diff --git a/Documentation/arm/CCN.txt b/Documentation/arm/CCN.txt index 0632b3aad83e..715776f06df6 100644 --- a/Documentation/arm/CCN.txt +++ b/Documentation/arm/CCN.txt @@ -38,7 +38,7 @@ Example of perf tool use: / # perf list | grep ccn ccn/cycles/ [Kernel PMU event] <...> - ccn/xp_valid_flit/ [Kernel PMU event] + ccn/xp_valid_flit,xp=?,port=?,vc=?,dir=?/ [Kernel PMU event] <...> / # perf stat -C 0 -e ccn/cycles/,ccn/xp_valid_flit,xp=1,port=0,vc=1,dir=1/ \ diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index e69274de8d0c..0500895b768f 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -287,8 +287,8 @@ implementing on-disk size changes. Start with a copy of the old inode_setattr and vmtruncate, and the reorder the vmtruncate + foofs_vmtruncate sequence to be in order of zeroing blocks using block_truncate_page or similar helpers, size update and on finally on-disk truncation which should not fail. -inode_change_ok now includes the size checks for ATTR_SIZE and must be called -in the beginning of ->setattr unconditionally. +setattr_prepare (which used to be inode_change_ok) now includes the size checks +for ATTR_SIZE and must be called in the beginning of ->setattr unconditionally. [mandatory] diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 302b5ed616a6..35e17f748ca7 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -265,6 +265,13 @@ aio-nr can grow to. ============================================================== +mount-max: + +This denotes the maximum number of mounts that may exist +in a mount namespace. + +============================================================== + 2. /proc/sys/fs/binfmt_misc ---------------------------------------------------------- diff --git a/Makefile b/Makefile index aa9fbee620ff..df72b644f78c 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 1 -SUBLEVEL = 36 +SUBLEVEL = 37 EXTRAVERSION = NAME = Series 4800 diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index b52101d37ec7..ee21eecbe0d2 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -117,7 +117,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) /* The ARM override for dma_max_pfn() */ static inline unsigned long dma_max_pfn(struct device *dev) { - return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask); + return dma_to_pfn(dev, *dev->dma_mask); } #define dma_max_pfn(dev) dma_max_pfn(dev) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index cd791948b286..7e459b7ee708 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -32,7 +32,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); /* Initialize cr4 shadow for this CPU. */ static inline void cr4_init_shadow(void) { - this_cpu_write(cpu_tlbstate.cr4, __read_cr4()); + this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe()); } /* Set in this cpu's CR4. */ diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 2c835e356349..d445c5f1aeb1 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -12,6 +12,7 @@ targets += purgatory.ro KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large KBUILD_CFLAGS += -m$(BITS) +KBUILD_CFLAGS += $(call cc-option,-fno-PIE) $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c index 27fd0dacad5f..4d523cfe51ce 100644 --- a/drivers/bus/arm-ccn.c +++ b/drivers/bus/arm-ccn.c @@ -183,6 +183,7 @@ struct arm_ccn { struct arm_ccn_component *xp; struct arm_ccn_dt dt; + int mn_id; }; @@ -322,6 +323,7 @@ struct arm_ccn_pmu_event { static ssize_t arm_ccn_pmu_event_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev)); struct arm_ccn_pmu_event *event = container_of(attr, struct arm_ccn_pmu_event, attr); ssize_t res; @@ -336,6 +338,26 @@ static ssize_t arm_ccn_pmu_event_show(struct device *dev, if (event->mask) res += snprintf(buf + res, PAGE_SIZE - res, ",mask=0x%x", event->mask); + + /* Arguments required by an event */ + switch (event->type) { + case CCN_TYPE_CYCLES: + break; + case CCN_TYPE_XP: + res += snprintf(buf + res, PAGE_SIZE - res, + ",xp=?,port=?,vc=?,dir=?"); + if (event->event == CCN_EVENT_WATCHPOINT) + res += snprintf(buf + res, PAGE_SIZE - res, + ",cmp_l=?,cmp_h=?,mask=?"); + break; + case CCN_TYPE_MN: + res += snprintf(buf + res, PAGE_SIZE - res, ",node=%d", ccn->mn_id); + break; + default: + res += snprintf(buf + res, PAGE_SIZE - res, ",node=?"); + break; + } + res += snprintf(buf + res, PAGE_SIZE - res, "\n"); return res; @@ -360,9 +382,9 @@ static umode_t arm_ccn_pmu_events_is_visible(struct kobject *kobj, } static struct arm_ccn_pmu_event arm_ccn_pmu_events[] = { - CCN_EVENT_MN(eobarrier, "dir=0,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE), - CCN_EVENT_MN(ecbarrier, "dir=0,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE), - CCN_EVENT_MN(dvmop, "dir=0,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE), + CCN_EVENT_MN(eobarrier, "dir=1,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE), + CCN_EVENT_MN(ecbarrier, "dir=1,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE), + CCN_EVENT_MN(dvmop, "dir=1,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE), CCN_EVENT_HNI(txdatflits, "dir=1,vc=3", CCN_IDX_MASK_ANY), CCN_EVENT_HNI(rxdatflits, "dir=0,vc=3", CCN_IDX_MASK_ANY), CCN_EVENT_HNI(txreqflits, "dir=1,vc=0", CCN_IDX_MASK_ANY), @@ -649,6 +671,12 @@ static int arm_ccn_pmu_event_init(struct perf_event *event) /* Validate node/xp vs topology */ switch (type) { + case CCN_TYPE_MN: + if (node_xp != ccn->mn_id) { + dev_warn(ccn->dev, "Invalid MN ID %d!\n", node_xp); + return -EINVAL; + } + break; case CCN_TYPE_XP: if (node_xp >= ccn->num_xps) { dev_warn(ccn->dev, "Invalid XP ID %d!\n", node_xp); @@ -1214,6 +1242,8 @@ static int arm_ccn_init_nodes(struct arm_ccn *ccn, int region, switch (type) { case CCN_TYPE_MN: + ccn->mn_id = id; + return 0; case CCN_TYPE_DT: return 0; case CCN_TYPE_XP: diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index cd0554f68316..4ff8c334e7c8 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -55,6 +55,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, return submit; } +static inline unsigned long __must_check +copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) +{ + if (access_ok(VERIFY_READ, from, n)) + return __copy_from_user_inatomic(to, from, n); + return -EFAULT; +} + static int submit_lookup_objects(struct msm_gem_submit *submit, struct drm_msm_gem_submit *args, struct drm_file *file) { @@ -62,6 +70,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, int ret = 0; spin_lock(&file->table_lock); + pagefault_disable(); for (i = 0; i < args->nr_bos; i++) { struct drm_msm_gem_submit_bo submit_bo; @@ -70,10 +79,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, void __user *userptr = to_user_ptr(args->bos + (i * sizeof(submit_bo))); - ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo)); - if (ret) { - ret = -EFAULT; - goto out_unlock; + ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo)); + if (unlikely(ret)) { + pagefault_enable(); + spin_unlock(&file->table_lock); + ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo)); + if (ret) + goto out; + spin_lock(&file->table_lock); + pagefault_disable(); } if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) { @@ -113,9 +127,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, } out_unlock: - submit->nr_bos = i; + pagefault_enable(); spin_unlock(&file->table_lock); +out: + submit->nr_bos = i; + return ret; } diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c index feb6d18de78d..16970fccc5cd 100644 --- a/drivers/mtd/nand/davinci_nand.c +++ b/drivers/mtd/nand/davinci_nand.c @@ -241,6 +241,9 @@ static void nand_davinci_hwctl_4bit(struct mtd_info *mtd, int mode) unsigned long flags; u32 val; + /* Reset ECC hardware */ + davinci_nand_readl(info, NAND_4BIT_ECC1_OFFSET); + spin_lock_irqsave(&davinci_nand_lock, flags); /* Start 4-bit ECC calculation for read/write */ diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index ad535a854e5c..eab132778e67 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -471,9 +472,8 @@ EXPORT_SYMBOL_GPL(can_free_echo_skb); /* * CAN device restart for bus-off recovery */ -static void can_restart(unsigned long data) +static void can_restart(struct net_device *dev) { - struct net_device *dev = (struct net_device *)data; struct can_priv *priv = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; struct sk_buff *skb; @@ -513,6 +513,14 @@ restart: netdev_err(dev, "Error %d during restart", err); } +static void can_restart_work(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct can_priv *priv = container_of(dwork, struct can_priv, restart_work); + + can_restart(priv->dev); +} + int can_restart_now(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -526,8 +534,8 @@ int can_restart_now(struct net_device *dev) if (priv->state != CAN_STATE_BUS_OFF) return -EBUSY; - /* Runs as soon as possible in the timer context */ - mod_timer(&priv->restart_timer, jiffies); + cancel_delayed_work_sync(&priv->restart_work); + can_restart(dev); return 0; } @@ -548,8 +556,8 @@ void can_bus_off(struct net_device *dev) netif_carrier_off(dev); if (priv->restart_ms) - mod_timer(&priv->restart_timer, - jiffies + (priv->restart_ms * HZ) / 1000); + schedule_delayed_work(&priv->restart_work, + msecs_to_jiffies(priv->restart_ms)); } EXPORT_SYMBOL_GPL(can_bus_off); @@ -658,6 +666,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) return NULL; priv = netdev_priv(dev); + priv->dev = dev; if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; @@ -667,7 +676,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max) priv->state = CAN_STATE_STOPPED; - init_timer(&priv->restart_timer); + INIT_DELAYED_WORK(&priv->restart_work, can_restart_work); return dev; } @@ -748,8 +757,6 @@ int open_candev(struct net_device *dev) if (!netif_carrier_ok(dev)) netif_carrier_on(dev); - setup_timer(&priv->restart_timer, can_restart, (unsigned long)dev); - return 0; } EXPORT_SYMBOL_GPL(open_candev); @@ -764,7 +771,7 @@ void close_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); - del_timer_sync(&priv->restart_timer); + cancel_delayed_work_sync(&priv->restart_work); can_flush_echo_skb(dev); } EXPORT_SYMBOL_GPL(close_candev); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 940f78e41993..d9e873c3a273 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -635,7 +635,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, } } - pp = eth_gro_receive(head, skb); + pp = call_gro_receive(eth_gro_receive, head, skb); out: skb_gro_remcsum_cleanup(skb, &grc); diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 2926295a936d..c9f87cdc85c1 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -2300,7 +2300,8 @@ static int arcmsr_iop_message_xfer(struct AdapterControlBlock *acb, } case ARCMSR_MESSAGE_WRITE_WQBUFFER: { unsigned char *ver_addr; - int32_t user_len, cnt2end; + uint32_t user_len; + int32_t cnt2end; uint8_t *pQbuffer, *ptmpuserbuffer; ver_addr = kmalloc(ARCMSR_API_DATA_BUFLEN, GFP_ATOMIC); if (!ver_addr) { @@ -2309,6 +2310,11 @@ static int arcmsr_iop_message_xfer(struct AdapterControlBlock *acb, } ptmpuserbuffer = ver_addr; user_len = pcmdmessagefld->cmdmessage.Length; + if (user_len > ARCMSR_API_DATA_BUFLEN) { + retvalue = ARCMSR_MESSAGE_FAIL; + kfree(ver_addr); + goto message_out; + } memcpy(ptmpuserbuffer, pcmdmessagefld->messagedatabuffer, user_len); spin_lock_irqsave(&acb->wqbuffer_lock, flags); diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 14e5c7cea929..1fcd31c6b37b 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -1862,7 +1862,7 @@ struct megasas_instance_template { }; #define MEGASAS_IS_LOGICAL(scp) \ - (scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1 + ((scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) #define MEGASAS_DEV_INDEX(inst, scp) \ ((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index a27af7882170..d60425996948 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -1323,7 +1323,7 @@ int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, bool hsm_import) attr->ia_valid |= ATTR_MTIME | ATTR_CTIME; } - /* POSIX: check before ATTR_*TIME_SET set (from inode_change_ok) */ + /* POSIX: check before ATTR_*TIME_SET set (from setattr_prepare) */ if (attr->ia_valid & TIMES_SET_FLAGS) { if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CFS_CAP_FOWNER)) diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 31c010372660..de59b4892bfb 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -320,32 +320,26 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - retval = posix_acl_equiv_mode(acl, &mode); - if (retval < 0) + struct iattr iattr; + + retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); + if (retval) goto err_out; - else { - struct iattr iattr; - if (retval == 0) { - /* - * ACL can be represented - * by the mode bits. So don't - * update ACL. - */ - acl = NULL; - value = NULL; - size = 0; - } - /* Updte the mode bits */ - iattr.ia_mode = ((mode & S_IALLUGO) | - (inode->i_mode & ~S_IALLUGO)); - iattr.ia_valid = ATTR_MODE; - /* FIXME should we update ctime ? - * What is the following setxattr update the - * mode ? + if (!acl) { + /* + * ACL can be represented + * by the mode bits. So don't + * update ACL. */ - v9fs_vfs_setattr_dotl(dentry, &iattr); + value = NULL; + size = 0; } + iattr.ia_valid = ATTR_MODE; + /* FIXME should we update ctime ? + * What is the following setxattr update the + * mode ? + */ + v9fs_vfs_setattr_dotl(dentry, &iattr); } break; case ACL_TYPE_DEFAULT: diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 53f1e8a21707..99c3c4ffe1d9 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1094,7 +1094,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) struct p9_wstat wstat; p9_debug(P9_DEBUG_VFS, "\n"); - retval = inode_change_ok(d_inode(dentry), iattr); + retval = setattr_prepare(dentry, iattr); if (retval) return retval; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 4d3ecfb55fcf..ce7ab92f7e84 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -560,7 +560,7 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) p9_debug(P9_DEBUG_VFS, "\n"); - retval = inode_change_ok(inode, iattr); + retval = setattr_prepare(dentry, iattr); if (retval) return retval; diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 335055d828e4..f57baaa511aa 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -303,7 +303,7 @@ adfs_notify_change(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid = attr->ia_valid; int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); /* * we can't change the UID or GID of any file - diff --git a/fs/affs/inode.c b/fs/affs/inode.c index a022f4accd76..87953b94a5ae 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -218,7 +218,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr) pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid); - error = inode_change_ok(inode,attr); + error = setattr_prepare(dentry, attr); if (error) goto out; diff --git a/fs/attr.c b/fs/attr.c index 6530ced19697..ee697ddc6c2e 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -17,19 +17,22 @@ #include /** - * inode_change_ok - check if attribute changes to an inode are allowed - * @inode: inode to check + * setattr_prepare - check if attribute changes to a dentry are allowed + * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr - * in the given inode. This includes the normal unix access permission - * checks, as well as checks for rlimits and others. + * in the given dentry. This includes the normal unix access permission + * checks, as well as checks for rlimits and others. The function also clears + * SGID bit from mode if user is not allowed to set it. Also file capabilities + * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ -int inode_change_ok(const struct inode *inode, struct iattr *attr) +int setattr_prepare(struct dentry *dentry, struct iattr *attr) { + struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* @@ -44,7 +47,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) - return 0; + goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && @@ -77,9 +80,19 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) return -EPERM; } +kill_priv: + /* User has permission for the change */ + if (ia_valid & ATTR_KILL_PRIV) { + int error; + + error = security_inode_killpriv(dentry); + if (error) + return error; + } + return 0; } -EXPORT_SYMBOL(inode_change_ok); +EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size @@ -217,13 +230,11 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; if (ia_valid & ATTR_KILL_PRIV) { - attr->ia_valid &= ~ATTR_KILL_PRIV; - ia_valid &= ~ATTR_KILL_PRIV; error = security_inode_need_killpriv(dentry); - if (error > 0) - error = security_inode_killpriv(dentry); - if (error) + if (error < 0) return error; + if (error == 0) + ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9a0124a95851..fb3e64d37cb4 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -83,11 +83,9 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &inode->i_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) return ret; - if (ret == 0) - acl = NULL; } ret = 0; break; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c4771af7fd6f..757a34bdd2b9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4975,7 +4975,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) if (btrfs_root_readonly(root)) return -EROFS; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 64fa248343f6..d7496e3dbfc4 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -94,11 +94,9 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &new_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &new_mode, &acl); + if (ret) goto out; - if (ret == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e876e1944519..4484aaf5c478 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1728,7 +1728,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err != 0) return err; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9fb3bc26a2ab..f82dfe7ae3e8 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2134,7 +2134,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = inode_change_ok(inode, attrs); + rc = setattr_prepare(direntry, attrs); if (rc < 0) goto out; @@ -2274,7 +2274,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = inode_change_ok(inode, attrs); + rc = setattr_prepare(direntry, attrs); if (rc < 0) { free_xid(xid); return rc; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index fc850b55db67..661dd53f0040 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -942,7 +942,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) } mutex_unlock(&crypt_stat->cs_mutex); - rc = inode_change_ok(inode, ia); + rc = setattr_prepare(dentry, ia); if (rc) goto out; if (ia->ia_valid & ATTR_SIZE) { diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 786e4cc8c889..159c30c18395 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1038,7 +1038,7 @@ int exofs_setattr(struct dentry *dentry, struct iattr *iattr) if (unlikely(error)) return error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (unlikely(error)) return error; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 27695e6f4e46..d6aeb84e90b6 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -193,15 +193,11 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - inode->i_ctime = CURRENT_TIME_SEC; - mark_inode_dirty(inode); - if (error == 0) - acl = NULL; - } + inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(inode); } break; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index f460ae36d5b7..f08604366cb5 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1547,7 +1547,7 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) return error; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 2ee2dc4351d1..3613e87c688f 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3244,7 +3244,7 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) int error, rc = 0; const unsigned int ia_valid = attr->ia_valid; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 69b1e73026a5..c3fe1e323951 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -196,15 +196,11 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - if (error == 0) - acl = NULL; - } + inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); } break; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 15213a567301..145d6ba4117d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1008,6 +1008,7 @@ struct ext4_inode_info { /* * Mount flags set via mount options or defaults */ +#define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Disable mbcache */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9b55c6f71bf2..5beca5c5413e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4751,7 +4751,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) int orphan = 0; const unsigned int ia_valid = attr->ia_valid; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index afb3eb3e8b0f..4723d8b02747 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1144,6 +1144,7 @@ enum { Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, + Opt_no_mbcache, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, }; @@ -1222,6 +1223,7 @@ static const match_table_t tokens = { {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, {Opt_init_itable, "init_itable=%u"}, + {Opt_no_mbcache, "no_mbcache"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, @@ -1385,6 +1387,7 @@ static const struct mount_opts { {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, + {Opt_no_mbcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_commit, 0, MOPT_GTE0}, {Opt_max_batch_time, 0, MOPT_GTE0}, {Opt_min_batch_time, 0, MOPT_GTE0}, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 16e28c08d1e8..cdc26e54400f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -80,7 +80,7 @@ # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif -static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *); +static void ext4_xattr_cache_insert(struct inode *, struct buffer_head *); static struct buffer_head *ext4_xattr_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); @@ -278,7 +278,6 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, struct ext4_xattr_entry *entry; size_t size; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -300,7 +299,7 @@ bad_block: error = -EIO; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_cache_insert(inode, bh); entry = BFIRST(bh); error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1); if (error == -EIO) @@ -426,7 +425,6 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -448,7 +446,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) error = -EIO; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_cache_insert(inode, bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: @@ -547,7 +545,8 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, int error = 0; struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); - ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr); + if (!test_opt(inode->i_sb, NO_MBCACHE)) + ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr); BUFFER_TRACE(bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bh); if (error) @@ -788,8 +787,9 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (i->value && i->value_len > sb->s_blocksize) return -ENOSPC; if (s->base) { - ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev, - bs->bh->b_blocknr); + if (!test_opt(inode->i_sb, NO_MBCACHE)) + ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev, + bs->bh->b_blocknr); BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) @@ -807,7 +807,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (!IS_LAST_ENTRY(s->first)) ext4_xattr_rehash(header(s->base), s->here); - ext4_xattr_cache_insert(ext4_mb_cache, + ext4_xattr_cache_insert(inode, bs->bh); } unlock_buffer(bs->bh); @@ -892,7 +892,8 @@ inserted: if (error) goto cleanup_dquot; } - mb_cache_entry_release(ce); + if (ce) + mb_cache_entry_release(ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ @@ -939,7 +940,7 @@ getblk_failed: memcpy(new_bh->b_data, s->base, new_bh->b_size); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext4_xattr_cache_insert(ext4_mb_cache, new_bh); + ext4_xattr_cache_insert(inode, new_bh); error = ext4_handle_dirty_xattr_block(handle, inode, new_bh); if (error) @@ -1529,12 +1530,17 @@ ext4_xattr_put_super(struct super_block *sb) * Returns 0, or a negative error number on failure. */ static void -ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) +ext4_xattr_cache_insert(struct inode *inode, struct buffer_head *bh) { + struct super_block *sb = inode->i_sb; + struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); __u32 hash = le32_to_cpu(BHDR(bh)->h_hash); struct mb_cache_entry *ce; int error; + if (test_opt(sb, NO_MBCACHE)) + return; + ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS); if (!ce) { ea_bdebug(bh, "out of memory"); @@ -1609,6 +1615,8 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, struct mb_cache_entry *ce; struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + if (test_opt(inode->i_sb, NO_MBCACHE)) + return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 4320ffab3495..c5e4a1856a0f 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -214,12 +214,10 @@ static int __f2fs_set_acl(struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; set_acl_inode(fi, inode->i_mode); - if (error == 0) - acl = NULL; } break; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2b52e48d7482..85e40c0fdcc4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -617,7 +617,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) struct f2fs_inode_info *fi = F2FS_I(inode); int err; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/fat/file.c b/fs/fat/file.c index 442d50a0e33e..5d37650483c6 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -388,7 +388,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_valid &= ~TIMES_SET_FLAGS; } - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); attr->ia_valid = ia_valid; if (error) { if (sbi->options.quiet) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 0572bca49f15..88b09a33d117 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1602,9 +1602,10 @@ int fuse_flush_times(struct inode *inode, struct fuse_file *ff) * vmtruncate() doesn't allow for this case, so do the rlimit checking * and the actual truncation by hand. */ -int fuse_do_setattr(struct inode *inode, struct iattr *attr, +int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, struct file *file) { + struct inode *inode = d_inode(dentry); struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); FUSE_ARGS(args); @@ -1619,7 +1620,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) attr->ia_valid |= ATTR_FORCE; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; @@ -1718,9 +1719,9 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return -EACCES; if (attr->ia_valid & ATTR_FILE) - return fuse_do_setattr(inode, attr, attr->ia_file); + return fuse_do_setattr(entry, attr, attr->ia_file); else - return fuse_do_setattr(inode, attr, NULL); + return fuse_do_setattr(entry, attr, NULL); } static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index d8f29ef2d819..1f03f0a36e35 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2797,7 +2797,7 @@ static void fuse_do_truncate(struct file *file) attr.ia_file = file; attr.ia_valid |= ATTR_FILE; - fuse_do_setattr(inode, &attr, file); + fuse_do_setattr(file->f_path.dentry, &attr, file); } static inline loff_t fuse_round_up(loff_t off) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 85f9d8273455..30d2bde45f68 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -913,7 +913,7 @@ bool fuse_write_update_size(struct inode *inode, loff_t pos); int fuse_flush_times(struct inode *inode, struct fuse_file *ff); int fuse_write_inode(struct inode *inode, struct writeback_control *wbc); -int fuse_do_setattr(struct inode *inode, struct iattr *attr, +int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, struct file *file); void fuse_set_initialized(struct fuse_conn *fc); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 1be3b061c05c..ff0ac96a8e7b 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -79,17 +79,11 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (type == ACL_TYPE_ACCESS) { umode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - - if (error == 0) - acl = NULL; - - if (mode != inode->i_mode) { - inode->i_mode = mode; + if (mode != inode->i_mode) mark_inode_dirty(inode); - } } if (acl) { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 1b3ca7a2e3fc..6f7f848a3c4e 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1759,7 +1759,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) goto out; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) goto out; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index b99ebddb10cb..6409b8b4afd4 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -604,7 +604,7 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) struct hfs_sb_info *hsb = HFS_SB(inode->i_sb); int error; - error = inode_change_ok(inode, attr); /* basic permission checks */ + error = setattr_prepare(dentry, attr); /* basic permission checks */ if (error) return error; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 6dd107d7421e..d87c8a27e063 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -246,7 +246,7 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index df0c9af68d05..71b3087b7e32 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -68,8 +68,8 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, case ACL_TYPE_ACCESS: xattr_name = POSIX_ACL_XATTR_ACCESS; if (acl) { - err = posix_acl_equiv_mode(acl, &inode->i_mode); - if (err < 0) + err = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (err) return err; } err = 0; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index f895a85d9304..81ce4e4ad0f9 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -812,7 +812,7 @@ static int hostfs_setattr(struct dentry *dentry, struct iattr *attr) int fd = HOSTFS_I(inode)->fd; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 933c73780813..efbed9520fdc 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -272,7 +272,7 @@ int hpfs_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) goto out_unlock; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) goto out_unlock; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 87724c1d7be6..a533d8c66489 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -400,7 +400,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) BUG_ON(!inode); - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 2f7a3c090489..f9f86f87d32b 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -235,9 +235,10 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: xprefix = JFFS2_XPREFIX_ACL_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - rc = posix_acl_equiv_mode(acl, &mode); - if (rc < 0) + umode_t mode; + + rc = posix_acl_update_mode(inode, &mode, &acl); + if (rc) return rc; if (inode->i_mode != mode) { struct iattr attr; @@ -249,8 +250,6 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (rc < 0) return rc; } - if (rc == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index fe5ea080b4ec..6273abad377f 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -193,7 +193,7 @@ int jffs2_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int rc; - rc = inode_change_ok(inode, iattr); + rc = setattr_prepare(dentry, iattr); if (rc) return rc; diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 0c8ca830b113..9fad9f4fe883 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -84,13 +84,11 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, case ACL_TYPE_ACCESS: ea_name = POSIX_ACL_XATTR_ACCESS; if (acl) { - rc = posix_acl_equiv_mode(acl, &inode->i_mode); - if (rc < 0) + rc = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (rc) return rc; inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); - if (rc == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/jfs/file.c b/fs/jfs/file.c index e98d39d75cf4..66d6362a9007 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -103,7 +103,7 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int rc; - rc = inode_change_ok(inode, iattr); + rc = setattr_prepare(dentry, iattr); if (rc) return rc; diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 756dd56aaf60..a17c850a4958 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -119,7 +119,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) return -EINVAL; mutex_lock(&kernfs_mutex); - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) goto out; diff --git a/fs/libfs.c b/fs/libfs.c index f4641fd27bda..50edbdc23cef 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -371,7 +371,7 @@ int simple_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) return error; diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 1a6f0167b16a..3abe1414c3f4 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -244,7 +244,7 @@ static int logfs_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int err = 0; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/minix/file.c b/fs/minix/file.c index 94f0eb9a6e2c..a6a4797aa0d4 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -26,7 +26,7 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/mount.h b/fs/mount.h index 6a61c2b3e385..2152c16ddf74 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -13,6 +13,8 @@ struct mnt_namespace { u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; + unsigned int mounts; /* # of mounts in the namespace */ + unsigned int pending_mounts; }; struct mnt_pcp { diff --git a/fs/namespace.c b/fs/namespace.c index 556721fb0cf6..f853aaf92ec9 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,9 @@ #include "pnode.h" #include "internal.h" +/* Maximum number of mounts in a mount namespace */ +unsigned int sysctl_mount_max __read_mostly = 100000; + static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; @@ -888,6 +891,9 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) list_splice(&head, n->list.prev); + n->mounts += n->pending_mounts; + n->pending_mounts = 0; + attach_shadowed(mnt, parent, shadows); touch_mnt_namespace(n); } @@ -1408,11 +1414,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { + struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); - __touch_mnt_namespace(p->mnt_ns); + ns = p->mnt_ns; + if (ns) { + ns->mounts--; + __touch_mnt_namespace(ns); + } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; @@ -1821,6 +1832,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse) return 0; } +int count_mounts(struct mnt_namespace *ns, struct mount *mnt) +{ + unsigned int max = READ_ONCE(sysctl_mount_max); + unsigned int mounts = 0, old, pending, sum; + struct mount *p; + + for (p = mnt; p; p = next_mnt(p, mnt)) + mounts++; + + old = ns->mounts; + pending = ns->pending_mounts; + sum = old + pending; + if ((old > sum) || + (pending > sum) || + (max < sum) || + (mounts > (max - sum))) + return -ENOSPC; + + ns->pending_mounts = pending + mounts; + return 0; +} + /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached @@ -1890,10 +1923,18 @@ static int attach_recursive_mnt(struct mount *source_mnt, struct path *parent_path) { HLIST_HEAD(tree_list); + struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mount *child, *p; struct hlist_node *n; int err; + /* Is there space to add these mounts to the mount namespace? */ + if (!parent_path) { + err = count_mounts(ns, source_mnt); + if (err) + goto out; + } + if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) @@ -1930,11 +1971,13 @@ static int attach_recursive_mnt(struct mount *source_mnt, out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); + child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: + ns->pending_mounts = 0; return err; } @@ -2758,6 +2801,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns) init_waitqueue_head(&new_ns->poll); new_ns->event = 0; new_ns->user_ns = get_user_ns(user_ns); + new_ns->mounts = 0; + new_ns->pending_mounts = 0; return new_ns; } @@ -2807,6 +2852,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, q = new; while (p) { q->mnt_ns = new_ns; + new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); @@ -2845,6 +2891,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m) struct mount *mnt = real_mount(m); mnt->mnt_ns = new_ns; new_ns->root = mnt; + new_ns->mounts++; list_add(&mnt->mnt_list, &new_ns->list); } else { mntput(m); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 9605a2f63549..7b1261bc2dee 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -884,7 +884,7 @@ int ncp_notify_change(struct dentry *dentry, struct iattr *attr) /* ageing the dentry to force validation */ ncp_age_dentry(server, dentry); - result = inode_change_ok(inode, attr); + result = setattr_prepare(dentry, attr); if (result < 0) goto out; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index aecbcd34d336..44f6f4f5eee0 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -59,13 +59,59 @@ static __be32 nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, struct nfsd_attrstat *resp) { + struct iattr *iap = &argp->attrs; + struct svc_fh *fhp; __be32 nfserr; + dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", SVCFH_fmt(&argp->fh), argp->attrs.ia_valid, (long) argp->attrs.ia_size); - fh_copy(&resp->fh, &argp->fh); - nfserr = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,0, (time_t)0); + fhp = fh_copy(&resp->fh, &argp->fh); + + /* + * NFSv2 does not differentiate between "set-[ac]time-to-now" + * which only requires access, and "set-[ac]time-to-X" which + * requires ownership. + * So if it looks like it might be "set both to the same time which + * is close to now", and if setattr_prepare fails, then we + * convert to "set to now" instead of "set to explicit time" + * + * We only call setattr_prepare as the last test as technically + * it is not an interface that we should be using. + */ +#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) +#define MAX_TOUCH_TIME_ERROR (30*60) + if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && + iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { + /* + * Looks probable. + * + * Now just make sure time is in the right ballpark. + * Solaris, at least, doesn't seem to care what the time + * request is. We require it be within 30 minutes of now. + */ + time_t delta = iap->ia_atime.tv_sec - get_seconds(); + + nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); + if (nfserr) + goto done; + + if (delta < 0) + delta = -delta; + if (delta < MAX_TOUCH_TIME_ERROR && + setattr_prepare(fhp->fh_dentry, iap) != 0) { + /* + * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. + * This will cause notify_change to set these times + * to "now" + */ + iap->ia_valid &= ~BOTH_TIME_SET; + } + } + + nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0); +done: return nfsd_return_attrs(nfserr, resp); } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 84d770be056e..92de3747ea8b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -302,42 +302,6 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { - /* - * NFSv2 does not differentiate between "set-[ac]time-to-now" - * which only requires access, and "set-[ac]time-to-X" which - * requires ownership. - * So if it looks like it might be "set both to the same time which - * is close to now", and if inode_change_ok fails, then we - * convert to "set to now" instead of "set to explicit time" - * - * We only call inode_change_ok as the last test as technically - * it is not an interface that we should be using. - */ -#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) -#define MAX_TOUCH_TIME_ERROR (30*60) - if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && - iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { - /* - * Looks probable. - * - * Now just make sure time is in the right ballpark. - * Solaris, at least, doesn't seem to care what the time - * request is. We require it be within 30 minutes of now. - */ - time_t delta = iap->ia_atime.tv_sec - get_seconds(); - if (delta < 0) - delta = -delta; - if (delta < MAX_TOUCH_TIME_ERROR && - inode_change_ok(inode, iap) != 0) { - /* - * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. - * This will cause notify_change to set these times - * to "now" - */ - iap->ia_valid &= ~BOTH_TIME_SET; - } - } - /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 258d9fe2521a..b40df2bb5ee4 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -839,7 +839,7 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) struct super_block *sb = inode->i_sb; int err; - err = inode_change_ok(inode, iattr); + err = setattr_prepare(dentry, iattr); if (err) return err; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d284f07eda77..c178763893f3 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2893,7 +2893,7 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) int err; unsigned int ia_valid = attr->ia_valid; - err = inode_change_ok(vi, attr); + err = setattr_prepare(dentry, attr); if (err) goto out; /* We do not support NTFS ACLs yet. */ diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 762e5a3aecd3..c7641f656494 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -241,13 +241,11 @@ int ocfs2_set_acl(handle_t *handle, case ACL_TYPE_ACCESS: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - ret = posix_acl_equiv_mode(acl, &mode); - if (ret < 0) - return ret; + umode_t mode; - if (ret == 0) - acl = NULL; + ret = posix_acl_update_mode(inode, &mode, &acl); + if (ret) + return ret; ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index b5cf27dcb18a..43ac2289c613 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -211,7 +211,7 @@ static int dlmfs_file_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); attr->ia_valid &= ~ATTR_SIZE; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index e00be7f509db..bc06b982e9ea 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1150,7 +1150,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) if (!(attr->ia_valid & OCFS2_VALID_ATTRS)) return 0; - status = inode_change_ok(inode, attr); + status = setattr_prepare(dentry, attr); if (status) return status; diff --git a/fs/omfs/file.c b/fs/omfs/file.c index d9e26cfbb793..bf83e6644333 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -349,7 +349,7 @@ static int omfs_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 0bb8347c0d8b..d293034ae2cb 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -54,7 +54,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not * check for a swapfile (which this won't be anyway). */ - err = inode_change_ok(dentry->d_inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/pnode.c b/fs/pnode.c index 99899705b105..234a9ac49958 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -259,7 +259,7 @@ static int propagate_one(struct mount *m) read_sequnlock_excl(&mount_lock); } hlist_add_head(&child->mnt_hash, list); - return 0; + return count_mounts(m->mnt_ns, child); } /* diff --git a/fs/pnode.h b/fs/pnode.h index 0fcdbe7ca648..550f5a8b4fcf 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -52,4 +52,5 @@ void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); +int count_mounts(struct mnt_namespace *ns, struct mount *mnt); #endif /* _LINUX_PNODE_H */ diff --git a/fs/posix_acl.c b/fs/posix_acl.c index a9dafa83678c..0ef1c3722504 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -598,6 +598,37 @@ no_mem: } EXPORT_SYMBOL_GPL(posix_acl_create); +/** + * posix_acl_update_mode - update mode in set_acl + * + * Update the file mode when setting an ACL: compute the new file permission + * bits based on the ACL. In addition, if the ACL is equivalent to the new + * file mode, set *acl to NULL to indicate that no ACL should be set. + * + * As with chmod, clear the setgit bit if the caller is not in the owning group + * or capable of CAP_FSETID (see inode_change_ok). + * + * Called from set_acl inode operations. + */ +int posix_acl_update_mode(struct inode *inode, umode_t *mode_p, + struct posix_acl **acl) +{ + umode_t mode = inode->i_mode; + int error; + + error = posix_acl_equiv_mode(*acl, &mode); + if (error < 0) + return error; + if (error == 0) + *acl = NULL; + if (!in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + mode &= ~S_ISGID; + *mode_p = mode; + return 0; +} +EXPORT_SYMBOL(posix_acl_update_mode); + /* * Fix up the uids and gids in posix acl extended attributes in place. */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 239dca3fb676..fab32ad5d96d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -517,7 +517,7 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_MODE) return -EPERM; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index e5dee5c3188e..d99099fe62d4 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -105,7 +105,7 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) struct proc_dir_entry *de = PDE(inode); int error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) return error; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fdda62e6115e..0dea606074c7 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -753,7 +753,7 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index ba1323a94924..aab2593f3179 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -168,7 +168,7 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) int ret = 0; /* POSIX UID/GID verification for setting inode attributes */ - ret = inode_change_ok(inode, ia); + ret = setattr_prepare(dentry, ia); if (ret) return ret; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f6f2fbad9777..7da1232a78e3 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3312,7 +3312,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid; int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4b34b9dc03dd..9b1824f35501 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -246,13 +246,9 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - if (error == 0) - acl = NULL; - } } break; case ACL_TYPE_DEFAULT: diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 82ddc09061e2..7ba997e31aeb 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -33,7 +33,7 @@ static int sysv_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 75e9b2db14ab..2dc8ce485c51 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1263,7 +1263,7 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) dbg_gen("ino %lu, mode %#x, ia_valid %#x", inode->i_ino, inode->i_mode, attr->ia_valid); - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/udf/file.c b/fs/udf/file.c index 7a95b8fed302..889f1e5da507 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -252,7 +252,7 @@ static int udf_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index 21154704c168..a958b36f40bb 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -496,7 +496,7 @@ int ufs_setattr(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid = attr->ia_valid; int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/utimes.c b/fs/utimes.c index aa138d64560a..61abc3051377 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -81,7 +81,7 @@ static int utimes_common(struct path *path, struct timespec *times) newattrs.ia_valid |= ATTR_MTIME_SET; } /* - * Tell inode_change_ok(), that this is an explicit time + * Tell setattr_prepare(), that this is an explicit time * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET * were used. */ @@ -90,7 +90,7 @@ static int utimes_common(struct path *path, struct timespec *times) /* * If times is NULL (or both times are UTIME_NOW), * then we need to check permissions, because - * inode_change_ok() won't do it. + * setattr_prepare() won't do it. */ error = -EACCES; if (IS_IMMUTABLE(inode)) diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 4b641676f258..e80dbfa2a7b9 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -284,16 +284,11 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); - - if (error <= 0) { - acl = NULL; - - if (error < 0) - return error; - } + umode_t mode; + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + return error; error = xfs_set_mode(inode, mode); if (error) return error; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 3b7591224f4a..550f8c4733ee 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -973,7 +973,7 @@ xfs_file_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = xfs_setattr_size(ip, &iattr); + error = xfs_vn_setattr_size(file->f_path.dentry, &iattr); if (error) goto out_unlock; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c29f34253e2b..6b67d617c092 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1766,7 +1766,7 @@ xfs_inactive_truncate( /* * Log the inode size first to prevent stale data exposure in the event * of a system crash before the truncate completes. See the related - * comment in xfs_setattr_size() for details. + * comment in xfs_vn_setattr_size() for details. */ ip->i_d.di_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 87f67c6b654c..82e49109d0b6 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -720,7 +720,7 @@ xfs_ioc_space( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = bf->l_start; - error = xfs_setattr_size(ip, &iattr); + error = xfs_vn_setattr_size(filp->f_path.dentry, &iattr); break; default: ASSERT(0); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f4cd7204e236..4e4d6511185b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -537,6 +537,30 @@ xfs_setattr_time( } } +static int +xfs_vn_change_ok( + struct dentry *dentry, + struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return -EROFS; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + return setattr_prepare(dentry, iattr); +} + +/* + * Set non-size attributes of an inode. + * + * Caution: The caller of this function is responsible for calling + * setattr_prepare() or otherwise verifying the change is fine. + */ int xfs_setattr_nonsize( struct xfs_inode *ip, @@ -553,21 +577,6 @@ xfs_setattr_nonsize( struct xfs_dquot *udqp = NULL, *gdqp = NULL; struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL; - trace_xfs_setattr(ip); - - /* If acls are being inherited, we already have this checked */ - if (!(flags & XFS_ATTR_NOACL)) { - if (mp->m_flags & XFS_MOUNT_RDONLY) - return -EROFS; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - error = inode_change_ok(inode, iattr); - if (error) - return error; - } - ASSERT((mask & ATTR_SIZE) == 0); /* @@ -741,8 +750,27 @@ out_dqrele: return error; } +int +xfs_vn_setattr_nonsize( + struct dentry *dentry, + struct iattr *iattr) +{ + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + int error; + + trace_xfs_setattr(ip); + + error = xfs_vn_change_ok(dentry, iattr); + if (error) + return error; + return xfs_setattr_nonsize(ip, iattr, 0); +} + /* * Truncate file. Must have write permission and not be a directory. + * + * Caution: The caller of this function is responsible for calling + * setattr_prepare() or otherwise verifying the change is fine. */ int xfs_setattr_size( @@ -758,18 +786,6 @@ xfs_setattr_size( uint commit_flags = 0; bool did_zeroing = false; - trace_xfs_setattr(ip); - - if (mp->m_flags & XFS_MOUNT_RDONLY) - return -EROFS; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - error = inode_change_ok(inode, iattr); - if (error) - return error; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); @@ -941,16 +957,32 @@ out_trans_cancel: goto out_unlock; } +int +xfs_vn_setattr_size( + struct dentry *dentry, + struct iattr *iattr) +{ + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + int error; + + trace_xfs_setattr(ip); + + error = xfs_vn_change_ok(dentry, iattr); + if (error) + return error; + return xfs_setattr_size(ip, iattr); +} + STATIC int xfs_vn_setattr( struct dentry *dentry, struct iattr *iattr) { - struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error; if (iattr->ia_valid & ATTR_SIZE) { - uint iolock = XFS_IOLOCK_EXCL; + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + uint iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); error = xfs_break_layouts(d_inode(dentry), &iolock, true); @@ -958,11 +990,11 @@ xfs_vn_setattr( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); iolock |= XFS_MMAPLOCK_EXCL; - error = xfs_setattr_size(ip, iattr); + error = xfs_vn_setattr_size(dentry, iattr); } xfs_iunlock(ip, iolock); } else { - error = xfs_setattr_nonsize(ip, iattr, 0); + error = xfs_vn_setattr_nonsize(dentry, iattr); } return error; diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index a0f84abb0d09..0259a383721a 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -33,6 +33,7 @@ extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr); extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap, int flags); -extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap); +extern int xfs_vn_setattr_nonsize(struct dentry *dentry, struct iattr *vap); +extern int xfs_vn_setattr_size(struct dentry *dentry, struct iattr *vap); #endif /* __XFS_IOPS_H__ */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 5e13b987d9e2..678e97fa3869 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -31,6 +31,7 @@ enum can_mode { * CAN common private data */ struct can_priv { + struct net_device *dev; struct can_device_stats can_stats; struct can_bittiming bittiming, data_bittiming; @@ -46,7 +47,7 @@ struct can_priv { u32 ctrlmode_static; /* static enabled options for driver/hardware */ int restart_ms; - struct timer_list restart_timer; + struct delayed_work restart_work; int (*do_set_bittiming)(struct net_device *dev); int (*do_set_data_bittiming)(struct net_device *dev); diff --git a/include/linux/fs.h b/include/linux/fs.h index ae327f6a53f6..31c3d818c981 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2816,7 +2816,7 @@ extern int buffer_migrate_page(struct address_space *, #define buffer_migrate_page NULL #endif -extern int inode_change_ok(const struct inode *, struct iattr *); +extern int setattr_prepare(struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); extern void setattr_copy(struct inode *inode, const struct iattr *attr); diff --git a/include/linux/mount.h b/include/linux/mount.h index f822c3c11377..dc6cd800cd5d 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -95,4 +95,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); +extern unsigned int sysctl_mount_max; + #endif /* _LINUX_MOUNT_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6c86c7edafa7..ddd47c3a757d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1957,7 +1957,10 @@ struct napi_gro_cb { /* Used in foo-over-udp, set in udp[46]_gro_receive */ u8 is_ipv6:1; - /* 7 bit hole */ + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; + + /* 3 bit hole */ /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -1968,6 +1971,25 @@ struct napi_gro_cb { #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) +#define GRO_RECURSION_LIMIT 15 +static inline int gro_recursion_inc_test(struct sk_buff *skb) +{ + return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; +} + +typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); +static inline struct sk_buff **call_gro_receive(gro_receive_t cb, + struct sk_buff **head, + struct sk_buff *skb) +{ + if (gro_recursion_inc_test(skb)) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb); +} + struct packet_type { __be16 type; /* This is really htons(ether_type). */ struct net_device *dev; /* NULL is wildcarded here */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 3e96a6a76103..d1a8ad7e5ae4 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -95,6 +95,7 @@ extern int set_posix_acl(struct inode *, int, struct posix_acl *); extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); +extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d204f3f9df8..3d3a365233f0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1434,6 +1434,8 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli { if (sk->sk_send_head == skb_unlinked) sk->sk_send_head = NULL; + if (tcp_sk(sk)->highest_sack == skb_unlinked) + tcp_sk(sk)->highest_sack = NULL; } static inline void tcp_init_send_head(struct sock *sk) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 388fc6f78c6f..71403502411b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -323,8 +323,7 @@ static struct file_system_type cpuset_fs_type = { /* * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy - * until we find one that does have some online cpus. The top - * cpuset always has some cpus online. + * until we find one that does have some online cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. @@ -333,8 +332,20 @@ static struct file_system_type cpuset_fs_type = { */ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) { - while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) + while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { cs = parent_cs(cs); + if (unlikely(!cs)) { + /* + * The top cpuset doesn't have any online cpu as a + * consequence of a race between cpuset_hotplug_work + * and cpu hotplug notifier. But we know the top + * cpuset's effective_cpus is on its way to to be + * identical to cpu_online_mask. + */ + cpumask_copy(pmask, cpu_online_mask); + return; + } + } cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 261ee21e62db..9650e7aee267 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -207,12 +208,34 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) +static bool ptrace_has_cap(const struct cred *tcred, unsigned int mode) { + struct user_namespace *tns = tcred->user_ns; + + /* When a root-owned process enters a user namespace created by a + * malicious user, the user shouldn't be able to execute code under + * uid 0 by attaching to the root-owned process via ptrace. + * Therefore, similar to the capable_wrt_inode_uidgid() check, + * verify that all the uids and gids of the target process are + * mapped into a namespace below the current one in which the caller + * is capable. + * No fsuid/fsgid check because __ptrace_may_access doesn't do it + * either. + */ + while ( + !kuid_has_mapping(tns, tcred->euid) || + !kuid_has_mapping(tns, tcred->suid) || + !kuid_has_mapping(tns, tcred->uid) || + !kgid_has_mapping(tns, tcred->egid) || + !kgid_has_mapping(tns, tcred->sgid) || + !kgid_has_mapping(tns, tcred->gid)) { + tns = tns->parent; + } + if (mode & PTRACE_MODE_NOAUDIT) - return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); + return has_ns_capability_noaudit(current, tns, CAP_SYS_PTRACE); else - return has_ns_capability(current, ns, CAP_SYS_PTRACE); + return has_ns_capability(current, tns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ @@ -264,7 +287,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(tcred->user_ns, mode)) + if (ptrace_has_cap(tcred, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -275,7 +298,7 @@ ok: dumpable = get_dumpable(task->mm); rcu_read_lock(); if (dumpable != SUID_DUMP_USER && - !ptrace_has_cap(__task_cred(task)->user_ns, mode)) { + !ptrace_has_cap(__task_cred(task), mode)) { rcu_read_unlock(); return -EPERM; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7d4900404c94..cebbff5f34fe 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -64,6 +64,7 @@ #include #include #include +#include #include #include @@ -1709,6 +1710,14 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, + { + .procname = "mount-max", + .data = &sysctl_mount_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, { } }; diff --git a/mm/ksm.c b/mm/ksm.c index 7ee101eaacdf..22a2883eb822 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -283,7 +283,8 @@ static inline struct rmap_item *alloc_rmap_item(void) { struct rmap_item *rmap_item; - rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL); + rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | + __GFP_NORETRY | __GFP_NOWARN); if (rmap_item) ksm_rmap_items++; return rmap_item; diff --git a/mm/shmem.c b/mm/shmem.c index 46511ad90bc5..feaaf6ea1b86 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -548,7 +548,7 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr) struct shmem_inode_info *info = SHMEM_I(inode); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 825e8fb5114b..f9e9a8148a43 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -334,16 +334,19 @@ static int rfcomm_sock_create(struct net *net, struct socket *sock, static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { - struct sockaddr_rc *sa = (struct sockaddr_rc *) addr; + struct sockaddr_rc sa; struct sock *sk = sock->sk; - int chan = sa->rc_channel; - int err = 0; - - BT_DBG("sk %p %pMR", sk, &sa->rc_bdaddr); + int len, err = 0; if (!addr || addr->sa_family != AF_BLUETOOTH) return -EINVAL; + memset(&sa, 0, sizeof(sa)); + len = min_t(unsigned int, sizeof(sa), addr_len); + memcpy(&sa, addr, len); + + BT_DBG("sk %p %pMR", sk, &sa.rc_bdaddr); + lock_sock(sk); if (sk->sk_state != BT_OPEN) { @@ -358,12 +361,13 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr write_lock(&rfcomm_sk_list.lock); - if (chan && __rfcomm_get_listen_sock_by_addr(chan, &sa->rc_bdaddr)) { + if (sa.rc_channel && + __rfcomm_get_listen_sock_by_addr(sa.rc_channel, &sa.rc_bdaddr)) { err = -EADDRINUSE; } else { /* Save source address */ - bacpy(&rfcomm_pi(sk)->src, &sa->rc_bdaddr); - rfcomm_pi(sk)->channel = chan; + bacpy(&rfcomm_pi(sk)->src, &sa.rc_bdaddr); + rfcomm_pi(sk)->channel = sa.rc_channel; sk->sk_state = BT_BOUND; } diff --git a/net/core/dev.c b/net/core/dev.c index 185a3398c651..56d820fc2707 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4060,6 +4060,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; NAPI_GRO_CB(skb)->udp_mark = 0; + NAPI_GRO_CB(skb)->recursion_counter = 0; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index f3bad41d725f..76f8389eacd2 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -434,7 +434,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*eh)); skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0cc98b135b8f..2095cd6c31fd 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1377,7 +1377,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 4b67937692c9..b22a75c0a3d9 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -188,7 +188,7 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head, if (!ops || !ops->callbacks.gro_receive) goto out_unlock; - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); @@ -355,7 +355,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, if (WARN_ON(!ops || !ops->callbacks.gro_receive)) goto out_unlock; - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 5a8ee3282550..53300b88d569 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -214,7 +214,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ skb_gro_postpull_rcsum(skb, greh, grehlen); - pp = ptype->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index f6ee0d561aab..3dac3d4aa26f 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -659,6 +659,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, if (len > 0xFFFF) return -EMSGSIZE; + /* Must have at least a full ICMP header. */ + if (len < icmph_len) + return -EINVAL; + /* * Check the flags. */ diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f9386160cbee..2af7b7e1a0f6 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -339,8 +339,13 @@ unflush: skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; - pp = uo_priv->offload->callbacks.gro_receive(head, skb, - uo_priv->offload); + + if (gro_recursion_inc_test(skb)) { + pp = NULL; + } else { + pp = uo_priv->offload->callbacks.gro_receive(head, skb, + uo_priv->offload); + } out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 08b62047c67f..db0b8428d248 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -247,7 +247,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, skb_gro_postpull_rcsum(skb, iph, nlen); - pp = ops->callbacks.gro_receive(head, skb); + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a3654d929814..b9d1baaa8bdc 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3344,19 +3344,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: - po->tp_version = val; - return 0; + break; default: return -EINVAL; } + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_version = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_RESERVE: { @@ -3819,6 +3825,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; + lock_sock(sk); /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { WARN(1, "Tx-ring is not supported.\n"); @@ -3900,7 +3907,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; } - lock_sock(sk); /* Detach socket from network */ spin_lock(&po->bind_lock); @@ -3949,11 +3955,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (!tx_ring) prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue); } - release_sock(sk); if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: + release_sock(sk); return err; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 70e3dacbf84a..bf7d6a44c6f2 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -386,6 +386,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; + if (tipc_mtu_bad(dev, 0)) { + dev_put(dev); + return -EINVAL; + } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); @@ -524,14 +528,17 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (!b_ptr) return NOTIFY_DONE; - b_ptr->mtu = dev->mtu; - switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev)) break; case NETDEV_DOWN: case NETDEV_CHANGEMTU: + if (tipc_mtu_bad(dev, 0)) { + bearer_disable(net, b_ptr, false); + break; + } + b_ptr->mtu = dev->mtu; tipc_reset_bearer(net, b_ptr); break; case NETDEV_CHANGEADDR: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 5cad243ee8fc..b7302b012624 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -38,6 +38,7 @@ #define _TIPC_BEARER_H #include "netlink.h" +#include "msg.h" #include #define MAX_BEARERS 2 @@ -61,6 +62,9 @@ #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 +/* minimum bearer MTU */ +#define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) + /** * struct tipc_node_map - set of node identifiers * @count: # of nodes in set @@ -218,4 +222,13 @@ void tipc_bearer_stop(struct net *net); void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, struct tipc_media_addr *dest); +/* check if device MTU is too low for tipc headers */ +static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +{ + if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + return false; + netdev_warn(dev, "MTU too low for tipc bearer\n"); + return true; +} + #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index f8dfee5072c0..e14f23542a1a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -374,6 +374,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { + err = -EINVAL; + goto err; + } b->mtu = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); #if IS_ENABLED(CONFIG_IPV6) diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh index 973e8c141567..17867e723a51 100755 --- a/scripts/gcc-x86_64-has-stack-protector.sh +++ b/scripts/gcc-x86_64-has-stack-protector.sh @@ -1,6 +1,6 @@ #!/bin/sh -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fstack-protector - -o - 2> /dev/null | grep -q "%gs" +echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs" if [ "$?" -eq "0" ] ; then echo y else