From e014ff8d4285b81f0de0719d8eee72bc50bfd4be Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 21 Aug 2006 10:02:50 +0200 Subject: [PATCH] uninline ioprio_best() Saves 376 bytes (5 callers) for me. Signed-off-by: Oleg Nesterov Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 88d5961f7a3f..8e2042b9d471 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -59,27 +59,6 @@ static inline int task_nice_ioprio(struct task_struct *task) /* * For inheritance, return the highest of the two given priorities */ -static inline int ioprio_best(unsigned short aprio, unsigned short bprio) -{ - unsigned short aclass = IOPRIO_PRIO_CLASS(aprio); - unsigned short bclass = IOPRIO_PRIO_CLASS(bprio); - - if (!ioprio_valid(aprio)) - return bprio; - if (!ioprio_valid(bprio)) - return aprio; - - if (aclass == IOPRIO_CLASS_NONE) - aclass = IOPRIO_CLASS_BE; - if (bclass == IOPRIO_CLASS_NONE) - bclass = IOPRIO_CLASS_BE; - - if (aclass == bclass) - return min(aprio, bprio); - if (aclass > bclass) - return bprio; - else - return aprio; -} +extern int ioprio_best(unsigned short aprio, unsigned short bprio); #endif -- cgit v1.2.3 From 5d67476fff2df6ff12f60b540fd0e74cf2a668f9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 31 Jul 2006 14:11:48 -0700 Subject: SUNRPC: make rpc_unlink() take a dentry argument instead of a path Signe-off-by: Trond Myklebust (cherry picked from 88bf6d811b01a4be7fd507d18bf5f1c527989089 commit) --- fs/nfs/idmap.c | 3 +-- include/linux/sunrpc/rpc_pipe_fs.h | 2 +- net/sunrpc/auth_gss/auth_gss.c | 2 +- net/sunrpc/rpc_pipe.c | 20 ++++++-------------- 4 files changed, 9 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b81e7ed3c902..df0be1214358 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -130,9 +130,8 @@ nfs_idmap_delete(struct nfs4_client *clp) if (!idmap) return; + rpc_unlink(idmap->idmap_dentry); dput(idmap->idmap_dentry); - idmap->idmap_dentry = NULL; - rpc_unlink(idmap->idmap_path); clp->cl_idmap = NULL; kfree(idmap); } diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 2c2189cb30aa..04d2767d5ef7 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -44,7 +44,7 @@ extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); extern int rpc_rmdir(char *); extern struct dentry *rpc_mkpipe(char *, void *, struct rpc_pipe_ops *, int flags); -extern int rpc_unlink(char *); +extern int rpc_unlink(struct dentry *); extern struct vfsmount *rpc_get_mount(void); extern void rpc_put_mount(void); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 4a9aa9393b97..beaa7b848246 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -718,7 +718,7 @@ gss_destroy(struct rpc_auth *auth) auth, auth->au_flavor); gss_auth = container_of(auth, struct gss_auth, rpc_auth); - rpc_unlink(gss_auth->path); + rpc_unlink(gss_auth->dentry); dput(gss_auth->dentry); gss_auth->dentry = NULL; gss_mech_put(gss_auth->mech); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index a3bd2db2e024..9144f2767b66 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -746,22 +746,15 @@ err_dput: } int -rpc_unlink(char *path) +rpc_unlink(struct dentry *dentry) { - struct nameidata nd; - struct dentry *dentry; + struct dentry *parent; struct inode *dir; - int error; + int error = 0; - if ((error = rpc_lookup_parent(path, &nd)) != 0) - return error; - dir = nd.dentry->d_inode; + parent = dget_parent(dentry); + dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(nd.last.name, nd.dentry, nd.last.len); - if (IS_ERR(dentry)) { - error = PTR_ERR(dentry); - goto out_release; - } d_drop(dentry); if (dentry->d_inode) { rpc_close_pipes(dentry->d_inode); @@ -769,9 +762,8 @@ rpc_unlink(char *path) } dput(dentry); inode_dir_notify(dir, DN_DELETE); -out_release: mutex_unlock(&dir->i_mutex); - rpc_release_path(&nd); + dput(parent); return error; } -- cgit v1.2.3 From dff02cc1a34fcb60904a2c57cb351857cc11219e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 31 Jul 2006 14:17:18 -0700 Subject: NFS: clean up rpc_rmdir Make it take a dentry argument instead of a path Signed-off-by: Trond Myklebust (cherry picked from 648d4116eb2509f010f7f34704a650150309b3e7 commit) --- include/linux/sunrpc/rpc_pipe_fs.h | 2 +- net/sunrpc/clnt.c | 6 +++--- net/sunrpc/rpc_pipe.c | 18 +++++------------- 3 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 04d2767d5ef7..a481472c9484 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -42,7 +42,7 @@ RPC_I(struct inode *inode) extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); -extern int rpc_rmdir(char *); +extern int rpc_rmdir(struct dentry *); extern struct dentry *rpc_mkpipe(char *, void *, struct rpc_pipe_ops *, int flags); extern int rpc_unlink(struct dentry *); extern struct vfsmount *rpc_get_mount(void); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d6409e757219..d307556872db 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -183,7 +183,7 @@ rpc_new_client(struct rpc_xprt *xprt, char *servname, out_no_auth: if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_pathname); + rpc_rmdir(clnt->cl_dentry); dput(clnt->cl_dentry); rpc_put_mount(); } @@ -320,8 +320,8 @@ rpc_destroy_client(struct rpc_clnt *clnt) rpc_destroy_client(clnt->cl_parent); goto out_free; } - if (clnt->cl_pathname[0]) - rpc_rmdir(clnt->cl_pathname); + if (!IS_ERR(clnt->cl_dentry)) + rpc_rmdir(clnt->cl_dentry); if (clnt->cl_xprt) { xprt_destroy(clnt->cl_xprt); clnt->cl_xprt = NULL; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9144f2767b66..9c355e1ae61a 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -684,28 +684,20 @@ err_dput: } int -rpc_rmdir(char *path) +rpc_rmdir(struct dentry *dentry) { - struct nameidata nd; - struct dentry *dentry; + struct dentry *parent; struct inode *dir; int error; - if ((error = rpc_lookup_parent(path, &nd)) != 0) - return error; - dir = nd.dentry->d_inode; + parent = dget_parent(dentry); + dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(nd.last.name, nd.dentry, nd.last.len); - if (IS_ERR(dentry)) { - error = PTR_ERR(dentry); - goto out_release; - } rpc_depopulate(dentry); error = __rpc_rmdir(dir, dentry); dput(dentry); -out_release: mutex_unlock(&dir->i_mutex); - rpc_release_path(&nd); + dput(parent); return error; } -- cgit v1.2.3 From 8e037094c414172481c5ce903efdab50ce932343 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 22 Aug 2006 20:06:15 -0400 Subject: SUNRPC: avoid choosing an IPMI port for RPC traffic Some hardware uses port 664 for its hardware-based IPMI listener. Teach the RPC client to avoid using that port by raising the default minimum port number to 665. Test plan: Find a mainboard known to use port 664 for IPMI; enable IPMI; mount NFS servers in a tight loop. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust (cherry picked from 58e8cb3a035d22fc386e1c53a5d98c3f219530fb commit) --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 840e47a4ccc5..3a0cca255b76 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -37,7 +37,7 @@ extern unsigned int xprt_max_resvport; #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) -#define RPC_DEF_MIN_RESVPORT (650U) +#define RPC_DEF_MIN_RESVPORT (665U) #define RPC_DEF_MAX_RESVPORT (1023U) /* -- cgit v1.2.3 From 3cedf13af9f7e61aca0dbbd11b601ac93bf93a9f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 24 Aug 2006 15:44:12 -0400 Subject: NFSv4: increase client-provided nfs4 clientid size Neil Brown observed that the current limit of 32 bytes isn't enough to hold two ip addresses and the rest of the stuff we're putting in it, so it's often truncated to the point where it's unlikely to be unique. This can cause spurious CLID_INUSE's from the server. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust (cherry picked from fc8c17ec251e984ab3df9182ed097aa5b577c915 commit) --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2d3fb6416d91..db9cbf68e12b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -659,7 +659,7 @@ struct nfs4_rename_res { struct nfs4_setclientid { const nfs4_verifier * sc_verifier; /* request */ unsigned int sc_name_len; - char sc_name[32]; /* request */ + char sc_name[48]; /* request */ u32 sc_prog; /* request */ unsigned int sc_netid_len; char sc_netid[4]; /* request */ -- cgit v1.2.3 From 3a13813e6effcfad5910d47b15b724621b50b878 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sat, 26 Aug 2006 20:28:30 -0700 Subject: [BRIDGE] netfilter: memory corruption fix The bridge-netfilter code will overwrite memory if there is not headroom in the skb to save the header. This first showed up when using Xen with sky2 driver that doesn't allocate the extra space. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netfilter_bridge.h | 14 ++++++++++++-- net/bridge/br_forward.c | 10 +++++++--- 2 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 10c13dc4665b..427c67ff89e9 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -48,15 +48,25 @@ enum nf_br_hook_priorities { /* Only used in br_forward.c */ static inline -void nf_bridge_maybe_copy_header(struct sk_buff *skb) +int nf_bridge_maybe_copy_header(struct sk_buff *skb) { + int err; + if (skb->nf_bridge) { if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + err = skb_cow(skb, 18); + if (err) + return err; memcpy(skb->data - 18, skb->nf_bridge->data, 18); skb_push(skb, 4); - } else + } else { + err = skb_cow(skb, 16); + if (err) + return err; memcpy(skb->data - 16, skb->nf_bridge->data, 16); + } } + return 0; } /* This is called by the IP fragmenting code and it ensures there is diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 6ccd32b30809..864fbbc7b24d 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -40,11 +40,15 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) else { #ifdef CONFIG_BRIDGE_NETFILTER /* ip_refrag calls ip_fragment, doesn't copy the MAC header. */ - nf_bridge_maybe_copy_header(skb); + if (nf_bridge_maybe_copy_header(skb)) + kfree_skb(skb); + else #endif - skb_push(skb, ETH_HLEN); + { + skb_push(skb, ETH_HLEN); - dev_queue_xmit(skb); + dev_queue_xmit(skb); + } } return 0; -- cgit v1.2.3 From 533475d3d48eb839be2b57f6b020150abae91063 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Sun, 27 Aug 2006 01:23:39 -0700 Subject: [PATCH] vcsa attribute bits -> ioctl(VT_GETHIFONTMASK) When reading /dev/vcsa while a font with more than 256 characters is loaded, one of the attribute bits records the 9th bit of the character. But depending on the console driver (vgacon or fbcon for instance), that's bit 3 or bit 0. And there is no way for userland to know that, thus no way for userland to safely grab the screen content. So here is a (tested) patch: Add a VT_GETHIFONTMASK ioctl for knowing which bit is the 9th bit for VC text (vc_hi_font_mask field of the vc_data structure). Signed-off-by: Samuel Thibault Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/vt_ioctl.c | 2 ++ include/linux/compat_ioctl.h | 1 + include/linux/vt.h | 1 + 3 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/char/vt_ioctl.c b/drivers/char/vt_ioctl.c index eccffaf26faa..a5628a8b6620 100644 --- a/drivers/char/vt_ioctl.c +++ b/drivers/char/vt_ioctl.c @@ -1011,6 +1011,8 @@ int vt_ioctl(struct tty_struct *tty, struct file * file, return -EPERM; vt_dont_switch = 0; return 0; + case VT_GETHIFONTMASK: + return put_user(vc->vc_hi_font_mask, (unsigned short __user *)arg); default: return -ENOIOCTLCMD; } diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 269d000bb2a3..bea0255196c4 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -216,6 +216,7 @@ COMPATIBLE_IOCTL(VT_RESIZE) COMPATIBLE_IOCTL(VT_RESIZEX) COMPATIBLE_IOCTL(VT_LOCKSWITCH) COMPATIBLE_IOCTL(VT_UNLOCKSWITCH) +COMPATIBLE_IOCTL(VT_GETHIFONTMASK) /* Little p (/dev/rtc, /dev/envctrl, etc.) */ COMPATIBLE_IOCTL(RTC_AIE_ON) COMPATIBLE_IOCTL(RTC_AIE_OFF) diff --git a/include/linux/vt.h b/include/linux/vt.h index 8ab334a48222..ba806e8711be 100644 --- a/include/linux/vt.h +++ b/include/linux/vt.h @@ -60,5 +60,6 @@ struct vt_consize { #define VT_RESIZEX 0x560A /* set kernel's idea of screensize + more */ #define VT_LOCKSWITCH 0x560B /* disallow vt switching */ #define VT_UNLOCKSWITCH 0x560C /* allow vt switching */ +#define VT_GETHIFONTMASK 0x560D /* return hi font mask */ #endif /* _LINUX_VT_H */ -- cgit v1.2.3 From ea817398e68dfa25612229fda7fc74580cf915fb Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Sun, 27 Aug 2006 01:23:52 -0700 Subject: [PATCH] Manage jbd allocations from its own slabs JBD currently allocates commit and frozen buffers from slabs. With CONFIG_SLAB_DEBUG, its possible for an allocation to cross the page boundary causing IO problems. https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=200127 So, instead of allocating these from regular slabs - manage allocation from its own slabs and disable slab debug for these slabs. [akpm@osdl.org: cleanups] Signed-off-by: Badari Pulavarty Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd/commit.c | 6 ++-- fs/jbd/journal.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++---- fs/jbd/transaction.c | 9 ++--- include/linux/jbd.h | 3 ++ 4 files changed, 97 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 0971814c38b8..42da60784311 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -261,7 +261,7 @@ void journal_commit_transaction(journal_t *journal) struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_state(bh); - kfree(jh->b_committed_data); + jbd_slab_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; jbd_unlock_bh_state(bh); } @@ -745,14 +745,14 @@ restart_loop: * Otherwise, we can just throw away the frozen data now. */ if (jh->b_committed_data) { - kfree(jh->b_committed_data); + jbd_slab_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; if (jh->b_frozen_data) { jh->b_committed_data = jh->b_frozen_data; jh->b_frozen_data = NULL; } } else if (jh->b_frozen_data) { - kfree(jh->b_frozen_data); + jbd_slab_free(jh->b_frozen_data, bh->b_size); jh->b_frozen_data = NULL; } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 8c9b28dff119..f66724ce443a 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -84,6 +84,7 @@ EXPORT_SYMBOL(journal_force_commit); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); +static int journal_create_jbd_slab(size_t slab_size); /* * Helper function used to manage commit timeouts @@ -328,10 +329,10 @@ repeat: char *tmp; jbd_unlock_bh_state(bh_in); - tmp = jbd_rep_kmalloc(bh_in->b_size, GFP_NOFS); + tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS); jbd_lock_bh_state(bh_in); if (jh_in->b_frozen_data) { - kfree(tmp); + jbd_slab_free(tmp, bh_in->b_size); goto repeat; } @@ -1069,17 +1070,17 @@ static int load_superblock(journal_t *journal) int journal_load(journal_t *journal) { int err; + journal_superblock_t *sb; err = load_superblock(journal); if (err) return err; + sb = journal->j_superblock; /* If this is a V2 superblock, then we have to check the * features flags on it. */ if (journal->j_format_version >= 2) { - journal_superblock_t *sb = journal->j_superblock; - if ((sb->s_feature_ro_compat & ~cpu_to_be32(JFS_KNOWN_ROCOMPAT_FEATURES)) || (sb->s_feature_incompat & @@ -1090,6 +1091,13 @@ int journal_load(journal_t *journal) } } + /* + * Create a slab for this blocksize + */ + err = journal_create_jbd_slab(cpu_to_be32(sb->s_blocksize)); + if (err) + return err; + /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (journal_recover(journal)) @@ -1611,6 +1619,77 @@ void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry) return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0)); } +/* + * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed + * and allocate frozen and commit buffers from these slabs. + * + * Reason for doing this is to avoid, SLAB_DEBUG - since it could + * cause bh to cross page boundary. + */ + +#define JBD_MAX_SLABS 5 +#define JBD_SLAB_INDEX(size) (size >> 11) + +static kmem_cache_t *jbd_slab[JBD_MAX_SLABS]; +static const char *jbd_slab_names[JBD_MAX_SLABS] = { + "jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k" +}; + +static void journal_destroy_jbd_slabs(void) +{ + int i; + + for (i = 0; i < JBD_MAX_SLABS; i++) { + if (jbd_slab[i]) + kmem_cache_destroy(jbd_slab[i]); + jbd_slab[i] = NULL; + } +} + +static int journal_create_jbd_slab(size_t slab_size) +{ + int i = JBD_SLAB_INDEX(slab_size); + + BUG_ON(i >= JBD_MAX_SLABS); + + /* + * Check if we already have a slab created for this size + */ + if (jbd_slab[i]) + return 0; + + /* + * Create a slab and force alignment to be same as slabsize - + * this will make sure that allocations won't cross the page + * boundary. + */ + jbd_slab[i] = kmem_cache_create(jbd_slab_names[i], + slab_size, slab_size, 0, NULL, NULL); + if (!jbd_slab[i]) { + printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n"); + return -ENOMEM; + } + return 0; +} + +void * jbd_slab_alloc(size_t size, gfp_t flags) +{ + int idx; + + idx = JBD_SLAB_INDEX(size); + BUG_ON(jbd_slab[idx] == NULL); + return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL); +} + +void jbd_slab_free(void *ptr, size_t size) +{ + int idx; + + idx = JBD_SLAB_INDEX(size); + BUG_ON(jbd_slab[idx] == NULL); + kmem_cache_free(jbd_slab[idx], ptr); +} + /* * Journal_head storage management */ @@ -1799,13 +1878,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh) printk(KERN_WARNING "%s: freeing " "b_frozen_data\n", __FUNCTION__); - kfree(jh->b_frozen_data); + jbd_slab_free(jh->b_frozen_data, bh->b_size); } if (jh->b_committed_data) { printk(KERN_WARNING "%s: freeing " "b_committed_data\n", __FUNCTION__); - kfree(jh->b_committed_data); + jbd_slab_free(jh->b_committed_data, bh->b_size); } bh->b_private = NULL; jh->b_bh = NULL; /* debug, really */ @@ -1961,6 +2040,7 @@ static void journal_destroy_caches(void) journal_destroy_revoke_caches(); journal_destroy_journal_head_cache(); journal_destroy_handle_cache(); + journal_destroy_jbd_slabs(); } static int __init journal_init(void) diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 508b2ea91f43..de2e4cbbf79a 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -666,8 +666,9 @@ repeat: if (!frozen_buffer) { JBUFFER_TRACE(jh, "allocate memory for buffer"); jbd_unlock_bh_state(bh); - frozen_buffer = jbd_kmalloc(jh2bh(jh)->b_size, - GFP_NOFS); + frozen_buffer = + jbd_slab_alloc(jh2bh(jh)->b_size, + GFP_NOFS); if (!frozen_buffer) { printk(KERN_EMERG "%s: OOM for frozen_buffer\n", @@ -879,7 +880,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh) repeat: if (!jh->b_committed_data) { - committed_data = jbd_kmalloc(jh2bh(jh)->b_size, GFP_NOFS); + committed_data = jbd_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!committed_data) { printk(KERN_EMERG "%s: No memory for committed data\n", __FUNCTION__); @@ -906,7 +907,7 @@ repeat: out: journal_put_journal_head(jh); if (unlikely(committed_data)) - kfree(committed_data); + jbd_slab_free(committed_data, bh->b_size); return err; } diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 20eb34403d0c..a04c154c5207 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -72,6 +72,9 @@ extern int journal_enable_debug; #endif extern void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry); +extern void * jbd_slab_alloc(size_t size, gfp_t flags); +extern void jbd_slab_free(void *ptr, size_t size); + #define jbd_kmalloc(size, flags) \ __jbd_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) #define jbd_rep_kmalloc(size, flags) \ -- cgit v1.2.3 From 36920e069a87c6fccffbc0ec5e74985d94d3bcc4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Sun, 27 Aug 2006 01:23:52 -0700 Subject: [PATCH] register_one_node() compile fix register_one_node()'s should be defined under CONFIG_NUMA=n. fixes following bug. CC init/version.o LD init/built-in.o LD .tmp_vmlinux1 mm/built-in.o: In function `add_memory': undefined reference to `register_one_node' Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/node.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/node.h b/include/linux/node.h index 81dcec84cd8f..bc001bc225c3 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -30,12 +30,20 @@ extern struct node node_devices[]; extern int register_node(struct node *, int, struct node *); extern void unregister_node(struct node *node); +#ifdef CONFIG_NUMA extern int register_one_node(int nid); extern void unregister_one_node(int nid); -#ifdef CONFIG_NUMA extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); #else +static inline int register_one_node(int nid) +{ + return 0; +} +static inline int unregister_one_node(int nid) +{ + return 0; +} static inline int register_cpu_under_node(unsigned int cpu, unsigned int nid) { return 0; -- cgit v1.2.3 From 4df46240a1312161e3c794f6ace50ef7eb5ff3d7 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 27 Aug 2006 01:23:56 -0700 Subject: [PATCH] lockdep: annotate reiserfs reiserfs seems to have another locking level layer for the i_mutex due to the xattrs-are-a-directory thing. Signed-off-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/reiserfs/xattr.c | 2 +- include/linux/fs.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 39fedaa88a0c..d935fb9394e3 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -424,7 +424,7 @@ int xattr_readdir(struct file *file, filldir_t filler, void *buf) int res = -ENOTDIR; if (!file->f_op || !file->f_op->readdir) goto out; - mutex_lock(&inode->i_mutex); + mutex_lock_nested(&inode->i_mutex, I_MUTEX_XATTR); // down(&inode->i_zombie); res = -ENOENT; if (!IS_DEADDIR(inode)) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 25610205c90d..555bc195c420 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -570,13 +570,14 @@ struct inode { * 3: quota file * * The locking order between these classes is - * parent -> child -> normal -> quota + * parent -> child -> normal -> xattr -> quota */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, + I_MUTEX_XATTR, I_MUTEX_QUOTA }; -- cgit v1.2.3 From 01da5fd83d6b2c5e36b77539f6cbdd8f49849225 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Sun, 27 Aug 2006 01:24:02 -0700 Subject: [PATCH] Fix tty layer DoS and comment relevant code Unlike the other tty comment patch this one has code changes. Specifically it limits the queue size for a tty to 64K characters (128Kbytes) worst case even if the tty is ignoring tty->throttle. This is because certain drivers don't honour the throttle value correctly, although it is a useful safeguard anyway. Signed-off-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/tty_io.c | 89 +++++++++++++++++++++++++++++++++++++++++++++------ include/linux/tty.h | 1 + 2 files changed, 80 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index 2cef982585f0..bb0d9199e994 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -265,6 +265,17 @@ static int check_tty_count(struct tty_struct *tty, const char *routine) */ +/** + * tty_buffer_free_all - free buffers used by a tty + * @tty: tty to free from + * + * Remove all the buffers pending on a tty whether queued with data + * or in the free ring. Must be called when the tty is no longer in use + * + * Locking: none + */ + + /** * tty_buffer_free_all - free buffers used by a tty * @tty: tty to free from @@ -287,19 +298,47 @@ static void tty_buffer_free_all(struct tty_struct *tty) kfree(thead); } tty->buf.tail = NULL; + tty->buf.memory_used = 0; } +/** + * tty_buffer_init - prepare a tty buffer structure + * @tty: tty to initialise + * + * Set up the initial state of the buffer management for a tty device. + * Must be called before the other tty buffer functions are used. + * + * Locking: none + */ + static void tty_buffer_init(struct tty_struct *tty) { spin_lock_init(&tty->buf.lock); tty->buf.head = NULL; tty->buf.tail = NULL; tty->buf.free = NULL; + tty->buf.memory_used = 0; } -static struct tty_buffer *tty_buffer_alloc(size_t size) +/** + * tty_buffer_alloc - allocate a tty buffer + * @tty: tty device + * @size: desired size (characters) + * + * Allocate a new tty buffer to hold the desired number of characters. + * Return NULL if out of memory or the allocation would exceed the + * per device queue + * + * Locking: Caller must hold tty->buf.lock + */ + +static struct tty_buffer *tty_buffer_alloc(struct tty_struct *tty, size_t size) { - struct tty_buffer *p = kmalloc(sizeof(struct tty_buffer) + 2 * size, GFP_ATOMIC); + struct tty_buffer *p; + + if (tty->buf.memory_used + size > 65536) + return NULL; + p = kmalloc(sizeof(struct tty_buffer) + 2 * size, GFP_ATOMIC); if(p == NULL) return NULL; p->used = 0; @@ -309,17 +348,27 @@ static struct tty_buffer *tty_buffer_alloc(size_t size) p->read = 0; p->char_buf_ptr = (char *)(p->data); p->flag_buf_ptr = (unsigned char *)p->char_buf_ptr + size; -/* printk("Flip create %p\n", p); */ + tty->buf.memory_used += size; return p; } -/* Must be called with the tty_read lock held. This needs to acquire strategy - code to decide if we should kfree or relink a given expired buffer */ +/** + * tty_buffer_free - free a tty buffer + * @tty: tty owning the buffer + * @b: the buffer to free + * + * Free a tty buffer, or add it to the free list according to our + * internal strategy + * + * Locking: Caller must hold tty->buf.lock + */ static void tty_buffer_free(struct tty_struct *tty, struct tty_buffer *b) { /* Dumb strategy for now - should keep some stats */ -/* printk("Flip dispose %p\n", b); */ + tty->buf.memory_used -= b->size; + WARN_ON(tty->buf.memory_used < 0); + if(b->size >= 512) kfree(b); else { @@ -328,6 +377,18 @@ static void tty_buffer_free(struct tty_struct *tty, struct tty_buffer *b) } } +/** + * tty_buffer_find - find a free tty buffer + * @tty: tty owning the buffer + * @size: characters wanted + * + * Locate an existing suitable tty buffer or if we are lacking one then + * allocate a new one. We round our buffers off in 256 character chunks + * to get better allocation behaviour. + * + * Locking: Caller must hold tty->buf.lock + */ + static struct tty_buffer *tty_buffer_find(struct tty_struct *tty, size_t size) { struct tty_buffer **tbh = &tty->buf.free; @@ -339,20 +400,28 @@ static struct tty_buffer *tty_buffer_find(struct tty_struct *tty, size_t size) t->used = 0; t->commit = 0; t->read = 0; - /* DEBUG ONLY */ -/* memset(t->data, '*', size); */ -/* printk("Flip recycle %p\n", t); */ + tty->buf.memory_used += t->size; return t; } tbh = &((*tbh)->next); } /* Round the buffer size out */ size = (size + 0xFF) & ~ 0xFF; - return tty_buffer_alloc(size); + return tty_buffer_alloc(tty, size); /* Should possibly check if this fails for the largest buffer we have queued and recycle that ? */ } +/** + * tty_buffer_request_room - grow tty buffer if needed + * @tty: tty structure + * @size: size desired + * + * Make at least size bytes of linear space available for the tty + * buffer. If we fail return the size we managed to find. + * + * Locking: Takes tty->buf.lock + */ int tty_buffer_request_room(struct tty_struct *tty, size_t size) { struct tty_buffer *b, *n; diff --git a/include/linux/tty.h b/include/linux/tty.h index e421d5e34818..04827ca65781 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -59,6 +59,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct tty_buffer *free; /* Free queue head */ + int memory_used; /* Buffer space used excluding free queue */ }; /* * The pty uses char_buf and flag_buf as a contiguous buffer -- cgit v1.2.3