From d8668fcb0b257d9fdcfbe5c172a99b8d85e1cd82 Mon Sep 17 00:00:00 2001 From: Shan Hai Date: Mon, 18 Mar 2013 10:30:43 +0800 Subject: libata: Use integer return value for atapi_command_packet_set The function returns type of ATAPI drives so it should return integer value. The commit 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) since v2.6.39 changed the type of return value from int to bool, the change would cause all of the ATAPI class drives to be treated as TYPE_TAPE and the max_sectors of the drives to be set to 65535 because of the commit f8d8e5799b7(libata: increase 128 KB / cmd limit for ATAPI tape drives), for the function would return true for all ATAPI class drives and the TYPE_TAPE is defined as 0x01. Cc: stable@vger.kernel.org Signed-off-by: Shan Hai Signed-off-by: Jeff Garzik --- include/linux/ata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 8f7a3d68371a..ee0bd9524055 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -954,7 +954,7 @@ static inline int atapi_cdb_len(const u16 *dev_id) } } -static inline bool atapi_command_packet_set(const u16 *dev_id) +static inline int atapi_command_packet_set(const u16 *dev_id) { return (dev_id[ATA_ID_CONFIG] >> 8) & 0x1f; } -- cgit v1.3-18-gd494 From a32450e127fc6e5ca6d958ceb3cfea4d30a00846 Mon Sep 17 00:00:00 2001 From: Shan Hai Date: Mon, 18 Mar 2013 10:30:44 +0800 Subject: libata: Set max sector to 65535 for Slimtype DVD A DS8A8SH drive The Slimtype DVD A DS8A8SH drive locks up when max sector is smaller than 65535, and the blow backtrace is observed on locking up: INFO: task flush-8:32:1130 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. flush-8:32 D ffffffff8180cf60 0 1130 2 0x00000000 ffff880273aef618 0000000000000046 0000000000000005 ffff880273aee000 ffff880273aee000 ffff880273aeffd8 ffff880273aee010 ffff880273aee000 ffff880273aeffd8 ffff880273aee000 ffff88026e842ea0 ffff880274a10000 Call Trace: [] schedule+0x5d/0x70 [] io_schedule+0x8c/0xd0 [] get_request+0x731/0x7d0 [] ? cfq_allow_merge+0x50/0x90 [] ? wake_up_bit+0x40/0x40 [] ? bio_attempt_back_merge+0x33/0x110 [] blk_queue_bio+0x23a/0x3f0 [] generic_make_request+0xc6/0x120 [] submit_bio+0x138/0x160 [] ? bio_alloc_bioset+0x96/0x120 [] submit_bh+0x1f1/0x220 [] __block_write_full_page+0x228/0x340 [] ? attach_nobh_buffers+0xc0/0xc0 [] ? I_BDEV+0x10/0x10 [] ? I_BDEV+0x10/0x10 [] block_write_full_page_endio+0xe6/0x100 [] block_write_full_page+0x15/0x20 [] blkdev_writepage+0x18/0x20 [] __writepage+0x17/0x40 [] write_cache_pages+0x34a/0x4a0 [] ? set_page_dirty+0x70/0x70 [] generic_writepages+0x51/0x80 [] do_writepages+0x20/0x50 [] __writeback_single_inode+0xa6/0x2b0 [] writeback_sb_inodes+0x311/0x4d0 [] __writeback_inodes_wb+0x86/0xd0 [] wb_writeback+0x1a3/0x330 [] ? _raw_spin_lock_irqsave+0x3f/0x50 [] ? get_nr_inodes+0x52/0x70 [] wb_do_writeback+0x1dc/0x260 [] ? schedule_timeout+0x204/0x240 [] bdi_writeback_thread+0x102/0x2b0 [] ? wb_do_writeback+0x260/0x260 [] kthread+0xc0/0xd0 [] ? kthread_worker_fn+0x1b0/0x1b0 [] ret_from_fork+0x7c/0xb0 [] ? kthread_worker_fn+0x1b0/0x1b0 The above trace was triggered by "dd if=/dev/zero of=/dev/sr0 bs=2048 count=32768" It was previously working by accident, since another bug introduced by 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) caused all drives to use maxsect=65535. Cc: stable@vger.kernel.org Signed-off-by: Shan Hai Signed-off-by: Jeff Garzik --- drivers/ata/libata-core.c | 4 ++++ include/linux/libata.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 497adea1f0d6..0075944a64dc 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2439,6 +2439,9 @@ int ata_dev_configure(struct ata_device *dev) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128, dev->max_sectors); + if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48) + dev->max_sectors = ATA_MAX_SECTORS_LBA48; + if (ap->ops->dev_config) ap->ops->dev_config(dev); @@ -4100,6 +4103,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Weird ATAPI devices */ { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 }, { "QUANTUM DAT DAT72-000", NULL, ATA_HORKAGE_ATAPI_MOD16_DMA }, + { "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, /* Devices we expect to fail diagnostics */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 91c9d109e5f1..eae7a053dc51 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -398,6 +398,7 @@ enum { ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ + ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.3-18-gd494 From 395b97a3aeff0b8d949ee3e67bf8c11c5ffd6861 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 27 Mar 2013 09:31:28 -0400 Subject: ftrace: Do not call stub functions in control loop The function tracing control loop used by perf spits out a warning if the called function is not a control function. This is because the control function references a per cpu allocated data structure on struct ftrace_ops that is not allocated for other types of functions. commit 0a016409e42 "ftrace: Optimize the function tracer list loop" Had an optimization done to all function tracing loops to optimize for a single registered ops. Unfortunately, this allows for a slight race when tracing starts or ends, where the stub function might be called after the current registered ops is removed. In this case we get the following dump: root# perf stat -e ftrace:function sleep 1 [ 74.339105] WARNING: at include/linux/ftrace.h:209 ftrace_ops_control_func+0xde/0xf0() [ 74.349522] Hardware name: PRIMERGY RX200 S6 [ 74.357149] Modules linked in: sg igb iTCO_wdt ptp pps_core iTCO_vendor_support i7core_edac dca lpc_ich i2c_i801 coretemp edac_core crc32c_intel mfd_core ghash_clmulni_intel dm_multipath acpi_power_meter pcspk r microcode vhost_net tun macvtap macvlan nfsd kvm_intel kvm auth_rpcgss nfs_acl lockd sunrpc uinput xfs libcrc32c sd_mod crc_t10dif sr_mod cdrom mgag200 i2c_algo_bit drm_kms_helper ttm qla2xxx mptsas ahci drm li bahci scsi_transport_sas mptscsih libata scsi_transport_fc i2c_core mptbase scsi_tgt dm_mirror dm_region_hash dm_log dm_mod [ 74.446233] Pid: 1377, comm: perf Tainted: G W 3.9.0-rc1 #1 [ 74.453458] Call Trace: [ 74.456233] [] warn_slowpath_common+0x7f/0xc0 [ 74.462997] [] ? rcu_note_context_switch+0xa0/0xa0 [ 74.470272] [] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.478117] [] warn_slowpath_null+0x1a/0x20 [ 74.484681] [] ftrace_ops_control_func+0xde/0xf0 [ 74.491760] [] ftrace_call+0x5/0x2f [ 74.497511] [] ? ftrace_call+0x5/0x2f [ 74.503486] [] ? ftrace_call+0x5/0x2f [ 74.509500] [] ? synchronize_sched+0x5/0x50 [ 74.516088] [] ? _cond_resched+0x5/0x40 [ 74.522268] [] ? synchronize_sched+0x5/0x50 [ 74.528837] [] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.536696] [] ? _cond_resched+0x5/0x40 [ 74.542878] [] ? mutex_lock+0x1d/0x50 [ 74.548869] [] unregister_ftrace_function+0x27/0x50 [ 74.556243] [] perf_ftrace_event_register+0x9f/0x140 [ 74.563709] [] ? _cond_resched+0x5/0x40 [ 74.569887] [] ? mutex_lock+0x1d/0x50 [ 74.575898] [] perf_trace_destroy+0x2e/0x50 [ 74.582505] [] tp_perf_event_destroy+0x9/0x10 [ 74.589298] [] free_event+0x70/0x1a0 [ 74.595208] [] perf_event_release_kernel+0x69/0xa0 [ 74.602460] [] ? _cond_resched+0x5/0x40 [ 74.608667] [] put_event+0x90/0xc0 [ 74.614373] [] perf_release+0x10/0x20 [ 74.620367] [] __fput+0xf4/0x280 [ 74.625894] [] ____fput+0xe/0x10 [ 74.631387] [] task_work_run+0xa7/0xe0 [ 74.637452] [] do_notify_resume+0x71/0xb0 [ 74.643843] [] int_signal+0x12/0x17 To fix this a new ftrace_ops flag is added that denotes the ftrace_list_end ftrace_ops stub as just that, a stub. This flag is now checked in the control loop and the function is not called if the flag is set. Thanks to Jovi for not just reporting the bug, but also pointing out where the bug was in the code. Link: http://lkml.kernel.org/r/514A8855.7090402@redhat.com Link: http://lkml.kernel.org/r/1364377499-1900-15-git-send-email-jovi.zhangwei@huawei.com Tested-by: WANG Chao Reported-by: WANG Chao Reported-by: zhangwei(Jovi) Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 ++ kernel/trace/ftrace.c | 5 +++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5ca8ef50e9b..167abf907802 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -89,6 +89,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * that the call back has its own recursion protection. If it does * not set this, then the ftrace infrastructure will add recursion * protection for the caller. + * STUB - The ftrace_ops is just a place holder. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -98,6 +99,7 @@ enum { FTRACE_OPS_FL_SAVE_REGS = 1 << 4, FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, + FTRACE_OPS_FL_STUB = 1 << 7, }; struct ftrace_ops { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cc4943c7ce6d..7e897106b7e0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -66,7 +66,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, }; /* ftrace_enabled is a method to turn ftrace on or off */ @@ -4131,7 +4131,8 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, preempt_disable_notrace(); trace_recursion_set(TRACE_CONTROL_BIT); do_for_each_ftrace_op(op, ftrace_control_list) { - if (!ftrace_function_local_disabled(op) && + if (!(op->flags & FTRACE_OPS_FL_STUB) && + !ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); -- cgit v1.3-18-gd494 From ca10b9e9a8ca7342ee07065289cbe74ac128c169 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Apr 2013 17:58:11 +0000 Subject: selinux: add a skb_owned_by() hook Commit 90ba9b1986b5ac (tcp: tcp_make_synack() can use alloc_skb()) broke certain SELinux/NetLabel configurations by no longer correctly assigning the sock to the outgoing SYNACK packet. Cost of atomic operations on the LISTEN socket is quite big, and we would like it to happen only if really needed. This patch introduces a new security_ops->skb_owned_by() method, that is a void operation unless selinux is active. Reported-by: Miroslav Vadkerti Diagnosed-by: Paul Moore Signed-off-by: Eric Dumazet Cc: "David S. Miller" Cc: linux-security-module@vger.kernel.org Acked-by: James Morris Tested-by: Paul Moore Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 8 ++++++++ net/ipv4/tcp_output.c | 1 + security/capability.c | 6 ++++++ security/security.c | 5 +++++ security/selinux/hooks.c | 7 +++++++ 5 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index eee7478cda70..6c3a78ace051 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1638,6 +1638,7 @@ struct security_operations { int (*tun_dev_attach_queue) (void *security); int (*tun_dev_attach) (struct sock *sk, void *security); int (*tun_dev_open) (void *security); + void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2588,6 +2589,8 @@ int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); +void security_skb_owned_by(struct sk_buff *skb, struct sock *sk); + #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, struct sock *other, @@ -2779,6 +2782,11 @@ static inline int security_tun_dev_open(void *security) { return 0; } + +static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5d0b4387cba6..b44cf81d8178 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2709,6 +2709,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst); + security_skb_owned_by(skb, sk); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) diff --git a/security/capability.c b/security/capability.c index 579775088967..6783c3e6c88e 100644 --- a/security/capability.c +++ b/security/capability.c @@ -737,6 +737,11 @@ static int cap_tun_dev_open(void *security) { return 0; } + +static void cap_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -1071,6 +1076,7 @@ void __init security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, tun_dev_open); set_to_cap_if_null(ops, tun_dev_attach_queue); set_to_cap_if_null(ops, tun_dev_attach); + set_to_cap_if_null(ops, skb_owned_by); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM set_to_cap_if_null(ops, xfrm_policy_alloc_security); diff --git a/security/security.c b/security/security.c index 7b88c6aeaed4..03f248b84e9f 100644 --- a/security/security.c +++ b/security/security.c @@ -1290,6 +1290,11 @@ int security_tun_dev_open(void *security) } EXPORT_SYMBOL(security_tun_dev_open); +void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ + security_ops->skb_owned_by(skb, sk); +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 2fa28c88900c..7171a957b933 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -51,6 +51,7 @@ #include #include #include /* for local_port_range[] */ +#include #include /* struct or_callable used in sock_rcv_skb */ #include #include @@ -4363,6 +4364,11 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } +static void selinux_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ + skb_set_owner_w(skb, sk); +} + static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; @@ -5664,6 +5670,7 @@ static struct security_operations selinux_ops = { .tun_dev_attach_queue = selinux_tun_dev_attach_queue, .tun_dev_attach = selinux_tun_dev_attach, .tun_dev_open = selinux_tun_dev_open, + .skb_owned_by = selinux_skb_owned_by, #ifdef CONFIG_SECURITY_NETWORK_XFRM .xfrm_policy_alloc_security = selinux_xfrm_policy_alloc, -- cgit v1.3-18-gd494 From 386afc91144b36b42117b0092893f15bc8798a80 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 9 Apr 2013 10:48:33 -0700 Subject: spinlocks and preemption points need to be at least compiler barriers In UP and non-preempt respectively, the spinlocks and preemption disable/enable points are stubbed out entirely, because there is no regular code that can ever hit the kind of concurrency they are meant to protect against. However, while there is no regular code that can cause scheduling, we _do_ end up having some exceptional (literally!) code that can do so, and that we need to make sure does not ever get moved into the critical region by the compiler. In particular, get_user() and put_user() is generally implemented as inline asm statements (even if the inline asm may then make a call instruction to call out-of-line), and can obviously cause a page fault and IO as a result. If that inline asm has been scheduled into the middle of a preemption-safe (or spinlock-protected) code region, we obviously lose. Now, admittedly this is *very* unlikely to actually ever happen, and we've not seen examples of actual bugs related to this. But partly exactly because it's so hard to trigger and the resulting bug is so subtle, we should be extra careful to get this right. So make sure that even when preemption is disabled, and we don't have to generate any actual *code* to explicitly tell the system that we are in a preemption-disabled region, we need to at least tell the compiler not to move things around the critical region. This patch grew out of the same discussion that caused commits 79e5f05edcbf ("ARC: Add implicit compiler barrier to raw_local_irq* functions") and 3e2e0d2c222b ("tile: comment assumption about __insn_mtspr for ") to come about. Note for stable: use discretion when/if applying this. As mentioned, this bug may never have actually bitten anybody, and gcc may never have done the required code motion for it to possibly ever trigger in practice. Cc: stable@vger.kernel.org Cc: Steven Rostedt Cc: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/preempt.h | 22 ++++++++++++++-------- include/linux/spinlock_up.h | 29 ++++++++++++++++++----------- 2 files changed, 32 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5a710b9c578e..87a03c746f17 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -93,14 +93,20 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ -#define preempt_disable() do { } while (0) -#define sched_preempt_enable_no_resched() do { } while (0) -#define preempt_enable_no_resched() do { } while (0) -#define preempt_enable() do { } while (0) - -#define preempt_disable_notrace() do { } while (0) -#define preempt_enable_no_resched_notrace() do { } while (0) -#define preempt_enable_notrace() do { } while (0) +/* + * Even if we don't have any preemption, we need preempt disable/enable + * to be barriers, so that we don't have things like get_user/put_user + * that can cause faults and scheduling migrate into our preempt-protected + * region. + */ +#define preempt_disable() barrier() +#define sched_preempt_enable_no_resched() barrier() +#define preempt_enable_no_resched() barrier() +#define preempt_enable() barrier() + +#define preempt_disable_notrace() barrier() +#define preempt_enable_no_resched_notrace() barrier() +#define preempt_enable_notrace() barrier() #endif /* CONFIG_PREEMPT_COUNT */ diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index a26e2fb604e6..e2369c167dbd 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -16,7 +16,10 @@ * In the debug case, 1 means unlocked, 0 means locked. (the values * are inverted, to catch initialization bugs) * - * No atomicity anywhere, we are on UP. + * No atomicity anywhere, we are on UP. However, we still need + * the compiler barriers, because we do not want the compiler to + * move potentially faulting instructions (notably user accesses) + * into the locked sequence, resulting in non-atomic execution. */ #ifdef CONFIG_DEBUG_SPINLOCK @@ -25,6 +28,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; + barrier(); } static inline void @@ -32,6 +36,7 @@ arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { local_irq_save(flags); lock->slock = 0; + barrier(); } static inline int arch_spin_trylock(arch_spinlock_t *lock) @@ -39,32 +44,34 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) char oldval = lock->slock; lock->slock = 0; + barrier(); return oldval > 0; } static inline void arch_spin_unlock(arch_spinlock_t *lock) { + barrier(); lock->slock = 1; } /* * Read-write spinlocks. No debug version. */ -#define arch_read_lock(lock) do { (void)(lock); } while (0) -#define arch_write_lock(lock) do { (void)(lock); } while (0) -#define arch_read_trylock(lock) ({ (void)(lock); 1; }) -#define arch_write_trylock(lock) ({ (void)(lock); 1; }) -#define arch_read_unlock(lock) do { (void)(lock); } while (0) -#define arch_write_unlock(lock) do { (void)(lock); } while (0) +#define arch_read_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_read_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_write_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_read_unlock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_unlock(lock) do { barrier(); (void)(lock); } while (0) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) /* for sched.c and kernel_lock.c: */ -# define arch_spin_lock(lock) do { (void)(lock); } while (0) -# define arch_spin_lock_flags(lock, flags) do { (void)(lock); } while (0) -# define arch_spin_unlock(lock) do { (void)(lock); } while (0) -# define arch_spin_trylock(lock) ({ (void)(lock); 1; }) +# define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) +# define arch_spin_unlock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_trylock(lock) ({ barrier(); (void)(lock); 1; }) #endif /* DEBUG_SPINLOCK */ #define arch_spin_is_contended(lock) (((void)(lock), 0)) -- cgit v1.3-18-gd494 From 8ce584c7416d8a85a6f3edc17d1cddefe331e87e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 30 Mar 2013 20:13:46 -0400 Subject: procfs: add proc_remove_subtree() just what it sounds like; do that only to procfs subtrees you've created - doing that to something shared with another driver is not only antisocial, but might cause interesting races with proc_create() and its ilk. Signed-off-by: Al Viro --- fs/proc/generic.c | 119 ++++++++++++++++++++++++++++++++++++------------ include/linux/proc_fs.h | 2 + 2 files changed, 91 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 4b3b3ffb52f1..21e1a8f1659d 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -755,37 +755,8 @@ void pde_put(struct proc_dir_entry *pde) free_proc_entry(pde); } -/* - * Remove a /proc entry and free it if it's not currently in use. - */ -void remove_proc_entry(const char *name, struct proc_dir_entry *parent) +static void entry_rundown(struct proc_dir_entry *de) { - struct proc_dir_entry **p; - struct proc_dir_entry *de = NULL; - const char *fn = name; - unsigned int len; - - spin_lock(&proc_subdir_lock); - if (__xlate_proc_name(name, &parent, &fn) != 0) { - spin_unlock(&proc_subdir_lock); - return; - } - len = strlen(fn); - - for (p = &parent->subdir; *p; p=&(*p)->next ) { - if (proc_match(len, fn, *p)) { - de = *p; - *p = de->next; - de->next = NULL; - break; - } - } - spin_unlock(&proc_subdir_lock); - if (!de) { - WARN(1, "name '%s'\n", name); - return; - } - spin_lock(&de->pde_unload_lock); /* * Stop accepting new callers into module. If you're @@ -817,6 +788,40 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); +} + +/* + * Remove a /proc entry and free it if it's not currently in use. + */ +void remove_proc_entry(const char *name, struct proc_dir_entry *parent) +{ + struct proc_dir_entry **p; + struct proc_dir_entry *de = NULL; + const char *fn = name; + unsigned int len; + + spin_lock(&proc_subdir_lock); + if (__xlate_proc_name(name, &parent, &fn) != 0) { + spin_unlock(&proc_subdir_lock); + return; + } + len = strlen(fn); + + for (p = &parent->subdir; *p; p=&(*p)->next ) { + if (proc_match(len, fn, *p)) { + de = *p; + *p = de->next; + de->next = NULL; + break; + } + } + spin_unlock(&proc_subdir_lock); + if (!de) { + WARN(1, "name '%s'\n", name); + return; + } + + entry_rundown(de); if (S_ISDIR(de->mode)) parent->nlink--; @@ -827,3 +832,57 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) pde_put(de); } EXPORT_SYMBOL(remove_proc_entry); + +int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) +{ + struct proc_dir_entry **p; + struct proc_dir_entry *root = NULL, *de, *next; + const char *fn = name; + unsigned int len; + + spin_lock(&proc_subdir_lock); + if (__xlate_proc_name(name, &parent, &fn) != 0) { + spin_unlock(&proc_subdir_lock); + return -ENOENT; + } + len = strlen(fn); + + for (p = &parent->subdir; *p; p=&(*p)->next ) { + if (proc_match(len, fn, *p)) { + root = *p; + *p = root->next; + root->next = NULL; + break; + } + } + if (!root) { + spin_unlock(&proc_subdir_lock); + return -ENOENT; + } + de = root; + while (1) { + next = de->subdir; + if (next) { + de->subdir = next->next; + next->next = NULL; + de = next; + continue; + } + spin_unlock(&proc_subdir_lock); + + entry_rundown(de); + next = de->parent; + if (S_ISDIR(de->mode)) + next->nlink--; + de->nlink = 0; + if (de == root) + break; + pde_put(de); + + spin_lock(&proc_subdir_lock); + de = next; + } + pde_put(root); + return 0; +} +EXPORT_SYMBOL(remove_proc_subtree); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8307f2f94d86..94dfb2aa5533 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -117,6 +117,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, const struct file_operations *proc_fops, void *data); extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); +extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); struct pid_namespace; @@ -202,6 +203,7 @@ static inline struct proc_dir_entry *proc_create_data(const char *name, return NULL; } #define remove_proc_entry(name, parent) do {} while (0) +#define remove_proc_subtree(name, parent) do {} while (0) static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} -- cgit v1.3-18-gd494 From 6b07a24fc38476e04f591cc17594bc1835b9efdd Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 10 Apr 2013 15:34:14 -0400 Subject: lsm: add the missing documentation for the security_skb_owned_by() hook Unfortunately we didn't catch the missing comments earlier when the patch was merged. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 6c3a78ace051..032c366ef1c6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1012,6 +1012,10 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * This hook can be used by the module to update any security state * associated with the TUN device's security structure. * @security pointer to the TUN devices's security structure. + * @skb_owned_by: + * This hook sets the packet's owning sock. + * @skb is the packet. + * @sk the sock which owns the packet. * * Security hooks for XFRM operations. * -- cgit v1.3-18-gd494 From 6a76f8c0ab19f215af2a3442870eeb5f0e81998d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 11 Apr 2013 15:55:01 +0900 Subject: tracing: Fix possible NULL pointer dereferences Currently set_ftrace_pid and set_graph_function files use seq_lseek for their fops. However seq_open() is called only for FMODE_READ in the fops->open() so that if an user tries to seek one of those file when she open it for writing, it sees NULL seq_file and then panic. It can be easily reproduced with following command: $ cd /sys/kernel/debug/tracing $ echo 1234 | sudo tee -a set_ftrace_pid In this example, GNU coreutils' tee opens the file with fopen(, "a") and then the fopen() internally calls lseek(). Link: http://lkml.kernel.org/r/1365663302-2170-1-git-send-email-namhyung@kernel.org Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: stable@vger.kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 +- kernel/trace/ftrace.c | 10 +++++----- kernel/trace/trace_stack.c | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 167abf907802..eb3ce327b975 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -396,7 +396,7 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence); +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 926ebfb74936..affc35d829cc 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2697,7 +2697,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file) } loff_t -ftrace_regex_lseek(struct file *file, loff_t offset, int whence) +ftrace_filter_lseek(struct file *file, loff_t offset, int whence) { loff_t ret; @@ -3570,7 +3570,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3578,7 +3578,7 @@ static const struct file_operations ftrace_notrace_fops = { .open = ftrace_notrace_open, .read = seq_read, .write = ftrace_notrace_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3783,8 +3783,8 @@ static const struct file_operations ftrace_graph_fops = { .open = ftrace_graph_open, .read = seq_read, .write = ftrace_graph_write, + .llseek = ftrace_filter_lseek, .release = ftrace_graph_release, - .llseek = seq_lseek, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -4439,7 +4439,7 @@ static const struct file_operations ftrace_pid_fops = { .open = ftrace_pid_open, .write = ftrace_pid_write, .read = seq_read, - .llseek = seq_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_pid_release, }; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 42ca822fc701..83a8b5b7bd35 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -322,7 +322,7 @@ static const struct file_operations stack_trace_filter_fops = { .open = stack_trace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; -- cgit v1.3-18-gd494 From 7f49ef69db6bbf756c0abca7e9b65b32e999eec8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Apr 2013 16:40:13 -0400 Subject: ftrace: Move ftrace_filter_lseek out of CONFIG_DYNAMIC_FTRACE section As ftrace_filter_lseek is now used with ftrace_pid_fops, it needs to be moved out of the #ifdef CONFIG_DYNAMIC_FTRACE section as the ftrace_pid_fops is defined when DYNAMIC_FTRACE is not. Cc: stable@vger.kernel.org Cc: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 ++- kernel/trace/ftrace.c | 28 ++++++++++++++-------------- 2 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eb3ce327b975..52da2a250795 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -396,7 +396,6 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init @@ -569,6 +568,8 @@ static inline int ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; } #endif /* CONFIG_DYNAMIC_FTRACE */ +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); + /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index affc35d829cc..2461ede45a8d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1052,6 +1052,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) static struct pid * const ftrace_swapper_pid = &init_struct_pid; +loff_t +ftrace_filter_lseek(struct file *file, loff_t offset, int whence) +{ + loff_t ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, whence); + else + file->f_pos = ret = 1; + + return ret; +} + #ifdef CONFIG_DYNAMIC_FTRACE #ifndef CONFIG_FTRACE_MCOUNT_RECORD @@ -2612,7 +2625,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash) * routine, you can use ftrace_filter_write() for the write * routine if @flag has FTRACE_ITER_FILTER set, or * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set. - * ftrace_regex_lseek() should be used as the lseek routine, and + * ftrace_filter_lseek() should be used as the lseek routine, and * release must call ftrace_regex_release(). */ int @@ -2696,19 +2709,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file) inode, file); } -loff_t -ftrace_filter_lseek(struct file *file, loff_t offset, int whence) -{ - loff_t ret; - - if (file->f_mode & FMODE_READ) - ret = seq_lseek(file, offset, whence); - else - file->f_pos = ret = 1; - - return ret; -} - static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; -- cgit v1.3-18-gd494 From 935d8aabd4331f47a89c3e1daa5779d23cf244ee Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 14 Apr 2013 10:06:31 -0700 Subject: Add file_ns_capable() helper function for open-time capability checking Nothing is using it yet, but this will allow us to delay the open-time checks to use time, without breaking the normal UNIX permission semantics where permissions are determined by the opener (and the file descriptor can then be passed to a different process, or the process can drop capabilities). Signed-off-by: Linus Torvalds --- include/linux/capability.h | 2 ++ kernel/capability.c | 24 ++++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 98503b792369..d9a4f7f40f32 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -35,6 +35,7 @@ struct cpu_vfs_cap_data { #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) +struct file; struct inode; struct dentry; struct user_namespace; @@ -211,6 +212,7 @@ extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool nsown_capable(int cap); extern bool inode_capable(const struct inode *inode, int cap); +extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/kernel/capability.c b/kernel/capability.c index 493d97259484..f6c2ce5701e1 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -392,6 +392,30 @@ bool ns_capable(struct user_namespace *ns, int cap) } EXPORT_SYMBOL(ns_capable); +/** + * file_ns_capable - Determine if the file's opener had a capability in effect + * @file: The file we want to check + * @ns: The usernamespace we want the capability in + * @cap: The capability to be tested for + * + * Return true if task that opened the file had a capability in effect + * when the file was opened. + * + * This does not set PF_SUPERPRIV because the caller may not + * actually be privileged. + */ +bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) +{ + if (WARN_ON_ONCE(!cap_valid(cap))) + return false; + + if (security_capable(file->f_cred, ns, cap) == 0) + return true; + + return false; +} +EXPORT_SYMBOL(file_ns_capable); + /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for -- cgit v1.3-18-gd494