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') 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 857aea1c5769386b1905bb38fbb4464c800b2df6 Mon Sep 17 00:00:00 2001 From: Charmaine Lee Date: Wed, 12 Feb 2014 12:07:38 +0100 Subject: drm/vmwgfx: Get maximum mob size from register SVGA_REG_MOB_MAX_SIZE This patch queries the register SVGA_REG_MOB_MAX_SIZE for the maximum size of a single mob. Signed-off-by: Charmaine Lee Reviewed-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/svga_reg.h | 9 ++++++++- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 3 +++ drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 1 + drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c | 3 +++ include/uapi/drm/vmwgfx_drm.h | 1 + 5 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/vmwgfx/svga_reg.h b/drivers/gpu/drm/vmwgfx/svga_reg.h index 71defa4d2d75..11323dd5196f 100644 --- a/drivers/gpu/drm/vmwgfx/svga_reg.h +++ b/drivers/gpu/drm/vmwgfx/svga_reg.h @@ -169,10 +169,17 @@ enum { SVGA_REG_TRACES = 45, /* Enable trace-based updates even when FIFO is on */ SVGA_REG_GMRS_MAX_PAGES = 46, /* Maximum number of 4KB pages for all GMRs */ SVGA_REG_MEMORY_SIZE = 47, /* Total dedicated device memory excluding FIFO */ + SVGA_REG_COMMAND_LOW = 48, /* Lower 32 bits and submits commands */ + SVGA_REG_COMMAND_HIGH = 49, /* Upper 32 bits of command buffer PA */ SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50, /* Max primary memory */ SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Suggested limit on mob mem */ SVGA_REG_DEV_CAP = 52, /* Write dev cap index, read value */ - SVGA_REG_TOP = 53, /* Must be 1 more than the last register */ + SVGA_REG_CMD_PREPEND_LOW = 53, + SVGA_REG_CMD_PREPEND_HIGH = 54, + SVGA_REG_SCREENTARGET_MAX_WIDTH = 55, + SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56, + SVGA_REG_MOB_MAX_SIZE = 57, + SVGA_REG_TOP = 58, /* Must be 1 more than the last register */ SVGA_PALETTE_BASE = 1024, /* Base of SVGA color map */ /* Next 768 (== 256*3) registers exist for colormap */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 3bdc0adc656d..0083cbf99edf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -667,6 +667,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->memory_size = 512*1024*1024; } dev_priv->max_mob_pages = 0; + dev_priv->max_mob_size = 0; if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { uint64_t mem_size = vmw_read(dev_priv, @@ -676,6 +677,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->prim_bb_mem = vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM); + dev_priv->max_mob_size = + vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE); } else dev_priv->prim_bb_mem = dev_priv->vram_size; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index ecaa302a6154..9e4be1725985 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -386,6 +386,7 @@ struct vmw_private { uint32_t max_gmr_ids; uint32_t max_gmr_pages; uint32_t max_mob_pages; + uint32_t max_mob_size; uint32_t memory_size; bool has_gmr; bool has_mob; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index f9881f9e62bd..47b70949bf3a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -102,6 +102,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, vmw_fp->gb_aware = true; param->value = dev_priv->max_mob_pages * PAGE_SIZE; break; + case DRM_VMW_PARAM_MAX_MOB_SIZE: + param->value = dev_priv->max_mob_size; + break; default: DRM_ERROR("Illegal vmwgfx get param request: %d\n", param->param); diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 9971c560ed9a..87792a5fee3b 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -87,6 +87,7 @@ #define DRM_VMW_PARAM_MAX_SURF_MEMORY 7 #define DRM_VMW_PARAM_3D_CAPS_SIZE 8 #define DRM_VMW_PARAM_MAX_MOB_MEMORY 9 +#define DRM_VMW_PARAM_MAX_MOB_SIZE 10 /** * struct drm_vmw_getparam_arg -- 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') 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') 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') 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') 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') 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 56eecdb912b536a4fa97fb5bfe5a940a54d79be6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:38 +0530 Subject: mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit Archs like ppc64 doesn't do tlb flush in set_pte/pmd functions when using a hash table MMU for various reasons (the flush is handled as part of the PTE modification when necessary). ppc64 thus doesn't implement flush_tlb_range for hash based MMUs. Additionally ppc64 require the tlb flushing to be batched within ptl locks. The reason to do that is to ensure that the hash page table is in sync with linux page table. We track the hpte index in linux pte and if we clear them without flushing hash and drop the ptl lock, we can have another cpu update the pte and can end up with duplicate entry in the hash table, which is fatal. We also want to keep set_pte_at simpler by not requiring them to do hash flush for performance reason. We do that by assuming that set_pte_at() is never *ever* called on a PTE that is already valid. This was the case until the NUMA code went in which broke that assumption. Fix that by introducing a new pair of helpers to set _PAGE_NUMA in a way similar to ptep/pmdp_set_wrprotect(), with a generic implementation using set_pte_at() and a powerpc specific one using the appropriate mechanism needed to keep the hash table in sync. Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgtable.h | 22 +++++++++++++++++++++ include/asm-generic/pgtable.h | 39 ++++++++++++++++++++++++++++++++++++++ mm/huge_memory.c | 9 ++------- mm/mprotect.c | 4 +--- 4 files changed, 64 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b39..3ebb188c3ff5 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +#define ptep_set_numa ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0); + return; +} + #define pmd_numa pmd_numa static inline int pmd_numa(pmd_t pmd) { return pte_numa(pmd_pte(pmd)); } +#define pmdp_set_numa pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA); + return; +} + #define pmd_mknonnuma pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8e4f41d9af4d..34c7bdc06014 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte) } #endif +#ifndef ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t ptent = *ptep; + + ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, ptep, ptent); + return; +} +#endif + #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { @@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } #endif + +#ifndef pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_mknuma(pmd); + set_pmd_at(mm, addr, pmdp, pmd); + return; +} +#endif #else extern int pte_numa(pte_t pte); extern int pmd_numa(pmd_t pmd); @@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte); extern pmd_t pmd_mknonnuma(pmd_t pmd); extern pte_t pte_mknuma(pte_t pte); extern pmd_t pmd_mknuma(pmd_t pmd); +extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ #else static inline int pmd_numa(pmd_t pmd) @@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return; +} + + static inline pmd_t pmd_mknuma(pmd_t pmd) { return pmd; } + +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + return ; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf974e1..da23eb96779f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 33eab902f10e..769a67a15803 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -69,12 +69,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } -- cgit v1.2.3 From ef2820a735f74ea60335f8ba3801b844f0cb184d Mon Sep 17 00:00:00 2001 From: Matija Glavinic Pecotic Date: Fri, 14 Feb 2014 14:51:18 +0100 Subject: net: sctp: Fix a_rwnd/rwnd management to reflect real state of the receiver's buffer Implementation of (a)rwnd calculation might lead to severe performance issues and associations completely stalling. These problems are described and solution is proposed which improves lksctp's robustness in congestion state. 1) Sudden drop of a_rwnd and incomplete window recovery afterwards Data accounted in sctp_assoc_rwnd_decrease takes only payload size (sctp data), but size of sk_buff, which is blamed against receiver buffer, is not accounted in rwnd. Theoretically, this should not be the problem as actual size of buffer is double the amount requested on the socket (SO_RECVBUF). Problem here is that this will have bad scaling for data which is less then sizeof sk_buff. E.g. in 4G (LTE) networks, link interfacing radio side will have a large portion of traffic of this size (less then 100B). An example of sudden drop and incomplete window recovery is given below. Node B exhibits problematic behavior. Node A initiates association and B is configured to advertise rwnd of 10000. A sends messages of size 43B (size of typical sctp message in 4G (LTE) network). On B data is left in buffer by not reading socket in userspace. Lets examine when we will hit pressure state and declare rwnd to be 0 for scenario with above stated parameters (rwnd == 10000, chunk size == 43, each chunk is sent in separate sctp packet) Logic is implemented in sctp_assoc_rwnd_decrease: socket_buffer (see below) is maximum size which can be held in socket buffer (sk_rcvbuf). current_alloced is amount of data currently allocated (rx_count) A simple expression is given for which it will be examined after how many packets for above stated parameters we enter pressure state: We start by condition which has to be met in order to enter pressure state: socket_buffer < currently_alloced; currently_alloced is represented as size of sctp packets received so far and not yet delivered to userspace. x is the number of chunks/packets (since there is no bundling, and each chunk is delivered in separate packet, we can observe each chunk also as sctp packet, and what is important here, having its own sk_buff): socket_buffer < x*each_sctp_packet; each_sctp_packet is sctp chunk size + sizeof(struct sk_buff). socket_buffer is twice the amount of initially requested size of socket buffer, which is in case of sctp, twice the a_rwnd requested: 2*rwnd < x*(payload+sizeof(struc sk_buff)); sizeof(struct sk_buff) is 190 (3.13.0-rc4+). Above is stated that rwnd is 10000 and each payload size is 43 20000 < x(43+190); x > 20000/233; x ~> 84; After ~84 messages, pressure state is entered and 0 rwnd is advertised while received 84*43B ~= 3612B sctp data. This is why external observer notices sudden drop from 6474 to 0, as it will be now shown in example: IP A.34340 > B.12345: sctp (1) [INIT] [init tag: 1875509148] [rwnd: 81920] [OS: 10] [MIS: 65535] [init TSN: 1096057017] IP B.12345 > A.34340: sctp (1) [INIT ACK] [init tag: 3198966556] [rwnd: 10000] [OS: 10] [MIS: 10] [init TSN: 902132839] IP A.34340 > B.12345: sctp (1) [COOKIE ECHO] IP B.12345 > A.34340: sctp (1) [COOKIE ACK] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057017] [SID: 0] [SSEQ 0] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057017] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057018] [SID: 0] [SSEQ 1] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057018] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057019] [SID: 0] [SSEQ 2] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057019] [a_rwnd 9914] [#gap acks 0] [#dup tsns 0] <...> IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057098] [SID: 0] [SSEQ 81] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057098] [a_rwnd 6517] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057099] [SID: 0] [SSEQ 82] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057099] [a_rwnd 6474] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057100] [SID: 0] [SSEQ 83] [PPID 0x18] --> Sudden drop IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] At this point, rwnd_press stores current rwnd value so it can be later restored in sctp_assoc_rwnd_increase. This however doesn't happen as condition to start slowly increasing rwnd until rwnd_press is returned to rwnd is never met. This condition is not met since rwnd, after it hit 0, must first reach rwnd_press by adding amount which is read from userspace. Let us observe values in above example. Initial a_rwnd is 10000, pressure was hit when rwnd was ~6500 and the amount of actual sctp data currently waiting to be delivered to userspace is ~3500. When userspace starts to read, sctp_assoc_rwnd_increase will be blamed only for sctp data, which is ~3500. Condition is never met, and when userspace reads all data, rwnd stays on 3569. IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 1505] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 3010] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057101] [SID: 0] [SSEQ 84] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057101] [a_rwnd 3569] [#gap acks 0] [#dup tsns 0] --> At this point userspace read everything, rwnd recovered only to 3569 IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057102] [SID: 0] [SSEQ 85] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057102] [a_rwnd 3569] [#gap acks 0] [#dup tsns 0] Reproduction is straight forward, it is enough for sender to send packets of size less then sizeof(struct sk_buff) and receiver keeping them in its buffers. 2) Minute size window for associations sharing the same socket buffer In case multiple associations share the same socket, and same socket buffer (sctp.rcvbuf_policy == 0), different scenarios exist in which congestion on one of the associations can permanently drop rwnd of other association(s). Situation will be typically observed as one association suddenly having rwnd dropped to size of last packet received and never recovering beyond that point. Different scenarios will lead to it, but all have in common that one of the associations (let it be association from 1)) nearly depleted socket buffer, and the other association blames socket buffer just for the amount enough to start the pressure. This association will enter pressure state, set rwnd_press and announce 0 rwnd. When data is read by userspace, similar situation as in 1) will occur, rwnd will increase just for the size read by userspace but rwnd_press will be high enough so that association doesn't have enough credit to reach rwnd_press and restore to previous state. This case is special case of 1), being worse as there is, in the worst case, only one packet in buffer for which size rwnd will be increased. Consequence is association which has very low maximum rwnd ('minute size', in our case down to 43B - size of packet which caused pressure) and as such unusable. Scenario happened in the field and labs frequently after congestion state (link breaks, different probabilities of packet drop, packet reordering) and with scenario 1) preceding. Here is given a deterministic scenario for reproduction: >From node A establish two associations on the same socket, with rcvbuf_policy being set to share one common buffer (sctp.rcvbuf_policy == 0). On association 1 repeat scenario from 1), that is, bring it down to 0 and restore up. Observe scenario 1). Use small payload size (here we use 43). Once rwnd is 'recovered', bring it down close to 0, as in just one more packet would close it. This has as a consequence that association number 2 is able to receive (at least) one more packet which will bring it in pressure state. E.g. if association 2 had rwnd of 10000, packet received was 43, and we enter at this point into pressure, rwnd_press will have 9957. Once payload is delivered to userspace, rwnd will increase for 43, but conditions to restore rwnd to original state, just as in 1), will never be satisfied. --> Association 1, between A.y and B.12345 IP A.55915 > B.12345: sctp (1) [INIT] [init tag: 836880897] [rwnd: 10000] [OS: 10] [MIS: 65535] [init TSN: 4032536569] IP B.12345 > A.55915: sctp (1) [INIT ACK] [init tag: 2873310749] [rwnd: 81920] [OS: 10] [MIS: 10] [init TSN: 3799315613] IP A.55915 > B.12345: sctp (1) [COOKIE ECHO] IP B.12345 > A.55915: sctp (1) [COOKIE ACK] --> Association 2, between A.z and B.12346 IP A.55915 > B.12346: sctp (1) [INIT] [init tag: 534798321] [rwnd: 10000] [OS: 10] [MIS: 65535] [init TSN: 2099285173] IP B.12346 > A.55915: sctp (1) [INIT ACK] [init tag: 516668823] [rwnd: 81920] [OS: 10] [MIS: 10] [init TSN: 3676403240] IP A.55915 > B.12346: sctp (1) [COOKIE ECHO] IP B.12346 > A.55915: sctp (1) [COOKIE ACK] --> Deplete socket buffer by sending messages of size 43B over association 1 IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315613] [SID: 0] [SSEQ 0] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315613] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0] <...> IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315696] [a_rwnd 6388] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315697] [SID: 0] [SSEQ 84] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315697] [a_rwnd 6345] [#gap acks 0] [#dup tsns 0] --> Sudden drop on 1 IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315698] [SID: 0] [SSEQ 85] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315698] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] --> Here userspace read, rwnd 'recovered' to 3698, now deplete again using association 1 so there is place in buffer for only one more packet IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315799] [SID: 0] [SSEQ 186] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315799] [a_rwnd 86] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315800] [SID: 0] [SSEQ 187] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 43] [#gap acks 0] [#dup tsns 0] --> Socket buffer is almost depleted, but there is space for one more packet, send them over association 2, size 43B IP B.12346 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3676403240] [SID: 0] [SSEQ 0] [PPID 0x18] IP A.55915 > B.12346: sctp (1) [SACK] [cum ack 3676403240] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] --> Immediate drop IP A.60995 > B.12346: sctp (1) [SACK] [cum ack 387491510] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] --> Read everything from the socket, both association recover up to maximum rwnd they are capable of reaching, note that association 1 recovered up to 3698, and association 2 recovered only to 43 IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 1548] [#gap acks 0] [#dup tsns 0] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 3053] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315801] [SID: 0] [SSEQ 188] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315801] [a_rwnd 3698] [#gap acks 0] [#dup tsns 0] IP B.12346 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3676403241] [SID: 0] [SSEQ 1] [PPID 0x18] IP A.55915 > B.12346: sctp (1) [SACK] [cum ack 3676403241] [a_rwnd 43] [#gap acks 0] [#dup tsns 0] A careful reader might wonder why it is necessary to reproduce 1) prior reproduction of 2). It is simply easier to observe when to send packet over association 2 which will push association into the pressure state. Proposed solution: Both problems share the same root cause, and that is improper scaling of socket buffer with rwnd. Solution in which sizeof(sk_buff) is taken into concern while calculating rwnd is not possible due to fact that there is no linear relationship between amount of data blamed in increase/decrease with IP packet in which payload arrived. Even in case such solution would be followed, complexity of the code would increase. Due to nature of current rwnd handling, slow increase (in sctp_assoc_rwnd_increase) of rwnd after pressure state is entered is rationale, but it gives false representation to the sender of current buffer space. Furthermore, it implements additional congestion control mechanism which is defined on implementation, and not on standard basis. Proposed solution simplifies whole algorithm having on mind definition from rfc: o Receiver Window (rwnd): This gives the sender an indication of the space available in the receiver's inbound buffer. Core of the proposed solution is given with these lines: sctp_assoc_rwnd_update: if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; else asoc->rwnd = 0; We advertise to sender (half of) actual space we have. Half is in the braces depending whether you would like to observe size of socket buffer as SO_RECVBUF or twice the amount, i.e. size is the one visible from userspace, that is, from kernelspace. In this way sender is given with good approximation of our buffer space, regardless of the buffer policy - we always advertise what we have. Proposed solution fixes described problems and removes necessity for rwnd restoration algorithm. Finally, as proposed solution is simplification, some lines of code, along with some bytes in struct sctp_association are saved. Version 2 of the patch addressed comments from Vlad. Name of the function is set to be more descriptive, and two parts of code are changed, in one removing the superfluous call to sctp_assoc_rwnd_update since call would not result in update of rwnd, and the other being reordering of the code in a way that call to sctp_assoc_rwnd_update updates rwnd. Version 3 corrected change introduced in v2 in a way that existing function is not reordered/copied in line, but it is correctly called. Thanks Vlad for suggesting. Signed-off-by: Matija Glavinic Pecotic Reviewed-by: Alexander Sverdlin Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 14 +------- net/sctp/associola.c | 82 ++++++++++------------------------------------ net/sctp/sm_statefuns.c | 2 +- net/sctp/socket.c | 6 ---- net/sctp/ulpevent.c | 8 +++-- 5 files changed, 25 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d992ca3145fe..6ee76c804893 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1653,17 +1653,6 @@ struct sctp_association { /* This is the last advertised value of rwnd over a SACK chunk. */ __u32 a_rwnd; - /* Number of bytes by which the rwnd has slopped. The rwnd is allowed - * to slop over a maximum of the association's frag_point. - */ - __u32 rwnd_over; - - /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one - * is releases slowly (1 PMTU at a time ). - */ - __u32 rwnd_press; - /* This is the sndbuf size in use for the association. * This corresponds to the sndbuf size for the association, * as specified in the sk->sndbuf. @@ -1892,8 +1881,7 @@ void sctp_assoc_update(struct sctp_association *old, __u32 sctp_association_get_next_tsn(struct sctp_association *); void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *); -void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); -void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); +void sctp_assoc_rwnd_update(struct sctp_association *, bool); void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5ae609200674..f558433537b8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1367,44 +1367,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) +/* Update asoc's rwnd for the approximated state in the buffer, + * and check whether SACK needs to be sent. + */ +void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) { + int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->rwnd_over) { - if (asoc->rwnd_over >= len) { - asoc->rwnd_over -= len; - } else { - asoc->rwnd += (len - asoc->rwnd_over); - asoc->rwnd_over = 0; - } - } else { - asoc->rwnd += len; - } + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - /* If we had window pressure, start recovering it - * once our rwnd had reached the accumulated pressure - * threshold. The idea is to recover slowly, but up - * to the initial advertised window. - */ - if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { - int change = min(asoc->pathmtu, asoc->rwnd_press); - asoc->rwnd += change; - asoc->rwnd_press -= change; - } + if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) + asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; + else + asoc->rwnd = 0; - pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->a_rwnd); + pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", + __func__, asoc, asoc->rwnd, rx_count, + asoc->base.sk->sk_rcvbuf); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (sctp_peer_needs_update(asoc)) { + if (update_peer && sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1426,45 +1417,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) } } -/* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) -{ - int rx_count; - int over = 0; - - if (unlikely(!asoc->rwnd || asoc->rwnd_over)) - pr_debug("%s: association:%p has asoc->rwnd:%u, " - "asoc->rwnd_over:%u!\n", __func__, asoc, - asoc->rwnd, asoc->rwnd_over); - - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - - /* If we've reached or overflowed our receive buffer, announce - * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored - * back to original value. - */ - if (rx_count >= asoc->base.sk->sk_rcvbuf) - over = 1; - - if (asoc->rwnd >= len) { - asoc->rwnd -= len; - if (over) { - asoc->rwnd_press += asoc->rwnd; - asoc->rwnd = 0; - } - } else { - asoc->rwnd_over = len - asoc->rwnd; - asoc->rwnd = 0; - } - - pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->rwnd_press); -} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 483dcd71b3c5..591b44d3b7de 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6176,7 +6176,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || + if ((!chunk->data_accepted) && (!asoc->rwnd || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e91d6e5df63..7075ac847fde 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2092,12 +2092,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); - /* When only partial message is copied to the user, increase - * rwnd by that amount. If all the data in the skb is read, - * rwnd is updated when the event is freed. - */ - if (!sctp_ulpevent_is_notification(event)) - sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 85c64658bd0b..8d198ae03606 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); + sctp_assoc_rwnd_update(asoc, false); if (!skb->data_len) return; @@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; + struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - sctp_assoc_rwnd_increase(event->asoc, len); + asoc = event->asoc; + sctp_association_hold(asoc); sctp_ulpevent_release_owner(event); + sctp_assoc_rwnd_update(asoc, true); + sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) -- 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') 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') 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 478b360a47b71f3b5030eacd3aae6acb1a32c2b6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 15 Feb 2014 23:48:45 +0100 Subject: netfilter: nf_tables: fix nf_trace always-on with XT_TRACE=n When using nftables with CONFIG_NETFILTER_XT_TARGET_TRACE=n, we get lots of "TRACE: filter:output:policy:1 IN=..." warnings as several places will leave skb->nf_trace uninitialised. Unlike iptables tracing functionality is not conditional in nftables, so always copy/zero nf_trace setting when nftables is enabled. Move this into __nf_copy() helper. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 5 ++++- net/core/skbuff.c | 3 --- net/ipv4/ip_output.c | 3 --- net/ipv6/ip6_output.c | 3 --- 4 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..d40d40b2915b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2725,7 +2725,7 @@ static inline void nf_reset(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -2742,6 +2742,9 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); #endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) + dst->nf_trace = src->nf_trace; +#endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5976ef0846bd..5d6236d9fdce 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -707,9 +707,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->mark = old->mark; new->skb_iif = old->skb_iif; __nf_copy(new, old); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - new->nf_trace = old->nf_trace; -#endif #ifdef CONFIG_NET_SCHED new->tc_index = old->tc_index; #ifdef CONFIG_NET_CLS_ACT diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8971780aec7c..73c6b63bba74 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26ccf81..4cfbe0f3793a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -517,9 +517,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif skb_copy_secmark(to, from); } -- 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') 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') 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 728a0cdf065b9f42d1ff25d94858f824bb0989ba Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sun, 9 Feb 2014 18:43:18 +0900 Subject: drm/ttm: declare 'struct device' in ttm_page_alloc.h Declare 'struct device' explicitly in ttm_page_alloc.h as this file does not include any file declaring it. This removes the following warning: warning: 'struct device' declared inside parameter list Signed-off-by: Alexandre Courbot Reviewed-by: Thierry Reding --- include/drm/ttm/ttm_page_alloc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_page_alloc.h b/include/drm/ttm/ttm_page_alloc.h index d1f61bfe0ebe..49a828425fa2 100644 --- a/include/drm/ttm/ttm_page_alloc.h +++ b/include/drm/ttm/ttm_page_alloc.h @@ -29,6 +29,8 @@ #include #include +struct device; + /** * Initialize pool allocator. */ -- cgit v1.2.3 From 8716ed4e7bed4e4c7e3f37940e950ddc0362f450 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 12 Feb 2014 12:48:23 -0500 Subject: drm: add DRM_CAPs for cursor size Some hardware may not support standard 64x64 cursors. Add a drm cap to query the cursor size from the kernel. Some examples include radeon CIK parts (128x128 cursors) and armada (32x64 or 64x32). This allows things like device specific ddxes to remove asics specific logic and also allows xf86-video-modesetting to work properly with hw cursors on this hardware. Default to 64 if the driver doesn't specify a size. Signed-off-by: Alex Deucher Reviewed-by: Rob Clark --- drivers/gpu/drm/drm_ioctl.c | 12 ++++++++++++ include/drm/drm_crtc.h | 3 +++ include/uapi/drm/drm.h | 2 ++ 3 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index dffc836144cc..f4dc9b7a3831 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -296,6 +296,18 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv) case DRM_CAP_ASYNC_PAGE_FLIP: req->value = dev->mode_config.async_page_flip; break; + case DRM_CAP_CURSOR_WIDTH: + if (dev->mode_config.cursor_width) + req->value = dev->mode_config.cursor_width; + else + req->value = 64; + break; + case DRM_CAP_CURSOR_HEIGHT: + if (dev->mode_config.cursor_height) + req->value = dev->mode_config.cursor_height; + else + req->value = 64; + break; default: return -EINVAL; } diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 71727b6210ae..8f3dee097579 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -907,6 +907,9 @@ struct drm_mode_config { /* whether async page flip is supported or not */ bool async_page_flip; + + /* cursor size */ + uint32_t cursor_width, cursor_height; }; #define obj_to_crtc(x) container_of(x, struct drm_crtc, base) diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 3c9a833992e8..b06c8ed68707 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -619,6 +619,8 @@ struct drm_gem_open { #define DRM_PRIME_CAP_EXPORT 0x2 #define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 +#define DRM_CAP_CURSOR_WIDTH 0x8 +#define DRM_CAP_CURSOR_HEIGHT 0x9 /** DRM_IOCTL_GET_CAP ioctl argument type */ struct drm_get_cap { -- 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 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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') 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 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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') 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 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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') 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 994c41ee0ac875797b4dfef509ac7753e2649b4d Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Thu, 30 Jan 2014 13:17:20 +0200 Subject: ARM: OMAP2+: clock: fix clkoutx2 with CLK_SET_RATE_PARENT If CLK_SET_RATE_PARENT is set for a clkoutx2 clock, calling clk_set_rate() on the clock "skips" the x2 multiplier as there are no set_rate and round_rate functions defined for the clkoutx2. This results in getting double the requested clock rates, breaking the display on omap3430 based devices. This got broken when d0f58bd3bba3877fb1af4664c4e33273d36f00e4 and related patches were merged for v3.14, as omapdss driver now relies more on the clk-framework and CLK_SET_RATE_PARENT. This patch implements set_rate and round_rate for clkoutx2. Tested on OMAP3430, OMAP3630, OMAP4460. Signed-off-by: Tomi Valkeinen Acked-by: Tero Kristo Signed-off-by: Paul Walmsley --- arch/arm/mach-omap2/cclock3xxx_data.c | 2 + arch/arm/mach-omap2/dpll3xxx.c | 92 +++++++++++++++++++++++++++++------ include/linux/clk/ti.h | 4 ++ 3 files changed, 83 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c index 3b05aea56d1f..11ed9152e665 100644 --- a/arch/arm/mach-omap2/cclock3xxx_data.c +++ b/arch/arm/mach-omap2/cclock3xxx_data.c @@ -433,7 +433,9 @@ static const struct clk_ops dpll4_m5x2_ck_ops = { .enable = &omap2_dflt_clk_enable, .disable = &omap2_dflt_clk_disable, .is_enabled = &omap2_dflt_clk_is_enabled, + .set_rate = &omap3_clkoutx2_set_rate, .recalc_rate = &omap3_clkoutx2_recalc, + .round_rate = &omap3_clkoutx2_round_rate, }; static const struct clk_ops dpll4_m5x2_ck_3630_ops = { diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c index 3185ced807c9..3c418ea54bbe 100644 --- a/arch/arm/mach-omap2/dpll3xxx.c +++ b/arch/arm/mach-omap2/dpll3xxx.c @@ -623,6 +623,32 @@ void omap3_dpll_deny_idle(struct clk_hw_omap *clk) /* Clock control for DPLL outputs */ +/* Find the parent DPLL for the given clkoutx2 clock */ +static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw) +{ + struct clk_hw_omap *pclk = NULL; + struct clk *parent; + + /* Walk up the parents of clk, looking for a DPLL */ + do { + do { + parent = __clk_get_parent(hw->clk); + hw = __clk_get_hw(parent); + } while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC)); + if (!hw) + break; + pclk = to_clk_hw_omap(hw); + } while (pclk && !pclk->dpll_data); + + /* clk does not have a DPLL as a parent? error in the clock data */ + if (!pclk) { + WARN_ON(1); + return NULL; + } + + return pclk; +} + /** * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate * @clk: DPLL output struct clk @@ -637,27 +663,14 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long rate; u32 v; struct clk_hw_omap *pclk = NULL; - struct clk *parent; if (!parent_rate) return 0; - /* Walk up the parents of clk, looking for a DPLL */ - do { - do { - parent = __clk_get_parent(hw->clk); - hw = __clk_get_hw(parent); - } while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC)); - if (!hw) - break; - pclk = to_clk_hw_omap(hw); - } while (pclk && !pclk->dpll_data); + pclk = omap3_find_clkoutx2_dpll(hw); - /* clk does not have a DPLL as a parent? error in the clock data */ - if (!pclk) { - WARN_ON(1); + if (!pclk) return 0; - } dd = pclk->dpll_data; @@ -672,6 +685,55 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, return rate; } +int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + return 0; +} + +long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + const struct dpll_data *dd; + u32 v; + struct clk_hw_omap *pclk = NULL; + + if (!*prate) + return 0; + + pclk = omap3_find_clkoutx2_dpll(hw); + + if (!pclk) + return 0; + + dd = pclk->dpll_data; + + /* TYPE J does not have a clkoutx2 */ + if (dd->flags & DPLL_J_TYPE) { + *prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate); + return *prate; + } + + WARN_ON(!dd->enable_mask); + + v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask; + v >>= __ffs(dd->enable_mask); + + /* If in bypass, the rate is fixed to the bypass rate*/ + if (v != OMAP3XXX_EN_DPLL_LOCKED) + return *prate; + + if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) { + unsigned long best_parent; + + best_parent = (rate / 2); + *prate = __clk_round_rate(__clk_get_parent(hw->clk), + best_parent); + } + + return *prate * 2; +} + /* OMAP3/4 non-CORE DPLL clkops */ const struct clk_hw_omap_ops clkhwops_omap3_dpll = { .allow_idle = omap3_dpll_allow_idle, diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 092b64168d7f..4a21a872dbbd 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -245,6 +245,10 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate, void omap2_init_clk_clkdm(struct clk_hw *clk); unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long parent_rate); +int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate); +long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate); int omap2_clkops_enable_clkdm(struct clk_hw *hw); void omap2_clkops_disable_clkdm(struct clk_hw *hw); int omap2_clk_disable_autoidle_all(void); -- cgit v1.2.3 From 113911006442a36c2b4669faf1699d9042ef80ab Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 18 Feb 2014 15:22:14 +0000 Subject: ASoC: dapm: Add locking to snd_soc_dapm_xxxx_pin functions The snd_soc_dapm_xxxx_pin all require the dapm_mutex to be held when they are called as they edit the dirty list, however very few of the callers do so. This patch adds unlocked versions of all the functions replacing the existing implementations with one that holds the lock internally. We also fix up the places where the lock was actually held on the caller side. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/extcon/extcon-arizona.c | 12 ---- drivers/input/misc/arizona-haptics.c | 16 ----- include/sound/soc-dapm.h | 8 +++ sound/soc/soc-dapm.c | 133 ++++++++++++++++++++++++++++++++--- 4 files changed, 131 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c index c20602f601ee..98a14f6143a7 100644 --- a/drivers/extcon/extcon-arizona.c +++ b/drivers/extcon/extcon-arizona.c @@ -222,27 +222,19 @@ static void arizona_extcon_pulse_micbias(struct arizona_extcon_info *info) struct snd_soc_dapm_context *dapm = arizona->dapm; int ret; - mutex_lock(&dapm->card->dapm_mutex); - ret = snd_soc_dapm_force_enable_pin(dapm, widget); if (ret != 0) dev_warn(arizona->dev, "Failed to enable %s: %d\n", widget, ret); - mutex_unlock(&dapm->card->dapm_mutex); - snd_soc_dapm_sync(dapm); if (!arizona->pdata.micd_force_micbias) { - mutex_lock(&dapm->card->dapm_mutex); - ret = snd_soc_dapm_disable_pin(arizona->dapm, widget); if (ret != 0) dev_warn(arizona->dev, "Failed to disable %s: %d\n", widget, ret); - mutex_unlock(&dapm->card->dapm_mutex); - snd_soc_dapm_sync(dapm); } } @@ -304,16 +296,12 @@ static void arizona_stop_mic(struct arizona_extcon_info *info) ARIZONA_MICD_ENA, 0, &change); - mutex_lock(&dapm->card->dapm_mutex); - ret = snd_soc_dapm_disable_pin(dapm, widget); if (ret != 0) dev_warn(arizona->dev, "Failed to disable %s: %d\n", widget, ret); - mutex_unlock(&dapm->card->dapm_mutex); - snd_soc_dapm_sync(dapm); if (info->micd_reva) { diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c index e7e12a5f5c2d..ef2e281b0a43 100644 --- a/drivers/input/misc/arizona-haptics.c +++ b/drivers/input/misc/arizona-haptics.c @@ -37,7 +37,6 @@ static void arizona_haptics_work(struct work_struct *work) struct arizona_haptics, work); struct arizona *arizona = haptics->arizona; - struct mutex *dapm_mutex = &arizona->dapm->card->dapm_mutex; int ret; if (!haptics->arizona->dapm) { @@ -67,18 +66,13 @@ static void arizona_haptics_work(struct work_struct *work) return; } - mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - ret = snd_soc_dapm_enable_pin(arizona->dapm, "HAPTICS"); if (ret != 0) { dev_err(arizona->dev, "Failed to start HAPTICS: %d\n", ret); - mutex_unlock(dapm_mutex); return; } - mutex_unlock(dapm_mutex); - ret = snd_soc_dapm_sync(arizona->dapm); if (ret != 0) { dev_err(arizona->dev, "Failed to sync DAPM: %d\n", @@ -87,18 +81,13 @@ static void arizona_haptics_work(struct work_struct *work) } } else { /* This disable sequence will be a noop if already enabled */ - mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - ret = snd_soc_dapm_disable_pin(arizona->dapm, "HAPTICS"); if (ret != 0) { dev_err(arizona->dev, "Failed to disable HAPTICS: %d\n", ret); - mutex_unlock(dapm_mutex); return; } - mutex_unlock(dapm_mutex); - ret = snd_soc_dapm_sync(arizona->dapm); if (ret != 0) { dev_err(arizona->dev, "Failed to sync DAPM: %d\n", @@ -152,16 +141,11 @@ static int arizona_haptics_play(struct input_dev *input, void *data, static void arizona_haptics_close(struct input_dev *input) { struct arizona_haptics *haptics = input_get_drvdata(input); - struct mutex *dapm_mutex = &haptics->arizona->dapm->card->dapm_mutex; cancel_work_sync(&haptics->work); - mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - if (haptics->arizona->dapm) snd_soc_dapm_disable_pin(haptics->arizona->dapm, "HAPTICS"); - - mutex_unlock(dapm_mutex); } static int arizona_haptics_probe(struct platform_device *pdev) diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 68d92e36facd..6e89ef6c11c1 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -449,14 +449,22 @@ void snd_soc_dapm_debugfs_init(struct snd_soc_dapm_context *dapm, /* dapm audio pin control and status */ int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_get_pin_status(struct snd_soc_dapm_context *dapm, const char *pin); int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm); int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm, const char *pin); void snd_soc_dapm_auto_nc_codec_pins(struct snd_soc_codec *codec); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index fd39cd2827d7..b9dc6acbba8c 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3210,15 +3210,11 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol, struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); const char *pin = (const char *)kcontrol->private_value; - mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - if (ucontrol->value.integer.value[0]) snd_soc_dapm_enable_pin(&card->dapm, pin); else snd_soc_dapm_disable_pin(&card->dapm, pin); - mutex_unlock(&card->dapm_mutex); - snd_soc_dapm_sync(&card->dapm); return 0; } @@ -3766,6 +3762,26 @@ void snd_soc_dapm_stream_event(struct snd_soc_pcm_runtime *rtd, int stream, mutex_unlock(&card->dapm_mutex); } +/** + * snd_soc_dapm_enable_pin_unlocked - enable pin. + * @dapm: DAPM context + * @pin: pin name + * + * Enables input/output pin and its parents or children widgets iff there is + * a valid audio route and active audio stream. + * + * Requires external locking. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + return snd_soc_dapm_set_pin(dapm, pin, 1); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin_unlocked); + /** * snd_soc_dapm_enable_pin - enable pin. * @dapm: DAPM context @@ -3773,17 +3789,26 @@ void snd_soc_dapm_stream_event(struct snd_soc_pcm_runtime *rtd, int stream, * * Enables input/output pin and its parents or children widgets iff there is * a valid audio route and active audio stream. + * * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to * do any widget power switching. */ int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin) { - return snd_soc_dapm_set_pin(dapm, pin, 1); + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_set_pin(dapm, pin, 1); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin); /** - * snd_soc_dapm_force_enable_pin - force a pin to be enabled + * snd_soc_dapm_force_enable_pin_unlocked - force a pin to be enabled * @dapm: DAPM context * @pin: pin name * @@ -3791,11 +3816,13 @@ EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin); * intended for use with microphone bias supplies used in microphone * jack detection. * + * Requires external locking. + * * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to * do any widget power switching. */ -int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, - const char *pin) +int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) { struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true); @@ -3811,24 +3838,102 @@ int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, return 0; } +EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin_unlocked); + +/** + * snd_soc_dapm_force_enable_pin - force a pin to be enabled + * @dapm: DAPM context + * @pin: pin name + * + * Enables input/output pin regardless of any other state. This is + * intended for use with microphone bias supplies used in microphone + * jack detection. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_force_enable_pin_unlocked(dapm, pin); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin); +/** + * snd_soc_dapm_disable_pin_unlocked - disable pin. + * @dapm: DAPM context + * @pin: pin name + * + * Disables input/output pin and its parents or children widgets. + * + * Requires external locking. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + return snd_soc_dapm_set_pin(dapm, pin, 0); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin_unlocked); + /** * snd_soc_dapm_disable_pin - disable pin. * @dapm: DAPM context * @pin: pin name * * Disables input/output pin and its parents or children widgets. + * * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to * do any widget power switching. */ int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm, const char *pin) { - return snd_soc_dapm_set_pin(dapm, pin, 0); + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_set_pin(dapm, pin, 0); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin); +/** + * snd_soc_dapm_nc_pin_unlocked - permanently disable pin. + * @dapm: DAPM context + * @pin: pin name + * + * Marks the specified pin as being not connected, disabling it along + * any parent or child widgets. At present this is identical to + * snd_soc_dapm_disable_pin() but in future it will be extended to do + * additional things such as disabling controls which only affect + * paths through the pin. + * + * Requires external locking. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + return snd_soc_dapm_set_pin(dapm, pin, 0); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin_unlocked); + /** * snd_soc_dapm_nc_pin - permanently disable pin. * @dapm: DAPM context @@ -3845,7 +3950,15 @@ EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin); */ int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin) { - return snd_soc_dapm_set_pin(dapm, pin, 0); + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_set_pin(dapm, pin, 0); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin); -- cgit v1.2.3 From ee5c23176fcc820f7a56d3e86001532af0d59b1e Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 19 Feb 2014 13:33:24 +0100 Subject: xfrm: Clone states properly on migration We loose a lot of information of the original state if we clone it with xfrm_state_clone(). In particular, there is no crypto algorithm attached if the original state uses an aead algorithm. This patch add the missing information to the clone state. Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 11 +++++++++++ net/xfrm/xfrm_state.c | 8 ++++++++ net/xfrm/xfrm_user.c | 5 ----- 3 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index afa5730fb3bd..fb5654a8ca3c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1648,6 +1648,11 @@ static inline int xfrm_aevent_is_on(struct net *net) } #endif +static inline int aead_len(struct xfrm_algo_aead *alg) +{ + return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); +} + static inline int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); @@ -1686,6 +1691,12 @@ static inline int xfrm_replay_clone(struct xfrm_state *x, return 0; } +static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) +{ + return kmemdup(orig, aead_len(orig), GFP_KERNEL); +} + + static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c101023be3d2..40f1b3e92e78 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1159,6 +1159,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) } x->props.aalgo = orig->props.aalgo; + if (orig->aead) { + x->aead = xfrm_algo_aead_clone(orig->aead); + if (!x->aead) + goto error; + } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) @@ -1201,6 +1206,9 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->tfcpad = orig->tfcpad; + x->replay_maxdiff = orig->replay_maxdiff; + x->replay_maxage = orig->replay_maxage; x->curlft.add_time = orig->curlft.add_time; x->km.state = orig->km.state; x->km.seq = orig->km.seq; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1ae3ec7c18b0..c274179d60a2 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -32,11 +32,6 @@ #include #endif -static inline int aead_len(struct xfrm_algo_aead *alg) -{ - return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); -} - static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) { struct nlattr *rt = attrs[type]; -- cgit v1.2.3 From c7fbd4158433c1c910c62850247728cb05a94e42 Mon Sep 17 00:00:00 2001 From: Peter De Schrijver Date: Thu, 20 Feb 2014 10:49:34 +0200 Subject: clk: tegra124: remove gr2d and gr3d clocks Tegra124 does not have gr2d and gr3d clocks. They have been replaced by the vic03 and gpu clocks respectively. Signed-off-by: Peter De Schrijver --- drivers/clk/tegra/clk-tegra124.c | 2 -- include/dt-bindings/clock/tegra124-car.h | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index b4cf65080da8..166e02f16c8a 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -769,10 +769,8 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true }, [tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true }, [tegra_clk_i2s2] = { .dt_id = TEGRA124_CLK_I2S2, .present = true }, - [tegra_clk_gr2d] = { .dt_id = TEGRA124_CLK_GR_2D, .present = true }, [tegra_clk_usbd] = { .dt_id = TEGRA124_CLK_USBD, .present = true }, [tegra_clk_isp_8] = { .dt_id = TEGRA124_CLK_ISP, .present = true }, - [tegra_clk_gr3d] = { .dt_id = TEGRA124_CLK_GR_3D, .present = true }, [tegra_clk_disp2] = { .dt_id = TEGRA124_CLK_DISP2, .present = true }, [tegra_clk_disp1] = { .dt_id = TEGRA124_CLK_DISP1, .present = true }, [tegra_clk_host1x_8] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true }, diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h index a1116a3b54ef..8c1603b10665 100644 --- a/include/dt-bindings/clock/tegra124-car.h +++ b/include/dt-bindings/clock/tegra124-car.h @@ -36,10 +36,10 @@ #define TEGRA124_CLK_PWM 17 #define TEGRA124_CLK_I2S2 18 /* 20 (register bit affects vi and vi_sensor) */ -#define TEGRA124_CLK_GR_2D 21 +/* 21 */ #define TEGRA124_CLK_USBD 22 #define TEGRA124_CLK_ISP 23 -#define TEGRA124_CLK_GR_3D 24 +/* 26 */ /* 25 */ #define TEGRA124_CLK_DISP2 26 #define TEGRA124_CLK_DISP1 27 -- cgit v1.2.3 From cf71d2bc0b8a473209d5c770ce560853bd720d14 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 20 Feb 2014 10:19:31 +0100 Subject: sit: fix panic with route cache in ip tunnels Bug introduced by commit 7d442fab0a67 ("ipv4: Cache dst in tunnels"). Because sit code does not call ip_tunnel_init(), the dst_cache was not initialized. CC: Tom Herbert Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 1 + net/ipv4/ip_tunnel.c | 7 ++++--- net/ipv6/sit.c | 19 +++++++++++++++++++ 3 files changed, 24 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 48ed75c21260..e77c10405d51 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -129,6 +129,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); void ip_tunnel_setup(struct net_device *dev, int net_id); +void ip_tunnel_dst_reset_all(struct ip_tunnel *t); /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 08f8cf99b3a2..78a89e61925d 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -93,13 +93,14 @@ static void tunnel_dst_reset(struct ip_tunnel *t) tunnel_dst_set(t, NULL); } -static void tunnel_dst_reset_all(struct ip_tunnel *t) +void ip_tunnel_dst_reset_all(struct ip_tunnel *t) { int i; for_each_possible_cpu(i) __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } +EXPORT_SYMBOL(ip_tunnel_dst_reset_all); static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) { @@ -713,7 +714,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - tunnel_dst_reset_all(t); + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); } @@ -1042,7 +1043,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); - tunnel_dst_reset_all(tunnel); + ip_tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3dfbcf1dcb1c..b4d74c86586c 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } + ip_tunnel_dst_reset_all(tunnel); dev_put(dev); } @@ -1082,6 +1083,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) t->parms.link = p->link; ipip6_tunnel_bind_dev(t->dev); } + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); } @@ -1112,6 +1114,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); return 0; } @@ -1271,6 +1274,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); break; @@ -1326,6 +1330,9 @@ static const struct net_device_ops ipip6_netdev_ops = { static void ipip6_dev_free(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + + free_percpu(tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1375,6 +1382,12 @@ static int ipip6_tunnel_init(struct net_device *dev) u64_stats_init(&ipip6_tunnel_stats->syncp); } + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + return 0; } @@ -1405,6 +1418,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) u64_stats_init(&ipip6_fb_stats->syncp); } + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + dev_hold(dev); rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; -- cgit v1.2.3 From feb71dae1f9e0aeb056f7f639a21e620d327fc66 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Feb 2014 15:32:37 -0800 Subject: blk-mq: merge blk_mq_insert_request and blk_mq_run_request It's almost identical to blk_mq_insert_request, so fold the two into one slightly more generic function by making the flush special case a bit smarted. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-exec.c | 2 +- block/blk-flush.c | 4 ++-- block/blk-mq.c | 53 ++++++++++---------------------------------------- block/blk-mq.h | 1 - include/linux/blk-mq.h | 3 +-- 5 files changed, 14 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/block/blk-exec.c b/block/blk-exec.c index c68613bb4c79..dbf4502b1d67 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, * be resued after dying flag is set */ if (q->mq_ops) { - blk_mq_insert_request(q, rq, at_head, true); + blk_mq_insert_request(rq, at_head, true, false); return; } diff --git a/block/blk-flush.c b/block/blk-flush.c index 66e2b697f5db..f598f794c3c6 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -137,7 +137,7 @@ static void mq_flush_run(struct work_struct *work) rq = container_of(work, struct request, mq_flush_work); memset(&rq->csd, 0, sizeof(rq->csd)); - blk_mq_run_request(rq, true, false); + blk_mq_insert_request(rq, false, true, false); } static bool blk_flush_queue_rq(struct request *rq) @@ -411,7 +411,7 @@ void blk_insert_flush(struct request *rq) if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { if (q->mq_ops) { - blk_mq_run_request(rq, false, true); + blk_mq_insert_request(rq, false, false, true); } else list_add_tail(&rq->queuelist, &q->queue_head); return; diff --git a/block/blk-mq.c b/block/blk-mq.c index 1e585e3444c2..2af840594dc1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -724,61 +724,28 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, blk_mq_add_timer(rq); } -void blk_mq_insert_request(struct request_queue *q, struct request *rq, - bool at_head, bool run_queue) +void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, + bool async) { + struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx, *current_ctx; + struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; + + current_ctx = blk_mq_get_ctx(q); + if (!cpu_online(ctx->cpu)) + rq->mq_ctx = ctx = current_ctx; - ctx = rq->mq_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); - if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) { + if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) && + !(rq->cmd_flags & (REQ_FLUSH_SEQ))) { blk_insert_flush(rq); } else { - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) { - ctx = current_ctx; - hctx = q->mq_ops->map_queue(q, ctx->cpu); - rq->mq_ctx = ctx; - } spin_lock(&ctx->lock); __blk_mq_insert_request(hctx, rq, at_head); spin_unlock(&ctx->lock); - - blk_mq_put_ctx(current_ctx); } - if (run_queue) - __blk_mq_run_hw_queue(hctx); -} -EXPORT_SYMBOL(blk_mq_insert_request); - -/* - * This is a special version of blk_mq_insert_request to bypass FLUSH request - * check. Should only be used internally. - */ -void blk_mq_run_request(struct request *rq, bool run_queue, bool async) -{ - struct request_queue *q = rq->q; - struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - - ctx = rq->mq_ctx; - if (!cpu_online(ctx->cpu)) { - ctx = current_ctx; - rq->mq_ctx = ctx; - } - hctx = q->mq_ops->map_queue(q, ctx->cpu); - - /* ctx->cpu might be offline */ - spin_lock(&ctx->lock); - __blk_mq_insert_request(hctx, rq, false); - spin_unlock(&ctx->lock); - blk_mq_put_ctx(current_ctx); if (run_queue) diff --git a/block/blk-mq.h b/block/blk-mq.h index ed0035cd458e..72beba1f9d55 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -23,7 +23,6 @@ struct blk_mq_ctx { }; void __blk_mq_complete_request(struct request *rq); -void blk_mq_run_request(struct request *rq, bool run_queue, bool async); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_init_flush(struct request_queue *q); void blk_mq_drain_queue(struct request_queue *q); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 18ba8a627f46..ff28fe37ddda 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -121,8 +121,7 @@ void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struc void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); -void blk_mq_insert_request(struct request_queue *, struct request *, - bool, bool); +void blk_mq_insert_request(struct request *, bool, bool, bool); void blk_mq_run_queues(struct request_queue *q, bool async); void blk_mq_free_request(struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); -- cgit v1.2.3 From d6a25b31315327eef7785b895c354cc45c3f3742 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Feb 2014 15:32:38 -0800 Subject: blk-mq: support partial I/O completions Add a new blk_mq_end_io_partial function to partially complete requests as needed by the SCSI layer. We do this by reusing blk_update_request to advance the bio instead of having a simplified version of it in the blk-mq code. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 37 +++++-------------------------------- include/linux/blk-mq.h | 8 +++++++- 2 files changed, 12 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/block/blk-mq.c b/block/blk-mq.c index 2af840594dc1..1b8b50df3655 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -283,38 +283,10 @@ void blk_mq_free_request(struct request *rq) __blk_mq_free_request(hctx, ctx, rq); } -static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error) +bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes) { - if (error) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = -EIO; - - if (unlikely(rq->cmd_flags & REQ_QUIET)) - set_bit(BIO_QUIET, &bio->bi_flags); - - /* don't actually finish bio if it's part of flush sequence */ - if (!(rq->cmd_flags & REQ_FLUSH_SEQ)) - bio_endio(bio, error); -} - -void blk_mq_end_io(struct request *rq, int error) -{ - struct bio *bio = rq->bio; - unsigned int bytes = 0; - - trace_block_rq_complete(rq->q, rq); - - while (bio) { - struct bio *next = bio->bi_next; - - bio->bi_next = NULL; - bytes += bio->bi_iter.bi_size; - blk_mq_bio_endio(rq, bio, error); - bio = next; - } - - blk_account_io_completion(rq, bytes); + if (blk_update_request(rq, error, blk_rq_bytes(rq))) + return true; blk_account_io_done(rq); @@ -322,8 +294,9 @@ void blk_mq_end_io(struct request *rq, int error) rq->end_io(rq, error); else blk_mq_free_request(rq); + return false; } -EXPORT_SYMBOL(blk_mq_end_io); +EXPORT_SYMBOL(blk_mq_end_io_partial); static void __blk_mq_complete_request_remote(void *data) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ff28fe37ddda..2ff2e8d982be 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -133,7 +133,13 @@ struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_ind struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int); void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int); -void blk_mq_end_io(struct request *rq, int error); +bool blk_mq_end_io_partial(struct request *rq, int error, + unsigned int nr_bytes); +static inline void blk_mq_end_io(struct request *rq, int error) +{ + bool done = !blk_mq_end_io_partial(rq, error, blk_rq_bytes(rq)); + BUG_ON(!done); +} void blk_mq_complete_request(struct request *rq); -- 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') 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') 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 f5ddcbbb40aa0ba7fbfe22355d287603dbeeaaac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Feb 2014 10:09:18 -0800 Subject: net-tcp: fastopen: fix high order allocations This patch fixes two bugs in fastopen : 1) The tcp_sendmsg(..., @size) argument was ignored. Code was relying on user not fooling the kernel with iovec mismatches 2) When MTU is about 64KB, tcp_send_syn_data() attempts order-5 allocations, which are likely to fail when memory gets fragmented. Fixes: 783237e8daf13 ("net-tcp: Fast Open client - sending SYN-data") Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Acked-by: Yuchung Cheng Tested-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- net/ipv4/tcp.c | 8 +++++--- net/ipv4/tcp_output.c | 7 ++++++- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 56fc366da6d5..8c4dd63134d4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1303,7 +1303,8 @@ struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ - u16 copied; /* queued in tcp_connect() */ + size_t size; + int copied; /* queued in tcp_connect() */ }; void tcp_free_fastopen_req(struct tcp_sock *tp); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9f3a2db9109e..97c8f5620c43 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3be16727f058..09805817627b 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2908,7 +2908,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; -- cgit v1.2.3 From e6cfc0295c7d51b008999a8b13a44fb43f8685ea Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 3 Feb 2014 15:33:37 +0000 Subject: asm-generic: add sched_setattr/sched_getattr syscalls Add the sched_setattr and sched_getattr syscalls to the generic syscall list, which is used by the following architectures: arc, arm64, c6x, hexagon, metag, openrisc, score, tile, unicore32. Signed-off-by: James Hogan Acked-by: Arnd Bergmann Acked-by: Catalin Marinas Cc: linux-arch@vger.kernel.org Cc: Vineet Gupta Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: Mark Salter Cc: Aurelien Jacquiot Cc: linux-c6x-dev@linux-c6x.org Cc: Richard Kuo Cc: linux-hexagon@vger.kernel.org Cc: linux-metag@vger.kernel.org Cc: Jonas Bonn Cc: linux@lists.openrisc.net Cc: Chen Liqin Cc: Lennox Wu Cc: Chris Metcalf Cc: Guan Xuetao --- include/uapi/asm-generic/unistd.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a20a9b4d3871..dde8041f40d2 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -692,9 +692,13 @@ __SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \ __SYSCALL(__NR_kcmp, sys_kcmp) #define __NR_finit_module 273 __SYSCALL(__NR_finit_module, sys_finit_module) +#define __NR_sched_setattr 274 +__SYSCALL(__NR_sched_setattr, sys_sched_setattr) +#define __NR_sched_getattr 275 +__SYSCALL(__NR_sched_getattr, sys_sched_getattr) #undef __NR_syscalls -#define __NR_syscalls 274 +#define __NR_syscalls 276 /* * All syscalls below here should go away really, -- 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') 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') 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') 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 b7e63a1079b266866a732cf699d8c4d61391bbda Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 26 Feb 2014 11:19:14 -0800 Subject: NFSv4: Fix another nfs4_sequence corruptor nfs4_release_lockowner needs to set the rpc_message reply to point to the nfs4_sequence_res in order to avoid another Oopsable situation in nfs41_assign_slot. Fixes: fbd4bfd1d9d21 (NFS: Add nfs4_sequence calls for RELEASE_LOCKOWNER) Cc: stable@vger.kernel.org # 3.12+ Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 10 +++++----- include/linux/nfs_xdr.h | 5 +++++ 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2da6a698b8f7..44e088dc357c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5828,8 +5828,7 @@ struct nfs_release_lockowner_data { struct nfs4_lock_state *lsp; struct nfs_server *server; struct nfs_release_lockowner_args args; - struct nfs4_sequence_args seq_args; - struct nfs4_sequence_res seq_res; + struct nfs_release_lockowner_res res; unsigned long timestamp; }; @@ -5837,7 +5836,7 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata { struct nfs_release_lockowner_data *data = calldata; nfs40_setup_sequence(data->server, - &data->seq_args, &data->seq_res, task); + &data->args.seq_args, &data->res.seq_res, task); data->timestamp = jiffies; } @@ -5846,7 +5845,7 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) struct nfs_release_lockowner_data *data = calldata; struct nfs_server *server = data->server; - nfs40_sequence_done(task, &data->seq_res); + nfs40_sequence_done(task, &data->res.seq_res); switch (task->tk_status) { case 0: @@ -5887,7 +5886,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) return -ENOMEM; - nfs4_init_sequence(&data->seq_args, &data->seq_res, 0); data->lsp = lsp; data->server = server; data->args.lock_owner.clientid = server->nfs_client->cl_clientid; @@ -5895,6 +5893,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st data->args.lock_owner.s_dev = server->s_dev; msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0); rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data); return 0; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b2fb167b2e6d..5624e4e2763c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -467,9 +467,14 @@ struct nfs_lockt_res { }; struct nfs_release_lockowner_args { + struct nfs4_sequence_args seq_args; struct nfs_lowner lock_owner; }; +struct nfs_release_lockowner_res { + struct nfs4_sequence_res seq_res; +}; + struct nfs4_delegreturnargs { struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; -- cgit v1.2.3 From 45ab2813d40d88fc575e753c38478de242d03f88 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 26 Feb 2014 13:37:38 -0500 Subject: tracing: Do not add event files for modules that fail tracepoints If a module fails to add its tracepoints due to module tainting, do not create the module event infrastructure in the debugfs directory. As the events will not work and worse yet, they will silently fail, making the user wonder why the events they enable do not display anything. Having a warning on module load and the events not visible to the users will make the cause of the problem much clearer. Link: http://lkml.kernel.org/r/20140227154923.265882695@goodmis.org Fixes: 6d723736e472 "tracing/events: add support for modules to TRACE_EVENT" Acked-by: Mathieu Desnoyers Cc: stable@vger.kernel.org # 2.6.31+ Cc: Rusty Russell Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 6 ++++++ kernel/trace/trace_events.c | 10 ++++++++++ kernel/tracepoint.c | 7 ++++++- 3 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index accc497f8d72..7159a0a933df 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -60,6 +60,12 @@ struct tp_module { unsigned int num_tracepoints; struct tracepoint * const *tracepoints_ptrs; }; +bool trace_module_has_bad_taint(struct module *mod); +#else +static inline bool trace_module_has_bad_taint(struct module *mod) +{ + return false; +} #endif /* CONFIG_MODULES */ struct tracepoint_iter { diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e71ffd4eccb5..f3989ceb5cd5 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1777,6 +1777,16 @@ static void trace_module_add_events(struct module *mod) { struct ftrace_event_call **call, **start, **end; + if (!mod->num_trace_events) + return; + + /* Don't add infrastructure for mods without tracepoints */ + if (trace_module_has_bad_taint(mod)) { + pr_err("%s: module has bad taint, not creating trace events\n", + mod->name); + return; + } + start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 29f26540e9c9..031cc5655a51 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -631,6 +631,11 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter) EXPORT_SYMBOL_GPL(tracepoint_iter_reset); #ifdef CONFIG_MODULES +bool trace_module_has_bad_taint(struct module *mod) +{ + return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)); +} + static int tracepoint_module_coming(struct module *mod) { struct tp_module *tp_mod, *iter; @@ -641,7 +646,7 @@ static int tracepoint_module_coming(struct module *mod) * module headers (for forced load), to make sure we don't cause a crash. * Staging and out-of-tree GPL modules are fine. */ - if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP))) + if (trace_module_has_bad_taint(mod)) return 0; mutex_lock(&tracepoints_mutex); tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); -- cgit v1.2.3 From 668f9abbd4334e6c29fa8acd71635c4f9101caa7 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 3 Mar 2014 15:38:18 -0800 Subject: mm: close PageTail race Commit bf6bddf1924e ("mm: introduce compaction and migration for ballooned pages") introduces page_count(page) into memory compaction which dereferences page->first_page if PageTail(page). This results in a very rare NULL pointer dereference on the aforementioned page_count(page). Indeed, anything that does compound_head(), including page_count() is susceptible to racing with prep_compound_page() and seeing a NULL or dangling page->first_page pointer. This patch uses Andrea's implementation of compound_trans_head() that deals with such a race and makes it the default compound_head() implementation. This includes a read memory barrier that ensures that if PageTail(head) is true that we return a head page that is neither NULL nor dangling. The patch then adds a store memory barrier to prep_compound_page() to ensure page->first_page is set. This is the safest way to ensure we see the head page that we are expecting, PageTail(page) is already in the unlikely() path and the memory barriers are unfortunately required. Hugetlbfs is the exception, we don't enforce a store memory barrier during init since no race is possible. Signed-off-by: David Rientjes Cc: Holger Kiehl Cc: Christoph Lameter Cc: Rafael Aquini Cc: Vlastimil Babka Cc: Michal Hocko Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Rik van Riel Cc: "Kirill A. Shutemov" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/aoe/aoecmd.c | 4 ++-- drivers/vfio/vfio_iommu_type1.c | 4 ++-- fs/proc/page.c | 5 ++--- include/linux/huge_mm.h | 41 ----------------------------------------- include/linux/mm.h | 14 ++++++++++++-- mm/ksm.c | 2 +- mm/memory-failure.c | 2 +- mm/page_alloc.c | 4 +++- mm/swap.c | 4 ++-- 9 files changed, 25 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 8184451b57c0..422b7d84f686 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -874,7 +874,7 @@ bio_pageinc(struct bio *bio) /* Non-zero page count for non-head members of * compound pages is no longer allowed by the kernel. */ - page = compound_trans_head(bv.bv_page); + page = compound_head(bv.bv_page); atomic_inc(&page->_count); } } @@ -887,7 +887,7 @@ bio_pagedec(struct bio *bio) struct bvec_iter iter; bio_for_each_segment(bv, bio, iter) { - page = compound_trans_head(bv.bv_page); + page = compound_head(bv.bv_page); atomic_dec(&page->_count); } } diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 4fb7a8f83c8a..54af4e933695 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -186,12 +186,12 @@ static bool is_invalid_reserved_pfn(unsigned long pfn) if (pfn_valid(pfn)) { bool reserved; struct page *tail = pfn_to_page(pfn); - struct page *head = compound_trans_head(tail); + struct page *head = compound_head(tail); reserved = !!(PageReserved(head)); if (head != tail) { /* * "head" is not a dangling pointer - * (compound_trans_head takes care of that) + * (compound_head takes care of that) * but the hugepage may have been split * from under us (and we may not hold a * reference count on the head page so it can diff --git a/fs/proc/page.c b/fs/proc/page.c index 02174a610315..e647c55275d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && - (PageLRU(compound_trans_head(page)) || - PageAnon(compound_trans_head(page)))) + else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || + PageAnon(compound_head(page)))) u |= 1 << KPF_THP; /* diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index db512014e061..b826239bdce0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,46 +157,6 @@ static inline int hpage_nr_pages(struct page *page) return HPAGE_PMD_NR; return 1; } -/* - * compound_trans_head() should be used instead of compound_head(), - * whenever the "page" passed as parameter could be the tail of a - * transparent hugepage that could be undergoing a - * __split_huge_page_refcount(). The page structure layout often - * changes across releases and it makes extensive use of unions. So if - * the page structure layout will change in a way that - * page->first_page gets clobbered by __split_huge_page_refcount, the - * implementation making use of smp_rmb() will be required. - * - * Currently we define compound_trans_head as compound_head, because - * page->private is in the same union with page->first_page, and - * page->private isn't clobbered. However this also means we're - * currently leaving dirt into the page->private field of anonymous - * pages resulting from a THP split, instead of setting page->private - * to zero like for every other page that has PG_private not set. But - * anonymous pages don't use page->private so this is not a problem. - */ -#if 0 -/* This will be needed if page->private will be clobbered in split_huge_page */ -static inline struct page *compound_trans_head(struct page *page) -{ - if (PageTail(page)) { - struct page *head; - head = page->first_page; - smp_rmb(); - /* - * head may be a dangling pointer. - * __split_huge_page_refcount clears PageTail before - * overwriting first_page, so if PageTail is still - * there it means the head pointer isn't dangling. - */ - if (PageTail(page)) - return head; - } - return page; -} -#else -#define compound_trans_head(page) compound_head(page) -#endif extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); @@ -226,7 +186,6 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define split_huge_page_pmd_mm(__mm, __address, __pmd) \ do { } while (0) -#define compound_trans_head(page) compound_head(page) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { diff --git a/include/linux/mm.h b/include/linux/mm.h index f28f46eade6a..03ab3e58f511 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -399,8 +399,18 @@ static inline void compound_unlock_irqrestore(struct page *page, static inline struct page *compound_head(struct page *page) { - if (unlikely(PageTail(page))) - return page->first_page; + if (unlikely(PageTail(page))) { + struct page *head = page->first_page; + + /* + * page->first_page may be a dangling pointer to an old + * compound page, so recheck that it is still a tail + * page before returning. + */ + smp_rmb(); + if (likely(PageTail(page))) + return head; + } return page; } diff --git a/mm/ksm.c b/mm/ksm.c index aa4c7c7250c1..68710e80994a 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item) static struct page *page_trans_compound_anon(struct page *page) { if (PageTransCompound(page)) { - struct page *head = compound_trans_head(page); + struct page *head = compound_head(page); /* * head may actually be splitted and freed from under * us but it's ok here. diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2f2f34a4e77d..90002ea43638 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1651,7 +1651,7 @@ int soft_offline_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_trans_head(page); + struct page *hpage = compound_head(page); if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e3758a09a009..3d1bf889465a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -369,9 +369,11 @@ void prep_compound_page(struct page *page, unsigned long order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - __SetPageTail(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } diff --git a/mm/swap.c b/mm/swap.c index b31ba67d440a..0092097b3f4c 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -98,7 +98,7 @@ static void put_compound_page(struct page *page) } /* __split_huge_page_refcount can run under us */ - page_head = compound_trans_head(page); + page_head = compound_head(page); /* * THP can not break up slab pages so avoid taking @@ -253,7 +253,7 @@ bool __get_page_tail(struct page *page) */ unsigned long flags; bool got; - struct page *page_head = compound_trans_head(page); + struct page *page_head = compound_head(page); /* Ref to put_compound_page() comment. */ if (!__compound_tail_refcounted(page_head)) { -- cgit v1.2.3 From 9050d7eba40b3d79551668f54e68fd6f51945ef3 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 3 Mar 2014 15:38:27 -0800 Subject: mm: include VM_MIXEDMAP flag in the VM_SPECIAL list to avoid m(un)locking Daniel Borkmann reported a VM_BUG_ON assertion failing: ------------[ cut here ]------------ kernel BUG at mm/mlock.c:528! invalid opcode: 0000 [#1] SMP Modules linked in: ccm arc4 iwldvm [...] video CPU: 3 PID: 2266 Comm: netsniff-ng Not tainted 3.14.0-rc2+ #8 Hardware name: LENOVO 2429BP3/2429BP3, BIOS G4ET37WW (1.12 ) 05/29/2012 task: ffff8801f87f9820 ti: ffff88002cb44000 task.ti: ffff88002cb44000 RIP: 0010:[] [] munlock_vma_pages_range+0x2e0/0x2f0 Call Trace: do_munmap+0x18f/0x3b0 vm_munmap+0x41/0x60 SyS_munmap+0x22/0x30 system_call_fastpath+0x1a/0x1f RIP munlock_vma_pages_range+0x2e0/0x2f0 ---[ end trace a0088dcf07ae10f2 ]--- because munlock_vma_pages_range() thinks it's unexpectedly in the middle of a THP page. This can be reproduced with default config since 3.11 kernels. A reproducer can be found in the kernel's selftest directory for networking by running ./psock_tpacket. The problem is that an order=2 compound page (allocated by alloc_one_pg_vec_page() is part of the munlocked VM_MIXEDMAP vma (mapped by packet_mmap()) and mistaken for a THP page and assumed to be order=9. The checks for THP in munlock came with commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages"), i.e. since 3.9, but did not trigger a bug. It just makes munlock_vma_pages_range() skip such compound pages until the next 512-pages-aligned page, when it encounters a head page. This is however not a problem for vma's where mlocking has no effect anyway, but it can distort the accounting. Since commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") this can trigger a VM_BUG_ON in PageTransHuge() check. This patch fixes the issue by adding VM_MIXEDMAP flag to VM_SPECIAL, a list of flags that make vma's non-mlockable and non-mergeable. The reasoning is that VM_MIXEDMAP vma's are similar to VM_PFNMAP, which is already on the VM_SPECIAL list, and both are intended for non-LRU pages where mlocking makes no sense anyway. Related Lkml discussion can be found in [2]. [1] tools/testing/selftests/net/psock_tpacket [2] https://lkml.org/lkml/2014/1/10/427 Signed-off-by: Vlastimil Babka Signed-off-by: Daniel Borkmann Reported-by: Daniel Borkmann Tested-by: Daniel Borkmann Cc: Thomas Hellstrom Cc: John David Anglin Cc: HATAYAMA Daisuke Cc: Konstantin Khlebnikov Cc: Carsten Otte Cc: Jared Hulbert Tested-by: Hannes Frederic Sowa Cc: Kirill A. Shutemov Acked-by: Rik van Riel Cc: Andrea Arcangeli Cc: [3.11.x+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/huge_memory.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 03ab3e58f511..a1fe25110f50 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -175,7 +175,7 @@ extern unsigned int kobjsize(const void *objp); * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ -#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP) +#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* * mapping from the currently active vm_flags protection bits (the diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4df39b1bde91..1546655a2d78 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1961,7 +1961,7 @@ out: return ret; } -#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) +#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) -- cgit v1.2.3 From 1ae71d03194ea7424cbd14e449581f67c463d20d Mon Sep 17 00:00:00 2001 From: Liu Ping Fan Date: Mon, 3 Mar 2014 15:38:39 -0800 Subject: mm: numa: bugfix for LAST_CPUPID_NOT_IN_PAGE_FLAGS When doing some numa tests on powerpc, I triggered an oops bug. I find it is caused by using page->_last_cpupid. It should be initialized as "-1 & LAST_CPUPID_MASK", but not "-1". Otherwise, in task_numa_fault(), we will miss the checking (last_cpupid == (-1 & LAST_CPUPID_MASK)). And finally cause an oops bug in task_numa_group(), since the online cpu is less than possible cpu. This happen with CONFIG_SPARSE_VMEMMAP disabled Call trace: SMP NR_CPUS=64 NUMA PowerNV Modules linked in: CPU: 24 PID: 804 Comm: systemd-udevd Not tainted3.13.0-rc1+ #32 task: c000001e2746aa80 ti: c000001e32c50000 task.ti:c000001e32c50000 REGS: c000001e32c53510 TRAP: 0300 Not tainted(3.13.0-rc1+) MSR: 9000000000009032 CR:28024424 XER: 20000000 CFAR: c000000000009324 DAR: 7265717569726857 DSISR:40000000 SOFTE: 1 NIP .task_numa_fault+0x1470/0x2370 LR .task_numa_fault+0x1468/0x2370 Call Trace: .task_numa_fault+0x1468/0x2370 (unreliable) .do_numa_page+0x480/0x4a0 .handle_mm_fault+0x4ec/0xc90 .do_page_fault+0x3a8/0x890 handle_page_fault+0x10/0x30 Instruction dump: 3c82fefb 3884b138 48d9cff1 60000000 48000574 3c62fefb3863af78 3c82fefb 3884b138 48d9cfd5 60000000 e93f0100 <812902e4> 7d2907b45529063e 7d2a07b4 ---[ end trace 15f2510da5ae07cf ]--- Signed-off-by: Liu Ping Fan Signed-off-by: Aneesh Kumar K.V Acked-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index a1fe25110f50..c1b7414c7bef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -767,7 +767,7 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { - return xchg(&page->_last_cpupid, cpupid); + return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) @@ -776,7 +776,7 @@ static inline int page_cpupid_last(struct page *page) } static inline void page_cpupid_reset_last(struct page *page) { - page->_last_cpupid = -1; + page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int page_cpupid_last(struct page *page) -- cgit v1.2.3 From defd884845297fd5690594bfe89656b01f16d87e Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Mon, 3 Feb 2014 12:54:39 -0800 Subject: iscsi/iser-target: Fix isert_conn->state hung shutdown issues This patch addresses a couple of different hug shutdown issues related to wait_event() + isert_conn->state. First, it changes isert_conn->conn_wait + isert_conn->conn_wait_comp_err from waitqueues to completions, and sets ISER_CONN_TERMINATING from within isert_disconnect_work(). Second, it splits isert_free_conn() into isert_wait_conn() that is called earlier in iscsit_close_connection() to ensure that all outstanding commands have completed before continuing. Finally, it breaks isert_cq_comp_err() into seperate TX / RX related code, and adds logic in isert_cq_rx_comp_err() to wait for outstanding commands to complete before setting ISER_CONN_DOWN and calling complete(&isert_conn->conn_wait_comp_err). Acked-by: Sagi Grimberg Cc: Or Gerlitz Cc: #3.10+ Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 106 +++++++++++++++----------------- drivers/infiniband/ulp/isert/ib_isert.h | 4 +- drivers/target/iscsi/iscsi_target.c | 4 ++ include/target/iscsi/iscsi_transport.h | 1 + 4 files changed, 55 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 5eb2b88cf947..862d7b4b0411 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -492,8 +492,8 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_conn->state = ISER_CONN_INIT; INIT_LIST_HEAD(&isert_conn->conn_accept_node); init_completion(&isert_conn->conn_login_comp); - init_waitqueue_head(&isert_conn->conn_wait); - init_waitqueue_head(&isert_conn->conn_wait_comp_err); + init_completion(&isert_conn->conn_wait); + init_completion(&isert_conn->conn_wait_comp_err); kref_init(&isert_conn->conn_kref); kref_get(&isert_conn->conn_kref); mutex_init(&isert_conn->conn_mutex); @@ -688,11 +688,11 @@ isert_disconnect_work(struct work_struct *work) pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); mutex_lock(&isert_conn->conn_mutex); - isert_conn->state = ISER_CONN_DOWN; + if (isert_conn->state == ISER_CONN_UP) + isert_conn->state = ISER_CONN_TERMINATING; if (isert_conn->post_recv_buf_count == 0 && atomic_read(&isert_conn->post_send_buf_count) == 0) { - pr_debug("Calling wake_up(&isert_conn->conn_wait);\n"); mutex_unlock(&isert_conn->conn_mutex); goto wake_up; } @@ -712,7 +712,7 @@ isert_disconnect_work(struct work_struct *work) mutex_unlock(&isert_conn->conn_mutex); wake_up: - wake_up(&isert_conn->conn_wait); + complete(&isert_conn->conn_wait); isert_put_conn(isert_conn); } @@ -1589,7 +1589,7 @@ isert_do_control_comp(struct work_struct *work) pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n"); /* * Call atomic_dec(&isert_conn->post_send_buf_count) - * from isert_free_conn() + * from isert_wait_conn() */ isert_conn->logout_posted = true; iscsit_logout_post_handler(cmd, cmd->conn); @@ -1691,31 +1691,39 @@ isert_send_completion(struct iser_tx_desc *tx_desc, } static void -isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn) +isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn) { struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_cmd *isert_cmd = tx_desc->isert_cmd; + + if (!isert_cmd) + isert_unmap_tx_desc(tx_desc, ib_dev); + else + isert_completion_put(tx_desc, isert_cmd, ib_dev); +} + +static void +isert_cq_rx_comp_err(struct isert_conn *isert_conn) +{ + struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct iscsi_conn *conn = isert_conn->conn; - if (tx_desc) { - struct isert_cmd *isert_cmd = tx_desc->isert_cmd; + if (isert_conn->post_recv_buf_count) + return; - if (!isert_cmd) - isert_unmap_tx_desc(tx_desc, ib_dev); - else - isert_completion_put(tx_desc, isert_cmd, ib_dev); + if (conn->sess) { + target_sess_cmd_list_set_waiting(conn->sess->se_sess); + target_wait_for_sess_cmds(conn->sess->se_sess); } - if (isert_conn->post_recv_buf_count == 0 && - atomic_read(&isert_conn->post_send_buf_count) == 0) { - pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); - pr_debug("Calling wake_up from isert_cq_comp_err\n"); + while (atomic_read(&isert_conn->post_send_buf_count)) + msleep(3000); - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->state != ISER_CONN_DOWN) - isert_conn->state = ISER_CONN_TERMINATING; - mutex_unlock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_DOWN; + mutex_unlock(&isert_conn->conn_mutex); - wake_up(&isert_conn->conn_wait_comp_err); - } + complete(&isert_conn->conn_wait_comp_err); } static void @@ -1740,8 +1748,9 @@ isert_cq_tx_work(struct work_struct *work) pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n"); pr_debug("TX wc.status: 0x%08x\n", wc.status); pr_debug("TX wc.vendor_err: 0x%08x\n", wc.vendor_err); + atomic_dec(&isert_conn->post_send_buf_count); - isert_cq_comp_err(tx_desc, isert_conn); + isert_cq_tx_comp_err(tx_desc, isert_conn); } } @@ -1784,7 +1793,7 @@ isert_cq_rx_work(struct work_struct *work) wc.vendor_err); } isert_conn->post_recv_buf_count--; - isert_cq_comp_err(NULL, isert_conn); + isert_cq_rx_comp_err(isert_conn); } } @@ -2702,22 +2711,11 @@ isert_free_np(struct iscsi_np *np) kfree(isert_np); } -static int isert_check_state(struct isert_conn *isert_conn, int state) -{ - int ret; - - mutex_lock(&isert_conn->conn_mutex); - ret = (isert_conn->state == state); - mutex_unlock(&isert_conn->conn_mutex); - - return ret; -} - -static void isert_free_conn(struct iscsi_conn *conn) +static void isert_wait_conn(struct iscsi_conn *conn) { struct isert_conn *isert_conn = conn->context; - pr_debug("isert_free_conn: Starting \n"); + pr_debug("isert_wait_conn: Starting \n"); /* * Decrement post_send_buf_count for special case when called * from isert_do_control_comp() -> iscsit_logout_post_handler() @@ -2727,38 +2725,29 @@ static void isert_free_conn(struct iscsi_conn *conn) atomic_dec(&isert_conn->post_send_buf_count); if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) { - pr_debug("Calling rdma_disconnect from isert_free_conn\n"); + pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); rdma_disconnect(isert_conn->conn_cm_id); } /* * Only wait for conn_wait_comp_err if the isert_conn made it * into full feature phase.. */ - if (isert_conn->state == ISER_CONN_UP) { - pr_debug("isert_free_conn: Before wait_event comp_err %d\n", - isert_conn->state); - mutex_unlock(&isert_conn->conn_mutex); - - wait_event(isert_conn->conn_wait_comp_err, - (isert_check_state(isert_conn, ISER_CONN_TERMINATING))); - - wait_event(isert_conn->conn_wait, - (isert_check_state(isert_conn, ISER_CONN_DOWN))); - - isert_put_conn(isert_conn); - return; - } if (isert_conn->state == ISER_CONN_INIT) { mutex_unlock(&isert_conn->conn_mutex); - isert_put_conn(isert_conn); return; } - pr_debug("isert_free_conn: wait_event conn_wait %d\n", - isert_conn->state); + if (isert_conn->state == ISER_CONN_UP) + isert_conn->state = ISER_CONN_TERMINATING; mutex_unlock(&isert_conn->conn_mutex); - wait_event(isert_conn->conn_wait, - (isert_check_state(isert_conn, ISER_CONN_DOWN))); + wait_for_completion(&isert_conn->conn_wait_comp_err); + + wait_for_completion(&isert_conn->conn_wait); +} + +static void isert_free_conn(struct iscsi_conn *conn) +{ + struct isert_conn *isert_conn = conn->context; isert_put_conn(isert_conn); } @@ -2771,6 +2760,7 @@ static struct iscsit_transport iser_target_transport = { .iscsit_setup_np = isert_setup_np, .iscsit_accept_np = isert_accept_np, .iscsit_free_np = isert_free_np, + .iscsit_wait_conn = isert_wait_conn, .iscsit_free_conn = isert_free_conn, .iscsit_get_login_rx = isert_get_login_rx, .iscsit_put_login_tx = isert_put_login_tx, diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 708a069002f3..41e799ff8ecc 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -116,8 +116,8 @@ struct isert_conn { struct isert_device *conn_device; struct work_struct conn_logout_work; struct mutex conn_mutex; - wait_queue_head_t conn_wait; - wait_queue_head_t conn_wait_comp_err; + struct completion conn_wait; + struct completion conn_wait_comp_err; struct kref conn_kref; struct list_head conn_fr_pool; int conn_fr_pool_size; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index ece82b0d8ea3..b83ec378d04f 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4196,6 +4196,10 @@ int iscsit_close_connection( iscsit_stop_timers_for_cmds(conn); iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + iscsit_free_queue_reqs_for_conn(conn); /* diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index ae5a17111968..4483fadfa68d 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -12,6 +12,7 @@ struct iscsit_transport { int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *); int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *); void (*iscsit_free_np)(struct iscsi_np *); + void (*iscsit_wait_conn)(struct iscsi_conn *); void (*iscsit_free_conn)(struct iscsi_conn *); int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *); int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32); -- cgit v1.2.3 From 70044d71d31d6973665ced5be04ef39ac1c09a48 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 7 Mar 2014 10:19:57 -0500 Subject: firewire: don't use PREPARE_DELAYED_WORK PREPARE_[DELAYED_]WORK() are being phased out. They have few users and a nasty surprise in terms of reentrancy guarantee as workqueue considers work items to be different if they don't have the same work function. firewire core-device and sbp2 have been been multiplexing work items with multiple work functions. Introduce fw_device_workfn() and sbp2_lu_workfn() which invoke fw_device->workfn and sbp2_logical_unit->workfn respectively and always use the two functions as the work functions and update the users to set the ->workfn fields instead of overriding work functions using PREPARE_DELAYED_WORK(). This fixes a variety of possible regressions since a2c1c57be8d9 "workqueue: consider work function when searching for busy work items" due to which fw_workqueue lost its required non-reentrancy property. Signed-off-by: Tejun Heo Acked-by: Stefan Richter Cc: linux1394-devel@lists.sourceforge.net Cc: stable@vger.kernel.org # v3.9+ Cc: stable@vger.kernel.org # v3.8.2+ Cc: stable@vger.kernel.org # v3.4.60+ Cc: stable@vger.kernel.org # v3.2.40+ --- drivers/firewire/core-device.c | 22 +++++++++++++++------- drivers/firewire/sbp2.c | 17 +++++++++++++---- include/linux/firewire.h | 1 + 3 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index de4aa409abe2..2c6d5e118ac1 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -916,7 +916,7 @@ static int lookup_existing_device(struct device *dev, void *data) old->config_rom_retries = 0; fw_notice(card, "rediscovered device %s\n", dev_name(dev)); - PREPARE_DELAYED_WORK(&old->work, fw_device_update); + old->workfn = fw_device_update; fw_schedule_device_work(old, 0); if (current_node == card->root_node) @@ -1075,7 +1075,7 @@ static void fw_device_init(struct work_struct *work) if (atomic_cmpxchg(&device->state, FW_DEVICE_INITIALIZING, FW_DEVICE_RUNNING) == FW_DEVICE_GONE) { - PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + device->workfn = fw_device_shutdown; fw_schedule_device_work(device, SHUTDOWN_DELAY); } else { fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n", @@ -1196,13 +1196,20 @@ static void fw_device_refresh(struct work_struct *work) dev_name(&device->device), fw_rcode_string(ret)); gone: atomic_set(&device->state, FW_DEVICE_GONE); - PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + device->workfn = fw_device_shutdown; fw_schedule_device_work(device, SHUTDOWN_DELAY); out: if (node_id == card->root_node->node_id) fw_schedule_bm_work(card, 0); } +static void fw_device_workfn(struct work_struct *work) +{ + struct fw_device *device = container_of(to_delayed_work(work), + struct fw_device, work); + device->workfn(work); +} + void fw_node_event(struct fw_card *card, struct fw_node *node, int event) { struct fw_device *device; @@ -1252,7 +1259,8 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) * power-up after getting plugged in. We schedule the * first config rom scan half a second after bus reset. */ - INIT_DELAYED_WORK(&device->work, fw_device_init); + device->workfn = fw_device_init; + INIT_DELAYED_WORK(&device->work, fw_device_workfn); fw_schedule_device_work(device, INITIAL_DELAY); break; @@ -1268,7 +1276,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) if (atomic_cmpxchg(&device->state, FW_DEVICE_RUNNING, FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) { - PREPARE_DELAYED_WORK(&device->work, fw_device_refresh); + device->workfn = fw_device_refresh; fw_schedule_device_work(device, device->is_local ? 0 : INITIAL_DELAY); } @@ -1283,7 +1291,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) smp_wmb(); /* update node_id before generation */ device->generation = card->generation; if (atomic_read(&device->state) == FW_DEVICE_RUNNING) { - PREPARE_DELAYED_WORK(&device->work, fw_device_update); + device->workfn = fw_device_update; fw_schedule_device_work(device, 0); } break; @@ -1308,7 +1316,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) device = node->data; if (atomic_xchg(&device->state, FW_DEVICE_GONE) == FW_DEVICE_RUNNING) { - PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + device->workfn = fw_device_shutdown; fw_schedule_device_work(device, list_empty(&card->link) ? 0 : SHUTDOWN_DELAY); } diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 281029daf98c..7aef911fdc71 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -146,6 +146,7 @@ struct sbp2_logical_unit { */ int generation; int retries; + work_func_t workfn; struct delayed_work work; bool has_sdev; bool blocked; @@ -864,7 +865,7 @@ static void sbp2_login(struct work_struct *work) /* set appropriate retry limit(s) in BUSY_TIMEOUT register */ sbp2_set_busy_timeout(lu); - PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect); + lu->workfn = sbp2_reconnect; sbp2_agent_reset(lu); /* This was a re-login. */ @@ -918,7 +919,7 @@ static void sbp2_login(struct work_struct *work) * If a bus reset happened, sbp2_update will have requeued * lu->work already. Reset the work from reconnect to login. */ - PREPARE_DELAYED_WORK(&lu->work, sbp2_login); + lu->workfn = sbp2_login; } static void sbp2_reconnect(struct work_struct *work) @@ -952,7 +953,7 @@ static void sbp2_reconnect(struct work_struct *work) lu->retries++ >= 5) { dev_err(tgt_dev(tgt), "failed to reconnect\n"); lu->retries = 0; - PREPARE_DELAYED_WORK(&lu->work, sbp2_login); + lu->workfn = sbp2_login; } sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5)); @@ -972,6 +973,13 @@ static void sbp2_reconnect(struct work_struct *work) sbp2_conditionally_unblock(lu); } +static void sbp2_lu_workfn(struct work_struct *work) +{ + struct sbp2_logical_unit *lu = container_of(to_delayed_work(work), + struct sbp2_logical_unit, work); + lu->workfn(work); +} + static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry) { struct sbp2_logical_unit *lu; @@ -998,7 +1006,8 @@ static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry) lu->blocked = false; ++tgt->dont_block; INIT_LIST_HEAD(&lu->orb_list); - INIT_DELAYED_WORK(&lu->work, sbp2_login); + lu->workfn = sbp2_login; + INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn); list_add_tail(&lu->link, &tgt->lu_list); return 0; diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 5d7782e42b8f..c3683bdf28fe 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -200,6 +200,7 @@ struct fw_device { unsigned irmc:1; unsigned bc_implemented:2; + work_func_t workfn; struct delayed_work work; struct fw_attribute_group attribute_group; }; -- cgit v1.2.3 From 2ca310fc4160ed0420da65534a21ae77b24326a8 Mon Sep 17 00:00:00 2001 From: Ditang Chen Date: Fri, 7 Mar 2014 13:27:57 +0800 Subject: SUNRPC: Fix oops when trace sunrpc_task events in nfs client When tracking sunrpc_task events in nfs client, the clnt pointer may be NULL. [ 139.269266] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [ 139.269915] IP: [] ftrace_raw_event_rpc_task_running+0x86/0xf0 [sunrpc] [ 139.269915] PGD 1d293067 PUD 1d294067 PMD 0 [ 139.269915] Oops: 0000 [#1] SMP [ 139.269915] Modules linked in: nfsv4 dns_resolver nfs lockd sunrpc fscache sg ppdev e1000 serio_raw pcspkr parport_pc parport i2c_piix4 i2c_core microcode xfs libcrc32c sd_mod sr_mod cdrom ata_generic crc_t10dif crct10dif_common pata_acpi ahci libahci ata_piix libata dm_mirror dm_region_hash dm_log dm_mod [ 139.269915] CPU: 0 PID: 59 Comm: kworker/0:2 Not tainted 3.10.0-84.el7.x86_64 #1 [ 139.269915] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 139.269915] Workqueue: rpciod rpc_async_schedule [sunrpc] [ 139.269915] task: ffff88001b598000 ti: ffff88001b632000 task.ti: ffff88001b632000 [ 139.269915] RIP: 0010:[] [] ftrace_raw_event_rpc_task_running+0x86/0xf0 [sunrpc] [ 139.269915] RSP: 0018:ffff88001b633d70 EFLAGS: 00010206 [ 139.269915] RAX: ffff88001dfc5338 RBX: ffff88001cc37a00 RCX: ffff88001dfc5334 [ 139.269915] RDX: ffff88001dfc5338 RSI: 0000000000000000 RDI: ffff88001dfc533c [ 139.269915] RBP: ffff88001b633db0 R08: 000000000000002c R09: 000000000000000a [ 139.269915] R10: 0000000000062180 R11: 00000020759fb9dc R12: ffffffffa0292c20 [ 139.269915] R13: ffff88001dfc5334 R14: 0000000000000000 R15: 0000000000000000 [ 139.269915] FS: 0000000000000000(0000) GS:ffff88001fc00000(0000) knlGS:0000000000000000 [ 139.269915] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 139.269915] CR2: 0000000000000004 CR3: 000000001d290000 CR4: 00000000000006f0 [ 139.269915] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 139.269915] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 139.269915] Stack: [ 139.269915] 000000001b633d98 0000000000000246 ffff88001df1dc00 ffff88001cc37a00 [ 139.269915] ffff88001bc35e60 0000000000000000 ffff88001ffa0a48 ffff88001bc35ee0 [ 139.269915] ffff88001b633e08 ffffffffa02704b5 0000000000010000 ffff88001cc37a70 [ 139.269915] Call Trace: [ 139.269915] [] __rpc_execute+0x1d5/0x400 [sunrpc] [ 139.269915] [] rpc_async_schedule+0x26/0x30 [sunrpc] [ 139.269915] [] process_one_work+0x17b/0x460 [ 139.269915] [] worker_thread+0x11b/0x400 [ 139.269915] [] ? rescuer_thread+0x3e0/0x3e0 [ 139.269915] [] kthread+0xc0/0xd0 [ 139.269915] [] ? kthread_create_on_node+0x110/0x110 [ 139.269915] [] ret_from_fork+0x7c/0xb0 [ 139.269915] [] ? kthread_create_on_node+0x110/0x110 [ 139.269915] Code: 4c 8b 45 c8 48 8d 7d d0 89 4d c4 41 89 c9 b9 28 00 00 00 e8 9d b4 e9 e0 48 85 c0 49 89 c5 74 a2 48 89 c7 e8 9d 3f e9 e0 48 89 c2 <41> 8b 46 04 48 8b 7d d0 4c 89 e9 4c 89 e6 89 42 0c 0f b7 83 d4 [ 139.269915] RIP [] ftrace_raw_event_rpc_task_running+0x86/0xf0 [sunrpc] [ 139.269915] RSP [ 139.269915] CR2: 0000000000000004 [ 140.946406] ---[ end trace ba486328b98d7622 ]--- Signed-off-by: Ditang Chen Signed-off-by: Trond Myklebust --- include/trace/events/sunrpc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ddc179b7a105..1fef3e6e9436 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -83,7 +83,7 @@ DECLARE_EVENT_CLASS(rpc_task_running, ), TP_fast_assign( - __entry->client_id = clnt->cl_clid; + __entry->client_id = clnt ? clnt->cl_clid : -1; __entry->task_id = task->tk_pid; __entry->action = action; __entry->runstate = task->tk_runstate; @@ -91,7 +91,7 @@ DECLARE_EVENT_CLASS(rpc_task_running, __entry->flags = task->tk_flags; ), - TP_printk("task:%u@%u flags=%4.4x state=%4.4lx status=%d action=%pf", + TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d action=%pf", __entry->task_id, __entry->client_id, __entry->flags, __entry->runstate, -- cgit v1.2.3 From c1bacbae8192dd2a9ebadd22d793b68054f6c6e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 8 Mar 2014 08:59:58 +0100 Subject: genirq: Provide irq_request/release_resources chip callbacks For certain irq types, e.g. gpios, it's necessary to request resources before starting up the irq. This might fail so we cannot use the irq_startup() callback because we might call the irq_set_type() callback before that which does not make sense when the resource is not available. Calling irq_startup() before irq_set_type() can lead to spurious interrupts which is not desired either. Signed-off-by: Thomas Gleixner Cc: Jean-Jacques Hiblot Cc: Grant Likely Cc: linux-arm-kernel@lists.infradead.org Reviewed-by: Linus Walleij Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1403080857160.18573@ionos.tec.linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 6 ++++++ kernel/irq/manage.c | 28 +++++++++++++++++++++++++++- 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 7dc10036eff5..e675971bdc3f 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -303,6 +303,10 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @irq_pm_shutdown: function called from core code on shutdown once per chip * @irq_calc_mask: Optional function to set irq_data.mask for special cases * @irq_print_chip: optional to print special chip info in show_interrupts + * @irq_request_resources: optional to request resources before calling + * any other callback related to this irq + * @irq_release_resources: optional to release resources acquired with + * irq_request_resources * @flags: chip specific flags */ struct irq_chip { @@ -336,6 +340,8 @@ struct irq_chip { void (*irq_calc_mask)(struct irq_data *data); void (*irq_print_chip)(struct irq_data *data, struct seq_file *p); + int (*irq_request_resources)(struct irq_data *data); + void (*irq_release_resources)(struct irq_data *data); unsigned long flags; }; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index d3bf660cb57f..5d35cbe22896 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -896,6 +896,23 @@ static void irq_setup_forced_threading(struct irqaction *new) } } +static int irq_request_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + return c->irq_request_resources ? c->irq_request_resources(d) : 0; +} + +static void irq_release_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + if (c->irq_release_resources) + c->irq_release_resources(d); +} + /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. @@ -1091,6 +1108,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { + ret = irq_request_resources(desc); + if (ret) { + pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", + new->name, irq, desc->irq_data.chip->name); + goto out_mask; + } + init_waitqueue_head(&desc->wait_for_threads); /* Setup the type (level, edge polarity) if configured: */ @@ -1261,8 +1285,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) *action_ptr = action->next; /* If this was the last handler, shut down the IRQ line: */ - if (!desc->action) + if (!desc->action) { irq_shutdown(desc); + irq_release_resources(desc); + } #ifdef CONFIG_SMP /* make sure affinity_hint is cleaned up */ -- cgit v1.2.3