From 0ab02ca8f887908152d1a96db5130fc661d36a1e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 11 Feb 2014 16:05:46 +0800 Subject: cgroup: protect modifications to cgroup_idr with cgroup_mutex Setup cgroupfs like this: # mount -t cgroup -o cpuacct xxx /cgroup # mkdir /cgroup/sub1 # mkdir /cgroup/sub2 Then run these two commands: # for ((; ;)) { mkdir /cgroup/sub1/tmp && rmdir /mnt/sub1/tmp; } & # for ((; ;)) { mkdir /cgroup/sub2/tmp && rmdir /mnt/sub2/tmp; } & After seconds you may see this warning: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 25243 at lib/idr.c:527 sub_remove+0x87/0x1b0() idr_remove called for id=6 which is not allocated. ... Call Trace: [] dump_stack+0x7a/0x96 [] warn_slowpath_common+0x8c/0xc0 [] warn_slowpath_fmt+0x46/0x50 [] sub_remove+0x87/0x1b0 [] ? css_killed_work_fn+0x32/0x1b0 [] idr_remove+0x25/0xd0 [] cgroup_destroy_css_killed+0x5b/0xc0 [] css_killed_work_fn+0x130/0x1b0 [] process_one_work+0x26c/0x550 [] worker_thread+0x12e/0x3b0 [] kthread+0xe6/0xf0 [] ret_from_fork+0x7c/0xb0 ---[ end trace 2d1577ec10cf80d0 ]--- It's because allocating/removing cgroup ID is not properly synchronized. The bug was introduced when we converted cgroup_ida to cgroup_idr. While synchronization is already done inside ida_simple_{get,remove}(), users are responsible for concurrent calls to idr_{alloc,remove}(). tj: Refreshed on top of b58c89986a77 ("cgroup: fix error return from cgroup_create()"). Fixes: 4e96ee8e981b ("cgroup: convert cgroup_ida to cgroup_idr") Cc: #3.12+ Reported-by: Michal Hocko Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5c097596104b..9450f025fe0c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -166,6 +166,8 @@ struct cgroup { * * The ID of the root cgroup is always 0, and a new cgroup * will be assigned with a smallest available ID. + * + * Allocating/Removing ID must be protected by cgroup_mutex. */ int id; -- cgit v1.2.3 From c0b00a525c127d0055c1df6283300e17f601a1a1 Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Mon, 3 Feb 2014 15:09:12 +0530 Subject: dma-buf: update debugfs output Russell King observed 'wierd' looking output from debugfs, and also suggested better ways of getting device names (use KBUILD_MODNAME, dev_name()) This patch addresses these issues to make the debugfs output correct and better looking. While at it, replace seq_printf with seq_puts to remove the checkpatch.pl warnings. Reported-by: Russell King - ARM Linux Signed-off-by: Sumit Semwal --- drivers/base/dma-buf.c | 25 ++++++++++++------------- include/linux/dma-buf.h | 2 +- 2 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 1e16cbd61da2..61d6d62cc0d3 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -616,36 +616,35 @@ static int dma_buf_describe(struct seq_file *s) if (ret) return ret; - seq_printf(s, "\nDma-buf Objects:\n"); - seq_printf(s, "\texp_name\tsize\tflags\tmode\tcount\n"); + seq_puts(s, "\nDma-buf Objects:\n"); + seq_puts(s, "size\tflags\tmode\tcount\texp_name\n"); list_for_each_entry(buf_obj, &db_list.head, list_node) { ret = mutex_lock_interruptible(&buf_obj->lock); if (ret) { - seq_printf(s, - "\tERROR locking buffer object: skipping\n"); + seq_puts(s, + "\tERROR locking buffer object: skipping\n"); continue; } - seq_printf(s, "\t"); - - seq_printf(s, "\t%s\t%08zu\t%08x\t%08x\t%08ld\n", - buf_obj->exp_name, buf_obj->size, + seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\n", + buf_obj->size, buf_obj->file->f_flags, buf_obj->file->f_mode, - (long)(buf_obj->file->f_count.counter)); + (long)(buf_obj->file->f_count.counter), + buf_obj->exp_name); - seq_printf(s, "\t\tAttached Devices:\n"); + seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; list_for_each_entry(attach_obj, &buf_obj->attachments, node) { - seq_printf(s, "\t\t"); + seq_puts(s, "\t"); - seq_printf(s, "%s\n", attach_obj->dev->init_name); + seq_printf(s, "%s\n", dev_name(attach_obj->dev)); attach_count++; } - seq_printf(s, "\n\t\tTotal %d devices attached\n", + seq_printf(s, "Total %d devices attached\n\n", attach_count); count++; diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index dfac5ed31120..f886985a28b2 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -171,7 +171,7 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, size_t size, int flags, const char *); #define dma_buf_export(priv, ops, size, flags) \ - dma_buf_export_named(priv, ops, size, flags, __FILE__) + dma_buf_export_named(priv, ops, size, flags, KBUILD_MODNAME) int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd); -- cgit v1.2.3 From 3ce4e860e578f843db36a1f7357ba00aeaa7610f Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 13 Feb 2014 10:48:02 -0700 Subject: PCI/MSI: Add pci_enable_msi_exact() and pci_enable_msix_exact() The new functions are special cases for pci_enable_msi_range() and pci_enable_msix_range() when a particular number of MSI or MSI-X is needed. By contrast with pci_enable_msi_range() and pci_enable_msix_range() functions, pci_enable_msi_exact() and pci_enable_msix_exact() return zero in case of success, which indicates MSI or MSI-X interrupts have been successfully allocated. Signed-off-by: Alexander Gordeev Signed-off-by: Bjorn Helgaas --- Documentation/PCI/MSI-HOWTO.txt | 86 ++++++++++++++++++++++++++++++++++++++++- include/linux/pci.h | 20 ++++++++++ 2 files changed, 104 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 96ee5eb9d4d4..10a93696e55a 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -159,6 +159,11 @@ static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) return pci_enable_msi_range(pdev, nvec, nvec); } +Note, unlike pci_enable_msi_exact() function, which could be also used to +enable a particular number of MSI-X interrupts, pci_enable_msi_range() +returns either a negative errno or 'nvec' (not negative errno or 0 - as +pci_enable_msi_exact() does). + 4.2.1.3 Single MSI mode The most notorious example of the request type described above is @@ -175,7 +180,22 @@ enable the single MSI mode, pci_enable_msi_range() returns either a negative errno or 1 (not negative errno or 0 - as pci_enable_msi() does). -4.2.3 pci_disable_msi +4.2.3 pci_enable_msi_exact + +int pci_enable_msi_exact(struct pci_dev *dev, int nvec) + +This variation on pci_enable_msi_range() call allows a device driver to +request exactly 'nvec' MSIs. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to request any more MSI interrupts for +this device. + +By contrast with pci_enable_msi_range() function, pci_enable_msi_exact() +returns zero in case of success, which indicates MSI interrupts have been +successfully allocated. + +4.2.4 pci_disable_msi void pci_disable_msi(struct pci_dev *dev) @@ -303,6 +323,11 @@ static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) nvec, nvec); } +Note, unlike pci_enable_msix_exact() function, which could be also used to +enable a particular number of MSI-X interrupts, pci_enable_msix_range() +returns either a negative errno or 'nvec' (not negative errno or 0 - as +pci_enable_msix_exact() does). + 4.3.1.3 Specific requirements to the number of MSI-X interrupts As noted above, there could be devices that can not operate with just any @@ -349,7 +374,64 @@ Note how pci_enable_msix_range() return value is analized for a fallback - any error code other than -ENOSPC indicates a fatal error and should not be retried. -4.3.2 pci_disable_msix +4.3.2 pci_enable_msix_exact + +int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) + +This variation on pci_enable_msix_range() call allows a device driver to +request exactly 'nvec' MSI-Xs. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to allocate any more MSI-X interrupts for +this device. + +By contrast with pci_enable_msix_range() function, pci_enable_msix_exact() +returns zero in case of success, which indicates MSI-X interrupts have been +successfully allocated. + +Another version of a routine that enables MSI-X mode for a device with +specific requirements described in chapter 4.3.1.3 might look like this: + +/* + * Assume 'minvec' and 'maxvec' are non-zero + */ +static int foo_driver_enable_msix(struct foo_adapter *adapter, + int minvec, int maxvec) +{ + int rc; + + minvec = roundup_pow_of_two(minvec); + maxvec = rounddown_pow_of_two(maxvec); + + if (minvec > maxvec) + return -ERANGE; + +retry: + rc = pci_enable_msix_exact(adapter->pdev, + adapter->msix_entries, maxvec); + + /* + * -ENOSPC is the only error code allowed to be analyzed + */ + if (rc == -ENOSPC) { + if (maxvec == 1) + return -ENOSPC; + + maxvec /= 2; + + if (minvec > maxvec) + return -ENOSPC; + + goto retry; + } else if (rc < 0) { + return rc; + } + + return maxvec; +} + +4.3.3 pci_disable_msix void pci_disable_msix(struct pci_dev *dev) diff --git a/include/linux/pci.h b/include/linux/pci.h index fb57c892b214..33aa2caf0f0c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1169,8 +1169,23 @@ void msi_remove_pci_irq_vectors(struct pci_dev *dev); void pci_restore_msi_state(struct pci_dev *dev); int pci_msi_enabled(void); int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); +static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +{ + int rc = pci_enable_msi_range(dev, nvec, nvec); + if (rc < 0) + return rc; + return 0; +} int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec); +static inline int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ + int rc = pci_enable_msix_range(dev, entries, nvec, nvec); + if (rc < 0) + return rc; + return 0; +} #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec) @@ -1189,9 +1204,14 @@ static inline int pci_msi_enabled(void) { return 0; } static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { return -ENOSYS; } +static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +{ return -ENOSYS; } static inline int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { return -ENOSYS; } +static inline int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ return -ENOSYS; } #endif #ifdef CONFIG_PCIEPORTBUS -- cgit v1.2.3 From d206940319c41df4299db75ed56142177bb2e5f6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Feb 2014 23:09:11 +0100 Subject: net: core: introduce netif_skb_dev_features Will be used by upcoming ipv4 forward path change that needs to determine feature mask using skb->dst->dev instead of skb->dev. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- net/core/dev.c | 22 ++++++++++++---------- 2 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 440a02ee6f92..21d4e6be8949 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3068,7 +3068,12 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -netdev_features_t netif_skb_features(struct sk_buff *skb); +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev); +static inline netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + return netif_skb_dev_features(skb, skb->dev); +} static inline bool net_gso_ok(netdev_features_t features, int gso_type) { diff --git a/net/core/dev.c b/net/core/dev.c index 4ad1b78c9c77..b1b0c8d4d7df 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2420,7 +2420,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2495,34 +2495,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - netdev_features_t features) + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { + } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev) { __be16 protocol = skb->protocol; - netdev_features_t features = skb->dev->features; + netdev_features_t features = dev->features; - if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2530,9 +2532,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } -EXPORT_SYMBOL(netif_skb_features); +EXPORT_SYMBOL(netif_skb_dev_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) -- cgit v1.2.3 From fe6cc55f3a9a053482a76f5a6b2257cee51b4663 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Feb 2014 23:09:12 +0100 Subject: net: ip, ipv6: handle gso skbs in forwarding path Marcelo Ricardo Leitner reported problems when the forwarding link path has a lower mtu than the incoming one if the inbound interface supports GRO. Given: Host R1 R2 Host sends tcp stream which is routed via R1 and R2. R1 performs GRO. In this case, the kernel will fail to send ICMP fragmentation needed messages (or pkt too big for ipv6), as GSO packets currently bypass dstmtu checks in forward path. Instead, Linux tries to send out packets exceeding the mtu. When locking route MTU on Host (i.e., no ipv4 DF bit set), R1 does not fragment the packets when forwarding, and again tries to send out packets exceeding R1-R2 link mtu. This alters the forwarding dstmtu checks to take the individual gso segment lengths into account. For ipv6, we send out pkt too big error for gso if the individual segments are too big. For ipv4, we either send icmp fragmentation needed, or, if the DF bit is not set, perform software segmentation and let the output path create fragments when the packet is leaving the machine. It is not 100% correct as the error message will contain the headers of the GRO skb instead of the original/segmented one, but it seems to work fine in my (limited) tests. Eric Dumazet suggested to simply shrink mss via ->gso_size to avoid sofware segmentation. However it turns out that skb_segment() assumes skb nr_frags is related to mss size so we would BUG there. I don't want to mess with it considering Herbert and Eric disagree on what the correct behavior should be. Hannes Frederic Sowa notes that when we would shrink gso_size skb_segment would then also need to deal with the case where SKB_MAX_FRAGS would be exceeded. This uses sofware segmentation in the forward path when we hit ipv4 non-DF packets and the outgoing link mtu is too small. Its not perfect, but given the lack of bug reports wrt. GRO fwd being broken this is a rare case anyway. Also its not like this could not be improved later once the dust settles. Acked-by: Herbert Xu Reported-by: Marcelo Ricardo Leitner Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 ++++++++++++ net/ipv4/ip_forward.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++-- net/ipv6/ip6_output.c | 17 ++++++++++-- 3 files changed, 101 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..3ebbbe7b6d05 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2916,5 +2916,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e9f1217a8afd..f3869c186d97 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include #include +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + !skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (unlikely(skb->len > mtu && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26ccf81..070a2fae2375 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); -- cgit v1.2.3 From fada94ee64e6e18793b1db60fb8278d2eddbf922 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Fri, 14 Feb 2014 10:52:57 +0800 Subject: workqueue: add args to workqueue lockdep name Tommi noticed a 'funny' lock class name: "%s#5" from a lock acquired in process_one_work(). Maybe #fmt plus #args could be used as the lock_name to give some more information for some fmt string like the above. __builtin_constant_p() check is removed (as there seems no good way to check all the variables in args list). However, by removing the check, it only adds two additional "s for those constants. Some lockdep name examples printed out after the change: lockdep name wq->name "events_long" events_long "%s"("khelper") khelper "xfs-data/%s"mp->m_fsname xfs-data/dm-3 Signed-off-by: Li Zhong Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 594521ba0d43..704f4f652d0a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -419,10 +419,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, static struct lock_class_key __key; \ const char *__lock_name; \ \ - if (__builtin_constant_p(fmt)) \ - __lock_name = (fmt); \ - else \ - __lock_name = #fmt; \ + __lock_name = #fmt#args; \ \ __alloc_workqueue_key((fmt), (flags), (max_active), \ &__key, __lock_name, ##args); \ -- cgit v1.2.3 From 99932d4fc03a13bb3e94938fe25458fabc8f2fc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 16 Feb 2014 15:55:20 +0100 Subject: netdevice: add queue selection fallback handler for ndo_select_queue Add a new argument for ndo_select_queue() callback that passes a fallback handler. This gets invoked through netdev_pick_tx(); fallback handler is currently __netdev_pick_tx() as most drivers invoke this function within their customized implementation in case for skbs that don't need any special handling. This fallback handler can then be replaced on other call-sites with different queue selection methods (e.g. in packet sockets, pktgen etc). This also has the nice side-effect that __netdev_pick_tx() is then only invoked from netdev_pick_tx() and export of that function to modules can be undone. Suggested-by: David S. Miller Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 4 ++-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +++--- drivers/net/ethernet/lantiq_etop.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 4 ++-- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- drivers/net/ethernet/tile/tilegx.c | 2 +- drivers/net/team/team.c | 2 +- drivers/net/tun.c | 2 +- drivers/net/wireless/mwifiex/main.c | 2 +- drivers/staging/bcm/Bcmnet.c | 2 +- drivers/staging/netlogic/xlr_net.c | 2 +- drivers/staging/rtl8188eu/os_dep/os_intfs.c | 2 +- include/linux/netdevice.h | 9 ++++++--- net/core/flow_dissector.c | 7 +++---- net/mac80211/iface.c | 6 ++++-- 17 files changed, 31 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 867664918715..1c6104d3501d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3707,7 +3707,7 @@ static inline int bond_slave_override(struct bonding *bond, static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9d7419e0390b..66c0df78c3ff 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1873,7 +1873,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) } u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct bnx2x *bp = netdev_priv(dev); @@ -1895,7 +1895,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); + return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index bfc58d488bb5..a89a40f88c25 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -496,7 +496,7 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6d4ada72dfd0..18076c4178b4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6881,7 +6881,7 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) } static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; #ifdef IXGBE_FCOE @@ -6907,7 +6907,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) break; default: - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); } f = &adapter->ring_feature[RING_F_FCOE]; @@ -6920,7 +6920,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, return txq + f->offset; #else - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); #endif } diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 8f9266c64c75..fd4b6aecf6ee 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -619,7 +619,7 @@ ltq_etop_set_multicast_list(struct net_device *dev) static u16 ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* we are currently only using the first queue */ return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8e8a7eb43a2c..13457032d15f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -629,7 +629,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk } u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; @@ -641,7 +641,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, if (vlan_tx_tag_present(skb)) up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT; - return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up; + return fallback(dev, skb) % rings_p_up + up * rings_p_up; } static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 3af04c3f42ea..9ca223bc90fc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -723,7 +723,7 @@ int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 023237a65720..17503da9f7a5 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -2071,7 +2071,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) /* Return subqueue id on this core (one per core). */ static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return smp_processor_id(); } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 28407426fd6f..c8624a8235ab 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1648,7 +1648,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 44c4db8450f0..8fe9cb7d0f72 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -366,7 +366,7 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) * hope the rxq no. may help here. */ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index 4d79761b9c87..9d3d2758ec35 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -748,7 +748,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) static u16 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c index 8dfdd2732bdc..95a2358267ba 100644 --- a/drivers/staging/bcm/Bcmnet.c +++ b/drivers/staging/bcm/Bcmnet.c @@ -40,7 +40,7 @@ static INT bcm_close(struct net_device *dev) } static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return ClassifyPacket(netdev_priv(dev), skb); } diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c index eedffed17e39..6f9ac27730af 100644 --- a/drivers/staging/netlogic/xlr_net.c +++ b/drivers/staging/netlogic/xlr_net.c @@ -307,7 +307,7 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, } static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return (u16)smp_processor_id(); } diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index 68f98fa114d2..7c9ee58f47bb 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -653,7 +653,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 21d4e6be8949..1de9c136b066 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -752,6 +752,9 @@ struct netdev_phys_port_id { unsigned char id_len; }; +typedef u16 (*select_queue_fallback_t)(struct net_device *dev, + struct sk_buff *skb); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -783,7 +786,7 @@ struct netdev_phys_port_id { * Required can not be NULL. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv); + * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -1005,7 +1008,8 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, + select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1551,7 +1555,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 87577d447554..75fe83f590ea 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -372,7 +372,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -392,7 +392,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } -EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, @@ -403,8 +402,8 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, - accel_priv); + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); else queue_index = __netdev_pick_tx(dev, skb); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d6d1f1df9119..ce1c44370610 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1057,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1075,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; -- cgit v1.2.3 From b9507bdaf40e91fea2b1c0c1ee7dc627c8ee6fd6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 16 Feb 2014 15:55:21 +0100 Subject: netdevice: move netdev_cap_txqueue for shared usage to header In order to allow users to invoke netdev_cap_txqueue, it needs to be moved into netdevice.h header file. While at it, also add kernel doc header to document the API. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ net/core/flow_dissector.c | 13 +------------ 2 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1de9c136b066..e8eeebd49a98 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2278,6 +2278,26 @@ static inline void netdev_reset_queue(struct net_device *dev_queue) netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); } +/** + * netdev_cap_txqueue - check if selected tx queue exceeds device queues + * @dev: network device + * @queue_index: given tx queue index + * + * Returns 0 if given tx queue index >= number of device tx queues, + * otherwise returns the originally passed tx queue index. + */ +static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + + return queue_index; +} + /** * netif_running - test if up * @dev: network device diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 75fe83f590ea..e29e810663d7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb) return poff; } -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -408,7 +397,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, queue_index = __netdev_pick_tx(dev, skb); if (!accel_priv) - queue_index = dev_cap_txqueue(dev, queue_index); + queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); -- cgit v1.2.3 From bcdfeb2eb4e42b811950b9cd226109291051732a Mon Sep 17 00:00:00 2001 From: Yan, Zheng Date: Tue, 11 Feb 2014 13:04:19 +0800 Subject: ceph: remove xattr when null value is given to setxattr() For the setxattr request, introduce a new flag CEPH_XATTR_REMOVE to distinguish null value case from the zero-length value case. Signed-off-by: Yan, Zheng --- fs/ceph/xattr.c | 16 ++++++++++++++-- include/linux/ceph/ceph_fs.h | 5 +++-- 2 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 28f9793b9167..231c02b16c0c 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -12,6 +12,9 @@ #define XATTR_CEPH_PREFIX "ceph." #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1) +static int __remove_xattr(struct ceph_inode_info *ci, + struct ceph_inode_xattr *xattr); + /* * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. @@ -359,6 +362,12 @@ static int __set_xattr(struct ceph_inode_info *ci, kfree(val); return err; } + if (update_xattr < 0) { + if (xattr) + __remove_xattr(ci, xattr); + kfree(name); + return 0; + } } if (!xattr) { @@ -862,6 +871,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name, dout("setxattr value=%.*s\n", (int)size, value); + if (!value) + flags |= CEPH_XATTR_REMOVE; + /* do request */ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR, USE_AUTH_MDS); @@ -965,8 +977,8 @@ retry: goto retry; } - err = __set_xattr(ci, newname, name_len, newval, - val_len, flags, 1, &xattr); + err = __set_xattr(ci, newname, name_len, newval, val_len, + flags, value ? 1 : -1, &xattr); if (!err) { dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 2623cffc73a1..25bfb0eff772 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -373,8 +373,9 @@ extern const char *ceph_mds_op_name(int op); /* * Ceph setxattr request flags. */ -#define CEPH_XATTR_CREATE 1 -#define CEPH_XATTR_REPLACE 2 +#define CEPH_XATTR_CREATE (1 << 0) +#define CEPH_XATTR_REPLACE (1 << 1) +#define CEPH_XATTR_REMOVE (1 << 31) union ceph_mds_request_args { struct { -- cgit v1.2.3 From 45a22f4c11fef4ecd5c61c0a299cd3f23d77be8e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Feb 2014 13:09:50 +0100 Subject: inotify: Fix reporting of cookies for inotify events My rework of handling of notification events (namely commit 7053aee26a35 "fsnotify: do not share events between notification groups") broke sending of cookies with inotify events. We didn't propagate the value passed to fsnotify() properly and passed 4 uninitialized bytes to userspace instead (so it is also an information leak). Sadly I didn't notice this during my testing because inotify cookies aren't used very much and LTP inotify tests ignore them. Fix the problem by passing the cookie value properly. Fixes: 7053aee26a3548ebaba046ae2e52396ccf56ac6c Reported-by: Vegard Nossum Signed-off-by: Jan Kara --- fs/notify/dnotify/dnotify.c | 2 +- fs/notify/fanotify/fanotify.c | 2 +- fs/notify/fsnotify.c | 2 +- fs/notify/inotify/inotify.h | 2 +- fs/notify/inotify/inotify_fsnotify.c | 3 ++- fs/notify/inotify/inotify_user.c | 2 +- include/linux/fsnotify_backend.h | 2 +- kernel/audit_tree.c | 2 +- kernel/audit_watch.c | 2 +- 9 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 0b9ff4395e6a..abc8cbcfe90e 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 0e792f5e3147..205dc2163822 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -147,7 +147,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *fanotify_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { int ret = 0; struct fanotify_event_info *event; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 1d4e1ea2f37c..9d3e9c50066a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell, return group->ops->handle_event(group, to_tell, inode_mark, vfsmount_mark, mask, data, data_is, - file_name); + file_name, cookie); } /* diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 485eef3f4407..ed855ef6f077 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name); + const unsigned char *file_name, u32 cookie); extern const struct fsnotify_ops inotify_fsnotify_ops; diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index d5ee56348bb8..43ab1e1a07a2 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -67,7 +67,7 @@ int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { struct inotify_inode_mark *i_mark; struct inotify_event_info *event; @@ -103,6 +103,7 @@ int inotify_handle_event(struct fsnotify_group *group, fsn_event = &event->fse; fsnotify_init_event(fsn_event, inode, mask); event->wd = i_mark->wd; + event->sync_cookie = cookie; event->name_len = len; if (len) strcpy(event->name, file_name); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 497395c8274b..6528b5a54ca0 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, /* Queue ignore event for the watch */ inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED, - NULL, FSNOTIFY_EVENT_NONE, NULL); + NULL, FSNOTIFY_EVENT_NONE, NULL, 0); i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); /* remove this mark from the idr */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3d286ff49ab0..c84bc7c2bfc8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -99,7 +99,7 @@ struct fsnotify_ops { struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name); + const unsigned char *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_event *event); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 67ccf0e7cca9..135944a7b28a 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -916,7 +916,7 @@ static int audit_tree_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { return 0; } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2596fac5dcb4..70b4554d2fbe 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -471,7 +471,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *dname) + const unsigned char *dname, u32 cookie) { struct inode *inode; struct audit_parent *parent; -- cgit v1.2.3 From 05fb7a56ad65ceaa1907bb9c66bfa1108847667f Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 23 Jan 2014 14:35:28 +0000 Subject: mfd: max8997: Naturalise cross-architecture discrepancies If we compile the MAX8997 for a 64bit architecture we receive the following warnings: drivers/mfd/max8997.c: In function ‘max8997_i2c_get_driver_data’: drivers/mfd/max8997.c:173:10: warning: cast from pointer to integer of different size return (int)match->data; ^ Signed-off-by: Lee Jones --- drivers/mfd/max8997.c | 6 +++--- include/linux/mfd/max8997-private.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index be88a3bf7b85..5adede0fb04c 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -164,15 +164,15 @@ static struct max8997_platform_data *max8997_i2c_parse_dt_pdata( return pd; } -static inline int max8997_i2c_get_driver_data(struct i2c_client *i2c, +static inline unsigned long max8997_i2c_get_driver_data(struct i2c_client *i2c, const struct i2c_device_id *id) { if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) { const struct of_device_id *match; match = of_match_node(max8997_pmic_dt_match, i2c->dev.of_node); - return (int)match->data; + return (unsigned long)match->data; } - return (int)id->driver_data; + return id->driver_data; } static int max8997_i2c_probe(struct i2c_client *i2c, diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h index ad1ae7f345ad..78c76cd4d37b 100644 --- a/include/linux/mfd/max8997-private.h +++ b/include/linux/mfd/max8997-private.h @@ -387,7 +387,7 @@ struct max8997_dev { struct i2c_client *muic; /* slave addr 0x4a */ struct mutex iolock; - int type; + unsigned long type; struct platform_device *battery; /* battery control (not fuel gauge) */ int irq; -- cgit v1.2.3 From 8bace2d5b4baa0f60b6094b53aeb79515ec94e4a Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 3 Feb 2014 08:22:30 +0000 Subject: mfd: max8998: Naturalise cross-architecture discrepancies If we compile the MAX8998 for a 64bit architecture we receive the following warnings: drivers/mfd/max8998.c: In function ‘max8998_i2c_get_driver_data’: drivers/mfd/max8998.c:178:10: warning: cast from pointer to integer of different size return (int)match->data; ^ Signed-off-by: Lee Jones --- drivers/mfd/max8998.c | 6 +++--- include/linux/mfd/max8998-private.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c index 612ca404e150..5d5e186b5d8b 100644 --- a/drivers/mfd/max8998.c +++ b/drivers/mfd/max8998.c @@ -169,16 +169,16 @@ static struct max8998_platform_data *max8998_i2c_parse_dt_pdata( return pd; } -static inline int max8998_i2c_get_driver_data(struct i2c_client *i2c, +static inline unsigned long max8998_i2c_get_driver_data(struct i2c_client *i2c, const struct i2c_device_id *id) { if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) { const struct of_device_id *match; match = of_match_node(max8998_dt_match, i2c->dev.of_node); - return (int)(long)match->data; + return (unsigned long)match->data; } - return (int)id->driver_data; + return id->driver_data; } static int max8998_i2c_probe(struct i2c_client *i2c, diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h index 4ecb24b4b863..d68ada502ff3 100644 --- a/include/linux/mfd/max8998-private.h +++ b/include/linux/mfd/max8998-private.h @@ -163,7 +163,7 @@ struct max8998_dev { int ono; u8 irq_masks_cur[MAX8998_NUM_IRQ_REGS]; u8 irq_masks_cache[MAX8998_NUM_IRQ_REGS]; - int type; + unsigned long type; bool wakeup; }; -- cgit v1.2.3 From 5c6fbd56d16f38fddec629e1dccdeee5ad7f5a42 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 3 Feb 2014 08:24:20 +0000 Subject: mfd: tps65217: Naturalise cross-architecture discrepancies If we compile the TPS65217 for a 64bit architecture we receive the following warnings: drivers/mfd/tps65217.c: In function ‘tps65217_probe’: drivers/mfd/tps65217.c:173:13: warning: cast from pointer to integer of different size chip_id = (unsigned int)match->data; ^ Signed-off-by: Lee Jones --- drivers/mfd/tps65217.c | 4 ++-- include/linux/mfd/tps65217.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c index 966cf65c5c36..3cc4c7084b92 100644 --- a/drivers/mfd/tps65217.c +++ b/drivers/mfd/tps65217.c @@ -158,7 +158,7 @@ static int tps65217_probe(struct i2c_client *client, { struct tps65217 *tps; unsigned int version; - unsigned int chip_id = ids->driver_data; + unsigned long chip_id = ids->driver_data; const struct of_device_id *match; bool status_off = false; int ret; @@ -170,7 +170,7 @@ static int tps65217_probe(struct i2c_client *client, "Failed to find matching dt id\n"); return -EINVAL; } - chip_id = (unsigned int)(unsigned long)match->data; + chip_id = (unsigned long)match->data; status_off = of_property_read_bool(client->dev.of_node, "ti,pmic-shutdown-controller"); } diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index a5a7f0130e96..54b5458ec084 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -252,7 +252,7 @@ struct tps65217_board { struct tps65217 { struct device *dev; struct tps65217_board *pdata; - unsigned int id; + unsigned long id; struct regulator_desc desc[TPS65217_NUM_REGULATOR]; struct regulator_dev *rdev[TPS65217_NUM_REGULATOR]; struct regmap *regmap; @@ -263,7 +263,7 @@ static inline struct tps65217 *dev_to_tps65217(struct device *dev) return dev_get_drvdata(dev); } -static inline int tps65217_chip_id(struct tps65217 *tps65217) +static inline unsigned long tps65217_chip_id(struct tps65217 *tps65217) { return tps65217->id; } -- cgit v1.2.3 From 6d35ab48090b10c5ea5604ed5d6e91f302dc6060 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 14 Feb 2014 17:19:29 +0100 Subject: sched: Add 'flags' argument to sched_{set,get}attr() syscalls Because of a recent syscall design debate; its deemed appropriate for each syscall to have a flags argument for future extension; without immediately requiring new syscalls. Cc: juri.lelli@gmail.com Cc: Ingo Molnar Suggested-by: Michael Kerrisk Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140214161929.GL27965@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner --- include/linux/syscalls.h | 6 ++++-- kernel/sched/core.c | 11 ++++++----- 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 40ed9e9a77e5..a747a77ea584 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -281,13 +281,15 @@ asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param); asmlinkage long sys_sched_setattr(pid_t pid, - struct sched_attr __user *attr); + struct sched_attr __user *attr, + unsigned int flags); asmlinkage long sys_sched_getscheduler(pid_t pid); asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param); asmlinkage long sys_sched_getattr(pid_t pid, struct sched_attr __user *attr, - unsigned int size); + unsigned int size, + unsigned int flags); asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr); asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a6e7470166c7..6edbef296ece 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3661,13 +3661,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) * @pid: the pid in question. * @uattr: structure containing the extended parameters. */ -SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr) +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) { struct sched_attr attr; struct task_struct *p; int retval; - if (!uattr || pid < 0) + if (!uattr || pid < 0 || flags) return -EINVAL; if (sched_copy_attr(uattr, &attr)) @@ -3804,8 +3805,8 @@ err_size: * @uattr: structure containing the extended parameters. * @size: sizeof(attr) for fwd/bwd comp. */ -SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, size) +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) { struct sched_attr attr = { .size = sizeof(struct sched_attr), @@ -3814,7 +3815,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, int retval; if (!uattr || pid < 0 || size > PAGE_SIZE || - size < SCHED_ATTR_SIZE_VER0) + size < SCHED_ATTR_SIZE_VER0 || flags) return -EINVAL; rcu_read_lock(); -- cgit v1.2.3 From 0dc83bd30b0bf5410c0933cfbbf8853248eff0a9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 21 Feb 2014 11:19:04 +0100 Subject: Revert "writeback: do not sync data dirtied after sync start" This reverts commit c4a391b53a72d2df4ee97f96f78c1d5971b47489. Dave Chinner has reported the commit may cause some inodes to be left out from sync(2). This is because we can call redirty_tail() for some inode (which sets i_dirtied_when to current time) after sync(2) has started or similarly requeue_inode() can set i_dirtied_when to current time if writeback had to skip some pages. The real problem is in the functions clobbering i_dirtied_when but fixing that isn't trivial so revert is a safer choice for now. CC: stable@vger.kernel.org # >= 3.13 Signed-off-by: Jan Kara --- fs/fs-writeback.c | 33 +++++++++++---------------------- fs/sync.c | 15 ++++++--------- fs/xfs/xfs_super.c | 2 +- include/linux/writeback.h | 2 +- include/trace/events/writeback.h | 6 +++--- 5 files changed, 22 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e0259a163f98..d754e3cf99a8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -40,18 +40,13 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - /* - * Write only inodes dirtied before this time. Don't forget to set - * older_than_this_is_set when you set this. - */ - unsigned long older_than_this; + unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ - unsigned int older_than_this_is_set:1; enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ @@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - WARN_ON_ONCE(!work->older_than_this_is_set); while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (inode_dirtied_after(inode, work->older_than_this)) + if (work->older_than_this && + inode_dirtied_after(inode, *work->older_than_this)) break; list_move(&inode->i_wb_list, &tmp); moved++; @@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, - .older_than_this = jiffies, - .older_than_this_is_set = 1, }; spin_lock(&wb->list_lock); @@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; + unsigned long oldest_jif; struct inode *inode; long progress; - if (!work->older_than_this_is_set) { - work->older_than_this = jiffies; - work->older_than_this_is_set = 1; - } + oldest_jif = jiffies; + work->older_than_this = &oldest_jif; spin_lock(&wb->list_lock); for (;;) { @@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - work->older_than_this = jiffies - + oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - work->older_than_this = jiffies; + oldest_jif = jiffies; trace_writeback_start(wb->bdi, work); if (list_empty(&wb->b_io)) @@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages - * @sb: the superblock - * @older_than_this: timestamp + * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this - * superblock that has been dirtied before given timestamp. + * super_block. */ -void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this) +void sync_inodes_sb(struct super_block *sb) { DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, - .older_than_this = older_than_this, - .older_than_this_is_set = 1, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, diff --git a/fs/sync.c b/fs/sync.c index e8ba024a055b..b28d1dd10e8b 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -27,11 +27,10 @@ * wait == 1 case since in that case write_inode() functions do * sync_dirty_buffer() and thus effectively write one block at a time. */ -static int __sync_filesystem(struct super_block *sb, int wait, - unsigned long start) +static int __sync_filesystem(struct super_block *sb, int wait) { if (wait) - sync_inodes_sb(sb, start); + sync_inodes_sb(sb); else writeback_inodes_sb(sb, WB_REASON_SYNC); @@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait, int sync_filesystem(struct super_block *sb) { int ret; - unsigned long start = jiffies; /* * We need to be protected against the filesystem going from @@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return 0; - ret = __sync_filesystem(sb, 0, start); + ret = __sync_filesystem(sb, 0); if (ret < 0) return ret; - return __sync_filesystem(sb, 1, start); + return __sync_filesystem(sb, 1); } EXPORT_SYMBOL_GPL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!(sb->s_flags & MS_RDONLY)) - sync_inodes_sb(sb, *((unsigned long *)arg)); + sync_inodes_sb(sb); } static void sync_fs_one_sb(struct super_block *sb, void *arg) @@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg) SYSCALL_DEFINE0(sync) { int nowait = 0, wait = 1; - unsigned long start = jiffies; wakeup_flusher_threads(0, WB_REASON_SYNC); - iterate_supers(sync_inodes_one_sb, &start); + iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); iterate_bdevs(fdatawrite_one_bdev, NULL); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f317488263dd..d971f4932b5d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -913,7 +913,7 @@ xfs_flush_inodes( struct super_block *sb = mp->m_super; if (down_read_trylock(&sb->s_umount)) { - sync_inodes_sb(sb, jiffies); + sync_inodes_sb(sb); up_read(&sb->s_umount); } } diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fc0e4320aa6d..021b8a319b9e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -97,7 +97,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this); +void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index c7bbbe794e65..464ea82e10db 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -287,11 +287,11 @@ TRACE_EVENT(writeback_queue_io, __field(int, reason) ), TP_fast_assign( - unsigned long older_than_this = work->older_than_this; + unsigned long *older_than_this = work->older_than_this; strncpy(__entry->name, dev_name(wb->bdi->dev), 32); - __entry->older = older_than_this; + __entry->older = older_than_this ? *older_than_this : 0; __entry->age = older_than_this ? - (jiffies - older_than_this) * 1000 / HZ : -1; + (jiffies - *older_than_this) * 1000 / HZ : -1; __entry->moved = moved; __entry->reason = work->reason; ), -- cgit v1.2.3 From ff57cd5863cf3014c1c5ed62ce2715294f065b17 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 21 Feb 2014 19:14:11 +0100 Subject: fsnotify: Allocate overflow events with proper type Commit 7053aee26a35 "fsnotify: do not share events between notification groups" used overflow event statically allocated in a group with the size of the generic notification event. This causes problems because some code looks at type specific parts of event structure and gets confused by a random data it sees there and causes crashes. Fix the problem by allocating overflow event with type corresponding to the group type so code cannot get confused. Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 13 +++++++++++++ fs/notify/group.c | 8 +++++++- fs/notify/inotify/inotify_user.c | 12 ++++++++++++ fs/notify/notification.c | 4 ++-- include/linux/fsnotify_backend.h | 2 +- 5 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index b6175fa11bf8..287a22c04149 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -698,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) struct fsnotify_group *group; int f_flags, fd; struct user_struct *user; + struct fanotify_event_info *oevent; pr_debug("%s: flags=%d event_f_flags=%d\n", __func__, flags, event_f_flags); @@ -730,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user; atomic_inc(&user->fanotify_listeners); + oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL); + if (unlikely(!oevent)) { + fd = -ENOMEM; + goto out_destroy_group; + } + group->overflow_event = &oevent->fse; + fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + oevent->tgid = get_pid(task_tgid(current)); + oevent->path.mnt = NULL; + oevent->path.dentry = NULL; + group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + oevent->response = 0; mutex_init(&group->fanotify_data.access_mutex); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); diff --git a/fs/notify/group.c b/fs/notify/group.c index ee674fe2cec7..ad1995980456 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group) /* clear the notification queue of all events */ fsnotify_flush_notify(group); + /* + * Destroy overflow event (we cannot use fsnotify_destroy_event() as + * that deliberately ignores overflow events. + */ + if (group->overflow_event) + group->ops->free_event(group->overflow_event); + fsnotify_put_group(group); } @@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) INIT_LIST_HEAD(&group->marks_list); group->ops = ops; - fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW); return group; } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 6528b5a54ca0..78a2ca3966c3 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod static struct fsnotify_group *inotify_new_group(unsigned int max_events) { struct fsnotify_group *group; + struct inotify_event_info *oevent; group = fsnotify_alloc_group(&inotify_fsnotify_ops); if (IS_ERR(group)) return group; + oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL); + if (unlikely(!oevent)) { + fsnotify_destroy_group(group); + return ERR_PTR(-ENOMEM); + } + group->overflow_event = &oevent->fse; + fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + oevent->wd = -1; + oevent->sync_cookie = 0; + oevent->name_len = 0; + group->max_events = max_events; spin_lock_init(&group->inotify_data.idr_lock); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 6a4ba17c0395..1e58402171a5 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -98,11 +98,11 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ - if (!list_empty(&group->overflow_event.list)) { + if (!list_empty(&group->overflow_event->list)) { mutex_unlock(&group->notification_mutex); return ret; } - event = &group->overflow_event; + event = group->overflow_event; goto queue; } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index c84bc7c2bfc8..64cf3ef50696 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -160,7 +160,7 @@ struct fsnotify_group { struct fasync_struct *fsn_fa; /* async notification */ - struct fsnotify_event overflow_event; /* Event we queue when the + struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ -- cgit v1.2.3 From fed95bab8d29b928fcf6225be72d37ded452e8a2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 25 Feb 2014 19:28:44 +0800 Subject: sysfs: fix namespace refcnt leak As mount() and kill_sb() is not a one-to-one match, we shoudn't get ns refcnt unconditionally in sysfs_mount(), and instead we should get the refcnt only when kernfs_mount() allocated a new superblock. v2: - Changed the name of the new argument, suggested by Tejun. - Made the argument optional, suggested by Tejun. v3: - Make the new argument as second-to-last arg, suggested by Tejun. Signed-off-by: Li Zefan Acked-by: Tejun Heo --- fs/kernfs/mount.c | 8 +++++++- fs/sysfs/mount.c | 5 +++-- include/linux/kernfs.h | 9 +++++---- 3 files changed, 15 insertions(+), 7 deletions(-) Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/mount.c | 8 +++++++- fs/sysfs/mount.c | 5 +++-- include/linux/kernfs.h | 9 +++++---- 3 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 0d6ce895a9ee..0f4152defe7b 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -94,6 +94,7 @@ const void *kernfs_super_ns(struct super_block *sb) * @fs_type: file_system_type of the fs being mounted * @flags: mount flags specified for the mount * @root: kernfs_root of the hierarchy being mounted + * @new_sb_created: tell the caller if we allocated a new superblock * @ns: optional namespace tag of the mount * * This is to be called from each kernfs user's file_system_type->mount() @@ -104,7 +105,8 @@ const void *kernfs_super_ns(struct super_block *sb) * The return value can be passed to the vfs layer verbatim. */ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns) + struct kernfs_root *root, bool *new_sb_created, + const void *ns) { struct super_block *sb; struct kernfs_super_info *info; @@ -122,6 +124,10 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, kfree(info); if (IS_ERR(sb)) return ERR_CAST(sb); + + if (new_sb_created) + *new_sb_created = !sb->s_root; + if (!sb->s_root) { error = kernfs_fill_super(sb); if (error) { diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 6211230814fd..3eaf5c6622eb 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, { struct dentry *root; void *ns; + bool new_sb; if (!(flags & MS_KERNMOUNT)) { if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) @@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, } ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); - root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns); - if (IS_ERR(root)) + root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns); + if (IS_ERR(root) || !new_sb) kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); return root; } diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5be9f0228a3b..d267623c28cf 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -249,7 +249,8 @@ void kernfs_notify(struct kernfs_node *kn); const void *kernfs_super_ns(struct super_block *sb); struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns); + struct kernfs_root *root, bool *new_sb_created, + const void *ns); void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); @@ -317,7 +318,7 @@ static inline const void *kernfs_super_ns(struct super_block *sb) static inline struct dentry * kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns) + struct kernfs_root *root, bool *new_sb_created, const void *ns) { return ERR_PTR(-ENOSYS); } static inline void kernfs_kill_sb(struct super_block *sb) { } @@ -368,9 +369,9 @@ static inline int kernfs_remove_by_name(struct kernfs_node *parent, static inline struct dentry * kernfs_mount(struct file_system_type *fs_type, int flags, - struct kernfs_root *root) + struct kernfs_root *root, bool *new_sb_created) { - return kernfs_mount_ns(fs_type, flags, root, NULL); + return kernfs_mount_ns(fs_type, flags, root, new_sb_created, NULL); } #endif /* __LINUX_KERNFS_H */ -- cgit v1.2.3 From f3713fd9cff733d9df83116422d8e4af6e86b2bb Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 25 Feb 2014 15:01:45 -0800 Subject: ipc,mqueue: remove limits for the amount of system-wide queues Commit 93e6f119c0ce ("ipc/mqueue: cleanup definition names and locations") added global hardcoded limits to the amount of message queues that can be created. While these limits are per-namespace, reality is that it ends up breaking userspace applications. Historically users have, at least in theory, been able to create up to INT_MAX queues, and limiting it to just 1024 is way too low and dramatic for some workloads and use cases. For instance, Madars reports: "This update imposes bad limits on our multi-process application. As our app uses approaches that each process opens its own set of queues (usually something about 3-5 queues per process). In some scenarios we might run up to 3000 processes or more (which of-course for linux is not a problem). Thus we might need up to 9000 queues or more. All processes run under one user." Other affected users can be found in launchpad bug #1155695: https://bugs.launchpad.net/ubuntu/+source/manpages/+bug/1155695 Instead of increasing this limit, revert it entirely and fallback to the original way of dealing queue limits -- where once a user's resource limit is reached, and all memory is used, new queues cannot be created. Signed-off-by: Davidlohr Bueso Reported-by: Madars Vitolins Acked-by: Doug Ledford Cc: Manfred Spraul Cc: [3.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 -- ipc/mq_sysctl.c | 18 ++++++++++++------ ipc/mqueue.c | 6 +++--- 3 files changed, 15 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e7831d203737..35e7eca4e33b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -118,9 +118,7 @@ extern int mq_init_ns(struct ipc_namespace *ns); * the new maximum will handle anyone else. I may have to revisit this * in the future. */ -#define MIN_QUEUESMAX 1 #define DFLT_QUEUESMAX 256 -#define HARD_QUEUESMAX 1024 #define MIN_MSGMAX 1 #define DFLT_MSG 10U #define DFLT_MSGMAX 10 diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 383d638340b8..5bb8bfe67149 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -22,6 +22,16 @@ static void *get_mq(ctl_table *table) return which; } +static int proc_mq_dointvec(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table mq_table; + memcpy(&mq_table, table, sizeof(mq_table)); + mq_table.data = get_mq(table); + + return proc_dointvec(&mq_table, write, buffer, lenp, ppos); +} + static int proc_mq_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -33,12 +43,10 @@ static int proc_mq_dointvec_minmax(ctl_table *table, int write, lenp, ppos); } #else +#define proc_mq_dointvec NULL #define proc_mq_dointvec_minmax NULL #endif -static int msg_queues_limit_min = MIN_QUEUESMAX; -static int msg_queues_limit_max = HARD_QUEUESMAX; - static int msg_max_limit_min = MIN_MSGMAX; static int msg_max_limit_max = HARD_MSGMAX; @@ -51,9 +59,7 @@ static ctl_table mq_sysctls[] = { .data = &init_ipc_ns.mq_queues_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_mq_dointvec_minmax, - .extra1 = &msg_queues_limit_min, - .extra2 = &msg_queues_limit_max, + .proc_handler = proc_mq_dointvec, }, { .procname = "msg_max", diff --git a/ipc/mqueue.c b/ipc/mqueue.c index ccf1f9fd263a..c3b31179122c 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -433,9 +433,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry, error = -EACCES; goto out_unlock; } - if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX || - (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && - !capable(CAP_SYS_RESOURCE))) { + + if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && + !capable(CAP_SYS_RESOURCE)) { error = -ENOSPC; goto out_unlock; } -- cgit v1.2.3 From 6fe50a28ba6e5fafb4a549dea666dd15297dd8bd Mon Sep 17 00:00:00 2001 From: David A. Long Date: Mon, 3 Feb 2014 14:25:49 -0500 Subject: uprobes: allow ignoring of probe hits Allow arches to decided to ignore a probe hit. ARM will use this to only call handlers if the conditions to execute a conditionally executed instruction are satisfied. Signed-off-by: David A. Long Acked-by: Oleg Nesterov --- include/linux/uprobes.h | 1 + kernel/events/uprobes.c | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index e32251e00e62..edff2b97b864 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -126,6 +126,7 @@ extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); +extern bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs); #else /* !CONFIG_UPROBES */ struct uprobes_state { }; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 307d87c0991a..04709b66369d 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1804,6 +1804,11 @@ static bool handle_trampoline(struct pt_regs *regs) return true; } +bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs) +{ + return false; +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. @@ -1858,7 +1863,11 @@ static void handle_swbp(struct pt_regs *regs) if (!get_utask()) goto out; + if (arch_uprobe_ignore(&uprobe->arch, regs)) + goto out; + handler_chain(uprobe, regs); + if (can_skip_sstep(uprobe, regs)) goto out; -- cgit v1.2.3