From 47376ceba54600cec4dd9e7c4fe8b98e4269633a Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Dec 2009 23:25:50 +0100 Subject: reiserfs: Fix reiserfs lock <-> inode mutex dependency inversion The reiserfs lock -> inode mutex dependency gets inverted when we relax the lock while walking to the tree. To fix this, use a specialized version of reiserfs_mutex_lock_safe that takes care of mutex subclasses. Then we can grab the inode mutex with I_MUTEX_XATTR subclass without any reiserfs lock dependency. This fixes the following report: [ INFO: possible circular locking dependency detected ] 2.6.32-06793-gf405425-dirty #2 ------------------------------------------------------- mv/18566 is trying to acquire lock: (&REISERFS_SB(s)->lock){+.+.+.}, at: [] reiserfs_write_lock+0x28= /0x40 but task is already holding lock: (&sb->s_type->i_mutex_key#5/3){+.+.+.}, at: [] reiserfs_for_each_xattr+0x10c/0x380 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sb->s_type->i_mutex_key#5/3){+.+.+.}: [] validate_chain+0xa23/0xf70 [] __lock_acquire+0x4e5/0xa70 [] lock_acquire+0x7a/0xa0 [] mutex_lock_nested+0x5f/0x2b0 [] reiserfs_for_each_xattr+0x84/0x380 [] reiserfs_delete_xattrs+0x15/0x50 [] reiserfs_delete_inode+0x8f/0x140 [] generic_delete_inode+0x9c/0x150 [] generic_drop_inode+0x3d/0x60 [] iput+0x47/0x50 [] do_unlinkat+0xdb/0x160 [] sys_unlink+0x10/0x20 [] sysenter_do_call+0x12/0x36 -> #0 (&REISERFS_SB(s)->lock){+.+.+.}: [] validate_chain+0xf68/0xf70 [] __lock_acquire+0x4e5/0xa70 [] lock_acquire+0x7a/0xa0 [] mutex_lock_nested+0x5f/0x2b0 [] reiserfs_write_lock+0x28/0x40 [] search_by_key+0x1f7b/0x21b0 [] search_by_entry_key+0x1f/0x3b0 [] reiserfs_find_entry+0x77/0x400 [] reiserfs_lookup+0x85/0x130 [] __lookup_hash+0xb4/0x110 [] lookup_one_len+0xb3/0x100 [] reiserfs_for_each_xattr+0x120/0x380 [] reiserfs_delete_xattrs+0x15/0x50 [] reiserfs_delete_inode+0x8f/0x140 [] generic_delete_inode+0x9c/0x150 [] generic_drop_inode+0x3d/0x60 [] iput+0x47/0x50 [] dentry_iput+0x6f/0xf0 [] d_kill+0x24/0x50 [] dput+0x5b/0x120 [] sys_renameat+0x1b9/0x230 [] sys_rename+0x28/0x30 [] sysenter_do_call+0x12/0x36 other info that might help us debug this: 2 locks held by mv/18566: #0: (&sb->s_type->i_mutex_key#5/1){+.+.+.}, at: [] lock_rename+0xcc/0xd0 #1: (&sb->s_type->i_mutex_key#5/3){+.+.+.}, at: [] reiserfs_for_each_xattr+0x10c/0x380 stack backtrace: Pid: 18566, comm: mv Tainted: G C 2.6.32-06793-gf405425-dirty #2 Call Trace: [] ? printk+0x18/0x1e [] print_circular_bug+0xc0/0xd0 [] validate_chain+0xf68/0xf70 [] ? trace_hardirqs_off+0xb/0x10 [] __lock_acquire+0x4e5/0xa70 [] lock_acquire+0x7a/0xa0 [] ? reiserfs_write_lock+0x28/0x40 [] mutex_lock_nested+0x5f/0x2b0 [] ? reiserfs_write_lock+0x28/0x40 [] ? reiserfs_write_lock+0x28/0x40 [] ? schedule+0x27a/0x440 [] reiserfs_write_lock+0x28/0x40 [] search_by_key+0x1f7b/0x21b0 [] ? __lock_acquire+0x506/0xa70 [] ? lock_release_non_nested+0x1e7/0x340 [] ? reiserfs_write_lock+0x28/0x40 [] ? trace_hardirqs_on_caller+0x124/0x170 [] ? trace_hardirqs_on+0xb/0x10 [] ? T.316+0x15/0x1a0 [] ? sched_clock_cpu+0x9d/0x100 [] search_by_entry_key+0x1f/0x3b0 [] ? __mutex_unlock_slowpath+0x9a/0x120 [] ? trace_hardirqs_on_caller+0x124/0x170 [] reiserfs_find_entry+0x77/0x400 [] reiserfs_lookup+0x85/0x130 [] ? sched_clock_cpu+0x9d/0x100 [] __lookup_hash+0xb4/0x110 [] lookup_one_len+0xb3/0x100 [] reiserfs_for_each_xattr+0x120/0x380 [] ? delete_one_xattr+0x0/0x1c0 [] ? math_error+0x22/0x150 [] ? reiserfs_write_lock+0x28/0x40 [] reiserfs_delete_xattrs+0x15/0x50 [] ? reiserfs_write_lock+0x28/0x40 [] reiserfs_delete_inode+0x8f/0x140 [] ? generic_delete_inode+0x5f/0x150 [] ? reiserfs_delete_inode+0x0/0x140 [] generic_delete_inode+0x9c/0x150 [] generic_drop_inode+0x3d/0x60 [] iput+0x47/0x50 [] dentry_iput+0x6f/0xf0 [] d_kill+0x24/0x50 [] dput+0x5b/0x120 [] sys_renameat+0x1b9/0x230 [] ? sched_clock_cpu+0x9d/0x100 [] ? trace_hardirqs_off+0xb/0x10 [] ? cpu_clock+0x4e/0x60 [] ? do_page_fault+0x155/0x370 [] ? up_read+0x16/0x30 [] ? do_page_fault+0x155/0x370 [] sys_rename+0x28/0x30 [] sysenter_do_call+0x12/0x36 Reported-by: Alexander Beregalov Signed-off-by: Frederic Weisbecker Cc: Chris Mason Cc: Ingo Molnar Cc: Thomas Gleixner --- include/linux/reiserfs_fs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index a05b4a20768d..4351b49e2b1e 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -97,6 +97,15 @@ static inline void reiserfs_mutex_lock_safe(struct mutex *m, reiserfs_write_lock(s); } +static inline void +reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass, + struct super_block *s) +{ + reiserfs_write_unlock(s); + mutex_lock_nested(m, subclass); + reiserfs_write_lock(s); +} + /* * When we schedule, we usually want to also release the write lock, * according to the previous bkl based locking scheme of reiserfs. -- cgit v1.2.3 From 2d1c861871d767153538a77c498752b36d4bb4b8 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 9 Dec 2009 17:52:13 +1100 Subject: PCI/cardbus: Add a fixup hook and fix powerpc The cardbus code creates PCI devices without ever going through the necessary fixup bits and pieces that normal PCI devices go through. There's in fact a commented out call to pcibios_fixup_bus() in there, it's commented because ... it doesn't work. I could make pcibios_fixup_bus() do the right thing on powerpc easily but I felt it cleaner instead to provide a specific hook pci_fixup_cardbus for which a weak empty implementation is provided by the PCI core. This fixes cardbus on powerbooks and probably all other PowerPC platforms which was broken completely for ever on some platforms and since 2.6.31 on others such as PowerBooks when we made the DMA ops mandatory (since those are setup by the fixups). Acked-by: Dominik Brodowski Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Jesse Barnes --- arch/powerpc/kernel/pci-common.c | 13 +++++++++++++ drivers/pci/pci.c | 5 +++++ drivers/pcmcia/cardbus.c | 2 +- include/linux/pci.h | 3 +++ 4 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index e8dfdbd9327a..cadbed679fbb 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1107,6 +1107,12 @@ void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { struct dev_archdata *sd = &dev->dev.archdata; + /* Cardbus can call us to add new devices to a bus, so ignore + * those who are already fully discovered + */ + if (dev->is_added) + continue; + /* Setup OF node pointer in archdata */ sd->of_node = pci_device_to_OF_node(dev); @@ -1147,6 +1153,13 @@ void __devinit pcibios_fixup_bus(struct pci_bus *bus) } EXPORT_SYMBOL(pcibios_fixup_bus); +void __devinit pci_fixup_cardbus(struct pci_bus *bus) +{ + /* Now fixup devices on that bus */ + pcibios_setup_bus_devices(bus); +} + + static int skip_isa_ioresource_align(struct pci_dev *dev) { if ((ppc_pci_flags & PPC_PCI_CAN_SKIP_ISA_ALIGN) && diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d50522bf16b1..864e703cf737 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2798,6 +2798,11 @@ int __attribute__ ((weak)) pci_ext_cfg_avail(struct pci_dev *dev) return 1; } +void __weak pci_fixup_cardbus(struct pci_bus *bus) +{ +} +EXPORT_SYMBOL(pci_fixup_cardbus); + static int __init pci_setup(char *str) { while (str) { diff --git a/drivers/pcmcia/cardbus.c b/drivers/pcmcia/cardbus.c index cdf50f3bc2df..d99f846451a3 100644 --- a/drivers/pcmcia/cardbus.c +++ b/drivers/pcmcia/cardbus.c @@ -222,7 +222,7 @@ int __ref cb_alloc(struct pcmcia_socket *s) unsigned int max, pass; s->functions = pci_scan_slot(bus, PCI_DEVFN(0, 0)); -/* pcibios_fixup_bus(bus); */ + pci_fixup_cardbus(bus); max = bus->secondary; for (pass = 0; pass < 2; pass++) diff --git a/include/linux/pci.h b/include/linux/pci.h index bf1e67080849..5da0690d9cee 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -566,6 +566,9 @@ void pcibios_align_resource(void *, struct resource *, resource_size_t, resource_size_t); void pcibios_update_irq(struct pci_dev *, int irq); +/* Weak but can be overriden by arch */ +void pci_fixup_cardbus(struct pci_bus *); + /* Generic PCI functions used internally */ extern struct pci_bus *pci_find_bus(int domain, int busnr); -- cgit v1.2.3 From 9a418af5df03ad133cd8c8f6742b75e542db6392 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 17 Dec 2009 13:55:48 +0100 Subject: mac80211: fix peer HT capabilities I noticed yesterday, because Jeff had noticed a speed regression, cf. bug http://bugzilla.intellinuxwireless.org/show_bug.cgi?id=2138 that the SM PS settings for peers were wrong. Instead of overwriting the SM PS settings with the local bits, we need to keep the remote bits. The bug was part of the original HT code from over two years ago, but unfortunately nobody noticed that it makes no sense -- we shouldn't be overwriting the peer's setting with our own but rather keep it intact when masking the peer capabilities with our own. While fixing that, I noticed that the masking of capabilities is completely useless for most of the bits, so also fix those other bits. Finally, I also noticed that PSMP_SUPPORT no longer exists in the final 802.11n version, so also remove that. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/rt2x00/rt2800lib.c | 3 +-- include/linux/ieee80211.h | 2 +- net/mac80211/ht.c | 25 ++++++++++++++++++++++--- 3 files changed, 24 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 6bf6c0f12f35..27bf887f1453 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -2080,8 +2080,7 @@ int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | IEEE80211_HT_CAP_TX_STBC | - IEEE80211_HT_CAP_RX_STBC | - IEEE80211_HT_CAP_PSMP_SUPPORT; + IEEE80211_HT_CAP_RX_STBC; spec->ht.ampdu_factor = 3; spec->ht.ampdu_density = 4; spec->ht.mcs.tx_params = diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9724a28c0c2..163c840437d6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -832,7 +832,7 @@ struct ieee80211_ht_cap { #define IEEE80211_HT_CAP_DELAY_BA 0x0400 #define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 #define IEEE80211_HT_CAP_DSSSCCK40 0x1000 -#define IEEE80211_HT_CAP_PSMP_SUPPORT 0x2000 +#define IEEE80211_HT_CAP_RESERVED 0x2000 #define IEEE80211_HT_CAP_40MHZ_INTOLERANT 0x4000 #define IEEE80211_HT_CAP_LSIG_TXOP_PROT 0x8000 diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 3787455fb696..d7dcee680728 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -34,9 +34,28 @@ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_supported_band *sband, ht_cap->ht_supported = true; - ht_cap->cap = le16_to_cpu(ht_cap_ie->cap_info) & sband->ht_cap.cap; - ht_cap->cap &= ~IEEE80211_HT_CAP_SM_PS; - ht_cap->cap |= sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS; + /* + * The bits listed in this expression should be + * the same for the peer and us, if the station + * advertises more then we can't use those thus + * we mask them out. + */ + ht_cap->cap = le16_to_cpu(ht_cap_ie->cap_info) & + (sband->ht_cap.cap | + ~(IEEE80211_HT_CAP_LDPC_CODING | + IEEE80211_HT_CAP_SUP_WIDTH_20_40 | + IEEE80211_HT_CAP_GRN_FLD | + IEEE80211_HT_CAP_SGI_20 | + IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_DSSSCCK40)); + /* + * The STBC bits are asymmetric -- if we don't have + * TX then mask out the peer's RX and vice versa. + */ + if (!(sband->ht_cap.cap & IEEE80211_HT_CAP_TX_STBC)) + ht_cap->cap &= ~IEEE80211_HT_CAP_RX_STBC; + if (!(sband->ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)) + ht_cap->cap &= ~IEEE80211_HT_CAP_TX_STBC; ampdu_info = ht_cap_ie->ampdu_params_info; ht_cap->ampdu_factor = -- cgit v1.2.3 From cc3e1bea5d87635c519da657303690f5538bb4eb Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 23 Dec 2009 06:52:08 -0500 Subject: ext4, jbd2: Add barriers for file systems with exernal journals This is a bit complicated because we are trying to optimize when we send barriers to the fs data disk. We could just throw in an extra barrier to the data disk whenever we send a barrier to the journal disk, but that's not always strictly necessary. We only need to send a barrier during a commit when there are data blocks which are must be written out due to an inode written in ordered mode, or if fsync() depends on the commit to force data blocks to disk. Finally, before we drop transactions from the beginning of the journal during a checkpoint operation, we need to guarantee that any blocks that were flushed out to the data disk are firmly on the rust platter before we drop the transaction from the journal. Thanks to Oleg Drokin for pointing out this flaw in ext3/ext4. Signed-off-by: "Theodore Ts'o" --- fs/ext4/fsync.c | 16 ++++++++++++++-- fs/jbd2/checkpoint.c | 15 +++++++++++++++ fs/jbd2/commit.c | 19 +++++++++++-------- include/linux/jbd2.h | 1 + 4 files changed, 41 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 0b22497d92e1..98bd140aad01 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -88,9 +88,21 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) return ext4_force_commit(inode->i_sb); commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; - if (jbd2_log_start_commit(journal, commit_tid)) + if (jbd2_log_start_commit(journal, commit_tid)) { + /* + * When the journal is on a different device than the + * fs data disk, we need to issue the barrier in + * writeback mode. (In ordered mode, the jbd2 layer + * will take care of issuing the barrier. In + * data=journal, all of the data blocks are written to + * the journal device.) + */ + if (ext4_should_writeback_data(inode) && + (journal->j_fs_dev != journal->j_dev) && + (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(inode->i_sb->s_bdev, NULL); jbd2_log_wait_commit(journal, commit_tid); - else if (journal->j_flags & JBD2_BARRIER) + } else if (journal->j_flags & JBD2_BARRIER) blkdev_issue_flush(inode->i_sb->s_bdev, NULL); return ret; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index ca0f5eb62b20..886849370950 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -22,6 +22,7 @@ #include #include #include +#include #include /* @@ -515,6 +516,20 @@ int jbd2_cleanup_journal_tail(journal_t *journal) journal->j_tail_sequence = first_tid; journal->j_tail = blocknr; spin_unlock(&journal->j_state_lock); + + /* + * If there is an external journal, we need to make sure that + * any data blocks that were recently written out --- perhaps + * by jbd2_log_do_checkpoint() --- are flushed out before we + * drop the transactions from the external journal. It's + * unlikely this will be necessary, especially with a + * appropriately sized journal, but we need this to guarantee + * correctness. Fortunately jbd2_cleanup_journal_tail() + * doesn't get called all that often. + */ + if ((journal->j_fs_dev != journal->j_dev) && + (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(journal->j_fs_dev, NULL); if (!(journal->j_flags & JBD2_ABORT)) jbd2_journal_update_superblock(journal, 1); return 0; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 6a10238d2c63..1bc74b6f26d2 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -259,6 +259,7 @@ static int journal_submit_data_buffers(journal_t *journal, ret = err; spin_lock(&journal->j_list_lock); J_ASSERT(jinode->i_transaction == commit_transaction); + commit_transaction->t_flushed_data_blocks = 1; jinode->i_flags &= ~JI_COMMIT_RUNNING; wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } @@ -708,8 +709,17 @@ start_journal_io: } } - /* Done it all: now write the commit record asynchronously. */ + /* + * If the journal is not located on the file system device, + * then we must flush the file system device before we issue + * the commit record + */ + if (commit_transaction->t_flushed_data_blocks && + (journal->j_fs_dev != journal->j_dev) && + (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(journal->j_fs_dev, NULL); + /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { err = journal_submit_commit_record(journal, commit_transaction, @@ -720,13 +730,6 @@ start_journal_io: blkdev_issue_flush(journal->j_dev, NULL); } - /* - * This is the right place to wait for data buffers both for ASYNC - * and !ASYNC commit. If commit is ASYNC, we need to wait only after - * the commit block went to disk (which happens above). If commit is - * SYNC, we need to wait for data buffers before we start writing - * commit block, which happens below in such setting. - */ err = journal_finish_inode_data_buffers(journal, commit_transaction); if (err) { printk(KERN_WARNING diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f1011f7f3d41..638ce4554c76 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -653,6 +653,7 @@ struct transaction_s * waiting for it to finish. */ unsigned int t_synchronous_commit:1; + unsigned int t_flushed_data_blocks:1; /* * For use by the filesystem to store fs-specific data -- cgit v1.2.3 From 17bd55d037a02b04d9119511cfd1a4b985d20f63 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 23 Dec 2009 07:57:07 -0500 Subject: fs-writeback: Add helper function to start writeback if idle ext4, at least, would like to start pushing on writeback if it starts to get close to ENOSPC when reserving worst-case blocks for delalloc writes. Writing out delalloc data will convert those worst-case predictions into usually smaller actual usage, freeing up space before we hit ENOSPC based on this speculation. Thanks to Jens for the suggestion for the helper function, & the naming help. I've made the helper return status on whether writeback was started even though I don't plan to use it in the ext4 patch; it seems like it would be potentially useful to test this in some cases. Signed-off-by: Eric Sandeen Acked-by: Jan Kara --- fs/fs-writeback.c | 17 +++++++++++++++++ include/linux/writeback.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 49bc1b8e8f19..f6c2155e0026 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1186,6 +1186,23 @@ void writeback_inodes_sb(struct super_block *sb) } EXPORT_SYMBOL(writeback_inodes_sb); +/** + * writeback_inodes_sb_if_idle - start writeback if none underway + * @sb: the superblock + * + * Invoke writeback_inodes_sb if no writeback is currently underway. + * Returns 1 if writeback was started, 0 if not. + */ +int writeback_inodes_sb_if_idle(struct super_block *sb) +{ + if (!writeback_in_progress(sb->s_bdi)) { + writeback_inodes_sb(sb); + return 1; + } else + return 0; +} +EXPORT_SYMBOL(writeback_inodes_sb_if_idle); + /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock diff --git a/include/linux/writeback.h b/include/linux/writeback.h index c18c008f4bbf..76e8903cd204 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -70,6 +70,7 @@ struct writeback_control { struct bdi_writeback; int inode_wait(void *); void writeback_inodes_sb(struct super_block *); +int writeback_inodes_sb_if_idle(struct super_block *); void sync_inodes_sb(struct super_block *); void writeback_inodes_wbc(struct writeback_control *wbc); long wb_do_writeback(struct bdi_writeback *wb, int force_wait); -- cgit v1.2.3 From 28f6aeea3f12d37bd258b2c0d5ba891bff4ec479 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Fri, 25 Dec 2009 17:30:22 -0800 Subject: net: restore ip source validation when using policy routing and the skb mark: there are cases where a back path validation requires us to use a different routing table for src ip validation than the one used for mapping ingress dst ip. One such a case is transparent proxying where we pretend to be the destination system and therefore the local table is used for incoming packets but possibly a main table would be used on outbound. Make the default behavior to allow the above and if users need to turn on the symmetry via sysctl src_valid_mark Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 + include/linux/sysctl.h | 1 + net/ipv4/devinet.c | 1 + net/ipv4/fib_frontend.c | 2 ++ 4 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 699e85c01a4d..b2304929434e 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -81,6 +81,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) +#define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 877ba039e6a4..bd27fbc9db62 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -482,6 +482,7 @@ enum NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, NET_IPV4_CONF_ACCEPT_LOCAL=23, + NET_IPV4_CONF_SRC_VMARK=24, __NET_IPV4_CONF_MAX }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5cdbc102a418..040c4f05b653 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1397,6 +1397,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), + DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 3323168ee52d..82dbf711d6d0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -252,6 +252,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, no_addr = in_dev->ifa_list == NULL; rpf = IN_DEV_RPFILTER(in_dev); accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); + if (mark && !IN_DEV_SRC_VMARK(in_dev)) + fl.mark = 0; } rcu_read_unlock(); -- cgit v1.2.3 From 81744ee44ab2845c16ffd7d6f762f7b4a49a4750 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 29 Dec 2009 08:35:35 +0100 Subject: block: Fix incorrect alignment offset reporting and update documentation queue_sector_alignment_offset returned the wrong value which caused partitions to report an incorrect alignment_offset. Since offset alignment calculation is needed several places it has been split into a separate helper function. The topology stacking function has been updated accordingly. Furthermore, comments have been added to clarify how the stacking function works. Signed-off-by: Martin K. Petersen Tested-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-settings.c | 44 +++++++++++++++++++++++++++++++++----------- include/linux/blkdev.h | 11 +++++++++-- 2 files changed, 42 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/blk-settings.c b/block/blk-settings.c index e14fcbcedbfa..d52d4adc440b 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -505,20 +505,30 @@ static unsigned int lcm(unsigned int a, unsigned int b) /** * blk_stack_limits - adjust queue_limits for stacked devices - * @t: the stacking driver limits (top) - * @b: the underlying queue limits (bottom) + * @t: the stacking driver limits (top device) + * @b: the underlying queue limits (bottom, component device) * @offset: offset to beginning of data within component device * * Description: - * Merges two queue_limit structs. Returns 0 if alignment didn't - * change. Returns -1 if adding the bottom device caused - * misalignment. + * This function is used by stacking drivers like MD and DM to ensure + * that all component devices have compatible block sizes and + * alignments. The stacking driver must provide a queue_limits + * struct (top) and then iteratively call the stacking function for + * all component (bottom) devices. The stacking function will + * attempt to combine the values and ensure proper alignment. + * + * Returns 0 if the top and bottom queue_limits are compatible. The + * top device's block sizes and alignment offsets may be adjusted to + * ensure alignment with the bottom device. If no compatible sizes + * and alignments exist, -1 is returned and the resulting top + * queue_limits will have the misaligned flag set to indicate that + * the alignment_offset is undefined. */ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset) { sector_t alignment; - unsigned int top, bottom, granularity; + unsigned int top, bottom; t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); @@ -536,15 +546,18 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); - granularity = max(b->physical_block_size, b->io_min); - alignment = b->alignment_offset - (offset & (granularity - 1)); + alignment = queue_limit_alignment_offset(b, offset); + /* Bottom device has different alignment. Check that it is + * compatible with the current top alignment. + */ if (t->alignment_offset != alignment) { top = max(t->physical_block_size, t->io_min) + t->alignment_offset; - bottom = granularity + alignment; + bottom = max(b->physical_block_size, b->io_min) + alignment; + /* Verify that top and bottom intervals line up */ if (max(top, bottom) & (min(top, bottom) - 1)) t->misaligned = 1; } @@ -561,32 +574,39 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->no_cluster |= b->no_cluster; t->discard_zeroes_data &= b->discard_zeroes_data; + /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; t->misaligned = 1; } + /* Minimum I/O a multiple of the physical block size? */ if (t->io_min & (t->physical_block_size - 1)) { t->io_min = t->physical_block_size; t->misaligned = 1; } + /* Optimal I/O a multiple of the physical block size? */ if (t->io_opt & (t->physical_block_size - 1)) { t->io_opt = 0; t->misaligned = 1; } + /* Find lowest common alignment_offset */ t->alignment_offset = lcm(t->alignment_offset, alignment) & (max(t->physical_block_size, t->io_min) - 1); + /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) t->misaligned = 1; /* Discard alignment and granularity */ if (b->discard_granularity) { + unsigned int granularity = b->discard_granularity; + offset &= granularity - 1; - alignment = b->discard_alignment - - (offset & (b->discard_granularity - 1)); + alignment = (granularity + b->discard_alignment - offset) + & (granularity - 1); if (t->discard_granularity != 0 && t->discard_alignment != alignment) { @@ -598,6 +618,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->discard_misaligned = 1; } + t->max_discard_sectors = min_not_zero(t->max_discard_sectors, + b->max_discard_sectors); t->discard_granularity = max(t->discard_granularity, b->discard_granularity); t->discard_alignment = lcm(t->discard_alignment, alignment) & diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 784a919aa0d0..59b832be3044 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1116,11 +1116,18 @@ static inline int queue_alignment_offset(struct request_queue *q) return q->limits.alignment_offset; } +static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t offset) +{ + unsigned int granularity = max(lim->physical_block_size, lim->io_min); + + offset &= granularity - 1; + return (granularity + lim->alignment_offset - offset) & (granularity - 1); +} + static inline int queue_sector_alignment_offset(struct request_queue *q, sector_t sector) { - return ((sector << 9) - q->limits.alignment_offset) - & (q->limits.io_min - 1); + return queue_limit_alignment_offset(&q->limits, sector << 9); } static inline int bdev_alignment_offset(struct block_device *bdev) -- cgit v1.2.3 From db5d247ae811f49185a71e703b65acad845e4b18 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Thu, 24 Dec 2009 12:05:58 +0100 Subject: firewire: fix use of multiple AV/C devices, allow multiple FCP listeners Control of more than one AV/C device at once --- e.g. camcorders, tape decks, audio devices, TV tuners --- failed or worked only unreliably, depending on driver implementation. This affected kernelspace and userspace drivers alike and was caused by firewire-core's inability to accept multiple registrations of FCP listeners. The fix allows multiple address handlers to be registered for the FCP command and response registers. When a request for these registers is received, all handlers are invoked, and the Firewire response is generated by the core and not by any handler. The cdev API does not change, i.e., userspace is still expected to send a response for FCP requests; this response is silently ignored. Signed-off-by: Clemens Ladisch Signed-off-by: Stefan Richter (changelog, rebased, whitespace) --- drivers/firewire/core-cdev.c | 26 ++++--- drivers/firewire/core-transaction.c | 118 ++++++++++++++++++++++++++------ drivers/media/dvb/firewire/firedtv-fw.c | 12 +--- include/linux/firewire-cdev.h | 3 + include/linux/firewire.h | 4 +- 5 files changed, 119 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 231e6ee5ba43..2cb22d160f6e 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -601,8 +601,9 @@ static void release_request(struct client *client, struct inbound_transaction_resource *r = container_of(resource, struct inbound_transaction_resource, resource); - fw_send_response(client->device->card, r->request, - RCODE_CONFLICT_ERROR); + if (r->request) + fw_send_response(client->device->card, r->request, + RCODE_CONFLICT_ERROR); kfree(r); } @@ -645,7 +646,8 @@ static void handle_request(struct fw_card *card, struct fw_request *request, failed: kfree(r); kfree(e); - fw_send_response(card, request, RCODE_CONFLICT_ERROR); + if (request) + fw_send_response(card, request, RCODE_CONFLICT_ERROR); } static void release_address_handler(struct client *client, @@ -715,15 +717,17 @@ static int ioctl_send_response(struct client *client, void *buffer) r = container_of(resource, struct inbound_transaction_resource, resource); - if (request->length < r->length) - r->length = request->length; - - if (copy_from_user(r->data, u64_to_uptr(request->data), r->length)) { - ret = -EFAULT; - goto out; + if (r->request) { + if (request->length < r->length) + r->length = request->length; + if (copy_from_user(r->data, u64_to_uptr(request->data), + r->length)) { + ret = -EFAULT; + goto out; + } + fw_send_response(client->device->card, r->request, + request->rcode); } - - fw_send_response(client->device->card, r->request, request->rcode); out: kfree(r); diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 842739df23e2..495849eb13cc 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -432,14 +432,20 @@ static struct fw_address_handler *lookup_overlapping_address_handler( return NULL; } +static bool is_enclosing_handler(struct fw_address_handler *handler, + unsigned long long offset, size_t length) +{ + return handler->offset <= offset && + offset + length <= handler->offset + handler->length; +} + static struct fw_address_handler *lookup_enclosing_address_handler( struct list_head *list, unsigned long long offset, size_t length) { struct fw_address_handler *handler; list_for_each_entry(handler, list, link) { - if (handler->offset <= offset && - offset + length <= handler->offset + handler->length) + if (is_enclosing_handler(handler, offset, length)) return handler; } @@ -465,6 +471,12 @@ const struct fw_address_region fw_unit_space_region = { .start = 0xfffff0000900ULL, .end = 0x1000000000000ULL, }; #endif /* 0 */ +static bool is_in_fcp_region(u64 offset, size_t length) +{ + return offset >= (CSR_REGISTER_BASE | CSR_FCP_COMMAND) && + offset + length <= (CSR_REGISTER_BASE | CSR_FCP_END); +} + /** * fw_core_add_address_handler - register for incoming requests * @handler: callback @@ -477,8 +489,11 @@ const struct fw_address_region fw_unit_space_region = * give the details of the particular request. * * Return value: 0 on success, non-zero otherwise. + * * The start offset of the handler's address region is determined by * fw_core_add_address_handler() and is returned in handler->offset. + * + * Address allocations are exclusive, except for the FCP registers. */ int fw_core_add_address_handler(struct fw_address_handler *handler, const struct fw_address_region *region) @@ -498,10 +513,12 @@ int fw_core_add_address_handler(struct fw_address_handler *handler, handler->offset = region->start; while (handler->offset + handler->length <= region->end) { - other = - lookup_overlapping_address_handler(&address_handler_list, - handler->offset, - handler->length); + if (is_in_fcp_region(handler->offset, handler->length)) + other = NULL; + else + other = lookup_overlapping_address_handler + (&address_handler_list, + handler->offset, handler->length); if (other != NULL) { handler->offset += other->length; } else { @@ -668,6 +685,9 @@ static struct fw_request *allocate_request(struct fw_packet *p) void fw_send_response(struct fw_card *card, struct fw_request *request, int rcode) { + if (WARN_ONCE(!request, "invalid for FCP address handlers")) + return; + /* unified transaction or broadcast transaction: don't respond */ if (request->ack != ACK_PENDING || HEADER_DESTINATION_IS_BROADCAST(request->request_header[0])) { @@ -686,26 +706,15 @@ void fw_send_response(struct fw_card *card, } EXPORT_SYMBOL(fw_send_response); -void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) +static void handle_exclusive_region_request(struct fw_card *card, + struct fw_packet *p, + struct fw_request *request, + unsigned long long offset) { struct fw_address_handler *handler; - struct fw_request *request; - unsigned long long offset; unsigned long flags; int tcode, destination, source; - if (p->ack != ACK_PENDING && p->ack != ACK_COMPLETE) - return; - - request = allocate_request(p); - if (request == NULL) { - /* FIXME: send statically allocated busy packet. */ - return; - } - - offset = - ((unsigned long long) - HEADER_GET_OFFSET_HIGH(p->header[1]) << 32) | p->header[2]; tcode = HEADER_GET_TCODE(p->header[0]); destination = HEADER_GET_DESTINATION(p->header[0]); source = HEADER_GET_SOURCE(p->header[1]); @@ -732,6 +741,73 @@ void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) request->data, request->length, handler->callback_data); } + +static void handle_fcp_region_request(struct fw_card *card, + struct fw_packet *p, + struct fw_request *request, + unsigned long long offset) +{ + struct fw_address_handler *handler; + unsigned long flags; + int tcode, destination, source; + + if ((offset != (CSR_REGISTER_BASE | CSR_FCP_COMMAND) && + offset != (CSR_REGISTER_BASE | CSR_FCP_RESPONSE)) || + request->length > 0x200) { + fw_send_response(card, request, RCODE_ADDRESS_ERROR); + + return; + } + + tcode = HEADER_GET_TCODE(p->header[0]); + destination = HEADER_GET_DESTINATION(p->header[0]); + source = HEADER_GET_SOURCE(p->header[1]); + + if (tcode != TCODE_WRITE_QUADLET_REQUEST && + tcode != TCODE_WRITE_BLOCK_REQUEST) { + fw_send_response(card, request, RCODE_TYPE_ERROR); + + return; + } + + spin_lock_irqsave(&address_handler_lock, flags); + list_for_each_entry(handler, &address_handler_list, link) { + if (is_enclosing_handler(handler, offset, request->length)) + handler->address_callback(card, NULL, tcode, + destination, source, + p->generation, p->speed, + offset, request->data, + request->length, + handler->callback_data); + } + spin_unlock_irqrestore(&address_handler_lock, flags); + + fw_send_response(card, request, RCODE_COMPLETE); +} + +void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) +{ + struct fw_request *request; + unsigned long long offset; + + if (p->ack != ACK_PENDING && p->ack != ACK_COMPLETE) + return; + + request = allocate_request(p); + if (request == NULL) { + /* FIXME: send statically allocated busy packet. */ + return; + } + + offset = ((u64)HEADER_GET_OFFSET_HIGH(p->header[1]) << 32) | + p->header[2]; + + if (!is_in_fcp_region(offset, request->length)) + handle_exclusive_region_request(card, p, request, offset); + else + handle_fcp_region_request(card, p, request, offset); + +} EXPORT_SYMBOL(fw_core_handle_request); void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) diff --git a/drivers/media/dvb/firewire/firedtv-fw.c b/drivers/media/dvb/firewire/firedtv-fw.c index fe44789ab037..6223bf01efe9 100644 --- a/drivers/media/dvb/firewire/firedtv-fw.c +++ b/drivers/media/dvb/firewire/firedtv-fw.c @@ -202,14 +202,8 @@ static void handle_fcp(struct fw_card *card, struct fw_request *request, unsigned long flags; int su; - if ((tcode != TCODE_WRITE_QUADLET_REQUEST && - tcode != TCODE_WRITE_BLOCK_REQUEST) || - offset != CSR_REGISTER_BASE + CSR_FCP_RESPONSE || - length == 0 || - (((u8 *)payload)[0] & 0xf0) != 0) { - fw_send_response(card, request, RCODE_TYPE_ERROR); + if (length < 2 || (((u8 *)payload)[0] & 0xf0) != 0) return; - } su = ((u8 *)payload)[1] & 0x7; @@ -230,10 +224,8 @@ static void handle_fcp(struct fw_card *card, struct fw_request *request, } spin_unlock_irqrestore(&node_list_lock, flags); - if (fdtv) { + if (fdtv) avc_recv(fdtv, payload, length); - fw_send_response(card, request, RCODE_COMPLETE); - } } static struct fw_address_handler fcp_handler = { diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index c6b3ca3af6df..1f716d9f714b 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -340,6 +340,9 @@ struct fw_cdev_send_response { * The @closure field is passed back to userspace in the response event. * The @handle field is an out parameter, returning a handle to the allocated * range to be used for later deallocation of the range. + * + * The address range is allocated on all local nodes. The address allocation + * is exclusive except for the FCP command and response registers. */ struct fw_cdev_allocate { __u64 offset; diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 9416a461b696..a0e67150a729 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -248,8 +248,8 @@ typedef void (*fw_transaction_callback_t)(struct fw_card *card, int rcode, void *data, size_t length, void *callback_data); /* - * Important note: The callback must guarantee that either fw_send_response() - * or kfree() is called on the @request. + * Important note: Except for the FCP registers, the callback must guarantee + * that either fw_send_response() or kfree() is called on the @request. */ typedef void (*fw_address_callback_t)(struct fw_card *card, struct fw_request *request, -- cgit v1.2.3 From 9bd3f98821a83041e77ee25158b80b535d02d7b4 Mon Sep 17 00:00:00 2001 From: Gui Jianfeng Date: Wed, 30 Dec 2009 08:41:07 +0100 Subject: block: blk_rq_err_sectors cleanup blk_rq_err_sectors() seems useless, get rid of it. Signed-off-by: Gui Jianfeng Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 59b832be3044..9b98173a8184 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -845,7 +845,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment - * blk_rq_err_sectors() : sectors left till the next error boundary */ static inline sector_t blk_rq_pos(const struct request *rq) { @@ -874,11 +873,6 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } -static inline unsigned int blk_rq_err_sectors(const struct request *rq) -{ - return blk_rq_err_bytes(rq) >> 9; -} - /* * Request issue related functions. */ -- cgit v1.2.3 From e96dc9674cb597de4fee757ed005c8465072d13f Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 15 Dec 2009 15:39:26 +0800 Subject: tracing/syscalls: Fix typo in SYSCALL_DEFINE0 The struct syscall_metadata variable name in SYSCALL_DEFINE0 should be __syscall_meta__##sname instead of __syscall_meta_##sname to match the name that is in SYSCALL_DEFINE1/2/3/4/5/6. This error causes event_enter_##sname->data to point to the wrong location, which causes syscalls which are defined by SYSCALL_DEFINE0() not to be traced. Signed-off-by: Lai Jiangshan LKML-Reference: <4B273D2E.1010807@cn.fujitsu.com> Acked-by: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 65793e90d6f6..207466a49f3d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -195,7 +195,7 @@ struct perf_event_attr; static const struct syscall_metadata __used \ __attribute__((__aligned__(4))) \ __attribute__((section("__syscalls_metadata"))) \ - __syscall_meta_##sname = { \ + __syscall_meta__##sname = { \ .name = "sys_"#sname, \ .nb_args = 0, \ .enter_event = &event_enter__##sname, \ -- cgit v1.2.3 From ed656d8deccc5669afa33387568e7ec6f14e3e94 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Sat, 26 Dec 2009 17:58:11 +0100 Subject: kfifo: Fix typo in comment It's DECLARE_KFIFO, not DECLARED_KFIFO. Signed-off-by: Rolf Eike Beer Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 3d44e9c65a8e..7c6b32a1421c 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -81,7 +81,7 @@ union { \ } /** - * INIT_KFIFO - Initialize a kfifo declared by DECLARED_KFIFO + * INIT_KFIFO - Initialize a kfifo declared by DECLARE_KFIFO * @name: name of the declared kfifo datatype */ #define INIT_KFIFO(name) \ -- cgit v1.2.3 From d7f0eea9e431e1b8b0742a74db1a9490730b2a25 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 30 Dec 2009 15:36:42 +0800 Subject: ACPI: introduce kernel parameter acpi_sleep=sci_force_enable Introduce kernel parameter acpi_sleep=sci_force_enable some laptop requires SCI_EN being set directly on resume, or else they hung somewhere in the resume code path. We already have a blacklist for these laptops but we still need this option, especially when debugging some suspend/resume problems, in case there are systems that need this workaround and are not yet in the blacklist. Signed-off-by: Zhang Rui Acked-by: Rafael J. Wysocki Signed-off-by: Len Brown --- Documentation/kernel-parameters.txt | 5 ++++- arch/x86/kernel/acpi/sleep.c | 2 ++ drivers/acpi/sleep.c | 29 +++++++++++++++++------------ include/linux/acpi.h | 1 + 4 files changed, 24 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5ba4d9dff113..736d45602886 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -240,7 +240,7 @@ and is between 256 and 4096 characters. It is defined in the file acpi_sleep= [HW,ACPI] Sleep options Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, - old_ordering, s4_nonvs } + old_ordering, s4_nonvs, sci_force_enable } See Documentation/power/video.txt for information on s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep @@ -253,6 +253,9 @@ and is between 256 and 4096 characters. It is defined in the file of _PTS is used by default). s4_nonvs prevents the kernel from saving/restoring the ACPI NVS memory during hibernation. + sci_force_enable causes the kernel to set SCI_EN directly + on resume from S1/S3 (which is against the ACPI spec, + but some broken systems don't work without it). acpi_use_timer_override [HW,ACPI] Use timer override. For some broken Nvidia NF5 boards diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 82e508677b91..f9961034e557 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -162,6 +162,8 @@ static int __init acpi_sleep_setup(char *str) #endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); + if (strncmp(str, "sci_force_enable", 16) == 0) + acpi_set_sci_en_on_resume(); str = strchr(str, ','); if (str != NULL) str += strspn(str, ", \t"); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 5f2c379ab7bf..79d33d908b5a 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -80,6 +80,23 @@ static int acpi_sleep_prepare(u32 acpi_state) #ifdef CONFIG_ACPI_SLEEP static u32 acpi_target_sleep_state = ACPI_STATE_S0; +/* + * According to the ACPI specification the BIOS should make sure that ACPI is + * enabled and SCI_EN bit is set on wake-up from S1 - S3 sleep states. Still, + * some BIOSes don't do that and therefore we use acpi_enable() to enable ACPI + * on such systems during resume. Unfortunately that doesn't help in + * particularly pathological cases in which SCI_EN has to be set directly on + * resume, although the specification states very clearly that this flag is + * owned by the hardware. The set_sci_en_on_resume variable will be set in such + * cases. + */ +static bool set_sci_en_on_resume; + +void __init acpi_set_sci_en_on_resume(void) +{ + set_sci_en_on_resume = true; +} + /* * ACPI 1.0 wants us to execute _PTS before suspending devices, so we allow the * user to request that behavior by using the 'acpi_old_suspend_ordering' @@ -170,18 +187,6 @@ static void acpi_pm_end(void) #endif /* CONFIG_ACPI_SLEEP */ #ifdef CONFIG_SUSPEND -/* - * According to the ACPI specification the BIOS should make sure that ACPI is - * enabled and SCI_EN bit is set on wake-up from S1 - S3 sleep states. Still, - * some BIOSes don't do that and therefore we use acpi_enable() to enable ACPI - * on such systems during resume. Unfortunately that doesn't help in - * particularly pathological cases in which SCI_EN has to be set directly on - * resume, although the specification states very clearly that this flag is - * owned by the hardware. The set_sci_en_on_resume variable will be set in such - * cases. - */ -static bool set_sci_en_on_resume; - extern void do_suspend_lowlevel(void); static u32 acpi_suspend_states[] = { diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ce945d4845fc..36924255c0d5 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -251,6 +251,7 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n, void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); void __init acpi_s4_no_nvs(void); +void __init acpi_set_sci_en_on_resume(void); #endif /* CONFIG_PM_SLEEP */ struct acpi_osc_context { -- cgit v1.2.3 From 0719d3434747889b314a1e8add776418c4148bcf Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 30 Dec 2009 00:39:22 +0100 Subject: reiserfs: Fix reiserfs lock <-> i_xattr_sem dependency inversion i_xattr_sem depends on the reiserfs lock. But after we grab i_xattr_sem, we may relax/relock the reiserfs lock while waiting on a freezed filesystem, creating a dependency inversion between the two locks. In order to avoid the i_xattr_sem -> reiserfs lock dependency, let's create a reiserfs_down_read_safe() that acts like reiserfs_mutex_lock_safe(): relax the reiserfs lock while grabbing another lock to avoid undesired dependencies induced by the heivyweight reiserfs lock. This fixes the following warning: [ 990.005931] ======================================================= [ 990.012373] [ INFO: possible circular locking dependency detected ] [ 990.013233] 2.6.33-rc1 #1 [ 990.013233] ------------------------------------------------------- [ 990.013233] dbench/1891 is trying to acquire lock: [ 990.013233] (&REISERFS_SB(s)->lock){+.+.+.}, at: [] reiserfs_write_lock+0x35/0x50 [ 990.013233] [ 990.013233] but task is already holding lock: [ 990.013233] (&REISERFS_I(inode)->i_xattr_sem){+.+.+.}, at: [] reiserfs_xattr_set_handle+0x8a/0x470 [ 990.013233] [ 990.013233] which lock already depends on the new lock. [ 990.013233] [ 990.013233] [ 990.013233] the existing dependency chain (in reverse order) is: [ 990.013233] [ 990.013233] -> #1 (&REISERFS_I(inode)->i_xattr_sem){+.+.+.}: [ 990.013233] [] __lock_acquire+0xf9c/0x1560 [ 990.013233] [] lock_acquire+0x8f/0xb0 [ 990.013233] [] down_write+0x44/0x80 [ 990.013233] [] reiserfs_xattr_set_handle+0x8a/0x470 [ 990.013233] [] reiserfs_xattr_set+0xb0/0x150 [ 990.013233] [] user_set+0x8a/0x90 [ 990.013233] [] reiserfs_setxattr+0xaa/0xb0 [ 990.013233] [] __vfs_setxattr_noperm+0x36/0xa0 [ 990.013233] [] vfs_setxattr+0xbc/0xc0 [ 990.013233] [] setxattr+0xc0/0x150 [ 990.013233] [] sys_fsetxattr+0x8d/0xa0 [ 990.013233] [] system_call_fastpath+0x16/0x1b [ 990.013233] [ 990.013233] -> #0 (&REISERFS_SB(s)->lock){+.+.+.}: [ 990.013233] [] __lock_acquire+0x12d0/0x1560 [ 990.013233] [] lock_acquire+0x8f/0xb0 [ 990.013233] [] __mutex_lock_common+0x47/0x3b0 [ 990.013233] [] mutex_lock_nested+0x3e/0x50 [ 990.013233] [] reiserfs_write_lock+0x35/0x50 [ 990.013233] [] reiserfs_prepare_write+0x45/0x180 [ 990.013233] [] reiserfs_xattr_set_handle+0x2a6/0x470 [ 990.013233] [] reiserfs_xattr_set+0xb0/0x150 [ 990.013233] [] user_set+0x8a/0x90 [ 990.013233] [] reiserfs_setxattr+0xaa/0xb0 [ 990.013233] [] __vfs_setxattr_noperm+0x36/0xa0 [ 990.013233] [] vfs_setxattr+0xbc/0xc0 [ 990.013233] [] setxattr+0xc0/0x150 [ 990.013233] [] sys_fsetxattr+0x8d/0xa0 [ 990.013233] [] system_call_fastpath+0x16/0x1b [ 990.013233] [ 990.013233] other info that might help us debug this: [ 990.013233] [ 990.013233] 2 locks held by dbench/1891: [ 990.013233] #0: (&sb->s_type->i_mutex_key#12){+.+.+.}, at: [] vfs_setxattr+0x78/0xc0 [ 990.013233] #1: (&REISERFS_I(inode)->i_xattr_sem){+.+.+.}, at: [] reiserfs_xattr_set_handle+0x8a/0x470 [ 990.013233] [ 990.013233] stack backtrace: [ 990.013233] Pid: 1891, comm: dbench Not tainted 2.6.33-rc1 #1 [ 990.013233] Call Trace: [ 990.013233] [] print_circular_bug+0xe9/0xf0 [ 990.013233] [] __lock_acquire+0x12d0/0x1560 [ 990.013233] [] ? reiserfs_xattr_set_handle+0x8a/0x470 [ 990.013233] [] lock_acquire+0x8f/0xb0 [ 990.013233] [] ? reiserfs_write_lock+0x35/0x50 [ 990.013233] [] ? reiserfs_xattr_set_handle+0x8a/0x470 [ 990.013233] [] __mutex_lock_common+0x47/0x3b0 [ 990.013233] [] ? reiserfs_write_lock+0x35/0x50 [ 990.013233] [] ? reiserfs_write_lock+0x35/0x50 [ 990.013233] [] ? mark_held_locks+0x72/0xa0 [ 990.013233] [] ? __mutex_unlock_slowpath+0xbd/0x140 [ 990.013233] [] ? trace_hardirqs_on_caller+0x14d/0x1a0 [ 990.013233] [] mutex_lock_nested+0x3e/0x50 [ 990.013233] [] reiserfs_write_lock+0x35/0x50 [ 990.013233] [] reiserfs_prepare_write+0x45/0x180 [ 990.013233] [] reiserfs_xattr_set_handle+0x2a6/0x470 [ 990.013233] [] reiserfs_xattr_set+0xb0/0x150 [ 990.013233] [] ? __mutex_lock_common+0x284/0x3b0 [ 990.013233] [] user_set+0x8a/0x90 [ 990.013233] [] reiserfs_setxattr+0xaa/0xb0 [ 990.013233] [] __vfs_setxattr_noperm+0x36/0xa0 [ 990.013233] [] vfs_setxattr+0xbc/0xc0 [ 990.013233] [] setxattr+0xc0/0x150 [ 990.013233] [] ? sched_clock_cpu+0xb8/0x100 [ 990.013233] [] ? trace_hardirqs_off+0xd/0x10 [ 990.013233] [] ? cpu_clock+0x43/0x50 [ 990.013233] [] ? fget+0xb0/0x110 [ 990.013233] [] ? fget+0x0/0x110 [ 990.013233] [] ? sysret_check+0x27/0x62 [ 990.013233] [] sys_fsetxattr+0x8d/0xa0 [ 990.013233] [] system_call_fastpath+0x16/0x1b Reported-and-tested-by: Christian Kujau Signed-off-by: Frederic Weisbecker Cc: Alexander Beregalov Cc: Chris Mason Cc: Ingo Molnar --- fs/reiserfs/xattr.c | 2 +- include/linux/reiserfs_fs.h | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 8891cd88a3f4..a0e2e7acdc75 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -484,7 +484,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, if (IS_ERR(dentry)) return PTR_ERR(dentry); - down_write(&REISERFS_I(inode)->i_xattr_sem); + reiserfs_down_read_safe(&REISERFS_I(inode)->i_xattr_sem, inode->i_sb); xahash = xattr_hash(buffer, buffer_size); while (buffer_pos < buffer_size || buffer_pos == 0) { diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 4351b49e2b1e..35d3f459b0ac 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -106,6 +106,14 @@ reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass, reiserfs_write_lock(s); } +static inline void +reiserfs_down_read_safe(struct rw_semaphore *sem, struct super_block *s) +{ + reiserfs_write_unlock(s); + down_read(sem); + reiserfs_write_lock(s); +} + /* * When we schedule, we usually want to also release the write lock, * according to the previous bkl based locking scheme of reiserfs. -- cgit v1.2.3 From c4a62ca362258d98f42efb282cfbf9b61caffdbe Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 30 Dec 2009 03:20:19 +0100 Subject: reiserfs: Warn on lock relax if taken recursively When we relax the reiserfs lock to avoid creating unwanted dependencies against others locks while grabbing these, we want to ensure it has not been taken recursively, otherwise the lock won't be really relaxed. Only its depth will be decreased. The unwanted dependency would then actually happen. To prevent from that, add a reiserfs_lock_check_recursive() call in the places that need it. Signed-off-by: Frederic Weisbecker Cc: Alexander Beregalov Cc: Chris Mason Cc: Ingo Molnar --- fs/reiserfs/lock.c | 9 +++++++++ include/linux/reiserfs_fs.h | 9 +++++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/fs/reiserfs/lock.c b/fs/reiserfs/lock.c index ee2cfc0fd8a7..b87aa2c1afc1 100644 --- a/fs/reiserfs/lock.c +++ b/fs/reiserfs/lock.c @@ -86,3 +86,12 @@ void reiserfs_check_lock_depth(struct super_block *sb, char *caller) reiserfs_panic(sb, "%s called without kernel lock held %d", caller); } + +#ifdef CONFIG_REISERFS_CHECK +void reiserfs_lock_check_recursive(struct super_block *sb) +{ + struct reiserfs_sb_info *sb_i = REISERFS_SB(sb); + + WARN_ONCE((sb_i->lock_depth > 0), "Unwanted recursive reiserfs lock!\n"); +} +#endif diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 35d3f459b0ac..793bf8351ab8 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -62,6 +62,12 @@ void reiserfs_write_unlock(struct super_block *s); int reiserfs_write_lock_once(struct super_block *s); void reiserfs_write_unlock_once(struct super_block *s, int lock_depth); +#ifdef CONFIG_REISERFS_CHECK +void reiserfs_lock_check_recursive(struct super_block *s); +#else +static inline void reiserfs_lock_check_recursive(struct super_block *s) { } +#endif + /* * Several mutexes depend on the write lock. * However sometimes we want to relax the write lock while we hold @@ -92,6 +98,7 @@ void reiserfs_write_unlock_once(struct super_block *s, int lock_depth); static inline void reiserfs_mutex_lock_safe(struct mutex *m, struct super_block *s) { + reiserfs_lock_check_recursive(s); reiserfs_write_unlock(s); mutex_lock(m); reiserfs_write_lock(s); @@ -101,6 +108,7 @@ static inline void reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass, struct super_block *s) { + reiserfs_lock_check_recursive(s); reiserfs_write_unlock(s); mutex_lock_nested(m, subclass); reiserfs_write_lock(s); @@ -109,6 +117,7 @@ reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass, static inline void reiserfs_down_read_safe(struct rw_semaphore *sem, struct super_block *s) { + reiserfs_lock_check_recursive(s); reiserfs_write_unlock(s); down_read(sem); reiserfs_write_lock(s); -- cgit v1.2.3 From 96d07d211739fd2450ac54e81d00fa40fcd4b1bd Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 20 Nov 2009 14:16:33 +0100 Subject: resource: move kernel function inside __KERNEL__ It is an internal function. Move it inside __KERNEL__ ifdef, along with task_struct declaration. Then we get: --- /usr/include/linux/resource.h 2009-09-14 15:09:29.000000000 +0200 +++ usr/include/linux/resource.h 2010-01-04 11:30:54.000000000 +0100 @@ -3,8 +3,6 @@ #include -struct task_struct; - /* * Resource control/accounting header file for linux */ @@ -70,6 +68,5 @@ */ #include -int getrusage(struct task_struct *p, int who, struct rusage *ru); #endif *********** include/linux/Kbuild is untouched, since unifdef is run even on headers-y nowadays. Signed-off-by: Jiri Slaby --- include/linux/resource.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/resource.h b/include/linux/resource.h index 40fc7e626082..f1e914eefeab 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -3,8 +3,6 @@ #include -struct task_struct; - /* * Resource control/accounting header file for linux */ @@ -70,6 +68,12 @@ struct rlimit { */ #include +#ifdef __KERNEL__ + +struct task_struct; + int getrusage(struct task_struct *p, int who, struct rusage __user *ru); +#endif /* __KERNEL__ */ + #endif -- cgit v1.2.3 From 3e10e716abf3c71bdb5d86b8f507f9e72236c9cd Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 19 Nov 2009 17:16:37 +0100 Subject: resource: add helpers for fetching rlimits We want to be sure that compiler fetches the limit variable only once, so add helpers for fetching current and maximal resource limits which do that. Add them to sched.h (instead of resource.h) due to circular dependency sched.h->resource.h->task_struct Alternative would be to create a separate res_access.h or similar. Signed-off-by: Jiri Slaby Cc: James Morris Cc: Heiko Carstens Cc: Andrew Morton Cc: Ingo Molnar --- include/linux/sched.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f2f842db03ce..8d4991be9d53 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2601,6 +2601,28 @@ static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ +static inline unsigned long task_rlimit(const struct task_struct *tsk, + unsigned int limit) +{ + return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur); +} + +static inline unsigned long task_rlimit_max(const struct task_struct *tsk, + unsigned int limit) +{ + return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max); +} + +static inline unsigned long rlimit(unsigned int limit) +{ + return task_rlimit(current, limit); +} + +static inline unsigned long rlimit_max(unsigned int limit) +{ + return task_rlimit_max(current, limit); +} + #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From cfe79c00a2f4f687eed8b7534d1d3d3d35540c29 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Wed, 6 Jan 2010 17:23:23 +0000 Subject: NOMMU: Avoiding duplicate icache flushes of shared maps When working with FDPIC, there are many shared mappings of read-only code regions between applications (the C library, applet packages like busybox, etc.), but the current do_mmap_pgoff() function will issue an icache flush whenever a VMA is added to an MM instead of only doing it when the map is initially created. The flush can instead be done when a region is first mmapped PROT_EXEC. Note that we may not rely on the first mapping of a region being executable - it's possible for it to be PROT_READ only, so we have to remember whether we've flushed the region or not, and then flush the entire region when a bit of it is made executable. However, this also affects the brk area. That will no longer be executable. We can mprotect() it to PROT_EXEC on MPU-mode kernels, but for NOMMU mode kernels, when it increases the brk allocation, making sys_brk() flush the extra from the icache should suffice. The brk area probably isn't used by NOMMU programs since the brk area can only use up the leavings from the stack allocation, where the stack allocation is larger than requested. Signed-off-by: David Howells Signed-off-by: Mike Frysinger Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 ++ mm/nommu.c | 11 ++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 84a524afb3dc..84d020bed083 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -123,6 +123,8 @@ struct vm_region { struct file *vm_file; /* the backing file or NULL */ atomic_t vm_usage; /* region usage count */ + bool vm_icache_flushed : 1; /* true if the icache has been flushed for + * this region */ }; /* diff --git a/mm/nommu.c b/mm/nommu.c index 6f9248f89bde..a8d17521624a 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -432,6 +432,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* * Ok, looks good - let it rip. */ + flush_icache_range(mm->brk, brk); return mm->brk = brk; } @@ -1353,10 +1354,14 @@ unsigned long do_mmap_pgoff(struct file *file, share: add_vma_to_mm(current->mm, vma); - up_write(&nommu_region_sem); + /* we flush the region from the icache only when the first executable + * mapping of it is made */ + if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) { + flush_icache_range(region->vm_start, region->vm_end); + region->vm_icache_flushed = true; + } - if (prot & PROT_EXEC) - flush_icache_range(result, result + len); + up_write(&nommu_region_sem); kleave(" = %lx", result); return result; -- cgit v1.2.3