diff --git a/Makefile b/Makefile index 49e8be1..85fb935 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 13 SUBLEVEL = 11 -EXTRAVERSION = -ckt13 +EXTRAVERSION = -ckt14 NAME = King of Alienated Frog Porn # *DOCUMENTATION* diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 87ba7cf..65d633f 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir) struct dentry *dentry, *tmp; mutex_lock(&dir->d_inode->i_mutex); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { spin_lock(&dentry->d_lock); if (!(d_unhashed(dentry)) && dentry->d_inode) { dget_dlock(dentry); diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index e030d2b..b67da3b 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -245,7 +245,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) struct group_info *group_info; int retval; - if (!capable(CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9c0280f..e2d26ce 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -286,24 +286,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -312,41 +297,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: they have + * 64-bit bases are that controlled by arch_prctl. Those bases + * only differ from the values in the GDT or LDT if the selector + * is 0. + * + * Loading the segment register resets the hidden base part of + * the register to 0 or the value from the GDT / LDT. If the + * next base address zero, writing 0 to the segment register is + * much faster than using wrmsr to explicitly zero the base. + * + * The thread_struct.fs and thread_struct.gs values are 0 + * if the fs and gs bases respectively are not overridden + * from the values implied by fsindex and gsindex. They + * are nonzero, and store the nonzero base addresses, if + * the bases are overridden. + * + * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should + * be impossible. + * + * Therefore we need to reload the segment registers if either + * the old or new selector is nonzero, and we need to override + * the base address if next thread expects it to be overridden. + * + * This code is unnecessarily slow in the case where the old and + * new indexes are zero and the new base is nonzero -- it will + * unnecessarily write 0 to the selector before writing the new + * base address. + * + * Note: This all depends on arch_prctl being the only way that + * user code can override the segment base. Once wrfsbase and + * wrgsbase are enabled, most of this code will need to change. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * If user code wrote a nonzero value to FS, then it also + * cleared the overridden base address. + * + * XXX: if user code wrote 0 to FS and cleared the base + * address itself, we won't notice and we'll incorrectly + * restore the prior base address next time we reschdule + * the process. */ if (fsindex) prev->fs = 0; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index f7fec09..e7650bd 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,21 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + if (LDT_empty(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -66,6 +81,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +210,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +224,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 97e766b..4919b95 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1994,7 +1994,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) rc = assign_eip_far(ctxt, ctxt->src.val, new_desc.l); if (rc != X86EMUL_CONTINUE) { - WARN_ON(!ctxt->mode != X86EMUL_MODE_PROT64); + WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64); /* assigning eip failed; restore the old cs */ ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS); return rc; @@ -2088,7 +2088,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) return rc; rc = assign_eip_far(ctxt, eip, new_desc.l); if (rc != X86EMUL_CONTINUE) { - WARN_ON(!ctxt->mode != X86EMUL_MODE_PROT64); + WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64); ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS); } return rc; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 431e875..ab6ba35 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -117,30 +117,45 @@ subsys_initcall(init_vdso); struct linux_binprm; -/* Put the vdso above the (randomized) stack with another randomized offset. - This way there is no hole in the middle of address space. - To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits */ +/* + * Put the vdso above the (randomized) stack with another randomized + * offset. This way there is no hole in the middle of address space. + * To save memory make sure it is still in the same PTE as the stack + * top. This doesn't give that many random bits. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ static unsigned long vdso_addr(unsigned long start, unsigned len) { unsigned long addr, end; unsigned offset; - end = (start + PMD_SIZE - 1) & PMD_MASK; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; if (end >= TASK_SIZE_MAX) end = TASK_SIZE_MAX; end -= len; - /* This loses some more bits than a modulo, but is cheaper */ - offset = get_random_int() & (PTRS_PER_PTE - 1); - addr = start + (offset << PAGE_SHIFT); - if (addr >= end) - addr = end; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } /* - * page-align it here so that get_unmapped_area doesn't - * align it wrongfully again to the next page. addr can come in 4K - * unaligned here as a result of stack start randomization. + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. */ - addr = PAGE_ALIGN(addr); addr = align_vdso_addr(addr); return addr; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 6d14eea..a205f8d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2976,11 +2976,21 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) u32 rctl, rfctl; u32 pages = 0; - /* Workaround Si errata on PCHx - configure jumbo frame flow */ - if ((hw->mac.type >= e1000_pch2lan) && - (adapter->netdev->mtu > ETH_DATA_LEN) && - e1000_lv_jumbo_workaround_ich8lan(hw, true)) - e_dbg("failed to enable jumbo frame workaround mode\n"); + /* Workaround Si errata on PCHx - configure jumbo frame flow. + * If jumbo frames not set, program related MAC/PHY registers + * to h/w defaults + */ + if (hw->mac.type >= e1000_pch2lan) { + s32 ret_val; + + if (adapter->netdev->mtu > ETH_DATA_LEN) + ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true); + else + ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false); + + if (ret_val) + e_dbg("failed to enable|disable jumbo frame workaround mode\n"); + } /* Program MC offset vector base */ rctl = er32(RCTL); diff --git a/drivers/staging/lustre/lustre/llite/dcache.c b/drivers/staging/lustre/lustre/llite/dcache.c index e7629be..c6ca9ca 100644 --- a/drivers/staging/lustre/lustre/llite/dcache.c +++ b/drivers/staging/lustre/lustre/llite/dcache.c @@ -278,7 +278,7 @@ void ll_invalidate_aliases(struct inode *inode) inode->i_ino, inode->i_generation, inode); ll_lock_dcache(inode); - ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) { CDEBUG(D_DENTRY, "dentry in drop %.*s (%p) parent %p " "inode %p flags %d\n", dentry->d_name.len, dentry->d_name.name, dentry, dentry->d_parent, diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index fd584ff..78092f6 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -665,7 +665,7 @@ void lustre_dump_dentry(struct dentry *dentry, int recur) return; list_for_each(tmp, &dentry->d_subdirs) { - struct dentry *d = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *d = list_entry(tmp, struct dentry, d_child); lustre_dump_dentry(d, recur - 1); } } diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c index 90bbdae..98b3cd6 100644 --- a/drivers/staging/lustre/lustre/llite/namei.c +++ b/drivers/staging/lustre/lustre/llite/namei.c @@ -175,14 +175,14 @@ static void ll_invalidate_negative_children(struct inode *dir) struct ll_d_hlist_node *p; ll_lock_dcache(dir); - ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!list_empty(&dentry->d_subdirs)) { struct dentry *child; list_for_each_entry_safe(child, tmp_subdir, &dentry->d_subdirs, - d_u.d_child) { + d_child) { if (child->d_inode == NULL) d_lustre_invalidate(child, 1); } @@ -363,7 +363,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry) discon_alias = invalid_alias = NULL; ll_lock_dcache(inode); - ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_u.d_alias) { LASSERT(alias != dentry); spin_lock(&alias->d_lock); @@ -953,7 +953,7 @@ static void ll_get_child_fid(struct inode * dir, struct qstr *name, { struct dentry *parent, *child; - parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_alias); + parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_u.d_alias); child = d_lookup(parent, name); if (child) { if (child->d_inode) diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c index 4cc4fd6..4e8fa75 100644 --- a/drivers/usb/gadget/at91_udc.c +++ b/drivers/usb/gadget/at91_udc.c @@ -871,12 +871,10 @@ static void clk_on(struct at91_udc *udc) return; udc->clocked = 1; - if (IS_ENABLED(CONFIG_COMMON_CLK)) { - clk_set_rate(udc->uclk, 48000000); - clk_prepare_enable(udc->uclk); - } - clk_prepare_enable(udc->iclk); - clk_prepare_enable(udc->fclk); + if (IS_ENABLED(CONFIG_COMMON_CLK)) + clk_enable(udc->uclk); + clk_enable(udc->iclk); + clk_enable(udc->fclk); } static void clk_off(struct at91_udc *udc) @@ -885,10 +883,10 @@ static void clk_off(struct at91_udc *udc) return; udc->clocked = 0; udc->gadget.speed = USB_SPEED_UNKNOWN; - clk_disable_unprepare(udc->fclk); - clk_disable_unprepare(udc->iclk); + clk_disable(udc->fclk); + clk_disable(udc->iclk); if (IS_ENABLED(CONFIG_COMMON_CLK)) - clk_disable_unprepare(udc->uclk); + clk_disable(udc->uclk); } /* @@ -1791,14 +1789,24 @@ static int at91udc_probe(struct platform_device *pdev) } /* don't do anything until we have both gadget driver and VBUS */ + if (IS_ENABLED(CONFIG_COMMON_CLK)) { + clk_set_rate(udc->uclk, 48000000); + retval = clk_prepare(udc->uclk); + if (retval) + goto fail1; + } + retval = clk_prepare(udc->fclk); + if (retval) + goto fail1a; + retval = clk_prepare_enable(udc->iclk); if (retval) - goto fail1; + goto fail1b; at91_udp_write(udc, AT91_UDP_TXVC, AT91_UDP_TXVC_TXVDIS); at91_udp_write(udc, AT91_UDP_IDR, 0xffffffff); /* Clear all pending interrupts - UDP may be used by bootloader. */ at91_udp_write(udc, AT91_UDP_ICR, 0xffffffff); - clk_disable_unprepare(udc->iclk); + clk_disable(udc->iclk); /* request UDC and maybe VBUS irqs */ udc->udp_irq = platform_get_irq(pdev, 0); @@ -1806,7 +1814,7 @@ static int at91udc_probe(struct platform_device *pdev) 0, driver_name, udc); if (retval < 0) { DBG("request irq %d failed\n", udc->udp_irq); - goto fail1; + goto fail1c; } if (gpio_is_valid(udc->board.vbus_pin)) { retval = gpio_request(udc->board.vbus_pin, "udc_vbus"); @@ -1859,6 +1867,13 @@ fail3: gpio_free(udc->board.vbus_pin); fail2: free_irq(udc->udp_irq, udc); +fail1c: + clk_unprepare(udc->iclk); +fail1b: + clk_unprepare(udc->fclk); +fail1a: + if (IS_ENABLED(CONFIG_COMMON_CLK)) + clk_unprepare(udc->uclk); fail1: if (IS_ENABLED(CONFIG_COMMON_CLK) && !IS_ERR(udc->uclk)) clk_put(udc->uclk); @@ -1907,6 +1922,11 @@ static int __exit at91udc_remove(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); + if (IS_ENABLED(CONFIG_COMMON_CLK)) + clk_unprepare(udc->uclk); + clk_unprepare(udc->fclk); + clk_unprepare(udc->iclk); + clk_put(udc->iclk); clk_put(udc->fclk); if (IS_ENABLED(CONFIG_COMMON_CLK)) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index d9a4367..9cca0ea 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -126,7 +126,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino) { struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { dentry->d_fsdata = (void *)inode->i_ino; break; diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 3d9d3f5..d096316 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -91,7 +91,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, spin_lock(&root->d_lock); if (prev) - next = prev->d_u.d_child.next; + next = prev->d_child.next; else { prev = dget_dlock(root); next = prev->d_subdirs.next; @@ -105,13 +105,13 @@ cont: return NULL; } - q = list_entry(next, struct dentry, d_u.d_child); + q = list_entry(next, struct dentry, d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); /* Already gone or negative dentry (under construction) - try next */ if (!d_count(q) || !simple_positive(q)) { spin_unlock(&q->d_lock); - next = q->d_u.d_child.next; + next = q->d_child.next; goto cont; } dget_dlock(q); @@ -161,13 +161,13 @@ again: goto relock; } spin_unlock(&p->d_lock); - next = p->d_u.d_child.next; + next = p->d_child.next; p = parent; if (next != &parent->d_subdirs) break; } } - ret = list_entry(next, struct dentry, d_u.d_child); + ret = list_entry(next, struct dentry, d_child); spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED); /* Negative dentry - try next */ @@ -447,7 +447,7 @@ found: spin_lock(&sbi->lookup_lock); spin_lock(&expired->d_parent->d_lock); spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + list_move(&expired->d_parent->d_subdirs, &expired->d_child); spin_unlock(&expired->d_lock); spin_unlock(&expired->d_parent->d_lock); spin_unlock(&sbi->lookup_lock); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 2a69bde..b3f4794 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -655,7 +655,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry) /* only consider parents below dentrys in the root */ if (IS_ROOT(parent->d_parent)) return; - d_child = &dentry->d_u.d_child; + d_child = &dentry->d_child; /* Set parent managed if it's becoming empty */ if (d_child->next == &parent->d_subdirs && d_child->prev == &parent->d_subdirs) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 2a0bcae..57bd52d 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -103,7 +103,7 @@ static unsigned fpos_off(loff_t p) /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on - * d_u.d_child when we initially get results back from the MDS, and + * d_child when we initially get results back from the MDS, and * falling back to a "normal" sync readdir if any dentries in the dir * are dropped. * @@ -138,11 +138,11 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx) p = parent->d_subdirs.prev; dout(" initial p %p/%p\n", p->prev, p->next); } else { - p = last->d_u.d_child.prev; + p = last->d_child.prev; } more: - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); while (1) { dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next, @@ -164,7 +164,7 @@ more: !dentry->d_inode ? " null" : ""); spin_unlock(&dentry->d_lock); p = p->prev; - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 278fd28..9d4d486 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -905,9 +905,9 @@ static void ceph_set_dentry_offset(struct dentry *dn) spin_lock(&dir->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &dir->d_subdirs); + list_move(&dn->d_child, &dir->d_subdirs); dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset, - dn->d_u.d_child.prev, dn->d_u.d_child.next); + dn->d_child.prev, dn->d_child.next); spin_unlock(&dn->d_lock); spin_unlock(&dir->d_lock); } @@ -1316,7 +1316,7 @@ retry_lookup: /* reorder parent's d_subdirs */ spin_lock(&parent->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &parent->d_subdirs); + list_move(&dn->d_child, &parent->d_subdirs); spin_unlock(&dn->d_lock); spin_unlock(&parent->d_lock); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 3be49dd..a8546aa 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -874,7 +874,7 @@ inode_has_hashed_dentries(struct inode *inode) struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 1da168c..9bc1147 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&parent->d_lock); - list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(de, &parent->d_subdirs, d_child) { /* don't know what to do with negative dentries */ if (de->d_inode ) coda_flag_inode(de->d_inode, flag); diff --git a/fs/dcache.c b/fs/dcache.c index 2e3c637..6ef3f68 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -44,7 +44,7 @@ /* * Usage: * dcache->d_inode->i_lock protects: - * - i_dentry, d_alias, d_inode of aliases + * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_anon bl list spinlock protects: @@ -59,7 +59,7 @@ * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent - * - d_alias, d_inode + * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock @@ -240,7 +240,6 @@ static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!hlist_unhashed(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); @@ -251,6 +250,8 @@ static void __d_free(struct rcu_head *head) */ static void d_free(struct dentry *dentry) { + WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); + BUG_ON((int)dentry->d_lockref.count > 0); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) @@ -289,7 +290,7 @@ static void dentry_iput(struct dentry * dentry) struct inode *inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -314,7 +315,7 @@ static void dentry_unlink_inode(struct dentry * dentry) struct inode *inode = dentry->d_inode; __d_clear_type(dentry); dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -436,7 +437,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) __releases(parent->d_lock) __releases(dentry->d_inode->i_lock) { - list_del(&dentry->d_u.d_child); + __list_del_entry(&dentry->d_child); /* * Inform d_walk() that we are no longer attached to the * dentry tree @@ -738,7 +739,7 @@ static struct dentry *__d_find_alias(struct inode *inode, int want_discon) again: discon_alias = NULL; - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -791,7 +792,7 @@ void d_prune_aliases(struct inode *inode) struct dentry *dentry; restart: spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { /* @@ -1092,7 +1093,7 @@ repeat: resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); @@ -1124,33 +1125,31 @@ resume: /* * All done at this level ... ascend and resume the search. */ + rcu_read_lock(); +ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; - rcu_read_lock(); spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); - /* - * might go back up the wrong parent if we have had a rename - * or deletion - */ - if (this_parent != child->d_parent || - (child->d_flags & DCACHE_DENTRY_KILLED) || - need_seqretry(&rename_lock, seq)) { - spin_unlock(&this_parent->d_lock); - rcu_read_unlock(); + /* might go back up the wrong parent if we have had a rename. */ + if (need_seqretry(&rename_lock, seq)) goto rename_retry; + next = child->d_child.next; + while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + next = next->next; } rcu_read_unlock(); - next = child->d_u.d_child.next; goto resume; } - if (need_seqretry(&rename_lock, seq)) { - spin_unlock(&this_parent->d_lock); + if (need_seqretry(&rename_lock, seq)) goto rename_retry; - } + rcu_read_unlock(); if (finish) finish(data); @@ -1160,6 +1159,9 @@ out_unlock: return; rename_retry: + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); + BUG_ON(seq & 1); if (!retry) return; seq = 1; @@ -1525,8 +1527,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); - INIT_HLIST_NODE(&dentry->d_alias); - INIT_LIST_HEAD(&dentry->d_u.d_child); + INIT_HLIST_NODE(&dentry->d_u.d_alias); + INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); this_cpu_inc(nr_dentry); @@ -1556,7 +1558,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) */ __dget_dlock(parent); dentry->d_parent = parent; - list_add(&dentry->d_u.d_child, &parent->d_subdirs); + list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; @@ -1649,7 +1651,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); __d_set_type(dentry, add_flags); if (inode) - hlist_add_head(&dentry->d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); dentry->d_inode = inode; dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); @@ -1673,7 +1675,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); @@ -1712,7 +1714,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, return NULL; } - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or @@ -1738,7 +1740,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) { struct dentry *result; - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); @@ -1769,7 +1771,7 @@ EXPORT_SYMBOL(d_instantiate_unique); */ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) { @@ -1808,7 +1810,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode) if (hlist_empty(&inode->i_dentry)) return NULL; - alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } @@ -1885,7 +1887,7 @@ struct dentry *d_obtain_alias(struct inode *inode) spin_lock(&tmp->d_lock); tmp->d_inode = inode; tmp->d_flags |= add_flags; - hlist_add_head(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); hlist_bl_unlock(&tmp->d_sb->s_anon); @@ -2328,7 +2330,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent) struct dentry *child; spin_lock(&dparent->d_lock); - list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dparent->d_subdirs, d_child) { if (dentry == child) { spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); __dget_dlock(dentry); @@ -2575,8 +2577,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target) /* Unhash the target: dput() will then get rid of it */ __d_drop(target); - list_del(&dentry->d_u.d_child); - list_del(&target->d_u.d_child); + list_del(&dentry->d_child); + list_del(&target->d_child); /* Switch the names.. */ switch_names(dentry, target); @@ -2586,15 +2588,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target) if (IS_ROOT(dentry)) { dentry->d_parent = target->d_parent; target->d_parent = target; - INIT_LIST_HEAD(&target->d_u.d_child); + INIT_LIST_HEAD(&target->d_child); } else { swap(dentry->d_parent, target->d_parent); /* And add them back to the (new) parent lists */ - list_add(&target->d_u.d_child, &target->d_parent->d_subdirs); + list_add(&target->d_child, &target->d_parent->d_subdirs); } - list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs); + list_add(&dentry->d_child, &dentry->d_parent->d_subdirs); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); @@ -2701,9 +2703,9 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon) swap(dentry->d_name.hash, anon->d_name.hash); dentry->d_parent = dentry; - list_del_init(&dentry->d_u.d_child); + list_del_init(&dentry->d_child); anon->d_parent = dparent; - list_move(&anon->d_u.d_child, &dparent->d_subdirs); + list_move(&anon->d_child, &dparent->d_subdirs); write_seqcount_end(&dentry->d_seq); write_seqcount_end(&anon->d_seq); @@ -3334,7 +3336,7 @@ void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || - !hlist_unhashed(&dentry->d_alias) || + !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 1576195..d7bf631 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -552,7 +552,7 @@ void debugfs_remove_recursive(struct dentry *dentry) * use the d_u.d_child as the rcu head and corrupt this list. */ spin_lock(&parent->d_lock); - list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &parent->d_subdirs, d_child) { if (!debugfs_positive(child)) continue; diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 48a359d..831d4f0 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result, inode = result->d_inode; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index f488bba..735d752 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -30,6 +30,7 @@ struct rock_state { int cont_size; int cont_extent; int cont_offset; + int cont_loops; struct inode *inode; }; @@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode) rs->inode = inode; } +/* Maximum number of Rock Ridge continuation entries */ +#define RR_MAX_CE_ENTRIES 32 + /* * Returns 0 if the caller should continue scanning, 1 if the scan must end * and -ve on error. @@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs) goto out; } ret = -EIO; + if (++rs->cont_loops >= RR_MAX_CE_ENTRIES) + goto out; bh = sb_bread(rs->inode->i_sb, rs->cont_extent); if (bh) { memcpy(rs->buffer, bh->b_data + rs->cont_offset, @@ -356,6 +362,9 @@ repeat: rs.cont_size = isonum_733(rr->u.CE.size); break; case SIG('E', 'R'): + /* Invalid length of ER tag id? */ + if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len) + goto out; ISOFS_SB(inode->i_sb)->s_rock = 1; printk(KERN_DEBUG "ISO 9660 Extensions: "); { diff --git a/fs/libfs.c b/fs/libfs.c index a184424..868c0b7 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -113,18 +113,18 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) spin_lock(&dentry->d_lock); /* d_lock not required for cursor */ - list_del(&cursor->d_u.d_child); + list_del(&cursor->d_child); p = dentry->d_subdirs.next; while (n && p != &dentry->d_subdirs) { struct dentry *next; - next = list_entry(p, struct dentry, d_u.d_child); + next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(next)) n--; spin_unlock(&next->d_lock); p = p->next; } - list_add_tail(&cursor->d_u.d_child, p); + list_add_tail(&cursor->d_child, p); spin_unlock(&dentry->d_lock); } } @@ -149,7 +149,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p, *q = &cursor->d_u.d_child; + struct list_head *p, *q = &cursor->d_child; if (!dir_emit_dots(file, ctx)) return 0; @@ -158,7 +158,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) list_move(q, &dentry->d_subdirs); for (p = q->next; p != &dentry->d_subdirs; p = p->next) { - struct dentry *next = list_entry(p, struct dentry, d_u.d_child); + struct dentry *next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (!simple_positive(next)) { spin_unlock(&next->d_lock); @@ -286,7 +286,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index c320ac5..dc9747d 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -406,7 +406,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dent = list_entry(next, struct dentry, d_u.d_child); + dent = list_entry(next, struct dentry, d_child); if ((unsigned long)dent->d_fsdata == fpos) { if (dent->d_inode) dget(dent); diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 32c0658..6d5e7c5 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -194,7 +194,7 @@ ncp_renew_dentries(struct dentry *parent) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dentry = list_entry(next, struct dentry, d_u.d_child); + dentry = list_entry(next, struct dentry, d_child); if (dentry->d_fsdata == NULL) ncp_age_dentry(server, dentry); @@ -216,7 +216,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent) spin_lock(&parent->d_lock); next = parent->d_subdirs.next; while (next != &parent->d_subdirs) { - dentry = list_entry(next, struct dentry, d_u.d_child); + dentry = list_entry(next, struct dentry, d_child); dentry->d_fsdata = NULL; ncp_age_dentry(server, dentry); next = next->next; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 66984a9..5b8ab0e 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -58,7 +58,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i */ spin_lock(&sb->s_root->d_inode->i_lock); spin_lock(&sb->s_root->d_lock); - hlist_del_init(&sb->s_root->d_alias); + hlist_del_init(&sb->s_root->d_u.d_alias); spin_unlock(&sb->s_root->d_lock); spin_unlock(&sb->s_root->d_inode->i_lock); } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 4bb21d6..a3153e2 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); - list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 0d3a97d..1167485 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -173,7 +173,7 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, diff --git a/include/linux/cred.h b/include/linux/cred.h index 04421e8..6c58dd7 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -68,6 +68,7 @@ extern void groups_free(struct group_info *); extern int set_current_groups(struct group_info *); extern int set_groups(struct cred *, struct group_info *); extern int groups_search(const struct group_info *, kgid_t); +extern bool may_setgroups(void); /* access the groups "array" with this macro */ #define GROUP_AT(gi, i) \ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3b50cac..0f0eb1c 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -124,15 +124,15 @@ struct dentry { void *d_fsdata; /* fs-specific data */ struct list_head d_lru; /* LRU list */ + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ /* - * d_child and d_rcu can share memory + * d_alias and d_rcu can share memory */ union { - struct list_head d_child; /* child of parent list */ + struct hlist_node d_alias; /* inode alias list */ struct rcu_head d_rcu; } d_u; - struct list_head d_subdirs; /* our children */ - struct hlist_node d_alias; /* inode alias list */ }; /* diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4836ba3..dd4f91b 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -63,6 +63,7 @@ extern struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); +extern bool userns_may_setgroups(const struct user_namespace *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -87,6 +88,10 @@ static inline void put_user_ns(struct user_namespace *ns) { } +static inline bool userns_may_setgroups(const struct user_namespace *ns) +{ + return true; +} #endif #endif /* _LINUX_USER_H */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8e5e0a9..6f2aae9 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -980,7 +980,7 @@ static void cgroup_d_remove_dir(struct dentry *dentry) parent = dentry->d_parent; spin_lock(&parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - list_del_init(&dentry->d_u.d_child); + list_del_init(&dentry->d_child); spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); remove_dir(dentry); diff --git a/kernel/groups.c b/kernel/groups.c index 90cf1c3..67b4ba3 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/security.h> #include <linux/syscalls.h> +#include <linux/user_namespace.h> #include <asm/uaccess.h> /* init to 2 - one for init_task, one to ensure it is never freed */ @@ -223,6 +224,14 @@ out: return i; } +bool may_setgroups(void) +{ + struct user_namespace *user_ns = current_user_ns(); + + return ns_capable(user_ns, CAP_SETGID) && + userns_may_setgroups(user_ns); +} + /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. @@ -233,7 +242,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) struct group_info *group_info; int retval; - if (!ns_capable(current_user_ns(), CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9270fbc..111cc34 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6062,7 +6062,7 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; @@ -6089,7 +6089,7 @@ static int instance_rmdir(struct inode *inode, struct dentry *dentry) int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ba983dc..396c823 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -427,7 +427,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) if (dir) { spin_lock(&dir->d_lock); /* probably unneeded */ - list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dir->d_subdirs, d_child) { if (child->d_inode) /* probably unneeded */ child->d_inode->i_private = NULL; } diff --git a/kernel/uid16.c b/kernel/uid16.c index 602e5bb..d58cc4d 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) struct group_info *group_info; int retval; - if (!ns_capable(current_user_ns(), CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 4612096..8ee5170 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -804,17 +804,16 @@ static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { - /* Allow mapping to your own filesystem ids */ - if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) { + const struct cred *cred = file->f_cred; + /* Don't allow mappings that would allow anything that wouldn't + * be allowed without the establishment of unprivileged mappings. + */ + if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && + uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); - if (uid_eq(uid, file->f_cred->fsuid)) - return true; - } - else if (cap_setid == CAP_SETGID) { - kgid_t gid = make_kgid(ns->parent, id); - if (gid_eq(gid, file->f_cred->fsgid)) + if (uid_eq(uid, cred->euid)) return true; } } @@ -834,6 +833,20 @@ static bool new_idmap_permitted(const struct file *file, return false; } +bool userns_may_setgroups(const struct user_namespace *ns) +{ + bool allowed; + + mutex_lock(&id_map_mutex); + /* It is not safe to use setgroups until a gid mapping in + * the user namespace has been established. + */ + allowed = ns->gid_map.nr_extents != 0; + mutex_unlock(&id_map_mutex); + + return allowed; +} + static void *userns_get(struct task_struct *task) { struct user_namespace *user_ns; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 8a1d4b54..b3c4223 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -253,7 +253,7 @@ batadv_frag_merge_packets(struct hlist_head *chain, struct sk_buff *skb) kfree(entry); /* Make room for the rest of the fragments. */ - if (pskb_expand_head(skb_out, 0, size - skb->len, GFP_ATOMIC) < 0) { + if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { kfree_skb(skb_out); skb_out = NULL; goto free; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d83045c..d540da2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1640,7 +1640,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif - .mtu_reduced = tcp_v4_mtu_reduced, + .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1672,7 +1672,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif - .mtu_reduced = tcp_v6_mtu_reduced, + .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG diff --git a/security/keys/gc.c b/security/keys/gc.c index d3222b6..009d937 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -157,12 +157,12 @@ static noinline void key_gc_unused_keys(struct list_head *keys) if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) atomic_dec(&key->user->nikeys); - key_user_put(key->user); - /* now throw away the key memory */ if (key->type->destroy) key->type->destroy(key); + key_user_put(key->user); + kfree(key->description); #ifdef KEY_DEBUGGING diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 5122aff..392ab0f 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1192,7 +1192,7 @@ static void sel_remove_entries(struct dentry *de) spin_lock(&de->d_lock); node = de->d_subdirs.next; while (node != &de->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_u.d_child); + struct dentry *d = list_entry(node, struct dentry, d_child); spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(node); @@ -1666,12 +1666,12 @@ static void sel_remove_classes(void) list_for_each(class_node, &class_dir->d_subdirs) { struct dentry *class_subdir = list_entry(class_node, - struct dentry, d_u.d_child); + struct dentry, d_child); struct list_head *class_subdir_node; list_for_each(class_subdir_node, &class_subdir->d_subdirs) { struct dentry *d = list_entry(class_subdir_node, - struct dentry, d_u.d_child); + struct dentry, d_child); if (d->d_inode) if (d->d_inode->i_mode & S_IFDIR) -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html