree(dev->caps.qp0_proxy); + kfree(dev->caps.qp1_tunnel); + kfree(dev->caps.qp1_proxy); + + pci_release_regions(pdev); + pci_disable_device(pdev); + memset(priv, 0, sizeof(*priv)); + priv->pci_dev_data = pci_dev_data; + priv->removed = 1; +} + static void mlx4_remove_one(struct pci_dev *pdev) { struct mlx4_dev *dev = pci_get_drvdata(pdev); struct mlx4_priv *priv = mlx4_priv(dev); - int p; - if (dev) { - /* in SRIOV it is not allowed to unload the pf's - * driver while there are alive vf's */ - if (mlx4_is_master(dev)) { - if (mlx4_how_many_lives_vf(dev)) - printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n"); - } - mlx4_stop_sense(dev); - mlx4_unregister_device(dev); - - for (p = 1; p <= dev->caps.num_ports; p++) { - mlx4_cleanup_port_info(&priv->port[p]); - mlx4_CLOSE_PORT(dev, p); - } - - if (mlx4_is_master(dev)) - mlx4_free_resource_tracker(dev, - RES_TR_FREE_SLAVES_ONLY); - - mlx4_cleanup_counters_table(dev); - mlx4_cleanup_mcg_table(dev); - mlx4_cleanup_qp_table(dev); - mlx4_cleanup_srq_table(dev); - mlx4_cleanup_cq_table(dev); - mlx4_cmd_use_polling(dev); - mlx4_cleanup_eq_table(dev); - mlx4_cleanup_mr_table(dev); - mlx4_cleanup_xrcd_table(dev); - mlx4_cleanup_pd_table(dev); - - if (mlx4_is_master(dev)) - mlx4_free_resource_tracker(dev, - RES_TR_FREE_STRUCTS_ONLY); - - iounmap(priv->kar); - mlx4_uar_free(dev, &priv->driver_uar); - mlx4_cleanup_uar_table(dev); - if (!mlx4_is_slave(dev)) - mlx4_clear_steering(dev); - mlx4_free_eq_table(dev); - if (mlx4_is_master(dev)) - mlx4_multi_func_cleanup(dev); - mlx4_close_hca(dev); - if (mlx4_is_slave(dev)) - mlx4_multi_func_cleanup(dev); - mlx4_cmd_cleanup(dev); - - if (dev->flags & MLX4_FLAG_MSI_X) - pci_disable_msix(pdev); - if (dev->flags & MLX4_FLAG_SRIOV) { - mlx4_warn(dev, "Disabling SR-IOV\n"); - pci_disable_sriov(pdev); - } - - if (!mlx4_is_slave(dev)) - mlx4_free_ownership(dev); - - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); - - kfree(priv); - pci_release_regions(pdev); - pci_disable_device(pdev); - pci_set_drvdata(pdev, NULL); - } + __mlx4_remove_one(pdev); + kfree(priv); + pci_set_drvdata(pdev, NULL); } int mlx4_restart_one(struct pci_dev *pdev) @@ -2454,7 +2474,7 @@ int mlx4_restart_one(struct pci_dev *pdev) int pci_dev_data; pci_dev_data = priv->pci_dev_data; - mlx4_remove_one(pdev); + __mlx4_remove_one(pdev); return __mlx4_init_one(pdev, pci_dev_data); } @@ -2509,7 +2529,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table); static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t state) { - mlx4_remove_one(pdev); + __mlx4_remove_one(pdev); return state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; @@ -2517,11 +2537,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) { - const struct pci_device_id *id; - int ret; + struct mlx4_dev *dev = pci_get_drvdata(pdev); + struct mlx4_priv *priv = mlx4_priv(dev); + int ret; - id = pci_match_id(mlx4_pci_table, pdev); - ret = __mlx4_init_one(pdev, id->driver_data); + ret = __mlx4_init_one(pdev, priv->pci_dev_data); return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index df15bb6631cc..da4f0002fd27 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -743,6 +743,7 @@ struct mlx4_priv { spinlock_t ctx_lock; int pci_dev_data; + int removed; struct list_head pgdir_list; struct mutex pgdir_mutex; From 78d2f0ceb0665162059a6f40d1aa8e8ed999936d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 14 May 2014 17:40:58 +0200 Subject: [PATCH 27/53] KVM: lapic: sync highest ISR to hardware apic on EOI commit fc57ac2c9ca8109ea97fcc594f4be436944230cc upstream. When Hyper-V enlightenments are in effect, Windows prefers to issue an Hyper-V MSR write to issue an EOI rather than an x2apic MSR write. The Hyper-V MSR write is not handled by the processor, and besides being slower, this also causes bugs with APIC virtualization. The reason is that on EOI the processor will modify the highest in-service interrupt (SVI) field of the VMCS, as explained in section 29.1.4 of the SDM; every other step in EOI virtualization is already done by apic_send_eoi or on VM entry, but this one is missing. We need to do the same, and be careful not to muck with the isr_count and highest_isr_cache fields that are unused when virtual interrupt delivery is enabled. Reviewed-by: Yang Zhang Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/lapic.c | 62 ++++++++++++++++++++++++++++++-------------- 1 file changed, 43 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 61d9fed5eb31..279d093524b4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -370,6 +370,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { + /* Note that we never get here with APIC virtualization enabled. */ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -381,12 +383,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) apic->highest_isr_cache = vec; } +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + + /* + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. + */ + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; +} + static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * We do get here for APIC virtualization enabled if the guest + * uses the Hyper-V APIC enlightenment. In this case we may need + * to trigger a new interrupt delivery by writing the SVI field; + * on the other hand isr_count and highest_isr_cache are unused + * and must be left alone. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); + else { --apic->isr_count; - BUG_ON(apic->isr_count < 0); - apic->highest_isr_cache = -1; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; + } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) @@ -466,22 +504,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - /* Note that isr_count is always 1 with vid enabled */ - if (!apic->isr_count) - return -1; - if (likely(apic->highest_isr_cache != -1)) - return apic->highest_isr_cache; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1619,6 +1641,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + /* Note that we never get here with APIC virtualization enabled. */ + if (vector == -1) return -1; From 2f05032467bb850e794f6ec0fd3f3497a168f356 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Fri, 6 Jun 2014 14:36:11 -0700 Subject: [PATCH 28/53] ARM: at91: fix at91_sysirq_mask_rtc for sam9x5 SoCs commit 9dcc87fec8947308e0111c65dcd881e6aa5b1673 upstream. sam9x5 SoCs have the following errata: "RTC: Interrupt Mask Register cannot be used Interrupt Mask Register read always returns 0." Hence we should not rely on what IMR claims about already masked IRQs and just disable all IRQs. Signed-off-by: Boris BREZILLON Reported-by: Bryan Evenson Reviewed-by: Johan Hovold Acked-by: Nicolas Ferre Cc: Bryan Evenson Cc: Andrew Victor Cc: Jean-Christophe Plagniol-Villard Cc: Alessandro Zummo Cc: Mark Roszko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-at91/sysirq_mask.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c index 2ba694f9626b..f8bc3511a8c8 100644 --- a/arch/arm/mach-at91/sysirq_mask.c +++ b/arch/arm/mach-at91/sysirq_mask.c @@ -25,24 +25,28 @@ #include "generic.h" -#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ -#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ +#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */ +#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */ +#define AT91_RTC_IRQ_MASK 0x1f /* Available IRQs mask */ void __init at91_sysirq_mask_rtc(u32 rtc_base) { void __iomem *base; - u32 mask; base = ioremap(rtc_base, 64); if (!base) return; - mask = readl_relaxed(base + AT91_RTC_IMR); - if (mask) { - pr_info("AT91: Disabling rtc irq\n"); - writel_relaxed(mask, base + AT91_RTC_IDR); - (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ - } + /* + * sam9x5 SoCs have the following errata: + * "RTC: Interrupt Mask Register cannot be used + * Interrupt Mask Register read always returns 0." + * + * Hence we're not relying on IMR values to disable + * interrupts. + */ + writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR); + (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */ iounmap(base); } From 06c757b88417d8abd71de7c37426812534226b04 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Thu, 29 May 2014 10:16:23 +0100 Subject: [PATCH 29/53] MIPS: KVM: Allocate at least 16KB for exception handlers commit 7006e2dfda9adfa40251093604db76d7e44263b3 upstream. Each MIPS KVM guest has its own copy of the KVM exception vector. This contains the TLB refill exception handler at offset 0x000, the general exception handler at offset 0x180, and interrupt exception handlers at offset 0x200 in case Cause_IV=1. A common handler is copied to offset 0x2000 and offset 0x3000 is used for temporarily storing k1 during entry from guest. However the amount of memory allocated for this purpose is calculated as 0x200 rounded up to the next page boundary, which is insufficient if 4KB pages are in use. This can lead to the common handler at offset 0x2000 being overwritten and infinitely recursive exceptions on the next exit from the guest. Increase the minimum size from 0x200 to 0x4000 to cover the full use of the page. Signed-off-by: James Hogan Cc: Paolo Bonzini Cc: Gleb Natapov Cc: kvm@vger.kernel.org Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: Sanjay Lal Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/mips/kvm/kvm_mips.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index dd203e59e6fd..426345ac6f6e 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -299,7 +299,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (cpu_has_veic || cpu_has_vint) { size = 0x200 + VECTORSPACING * 64; } else { - size = 0x200; + size = 0x4000; } /* Save Linux EBASE */ From c5ece48205da2cfe6b5fbfb82d305283c05299f1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:36 +0200 Subject: [PATCH 30/53] USB: cdc-acm: fix write and suspend race commit 5a345c20c17d87099224a4be12e69e5bd7023dca upstream. Fix race between write() and suspend() which could lead to writes being dropped (or I/O while suspended) if the device is runtime suspended while a write request is being processed. Specifically, suspend() releases the write_lock after determining the device is idle but before incrementing the susp_count, thus leaving a window where a concurrent write() can submit an urb. Fixes: 11ea859d64b6 ("USB: additional power savings for cdc-acm devices that support remote wakeup") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 89cce1a32059..a456d88aa170 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1434,18 +1434,15 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) struct acm *acm = usb_get_intfdata(intf); int cnt; - if (PMSG_IS_AUTO(message)) { - int b; - - spin_lock_irq(&acm->write_lock); - b = acm->transmitting; - spin_unlock_irq(&acm->write_lock); - if (b) - return -EBUSY; - } - spin_lock_irq(&acm->read_lock); spin_lock(&acm->write_lock); + if (PMSG_IS_AUTO(message)) { + if (acm->transmitting) { + spin_unlock(&acm->write_lock); + spin_unlock_irq(&acm->read_lock); + return -EBUSY; + } + } cnt = acm->susp_count++; spin_unlock(&acm->write_lock); spin_unlock_irq(&acm->read_lock); From 1b3fe0068c8d5efd5d81ce6f5616d9cec1921e3a Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:37 +0200 Subject: [PATCH 31/53] USB: cdc-acm: fix write and resume race commit e144ed28bed10684f9aaec6325ed974d53f76110 upstream. Fix race between write() and resume() due to improper locking that could lead to writes being reordered. Resume must be done atomically and susp_count be protected by the write_lock in order to prevent racing with write(). This could otherwise lead to writes being reordered if write() grabs the write_lock after susp_count is decremented, but before the delayed urb is submitted. Fixes: 11ea859d64b6 ("USB: additional power savings for cdc-acm devices that support remote wakeup") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index a456d88aa170..751e6ad153ba 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1461,27 +1461,20 @@ static int acm_resume(struct usb_interface *intf) struct acm *acm = usb_get_intfdata(intf); struct acm_wb *wb; int rv = 0; - int cnt; spin_lock_irq(&acm->read_lock); - acm->susp_count -= 1; - cnt = acm->susp_count; - spin_unlock_irq(&acm->read_lock); + spin_lock(&acm->write_lock); - if (cnt) - return 0; + if (--acm->susp_count) + goto out; if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) { - rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO); + rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC); - spin_lock_irq(&acm->write_lock); if (acm->delayed_wb) { wb = acm->delayed_wb; acm->delayed_wb = NULL; - spin_unlock_irq(&acm->write_lock); acm_start_wb(acm, wb); - } else { - spin_unlock_irq(&acm->write_lock); } /* @@ -1489,12 +1482,14 @@ static int acm_resume(struct usb_interface *intf) * do the write path at all cost */ if (rv < 0) - goto err_out; + goto out; - rv = acm_submit_read_urbs(acm, GFP_NOIO); + rv = acm_submit_read_urbs(acm, GFP_ATOMIC); } +out: + spin_unlock(&acm->write_lock); + spin_unlock_irq(&acm->read_lock); -err_out: return rv; } From 67e8477bd13b64ab4805dbd639f13192b49034ba Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:38 +0200 Subject: [PATCH 32/53] USB: cdc-acm: fix broken runtime suspend commit 140cb81ac8c625942a1d695875932c615767a526 upstream. The current ACM runtime-suspend implementation is broken in several ways: Firstly, it buffers only the first write request being made while suspended -- any further writes are silently dropped. Secondly, writes being dropped also leak write urbs, which are never reclaimed (until the device is unbound). Thirdly, even the single buffered write is not cleared at shutdown (which may happen before the device is resumed), something which can lead to another urb leak as well as a PM usage-counter leak. Fix this by implementing a delayed-write queue using urb anchors and making sure to discard the queue properly at shutdown. Fixes: 11ea859d64b6 ("USB: additional power savings for cdc-acm devices that support remote wakeup") Reported-by: Xiao Jin Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 32 ++++++++++++++++++++++---------- drivers/usb/class/cdc-acm.h | 2 +- 2 files changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 751e6ad153ba..b3307172e061 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -233,12 +233,9 @@ static int acm_write_start(struct acm *acm, int wbn) acm->susp_count); usb_autopm_get_interface_async(acm->control); if (acm->susp_count) { - if (!acm->delayed_wb) - acm->delayed_wb = wb; - else - usb_autopm_put_interface_async(acm->control); + usb_anchor_urb(wb->urb, &acm->delayed); spin_unlock_irqrestore(&acm->write_lock, flags); - return 0; /* A white lie */ + return 0; } usb_mark_last_busy(acm->dev); @@ -591,6 +588,8 @@ static void acm_port_destruct(struct tty_port *port) static void acm_port_shutdown(struct tty_port *port) { struct acm *acm = container_of(port, struct acm, port); + struct urb *urb; + struct acm_wb *wb; int i; dev_dbg(&acm->control->dev, "%s\n", __func__); @@ -599,6 +598,16 @@ static void acm_port_shutdown(struct tty_port *port) if (!acm->disconnected) { usb_autopm_get_interface(acm->control); acm_set_control(acm, acm->ctrlout = 0); + + for (;;) { + urb = usb_get_from_anchor(&acm->delayed); + if (!urb) + break; + wb = urb->context; + wb->use = 0; + usb_autopm_put_interface_async(acm->control); + } + usb_kill_urb(acm->ctrlurb); for (i = 0; i < ACM_NW; i++) usb_kill_urb(acm->wb[i].urb); @@ -1190,6 +1199,7 @@ made_compressed_probe: acm->bInterval = epread->bInterval; tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; + init_usb_anchor(&acm->delayed); buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma); if (!buf) { @@ -1459,7 +1469,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) static int acm_resume(struct usb_interface *intf) { struct acm *acm = usb_get_intfdata(intf); - struct acm_wb *wb; + struct urb *urb; int rv = 0; spin_lock_irq(&acm->read_lock); @@ -1471,10 +1481,12 @@ static int acm_resume(struct usb_interface *intf) if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) { rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC); - if (acm->delayed_wb) { - wb = acm->delayed_wb; - acm->delayed_wb = NULL; - acm_start_wb(acm, wb); + for (;;) { + urb = usb_get_from_anchor(&acm->delayed); + if (!urb) + break; + + acm_start_wb(acm, urb->context); } /* diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 0f76e4af600e..1683ac161cf6 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -117,7 +117,7 @@ struct acm { unsigned int throttled:1; /* actually throttled */ unsigned int throttle_req:1; /* throttle requested */ u8 bInterval; - struct acm_wb *delayed_wb; /* write queued for a device about to be woken */ + struct usb_anchor delayed; /* writes queued for a device about to be woken */ }; #define CDC_DATA_INTERFACE_TYPE 0x0a From 60c64b0c78420677a41bc25e6bd2373219b100c3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:39 +0200 Subject: [PATCH 33/53] USB: cdc-acm: fix runtime PM for control messages commit bae3f4c53585e9a170da9436e0f06919874bda9a upstream. Fix runtime PM handling of control messages by adding the required PM counter operations. Fixes: 11ea859d64b6 ("USB: additional power savings for cdc-acm devices that support remote wakeup") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index b3307172e061..8128b503a56e 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -122,13 +122,23 @@ static void acm_release_minor(struct acm *acm) static int acm_ctrl_msg(struct acm *acm, int request, int value, void *buf, int len) { - int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0), + int retval; + + retval = usb_autopm_get_interface(acm->control); + if (retval) + return retval; + + retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0), request, USB_RT_ACM, value, acm->control->altsetting[0].desc.bInterfaceNumber, buf, len, 5000); + dev_dbg(&acm->control->dev, "%s - rq 0x%02x, val %#x, len %#x, result %d\n", __func__, request, value, len, retval); + + usb_autopm_put_interface(acm->control); + return retval < 0 ? retval : 0; } From 52c84b338b8b42539b1e1a9be0ffaf41e730ccc2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:40 +0200 Subject: [PATCH 34/53] USB: cdc-acm: fix shutdown and suspend race commit ed797074031a37bb9bf4a70952fffc606b77274d upstream. We should stop I/O unconditionally at suspend rather than rely on the tty-port initialised flag (which is set prior to stopping I/O during shutdown) in order to prevent suspend returning with URBs still active. Fixes: 11ea859d64b6 ("USB: additional power savings for cdc-acm devices that support remote wakeup") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 8128b503a56e..89eb04c27d41 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1470,8 +1470,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) if (cnt) return 0; - if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) - stop_data_traffic(acm); + stop_data_traffic(acm); return 0; } From 39166123076c8944938ee9261cf3f23f5905392f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:44 +0200 Subject: [PATCH 35/53] USB: cdc-acm: fix I/O after failed open commit e4c36076c2a6195ec62c35b03c3fde84d0087dc8 upstream. Make sure to kill any already submitted read urbs on read-urb submission failures in open in order to prevent doing I/O for a closed port. Fixes: 088c64f81284 ("USB: cdc-acm: re-write read processing") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 89eb04c27d41..a9977008a509 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -523,6 +523,7 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) { struct acm *acm = container_of(port, struct acm, port); int retval = -ENODEV; + int i; dev_dbg(&acm->control->dev, "%s\n", __func__); @@ -571,6 +572,8 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) return 0; error_submit_read_urbs: + for (i = 0; i < acm->rx_buflimit; i++) + usb_kill_urb(acm->read_urbs[i]); acm->ctrlout = 0; acm_set_control(acm, acm->ctrlout); error_set_control: From 4421a014e97c6669db6eb8600ce83d29e5484842 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 26 May 2014 19:23:45 +0200 Subject: [PATCH 36/53] USB: cdc-acm: fix runtime PM imbalance at shutdown commit 5292afa657d0e790b7479ad8eef9450c1e040b3d upstream. Make sure only to decrement the PM counters if they were actually incremented. Note that the USB PM counter, but not necessarily the driver core PM counter, is reset when the interface is unbound. Fixes: 11ea859d64b6 ("USB: additional power savings for cdc-acm devices that support remote wakeup") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index a9977008a509..fbf3f11aed2c 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -604,12 +604,13 @@ static void acm_port_shutdown(struct tty_port *port) struct urb *urb; struct acm_wb *wb; int i; + int pm_err; dev_dbg(&acm->control->dev, "%s\n", __func__); mutex_lock(&acm->mutex); if (!acm->disconnected) { - usb_autopm_get_interface(acm->control); + pm_err = usb_autopm_get_interface(acm->control); acm_set_control(acm, acm->ctrlout = 0); for (;;) { @@ -627,7 +628,8 @@ static void acm_port_shutdown(struct tty_port *port) for (i = 0; i < acm->rx_buflimit; i++) usb_kill_urb(acm->read_urbs[i]); acm->control->needs_remote_wakeup = 0; - usb_autopm_put_interface(acm->control); + if (!pm_err) + usb_autopm_put_interface(acm->control); } mutex_unlock(&acm->mutex); } From 72d1e4f6c1530d2c9c8e0d82b2c2e2ab9bf7034a Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Wed, 23 Apr 2014 13:53:39 -0700 Subject: [PATCH 37/53] Drivers: hv: balloon: Ensure pressure reports are posted regularly commit ae339336dc950b9b05e7ccd3565dd3e8781c06d9 upstream. The current code posts periodic memory pressure status from a dedicated thread. Under some conditions, especially when we are releasing a lot of memory into the guest, we may not send timely pressure reports back to the host. Fix this issue by reporting pressure in all contexts that can be active in this driver. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/hv_balloon.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index deb5c25305af..694173f662d1 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -19,6 +19,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -459,6 +460,11 @@ static bool do_hot_add; */ static uint pressure_report_delay = 45; +/* + * The last time we posted a pressure report to host. + */ +static unsigned long last_post_time; + module_param(hot_add, bool, (S_IRUGO | S_IWUSR)); MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add"); @@ -542,6 +548,7 @@ struct hv_dynmem_device { static struct hv_dynmem_device dm_device; +static void post_status(struct hv_dynmem_device *dm); #ifdef CONFIG_MEMORY_HOTPLUG static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size) @@ -612,7 +619,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * have not been "onlined" within the allowed time. */ wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ); - + post_status(&dm_device); } return; @@ -951,11 +958,17 @@ static void post_status(struct hv_dynmem_device *dm) { struct dm_status status; struct sysinfo val; + unsigned long now = jiffies; + unsigned long last_post = last_post_time; if (pressure_report_delay > 0) { --pressure_report_delay; return; } + + if (!time_after(now, (last_post_time + HZ))) + return; + si_meminfo(&val); memset(&status, 0, sizeof(struct dm_status)); status.hdr.type = DM_STATUS_REPORT; @@ -983,6 +996,14 @@ static void post_status(struct hv_dynmem_device *dm) if (status.hdr.trans_id != atomic_read(&trans_id)) return; + /* + * If the last post time that we sampled has changed, + * we have raced, don't post the status. + */ + if (last_post != last_post_time) + return; + + last_post_time = jiffies; vmbus_sendpacket(dm->dev->channel, &status, sizeof(struct dm_status), (unsigned long)NULL, @@ -1117,7 +1138,7 @@ static void balloon_up(struct work_struct *dummy) if (ret == -EAGAIN) msleep(20); - + post_status(&dm_device); } while (ret == -EAGAIN); if (ret) { @@ -1144,8 +1165,10 @@ static void balloon_down(struct hv_dynmem_device *dm, struct dm_unballoon_response resp; int i; - for (i = 0; i < range_count; i++) + for (i = 0; i < range_count; i++) { free_balloon_pages(dm, &range_array[i]); + post_status(&dm_device); + } if (req->more_pages == 1) return; From 7f8954f5340870cc7b0040da2103f1fcbf730050 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Fri, 16 May 2014 16:55:20 +0300 Subject: [PATCH 38/53] ASoC: max98090: Fix reset at resume time commit 25b4ab430f8e166c9b63f4db28e7e812d5a59396 upstream. Reset needs to wait 20ms before other codec IO is performed. This wait was not being performed. Fix this by making sure the reset register is not restored with the cache, but use the manual reset method in resume with the wait. Signed-off-by: Liam Girdwood Signed-off-by: Jarkko Nikula Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/max98090.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 4fdcc1cefc25..9b7746c9546f 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -255,6 +255,7 @@ static struct reg_default max98090_reg[] = { static bool max98090_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { + case M98090_REG_SOFTWARE_RESET: case M98090_REG_DEVICE_STATUS: case M98090_REG_JACK_STATUS: case M98090_REG_REVISION_ID: @@ -2343,6 +2344,8 @@ static int max98090_runtime_resume(struct device *dev) regcache_cache_only(max98090->regmap, false); + max98090_reset(max98090); + regcache_sync(max98090->regmap); return 0; From 62d09fc9cb4b7183f1dd1c691de3213fccda4cfc Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sat, 24 May 2014 12:52:10 +0100 Subject: [PATCH 39/53] iio:adc:max1363 incorrect resolutions for max11604, max11605, max11610 and max11611. commit a91a73c8b39a6b8bcc53fafa5372c65387c81233 upstream. Reported-by: Erik Habbinga Signed-off-by: Jonathan Cameron Acked-by: Hartmut Knaack Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/max1363.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index 9e6da72ad823..b2b5dcbf7122 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -1214,8 +1214,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1038_channels, + .num_channels = ARRAY_SIZE(max1038_channels), }, [max11605] = { .bits = 8, @@ -1224,8 +1224,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1038_channels, + .num_channels = ARRAY_SIZE(max1038_channels), }, [max11606] = { .bits = 10, @@ -1274,8 +1274,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1138_channels, + .num_channels = ARRAY_SIZE(max1138_channels), }, [max11611] = { .bits = 10, @@ -1284,8 +1284,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = { .num_modes = ARRAY_SIZE(max1238_mode_list), .default_mode = s0to11, .info = &max1238_info, - .channels = max1238_channels, - .num_channels = ARRAY_SIZE(max1238_channels), + .channels = max1138_channels, + .num_channels = ARRAY_SIZE(max1138_channels), }, [max11612] = { .bits = 12, From 3605c64ece931ac1b5e921068d47a54874b961c8 Mon Sep 17 00:00:00 2001 From: Mario Schuknecht Date: Tue, 27 May 2014 07:19:00 +0100 Subject: [PATCH 40/53] staging: iio: tsl2x7x_core: fix proximity treshold commit c404618cd06dad771495fe1cf9d5a63b5664f65f upstream. Consider high byte of proximity min and max treshold in function 'tsl2x7x_chip_on'. So far, the high byte was not set. Signed-off-by: Mario Schuknecht Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/staging/iio/light/tsl2x7x_core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c index c99f890cc6c6..64c73adfa3b0 100644 --- a/drivers/staging/iio/light/tsl2x7x_core.c +++ b/drivers/staging/iio/light/tsl2x7x_core.c @@ -672,9 +672,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev) chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] = chip->tsl2x7x_settings.prox_pulse_count; chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] = - chip->tsl2x7x_settings.prox_thres_low; + (chip->tsl2x7x_settings.prox_thres_low) & 0xFF; + chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] = + (chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF; chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] = - chip->tsl2x7x_settings.prox_thres_high; + (chip->tsl2x7x_settings.prox_thres_high) & 0xFF; + chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] = + (chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF; /* and make sure we're not already on */ if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) { From 9e655732466125a675a3bb8b0ebedfc921dfdcd5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 6 Nov 2014 09:13:00 +0000 Subject: [PATCH 41/53] iio: adc: at91: signedness bug in at91_adc_get_trigger_value_by_name() commit 4f3bcd878f1d3c730fe00f619b7260c6125d49eb upstream. at91_adc_get_trigger_value_by_name() was returning -ENOMEM truncated to a positive u8 and that doesn't work. I've changed it to int and refactored it to preserve the error code. Signed-off-by: Dan Carpenter Acked-by: Alexandre Belloni Tested-by: Alexandre Belloni Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/at91_adc.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index e5b88d5d3b59..14fdaf0f9d23 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -161,12 +161,11 @@ static int at91_adc_channel_init(struct iio_dev *idev) return idev->num_channels; } -static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev, +static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev, struct at91_adc_trigger *triggers, const char *trigger_name) { struct at91_adc_state *st = iio_priv(idev); - u8 value = 0; int i; for (i = 0; i < st->trigger_number; i++) { @@ -179,15 +178,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev, return -ENOMEM; if (strcmp(trigger_name, name) == 0) { - value = triggers[i].value; kfree(name); - break; + if (triggers[i].value == 0) + return -EINVAL; + return triggers[i].value; } kfree(name); } - return value; + return -EINVAL; } static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) @@ -197,14 +197,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) struct iio_buffer *buffer = idev->buffer; struct at91_adc_reg_desc *reg = st->registers; u32 status = at91_adc_readl(st, reg->trigger_register); - u8 value; + int value; u8 bit; value = at91_adc_get_trigger_value_by_name(idev, st->trigger_list, idev->trig->name); - if (value == 0) - return -EINVAL; + if (value < 0) + return value; if (state) { st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL); From a6e3a4df4c6888337dcbfce8b831c98cd3c886a4 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Tue, 6 May 2014 09:53:00 +0100 Subject: [PATCH 42/53] iio: Fix endianness issue in ak8975_read_axis() commit 8ba42fb7b17649c9ab5b5e79d4e90370a0b4645e upstream. i2c_smbus_read_word_data() does host endian conversion already, no need for le16_to_cpu() Signed-off-by: Peter Meerwald Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/magnetometer/ak8975.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index af6c320a534e..53f829004a03 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -276,8 +276,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) { struct ak8975_data *data = iio_priv(indio_dev); struct i2c_client *client = data->client; - u16 meas_reg; - s16 raw; int ret; mutex_lock(&data->lock); @@ -322,16 +320,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) dev_err(&client->dev, "Read axis data fails\n"); goto exit; } - meas_reg = ret; mutex_unlock(&data->lock); - /* Endian conversion of the measured values. */ - raw = (s16) (le16_to_cpu(meas_reg)); - /* Clamp to valid range. */ - raw = clamp_t(s16, raw, -4096, 4095); - *val = raw; + *val = clamp_t(s16, ret, -4096, 4095); return IIO_VAL_INT; exit: From feaad01723471c67e10f5c5bc537299e686f78b8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 20 Jun 2014 22:00:53 -0700 Subject: [PATCH 43/53] lzo: properly check for overruns commit 206a81c18401c0cde6e579164f752c4b147324ce upstream. The lzo decompressor can, if given some really crazy data, possibly overrun some variable types. Modify the checking logic to properly detect overruns before they happen. Reported-by: "Don A. Bailey" Tested-by: "Don A. Bailey" Signed-off-by: Greg Kroah-Hartman --- lib/lzo/lzo1x_decompress_safe.c | 62 ++++++++++++++++++++++----------- 1 file changed, 41 insertions(+), 21 deletions(-) diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 569985d522d5..8563081e8da3 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -19,11 +19,31 @@ #include #include "lzodefs.h" -#define HAVE_IP(x) ((size_t)(ip_end - ip) >= (size_t)(x)) -#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x)) -#define NEED_IP(x) if (!HAVE_IP(x)) goto input_overrun -#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun -#define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun +#define HAVE_IP(t, x) \ + (((size_t)(ip_end - ip) >= (size_t)(t + x)) && \ + (((t + x) >= t) && ((t + x) >= x))) + +#define HAVE_OP(t, x) \ + (((size_t)(op_end - op) >= (size_t)(t + x)) && \ + (((t + x) >= t) && ((t + x) >= x))) + +#define NEED_IP(t, x) \ + do { \ + if (!HAVE_IP(t, x)) \ + goto input_overrun; \ + } while (0) + +#define NEED_OP(t, x) \ + do { \ + if (!HAVE_OP(t, x)) \ + goto output_overrun; \ + } while (0) + +#define TEST_LB(m_pos) \ + do { \ + if ((m_pos) < out) \ + goto lookbehind_overrun; \ + } while (0) int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len) @@ -58,14 +78,14 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, while (unlikely(*ip == 0)) { t += 255; ip++; - NEED_IP(1); + NEED_IP(1, 0); } t += 15 + *ip++; } t += 3; copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) { + if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) { const unsigned char *ie = ip + t; unsigned char *oe = op + t; do { @@ -81,8 +101,8 @@ copy_literal_run: } else #endif { - NEED_OP(t); - NEED_IP(t + 3); + NEED_OP(t, 0); + NEED_IP(t, 3); do { *op++ = *ip++; } while (--t > 0); @@ -95,7 +115,7 @@ copy_literal_run: m_pos -= t >> 2; m_pos -= *ip++ << 2; TEST_LB(m_pos); - NEED_OP(2); + NEED_OP(2, 0); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -119,10 +139,10 @@ copy_literal_run: while (unlikely(*ip == 0)) { t += 255; ip++; - NEED_IP(1); + NEED_IP(1, 0); } t += 31 + *ip++; - NEED_IP(2); + NEED_IP(2, 0); } m_pos = op - 1; next = get_unaligned_le16(ip); @@ -137,10 +157,10 @@ copy_literal_run: while (unlikely(*ip == 0)) { t += 255; ip++; - NEED_IP(1); + NEED_IP(1, 0); } t += 7 + *ip++; - NEED_IP(2); + NEED_IP(2, 0); } next = get_unaligned_le16(ip); ip += 2; @@ -154,7 +174,7 @@ copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) if (op - m_pos >= 8) { unsigned char *oe = op + t; - if (likely(HAVE_OP(t + 15))) { + if (likely(HAVE_OP(t, 15))) { do { COPY8(op, m_pos); op += 8; @@ -164,7 +184,7 @@ copy_literal_run: m_pos += 8; } while (op < oe); op = oe; - if (HAVE_IP(6)) { + if (HAVE_IP(6, 0)) { state = next; COPY4(op, ip); op += next; @@ -172,7 +192,7 @@ copy_literal_run: continue; } } else { - NEED_OP(t); + NEED_OP(t, 0); do { *op++ = *m_pos++; } while (op < oe); @@ -181,7 +201,7 @@ copy_literal_run: #endif { unsigned char *oe = op + t; - NEED_OP(t); + NEED_OP(t, 0); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -194,15 +214,15 @@ match_next: state = next; t = next; #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(6) && HAVE_OP(4))) { + if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) { COPY4(op, ip); op += t; ip += t; } else #endif { - NEED_IP(t + 3); - NEED_OP(t); + NEED_IP(t, 3); + NEED_OP(t, 0); while (t > 0) { *op++ = *ip++; t--; From ec804bd9e1ecad7a6d9f9428eaf388e3dac9cb63 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 29 Nov 2013 12:18:13 +0100 Subject: [PATCH 44/53] nohz: Fix another inconsistency between CONFIG_NO_HZ=n and nohz=off commit 0e576acbc1d9600cf2d9b4a141a2554639959d50 upstream. If CONFIG_NO_HZ=n tick_nohz_get_sleep_length() returns NSEC_PER_SEC/HZ. If CONFIG_NO_HZ=y and the nohz functionality is disabled via the command line option "nohz=off" or not enabled due to missing hardware support, then tick_nohz_get_sleep_length() returns 0. That happens because ts->sleep_length is never set in that case. Set it to NSEC_PER_SEC/HZ when the NOHZ mode is inactive. Reported-by: Michal Hocko Reported-by: Borislav Petkov Signed-off-by: Thomas Gleixner Cc: Rui Xiang Signed-off-by: Greg Kroah-Hartman --- kernel/time/tick-sched.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 4251374578bc..67f7a2d2efbc 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -720,8 +720,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) { + ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ }; return false; + } if (need_resched()) return false; From d2c44167ecbabae2c55f4777f351203282cb8ab2 Mon Sep 17 00:00:00 2001 From: "Wang, Xiaoming" Date: Thu, 12 Jun 2014 18:47:07 -0400 Subject: [PATCH 45/53] ALSA: compress: Cancel the optimization of compiler and fix the size of struct for all platform. commit 2bd0ae464a6cf7363bbf72c8545e0aa43caa57f0 upstream. Cancel the optimization of compiler for struct snd_compr_avail which size will be 0x1c in 32bit kernel while 0x20 in 64bit kernel under the optimizer. That will make compaction between 32bit and 64bit. So add packed to fix the size of struct snd_compr_avail to 0x1c for all platform. Signed-off-by: Zhang Dongxing Signed-off-by: xiaoming wang Acked-by: Vinod Koul Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- include/uapi/sound/compress_offload.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h index 5759810e1c1b..21eed488783f 100644 --- a/include/uapi/sound/compress_offload.h +++ b/include/uapi/sound/compress_offload.h @@ -80,7 +80,7 @@ struct snd_compr_tstamp { struct snd_compr_avail { __u64 avail; struct snd_compr_tstamp tstamp; -}; +} __attribute__((packed)); enum snd_compr_direction { SND_COMPRESS_PLAYBACK = 0, From f0fc13019347a4c99ca5c348ace1e22d4bba3b41 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Thu, 5 Jun 2014 11:13:44 +0800 Subject: [PATCH 46/53] ALSA: hda/realtek - Add support of ALC891 codec commit b6c5fbad16aa5026f508093a8d651c25e1cb6179 upstream. New codec support for ALC891. Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0923f09df503..c38d4effa457 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4664,6 +4664,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = { { .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 }, { .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 }, { .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 }, + { .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 }, { .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 }, { .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 }, { .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 }, From 9c2f4849d76e678d747542389dea63b02a21e29f Mon Sep 17 00:00:00 2001 From: David Henningsson Date: Fri, 13 Jun 2014 11:15:44 +0200 Subject: [PATCH 47/53] ALSA: hda - Add quirk for external mic on Lifebook U904 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 2041d56464a067461d7cc21734a0f024587ed2ff upstream. According to the bug reporter (Данило Шеган), the external mic starts to work and has proper jack detection if only pin 0x19 is marked properly as an external headset mic. AlsaInfo at https://bugs.launchpad.net/ubuntu/+source/pulseaudio/+bug/1328587/+attachment/4128991/+files/AlsaInfo.txt BugLink: https://bugs.launchpad.net/bugs/1328587 Signed-off-by: David Henningsson Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c38d4effa457..0b85e857f1c7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3356,6 +3356,7 @@ enum { ALC269_FIXUP_STEREO_DMIC, ALC269_FIXUP_QUANTA_MUTE, ALC269_FIXUP_LIFEBOOK, + ALC269_FIXUP_LIFEBOOK_EXTMIC, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -3463,6 +3464,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_QUANTA_MUTE }, + [ALC269_FIXUP_LIFEBOOK_EXTMIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1903c }, /* headset mic, with jack detect */ + { } + }, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -3713,6 +3721,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK_VENDOR(0x1025, "Acer Aspire", ALC271_FIXUP_DMIC), SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), From be3bae536eaf0a98926006a8ec00417a48b6a587 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 18 Jun 2014 13:32:31 +0200 Subject: [PATCH 48/53] ALSA: control: Protect user controls against concurrent access commit 07f4d9d74a04aa7c72c5dae0ef97565f28f17b92 upstream. The user-control put and get handlers as well as the tlv do not protect against concurrent access from multiple threads. Since the state of the control is not updated atomically it is possible that either two write operations or a write and a read operation race against each other. Both can lead to arbitrary memory disclosure. This patch introduces a new lock that protects user-controls from concurrent access. Since applications typically access controls sequentially than in parallel a single lock per card should be fine. Signed-off-by: Lars-Peter Clausen Acked-by: Jaroslav Kysela Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- include/sound/core.h | 2 ++ sound/core/control.c | 31 +++++++++++++++++++++++++------ sound/core/init.c | 1 + 3 files changed, 28 insertions(+), 6 deletions(-) diff --git a/include/sound/core.h b/include/sound/core.h index 5bfe5136441c..97cd9c3592f7 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -120,6 +120,8 @@ struct snd_card { int user_ctl_count; /* count of all user controls */ struct list_head controls; /* all controls for this card */ struct list_head ctl_files; /* active control files */ + struct mutex user_ctl_lock; /* protects user controls against + concurrent access */ struct snd_info_entry *proc_root; /* root for soundcard specific files */ struct snd_info_entry *proc_id; /* the card id */ diff --git a/sound/core/control.c b/sound/core/control.c index d8aa206e8bde..183fab277b69 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -992,6 +992,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file, struct user_element { struct snd_ctl_elem_info info; + struct snd_card *card; void *elem_data; /* element data */ unsigned long elem_data_size; /* size of element data in bytes */ void *tlv_data; /* TLV data */ @@ -1035,7 +1036,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol, { struct user_element *ue = kcontrol->private_data; + mutex_lock(&ue->card->user_ctl_lock); memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size); + mutex_unlock(&ue->card->user_ctl_lock); return 0; } @@ -1044,10 +1047,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol, { int change; struct user_element *ue = kcontrol->private_data; - + + mutex_lock(&ue->card->user_ctl_lock); change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0; if (change) memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size); + mutex_unlock(&ue->card->user_ctl_lock); return change; } @@ -1067,19 +1072,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol, new_data = memdup_user(tlv, size); if (IS_ERR(new_data)) return PTR_ERR(new_data); + mutex_lock(&ue->card->user_ctl_lock); change = ue->tlv_data_size != size; if (!change) change = memcmp(ue->tlv_data, new_data, size); kfree(ue->tlv_data); ue->tlv_data = new_data; ue->tlv_data_size = size; + mutex_unlock(&ue->card->user_ctl_lock); } else { - if (! ue->tlv_data_size || ! ue->tlv_data) - return -ENXIO; - if (size < ue->tlv_data_size) - return -ENOSPC; + int ret = 0; + + mutex_lock(&ue->card->user_ctl_lock); + if (!ue->tlv_data_size || !ue->tlv_data) { + ret = -ENXIO; + goto err_unlock; + } + if (size < ue->tlv_data_size) { + ret = -ENOSPC; + goto err_unlock; + } if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size)) - return -EFAULT; + ret = -EFAULT; +err_unlock: + mutex_unlock(&ue->card->user_ctl_lock); + if (ret) + return ret; } return change; } @@ -1211,6 +1229,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL); if (ue == NULL) return -ENOMEM; + ue->card = card; ue->info = *info; ue->info.access = 0; ue->elem_data = (char *)ue + sizeof(*ue); diff --git a/sound/core/init.c b/sound/core/init.c index 6ef06400dfc8..27791a58e448 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -208,6 +208,7 @@ int snd_card_create(int idx, const char *xid, INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->ctl_files_rwlock); + mutex_init(&card->user_ctl_lock); INIT_LIST_HEAD(&card->controls); INIT_LIST_HEAD(&card->ctl_files); spin_lock_init(&card->files_lock); From adbb1449ccc8c637b31d11dc0b8c3ad47228b199 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 18 Jun 2014 13:32:32 +0200 Subject: [PATCH 49/53] ALSA: control: Fix replacing user controls commit 82262a46627bebb0febcc26664746c25cef08563 upstream. There are two issues with the current implementation for replacing user controls. The first is that the code does not check if the control is actually a user control and neither does it check if the control is owned by the process that tries to remove it. That allows userspace applications to remove arbitrary controls, which can cause a user after free if a for example a driver does not expect a control to be removed from under its feed. The second issue is that on one hand when a control is replaced the user_ctl_count limit is not checked and on the other hand the user_ctl_count is increased (even though the number of user controls does not change). This allows userspace, once the user_ctl_count limit as been reached, to repeatedly replace a control until user_ctl_count overflows. Once that happens new controls can be added effectively bypassing the user_ctl_count limit. Both issues can be fixed by instead of open-coding the removal of the control that is to be replaced to use snd_ctl_remove_user_ctl(). This function does proper permission checks as well as decrements user_ctl_count after the control has been removed. Note that by using snd_ctl_remove_user_ctl() the check which returns -EBUSY at beginning of the function if the control already exists is removed. This is not a problem though since the check is quite useless, because the lock that is protecting the control list is released between the check and before adding the new control to the list, which means that it is possible that a different control with the same settings is added to the list after the check. Luckily there is another check that is done while holding the lock in snd_ctl_add(), so we'll rely on that to make sure that the same control is not added twice. Signed-off-by: Lars-Peter Clausen Acked-by: Jaroslav Kysela Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/control.c | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-) diff --git a/sound/core/control.c b/sound/core/control.c index 183fab277b69..15bc84492746 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1155,8 +1155,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, struct user_element *ue; int idx, err; - if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS) - return -ENOMEM; if (info->count < 1) return -EINVAL; access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE : @@ -1165,21 +1163,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE)); info->id.numid = 0; memset(&kctl, 0, sizeof(kctl)); - down_write(&card->controls_rwsem); - _kctl = snd_ctl_find_id(card, &info->id); - err = 0; - if (_kctl) { - if (replace) - err = snd_ctl_remove(card, _kctl); - else - err = -EBUSY; - } else { - if (replace) - err = -ENOENT; + + if (replace) { + err = snd_ctl_remove_user_ctl(file, &info->id); + if (err) + return err; } - up_write(&card->controls_rwsem); - if (err < 0) - return err; + + if (card->user_ctl_count >= MAX_USER_CONTROLS) + return -ENOMEM; + memcpy(&kctl.id, &info->id, sizeof(info->id)); kctl.count = info->owner ? info->owner : 1; access |= SNDRV_CTL_ELEM_ACCESS_USER; From 9abd94862196476a80dbfc07d3f8a01418fa36d8 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 18 Jun 2014 13:32:33 +0200 Subject: [PATCH 50/53] ALSA: control: Don't access controls outside of protected regions commit fd9f26e4eca5d08a27d12c0933fceef76ed9663d upstream. A control that is visible on the card->controls list can be freed at any time. This means we must not access any of its memory while not holding the controls_rw_lock. Otherwise we risk a use after free access. Signed-off-by: Lars-Peter Clausen Acked-by: Jaroslav Kysela Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/control.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/sound/core/control.c b/sound/core/control.c index 15bc84492746..d4a597fe86e4 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -331,6 +331,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) { struct snd_ctl_elem_id id; unsigned int idx; + unsigned int count; int err = -EINVAL; if (! kcontrol) @@ -359,8 +360,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) card->controls_count += kcontrol->count; kcontrol->id.numid = card->last_numid + 1; card->last_numid += kcontrol->count; + count = kcontrol->count; up_write(&card->controls_rwsem); - for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++) + for (idx = 0; idx < count; idx++, id.index++, id.numid++) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); return 0; @@ -389,6 +391,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace) { struct snd_ctl_elem_id id; + unsigned int count; unsigned int idx; struct snd_kcontrol *old; int ret; @@ -424,8 +427,9 @@ add: card->controls_count += kcontrol->count; kcontrol->id.numid = card->last_numid + 1; card->last_numid += kcontrol->count; + count = kcontrol->count; up_write(&card->controls_rwsem); - for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++) + for (idx = 0; idx < count; idx++, id.index++, id.numid++) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); return 0; @@ -898,9 +902,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file, result = kctl->put(kctl, control); } if (result > 0) { + struct snd_ctl_elem_id id = control->id; up_read(&card->controls_rwsem); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, - &control->id); + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id); return 0; } } @@ -1334,8 +1338,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file, } err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv); if (err > 0) { + struct snd_ctl_elem_id id = kctl->id; up_read(&card->controls_rwsem); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id); + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id); return 0; } } else { From 0255758b24b94398786df97623849a81a7d5b2ef Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 18 Jun 2014 13:32:34 +0200 Subject: [PATCH 51/53] ALSA: control: Handle numid overflow commit ac902c112d90a89e59916f751c2745f4dbdbb4bd upstream. Each control gets automatically assigned its numids when the control is created. The allocation is done by incrementing the numid by the amount of allocated numids per allocation. This means that excessive creation and destruction of controls (e.g. via SNDRV_CTL_IOCTL_ELEM_ADD/REMOVE) can cause the id to eventually overflow. Currently when this happens for the control that caused the overflow kctl->id.numid + kctl->count will also over flow causing it to be smaller than kctl->id.numid. Most of the code assumes that this is something that can not happen, so we need to make sure that it won't happen Signed-off-by: Lars-Peter Clausen Acked-by: Jaroslav Kysela Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/control.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/core/control.c b/sound/core/control.c index d4a597fe86e4..93215b4bec6b 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -289,6 +289,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card, { struct snd_kcontrol *kctl; + /* Make sure that the ids assigned to the control do not wrap around */ + if (card->last_numid >= UINT_MAX - count) + card->last_numid = 0; + list_for_each_entry(kctl, &card->controls, list) { if (kctl->id.numid < card->last_numid + 1 + count && kctl->id.numid + kctl->count > card->last_numid + 1) { From 7fba24c6c99b514716fd069094799df035f46054 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 18 Jun 2014 13:32:35 +0200 Subject: [PATCH 52/53] ALSA: control: Make sure that id->index does not overflow commit 883a1d49f0d77d30012f114b2e19fc141beb3e8e upstream. The ALSA control code expects that the range of assigned indices to a control is continuous and does not overflow. Currently there are no checks to enforce this. If a control with a overflowing index range is created that control becomes effectively inaccessible and unremovable since snd_ctl_find_id() will not be able to find it. This patch adds a check that makes sure that controls with a overflowing index range can not be created. Signed-off-by: Lars-Peter Clausen Acked-by: Jaroslav Kysela Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/control.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/core/control.c b/sound/core/control.c index 93215b4bec6b..98a29b26c5f4 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -343,6 +343,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) if (snd_BUG_ON(!card || !kcontrol->info)) goto error; id = kcontrol->id; + if (id.index > UINT_MAX - kcontrol->count) + goto error; + down_write(&card->controls_rwsem); if (snd_ctl_find_id(card, &id)) { up_write(&card->controls_rwsem); From 7ab9233c18a4413c7db130c96aa16fae89e06547 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 26 Jun 2014 15:13:14 -0400 Subject: [PATCH 53/53] Linux 3.10.45 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e55476c4aef0..8a63ca1db77a 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 10 -SUBLEVEL = 44 +SUBLEVEL = 45 EXTRAVERSION = NAME = TOSSUG Baby Fish