From 627ad9fd0733f0a31a266ff98a4a933eee710f0b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 20 Jun 2009 23:21:41 -0400 Subject: [PATCH 0001/1346] ext4: Fix type warning on 64-bit platforms in tracing events header Signed-off-by: "Theodore Ts'o" --- include/trace/events/ext4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index acf4cc9cd36..b456fb0a3c5 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -34,7 +34,8 @@ TRACE_EVENT(ext4_free_inode, TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu", jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode, - __entry->uid, __entry->gid, __entry->blocks) + __entry->uid, __entry->gid, + (unsigned long long) __entry->blocks) ); TRACE_EVENT(ext4_request_inode, From b574480507460b8e31b8d38dd4642219fc3b9a10 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 20 Jun 2009 23:34:44 -0400 Subject: [PATCH 0002/1346] jbd2: Remove GFP_ATOMIC kmalloc from inside spinlock critical region Fix jbd2_dev_to_name(), a function used when pretty-printting jbd2 and ext4 tracepoints. Signed-off-by: "Theodore Ts'o" --- fs/jbd2/journal.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 18bfd5dab64..7b545c3b394 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2410,6 +2410,7 @@ const char *jbd2_dev_to_name(dev_t device) int i = hash_32(device, CACHE_SIZE_BITS); char *ret; struct block_device *bd; + static struct devname_cache *new_dev; rcu_read_lock(); if (devcache[i] && devcache[i]->device == device) { @@ -2419,20 +2420,20 @@ const char *jbd2_dev_to_name(dev_t device) } rcu_read_unlock(); + new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); + if (!new_dev) + return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ spin_lock(&devname_cache_lock); if (devcache[i]) { if (devcache[i]->device == device) { + kfree(new_dev); ret = devcache[i]->devname; spin_unlock(&devname_cache_lock); return ret; } call_rcu(&devcache[i]->rcu, free_devcache); } - devcache[i] = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); - if (!devcache[i]) { - spin_unlock(&devname_cache_lock); - return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ - } + devcache[i] = new_dev; devcache[i]->device = device; bd = bdget(device); if (bd) { From f4a01017d678fe4baecf480e79d7c4f4b7ebc772 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 5 Jul 2009 22:08:16 -0400 Subject: [PATCH 0003/1346] ext4: Fix potential reclaim deadlock when truncating partial block The ext4_block_truncate_page() function previously called grab_cache_page(), which called find_or_create_page() with the __GFP_FS flag potentially set. This could cause a deadlock if the system is low on memory and it attempts a memory reclaim, which could potentially call back into ext4. So we need to call find_or_create_page() directly, and remove the __GFP_FP flag to avoid this potential deadlock. Thanks to Roland Dreier for reporting a lockdep warning which showed this problem. [20786.363249] ================================= [20786.363257] [ INFO: inconsistent lock state ] [20786.363265] 2.6.31-2-generic #14~rbd4gitd960eea9 [20786.363270] --------------------------------- [20786.363276] inconsistent {IN-RECLAIM_FS-W} -> {RECLAIM_FS-ON-W} usage. [20786.363285] http/8397 [HC0[0]:SC0[0]:HE1:SE1] takes: [20786.363291] (jbd2_handle){+.+.?.}, at: [] jbd2_journal_start+0xdb/0x150 [20786.363314] {IN-RECLAIM_FS-W} state was registered at: [20786.363320] [] mark_irqflags+0xc6/0x1a0 [20786.363334] [] __lock_acquire+0x287/0x430 [20786.363345] [] lock_acquire+0xa5/0x150 [20786.363355] [] jbd2_journal_start+0xfa/0x150 [20786.363365] [] ext4_journal_start_sb+0x58/0x90 [20786.363377] [] ext4_delete_inode+0xc5/0x2c0 [20786.363389] [] generic_delete_inode+0xd3/0x1a0 [20786.363401] [] generic_drop_inode+0x25/0x30 [20786.363411] [] iput+0x62/0x70 [20786.363420] [] dentry_iput+0x98/0x110 [20786.363429] [] d_kill+0x50/0x80 [20786.363438] [] dput+0x95/0x180 [20786.363447] [] ecryptfs_d_release+0x2b/0x70 [20786.363459] [] d_free+0x28/0x60 [20786.363468] [] d_kill+0x68/0x80 [20786.363477] [] prune_one_dentry+0xa3/0xc0 [20786.363487] [] __shrink_dcache_sb+0x271/0x290 [20786.363497] [] prune_dcache+0x109/0x1b0 [20786.363506] [] shrink_dcache_memory+0x3f/0x50 [20786.363516] [] shrink_slab+0x12d/0x190 [20786.363527] [] balance_pgdat+0x4d7/0x640 [20786.363537] [] kswapd+0x117/0x170 [20786.363546] [] kthread+0x9e/0xb0 [20786.363558] [] child_rip+0xa/0x20 [20786.363569] [] 0xffffffffffffffff [20786.363598] irq event stamp: 15997 [20786.363603] hardirqs last enabled at (15997): [] kmem_cache_alloc+0xfd/0x1a0 [20786.363617] hardirqs last disabled at (15996): [] kmem_cache_alloc+0x61/0x1a0 [20786.363628] softirqs last enabled at (15966): [] __do_softirq+0x14a/0x220 [20786.363641] softirqs last disabled at (15861): [] call_softirq+0x1c/0x30 [20786.363651] [20786.363653] other info that might help us debug this: [20786.363660] 3 locks held by http/8397: [20786.363665] #0: (&sb->s_type->i_mutex_key#8){+.+.+.}, at: [] do_truncate+0x64/0x90 [20786.363685] #1: (&sb->s_type->i_alloc_sem_key#5){+++++.}, at: [] notify_change+0x250/0x350 [20786.363707] #2: (jbd2_handle){+.+.?.}, at: [] jbd2_journal_start+0xdb/0x150 [20786.363724] [20786.363726] stack backtrace: [20786.363734] Pid: 8397, comm: http Tainted: G C 2.6.31-2-generic #14~rbd4gitd960eea9 [20786.363741] Call Trace: [20786.363752] [] print_usage_bug+0x18c/0x1a0 [20786.363763] [] ? check_usage_backwards+0x0/0xb0 [20786.363773] [] mark_lock_irq+0xf2/0x280 [20786.363783] [] mark_lock+0x137/0x1d0 [20786.363793] [] mark_held_locks+0x6c/0xa0 [20786.363803] [] lockdep_trace_alloc+0xaf/0xe0 [20786.363813] [] __alloc_pages_nodemask+0x7c/0x180 [20786.363824] [] ? find_get_page+0x91/0xf0 [20786.363835] [] alloc_pages_current+0x87/0xd0 [20786.363845] [] __page_cache_alloc+0x67/0x70 [20786.363856] [] find_or_create_page+0x4f/0xb0 [20786.363867] [] ext4_block_truncate_page+0x3e/0x460 [20786.363876] [] ? jbd2_journal_start+0xfa/0x150 [20786.363885] [] ? jbd2_journal_start+0xdb/0x150 [20786.363895] [] ? ext4_meta_trans_blocks+0x75/0xf0 [20786.363905] [] ext4_ext_truncate+0x1bb/0x1e0 [20786.363916] [] ? unmap_mapping_range+0x75/0x290 [20786.363926] [] ext4_truncate+0x498/0x630 [20786.363938] [] ? _raw_spin_unlock+0x5e/0xb0 [20786.363947] [] ? unmap_mapping_range+0xb6/0x290 [20786.363957] [] ? trace_hardirqs_on+0xd/0x10 [20786.363966] [] ? jbd2_journal_stop+0x1f8/0x2e0 [20786.363976] [] vmtruncate+0xb0/0x110 [20786.363986] [] inode_setattr+0x35/0x170 [20786.363995] [] ext4_setattr+0x186/0x370 [20786.364005] [] notify_change+0x16b/0x350 [20786.364014] [] do_truncate+0x70/0x90 [20786.364021] [] T.657+0xeb/0x110 [20786.364021] [] sys_ftruncate+0xe/0x10 [20786.364021] [] system_call_fastpath+0x16/0x1b Reported-by: Roland Dreier Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 60a26f3a6f8..9760ba09275 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3583,7 +3583,8 @@ int ext4_block_truncate_page(handle_t *handle, struct page *page; int err = 0; - page = grab_cache_page(mapping, from >> PAGE_CACHE_SHIFT); + page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, + mapping_gfp_mask(mapping) & ~__GFP_FS); if (!page) return -EINVAL; From 089ceecc1ea4a69ed8bcc5c7c7b96ce487e26b33 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Sun, 5 Jul 2009 22:17:31 -0400 Subject: [PATCH 0004/1346] ext4: mark several more functions in mballoc.c as noinline Ted noticed a stack-deep callchain through writepages->ext4_mb_regular_allocator->ext4_mb_init_cache->submit_bh ... With all the static functions in mballoc.c, gcc helpfully inlines for us, and we get something like this: ext4_mb_regular_allocator (232 bytes stack) ext4_mb_init_cache (232 bytes stack) submit_bh (starts 464 deeper) the 2 ext4 functions here get several others inlined; by telling gcc not to inline them, we can save stack space for when we head off into submit_bh land and associated block layer callchains. The following noinlined functions are only called once, so this won't impact any other callchains: ext4_mb_regular_allocator (104) (was 232) ext4_mb_find_by_goal (56) (noinlined) ext4_mb_init_group (24) (noinlined) ext4_mb_init_cache (136) (was 232) ext4_mb_generate_buddy (88) (noinlined) ext4_mb_generate_from_pa (40) (noinlined) submit_bh ext4_mb_simple_scan_group (24) (noinlined) ext4_mb_scan_aligned (56) (noinlined) ext4_mb_complex_scan_group (40) (noinlined) ext4_mb_try_best_found (24) (noinlined) now when we head off into submit_bh() we're only 264 bytes deeper in stack than when we entered ext4_mb_regular_allocator() (vs. 464 bytes before). Every 200 bytes helps. :) Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 519a0a686d9..4a45efabb20 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -657,7 +657,8 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } -static void ext4_mb_generate_buddy(struct super_block *sb, +static noinline_for_stack +void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); @@ -1480,7 +1481,8 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, ext4_mb_check_limits(ac, e4b, 0); } -static int ext4_mb_try_best_found(struct ext4_allocation_context *ac, +static noinline_for_stack +int ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; @@ -1507,7 +1509,8 @@ static int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return 0; } -static int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, +static noinline_for_stack +int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; @@ -1566,7 +1569,8 @@ static int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ -static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, +static noinline_for_stack +void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; @@ -1609,7 +1613,8 @@ static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ -static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, +static noinline_for_stack +void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; @@ -1668,7 +1673,8 @@ static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, * we try to find stripe-aligned chunks for stripe-size requests * XXX should do so at least for multiples of stripe size as well */ -static void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, +static noinline_for_stack +void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; @@ -1831,7 +1837,8 @@ void ext4_mb_put_buddy_cache_lock(struct super_block *sb, } -static int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) +static noinline_for_stack +int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) { int ret; @@ -3457,7 +3464,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ -static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, +static noinline_for_stack +void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); From 726447d803802cd0be8f62d17c4a34421781b938 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 13 Jul 2009 10:24:17 -0400 Subject: [PATCH 0005/1346] ext4: naturally align struct ext4_allocation_request As Ted noted, the ext4_allocation_request isn't well aligned. Looking at it with pahole we're wasting space on 64-bit arches: struct ext4_allocation_request { struct inode * inode; /* 0 8 */ ext4_lblk_t logical; /* 8 4 */ /* XXX 4 bytes hole, try to pack */ ext4_fsblk_t goal; /* 16 8 */ ext4_lblk_t lleft; /* 24 4 */ /* XXX 4 bytes hole, try to pack */ ext4_fsblk_t pleft; /* 32 8 */ ext4_lblk_t lright; /* 40 4 */ /* XXX 4 bytes hole, try to pack */ ext4_fsblk_t pright; /* 48 8 */ unsigned int len; /* 56 4 */ unsigned int flags; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ /* size: 64, cachelines: 1, members: 9 */ /* sum members: 52, holes: 3, sum holes: 12 */ }; Grouping 32-bit members together closes these holes and shrinks the structure by 12 bytes. which is important since ext4 can get on the hairy edge of stack overruns. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0ddf7e55abe..9714db393ef 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -93,20 +93,20 @@ typedef unsigned int ext4_group_t; struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; - /* logical block in target inode */ - ext4_lblk_t logical; - /* phys. target (a hint) */ - ext4_fsblk_t goal; - /* the closest logical allocated block to the left */ - ext4_lblk_t lleft; - /* phys. block for ^^^ */ - ext4_fsblk_t pleft; - /* the closest logical allocated block to the right */ - ext4_lblk_t lright; - /* phys. block for ^^^ */ - ext4_fsblk_t pright; /* how many blocks we want to allocate */ unsigned int len; + /* logical block in target inode */ + ext4_lblk_t logical; + /* the closest logical allocated block to the left */ + ext4_lblk_t lleft; + /* the closest logical allocated block to the right */ + ext4_lblk_t lright; + /* phys. target (a hint) */ + ext4_fsblk_t goal; + /* phys. block for the closest logical allocated block to the left */ + ext4_fsblk_t pleft; + /* phys. block for the closest logical allocated block to the right */ + ext4_fsblk_t pright; /* flags. see above EXT4_MB_HINT_* */ unsigned int flags; }; From 3e03f9ca6a2599db1823bb0ea24e0845219a0e69 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Sun, 5 Jul 2009 22:29:27 -0400 Subject: [PATCH 0006/1346] ext4: Use rcu_barrier() on module unload. The ext4 module uses rcu_call() thus it should use rcu_barrier()on module unload. The kmem cache ext4_pspace_cachep is sometimes free'ed using call_rcu() callbacks. Thus, we must wait for completion of call_rcu() before doing kmem_cache_destroy(). Signed-off-by: Jesper Dangaard Brouer Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4a45efabb20..2fcaf286f1d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2909,7 +2909,11 @@ int __init init_ext4_mballoc(void) void exit_ext4_mballoc(void) { - /* XXX: synchronize_rcu(); */ + /* + * Wait for completion of call_rcu()'s on ext4_pspace_cachep + * before destroying the slab cache. + */ + rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); From f91d1d04171026e56c7e343ee3cdcc801dd85cfb Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jul 2009 16:16:20 -0400 Subject: [PATCH 0007/1346] jbd2: Fix a race between checkpointing code and journal_get_write_access() The following race can happen: CPU1 CPU2 checkpointing code checks the buffer, adds it to an array for writeback do_get_write_access() ... lock_buffer() unlock_buffer() flush_batch() submits the buffer for IO __jbd2_journal_file_buffer() So a buffer under writeout is returned from do_get_write_access(). Since the filesystem code relies on the fact that journaled buffers cannot be written out, it does not take the buffer lock and so it can modify buffer while it is under writeout. That can lead to a filesystem corruption if we crash at the right moment. We fix the problem by clearing the buffer dirty bit under buffer_lock even if the buffer is on BJ_None list. Actually, we clear the dirty bit regardless the list the buffer is in and warn about the fact if the buffer is already journalled. Thanks for spotting the problem goes to dingdinghua . Reported-by: dingdinghua Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/transaction.c | 68 ++++++++++++++++++++++--------------------- 1 file changed, 35 insertions(+), 33 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 494501edba6..6213ac728f3 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -499,34 +499,15 @@ void jbd2_journal_unlock_updates (journal_t *journal) wake_up(&journal->j_wait_transaction_locked); } -/* - * Report any unexpected dirty buffers which turn up. Normally those - * indicate an error, but they can occur if the user is running (say) - * tune2fs to modify the live filesystem, so we need the option of - * continuing as gracefully as possible. # - * - * The caller should already hold the journal lock and - * j_list_lock spinlock: most callers will need those anyway - * in order to probe the buffer's journaling state safely. - */ -static void jbd_unexpected_dirty_buffer(struct journal_head *jh) +static void warn_dirty_buffer(struct buffer_head *bh) { - int jlist; + char b[BDEVNAME_SIZE]; - /* If this buffer is one which might reasonably be dirty - * --- ie. data, or not part of this journal --- then - * we're OK to leave it alone, but otherwise we need to - * move the dirty bit to the journal's own internal - * JBDDirty bit. */ - jlist = jh->b_jlist; - - if (jlist == BJ_Metadata || jlist == BJ_Reserved || - jlist == BJ_Shadow || jlist == BJ_Forget) { - struct buffer_head *bh = jh2bh(jh); - - if (test_clear_buffer_dirty(bh)) - set_buffer_jbddirty(bh); - } + printk(KERN_WARNING + "JBD: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). " + "There's a risk of filesystem corruption in case of system " + "crash.\n", + bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); } /* @@ -593,14 +574,16 @@ repeat: if (jh->b_next_transaction) J_ASSERT_JH(jh, jh->b_next_transaction == transaction); + warn_dirty_buffer(bh); } /* * In any case we need to clean the dirty flag and we must * do it under the buffer lock to be sure we don't race * with running write-out. */ - JBUFFER_TRACE(jh, "Unexpected dirty buffer"); - jbd_unexpected_dirty_buffer(jh); + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + clear_buffer_dirty(bh); + set_buffer_jbddirty(bh); } unlock_buffer(bh); @@ -843,6 +826,15 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) J_ASSERT_JH(jh, buffer_locked(jh2bh(jh))); if (jh->b_transaction == NULL) { + /* + * Previous jbd2_journal_forget() could have left the buffer + * with jbddirty bit set because it was being committed. When + * the commit finished, we've filed the buffer for + * checkpointing and marked it dirty. Now we are reallocating + * the buffer so the transaction freeing it must have + * committed and so it's safe to clear the dirty bit. + */ + clear_buffer_dirty(jh2bh(jh)); jh->b_transaction = transaction; /* first access by this transaction */ @@ -1644,8 +1636,13 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) if (jh->b_cp_transaction) { JBUFFER_TRACE(jh, "on running+cp transaction"); + /* + * We don't want to write the buffer anymore, clear the + * bit so that we don't confuse checks in + * __journal_file_buffer + */ + clear_buffer_dirty(bh); __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); - clear_buffer_jbddirty(bh); may_free = 0; } else { JBUFFER_TRACE(jh, "on running transaction"); @@ -1896,12 +1893,17 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, if (jh->b_transaction && jh->b_jlist == jlist) return; - /* The following list of buffer states needs to be consistent - * with __jbd_unexpected_dirty_buffer()'s handling of dirty - * state. */ - if (jlist == BJ_Metadata || jlist == BJ_Reserved || jlist == BJ_Shadow || jlist == BJ_Forget) { + /* + * For metadata buffers, we track dirty bit in buffer_jbddirty + * instead of buffer_dirty. We should not see a dirty bit set + * here because we clear it in do_get_write_access but e.g. + * tune2fs can modify the sb and set the dirty bit at any time + * so we try to gracefully handle that. + */ + if (buffer_dirty(bh)) + warn_dirty_buffer(bh); if (test_clear_buffer_dirty(bh) || test_clear_buffer_jbddirty(bh)) was_dirty = 1; From ffacfa7a79d6c00624196b2d13b0a7f72f2b8227 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jul 2009 16:22:22 -0400 Subject: [PATCH 0008/1346] ext4: Fix truncation of symlinks after failed write Contents of long symlinks is written via standard write methods. So when the write fails, we add inode to orphan list. But symlinks don't have .truncate method defined so nobody properly removes them from the on disk orphan list. Fix this by calling ext4_truncate() directly instead of calling vmtruncate() (which is saner anyway since we don't need anything vmtruncate() does except from calling .truncate in these paths). We also add inode to orphan list only if ext4_can_truncate() is true (currently, it can be false for symlinks when there are no blocks allocated) - otherwise orphan list processing will complain and ext4_truncate() will not remove inode from on-disk orphan list. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9760ba09275..ff2afc1909b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1513,14 +1513,14 @@ retry: * Add inode to orphan list in case we crash before * truncate finishes */ - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); + ext4_truncate(inode); /* - * If vmtruncate failed early the inode might + * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. @@ -1614,7 +1614,7 @@ static int ext4_ordered_write_end(struct file *file, ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1628,9 +1628,9 @@ static int ext4_ordered_write_end(struct file *file, ret = ret2; if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); + ext4_truncate(inode); /* - * If vmtruncate failed early the inode might still be + * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ @@ -1655,7 +1655,7 @@ static int ext4_writeback_write_end(struct file *file, ret2 = ext4_generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1670,9 +1670,9 @@ static int ext4_writeback_write_end(struct file *file, ret = ret2; if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); + ext4_truncate(inode); /* - * If vmtruncate failed early the inode might still be + * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ @@ -1722,7 +1722,7 @@ static int ext4_journalled_write_end(struct file *file, unlock_page(page); page_cache_release(page); - if (pos + len > inode->i_size) + if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1733,9 +1733,9 @@ static int ext4_journalled_write_end(struct file *file, if (!ret) ret = ret2; if (pos + len > inode->i_size) { - vmtruncate(inode, inode->i_size); + ext4_truncate(inode); /* - * If vmtruncate failed early the inode might still be + * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ @@ -2907,7 +2907,7 @@ retry: * i_size_read because we hold i_mutex. */ if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); + ext4_truncate(inode); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) From 5887e98b609e96ce61ee0528cf94a2bfdc809dd7 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sun, 5 Jul 2009 23:12:04 -0400 Subject: [PATCH 0009/1346] ext4: Calculate required journal credits for inserting an extent properly When we have space in the extent tree leaf node we should be able to insert the extent with much less journal credits. The code was doing proper calculation but missed a return statement. Reported-by: Andreas Dilger Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 50322a09bd0..73ebfb44ad7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1977,6 +1977,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, */ /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); + return ret; } } From 5adfee9c17314c1411095c23191c3cb0c2d25f9f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 8 Jul 2009 17:11:24 -0400 Subject: [PATCH 0010/1346] ext4: fix no journal corruption with locale-gen If there is no journal, ext4_should_writeback_data() should return TRUE. This will fix ext4_set_aops() to set ext4_da_ops in the case of delayed allocation; otherwise ext4_journaled_aops gets used by default, which doesn't handle delayed allocation properly. The advantage of using ext4_should_writeback_data() approach is that it should handle nobh better as well. Thanks to Curt Wohlgemuth for investigating this problem, and Aneesh Kumar for suggesting this approach. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_jbd2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index be2f426f680..d574a85aca5 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -281,10 +281,10 @@ static inline int ext4_should_order_data(struct inode *inode) static inline int ext4_should_writeback_data(struct inode *inode) { - if (EXT4_JOURNAL(inode) == NULL) - return 0; if (!S_ISREG(inode->i_mode)) return 0; + if (EXT4_JOURNAL(inode) == NULL) + return 1; if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) return 0; if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) From e6462869e4fd88be5141a356ee0c28d8067340cc Mon Sep 17 00:00:00 2001 From: Johann Lombardi Date: Sun, 5 Jul 2009 23:45:11 -0400 Subject: [PATCH 0011/1346] ext4: Fix goal inum check in the inode allocator The goal inode is specificed by inode number which belongs to [1; s_inodes_count]. Signed-off-by: Johann Lombardi Signed-off-by: "Theodore Ts'o" --- fs/ext4/ialloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 2f645732e3b..29e6dc7299b 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -833,7 +833,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode, if (!goal) goal = sbi->s_inode_goal; - if (goal && goal < le32_to_cpu(sbi->s_es->s_inodes_count)) { + if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) { group = (goal - 1) / EXT4_INODES_PER_GROUP(sb); ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb); ret2 = 0; From b767e78a179e5ab30fdbff1686d074ac270471eb Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 4 Jun 2009 08:06:06 -0400 Subject: [PATCH 0012/1346] ext4: Don't look at buffer_heads outside i_size. Buffer heads outside i_size will be unmapped. So when we are doing "walk_page_buffers" limit ourself to i_size. Signed-off-by: Aneesh Kumar K.V Reviewed-by: Josef Bacik Acked-by: Jan Kara Signed-off-by: "Theodore Ts'o" ---- --- fs/ext4/inode.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ff2afc1909b..b87b68cd324 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2578,7 +2578,7 @@ static int ext4_da_writepage(struct page *page, * all are mapped and non delay. We don't want to * do block allocation here. */ - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, + ret = block_prepare_write(page, 0, len, noalloc_get_block_write); if (!ret) { page_bufs = page_buffers(page); @@ -2600,7 +2600,7 @@ static int ext4_da_writepage(struct page *page, return 0; } /* now mark the buffer_heads as dirty and uptodate */ - block_commit_write(page, 0, PAGE_CACHE_SIZE); + block_commit_write(page, 0, len); } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) @@ -3246,6 +3246,8 @@ static int ext4_normal_writepage(struct page *page, static int __ext4_journalled_writepage(struct page *page, struct writeback_control *wbc) { + loff_t size; + unsigned int len; struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; struct buffer_head *page_bufs; @@ -3253,14 +3255,17 @@ static int __ext4_journalled_writepage(struct page *page, int ret = 0; int err; - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - noalloc_get_block_write); + size = i_size_read(inode); + if (page->index == size >> PAGE_CACHE_SHIFT) + len = size & ~PAGE_CACHE_MASK; + else + len = PAGE_CACHE_SIZE; + ret = block_prepare_write(page, 0, len, noalloc_get_block_write); if (ret != 0) goto out_unlock; page_bufs = page_buffers(page); - walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL, - bget_one); + walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); /* As soon as we unlock the page, it can go away, but we have * references to buffers so we are safe */ unlock_page(page); @@ -3271,19 +3276,18 @@ static int __ext4_journalled_writepage(struct page *page, goto out; } - ret = walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, do_journal_get_write_access); + ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, + do_journal_get_write_access); - err = walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, write_end_fn); + err = walk_page_buffers(handle, page_bufs, 0, len, NULL, + write_end_fn); if (ret == 0) ret = err; err = ext4_journal_stop(handle); if (!ret) ret = err; - walk_page_buffers(handle, page_bufs, 0, - PAGE_CACHE_SIZE, NULL, bput_one); + walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; goto out; From c364b22c9580a885e0f8c0d0f9710d67dc448958 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sun, 14 Jun 2009 17:57:10 -0400 Subject: [PATCH 0013/1346] ext4: Fix mmap/truncate race when blocksize < pagesize && delayed allocation It is possible to see buffer_heads which are not mapped in the writepage callback in the following scneario (where the fs blocksize is 1k and the page size is 4k): 1) truncate(f, 1024) 2) mmap(f, 0, 4096) 3) a[0] = 'a' 4) truncate(f, 4096) 5) writepage(...) Now if we get a writepage callback immediately after (4) and before an attempt to write at any other offset via mmap address (which implies we are yet to get a pagefault and do a get_block) what we would have is the page which is dirty have first block allocated and the other three buffer_heads unmapped. In the above case the writepage should go ahead and try to write the first blocks and clear the page_dirty flag. Further attempts to write to the page will again create a fault and result in allocating blocks and marking page dirty. If we don't write any other offset via mmap address we would still have written the first block to the disk and rest of the space will be considered as a hole. So to address this, we change all of the places where we look for delayed, unmapped, or unwritten buffer heads, and only check for delayed or unwritten buffer heads instead. Signed-off-by: Aneesh Kumar K.V Acked-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b87b68cd324..1275f34589c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2305,15 +2305,9 @@ flush_it: return; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) { - /* - * unmapped buffer is possible for holes. - * delay buffer is possible with delayed allocation. - * We also need to consider unwritten buffer as unmapped. - */ - return (!buffer_mapped(bh) || buffer_delay(bh) || - buffer_unwritten(bh)) && buffer_dirty(bh); + return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); } /* @@ -2400,7 +2394,7 @@ static int __mpage_da_writepage(struct page *page, * Otherwise we won't make progress * with the page in ext4_da_writepage */ - if (ext4_bh_unmapped_or_delay(NULL, bh)) { + if (ext4_bh_delay_or_unwritten(NULL, bh)) { mpage_add_bh_to_extent(mpd, logical, bh->b_size, bh->b_state); @@ -2517,7 +2511,6 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, * so call get_block_wrap with create = 0 */ ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0); - BUG_ON(create && ret == 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -2533,7 +2526,7 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, * - grab_page_cache when doing write_begin (have journal handle) */ static int ext4_da_writepage(struct page *page, - struct writeback_control *wbc) + struct writeback_control *wbc) { int ret = 0; loff_t size; @@ -2551,7 +2544,7 @@ static int ext4_da_writepage(struct page *page, if (page_has_buffers(page)) { page_bufs = page_buffers(page); if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_unmapped_or_delay)) { + ext4_bh_delay_or_unwritten)) { /* * We don't want to do block allocation * So redirty the page and return @@ -2584,7 +2577,7 @@ static int ext4_da_writepage(struct page *page, page_bufs = page_buffers(page); /* check whether all are mapped and non delay */ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_unmapped_or_delay)) { + ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; @@ -3232,7 +3225,7 @@ static int ext4_normal_writepage(struct page *page, * happily proceed with mapping them and writing the page. */ BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); + ext4_bh_delay_or_unwritten)); } if (!ext4_journal_current_handle()) @@ -3322,7 +3315,7 @@ static int ext4_journalled_writepage(struct page *page, * happily proceed with mapping them and writing the page. */ BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); + ext4_bh_delay_or_unwritten)); } if (ext4_journal_current_handle()) From 43ce1d23b43330634507a049b55c36e91d27282e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sun, 14 Jun 2009 17:58:45 -0400 Subject: [PATCH 0014/1346] ext4: Fix mmap/truncate race when blocksize < pagesize && !nodellaoc This patch fixes the mmap/truncate race that was fixed for delayed allocation by merging ext4_{journalled,normal,da}_writepage() into ext4_writepage(). Signed-off-by: Aneesh Kumar K.V Acked-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 234 +++++++++--------------------------- include/trace/events/ext4.h | 45 +------ 2 files changed, 58 insertions(+), 221 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1275f34589c..97c48b5b057 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -47,6 +47,10 @@ #define MPAGE_DA_EXTENT_TAIL 0x01 +static int __ext4_journalled_writepage(struct page *page, + struct writeback_control *wbc, + unsigned int len); + static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { @@ -2392,7 +2396,7 @@ static int __mpage_da_writepage(struct page *page, * We need to try to allocate * unmapped blocks in the same page. * Otherwise we won't make progress - * with the page in ext4_da_writepage + * with the page in ext4_writepage */ if (ext4_bh_delay_or_unwritten(NULL, bh)) { mpage_add_bh_to_extent(mpd, logical, @@ -2519,13 +2523,47 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, } /* + * Note that we don't need to start a transaction unless we're journaling data + * because we should have holes filled from ext4_page_mkwrite(). We even don't + * need to file the inode to the transaction's list in ordered mode because if + * we are writing back data added by write(), the inode is already there and if + * we are writing back data modified via mmap(), noone guarantees in which + * transaction the data will hit the disk. In case we are journaling data, we + * cannot start transaction directly because transaction start ranks above page + * lock so we have to do some magic. + * * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) * - shrink_page_list via pdflush (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) + * + * We don't do any block allocation in this function. If we have page with + * multiple blocks we need to write those buffer_heads that are mapped. This + * is important for mmaped based write. So if we do with blocksize 1K + * truncate(f, 1024); + * a = mmap(f, 0, 4096); + * a[0] = 'a'; + * truncate(f, 4096); + * we have in the page first buffer_head mapped via page_mkwrite call back + * but other bufer_heads would be unmapped but dirty(dirty done via the + * do_wp_page). So writepage should write the first block. If we modify + * the mmap area beyond 1024 we will again get a page_fault and the + * page_mkwrite callback will do the block allocation and mark the + * buffer_heads mapped. + * + * We redirty the page if we have any buffer_heads that is either delay or + * unwritten in the page. + * + * We can get recursively called as show below. + * + * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> + * ext4_writepage() + * + * But since we don't do any block allocation we should not deadlock. + * Page also have the dirty flag cleared so we don't get recurive page_lock. */ -static int ext4_da_writepage(struct page *page, +static int ext4_writepage(struct page *page, struct writeback_control *wbc) { int ret = 0; @@ -2534,7 +2572,7 @@ static int ext4_da_writepage(struct page *page, struct buffer_head *page_bufs; struct inode *inode = page->mapping->host; - trace_ext4_da_writepage(inode, page); + trace_ext4_writepage(inode, page); size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; @@ -2596,6 +2634,15 @@ static int ext4_da_writepage(struct page *page, block_commit_write(page, 0, len); } + if (PageChecked(page) && ext4_should_journal_data(inode)) { + /* + * It's mmapped pagecache. Add buffers and journal it. There + * doesn't seem much point in redirtying the page here. + */ + ClearPageChecked(page); + return __ext4_journalled_writepage(page, wbc, len); + } + if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) ret = nobh_writepage(page, noalloc_get_block_write, wbc); else @@ -3135,112 +3182,10 @@ static int bput_one(handle_t *handle, struct buffer_head *bh) return 0; } -/* - * Note that we don't need to start a transaction unless we're journaling data - * because we should have holes filled from ext4_page_mkwrite(). We even don't - * need to file the inode to the transaction's list in ordered mode because if - * we are writing back data added by write(), the inode is already there and if - * we are writing back data modified via mmap(), noone guarantees in which - * transaction the data will hit the disk. In case we are journaling data, we - * cannot start transaction directly because transaction start ranks above page - * lock so we have to do some magic. - * - * In all journaling modes block_write_full_page() will start the I/O. - * - * Problem: - * - * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> - * ext4_writepage() - * - * Similar for: - * - * ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ... - * - * Same applies to ext4_get_block(). We will deadlock on various things like - * lock_journal and i_data_sem - * - * Setting PF_MEMALLOC here doesn't work - too many internal memory - * allocations fail. - * - * 16May01: If we're reentered then journal_current_handle() will be - * non-zero. We simply *return*. - * - * 1 July 2001: @@@ FIXME: - * In journalled data mode, a data buffer may be metadata against the - * current transaction. But the same file is part of a shared mapping - * and someone does a writepage() on it. - * - * We will move the buffer onto the async_data list, but *after* it has - * been dirtied. So there's a small window where we have dirty data on - * BJ_Metadata. - * - * Note that this only applies to the last partial page in the file. The - * bit which block_write_full_page() uses prepare/commit for. (That's - * broken code anyway: it's wrong for msync()). - * - * It's a rare case: affects the final partial page, for journalled data - * where the file is subject to bith write() and writepage() in the same - * transction. To fix it we'll need a custom block_write_full_page(). - * We'll probably need that anyway for journalling writepage() output. - * - * We don't honour synchronous mounts for writepage(). That would be - * disastrous. Any write() or metadata operation will sync the fs for - * us. - * - */ -static int __ext4_normal_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - - if (test_opt(inode->i_sb, NOBH)) - return nobh_writepage(page, noalloc_get_block_write, wbc); - else - return block_write_full_page(page, noalloc_get_block_write, - wbc); -} - -static int ext4_normal_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - loff_t size = i_size_read(inode); - loff_t len; - - trace_ext4_normal_writepage(inode, page); - J_ASSERT(PageLocked(page)); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - - if (page_has_buffers(page)) { - /* if page has buffers it should all be mapped - * and allocated. If there are not buffers attached - * to the page we know the page is dirty but it lost - * buffers. That means that at some moment in time - * after write_begin() / write_end() has been called - * all buffers have been clean and thus they must have been - * written at least once. So they are all mapped and we can - * happily proceed with mapping them and writing the page. - */ - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_delay_or_unwritten)); - } - - if (!ext4_journal_current_handle()) - return __ext4_normal_writepage(page, wbc); - - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} - static int __ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc) + struct writeback_control *wbc, + unsigned int len) { - loff_t size; - unsigned int len; struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; struct buffer_head *page_bufs; @@ -3248,16 +3193,8 @@ static int __ext4_journalled_writepage(struct page *page, int ret = 0; int err; - size = i_size_read(inode); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - ret = block_prepare_write(page, 0, len, noalloc_get_block_write); - if (ret != 0) - goto out_unlock; - page_bufs = page_buffers(page); + BUG_ON(!page_bufs); walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); /* As soon as we unlock the page, it can go away, but we have * references to buffers so we are safe */ @@ -3282,67 +3219,10 @@ static int __ext4_journalled_writepage(struct page *page, walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; - goto out; - -out_unlock: - unlock_page(page); out: return ret; } -static int ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc) -{ - struct inode *inode = page->mapping->host; - loff_t size = i_size_read(inode); - loff_t len; - - trace_ext4_journalled_writepage(inode, page); - J_ASSERT(PageLocked(page)); - if (page->index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - - if (page_has_buffers(page)) { - /* if page has buffers it should all be mapped - * and allocated. If there are not buffers attached - * to the page we know the page is dirty but it lost - * buffers. That means that at some moment in time - * after write_begin() / write_end() has been called - * all buffers have been clean and thus they must have been - * written at least once. So they are all mapped and we can - * happily proceed with mapping them and writing the page. - */ - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_delay_or_unwritten)); - } - - if (ext4_journal_current_handle()) - goto no_write; - - if (PageChecked(page)) { - /* - * It's mmapped pagecache. Add buffers and journal it. There - * doesn't seem much point in redirtying the page here. - */ - ClearPageChecked(page); - return __ext4_journalled_writepage(page, wbc); - } else { - /* - * It may be a page full of checkpoint-mode buffers. We don't - * really know unless we go poke around in the buffer_heads. - * But block_write_full_page will do the right thing. - */ - return block_write_full_page(page, noalloc_get_block_write, - wbc); - } -no_write: - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} - static int ext4_readpage(struct file *file, struct page *page) { return mpage_readpage(page, ext4_get_block); @@ -3489,7 +3369,7 @@ static int ext4_journalled_set_page_dirty(struct page *page) static const struct address_space_operations ext4_ordered_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, + .writepage = ext4_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_ordered_write_end, @@ -3504,7 +3384,7 @@ static const struct address_space_operations ext4_ordered_aops = { static const struct address_space_operations ext4_writeback_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, + .writepage = ext4_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_writeback_write_end, @@ -3519,7 +3399,7 @@ static const struct address_space_operations ext4_writeback_aops = { static const struct address_space_operations ext4_journalled_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_journalled_writepage, + .writepage = ext4_writepage, .sync_page = block_sync_page, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, @@ -3533,7 +3413,7 @@ static const struct address_space_operations ext4_journalled_aops = { static const struct address_space_operations ext4_da_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, - .writepage = ext4_da_writepage, + .writepage = ext4_writepage, .writepages = ext4_da_writepages, .sync_page = block_sync_page, .write_begin = ext4_da_write_begin, diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b456fb0a3c5..dfbc9b0edc8 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -190,7 +190,7 @@ TRACE_EVENT(ext4_journalled_write_end, __entry->copied) ); -TRACE_EVENT(ext4_da_writepage, +TRACE_EVENT(ext4_writepage, TP_PROTO(struct inode *inode, struct page *page), TP_ARGS(inode, page), @@ -342,49 +342,6 @@ TRACE_EVENT(ext4_da_write_end, __entry->copied) ); -TRACE_EVENT(ext4_normal_writepage, - TP_PROTO(struct inode *inode, struct page *page), - - TP_ARGS(inode, page), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( pgoff_t, index ) - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->index = page->index; - ), - - TP_printk("dev %s ino %lu page_index %lu", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index) -); - -TRACE_EVENT(ext4_journalled_writepage, - TP_PROTO(struct inode *inode, struct page *page), - - TP_ARGS(inode, page), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( pgoff_t, index ) - - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->index = page->index; - ), - - TP_printk("dev %s ino %lu page_index %lu", - jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index) -); - TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), From 62e086be5d2abef8cad854bc5707329ad345f2ec Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sun, 14 Jun 2009 17:59:34 -0400 Subject: [PATCH 0015/1346] ext4: Move __ext4_journalled_writepage() to avoid forward declaration In addition, fix two unused variable warnings. Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 112 +++++++++++++++++++++++------------------------- 1 file changed, 54 insertions(+), 58 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 97c48b5b057..c98e3afea30 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -47,10 +47,6 @@ #define MPAGE_DA_EXTENT_TAIL 0x01 -static int __ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc, - unsigned int len); - static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { @@ -2522,6 +2518,59 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, return ret; } +static int bget_one(handle_t *handle, struct buffer_head *bh) +{ + get_bh(bh); + return 0; +} + +static int bput_one(handle_t *handle, struct buffer_head *bh) +{ + put_bh(bh); + return 0; +} + +static int __ext4_journalled_writepage(struct page *page, + struct writeback_control *wbc, + unsigned int len) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + struct buffer_head *page_bufs; + handle_t *handle = NULL; + int ret = 0; + int err; + + page_bufs = page_buffers(page); + BUG_ON(!page_bufs); + walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); + /* As soon as we unlock the page, it can go away, but we have + * references to buffers so we are safe */ + unlock_page(page); + + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, + do_journal_get_write_access); + + err = walk_page_buffers(handle, page_bufs, 0, len, NULL, + write_end_fn); + if (ret == 0) + ret = err; + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + + walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); + EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; +out: + return ret; +} + /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't @@ -2564,7 +2613,7 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock, * Page also have the dirty flag cleared so we don't get recurive page_lock. */ static int ext4_writepage(struct page *page, - struct writeback_control *wbc) + struct writeback_control *wbc) { int ret = 0; loff_t size; @@ -3170,59 +3219,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, ext4_get_block); } -static int bget_one(handle_t *handle, struct buffer_head *bh) -{ - get_bh(bh); - return 0; -} - -static int bput_one(handle_t *handle, struct buffer_head *bh) -{ - put_bh(bh); - return 0; -} - -static int __ext4_journalled_writepage(struct page *page, - struct writeback_control *wbc, - unsigned int len) -{ - struct address_space *mapping = page->mapping; - struct inode *inode = mapping->host; - struct buffer_head *page_bufs; - handle_t *handle = NULL; - int ret = 0; - int err; - - page_bufs = page_buffers(page); - BUG_ON(!page_bufs); - walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); - /* As soon as we unlock the page, it can go away, but we have - * references to buffers so we are safe */ - unlock_page(page); - - handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } - - ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, - do_journal_get_write_access); - - err = walk_page_buffers(handle, page_bufs, 0, len, NULL, - write_end_fn); - if (ret == 0) - ret = err; - err = ext4_journal_stop(handle); - if (!ret) - ret = err; - - walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); - EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; -out: - return ret; -} - static int ext4_readpage(struct file *file, struct page *page) { return mpage_readpage(page, ext4_get_block); From c79ee4e466dd12347f112e2af306dca35198458f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 16 Jun 2009 12:23:58 +0200 Subject: [PATCH 0016/1346] dma-debug: fix off-by-one error in overlap function This patch fixes a bug in the overlap function which returned true if one region ends exactly before the second region begins. This is no overlap but the function returned true in that case. Cc: stable@kernel.org Reported-by: Andrew Randrianasulu Signed-off-by: Joerg Roedel --- lib/dma-debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 3b93129a968..a9b6b5c9e09 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -862,7 +862,7 @@ static inline bool overlap(void *addr, u64 size, void *start, void *end) return ((addr >= start && addr < end) || (addr2 >= start && addr2 < end) || - ((addr < start) && (addr2 >= end))); + ((addr < start) && (addr2 > end))); } static void check_for_illegal_area(struct device *dev, void *addr, u64 size) From a7aea373b4ca428f1be2c1fedd2f26c8e3f2864d Mon Sep 17 00:00:00 2001 From: "Ira W. Snyder" Date: Thu, 23 Apr 2009 16:17:54 -0700 Subject: [PATCH 0017/1346] fsldma: use PCI Read Multiple command By default, the Freescale 83xx DMA controller uses the PCI Read Line command when reading data over the PCI bus. Setting the controller to use the PCI Read Multiple command instead allows the controller to read much larger bursts of data, which provides a drastic speed increase. The slowdown due to using PCI Read Line was only observed when a PCI-to-PCI bridge was between the devices trying to communicate. A simple test driver showed an increase from 4MB/sec to 116MB/sec when performing DMA over the PCI bus. Using DMA to transfer between blocks of local SDRAM showed no change in performance with this patch. The dmatest driver was also used to verify the correctness of the transfers, and showed no errors. Signed-off-by: Ira W. Snyder Acked-by: Timur Tabi Acked-by: Kumar Gala Signed-off-by: Dan Williams --- drivers/dma/fsldma.c | 10 ++++++++-- drivers/dma/fsldma.h | 1 + 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index f18d1bde043..a1cb25e277b 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -12,6 +12,11 @@ * also fit for MPC8560, MPC8555, MPC8548, MPC8641, and etc. * The support for MPC8349 DMA contorller is also added. * + * This driver instructs the DMA controller to issue the PCI Read Multiple + * command for PCI read operations, instead of using the default PCI Read Line + * command. Please be aware that this setting may result in read pre-fetching + * on some platforms. + * * This is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or @@ -49,9 +54,10 @@ static void dma_init(struct fsl_dma_chan *fsl_chan) case FSL_DMA_IP_83XX: /* Set the channel to below modes: * EOTIE - End-of-transfer interrupt enable + * PRC_RM - PCI read multiple */ - DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr, FSL_DMA_MR_EOTIE, - 32); + DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr, FSL_DMA_MR_EOTIE + | FSL_DMA_MR_PRC_RM, 32); break; } diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h index 4f21a512d84..dc7f2686579 100644 --- a/drivers/dma/fsldma.h +++ b/drivers/dma/fsldma.h @@ -38,6 +38,7 @@ /* Special MR definition for MPC8349 */ #define FSL_DMA_MR_EOTIE 0x00000080 +#define FSL_DMA_MR_PRC_RM 0x00000800 #define FSL_DMA_SR_CH 0x00000020 #define FSL_DMA_SR_PE 0x00000010 From be30b226f2ae618cd719e40267d9923db1db9001 Mon Sep 17 00:00:00 2001 From: Ira Snyder Date: Thu, 28 May 2009 09:20:42 +0000 Subject: [PATCH 0018/1346] fsldma: enable external start for the 83xx controller The 83xx controller has external start capability, but lacks external pause capability. Hook up the external start function pointer for the 83xx controller. Signed-off-by: Ira W. Snyder Signed-off-by: Dan Williams --- drivers/dma/fsldma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index a1cb25e277b..10bcf0cb0ef 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -877,9 +877,9 @@ static int __devinit fsl_dma_chan_probe(struct fsl_dma_device *fdev, switch (new_fsl_chan->feature & FSL_DMA_IP_MASK) { case FSL_DMA_IP_85XX: - new_fsl_chan->toggle_ext_start = fsl_chan_toggle_ext_start; new_fsl_chan->toggle_ext_pause = fsl_chan_toggle_ext_pause; case FSL_DMA_IP_83XX: + new_fsl_chan->toggle_ext_start = fsl_chan_toggle_ext_start; new_fsl_chan->set_src_loop_size = fsl_chan_set_src_loop_size; new_fsl_chan->set_dest_loop_size = fsl_chan_set_dest_loop_size; } From 43a1a3ed6bf5a1b9ae197b4f5f20033baf19db61 Mon Sep 17 00:00:00 2001 From: Ira Snyder Date: Thu, 28 May 2009 09:26:40 +0000 Subject: [PATCH 0019/1346] fsldma: do not clear bandwidth control bits on the 83xx controller The 83xx controller does not support the external pause feature. The bit in the mode register that controls external pause on the 85xx controller happens to be part of the bandwidth control settings for the 83xx controller. This patch fixes the driver so that it only clears the external pause bit if the hardware is the 85xx controller. When driving the 83xx controller, the bit is left untouched. This follows the existing convention that mode registers settings are not touched unless necessary. Signed-off-by: Ira W. Snyder Signed-off-by: Dan Williams --- drivers/dma/fsldma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 10bcf0cb0ef..6e60c77a145 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -147,10 +147,11 @@ static void dma_start(struct fsl_dma_chan *fsl_chan) if (fsl_chan->feature & FSL_DMA_CHAN_PAUSE_EXT) { DMA_OUT(fsl_chan, &fsl_chan->reg_base->bcr, 0, 32); mr_set |= FSL_DMA_MR_EMP_EN; - } else + } else if ((fsl_chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) { DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr, DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32) & ~FSL_DMA_MR_EMP_EN, 32); + } if (fsl_chan->feature & FSL_DMA_CHAN_START_EXT) mr_set |= FSL_DMA_MR_EMS_EN; From b0a5b83ee0fce9dbf8ff5fe1f8c9ae7dfafe458c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 16 Jun 2009 16:11:14 +0200 Subject: [PATCH 0020/1346] dma-debug: Put all hash-chain locks into the same lock class Alan Cox reported that lockdep runs out of its stack-trace entries with certain configs: BUG: MAX_STACK_TRACE_ENTRIES too low This happens because there are 1024 hash buckets, each with a separate lock. Lockdep puts each lock into a separate lock class and tracks them independently. But in reality we never take more than one of the buckets, so they really belong into a single lock-class. Annotate the has bucket lock init accordingly. [ Impact: reduce the lockdep footprint of dma-debug ] Reported-by: Alan Cox Signed-off-by: Ingo Molnar Signed-off-by: Joerg Roedel --- lib/dma-debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/dma-debug.c b/lib/dma-debug.c index a9b6b5c9e09..c9187fed0b9 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -716,7 +716,7 @@ void dma_debug_init(u32 num_entries) for (i = 0; i < HASH_SIZE; ++i) { INIT_LIST_HEAD(&dma_entry_hash[i].list); - dma_entry_hash[i].lock = SPIN_LOCK_UNLOCKED; + spin_lock_init(&dma_entry_hash[i].lock); } if (dma_debug_fs_init() != 0) { From a566a6b11c86147fe9fc9db7ab15f9eecca3e862 Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Mon, 15 Jun 2009 08:26:48 +0100 Subject: [PATCH 0021/1346] dlm: Fix uninitialised variable warning in lock.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CC [M] fs/dlm/lock.o fs/dlm/lock.c: In function ‘find_rsb’: fs/dlm/lock.c:438: warning: ‘r’ may be used uninitialized in this function Since r is used on the error path to set r_ret, set it to NULL. Signed-off-by: Steven Whitehouse Signed-off-by: David Teigland --- fs/dlm/lock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 205ec95b347..eb507c453c5 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -435,7 +435,7 @@ static int search_rsb(struct dlm_ls *ls, char *name, int len, int b, static int find_rsb(struct dlm_ls *ls, char *name, int namelen, unsigned int flags, struct dlm_rsb **r_ret) { - struct dlm_rsb *r, *tmp; + struct dlm_rsb *r = NULL, *tmp; uint32_t hash, bucket; int error = -EINVAL; From c78a87d0a1fc885dfdbe21fd5e07787691dfb068 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Thu, 18 Jun 2009 13:20:24 -0500 Subject: [PATCH 0022/1346] dlm: fix plock use-after-free Fix a regression from the original addition of nfs lock support 586759f03e2e9031ac5589912a51a909ed53c30a. When a synchronous (non-nfs) plock completes, the waiting thread will wake up and free the op struct. This races with the user thread in dev_write() which goes on to read the op's callback field to check if the lock is async and needs a callback. This check can happen on the freed op. The fix is to note the callback value before the op can be freed. Signed-off-by: David Teigland --- fs/dlm/plock.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 894a32d438d..16f682e26c0 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -353,7 +353,7 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, { struct dlm_plock_info info; struct plock_op *op; - int found = 0; + int found = 0, do_callback = 0; if (count != sizeof(info)) return -EINVAL; @@ -366,21 +366,24 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, spin_lock(&ops_lock); list_for_each_entry(op, &recv_list, list) { - if (op->info.fsid == info.fsid && op->info.number == info.number && + if (op->info.fsid == info.fsid && + op->info.number == info.number && op->info.owner == info.owner) { + struct plock_xop *xop = (struct plock_xop *)op; list_del_init(&op->list); - found = 1; - op->done = 1; memcpy(&op->info, &info, sizeof(info)); + if (xop->callback) + do_callback = 1; + else + op->done = 1; + found = 1; break; } } spin_unlock(&ops_lock); if (found) { - struct plock_xop *xop; - xop = (struct plock_xop *)op; - if (xop->callback) + if (do_callback) dlm_plock_callback(op); else wake_up(&recv_wq); From d4ec36bac3de39b7e10ec8f42fbdd20d9a9ed753 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sun, 21 Jun 2009 12:32:39 +0200 Subject: [PATCH 0023/1346] sched: Documentation/sched-rt-group: Fix style issues & bump version - add missing closing bracket - fix two 80-chars issues (as the rest of the document adheres to it) - bump a reference to kernel version, so the document does not feel aged Signed-off-by: Wolfram Sang Cc: Peter Zijlstra LKML-Reference: <1245580359-4465-1-git-send-email-w.sang@pengutronix.de> Signed-off-by: Ingo Molnar --- Documentation/scheduler/sched-rt-group.txt | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 1df7f9cdab0..86eabe6c341 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -73,7 +73,7 @@ The remaining CPU time will be used for user input and other tasks. Because realtime tasks have explicitly allocated the CPU time they need to perform their tasks, buffer underruns in the graphics or audio can be eliminated. -NOTE: the above example is not fully implemented as of yet (2.6.25). We still +NOTE: the above example is not fully implemented yet. We still lack an EDF scheduler to make non-uniform periods usable. @@ -140,14 +140,15 @@ The other option is: .o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups") -This uses the /cgroup virtual file system and "/cgroup//cpu.rt_runtime_us" -to control the CPU time reserved for each control group instead. +This uses the /cgroup virtual file system and +"/cgroup//cpu.rt_runtime_us" to control the CPU time reserved for each +control group instead. For more information on working with control groups, you should read Documentation/cgroups/cgroups.txt as well. -Group settings are checked against the following limits in order to keep the configuration -schedulable: +Group settings are checked against the following limits in order to keep the +configuration schedulable: \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period @@ -189,7 +190,7 @@ Implementing SCHED_EDF might take a while to complete. Priority Inheritance is the biggest challenge as the current linux PI infrastructure is geared towards the limited static priority levels 0-99. With deadline scheduling you need to do deadline inheritance (since priority is inversely proportional to the -deadline delta (deadline - now). +deadline delta (deadline - now)). This means the whole PI machinery will have to be reworked - and that is one of the most complex pieces of code we have. From b76a3f93d01fc93a87cb6eba4e854ffe378b4bac Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Mon, 8 Jun 2009 19:28:41 +0300 Subject: [PATCH 0024/1346] exofs: Fix bio leak in error handling path (sync read) When failing a read request in the sync path, called from write_begin, I forgot to free the allocated bio, fix it. Signed-off-by: Boaz Harrosh --- fs/exofs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 77d0a295eb1..bb5d6ed0f7a 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -295,6 +295,9 @@ static int read_exec(struct page_collect *pcol, bool is_sync) err: if (!is_sync) _unlock_pcol_pages(pcol, ret, READ); + else /* Pages unlocked by caller in sync mode only free bio */ + pcol_free(pcol); + kfree(pcol_copy); if (or) osd_end_request(or); From 27d2e1491985e95c486d991302e399f5c584b4eb Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 14 Jun 2009 17:23:09 +0300 Subject: [PATCH 0025/1346] exofs: Remove IBM copyrights Boaz, Congrats on getting all the OSD stuff into 2.6.30! I just pulled the git, and saw that the IBM copyrights are still there. Please remove them from all files: * Copyright (C) 2005, 2006 * International Business Machines IBM has revoked all rights on the code - they gave it to me. Thanks! Avishay Signed-off-by: Avishay Traeger Signed-off-by: Boaz Harrosh --- fs/exofs/common.h | 4 +--- fs/exofs/dir.c | 4 +--- fs/exofs/exofs.h | 4 +--- fs/exofs/file.c | 4 +--- fs/exofs/inode.c | 4 +--- fs/exofs/namei.c | 4 +--- fs/exofs/osd.c | 4 +--- fs/exofs/super.c | 4 +--- fs/exofs/symlink.c | 4 +--- 9 files changed, 9 insertions(+), 27 deletions(-) diff --git a/fs/exofs/common.h b/fs/exofs/common.h index 24667eedc02..c6718e4817f 100644 --- a/fs/exofs/common.h +++ b/fs/exofs/common.h @@ -2,9 +2,7 @@ * common.h - Common definitions for both Kernel and user-mode utilities * * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index 65b0c8c776a..4cfab1cc75c 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h index 0fd4c785967..c413b74ecf3 100644 --- a/fs/exofs/exofs.h +++ b/fs/exofs/exofs.h @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 6ed7fe48475..c6810038d63 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index bb5d6ed0f7a..6c10f747669 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index 77fdd765e76..b7dd0c23686 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c index b3d2ccb87aa..4372542df28 100644 --- a/fs/exofs/osd.c +++ b/fs/exofs/osd.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 8216c5b77b5..e47b38e55a2 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * diff --git a/fs/exofs/symlink.c b/fs/exofs/symlink.c index 36e2d7bc7f7..4dd687c3e74 100644 --- a/fs/exofs/symlink.c +++ b/fs/exofs/symlink.c @@ -1,8 +1,6 @@ /* * Copyright (C) 2005, 2006 - * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com) - * Copyright (C) 2005, 2006 - * International Business Machines + * Avishay Traeger (avishay@gmail.com) * Copyright (C) 2008, 2009 * Boaz Harrosh * From baaf94cdc7fe1c61e3c660a3b055724fd9d0a034 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Sun, 14 Jun 2009 16:52:10 +0300 Subject: [PATCH 0026/1346] exofs: Avoid using file_fsync() The use of file_fsync() in exofs_file_sync() is not necessary since it does some extra stuff not used by exofs. Open code just the parts that are currently needed. TODO: Farther optimization can be done to sync the sb only on inode update of new files, Usually the sb update is not needed in exofs. Signed-off-by: Boaz Harrosh --- fs/exofs/exofs.h | 3 +++ fs/exofs/file.c | 17 ++++++++++++----- fs/exofs/super.c | 2 +- 3 files changed, 16 insertions(+), 6 deletions(-) diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h index c413b74ecf3..5ec72e020b2 100644 --- a/fs/exofs/exofs.h +++ b/fs/exofs/exofs.h @@ -154,6 +154,9 @@ ino_t exofs_parent_ino(struct dentry *child); int exofs_set_link(struct inode *, struct exofs_dir_entry *, struct page *, struct inode *); +/* super.c */ +int exofs_sync_fs(struct super_block *sb, int wait); + /********************* * operation vectors * *********************/ diff --git a/fs/exofs/file.c b/fs/exofs/file.c index c6810038d63..839b9dc1e70 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -45,16 +45,23 @@ static int exofs_file_fsync(struct file *filp, struct dentry *dentry, { int ret; struct address_space *mapping = filp->f_mapping; + struct inode *inode = dentry->d_inode; + struct super_block *sb; ret = filemap_write_and_wait(mapping); if (ret) return ret; - /*Note: file_fsync below also calles sync_blockdev, which is a no-op - * for exofs, but other then that it does sync_inode and - * sync_superblock which is what we need here. - */ - return file_fsync(filp, dentry, datasync); + /* sync the inode attributes */ + ret = write_inode_now(inode, 1); + + /* This is a good place to write the sb */ + /* TODO: Sechedule an sb-sync on create */ + sb = inode->i_sb; + if (sb->s_dirt) + exofs_sync_fs(sb, 1); + + return ret; } static int exofs_flush(struct file *file, fl_owner_t id) diff --git a/fs/exofs/super.c b/fs/exofs/super.c index e47b38e55a2..a343b4ea62f 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -198,7 +198,7 @@ static const struct export_operations exofs_export_ops; /* * Write the superblock to the OSD */ -static int exofs_sync_fs(struct super_block *sb, int wait) +int exofs_sync_fs(struct super_block *sb, int wait) { struct exofs_sb_info *sbi; struct exofs_fscb *fscb; From 42c55aa838bbd274a7ad2be1fd81d423ca63da4e Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Wed, 17 Jun 2009 16:54:34 +0300 Subject: [PATCH 0027/1346] MAINTAINERS: Add osd maintained files (F:) OSD files are found in three places: drivers/scsi/osd/ include/scsi/osd_* fs/exofs/ Signed-off-by: Boaz Harrosh --- MAINTAINERS | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index dc226e78612..b9b20895509 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4321,7 +4321,7 @@ W: http://www.nongnu.org/orinoco/ S: Maintained F: drivers/net/wireless/orinoco/ -OSD LIBRARY +OSD LIBRARY and FILESYSTEM P: Boaz Harrosh M: bharrosh@panasas.com P: Benny Halevy @@ -4330,6 +4330,9 @@ L: osd-dev@open-osd.org W: http://open-osd.org T: git git://git.open-osd.org/open-osd.git S: Maintained +F: drivers/scsi/osd/ +F: drivers/include/scsi/osd_* +F: fs/exofs/ P54 WIRELESS DRIVER P: Michael Wu From 4859484b0957ddc7fe3e0fa349d98b0f1c7876bd Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 19 Jun 2009 23:24:11 +0200 Subject: [PATCH 0028/1346] HID: hiddev, fix lock imbalance Add omitted BKL to one switch/case. Cc: Stable Signed-off-by: Jiri Slaby Signed-off-by: Jiri Kosina --- drivers/hid/usbhid/hiddev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index e9b436d2d94..39e27f4be4a 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -527,8 +527,10 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, goto goodreturn; case HIDIOCGCOLLECTIONINDEX: + i = field->usage[uref->usage_index].collection_index; + unlock_kernel(); kfree(uref_multi); - return field->usage[uref->usage_index].collection_index; + return i; case HIDIOCGUSAGES: for (i = 0; i < uref_multi->num_values; i++) uref_multi->values[i] = From bc33dc5ae7ed7a422ab1141d3bf81c6cee2a5050 Mon Sep 17 00:00:00 2001 From: Huang Weiyi Date: Tue, 16 Jun 2009 16:56:09 +0800 Subject: [PATCH 0029/1346] mx31: remove duplicated #include Remove duplicated #include in arch/arm/mach-mx3/devices.c. Signed-off-by: Huang Weiyi Signed-off-by: Sascha Hauer --- arch/arm/mach-mx3/devices.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/mach-mx3/devices.c b/arch/arm/mach-mx3/devices.c index d927eddcad4..9e87e08fb12 100644 --- a/arch/arm/mach-mx3/devices.c +++ b/arch/arm/mach-mx3/devices.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include From c3a9c7f53a0eb1ec687ecf131f9cfb41bbdc26b5 Mon Sep 17 00:00:00 2001 From: Alberto Panizzo Date: Wed, 17 Jun 2009 15:05:21 +0200 Subject: [PATCH 0030/1346] ARM MXC: Armadillo 500 add NOR flash device support (resend). This patch add support for NOR flash mapping through the physmap driver. The purpose is to maintain the original Atmark partition model. Signed-off-by: Alberto Panizzo Signed-off-by: Sascha Hauer --- arch/arm/mach-mx3/armadillo5x0.c | 47 ++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/arch/arm/mach-mx3/armadillo5x0.c b/arch/arm/mach-mx3/armadillo5x0.c index 541181090b3..38d99e6c9d0 100644 --- a/arch/arm/mach-mx3/armadillo5x0.c +++ b/arch/arm/mach-mx3/armadillo5x0.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -96,6 +97,48 @@ static int armadillo5x0_pins[] = { }; +/* + * MTD NOR Flash + */ +static struct mtd_partition armadillo5x0_nor_flash_partitions[] = { + { + .name = "nor.bootloader", + .offset = 0x00000000, + .size = 4*32*1024, + }, { + .name = "nor.kernel", + .offset = MTDPART_OFS_APPEND, + .size = 16*128*1024, + }, { + .name = "nor.userland", + .offset = MTDPART_OFS_APPEND, + .size = 110*128*1024, + }, { + .name = "nor.config", + .offset = MTDPART_OFS_APPEND, + .size = 1*128*1024, + }, +}; + +static struct physmap_flash_data armadillo5x0_nor_flash_pdata = { + .width = 2, + .parts = armadillo5x0_nor_flash_partitions, + .nr_parts = ARRAY_SIZE(armadillo5x0_nor_flash_partitions), +}; + +static struct resource armadillo5x0_nor_flash_resource = { + .flags = IORESOURCE_MEM, + .start = CS0_BASE_ADDR, + .end = CS0_BASE_ADDR + SZ_64M - 1, +}; + +static struct platform_device armadillo5x0_nor_flash = { + .name = "physmap-flash", + .id = -1, + .num_resources = 1, + .resource = &armadillo5x0_nor_flash_resource, +}; + /* * FB support */ @@ -272,6 +315,10 @@ static void __init armadillo5x0_init(void) /* Register FB */ mxc_register_device(&mx3_ipu, &mx3_ipu_data); mxc_register_device(&mx3_fb, &mx3fb_pdata); + + /* Register NOR Flash */ + mxc_register_device(&armadillo5x0_nor_flash, + &armadillo5x0_nor_flash_pdata); } static void __init armadillo5x0_timer_init(void) From 0c8bad6a26aefbcb7b3d8d1e5d97c53076ac99af Mon Sep 17 00:00:00 2001 From: Alberto Panizzo Date: Wed, 17 Jun 2009 15:06:30 +0200 Subject: [PATCH 0031/1346] Armadillo 500 add NAND flash device support (resend). Since recent mxc_nand driver fixes from linux-mtd this patch add support for ST NAND02GW3B2CN6 (2k pages flash) placed on the armadillo 500 motherboard. Signed-off-by: Alberto Panizzo Signed-off-by: Sascha Hauer --- arch/arm/mach-mx3/armadillo5x0.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/arm/mach-mx3/armadillo5x0.c b/arch/arm/mach-mx3/armadillo5x0.c index 38d99e6c9d0..ee331fd6b1b 100644 --- a/arch/arm/mach-mx3/armadillo5x0.c +++ b/arch/arm/mach-mx3/armadillo5x0.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -47,8 +48,10 @@ #include #include #include +#include #include "devices.h" +#include "crm_regs.h" static int armadillo5x0_pins[] = { /* UART1 */ @@ -94,7 +97,14 @@ static int armadillo5x0_pins[] = { MX31_PIN_FPSHIFT__FPSHIFT, MX31_PIN_DRDY0__DRDY0, IOMUX_MODE(MX31_PIN_LCS1, IOMUX_CONFIG_GPIO), /*ADV7125_PSAVE*/ +}; +/* + * NAND Flash + */ +static struct mxc_nand_platform_data armadillo5x0_nand_flash_pdata = { + .width = 1, + .hw_ecc = 1, }; /* @@ -319,6 +329,12 @@ static void __init armadillo5x0_init(void) /* Register NOR Flash */ mxc_register_device(&armadillo5x0_nor_flash, &armadillo5x0_nor_flash_pdata); + + /* Register NAND Flash */ + mxc_register_device(&mxc_nand_device, &armadillo5x0_nand_flash_pdata); + + /* set NAND page size to 2k if not configured via boot mode pins */ + __raw_writel(__raw_readl(MXC_CCM_RCSR) | (1 << 30), MXC_CCM_RCSR); } static void __init armadillo5x0_timer_init(void) From 32c1ad9ab2ae4171d8f3dd0c70a611f799ad6775 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Thu, 18 Jun 2009 12:40:48 +0200 Subject: [PATCH 0032/1346] pcm037: add MT9T031 camera support Add support for the MT9T031 CMOS camera sensor from Aptina to the PCM037 board. Also add two I2C iomux pin definitions, needed for pcm037. Also remove now unneeded #ifdef CONFIG_I2C_IMX. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Sascha Hauer --- arch/arm/mach-mx3/pcm037.c | 118 ++++++++++++++++++--- arch/arm/plat-mxc/include/mach/iomux-mx3.h | 2 + 2 files changed, 108 insertions(+), 12 deletions(-) diff --git a/arch/arm/mach-mx3/pcm037.c b/arch/arm/mach-mx3/pcm037.c index c6f61a1f06c..d7b29b724a6 100644 --- a/arch/arm/mach-mx3/pcm037.c +++ b/arch/arm/mach-mx3/pcm037.c @@ -18,7 +18,7 @@ #include #include - +#include #include #include #include @@ -33,22 +33,23 @@ #include #include -#include +#include + #include #include #include #include +#include #include +#include +#include #include #include #include -#include +#include +#include #include #include -#include -#ifdef CONFIG_I2C_IMX -#include -#endif #include "devices.h" @@ -56,6 +57,8 @@ static unsigned int pcm037_pins[] = { /* I2C */ MX31_PIN_CSPI2_MOSI__SCL, MX31_PIN_CSPI2_MISO__SDA, + MX31_PIN_CSPI2_SS2__I2C3_SDA, + MX31_PIN_CSPI2_SCLK__I2C3_SCL, /* SDHC1 */ MX31_PIN_SD1_DATA3__SD1_DATA3, MX31_PIN_SD1_DATA2__SD1_DATA2, @@ -120,6 +123,22 @@ static unsigned int pcm037_pins[] = { MX31_PIN_D3_SPL__D3_SPL, MX31_PIN_D3_CLS__D3_CLS, MX31_PIN_LCS0__GPI03_23, + /* CSI */ + IOMUX_MODE(MX31_PIN_CSI_D5, IOMUX_CONFIG_GPIO), + MX31_PIN_CSI_D6__CSI_D6, + MX31_PIN_CSI_D7__CSI_D7, + MX31_PIN_CSI_D8__CSI_D8, + MX31_PIN_CSI_D9__CSI_D9, + MX31_PIN_CSI_D10__CSI_D10, + MX31_PIN_CSI_D11__CSI_D11, + MX31_PIN_CSI_D12__CSI_D12, + MX31_PIN_CSI_D13__CSI_D13, + MX31_PIN_CSI_D14__CSI_D14, + MX31_PIN_CSI_D15__CSI_D15, + MX31_PIN_CSI_HSYNC__CSI_HSYNC, + MX31_PIN_CSI_MCLK__CSI_MCLK, + MX31_PIN_CSI_PIXCLK__CSI_PIXCLK, + MX31_PIN_CSI_VSYNC__CSI_VSYNC, }; static struct physmap_flash_data pcm037_flash_data = { @@ -250,19 +269,43 @@ static struct mxc_nand_platform_data pcm037_nand_board_info = { .hw_ecc = 1, }; -#ifdef CONFIG_I2C_IMX static struct imxi2c_platform_data pcm037_i2c_1_data = { .bitrate = 100000, }; +static struct imxi2c_platform_data pcm037_i2c_2_data = { + .bitrate = 20000, +}; + static struct at24_platform_data board_eeprom = { .byte_len = 4096, .page_size = 32, .flags = AT24_FLAG_ADDR16, }; +static int pcm037_camera_power(struct device *dev, int on) +{ + /* disable or enable the camera in X7 or X8 PCM970 connector */ + gpio_set_value(IOMUX_TO_GPIO(MX31_PIN_CSI_D5), !on); + return 0; +} + +static struct i2c_board_info pcm037_i2c_2_devices[] = { + { + I2C_BOARD_INFO("mt9t031", 0x5d), + }, +}; + +static struct soc_camera_link iclink = { + .bus_id = 0, /* Must match with the camera ID */ + .power = pcm037_camera_power, + .board_info = &pcm037_i2c_2_devices[0], + .i2c_adapter_id = 2, + .module_name = "mt9t031", +}; + static struct i2c_board_info pcm037_i2c_devices[] = { - { + { I2C_BOARD_INFO("at24", 0x52), /* E0=0, E1=1, E2=0 */ .platform_data = &board_eeprom, }, { @@ -270,7 +313,14 @@ static struct i2c_board_info pcm037_i2c_devices[] = { .type = "pcf8563", } }; -#endif + +static struct platform_device pcm037_camera = { + .name = "soc-camera-pdrv", + .id = 0, + .dev = { + .platform_data = &iclink, + }, +}; /* Not connected by default */ #ifdef PCM970_SDHC_RW_SWITCH @@ -334,9 +384,41 @@ static struct imxmmc_platform_data sdhc_pdata = { .exit = pcm970_sdhc1_exit, }; +struct mx3_camera_pdata camera_pdata = { + .dma_dev = &mx3_ipu.dev, + .flags = MX3_CAMERA_DATAWIDTH_8 | MX3_CAMERA_DATAWIDTH_10, + .mclk_10khz = 2000, +}; + +static int __init pcm037_camera_alloc_dma(const size_t buf_size) +{ + dma_addr_t dma_handle; + void *buf; + int dma; + + if (buf_size < 2 * 1024 * 1024) + return -EINVAL; + + buf = dma_alloc_coherent(NULL, buf_size, &dma_handle, GFP_KERNEL); + if (!buf) { + pr_err("%s: cannot allocate camera buffer-memory\n", __func__); + return -ENOMEM; + } + + memset(buf, 0, buf_size); + + dma = dma_declare_coherent_memory(&mx3_camera.dev, + dma_handle, dma_handle, buf_size, + DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE); + + /* The way we call dma_declare_coherent_memory only a malloc can fail */ + return dma & DMA_MEMORY_MAP ? 0 : -ENOMEM; +} + static struct platform_device *devices[] __initdata = { &pcm037_flash, &pcm037_sram_device, + &pcm037_camera, }; static struct ipu_platform_data mx3_ipu_data = { @@ -415,18 +497,30 @@ static void __init mxc_board_init(void) } -#ifdef CONFIG_I2C_IMX + /* I2C adapters and devices */ i2c_register_board_info(1, pcm037_i2c_devices, ARRAY_SIZE(pcm037_i2c_devices)); mxc_register_device(&mxc_i2c_device1, &pcm037_i2c_1_data); -#endif + mxc_register_device(&mxc_i2c_device2, &pcm037_i2c_2_data); + mxc_register_device(&mxc_nand_device, &pcm037_nand_board_info); mxc_register_device(&mxcsdhc_device0, &sdhc_pdata); mxc_register_device(&mx3_ipu, &mx3_ipu_data); mxc_register_device(&mx3_fb, &mx3fb_pdata); if (!gpio_usbotg_hs_activate()) mxc_register_device(&mxc_otg_udc_device, &usb_pdata); + + /* CSI */ + /* Camera power: default - off */ + ret = gpio_request(IOMUX_TO_GPIO(MX31_PIN_CSI_D5), "mt9t031-power"); + if (!ret) + gpio_direction_output(IOMUX_TO_GPIO(MX31_PIN_CSI_D5), 1); + else + iclink.power = NULL; + + if (!pcm037_camera_alloc_dma(4 * 1024 * 1024)) + mxc_register_device(&mx3_camera, &camera_pdata); } static void __init pcm037_timer_init(void) diff --git a/arch/arm/plat-mxc/include/mach/iomux-mx3.h b/arch/arm/plat-mxc/include/mach/iomux-mx3.h index 27f8d1b2bc6..2eb182f7387 100644 --- a/arch/arm/plat-mxc/include/mach/iomux-mx3.h +++ b/arch/arm/plat-mxc/include/mach/iomux-mx3.h @@ -602,6 +602,8 @@ enum iomux_pins { #define MX31_PIN_I2C_DAT__SDA IOMUX_MODE(MX31_PIN_I2C_DAT, IOMUX_CONFIG_FUNC) #define MX31_PIN_DCD_DTE1__I2C2_SDA IOMUX_MODE(MX31_PIN_DCD_DTE1, IOMUX_CONFIG_ALT2) #define MX31_PIN_RI_DTE1__I2C2_SCL IOMUX_MODE(MX31_PIN_RI_DTE1, IOMUX_CONFIG_ALT2) +#define MX31_PIN_CSPI2_SS2__I2C3_SDA IOMUX_MODE(MX31_PIN_CSPI2_SS2, IOMUX_CONFIG_ALT1) +#define MX31_PIN_CSPI2_SCLK__I2C3_SCL IOMUX_MODE(MX31_PIN_CSPI2_SCLK, IOMUX_CONFIG_ALT1) #define MX31_PIN_CSI_D4__CSI_D4 IOMUX_MODE(MX31_PIN_CSI_D4, IOMUX_CONFIG_FUNC) #define MX31_PIN_CSI_D5__CSI_D5 IOMUX_MODE(MX31_PIN_CSI_D5, IOMUX_CONFIG_FUNC) #define MX31_PIN_CSI_D6__CSI_D6 IOMUX_MODE(MX31_PIN_CSI_D6, IOMUX_CONFIG_FUNC) From 574ec547c7771881e18e4e76ca970e323bcdc774 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Tue, 23 Jun 2009 13:26:23 +0200 Subject: [PATCH 0033/1346] ARM: add support for the EET board, based on the i.MX31 pcm037 module The "EET" variant of the pcm037 board has an OLED display, using a S6E63D6 display controller on the first SPI interface, using GPIO57 as a chip-select for it. S6E63D6 is initialised in the boot-loader, so we only have to take care of the LCD. EET also adds several buttons and LEDs on GPIOs. This patch adds a "pcm037_variant=" kernel command line parameter to specify at boot-time which board the kernel is running on, default is "pcm970", specify "eet" for the EET board. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Sascha Hauer --- arch/arm/mach-mx3/Kconfig | 8 ++ arch/arm/mach-mx3/Makefile | 1 + arch/arm/mach-mx3/pcm037.c | 65 ++++++++++- arch/arm/mach-mx3/pcm037.h | 11 ++ arch/arm/mach-mx3/pcm037_eet.c | 204 +++++++++++++++++++++++++++++++++ 5 files changed, 283 insertions(+), 6 deletions(-) create mode 100644 arch/arm/mach-mx3/pcm037.h create mode 100644 arch/arm/mach-mx3/pcm037_eet.c diff --git a/arch/arm/mach-mx3/Kconfig b/arch/arm/mach-mx3/Kconfig index 17a21a291e2..851f2458bf6 100644 --- a/arch/arm/mach-mx3/Kconfig +++ b/arch/arm/mach-mx3/Kconfig @@ -36,6 +36,14 @@ config MACH_PCM037 Include support for Phytec pcm037 platform. This includes specific configurations for the board and its peripherals. +config MACH_PCM037_EET + bool "Support pcm037 EET board extensions" + depends on MACH_PCM037 + help + Add support for PCM037 EET baseboard extensions. If you are using the + OLED display with EET, use "video=mx3fb:CMEL-OLED" kernel + command-line parameter. + config MACH_MX31LITE bool "Support MX31 LITEKIT (LogicPD)" select ARCH_MX31 diff --git a/arch/arm/mach-mx3/Makefile b/arch/arm/mach-mx3/Makefile index 0322696bd11..6b9775471be 100644 --- a/arch/arm/mach-mx3/Makefile +++ b/arch/arm/mach-mx3/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_MACH_MX31ADS) += mx31ads.o obj-$(CONFIG_MACH_MX31LILLY) += mx31lilly.o mx31lilly-db.o obj-$(CONFIG_MACH_MX31LITE) += mx31lite.o obj-$(CONFIG_MACH_PCM037) += pcm037.o +obj-$(CONFIG_MACH_PCM037_EET) += pcm037_eet.o obj-$(CONFIG_MACH_MX31_3DS) += mx31pdk.o obj-$(CONFIG_MACH_MX31MOBOARD) += mx31moboard.o mx31moboard-devboard.o \ mx31moboard-marxbot.o diff --git a/arch/arm/mach-mx3/pcm037.c b/arch/arm/mach-mx3/pcm037.c index d7b29b724a6..840cfda341d 100644 --- a/arch/arm/mach-mx3/pcm037.c +++ b/arch/arm/mach-mx3/pcm037.c @@ -52,6 +52,41 @@ #include #include "devices.h" +#include "pcm037.h" + +static enum pcm037_board_variant pcm037_instance = PCM037_PCM970; + +static int __init pcm037_variant_setup(char *str) +{ + if (!strcmp("eet", str)) + pcm037_instance = PCM037_EET; + else if (strcmp("pcm970", str)) + pr_warning("Unknown pcm037 baseboard variant %s\n", str); + + return 1; +} + +/* Supported values: "pcm970" (default) and "eet" */ +__setup("pcm037_variant=", pcm037_variant_setup); + +enum pcm037_board_variant pcm037_variant(void) +{ + return pcm037_instance; +} + +/* UART1 with RTS/CTS handshake signals */ +static unsigned int pcm037_uart1_handshake_pins[] = { + MX31_PIN_CTS1__CTS1, + MX31_PIN_RTS1__RTS1, + MX31_PIN_TXD1__TXD1, + MX31_PIN_RXD1__RXD1, +}; + +/* UART1 without RTS/CTS handshake signals */ +static unsigned int pcm037_uart1_pins[] = { + MX31_PIN_TXD1__TXD1, + MX31_PIN_RXD1__RXD1, +}; static unsigned int pcm037_pins[] = { /* I2C */ @@ -76,11 +111,6 @@ static unsigned int pcm037_pins[] = { MX31_PIN_CSPI1_SS0__SS0, MX31_PIN_CSPI1_SS1__SS1, MX31_PIN_CSPI1_SS2__SS2, - /* UART1 */ - MX31_PIN_CTS1__CTS1, - MX31_PIN_RTS1__RTS1, - MX31_PIN_TXD1__TXD1, - MX31_PIN_RXD1__RXD1, /* UART2 */ MX31_PIN_TXD2__TXD2, MX31_PIN_RXD2__RXD2, @@ -459,6 +489,22 @@ static const struct fb_videomode fb_modedb[] = { .sync = FB_SYNC_VERT_HIGH_ACT | FB_SYNC_OE_ACT_HIGH, .vmode = FB_VMODE_NONINTERLACED, .flag = 0, + }, { + /* 240x320 @ 60 Hz */ + .name = "CMEL-OLED", + .refresh = 60, + .xres = 240, + .yres = 320, + .pixclock = 185925, + .left_margin = 9, + .right_margin = 16, + .upper_margin = 7, + .lower_margin = 9, + .hsync_len = 1, + .vsync_len = 1, + .sync = FB_SYNC_OE_ACT_HIGH | FB_SYNC_CLK_INVERT, + .vmode = FB_VMODE_NONINTERLACED, + .flag = 0, }, }; @@ -479,6 +525,14 @@ static void __init mxc_board_init(void) mxc_iomux_setup_multiple_pins(pcm037_pins, ARRAY_SIZE(pcm037_pins), "pcm037"); + if (pcm037_variant() == PCM037_EET) + mxc_iomux_setup_multiple_pins(pcm037_uart1_pins, + ARRAY_SIZE(pcm037_uart1_pins), "pcm037_uart1"); + else + mxc_iomux_setup_multiple_pins(pcm037_uart1_handshake_pins, + ARRAY_SIZE(pcm037_uart1_handshake_pins), + "pcm037_uart1"); + platform_add_devices(devices, ARRAY_SIZE(devices)); mxc_register_device(&mxc_uart_device0, &uart_pdata); @@ -542,4 +596,3 @@ MACHINE_START(PCM037, "Phytec Phycore pcm037") .init_machine = mxc_board_init, .timer = &pcm037_timer, MACHINE_END - diff --git a/arch/arm/mach-mx3/pcm037.h b/arch/arm/mach-mx3/pcm037.h new file mode 100644 index 00000000000..d6929721a5f --- /dev/null +++ b/arch/arm/mach-mx3/pcm037.h @@ -0,0 +1,11 @@ +#ifndef __PCM037_H__ +#define __PCM037_H__ + +enum pcm037_board_variant { + PCM037_PCM970, + PCM037_EET, +}; + +extern enum pcm037_board_variant pcm037_variant(void); + +#endif diff --git a/arch/arm/mach-mx3/pcm037_eet.c b/arch/arm/mach-mx3/pcm037_eet.c new file mode 100644 index 00000000000..fe52fb1bb8b --- /dev/null +++ b/arch/arm/mach-mx3/pcm037_eet.c @@ -0,0 +1,204 @@ +/* + * Copyright (C) 2009 + * Guennadi Liakhovetski, DENX Software Engineering, + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include + +#include +#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE) +#include +#endif +#include + +#include + +#include "pcm037.h" +#include "devices.h" + +static unsigned int pcm037_eet_pins[] = { + /* SPI #1 */ + MX31_PIN_CSPI1_MISO__MISO, + MX31_PIN_CSPI1_MOSI__MOSI, + MX31_PIN_CSPI1_SCLK__SCLK, + MX31_PIN_CSPI1_SPI_RDY__SPI_RDY, + MX31_PIN_CSPI1_SS0__SS0, + MX31_PIN_CSPI1_SS1__SS1, + MX31_PIN_CSPI1_SS2__SS2, + + /* Reserve and hardwire GPIO 57 high - S6E63D6 chipselect */ + IOMUX_MODE(MX31_PIN_KEY_COL7, IOMUX_CONFIG_GPIO), + /* GPIO keys */ + IOMUX_MODE(MX31_PIN_GPIO1_0, IOMUX_CONFIG_GPIO), /* 0 */ + IOMUX_MODE(MX31_PIN_GPIO1_1, IOMUX_CONFIG_GPIO), /* 1 */ + IOMUX_MODE(MX31_PIN_GPIO1_2, IOMUX_CONFIG_GPIO), /* 2 */ + IOMUX_MODE(MX31_PIN_GPIO1_3, IOMUX_CONFIG_GPIO), /* 3 */ + IOMUX_MODE(MX31_PIN_SVEN0, IOMUX_CONFIG_GPIO), /* 32 */ + IOMUX_MODE(MX31_PIN_STX0, IOMUX_CONFIG_GPIO), /* 33 */ + IOMUX_MODE(MX31_PIN_SRX0, IOMUX_CONFIG_GPIO), /* 34 */ + IOMUX_MODE(MX31_PIN_SIMPD0, IOMUX_CONFIG_GPIO), /* 35 */ + IOMUX_MODE(MX31_PIN_RTS1, IOMUX_CONFIG_GPIO), /* 38 */ + IOMUX_MODE(MX31_PIN_CTS1, IOMUX_CONFIG_GPIO), /* 39 */ + IOMUX_MODE(MX31_PIN_KEY_ROW4, IOMUX_CONFIG_GPIO), /* 50 */ + IOMUX_MODE(MX31_PIN_KEY_ROW5, IOMUX_CONFIG_GPIO), /* 51 */ + IOMUX_MODE(MX31_PIN_KEY_ROW6, IOMUX_CONFIG_GPIO), /* 52 */ + IOMUX_MODE(MX31_PIN_KEY_ROW7, IOMUX_CONFIG_GPIO), /* 53 */ + + /* LEDs */ + IOMUX_MODE(MX31_PIN_DTR_DTE1, IOMUX_CONFIG_GPIO), /* 44 */ + IOMUX_MODE(MX31_PIN_DSR_DTE1, IOMUX_CONFIG_GPIO), /* 45 */ + IOMUX_MODE(MX31_PIN_KEY_COL5, IOMUX_CONFIG_GPIO), /* 55 */ + IOMUX_MODE(MX31_PIN_KEY_COL6, IOMUX_CONFIG_GPIO), /* 56 */ +}; + +/* SPI */ +static struct spi_board_info pcm037_spi_dev[] = { + { + .modalias = "dac124s085", + .max_speed_hz = 400000, + .bus_num = 0, + .chip_select = 0, /* Index in pcm037_spi1_cs[] */ + .mode = SPI_CPHA, + }, +}; + +/* Platform Data for MXC CSPI */ +#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE) +static int pcm037_spi1_cs[] = {MXC_SPI_CS(1), IOMUX_TO_GPIO(MX31_PIN_KEY_COL7)}; + +struct spi_imx_master pcm037_spi1_master = { + .chipselect = pcm037_spi1_cs, + .num_chipselect = ARRAY_SIZE(pcm037_spi1_cs), +}; +#endif + +/* GPIO-keys input device */ +static struct gpio_keys_button pcm037_gpio_keys[] = { + { + .type = EV_KEY, + .code = KEY_L, + .gpio = 0, + .desc = "Wheel Manual", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_A, + .gpio = 1, + .desc = "Wheel AF", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_V, + .gpio = 2, + .desc = "Wheel View", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_M, + .gpio = 3, + .desc = "Wheel Menu", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_UP, + .gpio = 32, + .desc = "Nav Pad Up", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_RIGHT, + .gpio = 33, + .desc = "Nav Pad Right", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_DOWN, + .gpio = 34, + .desc = "Nav Pad Down", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_LEFT, + .gpio = 35, + .desc = "Nav Pad Left", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_ENTER, + .gpio = 38, + .desc = "Nav Pad Ok", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = KEY_O, + .gpio = 39, + .desc = "Wheel Off", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = BTN_FORWARD, + .gpio = 50, + .desc = "Focus Forward", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = BTN_BACK, + .gpio = 51, + .desc = "Focus Backward", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = BTN_MIDDLE, + .gpio = 52, + .desc = "Release Half", + .wakeup = 0, + }, { + .type = EV_KEY, + .code = BTN_EXTRA, + .gpio = 53, + .desc = "Release Full", + .wakeup = 0, + }, +}; + +static struct gpio_keys_platform_data pcm037_gpio_keys_platform_data = { + .buttons = pcm037_gpio_keys, + .nbuttons = ARRAY_SIZE(pcm037_gpio_keys), + .rep = 0, /* No auto-repeat */ +}; + +static struct platform_device pcm037_gpio_keys_device = { + .name = "gpio-keys", + .id = -1, + .dev = { + .platform_data = &pcm037_gpio_keys_platform_data, + }, +}; + +static int eet_init_devices(void) +{ + if (!machine_is_pcm037() || pcm037_variant() != PCM037_EET) + return 0; + + mxc_iomux_setup_multiple_pins(pcm037_eet_pins, + ARRAY_SIZE(pcm037_eet_pins), "pcm037_eet"); + + /* SPI */ + spi_register_board_info(pcm037_spi_dev, ARRAY_SIZE(pcm037_spi_dev)); +#if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE) + mxc_register_device(&mxc_spi_device0, &pcm037_spi1_master); +#endif + + platform_device_register(&pcm037_gpio_keys_device); + + return 0; +} + +late_initcall(eet_init_devices); From 2a13877c5ef3207a2a5c56250742e60808677f90 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Fri, 10 Apr 2009 07:50:45 -0400 Subject: [PATCH 0034/1346] osdblk: a Linux block device for OSD objects Submitted driver exports a block device of the form /dev/osdblkX, where X is a decimal number. It does that by mounting a stacking block device on top of an osd object. For example, if you create a 2G object on an OSD device, you can then use this module to present that 2G object as a Linux block device. See inside patch for exact documentation. [Sitting at linux-next helped fix proper Kconfig dependency for this driver, thanks to Randy Dunlap] Signed-off-by: Jeff Garzik Signed-off-by: Boaz Harrosh --- drivers/block/Kconfig | 16 + drivers/block/Makefile | 1 + drivers/block/osdblk.c | 694 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 711 insertions(+) create mode 100644 drivers/block/osdblk.c diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index bb72ada9f07..1d886e079c5 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -298,6 +298,22 @@ config BLK_DEV_NBD If unsure, say N. +config BLK_DEV_OSD + tristate "OSD object-as-blkdev support" + depends on SCSI_OSD_ULD + ---help--- + Saying Y or M here will allow the exporting of a single SCSI + OSD (object-based storage) object as a Linux block device. + + For example, if you create a 2G object on an OSD device, + you can then use this module to present that 2G object as + a Linux block device. + + To compile this driver as a module, choose M here: the + module will be called osdblk. + + If unsure, say N. + config BLK_DEV_SX8 tristate "Promise SATA SX8 support" depends on PCI diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 7755a5e2a85..cdaa3f8fddf 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_XILINX_SYSACE) += xsysace.o obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o obj-$(CONFIG_MG_DISK) += mg_disk.o obj-$(CONFIG_SUNVDC) += sunvdc.o +obj-$(CONFIG_BLK_DEV_OSD) += osdblk.o obj-$(CONFIG_BLK_DEV_UMEM) += umem.o obj-$(CONFIG_BLK_DEV_NBD) += nbd.o diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c new file mode 100644 index 00000000000..3565d0dd123 --- /dev/null +++ b/drivers/block/osdblk.c @@ -0,0 +1,694 @@ + +/* + osdblk.c -- Export a single SCSI OSD object as a Linux block device + + + Copyright 2009 Red Hat, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; see the file COPYING. If not, write to + the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. + + + Instructions for use + -------------------- + + 1) Map a Linux block device to an existing OSD object. + + In this example, we will use partition id 1234, object id 5678, + OSD device /dev/osd1. + + $ echo "1234 5678 /dev/osd1" > /sys/class/osdblk/add + + + 2) List all active blkdev<->object mappings. + + In this example, we have performed step #1 twice, creating two blkdevs, + mapped to two separate OSD objects. + + $ cat /sys/class/osdblk/list + 0 174 1234 5678 /dev/osd1 + 1 179 1994 897123 /dev/osd0 + + The columns, in order, are: + - blkdev unique id + - blkdev assigned major + - OSD object partition id + - OSD object id + - OSD device + + + 3) Remove an active blkdev<->object mapping. + + In this example, we remove the mapping with blkdev unique id 1. + + $ echo 1 > /sys/class/osdblk/remove + + + NOTE: The actual creation and deletion of OSD objects is outside the scope + of this driver. + + */ + +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "osdblk" +#define PFX DRV_NAME ": " + +/* #define _OSDBLK_DEBUG */ +#ifdef _OSDBLK_DEBUG +#define OSDBLK_DEBUG(fmt, a...) \ + printk(KERN_NOTICE "osdblk @%s:%d: " fmt, __func__, __LINE__, ##a) +#else +#define OSDBLK_DEBUG(fmt, a...) \ + do { if (0) printk(fmt, ##a); } while (0) +#endif + +MODULE_AUTHOR("Jeff Garzik "); +MODULE_DESCRIPTION("block device inside an OSD object osdblk.ko"); +MODULE_LICENSE("GPL"); + +struct osdblk_device; + +enum { + OSDBLK_MINORS_PER_MAJOR = 256, /* max minors per blkdev */ + OSDBLK_MAX_REQ = 32, /* max parallel requests */ + OSDBLK_OP_TIMEOUT = 4 * 60, /* sync OSD req timeout */ +}; + +struct osdblk_request { + struct request *rq; /* blk layer request */ + struct bio *bio; /* cloned bio */ + struct osdblk_device *osdev; /* associated blkdev */ +}; + +struct osdblk_device { + int id; /* blkdev unique id */ + + int major; /* blkdev assigned major */ + struct gendisk *disk; /* blkdev's gendisk and rq */ + struct request_queue *q; + + struct osd_dev *osd; /* associated OSD */ + + char name[32]; /* blkdev name, e.g. osdblk34 */ + + spinlock_t lock; /* queue lock */ + + struct osd_obj_id obj; /* OSD partition, obj id */ + uint8_t obj_cred[OSD_CAP_LEN]; /* OSD cred */ + + struct osdblk_request req[OSDBLK_MAX_REQ]; /* request table */ + + struct list_head node; + + char osd_path[0]; /* OSD device path */ +}; + +static struct class *class_osdblk; /* /sys/class/osdblk */ +static DEFINE_MUTEX(ctl_mutex); /* Serialize open/close/setup/teardown */ +static LIST_HEAD(osdblkdev_list); + +static struct block_device_operations osdblk_bd_ops = { + .owner = THIS_MODULE, +}; + +static const struct osd_attr g_attr_logical_length = ATTR_DEF( + OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8); + +static void osdblk_make_credential(u8 cred_a[OSD_CAP_LEN], + const struct osd_obj_id *obj) +{ + osd_sec_init_nosec_doall_caps(cred_a, obj, false, true); +} + +/* copied from exofs; move to libosd? */ +/* + * Perform a synchronous OSD operation. copied from exofs; move to libosd? + */ +static int osd_sync_op(struct osd_request *or, int timeout, uint8_t *credential) +{ + int ret; + + or->timeout = timeout; + ret = osd_finalize_request(or, 0, credential, NULL); + if (ret) + return ret; + + ret = osd_execute_request(or); + + /* osd_req_decode_sense(or, ret); */ + return ret; +} + +/* + * Perform an asynchronous OSD operation. copied from exofs; move to libosd? + */ +static int osd_async_op(struct osd_request *or, osd_req_done_fn *async_done, + void *caller_context, u8 *cred) +{ + int ret; + + ret = osd_finalize_request(or, 0, cred, NULL); + if (ret) + return ret; + + ret = osd_execute_request_async(or, async_done, caller_context); + + return ret; +} + +/* copied from exofs; move to libosd? */ +static int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr) +{ + struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */ + void *iter = NULL; + int nelem; + + do { + nelem = 1; + osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter); + if ((cur_attr.attr_page == attr->attr_page) && + (cur_attr.attr_id == attr->attr_id)) { + attr->len = cur_attr.len; + attr->val_ptr = cur_attr.val_ptr; + return 0; + } + } while (iter); + + return -EIO; +} + +static int osdblk_get_obj_size(struct osdblk_device *osdev, u64 *size_out) +{ + struct osd_request *or; + struct osd_attr attr; + int ret; + + /* start request */ + or = osd_start_request(osdev->osd, GFP_KERNEL); + if (!or) + return -ENOMEM; + + /* create a get-attributes(length) request */ + osd_req_get_attributes(or, &osdev->obj); + + osd_req_add_get_attr_list(or, &g_attr_logical_length, 1); + + /* execute op synchronously */ + ret = osd_sync_op(or, OSDBLK_OP_TIMEOUT, osdev->obj_cred); + if (ret) + goto out; + + /* extract length from returned attribute info */ + attr = g_attr_logical_length; + ret = extract_attr_from_req(or, &attr); + if (ret) + goto out; + + *size_out = get_unaligned_be64(attr.val_ptr); + +out: + osd_end_request(or); + return ret; + +} + +static void osdblk_osd_complete(struct osd_request *or, void *private) +{ + struct osdblk_request *orq = private; + struct osd_sense_info osi; + int ret = osd_req_decode_sense(or, &osi); + + if (ret) { + ret = -EIO; + OSDBLK_DEBUG("osdblk_osd_complete with err=%d\n", ret); + } + + /* complete OSD request */ + osd_end_request(or); + + /* complete request passed to osdblk by block layer */ + __blk_end_request_all(orq->rq, ret); +} + +static void bio_chain_put(struct bio *chain) +{ + struct bio *tmp; + + while (chain) { + tmp = chain; + chain = chain->bi_next; + + bio_put(tmp); + } +} + +static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask) +{ + struct bio *tmp, *new_chain = NULL, *tail = NULL; + + while (old_chain) { + tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs); + if (!tmp) + goto err_out; + + __bio_clone(tmp, old_chain); + tmp->bi_bdev = NULL; + gfpmask &= ~__GFP_WAIT; + tmp->bi_next = NULL; + + if (!new_chain) + new_chain = tail = tmp; + else { + tail->bi_next = tmp; + tail = tmp; + } + + old_chain = old_chain->bi_next; + } + + return new_chain; + +err_out: + OSDBLK_DEBUG("bio_chain_clone with err\n"); + bio_chain_put(new_chain); + return NULL; +} + +static void osdblk_rq_fn(struct request_queue *q) +{ + struct osdblk_device *osdev = q->queuedata; + + while (1) { + struct request *rq; + struct osdblk_request *orq; + struct osd_request *or; + struct bio *bio; + bool do_write, do_flush; + + /* peek at request from block layer */ + rq = blk_fetch_request(q); + if (!rq) + break; + + /* filter out block requests we don't understand */ + if (!blk_fs_request(rq) && !blk_barrier_rq(rq)) { + blk_end_request_all(rq, 0); + continue; + } + + /* deduce our operation (read, write, flush) */ + /* I wish the block layer simplified cmd_type/cmd_flags/cmd[] + * into a clearly defined set of RPC commands: + * read, write, flush, scsi command, power mgmt req, + * driver-specific, etc. + */ + + do_flush = (rq->special == (void *) 0xdeadbeefUL); + do_write = (rq_data_dir(rq) == WRITE); + + if (!do_flush) { /* osd_flush does not use a bio */ + /* a bio clone to be passed down to OSD request */ + bio = bio_chain_clone(rq->bio, GFP_ATOMIC); + if (!bio) + break; + } else + bio = NULL; + + /* alloc internal OSD request, for OSD command execution */ + or = osd_start_request(osdev->osd, GFP_ATOMIC); + if (!or) { + bio_chain_put(bio); + OSDBLK_DEBUG("osd_start_request with err\n"); + break; + } + + orq = &osdev->req[rq->tag]; + orq->rq = rq; + orq->bio = bio; + orq->osdev = osdev; + + /* init OSD command: flush, write or read */ + if (do_flush) + osd_req_flush_object(or, &osdev->obj, + OSD_CDB_FLUSH_ALL, 0, 0); + else if (do_write) + osd_req_write(or, &osdev->obj, blk_rq_pos(rq) * 512ULL, + bio, blk_rq_bytes(rq)); + else + osd_req_read(or, &osdev->obj, blk_rq_pos(rq) * 512ULL, + bio, blk_rq_bytes(rq)); + + OSDBLK_DEBUG("%s 0x%x bytes at 0x%llx\n", + do_flush ? "flush" : do_write ? + "write" : "read", blk_rq_bytes(rq), + blk_rq_pos(rq) * 512ULL); + + /* begin OSD command execution */ + if (osd_async_op(or, osdblk_osd_complete, orq, + osdev->obj_cred)) { + osd_end_request(or); + blk_requeue_request(q, rq); + bio_chain_put(bio); + OSDBLK_DEBUG("osd_execute_request_async with err\n"); + break; + } + + /* remove the special 'flush' marker, now that the command + * is executing + */ + rq->special = NULL; + } +} + +static void osdblk_prepare_flush(struct request_queue *q, struct request *rq) +{ + /* add driver-specific marker, to indicate that this request + * is a flush command + */ + rq->special = (void *) 0xdeadbeefUL; +} + +static void osdblk_free_disk(struct osdblk_device *osdev) +{ + struct gendisk *disk = osdev->disk; + + if (!disk) + return; + + if (disk->flags & GENHD_FL_UP) + del_gendisk(disk); + if (disk->queue) + blk_cleanup_queue(disk->queue); + put_disk(disk); +} + +static int osdblk_init_disk(struct osdblk_device *osdev) +{ + struct gendisk *disk; + struct request_queue *q; + int rc; + u64 obj_size = 0; + + /* contact OSD, request size info about the object being mapped */ + rc = osdblk_get_obj_size(osdev, &obj_size); + if (rc) + return rc; + + /* create gendisk info */ + disk = alloc_disk(OSDBLK_MINORS_PER_MAJOR); + if (!disk) + return -ENOMEM; + + sprintf(disk->disk_name, DRV_NAME "%d", osdev->id); + disk->major = osdev->major; + disk->first_minor = 0; + disk->fops = &osdblk_bd_ops; + disk->private_data = osdev; + + /* init rq */ + q = blk_init_queue(osdblk_rq_fn, &osdev->lock); + if (!q) { + put_disk(disk); + return -ENOMEM; + } + + /* switch queue to TCQ mode; allocate tag map */ + rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL); + if (rc) { + blk_cleanup_queue(q); + put_disk(disk); + return rc; + } + + blk_queue_prep_rq(q, blk_queue_start_tag); + blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, osdblk_prepare_flush); + + disk->queue = q; + + q->queuedata = osdev; + + osdev->disk = disk; + osdev->q = q; + + /* finally, announce the disk to the world */ + set_capacity(disk, obj_size / 512ULL); + add_disk(disk); + + printk(KERN_INFO "%s: Added of size 0x%llx\n", + disk->disk_name, (unsigned long long)obj_size); + + return 0; +} + +/******************************************************************** + * /sys/class/osdblk/ + * add map OSD object to blkdev + * remove unmap OSD object + * list show mappings + *******************************************************************/ + +static void class_osdblk_release(struct class *cls) +{ + kfree(cls); +} + +static ssize_t class_osdblk_list(struct class *c, char *data) +{ + int n = 0; + struct list_head *tmp; + + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + + list_for_each(tmp, &osdblkdev_list) { + struct osdblk_device *osdev; + + osdev = list_entry(tmp, struct osdblk_device, node); + + n += sprintf(data+n, "%d %d %llu %llu %s\n", + osdev->id, + osdev->major, + osdev->obj.partition, + osdev->obj.id, + osdev->osd_path); + } + + mutex_unlock(&ctl_mutex); + return n; +} + +static ssize_t class_osdblk_add(struct class *c, const char *buf, size_t count) +{ + struct osdblk_device *osdev; + ssize_t rc; + int irc, new_id = 0; + struct list_head *tmp; + + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + /* new osdblk_device object */ + osdev = kzalloc(sizeof(*osdev) + strlen(buf) + 1, GFP_KERNEL); + if (!osdev) { + rc = -ENOMEM; + goto err_out_mod; + } + + /* static osdblk_device initialization */ + spin_lock_init(&osdev->lock); + INIT_LIST_HEAD(&osdev->node); + + /* generate unique id: find highest unique id, add one */ + + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + + list_for_each(tmp, &osdblkdev_list) { + struct osdblk_device *osdev; + + osdev = list_entry(tmp, struct osdblk_device, node); + if (osdev->id > new_id) + new_id = osdev->id + 1; + } + + osdev->id = new_id; + + /* add to global list */ + list_add_tail(&osdev->node, &osdblkdev_list); + + mutex_unlock(&ctl_mutex); + + /* parse add command */ + if (sscanf(buf, "%llu %llu %s", &osdev->obj.partition, &osdev->obj.id, + osdev->osd_path) != 3) { + rc = -EINVAL; + goto err_out_slot; + } + + /* initialize rest of new object */ + sprintf(osdev->name, DRV_NAME "%d", osdev->id); + + /* contact requested OSD */ + osdev->osd = osduld_path_lookup(osdev->osd_path); + if (IS_ERR(osdev->osd)) { + rc = PTR_ERR(osdev->osd); + goto err_out_slot; + } + + /* build OSD credential */ + osdblk_make_credential(osdev->obj_cred, &osdev->obj); + + /* register our block device */ + irc = register_blkdev(0, osdev->name); + if (irc < 0) { + rc = irc; + goto err_out_osd; + } + + osdev->major = irc; + + /* set up and announce blkdev mapping */ + rc = osdblk_init_disk(osdev); + if (rc) + goto err_out_blkdev; + + return count; + +err_out_blkdev: + unregister_blkdev(osdev->major, osdev->name); +err_out_osd: + osduld_put_device(osdev->osd); +err_out_slot: + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + list_del_init(&osdev->node); + mutex_unlock(&ctl_mutex); + + kfree(osdev); +err_out_mod: + OSDBLK_DEBUG("Error adding device %s\n", buf); + module_put(THIS_MODULE); + return rc; +} + +static ssize_t class_osdblk_remove(struct class *c, const char *buf, + size_t count) +{ + struct osdblk_device *osdev = NULL; + int target_id, rc; + unsigned long ul; + struct list_head *tmp; + + rc = strict_strtoul(buf, 10, &ul); + if (rc) + return rc; + + /* convert to int; abort if we lost anything in the conversion */ + target_id = (int) ul; + if (target_id != ul) + return -EINVAL; + + /* remove object from list immediately */ + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + + list_for_each(tmp, &osdblkdev_list) { + osdev = list_entry(tmp, struct osdblk_device, node); + if (osdev->id == target_id) { + list_del_init(&osdev->node); + break; + } + osdev = NULL; + } + + mutex_unlock(&ctl_mutex); + + if (!osdev) + return -ENOENT; + + /* clean up and free blkdev and associated OSD connection */ + osdblk_free_disk(osdev); + unregister_blkdev(osdev->major, osdev->name); + osduld_put_device(osdev->osd); + kfree(osdev); + + /* release module ref */ + module_put(THIS_MODULE); + + return count; +} + +static struct class_attribute class_osdblk_attrs[] = { + __ATTR(add, 0200, NULL, class_osdblk_add), + __ATTR(remove, 0200, NULL, class_osdblk_remove), + __ATTR(list, 0444, class_osdblk_list, NULL), + __ATTR_NULL +}; + +static int osdblk_sysfs_init(void) +{ + int ret = 0; + + /* + * create control files in sysfs + * /sys/class/osdblk/... + */ + class_osdblk = kzalloc(sizeof(*class_osdblk), GFP_KERNEL); + if (!class_osdblk) + return -ENOMEM; + + class_osdblk->name = DRV_NAME; + class_osdblk->owner = THIS_MODULE; + class_osdblk->class_release = class_osdblk_release; + class_osdblk->class_attrs = class_osdblk_attrs; + + ret = class_register(class_osdblk); + if (ret) { + kfree(class_osdblk); + class_osdblk = NULL; + printk(PFX "failed to create class osdblk\n"); + return ret; + } + + return 0; +} + +static void osdblk_sysfs_cleanup(void) +{ + if (class_osdblk) + class_destroy(class_osdblk); + class_osdblk = NULL; +} + +static int __init osdblk_init(void) +{ + int rc; + + rc = osdblk_sysfs_init(); + if (rc) + return rc; + + return 0; +} + +static void __exit osdblk_exit(void) +{ + osdblk_sysfs_cleanup(); +} + +module_init(osdblk_init); +module_exit(osdblk_exit); + From bc47df0fa705887242c26c7b040e7cf0170ab1f1 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Wed, 20 May 2009 18:50:34 +0300 Subject: [PATCH 0035/1346] osdblk: Adjust queue limits to lower device's limits call blk_queue_stack_limits() to copy queue limits from the underline osd scsi_device. This is absolutely needed because osdblk cannot sleep when allocating a lower-request and therefore cannot be bouncing. TODO: Dynamic changes of limits to the lower device queue will not reflect in the upper driver Signed-off-by: Boaz Harrosh --- drivers/block/osdblk.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 3565d0dd123..13c1aee6aa3 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -66,6 +66,7 @@ #include #include #include +#include #define DRV_NAME "osdblk" #define PFX DRV_NAME ": " @@ -437,6 +438,12 @@ static int osdblk_init_disk(struct osdblk_device *osdev) return rc; } + /* Set our limits to the lower device limits, because osdblk cannot + * sleep when allocating a lower-request and therefore cannot be + * bouncing. + */ + blk_queue_stack_limits(q, osd_request_queue(osdev->osd)); + blk_queue_prep_rq(q, blk_queue_start_tag); blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, osdblk_prepare_flush); From f6faac71d502be1c29c81b2f45657662c3b84470 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 23 Jun 2009 17:24:40 -0700 Subject: [PATCH 0036/1346] rcu: Mark Hierarchical RCU no longer experimental Removes the warnings about Hierarchical RCU being experimental, given that it has gone through almost six months of being the default RCU in mainline for the x86 with very little trouble. This makes hierarchical-RCU bootup look less scary. Signed-off-by: Paul E. McKenney Cc: akpm@linux-foundation.org Cc: niv@us.ibm.com Cc: dvhltc@us.ibm.com Cc: dipankar@in.ibm.com Cc: dhowells@redhat.com Cc: lethal@linux-sh.org Cc: kernel@wantstofly.org Cc: cl@linux-foundation.org Cc: schamp@sgi.com Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 0dccfbba6d2..7717b95c202 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1533,7 +1533,7 @@ void __init __rcu_init(void) int j; struct rcu_node *rnp; - printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n"); + printk(KERN_INFO "Hierarchical RCU implementation.\n"); #ifdef CONFIG_RCU_CPU_STALL_DETECTOR printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n"); #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ @@ -1546,7 +1546,6 @@ void __init __rcu_init(void) rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i); /* Register notifier for non-boot CPUs */ register_cpu_notifier(&rcu_nb); - printk(KERN_WARNING "Experimental hierarchical RCU init done.\n"); } module_param(blimit, int, 0); From 6fdc03709433ccc2005f0f593ae9d9dd04f7b485 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sat, 20 Jun 2009 13:23:59 +0200 Subject: [PATCH 0037/1346] firewire: core: do not DMA-map stack addresses The DMA mapping API cannot map on-stack addresses, as explained in Documentation/DMA-mapping.txt. Convert the two cases of on-stack packet payload buffers in firewire-core (payload of lock requests in the bus manager work and in iso resource management) to slab-allocated memory. There are a number on-stack buffers for quadlet write or quadlet read requests in firewire-core and firewire-sbp2. These are harmless; they are copied to/ from card driver internal DMA buffers since quadlet payloads are inlined with packet headers. Signed-off-by: Stefan Richter --- drivers/firewire/core-card.c | 14 +++++++------- drivers/firewire/core-cdev.c | 4 +++- drivers/firewire/core-iso.c | 24 +++++++++++++----------- drivers/firewire/core.h | 3 ++- include/linux/firewire.h | 1 + 5 files changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 543fccac81b..f74edae5cb4 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -196,8 +196,8 @@ static void allocate_broadcast_channel(struct fw_card *card, int generation) { int channel, bandwidth = 0; - fw_iso_resource_manage(card, generation, 1ULL << 31, - &channel, &bandwidth, true); + fw_iso_resource_manage(card, generation, 1ULL << 31, &channel, + &bandwidth, true, card->bm_transaction_data); if (channel == 31) { card->broadcast_channel_allocated = true; device_for_each_child(card->device, (void *)(long)generation, @@ -230,7 +230,6 @@ static void fw_card_bm_work(struct work_struct *work) bool do_reset = false; bool root_device_is_running; bool root_device_is_cmc; - __be32 lock_data[2]; spin_lock_irqsave(&card->lock, flags); @@ -273,22 +272,23 @@ static void fw_card_bm_work(struct work_struct *work) goto pick_me; } - lock_data[0] = cpu_to_be32(0x3f); - lock_data[1] = cpu_to_be32(local_id); + card->bm_transaction_data[0] = cpu_to_be32(0x3f); + card->bm_transaction_data[1] = cpu_to_be32(local_id); spin_unlock_irqrestore(&card->lock, flags); rcode = fw_run_transaction(card, TCODE_LOCK_COMPARE_SWAP, irm_id, generation, SCODE_100, CSR_REGISTER_BASE + CSR_BUS_MANAGER_ID, - lock_data, sizeof(lock_data)); + card->bm_transaction_data, + sizeof(card->bm_transaction_data)); if (rcode == RCODE_GENERATION) /* Another bus reset, BM work has been rescheduled. */ goto out; if (rcode == RCODE_COMPLETE && - lock_data[0] != cpu_to_be32(0x3f)) { + card->bm_transaction_data[0] != cpu_to_be32(0x3f)) { /* Somebody else is BM. Only act as IRM. */ if (local_id == irm_id) diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index d1d30c615b0..ced186d7e9a 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -125,6 +125,7 @@ struct iso_resource { int generation; u64 channels; s32 bandwidth; + __be32 transaction_data[2]; struct iso_resource_event *e_alloc, *e_dealloc; }; @@ -1049,7 +1050,8 @@ static void iso_resource_work(struct work_struct *work) r->channels, &channel, &bandwidth, todo == ISO_RES_ALLOC || todo == ISO_RES_REALLOC || - todo == ISO_RES_ALLOC_ONCE); + todo == ISO_RES_ALLOC_ONCE, + r->transaction_data); /* * Is this generation outdated already? As long as this resource sticks * in the idr, it will be scheduled again for a newer generation or at diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 166f19c6d38..110e731f557 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -177,9 +177,8 @@ EXPORT_SYMBOL(fw_iso_context_stop); */ static int manage_bandwidth(struct fw_card *card, int irm_id, int generation, - int bandwidth, bool allocate) + int bandwidth, bool allocate, __be32 data[2]) { - __be32 data[2]; int try, new, old = allocate ? BANDWIDTH_AVAILABLE_INITIAL : 0; /* @@ -215,9 +214,9 @@ static int manage_bandwidth(struct fw_card *card, int irm_id, int generation, } static int manage_channel(struct fw_card *card, int irm_id, int generation, - u32 channels_mask, u64 offset, bool allocate) + u32 channels_mask, u64 offset, bool allocate, __be32 data[2]) { - __be32 data[2], c, all, old; + __be32 c, all, old; int i, retry = 5; old = all = allocate ? cpu_to_be32(~0) : 0; @@ -260,7 +259,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation, } static void deallocate_channel(struct fw_card *card, int irm_id, - int generation, int channel) + int generation, int channel, __be32 buffer[2]) { u32 mask; u64 offset; @@ -269,7 +268,7 @@ static void deallocate_channel(struct fw_card *card, int irm_id, offset = channel < 32 ? CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI : CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO; - manage_channel(card, irm_id, generation, mask, offset, false); + manage_channel(card, irm_id, generation, mask, offset, false, buffer); } /** @@ -298,7 +297,7 @@ static void deallocate_channel(struct fw_card *card, int irm_id, */ void fw_iso_resource_manage(struct fw_card *card, int generation, u64 channels_mask, int *channel, int *bandwidth, - bool allocate) + bool allocate, __be32 buffer[2]) { u32 channels_hi = channels_mask; /* channels 31...0 */ u32 channels_lo = channels_mask >> 32; /* channels 63...32 */ @@ -310,10 +309,12 @@ void fw_iso_resource_manage(struct fw_card *card, int generation, if (channels_hi) c = manage_channel(card, irm_id, generation, channels_hi, - CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI, allocate); + CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI, + allocate, buffer); if (channels_lo && c < 0) { c = manage_channel(card, irm_id, generation, channels_lo, - CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO, allocate); + CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO, + allocate, buffer); if (c >= 0) c += 32; } @@ -325,12 +326,13 @@ void fw_iso_resource_manage(struct fw_card *card, int generation, if (*bandwidth == 0) return; - ret = manage_bandwidth(card, irm_id, generation, *bandwidth, allocate); + ret = manage_bandwidth(card, irm_id, generation, *bandwidth, + allocate, buffer); if (ret < 0) *bandwidth = 0; if (allocate && ret < 0 && c >= 0) { - deallocate_channel(card, irm_id, generation, c); + deallocate_channel(card, irm_id, generation, c, buffer); *channel = ret; } } diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h index c3cfc647e5e..6052816be35 100644 --- a/drivers/firewire/core.h +++ b/drivers/firewire/core.h @@ -120,7 +120,8 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event); int fw_iso_buffer_map(struct fw_iso_buffer *buffer, struct vm_area_struct *vma); void fw_iso_resource_manage(struct fw_card *card, int generation, - u64 channels_mask, int *channel, int *bandwidth, bool allocate); + u64 channels_mask, int *channel, int *bandwidth, + bool allocate, __be32 buffer[2]); /* -topology */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 9823946adbc..192d1e43c43 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -127,6 +127,7 @@ struct fw_card { struct delayed_work work; int bm_retries; int bm_generation; + __be32 bm_transaction_data[2]; bool broadcast_channel_allocated; u32 broadcast_channel; From 7ed9f7e5db58c6e8c2b4b738a75d5dcd8e17aad5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2009 12:31:37 -0700 Subject: [PATCH 0038/1346] fix RCU-callback-after-kmem_cache_destroy problem in sl[aou]b Jesper noted that kmem_cache_destroy() invokes synchronize_rcu() rather than rcu_barrier() in the SLAB_DESTROY_BY_RCU case, which could result in RCU callbacks accessing a kmem_cache after it had been destroyed. Cc: Acked-by: Matt Mackall Reported-by: Jesper Dangaard Brouer Signed-off-by: Paul E. McKenney Signed-off-by: Pekka Enberg --- mm/slab.c | 2 +- mm/slob.c | 2 ++ mm/slub.c | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/slab.c b/mm/slab.c index e74a16e4ced..5241b6598ba 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2547,7 +2547,7 @@ void kmem_cache_destroy(struct kmem_cache *cachep) } if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) - synchronize_rcu(); + rcu_barrier(); __kmem_cache_destroy(cachep); mutex_unlock(&cache_chain_mutex); diff --git a/mm/slob.c b/mm/slob.c index c78742defdc..9641da3d5e5 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -595,6 +595,8 @@ EXPORT_SYMBOL(kmem_cache_create); void kmem_cache_destroy(struct kmem_cache *c) { kmemleak_free(c); + if (c->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); slob_free(c, sizeof(struct kmem_cache)); } EXPORT_SYMBOL(kmem_cache_destroy); diff --git a/mm/slub.c b/mm/slub.c index 819f056b39c..a9201d83178 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2595,6 +2595,8 @@ static inline int kmem_cache_close(struct kmem_cache *s) */ void kmem_cache_destroy(struct kmem_cache *s) { + if (s->flags & SLAB_DESTROY_BY_RCU) + rcu_barrier(); down_write(&slub_lock); s->refcount--; if (!s->refcount) { From a32c7765e2796395aec49f699bd25c407155e9c5 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 26 Jun 2009 16:55:51 +0800 Subject: [PATCH 0039/1346] tracing: Fix stack tracer sysctl handling This made my machine completely frozen: # echo 1 > /proc/sys/kernel/stack_tracer_enabled # echo 2 > /proc/sys/kernel/stack_tracer_enabled The cause is register_ftrace_function() was called twice. Also fix ftrace_enabled sysctl, though seems nothing bad happened as I tested it. Signed-off-by: Li Zefan Cc: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <4A448D17.9010305@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 4 ++-- kernel/trace/trace_stack.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f3716bf04df..bce9e01a29c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3160,10 +3160,10 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ret = proc_dointvec(table, write, file, buffer, lenp, ppos); - if (ret || !write || (last_ftrace_enabled == ftrace_enabled)) + if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; - last_ftrace_enabled = ftrace_enabled; + last_ftrace_enabled = !!ftrace_enabled; if (ftrace_enabled) { diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 2d7aebd71db..e644af91012 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -326,10 +326,10 @@ stack_trace_sysctl(struct ctl_table *table, int write, ret = proc_dointvec(table, write, file, buffer, lenp, ppos); if (ret || !write || - (last_stack_tracer_enabled == stack_tracer_enabled)) + (last_stack_tracer_enabled == !!stack_tracer_enabled)) goto out; - last_stack_tracer_enabled = stack_tracer_enabled; + last_stack_tracer_enabled = !!stack_tracer_enabled; if (stack_tracer_enabled) register_ftrace_function(&trace_ops); From 82d5308127c3e3404ffbf41e503853c68660b18b Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 26 Jun 2009 17:07:02 +0800 Subject: [PATCH 0040/1346] trace_export: Repair missed fields Some fields for struct ftrace_graph_ret are missed when they are exported to user. Signed-off-by: Lai Jiangshan Cc: Frederic Weisbecker Cc: Steven Rostedt LKML-Reference: <4A448FB6.5000302@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/trace_event_types.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h index 5e32e375134..6db005e1248 100644 --- a/kernel/trace/trace_event_types.h +++ b/kernel/trace/trace_event_types.h @@ -26,6 +26,9 @@ TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET, ftrace_graph_ret_entry, ignore, TRACE_STRUCT( TRACE_FIELD(unsigned long, ret.func, func) + TRACE_FIELD(unsigned long long, ret.calltime, calltime) + TRACE_FIELD(unsigned long long, ret.rettime, rettime) + TRACE_FIELD(unsigned long, ret.overrun, overrun) TRACE_FIELD(int, ret.depth, depth) ), TP_RAW_FMT("<-- %lx (%d)") From ec5a36f94e7ca4b1f28ae4dd135cd415a704e772 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Mon, 29 Jun 2009 09:57:10 +0300 Subject: [PATCH 0041/1346] SLAB: Fix lockdep annotations Commit 8429db5... ("slab: setup cpu caches later on when interrupts are enabled") broke mm/slab.c lockdep annotations: [ 11.554715] ============================================= [ 11.555249] [ INFO: possible recursive locking detected ] [ 11.555560] 2.6.31-rc1 #896 [ 11.555861] --------------------------------------------- [ 11.556127] udevd/1899 is trying to acquire lock: [ 11.556436] (&nc->lock){-.-...}, at: [] kmem_cache_free+0xcd/0x25b [ 11.557101] [ 11.557102] but task is already holding lock: [ 11.557706] (&nc->lock){-.-...}, at: [] kfree+0x137/0x292 [ 11.558109] [ 11.558109] other info that might help us debug this: [ 11.558720] 2 locks held by udevd/1899: [ 11.558983] #0: (&nc->lock){-.-...}, at: [] kfree+0x137/0x292 [ 11.559734] #1: (&parent->list_lock){-.-...}, at: [] __drain_alien_cache+0x3b/0xbd [ 11.560442] [ 11.560443] stack backtrace: [ 11.561009] Pid: 1899, comm: udevd Not tainted 2.6.31-rc1 #896 [ 11.561276] Call Trace: [ 11.561632] [] __lock_acquire+0x15ec/0x168f [ 11.561901] [] ? __lock_acquire+0x1676/0x168f [ 11.562171] [] ? trace_hardirqs_on_caller+0x113/0x13e [ 11.562490] [] ? trace_hardirqs_on_thunk+0x3a/0x3f [ 11.562807] [] lock_acquire+0xc1/0xe5 [ 11.563073] [] ? kmem_cache_free+0xcd/0x25b [ 11.563385] [] _spin_lock+0x31/0x66 [ 11.563696] [] ? kmem_cache_free+0xcd/0x25b [ 11.563964] [] kmem_cache_free+0xcd/0x25b [ 11.564235] [] ? __free_pages+0x1b/0x24 [ 11.564551] [] slab_destroy+0x57/0x5c [ 11.564860] [] free_block+0xd8/0x123 [ 11.565126] [] __drain_alien_cache+0xa2/0xbd [ 11.565441] [] kfree+0x14c/0x292 [ 11.565752] [] skb_release_data+0xc6/0xcb [ 11.566020] [] __kfree_skb+0x19/0x86 [ 11.566286] [] consume_skb+0x2b/0x2d [ 11.566631] [] skb_free_datagram+0x14/0x3a [ 11.566901] [] netlink_recvmsg+0x164/0x258 [ 11.567170] [] sock_recvmsg+0xe5/0xfe [ 11.567486] [] ? might_fault+0xaf/0xb1 [ 11.567802] [] ? autoremove_wake_function+0x0/0x38 [ 11.568073] [] ? core_sys_select+0x3d/0x2b4 [ 11.568378] [] ? __lock_acquire+0x1676/0x168f [ 11.568693] [] ? sockfd_lookup_light+0x1b/0x54 [ 11.568961] [] sys_recvfrom+0xa3/0xf8 [ 11.569228] [] ? trace_hardirqs_on+0xd/0xf [ 11.569546] [] system_call_fastpath+0x16/0x1b# Fix that up. Closes-bug: http://bugzilla.kernel.org/show_bug.cgi?id=13654 Tested-by: Venkatesh Pallipadi Signed-off-by: Pekka Enberg --- mm/slab.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/slab.c b/mm/slab.c index 5241b6598ba..7b5d4deacfc 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1544,9 +1544,6 @@ void __init kmem_cache_init(void) } g_cpucache_up = EARLY; - - /* Annotate slab for lockdep -- annotate the malloc caches */ - init_lock_keys(); } void __init kmem_cache_init_late(void) @@ -1563,6 +1560,9 @@ void __init kmem_cache_init_late(void) /* Done! */ g_cpucache_up = FULL; + /* Annotate slab for lockdep -- annotate the malloc caches */ + init_lock_keys(); + /* * Register a cpu startup notifier callback that initializes * cpu_cache_get for all new cpus From 9230ccb1071d2d7e4ecb6314e67203b9f7f08140 Mon Sep 17 00:00:00 2001 From: Yan Li Date: Sun, 28 Jun 2009 22:30:56 -0700 Subject: [PATCH 0042/1346] Input: i8042 - more reset quirks for MSI Wind-clone netbooks When testing Moblin on various netbooks, we've got reports that many MSI Wind clones need the i8042 reset quirks for the keyboard and/or touchpad's proper function. Signed-off-by: Yan Li Signed-off-by: Andrew Morton Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042-x86ia64io.h | 28 +++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index fb8a3cd3ffd..924e8ed7f2c 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -392,6 +392,34 @@ static struct dmi_system_id __initdata i8042_dmi_reset_table[] = { DMI_MATCH(DMI_BOARD_VENDOR, "LG Electronics Inc."), }, }, + { + .ident = "Acer Aspire One 150", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"), + }, + }, + { + .ident = "Advent 4211", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "DIXONSXP"), + DMI_MATCH(DMI_PRODUCT_NAME, "Advent 4211"), + }, + }, + { + .ident = "Medion Akoya Mini E1210", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E1210"), + }, + }, + { + .ident = "Mivvy M310", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "VIOOO"), + DMI_MATCH(DMI_PRODUCT_NAME, "N10"), + }, + }, { } }; From c413ec446188ae53276eb60a60311b430448c6b0 Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Sun, 28 Jun 2009 22:50:58 -0700 Subject: [PATCH 0043/1346] Input: wacom - add DTF720a support and fix rotation on Intuos3 This patch adds DTF720a support and fixes an Intuos3 rotation pen out-proximity bug. Signed-off-by: Ping Cheng Signed-off-by: Dmitry Torokhov --- drivers/input/tablet/wacom_wac.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index 38bf86384ae..c896d6a21b7 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -384,6 +384,8 @@ static int wacom_intuos_inout(struct wacom_wac *wacom, void *wcombo) wacom_report_key(wcombo, BTN_STYLUS2, 0); wacom_report_key(wcombo, BTN_TOUCH, 0); wacom_report_abs(wcombo, ABS_WHEEL, 0); + if (wacom->features->type >= INTUOS3S) + wacom_report_abs(wcombo, ABS_Z, 0); } wacom_report_key(wcombo, wacom->tool[idx], 0); wacom_report_abs(wcombo, ABS_MISC, 0); /* reset tool id */ @@ -836,6 +838,7 @@ static struct wacom_features wacom_features[] = { { "Wacom DTU710", 8, 34080, 27660, 511, 0, PL }, { "Wacom DTF521", 8, 6282, 4762, 511, 0, PL }, { "Wacom DTF720", 8, 6858, 5506, 511, 0, PL }, + { "Wacom DTF720a", 8, 6858, 5506, 511, 0, PL }, { "Wacom Cintiq Partner",8, 20480, 15360, 511, 0, PTU }, { "Wacom Intuos2 4x5", 10, 12700, 10600, 1023, 31, INTUOS }, { "Wacom Intuos2 6x8", 10, 20320, 16240, 1023, 31, INTUOS }, @@ -897,8 +900,9 @@ static struct usb_device_id wacom_ids[] = { { USB_DEVICE(USB_VENDOR_ID_WACOM, 0x37) }, { USB_DEVICE(USB_VENDOR_ID_WACOM, 0x38) }, { USB_DEVICE(USB_VENDOR_ID_WACOM, 0x39) }, - { USB_DEVICE(USB_VENDOR_ID_WACOM, 0xC0) }, { USB_DEVICE(USB_VENDOR_ID_WACOM, 0xC4) }, + { USB_DEVICE(USB_VENDOR_ID_WACOM, 0xC0) }, + { USB_DEVICE(USB_VENDOR_ID_WACOM, 0xC2) }, { USB_DEVICE(USB_VENDOR_ID_WACOM, 0x03) }, { USB_DEVICE(USB_VENDOR_ID_WACOM, 0x41) }, { USB_DEVICE(USB_VENDOR_ID_WACOM, 0x42) }, From 00b8ac409cad653137f087e3ff69c020174cbc15 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 28 Jun 2009 22:30:56 -0700 Subject: [PATCH 0044/1346] Input: dm355evm_keys - fix kconfig symbol names The keypad driver for the DM355 EVM got slightly broken as it merged, since it moved from input/keyboard to input/misc and its Kconfig symbol changed. This patch copes with the changed Kconfig symbol. Signed-off-by: David Brownell Signed-off-by: Dmitry Torokhov --- drivers/mfd/dm355evm_msp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mfd/dm355evm_msp.c b/drivers/mfd/dm355evm_msp.c index 7ac12cb0be4..5b6e58a3ba4 100644 --- a/drivers/mfd/dm355evm_msp.c +++ b/drivers/mfd/dm355evm_msp.c @@ -32,8 +32,7 @@ * This driver was tested with firmware revision A4. */ -#if defined(CONFIG_KEYBOARD_DM355EVM) \ - || defined(CONFIG_KEYBOARD_DM355EVM_MODULE) +#if defined(CONFIG_INPUT_DM355EVM) || defined(CONFIG_INPUT_DM355EVM_MODULE) #define msp_has_keyboard() true #else #define msp_has_keyboard() false From ca865a77b5949f5c403e0f13de5a5a9cd499a11e Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Sun, 28 Jun 2009 22:38:44 -0700 Subject: [PATCH 0045/1346] Input: gpio-keys - revert 'change timer to workqueue' This reverts commit 0b346838c5862bfe911432956a106d602535d030. This commit breaks GPIO debouncing by replacing the original mod_timer with schedule_delayed_work in the interrupt handler. The latter does not kick the timer further on GPIO line changes as it should to perform debouncing. Signed-off-by: Jani Nikula Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/gpio_keys.c | 32 +++++++++++++++++++----------- 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index 2157cd7de00..9767213b6c8 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -22,14 +22,13 @@ #include #include #include -#include #include struct gpio_button_data { struct gpio_keys_button *button; struct input_dev *input; - struct delayed_work work; + struct timer_list timer; }; struct gpio_keys_drvdata { @@ -37,10 +36,8 @@ struct gpio_keys_drvdata { struct gpio_button_data data[0]; }; -static void gpio_keys_report_event(struct work_struct *work) +static void gpio_keys_report_event(struct gpio_button_data *bdata) { - struct gpio_button_data *bdata = - container_of(work, struct gpio_button_data, work.work); struct gpio_keys_button *button = bdata->button; struct input_dev *input = bdata->input; unsigned int type = button->type ?: EV_KEY; @@ -50,17 +47,25 @@ static void gpio_keys_report_event(struct work_struct *work) input_sync(input); } +static void gpio_check_button(unsigned long _data) +{ + struct gpio_button_data *data = (struct gpio_button_data *)_data; + + gpio_keys_report_event(data); +} + static irqreturn_t gpio_keys_isr(int irq, void *dev_id) { struct gpio_button_data *bdata = dev_id; struct gpio_keys_button *button = bdata->button; - unsigned long delay; BUG_ON(irq != gpio_to_irq(button->gpio)); - delay = button->debounce_interval ? - msecs_to_jiffies(button->debounce_interval) : 0; - schedule_delayed_work(&bdata->work, delay); + if (button->debounce_interval) + mod_timer(&bdata->timer, + jiffies + msecs_to_jiffies(button->debounce_interval)); + else + gpio_keys_report_event(bdata); return IRQ_HANDLED; } @@ -107,7 +112,8 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev) bdata->input = input; bdata->button = button; - INIT_DELAYED_WORK(&bdata->work, gpio_keys_report_event); + setup_timer(&bdata->timer, + gpio_check_button, (unsigned long)bdata); error = gpio_request(button->gpio, button->desc ?: "gpio_keys"); if (error < 0) { @@ -166,7 +172,8 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev) fail2: while (--i >= 0) { free_irq(gpio_to_irq(pdata->buttons[i].gpio), &ddata->data[i]); - cancel_delayed_work_sync(&ddata->data[i].work); + if (pdata->buttons[i].debounce_interval) + del_timer_sync(&ddata->data[i].timer); gpio_free(pdata->buttons[i].gpio); } @@ -190,7 +197,8 @@ static int __devexit gpio_keys_remove(struct platform_device *pdev) for (i = 0; i < pdata->nbuttons; i++) { int irq = gpio_to_irq(pdata->buttons[i].gpio); free_irq(irq, &ddata->data[i]); - cancel_delayed_work_sync(&ddata->data[i].work); + if (pdata->buttons[i].debounce_interval) + del_timer_sync(&ddata->data[i].timer); gpio_free(pdata->buttons[i].gpio); } From da0d03fe6cecde837f113a8a587f5a872d0fade0 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Sun, 28 Jun 2009 22:38:56 -0700 Subject: [PATCH 0046/1346] Input: gpio-keys - avoid possibility of sleeping in timer function The gpio_get_value function may sleep, so it should not be called in a timer function. Move gpio_get_value calls to workqueue. Signed-off-by: Jani Nikula Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/gpio_keys.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index 9767213b6c8..efed0c9e242 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -29,6 +30,7 @@ struct gpio_button_data { struct gpio_keys_button *button; struct input_dev *input; struct timer_list timer; + struct work_struct work; }; struct gpio_keys_drvdata { @@ -36,8 +38,10 @@ struct gpio_keys_drvdata { struct gpio_button_data data[0]; }; -static void gpio_keys_report_event(struct gpio_button_data *bdata) +static void gpio_keys_report_event(struct work_struct *work) { + struct gpio_button_data *bdata = + container_of(work, struct gpio_button_data, work); struct gpio_keys_button *button = bdata->button; struct input_dev *input = bdata->input; unsigned int type = button->type ?: EV_KEY; @@ -47,11 +51,11 @@ static void gpio_keys_report_event(struct gpio_button_data *bdata) input_sync(input); } -static void gpio_check_button(unsigned long _data) +static void gpio_keys_timer(unsigned long _data) { struct gpio_button_data *data = (struct gpio_button_data *)_data; - gpio_keys_report_event(data); + schedule_work(&data->work); } static irqreturn_t gpio_keys_isr(int irq, void *dev_id) @@ -65,7 +69,7 @@ static irqreturn_t gpio_keys_isr(int irq, void *dev_id) mod_timer(&bdata->timer, jiffies + msecs_to_jiffies(button->debounce_interval)); else - gpio_keys_report_event(bdata); + schedule_work(&bdata->work); return IRQ_HANDLED; } @@ -113,7 +117,8 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev) bdata->input = input; bdata->button = button; setup_timer(&bdata->timer, - gpio_check_button, (unsigned long)bdata); + gpio_keys_timer, (unsigned long)bdata); + INIT_WORK(&bdata->work, gpio_keys_report_event); error = gpio_request(button->gpio, button->desc ?: "gpio_keys"); if (error < 0) { @@ -174,6 +179,7 @@ static int __devinit gpio_keys_probe(struct platform_device *pdev) free_irq(gpio_to_irq(pdata->buttons[i].gpio), &ddata->data[i]); if (pdata->buttons[i].debounce_interval) del_timer_sync(&ddata->data[i].timer); + cancel_work_sync(&ddata->data[i].work); gpio_free(pdata->buttons[i].gpio); } @@ -199,6 +205,7 @@ static int __devexit gpio_keys_remove(struct platform_device *pdev) free_irq(irq, &ddata->data[i]); if (pdata->buttons[i].debounce_interval) del_timer_sync(&ddata->data[i].timer); + cancel_work_sync(&ddata->data[i].work); gpio_free(pdata->buttons[i].gpio); } From cb589529f74d69abc111887b45308f333f950ade Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 29 Jun 2009 00:00:52 -0700 Subject: [PATCH 0047/1346] Input: arrange keyboards alphabetically Hopefully it will reduce conflicts when merging patches. Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/Kconfig | 299 ++++++++++++++++---------------- drivers/input/keyboard/Makefile | 32 ++-- 2 files changed, 165 insertions(+), 166 deletions(-) diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 9d8f796c674..d2df1030675 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -12,6 +12,42 @@ menuconfig INPUT_KEYBOARD if INPUT_KEYBOARD +config KEYBOARD_AAED2000 + tristate "AAED-2000 keyboard" + depends on MACH_AAED2000 + select INPUT_POLLDEV + default y + help + Say Y here to enable the keyboard on the Agilent AAED-2000 + development board. + + To compile this driver as a module, choose M here: the + module will be called aaed2000_kbd. + +config KEYBOARD_AMIGA + tristate "Amiga keyboard" + depends on AMIGA + help + Say Y here if you are running Linux on any AMIGA and have a keyboard + attached. + + To compile this driver as a module, choose M here: the + module will be called amikbd. + +config ATARI_KBD_CORE + bool + +config KEYBOARD_ATARI + tristate "Atari keyboard" + depends on ATARI + select ATARI_KBD_CORE + help + Say Y here if you are running Linux on any Atari and have a keyboard + attached. + + To compile this driver as a module, choose M here: the + module will be called atakbd. + config KEYBOARD_ATKBD tristate "AT keyboard" if EMBEDDED || !X86 default y @@ -68,16 +104,25 @@ config KEYBOARD_ATKBD_RDI_KEYCODES right-hand column will be interpreted as the key shown in the left-hand column. -config KEYBOARD_SUNKBD - tristate "Sun Type 4 and Type 5 keyboard" - select SERIO +config KEYBOARD_BFIN + tristate "Blackfin BF54x keypad support" + depends on (BF54x && !BF544) help - Say Y here if you want to use a Sun Type 4 or Type 5 keyboard, - connected either to the Sun keyboard connector or to an serial - (RS-232) port via a simple adapter. + Say Y here if you want to use the BF54x keypad. To compile this driver as a module, choose M here: the - module will be called sunkbd. + module will be called bf54x-keys. + +config KEYBOARD_CORGI + tristate "Corgi keyboard" + depends on PXA_SHARPSL + default y + help + Say Y here to enable the keyboard on the Sharp Zaurus SL-C7xx + series of PDAs. + + To compile this driver as a module, choose M here: the + module will be called corgikbd. config KEYBOARD_LKKBD tristate "DECstation/VAXstation LK201/LK401 keyboard" @@ -91,113 +136,29 @@ config KEYBOARD_LKKBD To compile this driver as a module, choose M here: the module will be called lkkbd. -config KEYBOARD_LOCOMO - tristate "LoCoMo Keyboard Support" - depends on SHARP_LOCOMO && INPUT_KEYBOARD +config KEYBOARD_EP93XX + tristate "EP93xx Matrix Keypad support" + depends on ARCH_EP93XX help - Say Y here if you are running Linux on a Sharp Zaurus Collie or Poodle based PDA + Say Y here to enable the matrix keypad on the Cirrus EP93XX. To compile this driver as a module, choose M here: the - module will be called locomokbd. + module will be called ep93xx_keypad. -config KEYBOARD_XTKBD - tristate "XT keyboard" - select SERIO +config KEYBOARD_GPIO + tristate "GPIO Buttons" + depends on GENERIC_GPIO help - Say Y here if you want to use the old IBM PC/XT keyboard (or - compatible) on your system. This is only possible with a - parallel port keyboard adapter, you cannot connect it to the - keyboard port on a PC that runs Linux. + This driver implements support for buttons connected + to GPIO pins of various CPUs (and some other chips). + + Say Y here if your device has buttons connected + directly to such GPIO pins. Your board-specific + setup logic must also provide a platform device, + with configuration data saying which GPIOs are used. To compile this driver as a module, choose M here: the - module will be called xtkbd. - -config KEYBOARD_NEWTON - tristate "Newton keyboard" - select SERIO - help - Say Y here if you have a Newton keyboard on a serial port. - - To compile this driver as a module, choose M here: the - module will be called newtonkbd. - -config KEYBOARD_STOWAWAY - tristate "Stowaway keyboard" - select SERIO - help - Say Y here if you have a Stowaway keyboard on a serial port. - Stowaway compatible keyboards like Dicota Input-PDA keyboard - are also supported by this driver. - - To compile this driver as a module, choose M here: the - module will be called stowaway. - -config KEYBOARD_CORGI - tristate "Corgi keyboard" - depends on PXA_SHARPSL - default y - help - Say Y here to enable the keyboard on the Sharp Zaurus SL-C7xx - series of PDAs. - - To compile this driver as a module, choose M here: the - module will be called corgikbd. - -config KEYBOARD_SPITZ - tristate "Spitz keyboard" - depends on PXA_SHARPSL - default y - help - Say Y here to enable the keyboard on the Sharp Zaurus SL-C1000, - SL-C3000 and Sl-C3100 series of PDAs. - - To compile this driver as a module, choose M here: the - module will be called spitzkbd. - -config KEYBOARD_TOSA - tristate "Tosa keyboard" - depends on MACH_TOSA - default y - help - Say Y here to enable the keyboard on the Sharp Zaurus SL-6000x (Tosa) - - To compile this driver as a module, choose M here: the - module will be called tosakbd. - -config KEYBOARD_TOSA_USE_EXT_KEYCODES - bool "Tosa keyboard: use extended keycodes" - depends on KEYBOARD_TOSA - default n - help - Say Y here to enable the tosa keyboard driver to generate extended - (>= 127) keycodes. Be aware, that they can't be correctly interpreted - by either console keyboard driver or by Kdrive keybd driver. - - Say Y only if you know, what you are doing! - -config KEYBOARD_AMIGA - tristate "Amiga keyboard" - depends on AMIGA - help - Say Y here if you are running Linux on any AMIGA and have a keyboard - attached. - - To compile this driver as a module, choose M here: the - module will be called amikbd. - -config ATARI_KBD_CORE - bool - -config KEYBOARD_ATARI - tristate "Atari keyboard" - depends on ATARI - select ATARI_KBD_CORE - help - Say Y here if you are running Linux on any Atari and have a keyboard - attached. - - To compile this driver as a module, choose M here: the - module will be called atakbd. + module will be called gpio-keys. config KEYBOARD_HIL_OLD tristate "HP HIL keyboard support (simple driver)" @@ -261,14 +222,33 @@ config KEYBOARD_LM8323 To compile this driver as a module, choose M here: the module will be called lm8323. -config KEYBOARD_OMAP - tristate "TI OMAP keypad support" - depends on (ARCH_OMAP1 || ARCH_OMAP2) +config KEYBOARD_LOCOMO + tristate "LoCoMo Keyboard Support" + depends on SHARP_LOCOMO help - Say Y here if you want to use the OMAP keypad. + Say Y here if you are running Linux on a Sharp Zaurus Collie or Poodle based PDA To compile this driver as a module, choose M here: the - module will be called omap-keypad. + module will be called locomokbd. + +config KEYBOARD_MAPLE + tristate "Maple bus keyboard" + depends on SH_DREAMCAST && MAPLE + help + Say Y here if you have a Dreamcast console running Linux and have + a keyboard attached to its Maple bus. + + To compile this driver as a module, choose M here: the + module will be called maple_keyb. + +config KEYBOARD_NEWTON + tristate "Newton keyboard" + select SERIO + help + Say Y here if you have a Newton keyboard on a serial port. + + To compile this driver as a module, choose M here: the + module will be called newtonkbd. config KEYBOARD_PXA27x tristate "PXA27x/PXA3xx keypad support" @@ -288,51 +268,38 @@ config KEYBOARD_PXA930_ROTARY To compile this driver as a module, choose M here: the module will be called pxa930_rotary. -config KEYBOARD_AAED2000 - tristate "AAED-2000 keyboard" - depends on MACH_AAED2000 - select INPUT_POLLDEV +config KEYBOARD_SPITZ + tristate "Spitz keyboard" + depends on PXA_SHARPSL default y help - Say Y here to enable the keyboard on the Agilent AAED-2000 - development board. + Say Y here to enable the keyboard on the Sharp Zaurus SL-C1000, + SL-C3000 and Sl-C3100 series of PDAs. To compile this driver as a module, choose M here: the - module will be called aaed2000_kbd. + module will be called spitzkbd. -config KEYBOARD_GPIO - tristate "GPIO Buttons" - depends on GENERIC_GPIO +config KEYBOARD_STOWAWAY + tristate "Stowaway keyboard" + select SERIO help - This driver implements support for buttons connected - to GPIO pins of various CPUs (and some other chips). - - Say Y here if your device has buttons connected - directly to such GPIO pins. Your board-specific - setup logic must also provide a platform device, - with configuration data saying which GPIOs are used. + Say Y here if you have a Stowaway keyboard on a serial port. + Stowaway compatible keyboards like Dicota Input-PDA keyboard + are also supported by this driver. To compile this driver as a module, choose M here: the - module will be called gpio-keys. + module will be called stowaway. -config KEYBOARD_MAPLE - tristate "Maple bus keyboard" - depends on SH_DREAMCAST && MAPLE +config KEYBOARD_SUNKBD + tristate "Sun Type 4 and Type 5 keyboard" + select SERIO help - Say Y here if you have a Dreamcast console running Linux and have - a keyboard attached to its Maple bus. + Say Y here if you want to use a Sun Type 4 or Type 5 keyboard, + connected either to the Sun keyboard connector or to an serial + (RS-232) port via a simple adapter. To compile this driver as a module, choose M here: the - module will be called maple_keyb. - -config KEYBOARD_BFIN - tristate "Blackfin BF54x keypad support" - depends on (BF54x && !BF544) - help - Say Y here if you want to use the BF54x keypad. - - To compile this driver as a module, choose M here: the - module will be called bf54x-keys. + module will be called sunkbd. config KEYBOARD_SH_KEYSC tristate "SuperH KEYSC keypad support" @@ -344,13 +311,45 @@ config KEYBOARD_SH_KEYSC To compile this driver as a module, choose M here: the module will be called sh_keysc. -config KEYBOARD_EP93XX - tristate "EP93xx Matrix Keypad support" - depends on ARCH_EP93XX +config KEYBOARD_OMAP + tristate "TI OMAP keypad support" + depends on (ARCH_OMAP1 || ARCH_OMAP2) help - Say Y here to enable the matrix keypad on the Cirrus EP93XX. + Say Y here if you want to use the OMAP keypad. To compile this driver as a module, choose M here: the - module will be called ep93xx_keypad. + module will be called omap-keypad. + +config KEYBOARD_TOSA + tristate "Tosa keyboard" + depends on MACH_TOSA + default y + help + Say Y here to enable the keyboard on the Sharp Zaurus SL-6000x (Tosa) + + To compile this driver as a module, choose M here: the + module will be called tosakbd. + +config KEYBOARD_TOSA_USE_EXT_KEYCODES + bool "Tosa keyboard: use extended keycodes" + depends on KEYBOARD_TOSA + help + Say Y here to enable the tosa keyboard driver to generate extended + (>= 127) keycodes. Be aware, that they can't be correctly interpreted + by either console keyboard driver or by Kdrive keybd driver. + + Say Y only if you know, what you are doing! + +config KEYBOARD_XTKBD + tristate "XT keyboard" + select SERIO + help + Say Y here if you want to use the old IBM PC/XT keyboard (or + compatible) on your system. This is only possible with a + parallel port keyboard adapter, you cannot connect it to the + keyboard port on a PC that runs Linux. + + To compile this driver as a module, choose M here: the + module will be called xtkbd. endif diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index 156b647a259..632efbc18c4 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -4,29 +4,29 @@ # Each configuration option enables a list of files. -obj-$(CONFIG_KEYBOARD_ATKBD) += atkbd.o -obj-$(CONFIG_KEYBOARD_SUNKBD) += sunkbd.o -obj-$(CONFIG_KEYBOARD_LKKBD) += lkkbd.o -obj-$(CONFIG_KEYBOARD_XTKBD) += xtkbd.o +obj-$(CONFIG_KEYBOARD_AAED2000) += aaed2000_kbd.o obj-$(CONFIG_KEYBOARD_AMIGA) += amikbd.o obj-$(CONFIG_KEYBOARD_ATARI) += atakbd.o -obj-$(CONFIG_KEYBOARD_LOCOMO) += locomokbd.o -obj-$(CONFIG_KEYBOARD_NEWTON) += newtonkbd.o -obj-$(CONFIG_KEYBOARD_STOWAWAY) += stowaway.o +obj-$(CONFIG_KEYBOARD_ATKBD) += atkbd.o +obj-$(CONFIG_KEYBOARD_BFIN) += bf54x-keys.o obj-$(CONFIG_KEYBOARD_CORGI) += corgikbd.o -obj-$(CONFIG_KEYBOARD_SPITZ) += spitzkbd.o -obj-$(CONFIG_KEYBOARD_TOSA) += tosakbd.o +obj-$(CONFIG_KEYBOARD_EP93XX) += ep93xx_keypad.o +obj-$(CONFIG_KEYBOARD_GPIO) += gpio_keys.o obj-$(CONFIG_KEYBOARD_HIL) += hil_kbd.o obj-$(CONFIG_KEYBOARD_HIL_OLD) += hilkbd.o +obj-$(CONFIG_KEYBOARD_HP6XX) += jornada680_kbd.o +obj-$(CONFIG_KEYBOARD_HP7XX) += jornada720_kbd.o +obj-$(CONFIG_KEYBOARD_LKKBD) += lkkbd.o obj-$(CONFIG_KEYBOARD_LM8323) += lm8323.o +obj-$(CONFIG_KEYBOARD_LOCOMO) += locomokbd.o +obj-$(CONFIG_KEYBOARD_MAPLE) += maple_keyb.o +obj-$(CONFIG_KEYBOARD_NEWTON) += newtonkbd.o obj-$(CONFIG_KEYBOARD_OMAP) += omap-keypad.o obj-$(CONFIG_KEYBOARD_PXA27x) += pxa27x_keypad.o obj-$(CONFIG_KEYBOARD_PXA930_ROTARY) += pxa930_rotary.o -obj-$(CONFIG_KEYBOARD_AAED2000) += aaed2000_kbd.o -obj-$(CONFIG_KEYBOARD_GPIO) += gpio_keys.o -obj-$(CONFIG_KEYBOARD_HP6XX) += jornada680_kbd.o -obj-$(CONFIG_KEYBOARD_HP7XX) += jornada720_kbd.o -obj-$(CONFIG_KEYBOARD_MAPLE) += maple_keyb.o -obj-$(CONFIG_KEYBOARD_BFIN) += bf54x-keys.o obj-$(CONFIG_KEYBOARD_SH_KEYSC) += sh_keysc.o -obj-$(CONFIG_KEYBOARD_EP93XX) += ep93xx_keypad.o +obj-$(CONFIG_KEYBOARD_SPITZ) += spitzkbd.o +obj-$(CONFIG_KEYBOARD_STOWAWAY) += stowaway.o +obj-$(CONFIG_KEYBOARD_SUNKBD) += sunkbd.o +obj-$(CONFIG_KEYBOARD_TOSA) += tosakbd.o +obj-$(CONFIG_KEYBOARD_XTKBD) += xtkbd.o From bab7614d6d1b1fc96ec6c5a7ca34c8641060e659 Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Mon, 29 Jun 2009 00:20:52 -0700 Subject: [PATCH 0048/1346] Input: add support for generic GPIO-based matrix keypad Original patch by Marek Vasut, modified by Eric in: 1. use delayed work to simplify the debouncing 2. combine col_polarity/row_polarity into a single active_low field 3. use a generic bit array based XOR algorithm to detect key press/release, which should make the column assertion time shorter and code a bit cleaner 4. remove the ALT_FN handling, which is no way generic, the ALT_FN key should be treated as no different from other keys, and translation will be done by user space by commands like 'loadkeys'. 5. explicitly disable row IRQs and flush potential pending work, and schedule an immediate scan after resuming as suggested by Uli Luckas 6. incorporate review comments from many others Patch tested on Littleton/PXA310 (though PXA310 has a dedicate keypad controller, I have to configure those pins as generic GPIO to use this driver, works quite well, though), and Sharp Zaurus model SL-C7x0 and SL-C1000. [dtor@mail.ru: fix error unwinding path, support changing keymap from userspace] Signed-off-by: Marek Vasut Reviewed-by: Trilok Soni Reviewed-by: Uli Luckas Reviewed-by: Russell King Reviewed-by: Robert Jarzmik Signed-off-by: Eric Miao Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/Kconfig | 13 +- drivers/input/keyboard/Makefile | 1 + drivers/input/keyboard/matrix_keypad.c | 453 +++++++++++++++++++++++++ include/linux/input/matrix_keypad.h | 65 ++++ 4 files changed, 530 insertions(+), 2 deletions(-) create mode 100644 drivers/input/keyboard/matrix_keypad.c create mode 100644 include/linux/input/matrix_keypad.h diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index d2df1030675..a6b989a9dc0 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -158,7 +158,16 @@ config KEYBOARD_GPIO with configuration data saying which GPIOs are used. To compile this driver as a module, choose M here: the - module will be called gpio-keys. + module will be called gpio_keys. + +config KEYBOARD_MATRIX + tristate "GPIO driven matrix keypad support" + depends on GENERIC_GPIO + help + Enable support for GPIO driven matrix keypad. + + To compile this driver as a module, choose M here: the + module will be called matrix_keypad. config KEYBOARD_HIL_OLD tristate "HP HIL keyboard support (simple driver)" @@ -254,7 +263,7 @@ config KEYBOARD_PXA27x tristate "PXA27x/PXA3xx keypad support" depends on PXA27x || PXA3xx help - Enable support for PXA27x/PXA3xx keypad controller + Enable support for PXA27x/PXA3xx keypad controller. To compile this driver as a module, choose M here: the module will be called pxa27x_keypad. diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index 632efbc18c4..b5b5eae9724 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_KEYBOARD_LKKBD) += lkkbd.o obj-$(CONFIG_KEYBOARD_LM8323) += lm8323.o obj-$(CONFIG_KEYBOARD_LOCOMO) += locomokbd.o obj-$(CONFIG_KEYBOARD_MAPLE) += maple_keyb.o +obj-$(CONFIG_KEYBOARD_MATRIX) += matrix_keypad.o obj-$(CONFIG_KEYBOARD_NEWTON) += newtonkbd.o obj-$(CONFIG_KEYBOARD_OMAP) += omap-keypad.o obj-$(CONFIG_KEYBOARD_PXA27x) += pxa27x_keypad.o diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c new file mode 100644 index 00000000000..e9b2e7cb05b --- /dev/null +++ b/drivers/input/keyboard/matrix_keypad.c @@ -0,0 +1,453 @@ +/* + * GPIO driven matrix keyboard driver + * + * Copyright (c) 2008 Marek Vasut + * + * Based on corgikbd.c + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct matrix_keypad { + const struct matrix_keypad_platform_data *pdata; + struct input_dev *input_dev; + unsigned short *keycodes; + + uint32_t last_key_state[MATRIX_MAX_COLS]; + struct delayed_work work; + bool scan_pending; + bool stopped; + spinlock_t lock; +}; + +/* + * NOTE: normally the GPIO has to be put into HiZ when de-activated to cause + * minmal side effect when scanning other columns, here it is configured to + * be input, and it should work on most platforms. + */ +static void __activate_col(const struct matrix_keypad_platform_data *pdata, + int col, bool on) +{ + bool level_on = !pdata->active_low; + + if (on) { + gpio_direction_output(pdata->col_gpios[col], level_on); + } else { + gpio_set_value_cansleep(pdata->col_gpios[col], !level_on); + gpio_direction_input(pdata->col_gpios[col]); + } +} + +static void activate_col(const struct matrix_keypad_platform_data *pdata, + int col, bool on) +{ + __activate_col(pdata, col, on); + + if (on && pdata->col_scan_delay_us) + udelay(pdata->col_scan_delay_us); +} + +static void activate_all_cols(const struct matrix_keypad_platform_data *pdata, + bool on) +{ + int col; + + for (col = 0; col < pdata->num_col_gpios; col++) + __activate_col(pdata, col, on); +} + +static bool row_asserted(const struct matrix_keypad_platform_data *pdata, + int row) +{ + return gpio_get_value_cansleep(pdata->row_gpios[row]) ? + !pdata->active_low : pdata->active_low; +} + +static void enable_row_irqs(struct matrix_keypad *keypad) +{ + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + int i; + + for (i = 0; i < pdata->num_row_gpios; i++) + enable_irq(gpio_to_irq(pdata->row_gpios[i])); +} + +static void disable_row_irqs(struct matrix_keypad *keypad) +{ + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + int i; + + for (i = 0; i < pdata->num_row_gpios; i++) + disable_irq_nosync(gpio_to_irq(pdata->row_gpios[i])); +} + +/* + * This gets the keys from keyboard and reports it to input subsystem + */ +static void matrix_keypad_scan(struct work_struct *work) +{ + struct matrix_keypad *keypad = + container_of(work, struct matrix_keypad, work.work); + struct input_dev *input_dev = keypad->input_dev; + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + uint32_t new_state[MATRIX_MAX_COLS]; + int row, col, code; + + /* de-activate all columns for scanning */ + activate_all_cols(pdata, false); + + memset(new_state, 0, sizeof(new_state)); + + /* assert each column and read the row status out */ + for (col = 0; col < pdata->num_col_gpios; col++) { + + activate_col(pdata, col, true); + + for (row = 0; row < pdata->num_row_gpios; row++) + new_state[col] |= + row_asserted(pdata, row) ? (1 << row) : 0; + + activate_col(pdata, col, false); + } + + for (col = 0; col < pdata->num_col_gpios; col++) { + uint32_t bits_changed; + + bits_changed = keypad->last_key_state[col] ^ new_state[col]; + if (bits_changed == 0) + continue; + + for (row = 0; row < pdata->num_row_gpios; row++) { + if ((bits_changed & (1 << row)) == 0) + continue; + + code = (row << 4) + col; + input_event(input_dev, EV_MSC, MSC_SCAN, code); + input_report_key(input_dev, + keypad->keycodes[code], + new_state[col] & (1 << row)); + } + } + input_sync(input_dev); + + memcpy(keypad->last_key_state, new_state, sizeof(new_state)); + + activate_all_cols(pdata, true); + + /* Enable IRQs again */ + spin_lock_irq(&keypad->lock); + keypad->scan_pending = false; + enable_row_irqs(keypad); + spin_unlock_irq(&keypad->lock); +} + +static irqreturn_t matrix_keypad_interrupt(int irq, void *id) +{ + struct matrix_keypad *keypad = id; + unsigned long flags; + + spin_lock_irqsave(&keypad->lock, flags); + + /* + * See if another IRQ beaten us to it and scheduled the + * scan already. In that case we should not try to + * disable IRQs again. + */ + if (unlikely(keypad->scan_pending || keypad->stopped)) + goto out; + + disable_row_irqs(keypad); + keypad->scan_pending = true; + schedule_delayed_work(&keypad->work, + msecs_to_jiffies(keypad->pdata->debounce_ms)); + +out: + spin_unlock_irqrestore(&keypad->lock, flags); + return IRQ_HANDLED; +} + +static int matrix_keypad_start(struct input_dev *dev) +{ + struct matrix_keypad *keypad = input_get_drvdata(dev); + + keypad->stopped = false; + mb(); + + /* + * Schedule an immediate key scan to capture current key state; + * columns will be activated and IRQs be enabled after the scan. + */ + schedule_delayed_work(&keypad->work, 0); + + return 0; +} + +static void matrix_keypad_stop(struct input_dev *dev) +{ + struct matrix_keypad *keypad = input_get_drvdata(dev); + + keypad->stopped = true; + mb(); + flush_work(&keypad->work.work); + /* + * matrix_keypad_scan() will leave IRQs enabled; + * we should disable them now. + */ + disable_row_irqs(keypad); +} + +#ifdef CONFIG_PM +static int matrix_keypad_suspend(struct platform_device *pdev, pm_message_t state) +{ + struct matrix_keypad *keypad = platform_get_drvdata(pdev); + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + int i; + + matrix_keypad_stop(keypad->input_dev); + + if (device_may_wakeup(&pdev->dev)) + for (i = 0; i < pdata->num_row_gpios; i++) + enable_irq_wake(gpio_to_irq(pdata->row_gpios[i])); + + return 0; +} + +static int matrix_keypad_resume(struct platform_device *pdev) +{ + struct matrix_keypad *keypad = platform_get_drvdata(pdev); + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + int i; + + if (device_may_wakeup(&pdev->dev)) + for (i = 0; i < pdata->num_row_gpios; i++) + disable_irq_wake(gpio_to_irq(pdata->row_gpios[i])); + + matrix_keypad_start(keypad->input_dev); + + return 0; +} +#else +#define matrix_keypad_suspend NULL +#define matrix_keypad_resume NULL +#endif + +static int __devinit init_matrix_gpio(struct platform_device *pdev, + struct matrix_keypad *keypad) +{ + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + int i, err = -EINVAL; + + /* initialized strobe lines as outputs, activated */ + for (i = 0; i < pdata->num_col_gpios; i++) { + err = gpio_request(pdata->col_gpios[i], "matrix_kbd_col"); + if (err) { + dev_err(&pdev->dev, + "failed to request GPIO%d for COL%d\n", + pdata->col_gpios[i], i); + goto err_free_cols; + } + + gpio_direction_output(pdata->col_gpios[i], !pdata->active_low); + } + + for (i = 0; i < pdata->num_row_gpios; i++) { + err = gpio_request(pdata->row_gpios[i], "matrix_kbd_row"); + if (err) { + dev_err(&pdev->dev, + "failed to request GPIO%d for ROW%d\n", + pdata->row_gpios[i], i); + goto err_free_rows; + } + + gpio_direction_input(pdata->row_gpios[i]); + } + + for (i = 0; i < pdata->num_row_gpios; i++) { + err = request_irq(gpio_to_irq(pdata->row_gpios[i]), + matrix_keypad_interrupt, + IRQF_DISABLED | + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, + "matrix-keypad", keypad); + if (err) { + dev_err(&pdev->dev, + "Unable to acquire interrupt for GPIO line %i\n", + pdata->row_gpios[i]); + goto err_free_irqs; + } + } + + /* initialized as disabled - enabled by input->open */ + disable_row_irqs(keypad); + return 0; + +err_free_irqs: + while (--i >= 0) + free_irq(gpio_to_irq(pdata->row_gpios[i]), keypad); + i = pdata->num_row_gpios; +err_free_rows: + while (--i >= 0) + gpio_free(pdata->row_gpios[i]); + i = pdata->num_col_gpios; +err_free_cols: + while (--i >= 0) + gpio_free(pdata->col_gpios[i]); + + return err; +} + +static int __devinit matrix_keypad_probe(struct platform_device *pdev) +{ + const struct matrix_keypad_platform_data *pdata; + const struct matrix_keymap_data *keymap_data; + struct matrix_keypad *keypad; + struct input_dev *input_dev; + unsigned short *keycodes; + int i; + int err; + + pdata = pdev->dev.platform_data; + if (!pdata) { + dev_err(&pdev->dev, "no platform data defined\n"); + return -EINVAL; + } + + keymap_data = pdata->keymap_data; + if (!keymap_data) { + dev_err(&pdev->dev, "no keymap data defined\n"); + return -EINVAL; + } + + if (!keymap_data->max_keymap_size) { + dev_err(&pdev->dev, "invalid keymap data supplied\n"); + return -EINVAL; + } + + keypad = kzalloc(sizeof(struct matrix_keypad), GFP_KERNEL); + keycodes = kzalloc(keymap_data->max_keymap_size * + sizeof(keypad->keycodes), + GFP_KERNEL); + input_dev = input_allocate_device(); + if (!keypad || !keycodes || !input_dev) { + err = -ENOMEM; + goto err_free_mem; + } + + keypad->input_dev = input_dev; + keypad->pdata = pdata; + keypad->keycodes = keycodes; + keypad->stopped = true; + INIT_DELAYED_WORK(&keypad->work, matrix_keypad_scan); + spin_lock_init(&keypad->lock); + + input_dev->name = pdev->name; + input_dev->id.bustype = BUS_HOST; + input_dev->dev.parent = &pdev->dev; + input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP); + input_dev->open = matrix_keypad_start; + input_dev->close = matrix_keypad_stop; + + input_dev->keycode = keycodes; + input_dev->keycodesize = sizeof(*keycodes); + input_dev->keycodemax = keymap_data->max_keymap_size; + + for (i = 0; i < keymap_data->keymap_size; i++) { + unsigned int key = keymap_data->keymap[i]; + unsigned int row = KEY_ROW(key); + unsigned int col = KEY_COL(key); + unsigned short code = KEY_VAL(key); + + keycodes[(row << 4) + col] = code; + __set_bit(code, input_dev->keybit); + } + __clear_bit(KEY_RESERVED, input_dev->keybit); + + input_set_capability(input_dev, EV_MSC, MSC_SCAN); + input_set_drvdata(input_dev, keypad); + + err = init_matrix_gpio(pdev, keypad); + if (err) + goto err_free_mem; + + err = input_register_device(keypad->input_dev); + if (err) + goto err_free_mem; + + device_init_wakeup(&pdev->dev, pdata->wakeup); + platform_set_drvdata(pdev, keypad); + + return 0; + +err_free_mem: + input_free_device(input_dev); + kfree(keycodes); + kfree(keypad); + return err; +} + +static int __devexit matrix_keypad_remove(struct platform_device *pdev) +{ + struct matrix_keypad *keypad = platform_get_drvdata(pdev); + const struct matrix_keypad_platform_data *pdata = keypad->pdata; + int i; + + device_init_wakeup(&pdev->dev, 0); + + for (i = 0; i < pdata->num_row_gpios; i++) { + free_irq(gpio_to_irq(pdata->row_gpios[i]), keypad); + gpio_free(pdata->row_gpios[i]); + } + + for (i = 0; i < pdata->num_col_gpios; i++) + gpio_free(pdata->col_gpios[i]); + + input_unregister_device(keypad->input_dev); + platform_set_drvdata(pdev, NULL); + kfree(keypad->keycodes); + kfree(keypad); + + return 0; +} + +static struct platform_driver matrix_keypad_driver = { + .probe = matrix_keypad_probe, + .remove = __devexit_p(matrix_keypad_remove), + .suspend = matrix_keypad_suspend, + .resume = matrix_keypad_resume, + .driver = { + .name = "matrix-keypad", + .owner = THIS_MODULE, + }, +}; + +static int __init matrix_keypad_init(void) +{ + return platform_driver_register(&matrix_keypad_driver); +} + +static void __exit matrix_keypad_exit(void) +{ + platform_driver_unregister(&matrix_keypad_driver); +} + +module_init(matrix_keypad_init); +module_exit(matrix_keypad_exit); + +MODULE_AUTHOR("Marek Vasut "); +MODULE_DESCRIPTION("GPIO Driven Matrix Keypad Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:matrix-keypad"); diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h new file mode 100644 index 00000000000..7964516c695 --- /dev/null +++ b/include/linux/input/matrix_keypad.h @@ -0,0 +1,65 @@ +#ifndef _MATRIX_KEYPAD_H +#define _MATRIX_KEYPAD_H + +#include +#include + +#define MATRIX_MAX_ROWS 16 +#define MATRIX_MAX_COLS 16 + +#define KEY(row, col, val) ((((row) & (MATRIX_MAX_ROWS - 1)) << 24) |\ + (((col) & (MATRIX_MAX_COLS - 1)) << 16) |\ + (val & 0xffff)) + +#define KEY_ROW(k) (((k) >> 24) & 0xff) +#define KEY_COL(k) (((k) >> 16) & 0xff) +#define KEY_VAL(k) ((k) & 0xffff) + +/** + * struct matrix_keymap_data - keymap for matrix keyboards + * @keymap: pointer to array of uint32 values encoded with KEY() macro + * representing keymap + * @keymap_size: number of entries (initialized) in this keymap + * @max_keymap_size: maximum size of keymap supported by the device + * + * This structure is supposed to be used by platform code to supply + * keymaps to drivers that implement matrix-like keypads/keyboards. + */ +struct matrix_keymap_data { + const uint32_t *keymap; + unsigned int keymap_size; + unsigned int max_keymap_size; +}; + +/** + * struct matrix_keypad_platform_data - platform-dependent keypad data + * @keymap_data: pointer to &matrix_keymap_data + * @row_gpios: array of gpio numbers reporesenting rows + * @col_gpios: array of gpio numbers reporesenting colums + * @num_row_gpios: actual number of row gpios used by device + * @num_col_gpios: actual number of col gpios used by device + * @col_scan_delay_us: delay, measured in microseconds, that is + * needed before we can keypad after activating column gpio + * @debounce_ms: debounce interval in milliseconds + * + * This structure represents platform-specific data that use used by + * matrix_keypad driver to perform proper initialization. + */ +struct matrix_keypad_platform_data { + const struct matrix_keymap_data *keymap_data; + + unsigned int row_gpios[MATRIX_MAX_ROWS]; + unsigned int col_gpios[MATRIX_MAX_COLS]; + unsigned int num_row_gpios; + unsigned int num_col_gpios; + + unsigned int col_scan_delay_us; + + /* key debounce interval in milli-second */ + unsigned int debounce_ms; + + bool active_low; + bool wakeup; +}; + +#endif /* _MATRIX_KEYPAD_H */ From 238a24f626628cb16a3015f332d649f08246ca89 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 29 Jun 2009 15:55:10 +0800 Subject: [PATCH 0049/1346] tracing/fastboot: Document the need of initcall_debug To use boot tracer, one should pass initcall_debug as well as ftrace=initcall to the command line. Signed-off-by: Li Zefan Cc: Frederic Weisbecker Cc: Steven Rostedt LKML-Reference: <4A48735E.9050002@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 1551f47e766..019f380fd76 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -226,13 +226,13 @@ config BOOT_TRACER the timings of the initcalls and traces key events and the identity of tasks that can cause boot delays, such as context-switches. - Its aim is to be parsed by the /scripts/bootgraph.pl tool to + Its aim is to be parsed by the scripts/bootgraph.pl tool to produce pretty graphics about boot inefficiencies, giving a visual representation of the delays during initcalls - but the raw /debug/tracing/trace text output is readable too. - You must pass in ftrace=initcall to the kernel command line - to enable this on bootup. + You must pass in initcall_debug and ftrace=initcall to the kernel + command line to enable this on bootup. config TRACE_BRANCH_PROFILING bool From 0d07348931daef854aca8c834a89f1a99ba4ff2b Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Wed, 24 Jun 2009 12:08:27 +0900 Subject: [PATCH 0050/1346] PCI MSI: Return if alloc_msi_entry for MSI-X failed In current code it continues setup even if alloc_msi_entry() for MSI-X is failed due to lack of memory. It means arch_setup_msi_irqs() might be called with msi_desc entries less than its argument nvec. At least x86's arch_setup_msi_irqs() uses list_for_each_entry() for dev->msi_list that suspected to have entries same numbers as nvec, and it doesn't check the number of allocated vectors and passed arg nvec. Therefore it will result in success of pci_enable_msix(), with less vectors allocated than requested. This patch fixes the error route to return -ENOMEM, instead of continuing the setup (proposed by Matthew Wilcox). Note that there is no iounmap in msi_free_irqs() if no msi_disc is allocated. Reviewed-by: Matthew Wilcox Signed-off-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- drivers/pci/msi.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index d9f06fbfa0b..628c14150d4 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -439,8 +439,14 @@ static int msix_capability_init(struct pci_dev *dev, for (i = 0; i < nvec; i++) { entry = alloc_msi_entry(dev); - if (!entry) - break; + if (!entry) { + if (!i) + iounmap(base); + else + msi_free_irqs(dev); + /* No enough memory. Don't try again */ + return -ENOMEM; + } j = entries[i].entry; entry->msi_attrib.is_msix = 1; From 50e5628a4ac465a52f0d4ca6567343be029731a0 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 28 Jun 2009 09:26:40 -0700 Subject: [PATCH 0051/1346] PCI ECRC: Remove unnecessary semicolons Acked-by: Andrew Patterson Signed-off-by: Joe Perches Signed-off-by: Jesse Barnes --- drivers/pci/pcie/aer/ecrc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pcie/aer/ecrc.c b/drivers/pci/pcie/aer/ecrc.c index ece97df4df6..a928d8ab6bd 100644 --- a/drivers/pci/pcie/aer/ecrc.c +++ b/drivers/pci/pcie/aer/ecrc.c @@ -106,7 +106,7 @@ void pcie_set_ecrc_checking(struct pci_dev *dev) disable_ecrc_checking(dev); break; case ECRC_POLICY_ON: - enable_ecrc_checking(dev);; + enable_ecrc_checking(dev); break; default: return; From 977badb2f385db14d8ba3fcf02fbd7ead8e63d0f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fernando=20Luis=20V=C3=A1zquez=20Cao?= Date: Fri, 26 Jun 2009 11:27:41 +0900 Subject: [PATCH 0052/1346] PCI: remove pci_dac_dma_... APIs on mn10300 It seems that mn10300 made it upstream after Jan Beulich's pci_dac_dma_* cleanup work and still defines pci_dac_dma_supported(). This API is not required by the PCI subsystem anymore, so remove it. Acked-by: David Howells Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: Jesse Barnes --- arch/mn10300/include/asm/pci.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h index e58b9a46e1b..35d2ed6396f 100644 --- a/arch/mn10300/include/asm/pci.h +++ b/arch/mn10300/include/asm/pci.h @@ -70,10 +70,6 @@ struct pci_dev; */ #define PCI_DMA_BUS_IS_PHYS (1) - -/* This is always fine. */ -#define pci_dac_dma_supported(pci_dev, mask) (0) - /* Return the index of the PCI controller for device. */ static inline int pci_controller_num(struct pci_dev *dev) { From 654b75e044119bf8e7d773bce41ea039281bbfbe Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 26 Jun 2009 14:04:46 +0800 Subject: [PATCH 0053/1346] PCI: check if bus has a proper bridge device before triggering SBR For devices attached to the root bus, we can't trigger Secondary Bus Reset because there is no bridge device associated with the bus. So need to check bus->self again NULL first before using it. Reviewed-by: Kenji Kaneshige Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- drivers/pci/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6c93af5ced1..d5d6f5667d8 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2171,7 +2171,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) u16 ctrl; struct pci_dev *pdev; - if (dev->subordinate) + if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) From 503998ca4a295f7da233689850ba4b9d13cf41e7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 24 Jun 2009 09:18:14 -0700 Subject: [PATCH 0054/1346] PCI: fix kernel-doc warnings Add documentation for missing parameters in PCI hotplug code. Signed-off-by: Randy Dunlap Signed-off-by: Jesse Barnes --- drivers/pci/hotplug/pci_hotplug_core.c | 2 ++ drivers/pci/slot.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index 844580489d4..5c5043f239c 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -555,6 +555,8 @@ static struct hotplug_slot *get_slot_from_name (const char *name) * @slot: pointer to the &struct hotplug_slot to register * @devnr: device number * @name: name registered with kobject core + * @owner: caller module owner + * @mod_name: caller module name * * Registers a hotplug slot with the pci hotplug subsystem, which will allow * userspace interaction to the slot. diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index eddb0748b0e..8c02b6c53bd 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -311,7 +311,7 @@ EXPORT_SYMBOL_GPL(pci_destroy_slot); #include /** * pci_hp_create_link - create symbolic link to the hotplug driver module. - * @slot: struct pci_slot + * @pci_slot: struct pci_slot * * Helper function for pci_hotplug_core.c to create symbolic link to * the hotplug driver module. @@ -334,7 +334,7 @@ EXPORT_SYMBOL_GPL(pci_hp_create_module_link); /** * pci_hp_remove_link - remove symbolic link to the hotplug driver module. - * @slot: struct pci_slot + * @pci_slot: struct pci_slot * * Helper function for pci_hotplug_core.c to remove symbolic link to * the hotplug driver module. From 7a661c6f1082693a7e9627e9ad2d1546a9337fdc Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 24 Jun 2009 16:02:27 +0100 Subject: [PATCH 0055/1346] PCI: More PATA quirks for not entering D3 The ALi loses some state if it goes into D3. Unfortunately even with the chipset documents I can't figure out how to restore some bits of it. The VIA one saves/restores apparently fine but the ACPI _GTM methods break on some platforms if we do this and this causes cable misdetections. These are both effectively regressions as historically nothing matched the devices and then decided not to bind to them. Nowdays something is binding to all sorts of devices and a result they get dumped into D3. Signed-off-by: Alan Cox Acked-by: Jeff Garzik Signed-off-by: Jesse Barnes --- drivers/pci/quirks.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 56552d74abe..06b96562396 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1058,6 +1058,11 @@ static void __devinit quirk_no_ata_d3(struct pci_dev *pdev) } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_ANY_ID, quirk_no_ata_d3); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, PCI_ANY_ID, quirk_no_ata_d3); +/* ALi loses some register settings that we cannot then restore */ +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, quirk_no_ata_d3); +/* VIA comes back fine but we need to keep it alive or ACPI GTM failures + occur when mode detecting */ +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_VIA, PCI_ANY_ID, quirk_no_ata_d3); /* This was originally an Alpha specific thing, but it really fits here. * The i82375 PCI/EISA bridge appears as non-classified. Fix that. From 2fc90f6133a87da8177636866557d4cc5f56e661 Mon Sep 17 00:00:00 2001 From: Alexey Zaytsev Date: Wed, 24 Jun 2009 16:22:30 +0400 Subject: [PATCH 0056/1346] PCI: make pci_name() take const argument Since this function should never modify it (saves warnings when called with const args too). Signed-off-by: Alexey Zaytsev Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/pci.h b/include/linux/pci.h index d304ddf412d..115fb7ba508 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1145,7 +1145,7 @@ static inline void pci_set_drvdata(struct pci_dev *pdev, void *data) /* If you want to know what to call your pci_dev, ask this function. * Again, it's a wrapper around the generic device. */ -static inline const char *pci_name(struct pci_dev *pdev) +static inline const char *pci_name(const struct pci_dev *pdev) { return dev_name(&pdev->dev); } From 2c21fd4b333e4c780a46edcd6d1e85bfc6cdf371 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Tue, 23 Jun 2009 17:40:04 +0900 Subject: [PATCH 0057/1346] PCI MSI: shorten PCI_MSIX_ENTRY_* symbol names These names are too long! Drop _OFFSET to save some bytes/lines. Reviewed-by: Matthew Wilcox Signed-off-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- drivers/pci/msi.c | 18 ++++++++---------- drivers/pci/msi.h | 10 +++++----- 2 files changed, 13 insertions(+), 15 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 628c14150d4..a088fc6f583 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -151,7 +151,7 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag) { u32 mask_bits = desc->masked; unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET; + PCI_MSIX_ENTRY_VECTOR_CTRL; mask_bits &= ~1; mask_bits |= flag; writel(mask_bits, desc->mask_base + offset); @@ -188,9 +188,9 @@ void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg) void __iomem *base = entry->mask_base + entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; - msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET); - msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET); - msg->data = readl(base + PCI_MSIX_ENTRY_DATA_OFFSET); + msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR); + msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR); + msg->data = readl(base + PCI_MSIX_ENTRY_DATA); } else { struct pci_dev *dev = entry->dev; int pos = entry->msi_attrib.pos; @@ -225,11 +225,9 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg) base = entry->mask_base + entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; - writel(msg->address_lo, - base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET); - writel(msg->address_hi, - base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET); - writel(msg->data, base + PCI_MSIX_ENTRY_DATA_OFFSET); + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); + writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); + writel(msg->data, base + PCI_MSIX_ENTRY_DATA); } else { struct pci_dev *dev = entry->dev; int pos = entry->msi_attrib.pos; @@ -493,7 +491,7 @@ static int msix_capability_init(struct pci_dev *dev, set_irq_msi(entry->irq, entry); j = entries[i].entry; entry->masked = readl(base + j * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET); + PCI_MSIX_ENTRY_VECTOR_CTRL); msix_mask_irq(entry, 1); i++; } diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h index a0662842550..de27c1cb5a2 100644 --- a/drivers/pci/msi.h +++ b/drivers/pci/msi.h @@ -6,11 +6,11 @@ #ifndef MSI_H #define MSI_H -#define PCI_MSIX_ENTRY_SIZE 16 -#define PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET 0 -#define PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET 4 -#define PCI_MSIX_ENTRY_DATA_OFFSET 8 -#define PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET 12 +#define PCI_MSIX_ENTRY_SIZE 16 +#define PCI_MSIX_ENTRY_LOWER_ADDR 0 +#define PCI_MSIX_ENTRY_UPPER_ADDR 4 +#define PCI_MSIX_ENTRY_DATA 8 +#define PCI_MSIX_ENTRY_VECTOR_CTRL 12 #define msi_control_reg(base) (base + PCI_MSI_FLAGS) #define msi_lower_address_reg(base) (base + PCI_MSI_ADDRESS_LO) From 7ba1930db02fc3118165338ef4e562869f575583 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Tue, 23 Jun 2009 17:39:27 +0900 Subject: [PATCH 0058/1346] PCI MSI: Unmask MSI if setup failed The initial state of mask register of MSI is unmasked. We set it masked before calling arch_setup_msi_irqs(). If arch_setup_msi_irq() fails, it is better to restore the state of the mask register. Reviewed-by: Matthew Wilcox Signed-off-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- drivers/pci/msi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index a088fc6f583..9ab4fe8f20a 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -383,6 +383,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) /* Configure MSI capability structure */ ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { + msi_mask_irq(entry, mask, ~mask); msi_free_irqs(dev); return ret; } From 12abb8ba8444f7c9b355bbdd44a6d0839f7a41b6 Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Wed, 24 Jun 2009 12:08:09 +0900 Subject: [PATCH 0059/1346] PCI MSI: Fix restoration of MSI/MSI-X mask states in suspend/resume There are 2 problems on mask states in suspend/resume. [1]: It is better to restore the mask states of MSI/MSI-X to initial states (MSI is unmasked, MSI-X is masked) when we release the device. The pci_msi_shutdown() does the restoration of mask states for MSI, while the msi_free_irqs() does it for MSI-X. In other words, in the "disable" path both of MSI and MSI-X are handled, but in the "shutdown" path only MSI is handled. MSI: pci_disable_msi() => pci_msi_shutdown() [ mask states for MSI restored ] => msi_set_enable(dev, pos, 0); => msi_free_irqs() MSI-X: pci_disable_msix() => pci_msix_shutdown() => msix_set_enable(dev, 0); => msix_free_all_irqs => msi_free_irqs() [ mask states for MSI-X restored ] This patch moves the masking for MSI-X from msi_free_irqs() to pci_msix_shutdown(). This change has some positive side effects: - It prevents OS from touching mask states before reading preserved bits in the register, which can be happen if msi_free_irqs() is called from error path in msix_capability_init(). - It also prevents touching the register after turning off MSI-X in "disable" path, which can be a problem on some devices. [2]: We have cache of the mask state in msi_desc, which is automatically updated when msi/msix_mask_irq() is called. This cached states are used for the resume. But since what need to be restored in the resume is the states before the shutdown on the suspend, calling msi/msix_mask_irq() from pci_msi/msix_shutdown() is not appropriate. This patch introduces __msi/msix_mask_irq() that do mask as same as msi/msix_mask_irq() but does not update cached state, for use in pci_msi/msix_shutdown(). [updated: get rid of msi/msix_mask_irq_nocache() (proposed by Matthew Wilcox)] Reviewed-by: Matthew Wilcox Signed-off-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- drivers/pci/msi.c | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 9ab4fe8f20a..d986afb7032 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -127,17 +127,23 @@ static inline __attribute_const__ u32 msi_enabled_mask(u16 control) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { u32 mask_bits = desc->masked; if (!desc->msi_attrib.maskbit) - return; + return 0; mask_bits &= ~mask; mask_bits |= flag; pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits); - desc->masked = mask_bits; + + return mask_bits; +} + +static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + desc->masked = __msi_mask_irq(desc, mask, flag); } /* @@ -147,7 +153,7 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) * file. This saves a few milliseconds when initialising devices with lots * of MSI-X interrupts. */ -static void msix_mask_irq(struct msi_desc *desc, u32 flag) +static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag) { u32 mask_bits = desc->masked; unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + @@ -155,7 +161,13 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag) mask_bits &= ~1; mask_bits |= flag; writel(mask_bits, desc->mask_base + offset); - desc->masked = mask_bits; + + return mask_bits; +} + +static void msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + desc->masked = __msix_mask_irq(desc, flag); } static void msi_set_mask_bit(unsigned irq, u32 flag) @@ -616,9 +628,11 @@ void pci_msi_shutdown(struct pci_dev *dev) pci_intx_for_msi(dev, 1); dev->msi_enabled = 0; + /* Return the device with MSI unmasked as initial states */ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &ctrl); mask = msi_capable_mask(ctrl); - msi_mask_irq(desc, mask, ~mask); + /* Keep cached state to be restored */ + __msi_mask_irq(desc, mask, ~mask); /* Restore dev->irq to its default pin-assertion irq */ dev->irq = desc->msi_attrib.default_irq; @@ -658,7 +672,6 @@ static int msi_free_irqs(struct pci_dev* dev) list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { if (entry->msi_attrib.is_msix) { - msix_mask_irq(entry, 1); if (list_is_last(&entry->list, &dev->msi_list)) iounmap(entry->mask_base); } @@ -746,9 +759,17 @@ static void msix_free_all_irqs(struct pci_dev *dev) void pci_msix_shutdown(struct pci_dev* dev) { + struct msi_desc *entry; + if (!pci_msi_enable || !dev || !dev->msix_enabled) return; + /* Return the device with MSI-X masked as initial states */ + list_for_each_entry(entry, &dev->msi_list, list) { + /* Keep cached states to be restored */ + __msix_mask_irq(entry, 1); + } + msix_set_enable(dev, 0); pci_intx_for_msi(dev, 1); dev->msix_enabled = 0; From 2cdb3f1d834aab27a927be7555fbf4f9e43e9261 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 24 Jun 2009 19:01:19 -0700 Subject: [PATCH 0060/1346] x86/PCI: fix boundary checking when using root CRS Don't touch info->res_num if we are out of space. Acked-by: Gary Hade Tested-by: Gary Hade Signed-off-by: Yinghai Lu Signed-off-by: Jesse Barnes --- arch/x86/pci/acpi.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b26626dc517..8bf152910eb 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -68,6 +68,10 @@ setup_resource(struct acpi_resource *acpi_res, void *data) unsigned long flags; struct resource *root; int max_root_bus_resources = PCI_BUS_NUM_RESOURCES; + u64 start, end; + + if (bus_has_transparent_bridge(info->bus)) + max_root_bus_resources -= 3; status = resource_to_addr(acpi_res, &addr); if (!ACPI_SUCCESS(status)) @@ -84,25 +88,24 @@ setup_resource(struct acpi_resource *acpi_res, void *data) } else return AE_OK; - res = &info->res[info->res_num]; - res->name = info->name; - res->flags = flags; - res->start = addr.minimum + addr.translation_offset; - res->end = res->start + addr.address_length - 1; - res->child = NULL; - - if (bus_has_transparent_bridge(info->bus)) - max_root_bus_resources -= 3; + start = addr.minimum + addr.translation_offset; + end = start + addr.address_length - 1; if (info->res_num >= max_root_bus_resources) { printk(KERN_WARNING "PCI: Failed to allocate 0x%lx-0x%lx " "from %s for %s due to _CRS returning more than " - "%d resource descriptors\n", (unsigned long) res->start, - (unsigned long) res->end, root->name, info->name, + "%d resource descriptors\n", (unsigned long) start, + (unsigned long) end, root->name, info->name, max_root_bus_resources); - info->res_num++; return AE_OK; } + res = &info->res[info->res_num]; + res->name = info->name; + res->flags = flags; + res->start = start; + res->end = end; + res->child = NULL; + if (insert_resource(root, res)) { printk(KERN_ERR "PCI: Failed to allocate 0x%lx-0x%lx " "from %s for %s\n", (unsigned long) res->start, From 626fdfec1588ac1341a37805809d03a719d977e0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 24 Jun 2009 20:00:12 -0700 Subject: [PATCH 0061/1346] x86/PCI: get root CRS before scanning children This allows us to remove adjust_transparent_bridge_resources and give x86_pci_root_bus_res_quirks a chance when _CRS is not used or not there. Acked-by: Gary Hade Tested-by: Gary Hade Signed-off-by: Yinghai Lu Signed-off-by: Jesse Barnes --- arch/x86/pci/acpi.c | 32 +++++++++----------------------- arch/x86/pci/amd_bus.c | 8 ++++++-- 2 files changed, 15 insertions(+), 25 deletions(-) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 8bf152910eb..1014eb4bfc3 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -117,23 +117,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data) return AE_OK; } -static void -adjust_transparent_bridge_resources(struct pci_bus *bus) -{ - struct pci_dev *dev; - - list_for_each_entry(dev, &bus->devices, bus_list) { - int i; - u16 class = dev->class >> 8; - - if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent) { - for(i = 3; i < PCI_BUS_NUM_RESOURCES; i++) - dev->subordinate->resource[i] = - dev->bus->resource[i - 3]; - } - } -} - static void get_current_resources(struct acpi_device *device, int busnum, int domain, struct pci_bus *bus) @@ -161,8 +144,6 @@ get_current_resources(struct acpi_device *device, int busnum, info.res_num = 0; acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, &info); - if (info.res_num) - adjust_transparent_bridge_resources(bus); return; @@ -225,8 +206,15 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do */ memcpy(bus->sysdata, sd, sizeof(*sd)); kfree(sd); - } else - bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd); + } else { + bus = pci_create_bus(NULL, busnum, &pci_root_ops, sd); + if (bus) { + if (pci_probe & PCI_USE__CRS) + get_current_resources(device, busnum, domain, + bus); + bus->subordinate = pci_scan_child_bus(bus); + } + } if (!bus) kfree(sd); @@ -241,8 +229,6 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do #endif } - if (bus && (pci_probe & PCI_USE__CRS)) - get_current_resources(device, busnum, domain, bus); return bus; } diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index f893d6a6e80..3ffa10df20b 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -100,8 +100,9 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) int j; struct pci_root_info *info; - /* don't go for it if _CRS is used */ - if (pci_probe & PCI_USE__CRS) + /* don't go for it if _CRS is used already */ + if (b->resource[0] != &ioport_resource || + b->resource[1] != &iomem_resource) return; /* if only one root bus, don't need to anything */ @@ -116,6 +117,9 @@ void x86_pci_root_bus_res_quirks(struct pci_bus *b) if (i == pci_root_num) return; + printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n", + b->number); + info = &pci_root_info[i]; for (j = 0; j < info->res_num; j++) { struct resource *res; From 9e314996e3dc5189b9b36dce67088e882e989897 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 30 Jun 2009 15:00:20 +0200 Subject: [PATCH 0062/1346] x86: Fix symbol annotation for arch/x86/lib/clear_page_64.S::clear_page_c Noticed the zero-sized function symbol while looking at 'perf' profiles, it causes the profiler to display those addresses in hexa. Turns out that this was wrong/bogus for an eternity. Signed-off-by: Mike Galbraith Acked-by: Alexander van Heukelum Acked-by: Cyrill Gorcunov LKML-Reference: <1246366820.6538.1.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- arch/x86/lib/clear_page_64.S | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index 9a10a78bb4a..ebeafcce04a 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -5,15 +5,14 @@ * Zero a page. * rdi page */ - ALIGN -clear_page_c: +ENTRY(clear_page_c) CFI_STARTPROC movl $4096/8,%ecx xorl %eax,%eax rep stosq ret CFI_ENDPROC -ENDPROC(clear_page) +ENDPROC(clear_page_c) ENTRY(clear_page) CFI_STARTPROC From 789d03f584484af85dbdc64935270c8e45f36ef7 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 30 Jun 2009 11:52:23 +0100 Subject: [PATCH 0063/1346] x86: Fix fixmap ordering The merge of the 32- and 64-bit fixmap headers made a latent bug on x86-64 a real one: with the right config settings it is possible for FIX_OHCI1394_BASE to overlap the FIX_BTMAP_* range. Signed-off-by: Jan Beulich Cc: # for 2.6.30.x LKML-Reference: <4A4A0A8702000078000082E8@vpn.id2.novell.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fixmap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 2d81af3974a..3eb0f79a532 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -114,9 +114,6 @@ enum fixed_addresses { FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ FIX_TEXT_POKE1, __end_of_permanent_fixed_addresses, -#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT - FIX_OHCI1394_BASE, -#endif /* * 256 temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. @@ -129,6 +126,9 @@ enum fixed_addresses { FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 - (__end_of_permanent_fixed_addresses & 255), FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1, +#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT + FIX_OHCI1394_BASE, +#endif #ifdef CONFIG_X86_32 FIX_WP_TEST, #endif From 04a820ead0838c76e9c1242feb5e71048bf3e9dc Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Tue, 30 Jun 2009 02:14:00 -0400 Subject: [PATCH 0064/1346] olpc_battery: Fix up eeprom read function The eeprom read function was placing values into the wrong place in 'buf'; we were starting from buf[off], rather than buf[0]. Also, the for loop that we were using was much uglier than it needed to be. This cleans it up a bit. Signed-off-by: Andres Salomon Signed-off-by: Anton Vorontsov --- drivers/power/olpc_battery.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/power/olpc_battery.c b/drivers/power/olpc_battery.c index 5fbca2681ba..9c216dd4155 100644 --- a/drivers/power/olpc_battery.c +++ b/drivers/power/olpc_battery.c @@ -8,6 +8,7 @@ * published by the Free Software Foundation. */ +#include #include #include #include @@ -334,21 +335,21 @@ static ssize_t olpc_bat_eeprom_read(struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { uint8_t ec_byte; - int ret, end; + int ret; + int i; if (off >= EEPROM_SIZE) return 0; if (off + count > EEPROM_SIZE) count = EEPROM_SIZE - off; - end = EEPROM_START + off + count; - for (ec_byte = EEPROM_START + off; ec_byte < end; ec_byte++) { - ret = olpc_ec_cmd(EC_BAT_EEPROM, &ec_byte, 1, - &buf[ec_byte - EEPROM_START], 1); + for (i = 0; i < count; i++) { + ec_byte = EEPROM_START + off + i; + ret = olpc_ec_cmd(EC_BAT_EEPROM, &ec_byte, 1, &buf[i], 1); if (ret) { - printk(KERN_ERR "olpc-battery: EC command " - "EC_BAT_EEPROM @ 0x%x failed -" - " %d!\n", ec_byte, ret); + pr_err("olpc-battery: " + "EC_BAT_EEPROM cmd @ 0x%x failed - %d!\n", + ec_byte, ret); return -EIO; } } From 8f7e57985fa794ab6afdcd3642581d9e1fe6de31 Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Tue, 30 Jun 2009 02:16:17 -0400 Subject: [PATCH 0065/1346] olpc_battery: Ensure that the TRICKLE bit is checked There are times when the battery is present but trickle charging, and the EC sets only the TRICKLE bit. So we must check for the bit when we're checking the charging/present status. Signed-off-by: Andres Salomon Signed-off-by: Anton Vorontsov --- drivers/power/olpc_battery.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/power/olpc_battery.c b/drivers/power/olpc_battery.c index 9c216dd4155..58e419299cd 100644 --- a/drivers/power/olpc_battery.c +++ b/drivers/power/olpc_battery.c @@ -36,6 +36,7 @@ #define BAT_STAT_AC 0x10 #define BAT_STAT_CHARGING 0x20 #define BAT_STAT_DISCHARGING 0x40 +#define BAT_STAT_TRICKLE 0x80 #define BAT_ERR_INFOFAIL 0x02 #define BAT_ERR_OVERVOLTAGE 0x04 @@ -90,7 +91,7 @@ static char bat_serial[17]; /* Ick */ static int olpc_bat_get_status(union power_supply_propval *val, uint8_t ec_byte) { if (olpc_platform_info.ecver > 0x44) { - if (ec_byte & BAT_STAT_CHARGING) + if (ec_byte & (BAT_STAT_CHARGING | BAT_STAT_TRICKLE)) val->intval = POWER_SUPPLY_STATUS_CHARGING; else if (ec_byte & BAT_STAT_DISCHARGING) val->intval = POWER_SUPPLY_STATUS_DISCHARGING; @@ -220,7 +221,8 @@ static int olpc_bat_get_property(struct power_supply *psy, It doesn't matter though -- the EC will return the last-known information, and it's as if we just ran that _little_ bit faster and managed to read it out before the battery went away. */ - if (!(ec_byte & BAT_STAT_PRESENT) && psp != POWER_SUPPLY_PROP_PRESENT) + if (!(ec_byte & (BAT_STAT_PRESENT | BAT_STAT_TRICKLE)) && + psp != POWER_SUPPLY_PROP_PRESENT) return -ENODEV; switch (psp) { @@ -230,7 +232,8 @@ static int olpc_bat_get_property(struct power_supply *psy, return ret; break; case POWER_SUPPLY_PROP_PRESENT: - val->intval = !!(ec_byte & BAT_STAT_PRESENT); + val->intval = !!(ec_byte & (BAT_STAT_PRESENT | + BAT_STAT_TRICKLE)); break; case POWER_SUPPLY_PROP_HEALTH: From bfdb46ce8494eae30dbaae65c81e684e6db6228b Mon Sep 17 00:00:00 2001 From: Ryan Mallon Date: Thu, 18 Jun 2009 11:26:26 +1200 Subject: [PATCH 0066/1346] Add ds2782 battery gas gauge driver This patch adds a driver for ds2782 battery devices. Signed-off-by: Ryan Mallon Signed-off-by: Anton Vorontsov --- drivers/power/Kconfig | 7 + drivers/power/Makefile | 1 + drivers/power/ds2782_battery.c | 330 +++++++++++++++++++++++++++++++++ 3 files changed, 338 insertions(+) create mode 100644 drivers/power/ds2782_battery.c diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 7eda34838bf..bdbc4f73fcd 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -43,6 +43,13 @@ config BATTERY_DS2760 help Say Y here to enable support for batteries with ds2760 chip. +config BATTERY_DS2782 + tristate "DS2782 standalone gas-gauge" + depends on I2C + help + Say Y here to enable support for the DS2782 standalone battery + gas-gauge. + config BATTERY_PMU tristate "Apple PMU battery" depends on PPC32 && ADB_PMU diff --git a/drivers/power/Makefile b/drivers/power/Makefile index daf3179689a..380d17c9ae2 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_APM_POWER) += apm_power.o obj-$(CONFIG_WM8350_POWER) += wm8350_power.o obj-$(CONFIG_BATTERY_DS2760) += ds2760_battery.o +obj-$(CONFIG_BATTERY_DS2782) += ds2782_battery.o obj-$(CONFIG_BATTERY_PMU) += pmu_battery.o obj-$(CONFIG_BATTERY_OLPC) += olpc_battery.o obj-$(CONFIG_BATTERY_TOSA) += tosa_battery.o diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c new file mode 100644 index 00000000000..da14f374cb6 --- /dev/null +++ b/drivers/power/ds2782_battery.c @@ -0,0 +1,330 @@ +/* + * I2C client/driver for the Maxim/Dallas DS2782 Stand-Alone Fuel Gauge IC + * + * Copyright (C) 2009 Bluewater Systems Ltd + * + * Author: Ryan Mallon + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define DS2782_REG_RARC 0x06 /* Remaining active relative capacity */ + +#define DS2782_REG_VOLT_MSB 0x0c +#define DS2782_REG_TEMP_MSB 0x0a +#define DS2782_REG_CURRENT_MSB 0x0e + +/* EEPROM Block */ +#define DS2782_REG_RSNSP 0x69 /* Sense resistor value */ + +/* Current unit measurement in uA for a 1 milli-ohm sense resistor */ +#define DS2782_CURRENT_UNITS 1563 + +#define to_ds2782_info(x) container_of(x, struct ds2782_info, battery) + +struct ds2782_info { + struct i2c_client *client; + struct power_supply battery; + int id; +}; + +static DEFINE_IDR(battery_id); +static DEFINE_MUTEX(battery_lock); + +static inline int ds2782_read_reg(struct ds2782_info *info, int reg, u8 *val) +{ + int ret; + + ret = i2c_smbus_read_byte_data(info->client, reg); + if (ret < 0) { + dev_err(&info->client->dev, "register read failed\n"); + return ret; + } + + *val = ret; + return 0; +} + +static inline int ds2782_read_reg16(struct ds2782_info *info, int reg_msb, + s16 *val) +{ + int ret; + + ret = swab16(i2c_smbus_read_word_data(info->client, reg_msb)); + if (ret < 0) { + dev_err(&info->client->dev, "register read failed\n"); + return ret; + } + + *val = ret; + return 0; +} + +static int ds2782_get_temp(struct ds2782_info *info, int *temp) +{ + s16 raw; + int err; + + /* + * Temperature is measured in units of 0.125 degrees celcius, the + * power_supply class measures temperature in tenths of degrees + * celsius. The temperature value is stored as a 10 bit number, plus + * sign in the upper bits of a 16 bit register. + */ + err = ds2782_read_reg16(info, DS2782_REG_TEMP_MSB, &raw); + if (err) + return err; + *temp = ((raw / 32) * 125) / 100; + return 0; +} + +static int ds2782_get_current(struct ds2782_info *info, int *current_uA) +{ + int sense_res; + int err; + u8 sense_res_raw; + s16 raw; + + /* + * The units of measurement for current are dependent on the value of + * the sense resistor. + */ + err = ds2782_read_reg(info, DS2782_REG_RSNSP, &sense_res_raw); + if (err) + return err; + if (sense_res_raw == 0) { + dev_err(&info->client->dev, "sense resistor value is 0\n"); + return -ENXIO; + } + sense_res = 1000 / sense_res_raw; + + dev_dbg(&info->client->dev, "sense resistor = %d milli-ohms\n", + sense_res); + err = ds2782_read_reg16(info, DS2782_REG_CURRENT_MSB, &raw); + if (err) + return err; + *current_uA = raw * (DS2782_CURRENT_UNITS / sense_res); + return 0; +} + +static int ds2782_get_voltage(struct ds2782_info *info, int *voltage_uA) +{ + s16 raw; + int err; + + /* + * Voltage is measured in units of 4.88mV. The voltage is stored as + * a 10-bit number plus sign, in the upper bits of a 16-bit register + */ + err = ds2782_read_reg16(info, DS2782_REG_VOLT_MSB, &raw); + if (err) + return err; + *voltage_uA = (raw / 32) * 4800; + return 0; +} + +static int ds2782_get_capacity(struct ds2782_info *info, int *capacity) +{ + int err; + u8 raw; + + err = ds2782_read_reg(info, DS2782_REG_RARC, &raw); + if (err) + return err; + *capacity = raw; + return raw; +} + +static int ds2782_get_status(struct ds2782_info *info, int *status) +{ + int err; + int current_uA; + int capacity; + + err = ds2782_get_current(info, ¤t_uA); + if (err) + return err; + + err = ds2782_get_capacity(info, &capacity); + if (err) + return err; + + if (capacity == 100) + *status = POWER_SUPPLY_STATUS_FULL; + else if (current_uA == 0) + *status = POWER_SUPPLY_STATUS_NOT_CHARGING; + else if (current_uA < 0) + *status = POWER_SUPPLY_STATUS_DISCHARGING; + else + *status = POWER_SUPPLY_STATUS_CHARGING; + + return 0; +} + +static int ds2782_battery_get_property(struct power_supply *psy, + enum power_supply_property prop, + union power_supply_propval *val) +{ + struct ds2782_info *info = to_ds2782_info(psy); + int ret; + + switch (prop) { + case POWER_SUPPLY_PROP_STATUS: + ret = ds2782_get_status(info, &val->intval); + break; + + case POWER_SUPPLY_PROP_CAPACITY: + ret = ds2782_get_capacity(info, &val->intval); + break; + + case POWER_SUPPLY_PROP_VOLTAGE_NOW: + ret = ds2782_get_voltage(info, &val->intval); + break; + + case POWER_SUPPLY_PROP_CURRENT_NOW: + ret = ds2782_get_current(info, &val->intval); + break; + + case POWER_SUPPLY_PROP_TEMP: + ret = ds2782_get_temp(info, &val->intval); + break; + + default: + ret = -EINVAL; + } + + return ret; +} + +static enum power_supply_property ds2782_battery_props[] = { + POWER_SUPPLY_PROP_STATUS, + POWER_SUPPLY_PROP_CAPACITY, + POWER_SUPPLY_PROP_VOLTAGE_NOW, + POWER_SUPPLY_PROP_CURRENT_NOW, + POWER_SUPPLY_PROP_TEMP, +}; + +static void ds2782_power_supply_init(struct power_supply *battery) +{ + battery->type = POWER_SUPPLY_TYPE_BATTERY; + battery->properties = ds2782_battery_props; + battery->num_properties = ARRAY_SIZE(ds2782_battery_props); + battery->get_property = ds2782_battery_get_property; + battery->external_power_changed = NULL; +} + +static int ds2782_battery_remove(struct i2c_client *client) +{ + struct ds2782_info *info = i2c_get_clientdata(client); + + power_supply_unregister(&info->battery); + kfree(info->battery.name); + + mutex_lock(&battery_lock); + idr_remove(&battery_id, info->id); + mutex_unlock(&battery_lock); + + i2c_set_clientdata(client, info); + + kfree(info); + return 0; +} + +static int ds2782_battery_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct ds2782_info *info; + int ret; + int num; + + /* Get an ID for this battery */ + ret = idr_pre_get(&battery_id, GFP_KERNEL); + if (ret == 0) { + ret = -ENOMEM; + goto fail_id; + } + + mutex_lock(&battery_lock); + ret = idr_get_new(&battery_id, client, &num); + mutex_unlock(&battery_lock); + if (ret < 0) + goto fail_id; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + ret = -ENOMEM; + goto fail_info; + } + + info->battery.name = kasprintf(GFP_KERNEL, "ds2782-%d", num); + if (!info->battery.name) { + ret = -ENOMEM; + goto fail_name; + } + + i2c_set_clientdata(client, info); + info->client = client; + ds2782_power_supply_init(&info->battery); + + ret = power_supply_register(&client->dev, &info->battery); + if (ret) { + dev_err(&client->dev, "failed to register battery\n"); + goto fail_register; + } + + return 0; + +fail_register: + kfree(info->battery.name); +fail_name: + i2c_set_clientdata(client, info); + kfree(info); +fail_info: + mutex_lock(&battery_lock); + idr_remove(&battery_id, num); + mutex_unlock(&battery_lock); +fail_id: + return ret; +} + +static const struct i2c_device_id ds2782_id[] = { + {"ds2782", 0}, + {}, +}; + +static struct i2c_driver ds2782_battery_driver = { + .driver = { + .name = "ds2782-battery", + }, + .probe = ds2782_battery_probe, + .remove = ds2782_battery_remove, + .id_table = ds2782_id, +}; + +static int __init ds2782_init(void) +{ + return i2c_add_driver(&ds2782_battery_driver); +} +module_init(ds2782_init); + +static void __exit ds2782_exit(void) +{ + i2c_del_driver(&ds2782_battery_driver); +} +module_exit(ds2782_exit); + +MODULE_AUTHOR("Ryan Mallon "); +MODULE_DESCRIPTION("Maxim/Dallas DS2782 Stand-Alone Fuel Gauage IC driver"); +MODULE_LICENSE("GPL"); From 1f208ea67821703fd4de056ea6f0baa81f4ad4a5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 09:00:44 +1000 Subject: [PATCH 0067/1346] perf report: Fix -z option Fix a copy and paste error, -z was setting the group option. Signed-off-by: Anton Blanchard Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org LKML-Reference: <20090630230140.714204656@samba.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-top.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index cf0d21f1ae1..5c2965562c5 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -675,7 +675,7 @@ static const struct option options[] = { "put the counters into a counter group"), OPT_STRING('s', "sym-filter", &sym_filter, "pattern", "only display symbols matchig this pattern"), - OPT_BOOLEAN('z', "zero", &group, + OPT_BOOLEAN('z', "zero", &zero, "zero history across updates"), OPT_INTEGER('F', "freq", &freq, "profile at this frequency"), From 6717534ddc328ae5cdf89f1ef802db83fc451f19 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 09:00:45 +1000 Subject: [PATCH 0068/1346] perf_counter tools: Remove zlib dependency The zlib devel libraries may not be installed and since we aren't using zlib we may as well remove it. Signed-off-by: Anton Blanchard Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org LKML-Reference: <20090630230140.802078956@samba.org> Signed-off-by: Ingo Molnar --- tools/perf/Makefile | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 9c6d0ae3708..f572c90f610 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -381,12 +381,6 @@ ifndef CC_LD_DYNPATH endif endif -ifdef ZLIB_PATH - BASIC_CFLAGS += -I$(ZLIB_PATH)/include - EXTLIBS += -L$(ZLIB_PATH)/$(lib) $(CC_LD_DYNPATH)$(ZLIB_PATH)/$(lib) -endif -EXTLIBS += -lz - ifdef NEEDS_SOCKET EXTLIBS += -lsocket endif From 2ab52083ffc057014e502cf3473adc41436922fa Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 09:00:46 +1000 Subject: [PATCH 0069/1346] perf top: Move skip symbols to an array Move the list of symbols we skip into an array, making it easier to add new ones. Signed-off-by: Anton Blanchard Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org LKML-Reference: <20090630230140.904782938@samba.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-top.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5c2965562c5..731ec6d79c1 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -286,11 +286,22 @@ static void *display_thread(void *arg) return NULL; } +/* Tag samples to be skipped. */ +char *skip_symbols[] = { + "default_idle", + "cpu_idle", + "enter_idle", + "exit_idle", + "mwait_idle", + NULL +}; + static int symbol_filter(struct dso *self, struct symbol *sym) { static int filter_match; struct sym_entry *syme; const char *name = sym->name; + int i; if (!strcmp(name, "_text") || !strcmp(name, "_etext") || @@ -302,13 +313,12 @@ static int symbol_filter(struct dso *self, struct symbol *sym) return 1; syme = dso__sym_priv(self, sym); - /* Tag samples to be skipped. */ - if (!strcmp("default_idle", name) || - !strcmp("cpu_idle", name) || - !strcmp("enter_idle", name) || - !strcmp("exit_idle", name) || - !strcmp("mwait_idle", name)) - syme->skip = 1; + for (i = 0; skip_symbols[i]; i++) { + if (!strcmp(skip_symbols[i], name)) { + syme->skip = 1; + break; + } + } if (filter_match == 1) { filter_end = sym->start; From 3a3393ef75a14ae259a82f3f38624efa17884168 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 09:00:47 +1000 Subject: [PATCH 0070/1346] perf top: Add ppc64 specific skip symbols and strip ppc64 . prefix Filter out some ppc64 specific idle loop functions and remove leading '.' on ppc64 text symbols. Signed-off-by: Anton Blanchard Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org LKML-Reference: <20090630230140.995643441@samba.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-top.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 731ec6d79c1..0506cd6e04c 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -293,6 +293,8 @@ char *skip_symbols[] = { "enter_idle", "exit_idle", "mwait_idle", + "ppc64_runlatch_off", + "pseries_dedicated_idle_sleep", NULL }; @@ -303,6 +305,13 @@ static int symbol_filter(struct dso *self, struct symbol *sym) const char *name = sym->name; int i; + /* + * ppc64 uses function descriptors and appends a '.' to the + * start of every instruction address. Remove it. + */ + if (name[0] == '.') + name++; + if (!strcmp(name, "_text") || !strcmp(name, "_etext") || !strcmp(name, "_sinittext") || From d8db1b57d31a6b30ea2f0df318eab50fc92b38d6 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 09:00:48 +1000 Subject: [PATCH 0071/1346] perf report: Fix reporting of hypervisor PERF_EVENT_MISC_* is not a bitmask, so we have to mask and compare. Signed-off-by: Anton Blanchard Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org LKML-Reference: <20090630230141.088394681@samba.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 135b7837e6b..88e88c510ae 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1213,6 +1213,7 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) struct map *map = NULL; void *more_data = event->ip.__more_data; struct ip_callchain *chain = NULL; + int cpumode; if (sample_type & PERF_SAMPLE_PERIOD) { period = *(u64 *)more_data; @@ -1256,7 +1257,9 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) if (comm_list && !strlist__has_entry(comm_list, thread->comm)) return 0; - if (event->header.misc & PERF_EVENT_MISC_KERNEL) { + cpumode = event->header.misc & PERF_EVENT_MISC_CPUMODE_MASK; + + if (cpumode == PERF_EVENT_MISC_KERNEL) { show = SHOW_KERNEL; level = 'k'; @@ -1264,7 +1267,7 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) dprintf(" ...... dso: %s\n", dso->name); - } else if (event->header.misc & PERF_EVENT_MISC_USER) { + } else if (cpumode == PERF_EVENT_MISC_USER) { show = SHOW_USER; level = '.'; From fb9c818873a788c5c01c9868cc6050df96e2c7df Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 09:00:49 +1000 Subject: [PATCH 0072/1346] perf report: Add hypervisor dso Add a dso for hypervisor samples. We don't get any symbol information on the ppc64 hypervisor but this at least gives us a high level summary of the time spent in there. Signed-off-by: Anton Blanchard Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org LKML-Reference: <20090630230141.182536873@samba.org> Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 88e88c510ae..3f5d8ea05ff 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -121,6 +121,7 @@ typedef union event_union { static LIST_HEAD(dsos); static struct dso *kernel_dso; static struct dso *vdso; +static struct dso *hypervisor_dso; static void dsos__add(struct dso *dso) { @@ -202,6 +203,11 @@ static int load_kernel(void) dsos__add(vdso); + hypervisor_dso = dso__new("[hypervisor]", 0); + if (!hypervisor_dso) + return -1; + dsos__add(hypervisor_dso); + return err; } @@ -640,7 +646,8 @@ sort__sym_print(FILE *fp, struct hist_entry *self) if (self->sym) { ret += fprintf(fp, "[%c] %s", - self->dso == kernel_dso ? 'k' : '.', self->sym->name); + self->dso == kernel_dso ? 'k' : + self->dso == hypervisor_dso ? 'h' : '.', self->sym->name); } else { ret += fprintf(fp, "%#016llx", (u64)self->ip); } @@ -963,6 +970,9 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, } switch (context) { + case PERF_CONTEXT_HV: + dso = hypervisor_dso; + break; case PERF_CONTEXT_KERNEL: dso = kernel_dso; break; @@ -1275,6 +1285,9 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) } else { show = SHOW_HV; level = 'H'; + + dso = hypervisor_dso; + dprintf(" ...... dso: [hypervisor]\n"); } From 944c54e7fc5ccf961bef2b5449958436b85de459 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 1 Jul 2009 00:10:16 +0200 Subject: [PATCH 0073/1346] ia64/PCI: adjust section annotation for pcibios_setup() Should be __init. Acked-by: Tony Luck Signed-off-by: Jesse Barnes --- arch/ia64/pci/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 729298f4b23..7de76dd352f 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -537,7 +537,7 @@ pcibios_align_resource (void *data, struct resource *res, /* * PCI BIOS setup, always defaults to SAL interface */ -char * __devinit +char * __init pcibios_setup (char *str) { return str; From 9198aa77b69647d1d91207f8075763abe7dc0bf4 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 1 Jul 2009 05:35:13 +0200 Subject: [PATCH 0074/1346] perf_counter tools: Fix storage size allocation of callchain list Fix a confusion while giving the size of a callchain list during its allocation. We are using the wrong structure size. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246419315-9968-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/util/callchain.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index ad3c2857896..bbf7813fefe 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -74,7 +74,7 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain, int start) for (i = start; i < chain->nr; i++) { struct callchain_list *call; - call = malloc(sizeof(*chain)); + call = malloc(sizeof(*call)); if (!call) { perror("not enough memory for the code path tree"); return; From 4424961ad6621a02c6b4c9093e801002c1bb9f65 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 1 Jul 2009 05:35:14 +0200 Subject: [PATCH 0075/1346] perf_counter tools: Resolve symbols in callchains This patch resolves the names, when possible, of each ip present in the callchains while using the -c option with perf report. Example: 5.40% [k] __d_lookup 5.37% perf_callchain perf_counter_overflow intel_pmu_handle_irq perf_counter_nmi_handler notifier_call_chain atomic_notifier_call_chain notify_die do_nmi nmi do_lookup __link_path_walk path_walk do_path_lookup user_path_at sys_faccessat sys_access system_call_fastpath 0x7fb609846f77 0.01% perf_callchain perf_counter_overflow intel_pmu_handle_irq perf_counter_nmi_handler notifier_call_chain atomic_notifier_call_chain notify_die do_nmi nmi do_lookup __link_path_walk path_walk do_path_lookup user_path_at sys_faccessat Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246419315-9968-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 102 +++++++++++++++++++++++------------- tools/perf/util/callchain.c | 33 +++++++----- tools/perf/util/callchain.h | 5 +- 3 files changed, 90 insertions(+), 50 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3f5d8ea05ff..197793051fa 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -794,8 +794,15 @@ callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples) ret += callchain__fprintf(fp, self->parent, total_samples); - list_for_each_entry(chain, &self->val, list) - ret += fprintf(fp, " %p\n", (void *)chain->ip); + list_for_each_entry(chain, &self->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + if (chain->sym) + ret += fprintf(fp, " %s\n", chain->sym->name); + else + ret += fprintf(fp, " %p\n", + (void *)chain->ip); + } return ret; } @@ -930,6 +937,55 @@ static int call__match(struct symbol *sym) return 0; } +static struct symbol ** +resolve_callchain(struct thread *thread, struct map *map, + struct ip_callchain *chain, struct hist_entry *entry) +{ + int i; + struct symbol **syms; + u64 context = PERF_CONTEXT_MAX; + + if (callchain) { + syms = calloc(chain->nr, sizeof(*syms)); + if (!syms) { + fprintf(stderr, "Can't allocate memory for symbols\n"); + exit(-1); + } + } + + for (i = 0; i < chain->nr; i++) { + u64 ip = chain->ips[i]; + struct dso *dso = NULL; + struct symbol *sym; + + if (ip >= PERF_CONTEXT_MAX) { + context = ip; + continue; + } + + switch (context) { + case PERF_CONTEXT_KERNEL: + dso = kernel_dso; + break; + default: + break; + } + + sym = resolve_symbol(thread, NULL, &dso, &ip); + + if (sym) { + if (sort__has_parent && call__match(sym) && + !entry->parent) + entry->parent = sym; + if (!callchain) + break; + syms[i] = sym; + } + } + + return syms; +} + /* * collect histogram counts */ @@ -942,6 +998,7 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, struct rb_node **p = &hist.rb_node; struct rb_node *parent = NULL; struct hist_entry *he; + struct symbol **syms = NULL; struct hist_entry entry = { .thread = thread, .map = map, @@ -955,39 +1012,11 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, }; int cmp; - if (sort__has_parent && chain) { - u64 context = PERF_CONTEXT_MAX; - int i; - - for (i = 0; i < chain->nr; i++) { - u64 ip = chain->ips[i]; - struct dso *dso = NULL; - struct symbol *sym; - - if (ip >= PERF_CONTEXT_MAX) { - context = ip; - continue; - } - - switch (context) { case PERF_CONTEXT_HV: dso = hypervisor_dso; break; - case PERF_CONTEXT_KERNEL: - dso = kernel_dso; - break; - default: - break; - } - - sym = resolve_symbol(thread, NULL, &dso, &ip); - - if (sym && call__match(sym)) { - entry.parent = sym; - break; - } - } - } + if ((sort__has_parent || callchain) && chain) + syms = resolve_callchain(thread, map, chain, &entry); while (*p != NULL) { parent = *p; @@ -997,8 +1026,10 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, if (!cmp) { he->count += count; - if (callchain) - append_chain(&he->callchain, chain); + if (callchain) { + append_chain(&he->callchain, chain, syms); + free(syms); + } return 0; } @@ -1014,7 +1045,8 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, *he = entry; if (callchain) { callchain_init(&he->callchain); - append_chain(&he->callchain, chain); + append_chain(&he->callchain, chain, syms); + free(syms); } rb_link_node(&he->rb_node, parent, p); rb_insert_color(&he->rb_node, &hist); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index bbf7813fefe..6568cb198ba 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -67,7 +67,8 @@ static struct callchain_node *create_child(struct callchain_node *parent) } static void -fill_node(struct callchain_node *node, struct ip_callchain *chain, int start) +fill_node(struct callchain_node *node, struct ip_callchain *chain, int start, + struct symbol **syms) { int i; @@ -80,24 +81,26 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain, int start) return; } call->ip = chain->ips[i]; + call->sym = syms[i]; list_add_tail(&call->list, &node->val); } node->val_nr = i - start; } -static void add_child(struct callchain_node *parent, struct ip_callchain *chain) +static void add_child(struct callchain_node *parent, struct ip_callchain *chain, + struct symbol **syms) { struct callchain_node *new; new = create_child(parent); - fill_node(new, chain, parent->val_nr); + fill_node(new, chain, parent->val_nr, syms); new->hit = 1; } static void split_add_child(struct callchain_node *parent, struct ip_callchain *chain, - struct callchain_list *to_split, int idx) + struct callchain_list *to_split, int idx, struct symbol **syms) { struct callchain_node *new; @@ -109,21 +112,22 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, parent->val_nr = idx; /* create the new one */ - add_child(parent, chain); + add_child(parent, chain, syms); } static int __append_chain(struct callchain_node *root, struct ip_callchain *chain, - int start); + int start, struct symbol **syms); static int -__append_chain_children(struct callchain_node *root, struct ip_callchain *chain) +__append_chain_children(struct callchain_node *root, struct ip_callchain *chain, + struct symbol **syms) { struct callchain_node *rnode; /* lookup in childrens */ list_for_each_entry(rnode, &root->children, brothers) { - int ret = __append_chain(rnode, chain, root->val_nr); + int ret = __append_chain(rnode, chain, root->val_nr, syms); if (!ret) return 0; } @@ -132,7 +136,7 @@ __append_chain_children(struct callchain_node *root, struct ip_callchain *chain) static int __append_chain(struct callchain_node *root, struct ip_callchain *chain, - int start) + int start, struct symbol **syms) { struct callchain_list *cnode; int i = start; @@ -154,7 +158,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, /* we match only a part of the node. Split it and add the new chain */ if (i < root->val_nr) { - split_add_child(root, chain, cnode, i); + split_add_child(root, chain, cnode, i, syms); return 0; } @@ -164,11 +168,12 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, return 0; } - return __append_chain_children(root, chain); + return __append_chain_children(root, chain, syms); } -void append_chain(struct callchain_node *root, struct ip_callchain *chain) +void append_chain(struct callchain_node *root, struct ip_callchain *chain, + struct symbol **syms) { - if (__append_chain_children(root, chain) == -1) - add_child(root, chain); + if (__append_chain_children(root, chain, syms) == -1) + add_child(root, chain, syms); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index fa1cd2f71fd..c942daa712e 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -4,6 +4,7 @@ #include "../perf.h" #include "list.h" #include "rbtree.h" +#include "symbol.h" struct callchain_node { @@ -18,6 +19,7 @@ struct callchain_node { struct callchain_list { unsigned long ip; + struct symbol *sym; struct list_head list; }; @@ -28,6 +30,7 @@ static inline void callchain_init(struct callchain_node *node) INIT_LIST_HEAD(&node->val); } -void append_chain(struct callchain_node *root, struct ip_callchain *chain); +void append_chain(struct callchain_node *root, struct ip_callchain *chain, + struct symbol **syms); void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node); #endif From deac911cbdcb124fa0cee47c588e0cb0400b23b7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 1 Jul 2009 05:35:15 +0200 Subject: [PATCH 0076/1346] perf_counter tools: Various fixes for callchains The symbol resolving has of course revealed some bugs in the callchain tree handling. This patch fixes some of them, including: - inherit the children from the parents while splitting a node - fix list range moving - fix indexes setting in callchains - create a child on the current node if the path doesn't match in the existent children (was only done on the root) - compare using symbols when possible so that we can match a function using any ip inside by referring to its start address. The practical effects are: - remove double callchains - fix upside down or any random order of callchains - fix wrong paths - fix bad hits and percentage accounts Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246419315-9968-4-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/util/callchain.c | 122 ++++++++++++++++++++++++++---------- 1 file changed, 90 insertions(+), 32 deletions(-) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 6568cb198ba..440db12c635 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -4,6 +4,9 @@ * Handle the callchains from the stream in an ad-hoc radix tree and then * sort them in an rbtree. * + * Using a radix for code path provides a fast retrieval and factorizes + * memory use. Also that lets us use the paths in a hierarchical graph view. + * */ #include @@ -14,7 +17,8 @@ #include "callchain.h" -static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) +static void +rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -49,7 +53,12 @@ void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node) rb_insert_callchain(rb_root, node); } -static struct callchain_node *create_child(struct callchain_node *parent) +/* + * Create a child for a parent. If inherit_children, then the new child + * will become the new parent of it's parent children + */ +static struct callchain_node * +create_child(struct callchain_node *parent, bool inherit_children) { struct callchain_node *new; @@ -61,14 +70,27 @@ static struct callchain_node *create_child(struct callchain_node *parent) new->parent = parent; INIT_LIST_HEAD(&new->children); INIT_LIST_HEAD(&new->val); + + if (inherit_children) { + struct callchain_node *next; + + list_splice(&parent->children, &new->children); + INIT_LIST_HEAD(&parent->children); + + list_for_each_entry(next, &new->children, brothers) + next->parent = new; + } list_add_tail(&new->brothers, &parent->children); return new; } +/* + * Fill the node with callchain values + */ static void -fill_node(struct callchain_node *node, struct ip_callchain *chain, int start, - struct symbol **syms) +fill_node(struct callchain_node *node, struct ip_callchain *chain, + int start, struct symbol **syms) { int i; @@ -84,54 +106,80 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain, int start, call->sym = syms[i]; list_add_tail(&call->list, &node->val); } - node->val_nr = i - start; + node->val_nr = chain->nr - start; + if (!node->val_nr) + printf("Warning: empty node in callchain tree\n"); } -static void add_child(struct callchain_node *parent, struct ip_callchain *chain, - struct symbol **syms) +static void +add_child(struct callchain_node *parent, struct ip_callchain *chain, + int start, struct symbol **syms) { struct callchain_node *new; - new = create_child(parent); - fill_node(new, chain, parent->val_nr, syms); + new = create_child(parent, false); + fill_node(new, chain, start, syms); new->hit = 1; } +/* + * Split the parent in two parts (a new child is created) and + * give a part of its callchain to the created child. + * Then create another child to host the given callchain of new branch + */ static void split_add_child(struct callchain_node *parent, struct ip_callchain *chain, - struct callchain_list *to_split, int idx, struct symbol **syms) + struct callchain_list *to_split, int idx_parents, int idx_local, + struct symbol **syms) { struct callchain_node *new; + struct list_head *old_tail; + int idx_total = idx_parents + idx_local; /* split */ - new = create_child(parent); - list_move_tail(&to_split->list, &new->val); - new->hit = parent->hit; - parent->hit = 0; - parent->val_nr = idx; + new = create_child(parent, true); - /* create the new one */ - add_child(parent, chain, syms); + /* split the callchain and move a part to the new child */ + old_tail = parent->val.prev; + list_del_range(&to_split->list, old_tail); + new->val.next = &to_split->list; + new->val.prev = old_tail; + to_split->list.prev = &new->val; + old_tail->next = &new->val; + + /* split the hits */ + new->hit = parent->hit; + new->val_nr = parent->val_nr - idx_local; + parent->val_nr = idx_local; + + /* create a new child for the new branch if any */ + if (idx_total < chain->nr) { + parent->hit = 0; + add_child(parent, chain, idx_total, syms); + } else { + parent->hit = 1; + } } static int __append_chain(struct callchain_node *root, struct ip_callchain *chain, int start, struct symbol **syms); -static int +static void __append_chain_children(struct callchain_node *root, struct ip_callchain *chain, - struct symbol **syms) + struct symbol **syms, int start) { struct callchain_node *rnode; /* lookup in childrens */ list_for_each_entry(rnode, &root->children, brothers) { - int ret = __append_chain(rnode, chain, root->val_nr, syms); + int ret = __append_chain(rnode, chain, start, syms); if (!ret) - return 0; + return; } - return -1; + /* nothing in children, add to the current node */ + add_child(root, chain, start, syms); } static int @@ -142,14 +190,22 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, int i = start; bool found = false; - /* lookup in the current node */ + /* + * Lookup in the current node + * If we have a symbol, then compare the start to match + * anywhere inside a function. + */ list_for_each_entry(cnode, &root->val, list) { - if (cnode->ip != chain->ips[i++]) + if (i == chain->nr) + break; + if (cnode->sym && syms[i]) { + if (cnode->sym->start != syms[i]->start) + break; + } else if (cnode->ip != chain->ips[i]) break; if (!found) found = true; - if (i == chain->nr) - break; + i++; } /* matches not, relay on the parent */ @@ -157,23 +213,25 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, return -1; /* we match only a part of the node. Split it and add the new chain */ - if (i < root->val_nr) { - split_add_child(root, chain, cnode, i, syms); + if (i - start < root->val_nr) { + split_add_child(root, chain, cnode, start, i - start, syms); return 0; } /* we match 100% of the path, increment the hit */ - if (i == root->val_nr) { + if (i - start == root->val_nr && i == chain->nr) { root->hit++; return 0; } - return __append_chain_children(root, chain, syms); + /* We match the node and still have a part remaining */ + __append_chain_children(root, chain, syms, i); + + return 0; } void append_chain(struct callchain_node *root, struct ip_callchain *chain, struct symbol **syms) { - if (__append_chain_children(root, chain, syms) == -1) - add_child(root, chain, syms); + __append_chain_children(root, chain, syms, 0); } From 0a456fc58fb8ef3c53d18297ab5cd5d2a70d146b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 1 Jul 2009 13:07:01 +1000 Subject: [PATCH 0077/1346] powerpc/perf_counter: Enable alternate PR/HV bits for POWER7 POWER7 has the same PR/HV bit layout as POWER6, so set the flag. Signed-off-by: Anton Blanchard Acked-by: Paul Mackerras Cc: a.p.zijlstra@chello.nl Cc: benh@kernel.crashing.org LKML-Reference: <20090701030701.GI3563@kryten> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/power7-pmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 5d755ef7ac8..5a9f5cbd40a 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -358,6 +358,7 @@ static struct power_pmu power7_pmu = { .get_constraint = power7_get_constraint, .get_alternatives = power7_get_alternatives, .disable_pmc = power7_disable_pmc, + .flags = PPMU_ALT_SIPR, .n_generic = ARRAY_SIZE(power7_generic_events), .generic_events = power7_generic_events, .cache_events = &power7_cache_events, From 61c45981ddbd718136d49464f00d2f11938aaa6e Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 1 Jul 2009 13:04:34 +1000 Subject: [PATCH 0078/1346] perf_counter tools: Rework event string parsing/syntax This reworks the parser for event descriptors to make it more consistent in what it accepts. It is now structured as a recursive descent parser for the following grammar: events ::= event ( ("," | space) space* event )* event ::= ( raw_event | numeric_event | symbolic_event | generic_hw_event ) [ event_modifier ] raw_event ::= "r" hex_number numeric_event ::= number ":" number number ::= decimal_number | "0x" hex_number | "0" octal_number symbolic_event ::= string_from_event_symbols_array generic_hw_event::= cache_type ( "-" ( cache_op | cache_result ) )* event_modifier ::= ":" ( "u" | "k" | "h" )+ with the extra restriction that you can have at most one cache_op and at most one cache_result. We pass the current string pointer by reference (i.e. as a const char **) to the various parsing functions so that they can advance the pointer to indicate how much they consumed. They return 0 if they didn't recognize the thing at the pointer or 1 if they did (and advance the pointer past it). This also fixes parse_aliases to take the longest matching alias from the table, not the first one. Otherwise "l1-data" would match the "l1-d" alias and the "ata" would not be consumed. This allows event modifiers indicating what processor modes to count in to be applied to any event, not just numeric events, and adds a ":h" modifier to indicate counting in hypervisor mode. Specifying ":u" now sets both exclude_kernel and exclude_hv, and so on. Multiple modes can be specified, e.g. ":uk" will count in user or hypervisor mode (i.e. only exclude_kernel will be set). Signed-off-by: Paul Mackerras Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: <19018.53826.843815.189847@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar --- tools/perf/util/parse-events.c | 242 ++++++++++++++++++++++----------- 1 file changed, 165 insertions(+), 77 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4d042f104cd..e6b83a3311a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -184,16 +184,20 @@ char *event_name(int counter) return "unknown"; } -static int parse_aliases(const char *str, char *names[][MAX_ALIASES], int size) +static int parse_aliases(const char **str, char *names[][MAX_ALIASES], int size) { int i, j; + int n, longest = -1; for (i = 0; i < size; i++) { - for (j = 0; j < MAX_ALIASES; j++) { - if (!names[i][j]) - break; - if (strcasestr(str, names[i][j])) - return i; + for (j = 0; j < MAX_ALIASES && names[i][j]; j++) { + n = strlen(names[i][j]); + if (n > longest && !strncasecmp(*str, names[i][j], n)) + longest = n; + } + if (longest > 0) { + *str += longest; + return i; } } @@ -201,30 +205,53 @@ static int parse_aliases(const char *str, char *names[][MAX_ALIASES], int size) } static int -parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr) +parse_generic_hw_event(const char **str, struct perf_counter_attr *attr) { - int cache_type = -1, cache_op = 0, cache_result = 0; + const char *s = *str; + int cache_type = -1, cache_op = -1, cache_result = -1; - cache_type = parse_aliases(str, hw_cache, PERF_COUNT_HW_CACHE_MAX); + cache_type = parse_aliases(&s, hw_cache, PERF_COUNT_HW_CACHE_MAX); /* * No fallback - if we cannot get a clear cache type * then bail out: */ if (cache_type == -1) - return -EINVAL; + return 0; + + while ((cache_op == -1 || cache_result == -1) && *s == '-') { + ++s; + + if (cache_op == -1) { + cache_op = parse_aliases(&s, hw_cache_op, + PERF_COUNT_HW_CACHE_OP_MAX); + if (cache_op >= 0) { + if (!is_cache_op_valid(cache_type, cache_op)) + return 0; + continue; + } + } + + if (cache_result == -1) { + cache_result = parse_aliases(&s, hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX); + if (cache_result >= 0) + continue; + } + + /* + * Can't parse this as a cache op or result, so back up + * to the '-'. + */ + --s; + break; + } - cache_op = parse_aliases(str, hw_cache_op, PERF_COUNT_HW_CACHE_OP_MAX); /* * Fall back to reads: */ if (cache_op == -1) cache_op = PERF_COUNT_HW_CACHE_OP_READ; - if (!is_cache_op_valid(cache_type, cache_op)) - return -EINVAL; - - cache_result = parse_aliases(str, hw_cache_result, - PERF_COUNT_HW_CACHE_RESULT_MAX); /* * Fall back to accesses: */ @@ -234,19 +261,110 @@ parse_generic_hw_symbols(const char *str, struct perf_counter_attr *attr) attr->config = cache_type | (cache_op << 8) | (cache_result << 16); attr->type = PERF_TYPE_HW_CACHE; - return 0; + *str = s; + return 1; } static int check_events(const char *str, unsigned int i) { - if (!strncmp(str, event_symbols[i].symbol, - strlen(event_symbols[i].symbol))) - return 1; + int n; - if (strlen(event_symbols[i].alias)) - if (!strncmp(str, event_symbols[i].alias, - strlen(event_symbols[i].alias))) + n = strlen(event_symbols[i].symbol); + if (!strncmp(str, event_symbols[i].symbol, n)) + return n; + + n = strlen(event_symbols[i].alias); + if (n) + if (!strncmp(str, event_symbols[i].alias, n)) + return n; + return 0; +} + +static int +parse_symbolic_event(const char **strp, struct perf_counter_attr *attr) +{ + const char *str = *strp; + unsigned int i; + int n; + + for (i = 0; i < ARRAY_SIZE(event_symbols); i++) { + n = check_events(str, i); + if (n > 0) { + attr->type = event_symbols[i].type; + attr->config = event_symbols[i].config; + *strp = str + n; return 1; + } + } + return 0; +} + +static int parse_raw_event(const char **strp, struct perf_counter_attr *attr) +{ + const char *str = *strp; + u64 config; + int n; + + if (*str != 'r') + return 0; + n = hex2u64(str + 1, &config); + if (n > 0) { + *strp = str + n + 1; + attr->type = PERF_TYPE_RAW; + attr->config = config; + return 1; + } + return 0; +} + +static int +parse_numeric_event(const char **strp, struct perf_counter_attr *attr) +{ + const char *str = *strp; + char *endp; + unsigned long type; + u64 config; + + type = strtoul(str, &endp, 0); + if (endp > str && type < PERF_TYPE_MAX && *endp == ':') { + str = endp + 1; + config = strtoul(str, &endp, 0); + if (endp > str) { + attr->type = type; + attr->config = config; + *strp = endp; + return 1; + } + } + return 0; +} + +static int +parse_event_modifier(const char **strp, struct perf_counter_attr *attr) +{ + const char *str = *strp; + int eu = 1, ek = 1, eh = 1; + + if (*str++ != ':') + return 0; + while (*str) { + if (*str == 'u') + eu = 0; + else if (*str == 'k') + ek = 0; + else if (*str == 'h') + eh = 0; + else + break; + ++str; + } + if (str >= *strp + 2) { + *strp = str; + attr->exclude_user = eu; + attr->exclude_kernel = ek; + attr->exclude_hv = eh; + return 1; + } return 0; } @@ -254,73 +372,43 @@ static int check_events(const char *str, unsigned int i) * Each event can have multiple symbolic names. * Symbolic names are (almost) exactly matched. */ -static int parse_event_symbols(const char *str, struct perf_counter_attr *attr) +static int parse_event_symbols(const char **str, struct perf_counter_attr *attr) { - u64 config, id; - int type; - unsigned int i; - const char *sep, *pstr; - - if (str[0] == 'r' && hex2u64(str + 1, &config) > 0) { - attr->type = PERF_TYPE_RAW; - attr->config = config; - + if (!(parse_raw_event(str, attr) || + parse_numeric_event(str, attr) || + parse_symbolic_event(str, attr) || + parse_generic_hw_event(str, attr))) return 0; - } - pstr = str; - sep = strchr(pstr, ':'); - if (sep) { - type = atoi(pstr); - pstr = sep + 1; - id = atoi(pstr); - sep = strchr(pstr, ':'); - if (sep) { - pstr = sep + 1; - if (strchr(pstr, 'k')) - attr->exclude_user = 1; - if (strchr(pstr, 'u')) - attr->exclude_kernel = 1; - } - attr->type = type; - attr->config = id; + parse_event_modifier(str, attr); - return 0; - } - - for (i = 0; i < ARRAY_SIZE(event_symbols); i++) { - if (check_events(str, i)) { - attr->type = event_symbols[i].type; - attr->config = event_symbols[i].config; - - return 0; - } - } - - return parse_generic_hw_symbols(str, attr); + return 1; } int parse_events(const struct option *opt, const char *str, int unset) { struct perf_counter_attr attr; - int ret; - memset(&attr, 0, sizeof(attr)); -again: - if (nr_counters == MAX_COUNTERS) - return -1; + for (;;) { + if (nr_counters == MAX_COUNTERS) + return -1; - ret = parse_event_symbols(str, &attr); - if (ret < 0) - return ret; + memset(&attr, 0, sizeof(attr)); + if (!parse_event_symbols(&str, &attr)) + return -1; - attrs[nr_counters] = attr; - nr_counters++; + if (!(*str == 0 || *str == ',' || isspace(*str))) + return -1; - str = strstr(str, ","); - if (str) { - str++; - goto again; + attrs[nr_counters] = attr; + nr_counters++; + + if (*str == 0) + break; + if (*str == ',') + ++str; + while (isspace(*str)) + ++str; } return 0; From 4a2bb6fcc80e6330ca2f2393e98605052cc7780b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 30 Jun 2009 17:08:09 -0400 Subject: [PATCH 0079/1346] kprobes: No need to unlock kprobe_insn_mutex Remove needless kprobe_insn_mutex unlocking during safety check in garbage collection, because if someone releases a dirty slot during safety check (which ensures other cpus doesn't execute all dirty slots), the safety check must be fail. So, we need to hold the mutex while checking safety. Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Jim Keniston Cc: Ananth N Mavinakayanahalli LKML-Reference: <20090630210809.17851.28781.stgit@localhost.localdomain> Signed-off-by: Ingo Molnar --- kernel/kprobes.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c0fa54b276d..16b5739c516 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -237,13 +237,9 @@ static int __kprobes collect_garbage_slots(void) { struct kprobe_insn_page *kip; struct hlist_node *pos, *next; - int safety; /* Ensure no-one is preepmted on the garbages */ - mutex_unlock(&kprobe_insn_mutex); - safety = check_safety(); - mutex_lock(&kprobe_insn_mutex); - if (safety != 0) + if (check_safety()) return -EAGAIN; hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) { From 88a69dfbc6ab1e3b51bba8c9103055e21089ebb9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 1 Jul 2009 11:17:20 +0200 Subject: [PATCH 0080/1346] perf report: Fix HV bit mismerge MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix: builtin-report.c: In function ‘hist_entry__add’: builtin-report.c:1015: error: case label not within a switch statement builtin-report.c:1017: error: break statement not within loop or switch Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 197793051fa..7d2b49adcdc 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -964,6 +964,9 @@ resolve_callchain(struct thread *thread, struct map *map, } switch (context) { + case PERF_CONTEXT_HV: + dso = hypervisor_dso; + break; case PERF_CONTEXT_KERNEL: dso = kernel_dso; break; @@ -1012,9 +1015,6 @@ hist_entry__add(struct thread *thread, struct map *map, struct dso *dso, }; int cmp; - case PERF_CONTEXT_HV: - dso = hypervisor_dso; - break; if ((sort__has_parent || callchain) && chain) syms = resolve_callchain(thread, map, chain, &entry); From a70c352a37671fe1ebcbd317b439aa4760f4ccb7 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Wed, 1 Jul 2009 11:51:18 +0300 Subject: [PATCH 0081/1346] xen: Use kcalloc() in xen_init_IRQ() The init_IRQ() function is now called with slab allocator initialized. Therefore, we must not use the bootmem allocator in xen_init_IRQ(). Fixes the following boot-time warning: ------------[ cut here ]------------ WARNING: at mm/bootmem.c:535 alloc_arch_preferred_bootmem+0x27/0x45() Modules linked in: Pid: 0, comm: swapper Not tainted 2.6.30 #1 Call Trace: [] ? warn_slowpath_common+0x73/0xb0 [] ? pvclock_clocksource_read+0x49/0x90 [] ? alloc_arch_preferred_bootmem+0x27/0x45 [] ? ___alloc_bootmem_nopanic+0x39/0xc9 [] ? ___alloc_bootmem+0x9/0x2f [] ? xen_init_IRQ+0x25/0x61 [] ? start_kernel+0x1b5/0x29e ---[ end trace 4eaa2a86a8e2da22 ]--- Acked-by: Jeremy Fitzhardinge Tested-by: Christian Kujau Reported-by: Christian Kujau Signed-off-by: Pekka Enberg Cc: lists@nerdbynature.de Cc: jeremy.fitzhardinge@citrix.com LKML-Reference: <1246438278.22417.28.camel@penberg-laptop> Signed-off-by: Ingo Molnar --- drivers/xen/events.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 891d2e90753..abad71b1632 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -927,9 +927,9 @@ static struct irq_chip xen_dynamic_chip __read_mostly = { void __init xen_init_IRQ(void) { int i; - size_t size = nr_cpu_ids * sizeof(struct cpu_evtchn_s); - cpu_evtchn_mask_p = alloc_bootmem(size); + cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s), + GFP_KERNEL); BUG_ON(cpu_evtchn_mask_p == NULL); init_evtchn_cpu_bindings(); From f37a291c527c954df4da568de718ebb36b8261c0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 1 Jul 2009 12:37:06 +0200 Subject: [PATCH 0082/1346] perf_counter tools: Add more warnings and fix/annotate them Enable -Wextra. This found a few real bugs plus a number of signed/unsigned type mismatches/uncleanlinesses. It also required a few annotations All things considered it was still worth it so lets try with this enabled for now. Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- tools/perf/Makefile | 2 +- tools/perf/builtin-annotate.c | 12 ++++----- tools/perf/builtin-help.c | 6 +++-- tools/perf/builtin-list.c | 2 +- tools/perf/builtin-record.c | 4 +-- tools/perf/builtin-report.c | 22 +++++++-------- tools/perf/builtin-stat.c | 18 +++++++------ tools/perf/builtin-top.c | 8 +++--- tools/perf/perf.c | 5 +--- tools/perf/perf.h | 2 ++ tools/perf/util/alias.c | 2 +- tools/perf/util/cache.h | 1 + tools/perf/util/callchain.c | 15 ++++++----- tools/perf/util/callchain.h | 10 +++---- tools/perf/util/color.c | 10 ++++--- tools/perf/util/config.c | 18 +++++++------ tools/perf/util/exec_cmd.c | 5 +++- tools/perf/util/help.c | 26 ++++++++++-------- tools/perf/util/help.h | 6 ++--- tools/perf/util/parse-events.c | 2 +- tools/perf/util/parse-options.c | 2 +- tools/perf/util/parse-options.h | 25 +++++++++-------- tools/perf/util/quote.c | 48 ++++++++++++++++++--------------- tools/perf/util/quote.h | 2 +- tools/perf/util/strbuf.c | 13 ++++----- tools/perf/util/strbuf.h | 10 +++---- tools/perf/util/wrapper.c | 5 ++-- 27 files changed, 152 insertions(+), 129 deletions(-) diff --git a/tools/perf/Makefile b/tools/perf/Makefile index f572c90f610..eddf076b19d 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -164,7 +164,7 @@ endif # CFLAGS and LDFLAGS are for the users to override from the command line. -CFLAGS = $(M64) -ggdb3 -Wall -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -Werror -O6 +CFLAGS = $(M64) -ggdb3 -Wall -Wextra -Wstrict-prototypes -Wmissing-declarations -Wmissing-prototypes -std=gnu99 -Wdeclaration-after-statement -Werror -O6 LDFLAGS = -lpthread -lrt -lelf -lm ALL_CFLAGS = $(CFLAGS) ALL_LDFLAGS = $(LDFLAGS) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 722c0f54e54..6cba70daf12 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -160,7 +160,7 @@ static void dsos__fprintf(FILE *fp) static struct symbol *vdso__find_symbol(struct dso *dso, u64 ip) { - return dso__find_symbol(kernel_dso, ip); + return dso__find_symbol(dso, ip); } static int load_kernel(void) @@ -203,7 +203,7 @@ static u64 map__map_ip(struct map *map, u64 ip) return ip - map->start + map->pgoff; } -static u64 vdso__map_ip(struct map *map, u64 ip) +static u64 vdso__map_ip(struct map *map __used, u64 ip) { return ip; } @@ -600,7 +600,7 @@ static LIST_HEAD(hist_entry__sort_list); static int sort_dimension__add(char *tok) { - int i; + unsigned int i; for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { struct sort_dimension *sd = &sort_dimensions[i]; @@ -1069,7 +1069,7 @@ parse_line(FILE *file, struct symbol *sym, u64 start, u64 len) static const char *prev_color; unsigned int offset; size_t line_len; - u64 line_ip; + s64 line_ip; int ret; char *c; @@ -1428,7 +1428,7 @@ more: head += size; - if (offset + head < stat.st_size) + if (offset + head < (unsigned long)stat.st_size) goto more; rc = EXIT_SUCCESS; @@ -1492,7 +1492,7 @@ static void setup_sorting(void) free(str); } -int cmd_annotate(int argc, const char **argv, const char *prefix) +int cmd_annotate(int argc, const char **argv, const char *prefix __used) { symbol__init(); diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 0f32dc3f3c4..2599d86a733 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -3,6 +3,7 @@ * * Builtin help command */ +#include "perf.h" #include "util/cache.h" #include "builtin.h" #include "util/exec_cmd.h" @@ -277,7 +278,7 @@ static struct cmdnames main_cmds, other_cmds; void list_common_cmds_help(void) { - int i, longest = 0; + unsigned int i, longest = 0; for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { if (longest < strlen(common_cmds[i].name)) @@ -415,9 +416,10 @@ static void show_html_page(const char *perf_cmd) open_html(page_path.buf); } -int cmd_help(int argc, const char **argv, const char *prefix) +int cmd_help(int argc, const char **argv, const char *prefix __used) { const char *alias; + load_command_list("perf-", &main_cmds, &other_cmds); perf_config(perf_help_config, NULL); diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index fe60e37c96e..f990fa8a35c 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -13,7 +13,7 @@ #include "util/parse-options.h" #include "util/parse-events.h" -int cmd_list(int argc, const char **argv, const char *prefix) +int cmd_list(int argc __used, const char **argv __used, const char *prefix __used) { print_events(); return 0; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index d18546f37d7..4ef78a5e6f3 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -294,7 +294,7 @@ static void pid_synthesize_mmap_samples(pid_t pid) while (1) { char bf[BUFSIZ], *pbf = bf; struct mmap_event mmap_ev = { - .header.type = PERF_EVENT_MMAP, + .header = { .type = PERF_EVENT_MMAP }, }; int n; size_t size; @@ -650,7 +650,7 @@ static const struct option options[] = { OPT_END() }; -int cmd_record(int argc, const char **argv, const char *prefix) +int cmd_record(int argc, const char **argv, const char *prefix __used) { int counter; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 7d2b49adcdc..007363db3b1 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -177,7 +177,7 @@ static void dsos__fprintf(FILE *fp) static struct symbol *vdso__find_symbol(struct dso *dso, u64 ip) { - return dso__find_symbol(kernel_dso, ip); + return dso__find_symbol(dso, ip); } static int load_kernel(void) @@ -239,7 +239,7 @@ static u64 map__map_ip(struct map *map, u64 ip) return ip - map->start + map->pgoff; } -static u64 vdso__map_ip(struct map *map, u64 ip) +static u64 vdso__map_ip(struct map *map __used, u64 ip) { return ip; } @@ -712,7 +712,7 @@ static LIST_HEAD(hist_entry__sort_list); static int sort_dimension__add(char *tok) { - int i; + unsigned int i; for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { struct sort_dimension *sd = &sort_dimensions[i]; @@ -801,7 +801,7 @@ callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples) ret += fprintf(fp, " %s\n", chain->sym->name); else ret += fprintf(fp, " %p\n", - (void *)chain->ip); + (void *)(long)chain->ip); } return ret; @@ -938,12 +938,12 @@ static int call__match(struct symbol *sym) } static struct symbol ** -resolve_callchain(struct thread *thread, struct map *map, +resolve_callchain(struct thread *thread, struct map *map __used, struct ip_callchain *chain, struct hist_entry *entry) { - int i; - struct symbol **syms; u64 context = PERF_CONTEXT_MAX; + struct symbol **syms; + unsigned int i; if (callchain) { syms = calloc(chain->nr, sizeof(*syms)); @@ -1183,7 +1183,7 @@ static size_t output__fprintf(FILE *fp, u64 total_samples) fprintf(fp, "# ........"); list_for_each_entry(se, &hist_entry__sort_list, list) { - int i; + unsigned int i; if (exclude_other && (se == &sort_parent)) continue; @@ -1271,7 +1271,7 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) (long long)period); if (sample_type & PERF_SAMPLE_CALLCHAIN) { - int i; + unsigned int i; chain = (void *)more_data; @@ -1667,7 +1667,7 @@ more: if (offset + head >= header->data_offset + header->data_size) goto done; - if (offset + head < stat.st_size) + if (offset + head < (unsigned long)stat.st_size) goto more; done: @@ -1756,7 +1756,7 @@ static void setup_list(struct strlist **list, const char *list_str, } } -int cmd_report(int argc, const char **argv, const char *prefix) +int cmd_report(int argc, const char **argv, const char *prefix __used) { symbol__init(); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 2e03524a1de..095a90e012a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -64,7 +64,7 @@ static struct perf_counter_attr default_attrs[] = { static int system_wide = 0; static int verbose = 0; -static int nr_cpus = 0; +static unsigned int nr_cpus = 0; static int run_idx = 0; static int run_count = 1; @@ -108,7 +108,8 @@ static void create_perf_stat_counter(int counter, int pid) PERF_FORMAT_TOTAL_TIME_RUNNING; if (system_wide) { - int cpu; + unsigned int cpu; + for (cpu = 0; cpu < nr_cpus; cpu++) { fd[cpu][counter] = sys_perf_counter_open(attr, -1, cpu, -1, 0); if (fd[cpu][counter] < 0 && verbose) @@ -150,8 +151,8 @@ static inline int nsec_counter(int counter) static void read_counter(int counter) { u64 *count, single_count[3]; - ssize_t res; - int cpu, nv; + unsigned int cpu; + size_t res, nv; int scaled; count = event_res[run_idx][counter]; @@ -165,6 +166,7 @@ static void read_counter(int counter) res = read(fd[cpu][counter], single_count, nv * sizeof(u64)); assert(res == nv * sizeof(u64)); + close(fd[cpu][counter]); fd[cpu][counter] = -1; @@ -200,7 +202,7 @@ static void read_counter(int counter) runtime_cycles[run_idx] = count[0]; } -static int run_perf_stat(int argc, const char **argv) +static int run_perf_stat(int argc __used, const char **argv) { unsigned long long t0, t1; int status = 0; @@ -390,7 +392,7 @@ static void calc_avg(void) event_res_avg[j]+1, event_res[i][j]+1); update_avg("counter/2", j, event_res_avg[j]+2, event_res[i][j]+2); - if (event_scaled[i][j] != -1) + if (event_scaled[i][j] != (u64)-1) update_avg("scaled", j, event_scaled_avg + j, event_scaled[i]+j); else @@ -510,7 +512,7 @@ static const struct option options[] = { OPT_END() }; -int cmd_stat(int argc, const char **argv, const char *prefix) +int cmd_stat(int argc, const char **argv, const char *prefix __used) { int status; @@ -528,7 +530,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix) nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); assert(nr_cpus <= MAX_NR_CPUS); - assert(nr_cpus >= 0); + assert((int)nr_cpus >= 0); /* * We dont want to block the signals - that would cause diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 0506cd6e04c..5f5e7df8302 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -269,7 +269,7 @@ static void print_sym_table(void) } } -static void *display_thread(void *arg) +static void *display_thread(void *arg __used) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; int delay_msecs = delay_secs * 1000; @@ -287,7 +287,7 @@ static void *display_thread(void *arg) } /* Tag samples to be skipped. */ -char *skip_symbols[] = { +static const char *skip_symbols[] = { "default_idle", "cpu_idle", "enter_idle", @@ -426,7 +426,7 @@ static void process_event(u64 ip, int counter, int user) struct mmap_data { int counter; void *base; - unsigned int mask; + int mask; unsigned int prev; }; @@ -705,7 +705,7 @@ static const struct option options[] = { OPT_END() }; -int cmd_top(int argc, const char **argv, const char *prefix) +int cmd_top(int argc, const char **argv, const char *prefix __used) { int counter; diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 4eb72593370..c5656784c61 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -229,9 +229,6 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) use_pager = 1; commit_pager_choice(); - if (p->option & NEED_WORK_TREE) - /* setup_work_tree() */; - status = p->fn(argc, argv, prefix); if (status) return status & 0xff; @@ -266,7 +263,7 @@ static void handle_internal_command(int argc, const char **argv) { "annotate", cmd_annotate, 0 }, { "version", cmd_version, 0 }, }; - int i; + unsigned int i; static const char ext[] = STRIP_EXTENSION; if (sizeof(ext) > 1) { diff --git a/tools/perf/perf.h b/tools/perf/perf.h index ce394192c85..27887c91643 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -52,6 +52,8 @@ static inline unsigned long long rdclock(void) #define __user #define asmlinkage +#define __used __attribute__((__unused__)) + #define unlikely(x) __builtin_expect(!!(x), 0) #define min(x, y) ({ \ typeof(x) _min1 = (x); \ diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c index 9b3dd2b428d..b8144e80bb1 100644 --- a/tools/perf/util/alias.c +++ b/tools/perf/util/alias.c @@ -3,7 +3,7 @@ static const char *alias_key; static char *alias_val; -static int alias_lookup_cb(const char *k, const char *v, void *cb) +static int alias_lookup_cb(const char *k, const char *v, void *cb __used) { if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { if (!v) diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 393d6146d13..161d5f413e2 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -3,6 +3,7 @@ #include "util.h" #include "strbuf.h" +#include "../perf.h" #define PERF_DIR_ENVIRONMENT "PERF_DIR" #define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE" diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 440db12c635..3dceabd9b5e 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -92,7 +92,7 @@ static void fill_node(struct callchain_node *node, struct ip_callchain *chain, int start, struct symbol **syms) { - int i; + unsigned int i; for (i = start; i < chain->nr; i++) { struct callchain_list *call; @@ -135,7 +135,7 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, { struct callchain_node *new; struct list_head *old_tail; - int idx_total = idx_parents + idx_local; + unsigned int idx_total = idx_parents + idx_local; /* split */ new = create_child(parent, true); @@ -164,17 +164,18 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, static int __append_chain(struct callchain_node *root, struct ip_callchain *chain, - int start, struct symbol **syms); + unsigned int start, struct symbol **syms); static void __append_chain_children(struct callchain_node *root, struct ip_callchain *chain, - struct symbol **syms, int start) + struct symbol **syms, unsigned int start) { struct callchain_node *rnode; /* lookup in childrens */ list_for_each_entry(rnode, &root->children, brothers) { - int ret = __append_chain(rnode, chain, start, syms); + unsigned int ret = __append_chain(rnode, chain, start, syms); + if (!ret) return; } @@ -184,10 +185,10 @@ __append_chain_children(struct callchain_node *root, struct ip_callchain *chain, static int __append_chain(struct callchain_node *root, struct ip_callchain *chain, - int start, struct symbol **syms) + unsigned int start, struct symbol **syms) { struct callchain_list *cnode; - int i = start; + unsigned int i = start; bool found = false; /* diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c942daa712e..251d99ecd22 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -10,15 +10,15 @@ struct callchain_node { struct callchain_node *parent; struct list_head brothers; - struct list_head children; - struct list_head val; + struct list_head children; + struct list_head val; struct rb_node rb_node; - int val_nr; - int hit; + unsigned int val_nr; + u64 hit; }; struct callchain_list { - unsigned long ip; + u64 ip; struct symbol *sym; struct list_head list; }; diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 9a8c20ccc53..26f82318b86 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -11,7 +11,8 @@ static int parse_color(const char *name, int len) }; char *end; int i; - for (i = 0; i < ARRAY_SIZE(color_names); i++) { + + for (i = 0; i < (int)ARRAY_SIZE(color_names); i++) { const char *str = color_names[i]; if (!strncasecmp(name, str, len) && !str[len]) return i - 1; @@ -28,7 +29,8 @@ static int parse_attr(const char *name, int len) static const char * const attr_names[] = { "bold", "dim", "ul", "blink", "reverse" }; - int i; + unsigned int i; + for (i = 0; i < ARRAY_SIZE(attr_names); i++) { const char *str = attr_names[i]; if (!strncasecmp(name, str, len) && !str[len]) @@ -222,10 +224,12 @@ int color_fwrite_lines(FILE *fp, const char *color, { if (!*color) return fwrite(buf, count, 1, fp) != 1; + while (count) { char *p = memchr(buf, '\n', count); + if (p != buf && (fputs(color, fp) < 0 || - fwrite(buf, p ? p - buf : count, 1, fp) != 1 || + fwrite(buf, p ? (size_t)(p - buf) : count, 1, fp) != 1 || fputs(PERF_COLOR_RESET, fp) < 0)) return -1; if (!p) diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 3dd13faa6a2..780df541006 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -47,10 +47,12 @@ static int get_next_char(void) static char *parse_value(void) { static char value[1024]; - int quote = 0, comment = 0, len = 0, space = 0; + int quote = 0, comment = 0, space = 0; + size_t len = 0; for (;;) { int c = get_next_char(); + if (len >= sizeof(value) - 1) return NULL; if (c == '\n') { @@ -353,13 +355,13 @@ int perf_config_string(const char **dest, const char *var, const char *value) return 0; } -static int perf_default_core_config(const char *var, const char *value) +static int perf_default_core_config(const char *var __used, const char *value __used) { /* Add other config variables here and to Documentation/config.txt. */ return 0; } -int perf_default_config(const char *var, const char *value, void *dummy) +int perf_default_config(const char *var, const char *value, void *dummy __used) { if (!prefixcmp(var, "core.")) return perf_default_core_config(var, value); @@ -471,10 +473,10 @@ static int matches(const char* key, const char* value) !regexec(store.value_regex, value, 0, NULL, 0))); } -static int store_aux(const char* key, const char* value, void *cb) +static int store_aux(const char* key, const char* value, void *cb __used) { + int section_len; const char *ep; - size_t section_len; switch (store.state) { case KEY_SEEN: @@ -551,7 +553,7 @@ static int store_write_section(int fd, const char* key) strbuf_addf(&sb, "[%.*s]\n", store.baselen, key); } - success = write_in_full(fd, sb.buf, sb.len) == sb.len; + success = (write_in_full(fd, sb.buf, sb.len) == (ssize_t)sb.len); strbuf_release(&sb); return success; @@ -599,7 +601,7 @@ static int store_write_pair(int fd, const char* key, const char* value) } strbuf_addf(&sb, "%s\n", quote); - success = write_in_full(fd, sb.buf, sb.len) == sb.len; + success = (write_in_full(fd, sb.buf, sb.len) == (ssize_t)sb.len); strbuf_release(&sb); return success; @@ -741,7 +743,7 @@ int perf_config_set_multivar(const char* key, const char* value, } else { struct stat st; char* contents; - size_t contents_sz, copy_begin, copy_end; + ssize_t contents_sz, copy_begin, copy_end; int i, new_line = 0; if (value_regex == NULL) diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c index d3929226315..34a35286738 100644 --- a/tools/perf/util/exec_cmd.c +++ b/tools/perf/util/exec_cmd.c @@ -1,6 +1,9 @@ #include "cache.h" #include "exec_cmd.h" #include "quote.h" + +#include + #define MAX_ARGS 32 extern char **environ; @@ -51,7 +54,7 @@ const char *perf_extract_argv0_path(const char *argv0) slash--; if (slash >= argv0) { - argv0_path = strndup(argv0, slash - argv0); + argv0_path = xstrndup(argv0, slash - argv0); return slash + 1; } diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c index 17a00e0df2c..fbb00978b2e 100644 --- a/tools/perf/util/help.c +++ b/tools/perf/util/help.c @@ -26,7 +26,7 @@ static int term_columns(void) return 80; } -void add_cmdname(struct cmdnames *cmds, const char *name, int len) +void add_cmdname(struct cmdnames *cmds, const char *name, size_t len) { struct cmdname *ent = malloc(sizeof(*ent) + len + 1); @@ -40,7 +40,8 @@ void add_cmdname(struct cmdnames *cmds, const char *name, int len) static void clean_cmdnames(struct cmdnames *cmds) { - int i; + unsigned int i; + for (i = 0; i < cmds->cnt; ++i) free(cmds->names[i]); free(cmds->names); @@ -57,7 +58,7 @@ static int cmdname_compare(const void *a_, const void *b_) static void uniq(struct cmdnames *cmds) { - int i, j; + unsigned int i, j; if (!cmds->cnt) return; @@ -71,7 +72,7 @@ static void uniq(struct cmdnames *cmds) void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) { - int ci, cj, ei; + size_t ci, cj, ei; int cmp; ci = cj = ei = 0; @@ -106,8 +107,9 @@ static void pretty_print_string_list(struct cmdnames *cmds, int longest) printf(" "); for (j = 0; j < cols; j++) { - int n = j * rows + i; - int size = space; + unsigned int n = j * rows + i; + unsigned int size = space; + if (n >= cmds->cnt) break; if (j == cols-1 || n + rows >= cmds->cnt) @@ -208,7 +210,7 @@ void load_command_list(const char *prefix, void list_commands(const char *title, struct cmdnames *main_cmds, struct cmdnames *other_cmds) { - int i, longest = 0; + unsigned int i, longest = 0; for (i = 0; i < main_cmds->cnt; i++) if (longest < main_cmds->names[i]->len) @@ -239,7 +241,8 @@ void list_commands(const char *title, struct cmdnames *main_cmds, int is_in_cmdlist(struct cmdnames *c, const char *s) { - int i; + unsigned int i; + for (i = 0; i < c->cnt; i++) if (!strcmp(s, c->names[i]->name)) return 1; @@ -271,7 +274,8 @@ static int levenshtein_compare(const void *p1, const void *p2) static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) { - int i; + unsigned int i; + ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc); for (i = 0; i < old->cnt; i++) @@ -283,7 +287,7 @@ static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) const char *help_unknown_cmd(const char *cmd) { - int i, n = 0, best_similarity = 0; + unsigned int i, n = 0, best_similarity = 0; struct cmdnames main_cmds, other_cmds; memset(&main_cmds, 0, sizeof(main_cmds)); @@ -345,7 +349,7 @@ const char *help_unknown_cmd(const char *cmd) exit(1); } -int cmd_version(int argc, const char **argv, const char *prefix) +int cmd_version(int argc __used, const char **argv __used, const char *prefix __used) { printf("perf version %s\n", perf_version_string); return 0; diff --git a/tools/perf/util/help.h b/tools/perf/util/help.h index 56bc15406ff..7128783637b 100644 --- a/tools/perf/util/help.h +++ b/tools/perf/util/help.h @@ -2,8 +2,8 @@ #define HELP_H struct cmdnames { - int alloc; - int cnt; + size_t alloc; + size_t cnt; struct cmdname { size_t len; /* also used for similarity index in help.c */ char name[FLEX_ARRAY]; @@ -19,7 +19,7 @@ static inline void mput_char(char c, unsigned int num) void load_command_list(const char *prefix, struct cmdnames *main_cmds, struct cmdnames *other_cmds); -void add_cmdname(struct cmdnames *cmds, const char *name, int len); +void add_cmdname(struct cmdnames *cmds, const char *name, size_t len); /* Here we require that excludes is a sorted list. */ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes); int is_in_cmdlist(struct cmdnames *c, const char *s); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index e6b83a3311a..aed70901df2 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -385,7 +385,7 @@ static int parse_event_symbols(const char **str, struct perf_counter_attr *attr) return 1; } -int parse_events(const struct option *opt, const char *str, int unset) +int parse_events(const struct option *opt __used, const char *str, int unset __used) { struct perf_counter_attr attr; diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index b3affb1658d..9a897b7cce7 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -485,7 +485,7 @@ int parse_options_usage(const char * const *usagestr, } -int parse_opt_verbosity_cb(const struct option *opt, const char *arg, +int parse_opt_verbosity_cb(const struct option *opt, const char *arg __used, int unset) { int *target = opt->value; diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index a1039a6ce0e..15c8aba9c62 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -90,21 +90,20 @@ struct option { intptr_t defval; }; -#define OPT_END() { OPTION_END } -#define OPT_ARGUMENT(l, h) { OPTION_ARGUMENT, 0, (l), NULL, NULL, (h) } -#define OPT_GROUP(h) { OPTION_GROUP, 0, NULL, NULL, NULL, (h) } -#define OPT_BIT(s, l, v, h, b) { OPTION_BIT, (s), (l), (v), NULL, (h), 0, NULL, (b) } -#define OPT_BOOLEAN(s, l, v, h) { OPTION_BOOLEAN, (s), (l), (v), NULL, (h) } -#define OPT_SET_INT(s, l, v, h, i) { OPTION_SET_INT, (s), (l), (v), NULL, (h), 0, NULL, (i) } -#define OPT_SET_PTR(s, l, v, h, p) { OPTION_SET_PTR, (s), (l), (v), NULL, (h), 0, NULL, (p) } -#define OPT_INTEGER(s, l, v, h) { OPTION_INTEGER, (s), (l), (v), NULL, (h) } -#define OPT_LONG(s, l, v, h) { OPTION_LONG, (s), (l), (v), NULL, (h) } -#define OPT_STRING(s, l, v, a, h) { OPTION_STRING, (s), (l), (v), (a), (h) } +#define OPT_END() { .type = OPTION_END } +#define OPT_ARGUMENT(l, h) { .type = OPTION_ARGUMENT, .long_name = (l), .help = (h) } +#define OPT_GROUP(h) { .type = OPTION_GROUP, .help = (h) } +#define OPT_BIT(s, l, v, h, b) { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (b) } +#define OPT_BOOLEAN(s, l, v, h) { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = (v), .help = (h) } +#define OPT_SET_INT(s, l, v, h, i) { .type = OPTION_SET_INT, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (i) } +#define OPT_SET_PTR(s, l, v, h, p) { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) } +#define OPT_INTEGER(s, l, v, h) { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = (v), .help = (h) } +#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = (v), .help = (h) } +#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h) } #define OPT_DATE(s, l, v, h) \ - { OPTION_CALLBACK, (s), (l), (v), "time",(h), 0, \ - parse_opt_approxidate_cb } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } #define OPT_CALLBACK(s, l, v, a, h, f) \ - { OPTION_CALLBACK, (s), (l), (v), (a), (h), 0, (f) } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) } /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index f18c5212bc9..c6e5dc0dc82 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -162,12 +162,16 @@ static inline int sq_must_quote(char c) return sq_lookup[(unsigned char)c] + quote_path_fully > 0; } -/* returns the longest prefix not needing a quote up to maxlen if positive. - This stops at the first \0 because it's marked as a character needing an - escape */ -static size_t next_quote_pos(const char *s, ssize_t maxlen) +/* + * Returns the longest prefix not needing a quote up to maxlen if + * positive. + * This stops at the first \0 because it's marked as a character + * needing an escape. + */ +static ssize_t next_quote_pos(const char *s, ssize_t maxlen) { - size_t len; + ssize_t len; + if (maxlen < 0) { for (len = 0; !sq_must_quote(s[len]); len++); } else { @@ -192,22 +196,22 @@ static size_t next_quote_pos(const char *s, ssize_t maxlen) static size_t quote_c_style_counted(const char *name, ssize_t maxlen, struct strbuf *sb, FILE *fp, int no_dq) { -#undef EMIT -#define EMIT(c) \ - do { \ - if (sb) strbuf_addch(sb, (c)); \ - if (fp) fputc((c), fp); \ - count++; \ - } while (0) -#define EMITBUF(s, l) \ - do { \ - int __ret; \ - if (sb) strbuf_add(sb, (s), (l)); \ - if (fp) __ret = fwrite((s), (l), 1, fp); \ - count += (l); \ +#define EMIT(c) \ + do { \ + if (sb) strbuf_addch(sb, (c)); \ + if (fp) fputc((c), fp); \ + count++; \ } while (0) - size_t len, count = 0; +#define EMITBUF(s, l) \ + do { \ + int __ret; \ + if (sb) strbuf_add(sb, (s), (l)); \ + if (fp) __ret = fwrite((s), (l), 1, fp); \ + count += (l); \ + } while (0) + + ssize_t len, count = 0; const char *p = name; for (;;) { @@ -273,8 +277,8 @@ void write_name_quoted(const char *name, FILE *fp, int terminator) fputc(terminator, fp); } -extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, - const char *name, FILE *fp, int terminator) +void write_name_quotedpfx(const char *pfx, ssize_t pfxlen, + const char *name, FILE *fp, int terminator) { int needquote = 0; @@ -306,7 +310,7 @@ char *quote_path_relative(const char *in, int len, len = strlen(in); /* "../" prefix itself does not need quoting, but "in" might. */ - needquote = next_quote_pos(in, len) < len; + needquote = (next_quote_pos(in, len) < len); strbuf_setlen(out, 0); strbuf_grow(out, len); diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h index 5dfad89816d..a5454a1d1c1 100644 --- a/tools/perf/util/quote.h +++ b/tools/perf/util/quote.h @@ -53,7 +53,7 @@ extern size_t quote_c_style(const char *name, struct strbuf *, FILE *, int no_dq extern void quote_two_c_style(struct strbuf *, const char *, const char *, int); extern void write_name_quoted(const char *name, FILE *, int terminator); -extern void write_name_quotedpfx(const char *pfx, size_t pfxlen, +extern void write_name_quotedpfx(const char *pfx, ssize_t pfxlen, const char *name, FILE *, int terminator); /* quote path as relative to the given prefix */ diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 464e7ca898c..5249d5a1b0c 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -16,7 +16,7 @@ int prefixcmp(const char *str, const char *prefix) */ char strbuf_slopbuf[1]; -void strbuf_init(struct strbuf *sb, size_t hint) +void strbuf_init(struct strbuf *sb, ssize_t hint) { sb->alloc = sb->len = 0; sb->buf = strbuf_slopbuf; @@ -92,7 +92,8 @@ void strbuf_ltrim(struct strbuf *sb) void strbuf_tolower(struct strbuf *sb) { - int i; + unsigned int i; + for (i = 0; i < sb->len; i++) sb->buf[i] = tolower(sb->buf[i]); } @@ -264,7 +265,7 @@ size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) return res; } -ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) +ssize_t strbuf_read(struct strbuf *sb, int fd, ssize_t hint) { size_t oldlen = sb->len; size_t oldalloc = sb->alloc; @@ -293,7 +294,7 @@ ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint) #define STRBUF_MAXLINK (2*PATH_MAX) -int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint) +int strbuf_readlink(struct strbuf *sb, const char *path, ssize_t hint) { size_t oldalloc = sb->alloc; @@ -301,7 +302,7 @@ int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint) hint = 32; while (hint < STRBUF_MAXLINK) { - int len; + ssize_t len; strbuf_grow(sb, hint); len = readlink(path, sb->buf, hint); @@ -343,7 +344,7 @@ int strbuf_getline(struct strbuf *sb, FILE *fp, int term) return 0; } -int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint) +int strbuf_read_file(struct strbuf *sb, const char *path, ssize_t hint) { int fd, len; diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 9ee908a3ec5..d2aa86c014c 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -50,7 +50,7 @@ struct strbuf { #define STRBUF_INIT { 0, 0, strbuf_slopbuf } /*----- strbuf life cycle -----*/ -extern void strbuf_init(struct strbuf *, size_t); +extern void strbuf_init(struct strbuf *buf, ssize_t hint); extern void strbuf_release(struct strbuf *); extern char *strbuf_detach(struct strbuf *, size_t *); extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); @@ -61,7 +61,7 @@ static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) { } /*----- strbuf size related -----*/ -static inline size_t strbuf_avail(const struct strbuf *sb) { +static inline ssize_t strbuf_avail(const struct strbuf *sb) { return sb->alloc ? sb->alloc - sb->len - 1 : 0; } @@ -122,9 +122,9 @@ extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); /* XXX: if read fails, any partial read is undone */ -extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); -extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint); -extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint); +extern ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint); +extern int strbuf_read_file(struct strbuf *sb, const char *path, ssize_t hint); +extern int strbuf_readlink(struct strbuf *sb, const char *path, ssize_t hint); extern int strbuf_getline(struct strbuf *, FILE *, int); diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c index 6350d65f6d9..4574ac28396 100644 --- a/tools/perf/util/wrapper.c +++ b/tools/perf/util/wrapper.c @@ -7,7 +7,7 @@ * There's no pack memory to release - but stay close to the Git * version so wrap this away: */ -static inline void release_pack_memory(size_t size, int flag) +static inline void release_pack_memory(size_t size __used, int flag __used) { } @@ -59,7 +59,8 @@ void *xmemdupz(const void *data, size_t len) char *xstrndup(const char *str, size_t len) { char *p = memchr(str, '\0', len); - return xmemdupz(str, p ? p - str : len); + + return xmemdupz(str, p ? (size_t)(p - str) : len); } void *xrealloc(void *ptr, size_t size) From b9ebdcc0ce1c676ebf5dc4f6df6b440d8fcf88ab Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 15:05:09 +0530 Subject: [PATCH 0083/1346] perf stat: Define MATCH_EVENT for easy attr checking MATCH_EVENT is useful: 1. for multiple attrs checking 2. avoid repetition of PERF_TYPE_ and PERF_COUNT_ and save space 3. avoids line breakage Signed-off-by: Jaswinder Singh Rajput Cc: Peter Zijlstra LKML-Reference: <1246440909.3403.5.camel@hpdv5.satnam> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 095a90e012a..01cc07efb72 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -96,6 +96,10 @@ static u64 walltime_nsecs_noise; static u64 runtime_cycles_avg; static u64 runtime_cycles_noise; +#define MATCH_EVENT(t, c, counter) \ + (attrs[counter].type == PERF_TYPE_##t && \ + attrs[counter].config == PERF_COUNT_##c) + #define ERR_PERF_OPEN \ "Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n" @@ -133,13 +137,8 @@ static void create_perf_stat_counter(int counter, int pid) */ static inline int nsec_counter(int counter) { - if (attrs[counter].type != PERF_TYPE_SOFTWARE) - return 0; - - if (attrs[counter].config == PERF_COUNT_SW_CPU_CLOCK) - return 1; - - if (attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) + if (MATCH_EVENT(SOFTWARE, SW_CPU_CLOCK, counter) || + MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) return 1; return 0; @@ -194,11 +193,9 @@ static void read_counter(int counter) /* * Save the full runtime - to allow normalization during printout: */ - if (attrs[counter].type == PERF_TYPE_SOFTWARE && - attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) + if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) runtime_nsecs[run_idx] = count[0]; - if (attrs[counter].type == PERF_TYPE_HARDWARE && - attrs[counter].config == PERF_COUNT_HW_CPU_CYCLES) + if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter)) runtime_cycles[run_idx] = count[0]; } @@ -292,9 +289,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise) fprintf(stderr, " %14.6f %-24s", msecs, event_name(counter)); - if (attrs[counter].type == PERF_TYPE_SOFTWARE && - attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) { - + if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) { if (walltime_nsecs_avg) fprintf(stderr, " # %10.3f CPUs ", (double)count[0] / (double)walltime_nsecs_avg); @@ -307,9 +302,7 @@ static void abs_printout(int counter, u64 *count, u64 *noise) fprintf(stderr, " %14Ld %-24s", count[0], event_name(counter)); if (runtime_cycles_avg && - attrs[counter].type == PERF_TYPE_HARDWARE && - attrs[counter].config == PERF_COUNT_HW_INSTRUCTIONS) { - + MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) { fprintf(stderr, " # %10.3f IPC ", (double)count[0] / (double)runtime_cycles_avg); } else { From 44973998a111dfda09b952aa0f27cad326a97793 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 17:49:38 +0530 Subject: [PATCH 0084/1346] x86: Remove double declaration of MSR_P6_EVNTSEL0 and MSR_P6_EVNTSEL1 MSR_P6_EVNTSEL0 and MSR_P6_EVNTSEL1 is already declared in msr-index.h. Signed-off-by: Jaswinder Singh Rajput LKML-Reference: <1246450778.6940.8.camel@hpdv5.satnam> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/msr-index.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 1692fb5050e..6be7fc254b5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -246,10 +246,6 @@ #define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << 38) #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << 39) -/* Intel Model 6 */ -#define MSR_P6_EVNTSEL0 0x00000186 -#define MSR_P6_EVNTSEL1 0x00000187 - /* P4/Xeon+ specific */ #define MSR_IA32_MCG_EAX 0x00000180 #define MSR_IA32_MCG_EBX 0x00000181 From 73c24cb86c51ff6445b292d9914d31236204393b Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 18:36:18 +0530 Subject: [PATCH 0085/1346] perf list: Add cache events After: $ ./perf list List of pre-defined events (to be used in -e): cpu-cycles OR cycles [Hardware event] instructions [Hardware event] cache-references [Hardware event] cache-misses [Hardware event] branch-instructions OR branches [Hardware event] branch-misses [Hardware event] bus-cycles [Hardware event] cpu-clock [Software event] task-clock [Software event] page-faults OR faults [Software event] minor-faults [Software event] major-faults [Software event] context-switches OR cs [Software event] cpu-migrations OR migrations [Software event] L1-d$-loads [Hardware cache event] L1-d$-load-misses [Hardware cache event] L1-d$-stores [Hardware cache event] L1-d$-store-misses [Hardware cache event] L1-d$-prefetches [Hardware cache event] L1-d$-prefetch-misses [Hardware cache event] L1-i$-loads [Hardware cache event] L1-i$-load-misses [Hardware cache event] L1-i$-prefetches [Hardware cache event] L1-i$-prefetch-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-stores [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-prefetches [Hardware cache event] LLC-prefetch-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-stores [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-prefetches [Hardware cache event] dTLB-prefetch-misses [Hardware cache event] iTLB-loads [Hardware cache event] iTLB-load-misses [Hardware cache event] branch-loads [Hardware cache event] branch-load-misses [Hardware cache event] rNNN [raw hardware event descriptor] Signed-off-by: Jaswinder Singh Rajput Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: <1246453578.3072.1.camel@ht.satnam> Signed-off-by: Ingo Molnar --- tools/perf/util/parse-events.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index aed70901df2..5184959e061 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -428,7 +428,7 @@ static const char * const event_type_descriptors[] = { void print_events(void) { struct event_symbol *syms = event_symbols; - unsigned int i, type, prev_type = -1; + unsigned int i, type, op, prev_type = -1; char name[40]; fprintf(stderr, "\n"); @@ -452,6 +452,21 @@ void print_events(void) prev_type = type; } + fprintf(stderr, "\n"); + for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!is_cache_op_valid(type, op)) + continue; + + for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + fprintf(stderr, " %-40s [%s]\n", + event_cache_name(type, op, i), + event_type_descriptors[4]); + } + } + } + fprintf(stderr, "\n"); fprintf(stderr, " %-40s [raw hardware event descriptor]\n", "rNNN"); From b25ae679f613ed04aaf6ccbfdb9122fce668e4bb Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 19:53:14 +0530 Subject: [PATCH 0086/1346] x86: Mark device_nb as static and fix NULL noise This sparse warning: arch/x86/kernel/amd_iommu.c:1195:23: warning: symbol 'device_nb' was not declared. Should it be static? triggers because device_nb is global but is only used in a single .c file. change device_nb to static to fix that - this also addresses the sparse warning. This sparse warning: arch/x86/kernel/amd_iommu.c:1766:10: warning: Using plain integer as NULL pointer triggers because plain integer 0 is used in place of a NULL pointer. change 0 to NULL to fix that - this also address the sparse warning. Signed-off-by: Jaswinder Singh Rajput Cc: Joerg Roedel LKML-Reference: <1246458194.6940.20.camel@hpdv5.satnam> Signed-off-by: Ingo Molnar --- arch/x86/kernel/amd_iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 9372f0406ad..6c99f503780 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1192,7 +1192,7 @@ out: return 0; } -struct notifier_block device_nb = { +static struct notifier_block device_nb = { .notifier_call = device_change_notifier, }; @@ -1763,7 +1763,7 @@ static void *alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; virt_addr = (void *)__get_free_pages(flag, get_order(size)); if (!virt_addr) - return 0; + return NULL; paddr = virt_to_phys(virt_addr); From 76c06927f2a78143763dcff9b4c362d15eb29cc2 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 1 Jul 2009 19:54:23 +0530 Subject: [PATCH 0087/1346] x86: Declare check_efer() before it gets used This sparse warning: arch/x86/mm/init.c:83:16: warning: symbol 'check_efer' was not declared. Should it be static? triggers because check_efer() is not decalared before using it. asm/proto.h includes the declaration of check_efer(), so including asm/proto.h to fix that - this also addresses the sparse warning. Signed-off-by: Jaswinder Singh Rajput Cc: Andrew Morton LKML-Reference: <1246458263.6940.22.camel@hpdv5.satnam> Signed-off-by: Ingo Molnar --- arch/x86/mm/init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 47ce9a2ce5e..0607119cef9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -12,6 +12,7 @@ #include #include #include +#include DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); From 63eeaf38251183ec2b1caee11e4a2c040cb5ce6c Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Thu, 18 Jun 2009 16:56:52 -0700 Subject: [PATCH 0088/1346] drm/i915: enable error detection & state collection This patch enables error detection by enabling several types of error interrupts. When an error interrupt is received, the interrupt handler captures the error state; hopefully resulting in an accurate set of error data (error type, active head pointer, etc.). The new record is then available from sysfs. The current code will also dump the error state to the system log. Signed-off-by: Jesse Barnes Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/i915_dma.c | 1 + drivers/gpu/drm/i915/i915_drv.h | 19 ++++ drivers/gpu/drm/i915/i915_gem_debugfs.c | 34 ++++++ drivers/gpu/drm/i915/i915_irq.c | 139 +++++++++++++++++++++++- drivers/gpu/drm/i915/i915_reg.h | 14 +++ 5 files changed, 204 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index f112c769d53..f83364974a8 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1180,6 +1180,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) pci_enable_msi(dev->pdev); spin_lock_init(&dev_priv->user_irq_lock); + spin_lock_init(&dev_priv->error_lock); dev_priv->user_irq_refcount = 0; ret = drm_vblank_init(dev, I915_NUM_PIPE); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index bb4c2d387b6..596e119d3e0 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -133,6 +133,22 @@ struct sdvo_device_mapping { u8 initialized; }; +struct drm_i915_error_state { + u32 eir; + u32 pgtbl_er; + u32 pipeastat; + u32 pipebstat; + u32 ipeir; + u32 ipehr; + u32 instdone; + u32 acthd; + u32 instpm; + u32 instps; + u32 instdone1; + u32 seqno; + struct timeval time; +}; + typedef struct drm_i915_private { struct drm_device *dev; @@ -209,6 +225,9 @@ typedef struct drm_i915_private { int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */ int num_fence_regs; /* 8 on pre-965, 16 otherwise */ + spinlock_t error_lock; + struct drm_i915_error_state *first_error; + /* Register state */ u8 saveLBB; u32 saveDSPACNTR; diff --git a/drivers/gpu/drm/i915/i915_gem_debugfs.c b/drivers/gpu/drm/i915/i915_gem_debugfs.c index 28146e405e8..cacae945338 100644 --- a/drivers/gpu/drm/i915/i915_gem_debugfs.c +++ b/drivers/gpu/drm/i915/i915_gem_debugfs.c @@ -323,6 +323,39 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data) return 0; } +static int i915_error_state(struct seq_file *m, void *unused) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + drm_i915_private_t *dev_priv = dev->dev_private; + struct drm_i915_error_state *error; + unsigned long flags; + + spin_lock_irqsave(&dev_priv->error_lock, flags); + if (!dev_priv->first_error) { + seq_printf(m, "no error state collected\n"); + goto out; + } + + error = dev_priv->first_error; + + seq_printf(m, "EIR: 0x%08x\n", error->eir); + seq_printf(m, " PGTBL_ER: 0x%08x\n", error->pgtbl_er); + seq_printf(m, " INSTPM: 0x%08x\n", error->instpm); + seq_printf(m, " IPEIR: 0x%08x\n", error->ipeir); + seq_printf(m, " IPEHR: 0x%08x\n", error->ipehr); + seq_printf(m, " INSTDONE: 0x%08x\n", error->instdone); + seq_printf(m, " ACTHD: 0x%08x\n", error->acthd); + if (IS_I965G(dev)) { + seq_printf(m, " INSTPS: 0x%08x\n", error->instps); + seq_printf(m, " INSTDONE1: 0x%08x\n", error->instdone1); + } + +out: + spin_unlock_irqrestore(&dev_priv->error_lock, flags); + + return 0; +} static struct drm_info_list i915_gem_debugfs_list[] = { {"i915_gem_active", i915_gem_object_list_info, 0, (void *) ACTIVE_LIST}, @@ -336,6 +369,7 @@ static struct drm_info_list i915_gem_debugfs_list[] = { {"i915_ringbuffer_data", i915_ringbuffer_data, 0}, {"i915_ringbuffer_info", i915_ringbuffer_info, 0}, {"i915_batchbuffers", i915_batchbuffer_info, 0}, + {"i915_error_state", i915_error_state, 0}, }; #define I915_GEM_DEBUGFS_ENTRIES ARRAY_SIZE(i915_gem_debugfs_list) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 228546f6eaa..17b308592c4 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -26,6 +26,7 @@ * */ +#include #include "drmP.h" #include "drm.h" #include "i915_drm.h" @@ -41,9 +42,10 @@ * we leave them always unmasked in IMR and then control enabling them through * PIPESTAT alone. */ -#define I915_INTERRUPT_ENABLE_FIX (I915_ASLE_INTERRUPT | \ - I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | \ - I915_DISPLAY_PIPE_B_EVENT_INTERRUPT) +#define I915_INTERRUPT_ENABLE_FIX (I915_ASLE_INTERRUPT | \ + I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | \ + I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | \ + I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT) /** Interrupts that we mask and unmask at runtime. */ #define I915_INTERRUPT_ENABLE_VAR (I915_USER_INTERRUPT) @@ -288,6 +290,47 @@ irqreturn_t igdng_irq_handler(struct drm_device *dev) return ret; } +static void i915_capture_error_state(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_error_state *error; + unsigned long flags; + + spin_lock_irqsave(&dev_priv->error_lock, flags); + if (dev_priv->first_error) + goto out; + + error = kmalloc(sizeof(*error), GFP_ATOMIC); + if (!error) { + DRM_DEBUG("out ot memory, not capturing error state\n"); + goto out; + } + + error->eir = I915_READ(EIR); + error->pgtbl_er = I915_READ(PGTBL_ER); + error->pipeastat = I915_READ(PIPEASTAT); + error->pipebstat = I915_READ(PIPEBSTAT); + error->instpm = I915_READ(INSTPM); + if (!IS_I965G(dev)) { + error->ipeir = I915_READ(IPEIR); + error->ipehr = I915_READ(IPEHR); + error->instdone = I915_READ(INSTDONE); + error->acthd = I915_READ(ACTHD); + } else { + error->ipeir = I915_READ(IPEIR_I965); + error->ipehr = I915_READ(IPEHR_I965); + error->instdone = I915_READ(INSTDONE_I965); + error->instps = I915_READ(INSTPS); + error->instdone1 = I915_READ(INSTDONE1); + error->acthd = I915_READ(ACTHD_I965); + } + + dev_priv->first_error = error; + +out: + spin_unlock_irqrestore(&dev_priv->error_lock, flags); +} + irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) { struct drm_device *dev = (struct drm_device *) arg; @@ -362,6 +405,80 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) I915_READ(PORT_HOTPLUG_STAT); } + if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT) { + u32 eir = I915_READ(EIR); + + i915_capture_error_state(dev); + + printk(KERN_ERR "render error detected, EIR: 0x%08x\n", + eir); + if (eir & I915_ERROR_PAGE_TABLE) { + u32 pgtbl_err = I915_READ(PGTBL_ER); + printk(KERN_ERR "page table error\n"); + printk(KERN_ERR " PGTBL_ER: 0x%08x\n", + pgtbl_err); + I915_WRITE(PGTBL_ER, pgtbl_err); + (void)I915_READ(PGTBL_ER); + } + if (eir & I915_ERROR_MEMORY_REFRESH) { + printk(KERN_ERR "memory refresh error\n"); + printk(KERN_ERR "PIPEASTAT: 0x%08x\n", + pipea_stats); + printk(KERN_ERR "PIPEBSTAT: 0x%08x\n", + pipeb_stats); + /* pipestat has already been acked */ + } + if (eir & I915_ERROR_INSTRUCTION) { + printk(KERN_ERR "instruction error\n"); + printk(KERN_ERR " INSTPM: 0x%08x\n", + I915_READ(INSTPM)); + if (!IS_I965G(dev)) { + u32 ipeir = I915_READ(IPEIR); + + printk(KERN_ERR " IPEIR: 0x%08x\n", + I915_READ(IPEIR)); + printk(KERN_ERR " IPEHR: 0x%08x\n", + I915_READ(IPEHR)); + printk(KERN_ERR " INSTDONE: 0x%08x\n", + I915_READ(INSTDONE)); + printk(KERN_ERR " ACTHD: 0x%08x\n", + I915_READ(ACTHD)); + I915_WRITE(IPEIR, ipeir); + (void)I915_READ(IPEIR); + } else { + u32 ipeir = I915_READ(IPEIR_I965); + + printk(KERN_ERR " IPEIR: 0x%08x\n", + I915_READ(IPEIR_I965)); + printk(KERN_ERR " IPEHR: 0x%08x\n", + I915_READ(IPEHR_I965)); + printk(KERN_ERR " INSTDONE: 0x%08x\n", + I915_READ(INSTDONE_I965)); + printk(KERN_ERR " INSTPS: 0x%08x\n", + I915_READ(INSTPS)); + printk(KERN_ERR " INSTDONE1: 0x%08x\n", + I915_READ(INSTDONE1)); + printk(KERN_ERR " ACTHD: 0x%08x\n", + I915_READ(ACTHD_I965)); + I915_WRITE(IPEIR_I965, ipeir); + (void)I915_READ(IPEIR_I965); + } + } + + I915_WRITE(EIR, eir); + (void)I915_READ(EIR); + eir = I915_READ(EIR); + if (eir) { + /* + * some errors might have become stuck, + * mask them. + */ + DRM_ERROR("EIR stuck: 0x%08x, masking\n", eir); + I915_WRITE(EMR, I915_READ(EMR) | eir); + I915_WRITE(IIR, I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT); + } + } + I915_WRITE(IIR, iir); new_iir = I915_READ(IIR); /* Flush posted writes */ @@ -732,6 +849,7 @@ int i915_driver_irq_postinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; u32 enable_mask = I915_INTERRUPT_ENABLE_FIX | I915_INTERRUPT_ENABLE_VAR; + u32 error_mask; DRM_INIT_WAITQUEUE(&dev_priv->irq_queue); @@ -768,6 +886,21 @@ int i915_driver_irq_postinstall(struct drm_device *dev) i915_enable_irq(dev_priv, I915_DISPLAY_PORT_INTERRUPT); } + /* + * Enable some error detection, note the instruction error mask + * bit is reserved, so we leave it masked. + */ + if (IS_G4X(dev)) { + error_mask = ~(GM45_ERROR_PAGE_TABLE | + GM45_ERROR_MEM_PRIV | + GM45_ERROR_CP_PRIV | + I915_ERROR_MEMORY_REFRESH); + } else { + error_mask = ~(I915_ERROR_PAGE_TABLE | + I915_ERROR_MEMORY_REFRESH); + } + I915_WRITE(EMR, error_mask); + /* Disable pipe interrupt enables, clear pending pipe status */ I915_WRITE(PIPEASTAT, I915_READ(PIPEASTAT) & 0x8000ffff); I915_WRITE(PIPEBSTAT, I915_READ(PIPEBSTAT) & 0x8000ffff); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 88bf7521405..ad3d1b5db95 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -206,6 +206,7 @@ /* * Instruction and interrupt control regs */ +#define PGTBL_ER 0x02024 #define PRB0_TAIL 0x02030 #define PRB0_HEAD 0x02034 #define PRB0_START 0x02038 @@ -226,11 +227,18 @@ #define PRB1_HEAD 0x02044 /* 915+ only */ #define PRB1_START 0x02048 /* 915+ only */ #define PRB1_CTL 0x0204c /* 915+ only */ +#define IPEIR_I965 0x02064 +#define IPEHR_I965 0x02068 +#define INSTDONE_I965 0x0206c +#define INSTPS 0x02070 /* 965+ only */ +#define INSTDONE1 0x0207c /* 965+ only */ #define ACTHD_I965 0x02074 #define HWS_PGA 0x02080 #define HWS_ADDRESS_MASK 0xfffff000 #define HWS_START_ADDRESS_SHIFT 4 #define IPEIR 0x02088 +#define IPEHR 0x0208c +#define INSTDONE 0x02090 #define NOPID 0x02094 #define HWSTAM 0x02098 #define SCPD0 0x0209c /* 915+ only */ @@ -258,6 +266,12 @@ #define EIR 0x020b0 #define EMR 0x020b4 #define ESR 0x020b8 +#define GM45_ERROR_PAGE_TABLE (1<<5) +#define GM45_ERROR_MEM_PRIV (1<<4) +#define I915_ERROR_PAGE_TABLE (1<<4) +#define GM45_ERROR_CP_PRIV (1<<3) +#define I915_ERROR_MEMORY_REFRESH (1<<1) +#define I915_ERROR_INSTRUCTION (1<<0) #define INSTPM 0x020c0 #define ACTHD 0x020c8 #define FW_BLC 0x020d8 From 7662c8bd6545c12ac7b2b39e4554c3ba34789c50 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 26 Jun 2009 11:23:55 +0800 Subject: [PATCH 0089/1346] drm/i915: add FIFO watermark support This patch from jbarnes and myself adds FIFO watermark control to the driver. This is needed for both power saving features on new platforms with the so-called "big FIFO" and for controlling FIFO allocation between pipes in multi-head configurations. It's also necessary infrastructure to support things like framebuffer compression and configuration supportability checks (i.e. checking a configuration against available bandwidth). Signed-off-by: Jesse Barnes Signed-off-by: Shaohua Li Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/i915_dma.c | 40 +++ drivers/gpu/drm/i915/i915_drv.h | 4 + drivers/gpu/drm/i915/i915_irq.c | 4 + drivers/gpu/drm/i915/i915_reg.h | 46 ++- drivers/gpu/drm/i915/intel_display.c | 425 ++++++++++++++++++++++++++- 5 files changed, 513 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index f83364974a8..6096600aff6 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1082,6 +1082,44 @@ void i915_master_destroy(struct drm_device *dev, struct drm_master *master) master->driver_priv = NULL; } +static void i915_get_mem_freq(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + u32 tmp; + + if (!IS_IGD(dev)) + return; + + tmp = I915_READ(CLKCFG); + + switch (tmp & CLKCFG_FSB_MASK) { + case CLKCFG_FSB_533: + dev_priv->fsb_freq = 533; /* 133*4 */ + break; + case CLKCFG_FSB_800: + dev_priv->fsb_freq = 800; /* 200*4 */ + break; + case CLKCFG_FSB_667: + dev_priv->fsb_freq = 667; /* 167*4 */ + break; + case CLKCFG_FSB_400: + dev_priv->fsb_freq = 400; /* 100*4 */ + break; + } + + switch (tmp & CLKCFG_MEM_MASK) { + case CLKCFG_MEM_533: + dev_priv->mem_freq = 533; + break; + case CLKCFG_MEM_667: + dev_priv->mem_freq = 667; + break; + case CLKCFG_MEM_800: + dev_priv->mem_freq = 800; + break; + } +} + /** * i915_driver_load - setup chip and create an initial config * @dev: DRM device @@ -1165,6 +1203,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto out_iomapfree; } + i915_get_mem_freq(dev); + /* On the 945G/GM, the chipset reports the MSI capability on the * integrated graphics even though the support isn't actually there * according to the published specs. It doesn't appear to function diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 596e119d3e0..47ecb617e51 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -225,6 +225,8 @@ typedef struct drm_i915_private { int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */ int num_fence_regs; /* 8 on pre-965, 16 otherwise */ + unsigned int fsb_freq, mem_freq; + spinlock_t error_lock; struct drm_i915_error_state *first_error; @@ -889,6 +891,8 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller); #define SUPPORTS_INTEGRATED_HDMI(dev) (IS_G4X(dev) || IS_IGDNG(dev)) #define SUPPORTS_INTEGRATED_DP(dev) (IS_G4X(dev) || IS_IGDNG(dev)) #define I915_HAS_HOTPLUG(dev) (IS_I945G(dev) || IS_I945GM(dev) || IS_I965G(dev)) +/* dsparb controlled by hw only */ +#define DSPARB_HWCONTROL(dev) (IS_G4X(dev)) #define PRIMARY_RINGBUFFER_SIZE (128*1024) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 17b308592c4..7ba23a69a0c 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -376,11 +376,15 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) * Clear the PIPE(A|B)STAT regs before the IIR */ if (pipea_stats & 0x8000ffff) { + if (pipea_stats & PIPE_FIFO_UNDERRUN_STATUS) + DRM_DEBUG("pipe a underrun\n"); I915_WRITE(PIPEASTAT, pipea_stats); irq_received = 1; } if (pipeb_stats & 0x8000ffff) { + if (pipeb_stats & PIPE_FIFO_UNDERRUN_STATUS) + DRM_DEBUG("pipe b underrun\n"); I915_WRITE(PIPEBSTAT, pipeb_stats); irq_received = 1; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index ad3d1b5db95..6c085848409 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -275,7 +275,13 @@ #define INSTPM 0x020c0 #define ACTHD 0x020c8 #define FW_BLC 0x020d8 +#define FW_BLC2 0x020dc #define FW_BLC_SELF 0x020e0 /* 915+ only */ +#define FW_BLC_SELF_EN (1<<15) +#define MM_BURST_LENGTH 0x00700000 +#define MM_FIFO_WATERMARK 0x0001F000 +#define LM_BURST_LENGTH 0x00000700 +#define LM_FIFO_WATERMARK 0x0000001F #define MI_ARB_STATE 0x020e4 /* 915+ only */ #define CACHE_MODE_0 0x02120 /* 915+ only */ #define CM0_MASK_SHIFT 16 @@ -585,17 +591,21 @@ /* Clocking configuration register */ #define CLKCFG 0x10c00 -#define CLKCFG_FSB_400 (0 << 0) /* hrawclk 100 */ +#define CLKCFG_FSB_400 (5 << 0) /* hrawclk 100 */ #define CLKCFG_FSB_533 (1 << 0) /* hrawclk 133 */ #define CLKCFG_FSB_667 (3 << 0) /* hrawclk 166 */ #define CLKCFG_FSB_800 (2 << 0) /* hrawclk 200 */ #define CLKCFG_FSB_1067 (6 << 0) /* hrawclk 266 */ #define CLKCFG_FSB_1333 (7 << 0) /* hrawclk 333 */ -/* this is a guess, could be 5 as well */ +/* Note, below two are guess */ #define CLKCFG_FSB_1600 (4 << 0) /* hrawclk 400 */ -#define CLKCFG_FSB_1600_ALT (5 << 0) /* hrawclk 400 */ +#define CLKCFG_FSB_1600_ALT (0 << 0) /* hrawclk 400 */ #define CLKCFG_FSB_MASK (7 << 0) - +#define CLKCFG_MEM_533 (1 << 4) +#define CLKCFG_MEM_667 (2 << 4) +#define CLKCFG_MEM_800 (3 << 4) +#define CLKCFG_MEM_MASK (7 << 4) + /** GM965 GM45 render standby register */ #define MCHBAR_RENDER_STANDBY 0x111B8 @@ -1595,6 +1605,34 @@ #define DSPARB_CSTART_SHIFT 7 #define DSPARB_BSTART_MASK (0x7f) #define DSPARB_BSTART_SHIFT 0 +#define DSPARB_BEND_SHIFT 9 /* on 855 */ +#define DSPARB_AEND_SHIFT 0 + +#define DSPFW1 0x70034 +#define DSPFW2 0x70038 +#define DSPFW3 0x7003c +#define IGD_SELF_REFRESH_EN (1<<30) + +/* FIFO watermark sizes etc */ +#define I915_FIFO_LINE_SIZE 64 +#define I830_FIFO_LINE_SIZE 32 +#define I945_FIFO_SIZE 127 /* 945 & 965 */ +#define I915_FIFO_SIZE 95 +#define I855GM_FIFO_SIZE 255 +#define I830_FIFO_SIZE 95 +#define I915_MAX_WM 0x3f + +#define IGD_DISPLAY_FIFO 512 /* in 64byte unit */ +#define IGD_FIFO_LINE_SIZE 64 +#define IGD_MAX_WM 0x1ff +#define IGD_DFT_WM 0x3f +#define IGD_DFT_HPLLOFF_WM 0 +#define IGD_GUARD_WM 10 +#define IGD_CURSOR_FIFO 64 +#define IGD_CURSOR_MAX_WM 0x3f +#define IGD_CURSOR_DFT_WM 0 +#define IGD_CURSOR_GUARD_WM 5 + /* * The two pipe frame counter registers are not synchronized, so * reading a stable value is somewhat tricky. The following code diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 73e7b9cecac..a84ac05ef04 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -25,6 +25,7 @@ */ #include +#include #include "drmP.h" #include "intel_drv.h" #include "i915_drm.h" @@ -34,6 +35,7 @@ #include "drm_crtc_helper.h" bool intel_pipe_has_type (struct drm_crtc *crtc, int type); +static void intel_update_watermarks(struct drm_device *dev); typedef struct { /* given values */ @@ -1005,7 +1007,7 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - int plane = intel_crtc->pipe; + int plane = intel_crtc->plane; int pch_dpll_reg = (pipe == 0) ? PCH_DPLL_A : PCH_DPLL_B; int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF; int dspcntr_reg = (plane == 0) ? DSPACNTR : DSPBCNTR; @@ -1335,8 +1337,10 @@ static void i9xx_crtc_dpms(struct drm_crtc *crtc, int mode) /* Give the overlay scaler a chance to enable if it's on this pipe */ //intel_crtc_dpms_video(crtc, true); TODO + intel_update_watermarks(dev); break; case DRM_MODE_DPMS_OFF: + intel_update_watermarks(dev); /* Give the overlay scaler a chance to disable if it's on this pipe */ //intel_crtc_dpms_video(crtc, FALSE); TODO @@ -1515,7 +1519,6 @@ static int intel_get_core_clock_speed(struct drm_device *dev) return 0; /* Silence gcc warning */ } - /** * Return the pipe currently connected to the panel fitter, * or -1 if the panel fitter is not present or not in use @@ -1585,6 +1588,420 @@ igdng_compute_m_n(int bytes_per_pixel, int nlanes, } +struct intel_watermark_params { + unsigned long fifo_size; + unsigned long max_wm; + unsigned long default_wm; + unsigned long guard_size; + unsigned long cacheline_size; +}; + +/* IGD has different values for various configs */ +static struct intel_watermark_params igd_display_wm = { + IGD_DISPLAY_FIFO, + IGD_MAX_WM, + IGD_DFT_WM, + IGD_GUARD_WM, + IGD_FIFO_LINE_SIZE +}; +static struct intel_watermark_params igd_display_hplloff_wm = { + IGD_DISPLAY_FIFO, + IGD_MAX_WM, + IGD_DFT_HPLLOFF_WM, + IGD_GUARD_WM, + IGD_FIFO_LINE_SIZE +}; +static struct intel_watermark_params igd_cursor_wm = { + IGD_CURSOR_FIFO, + IGD_CURSOR_MAX_WM, + IGD_CURSOR_DFT_WM, + IGD_CURSOR_GUARD_WM, + IGD_FIFO_LINE_SIZE, +}; +static struct intel_watermark_params igd_cursor_hplloff_wm = { + IGD_CURSOR_FIFO, + IGD_CURSOR_MAX_WM, + IGD_CURSOR_DFT_WM, + IGD_CURSOR_GUARD_WM, + IGD_FIFO_LINE_SIZE +}; +static struct intel_watermark_params i945_wm_info = { + I915_FIFO_LINE_SIZE, + I915_MAX_WM, + 1, + 0, + IGD_FIFO_LINE_SIZE +}; +static struct intel_watermark_params i915_wm_info = { + I945_FIFO_SIZE, + I915_MAX_WM, + 1, + 0, + I915_FIFO_LINE_SIZE +}; +static struct intel_watermark_params i855_wm_info = { + I855GM_FIFO_SIZE, + I915_MAX_WM, + 1, + 0, + I830_FIFO_LINE_SIZE +}; +static struct intel_watermark_params i830_wm_info = { + I830_FIFO_SIZE, + I915_MAX_WM, + 1, + 0, + I830_FIFO_LINE_SIZE +}; + +static unsigned long intel_calculate_wm(unsigned long clock_in_khz, + struct intel_watermark_params *wm, + int pixel_size, + unsigned long latency_ns) +{ + unsigned long bytes_required, wm_size; + + bytes_required = (clock_in_khz * pixel_size * latency_ns) / 1000000; + bytes_required /= wm->cacheline_size; + wm_size = wm->fifo_size - bytes_required - wm->guard_size; + + if (wm_size > wm->max_wm) + wm_size = wm->max_wm; + if (wm_size == 0) + wm_size = wm->default_wm; + return wm_size; +} + +struct cxsr_latency { + int is_desktop; + unsigned long fsb_freq; + unsigned long mem_freq; + unsigned long display_sr; + unsigned long display_hpll_disable; + unsigned long cursor_sr; + unsigned long cursor_hpll_disable; +}; + +static struct cxsr_latency cxsr_latency_table[] = { + {1, 800, 400, 3382, 33382, 3983, 33983}, /* DDR2-400 SC */ + {1, 800, 667, 3354, 33354, 3807, 33807}, /* DDR2-667 SC */ + {1, 800, 800, 3347, 33347, 3763, 33763}, /* DDR2-800 SC */ + + {1, 667, 400, 3400, 33400, 4021, 34021}, /* DDR2-400 SC */ + {1, 667, 667, 3372, 33372, 3845, 33845}, /* DDR2-667 SC */ + {1, 667, 800, 3386, 33386, 3822, 33822}, /* DDR2-800 SC */ + + {1, 400, 400, 3472, 33472, 4173, 34173}, /* DDR2-400 SC */ + {1, 400, 667, 3443, 33443, 3996, 33996}, /* DDR2-667 SC */ + {1, 400, 800, 3430, 33430, 3946, 33946}, /* DDR2-800 SC */ + + {0, 800, 400, 3438, 33438, 4065, 34065}, /* DDR2-400 SC */ + {0, 800, 667, 3410, 33410, 3889, 33889}, /* DDR2-667 SC */ + {0, 800, 800, 3403, 33403, 3845, 33845}, /* DDR2-800 SC */ + + {0, 667, 400, 3456, 33456, 4103, 34106}, /* DDR2-400 SC */ + {0, 667, 667, 3428, 33428, 3927, 33927}, /* DDR2-667 SC */ + {0, 667, 800, 3443, 33443, 3905, 33905}, /* DDR2-800 SC */ + + {0, 400, 400, 3528, 33528, 4255, 34255}, /* DDR2-400 SC */ + {0, 400, 667, 3500, 33500, 4079, 34079}, /* DDR2-667 SC */ + {0, 400, 800, 3487, 33487, 4029, 34029}, /* DDR2-800 SC */ +}; + +static struct cxsr_latency *intel_get_cxsr_latency(int is_desktop, int fsb, + int mem) +{ + int i; + struct cxsr_latency *latency; + + if (fsb == 0 || mem == 0) + return NULL; + + for (i = 0; i < ARRAY_SIZE(cxsr_latency_table); i++) { + latency = &cxsr_latency_table[i]; + if (is_desktop == latency->is_desktop && + fsb == latency->fsb_freq && mem == latency->mem_freq) + break; + } + if (i >= ARRAY_SIZE(cxsr_latency_table)) { + DRM_DEBUG("Unknown FSB/MEM found, disable CxSR\n"); + return NULL; + } + return latency; +} + +static void igd_disable_cxsr(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 reg; + + /* deactivate cxsr */ + reg = I915_READ(DSPFW3); + reg &= ~(IGD_SELF_REFRESH_EN); + I915_WRITE(DSPFW3, reg); + DRM_INFO("Big FIFO is disabled\n"); +} + +static void igd_enable_cxsr(struct drm_device *dev, unsigned long clock, + int pixel_size) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 reg; + unsigned long wm; + struct cxsr_latency *latency; + + latency = intel_get_cxsr_latency(IS_IGDG(dev), dev_priv->fsb_freq, + dev_priv->mem_freq); + if (!latency) { + DRM_DEBUG("Unknown FSB/MEM found, disable CxSR\n"); + igd_disable_cxsr(dev); + return; + } + + /* Display SR */ + wm = intel_calculate_wm(clock, &igd_display_wm, pixel_size, + latency->display_sr); + reg = I915_READ(DSPFW1); + reg &= 0x7fffff; + reg |= wm << 23; + I915_WRITE(DSPFW1, reg); + DRM_DEBUG("DSPFW1 register is %x\n", reg); + + /* cursor SR */ + wm = intel_calculate_wm(clock, &igd_cursor_wm, pixel_size, + latency->cursor_sr); + reg = I915_READ(DSPFW3); + reg &= ~(0x3f << 24); + reg |= (wm & 0x3f) << 24; + I915_WRITE(DSPFW3, reg); + + /* Display HPLL off SR */ + wm = intel_calculate_wm(clock, &igd_display_hplloff_wm, + latency->display_hpll_disable, I915_FIFO_LINE_SIZE); + reg = I915_READ(DSPFW3); + reg &= 0xfffffe00; + reg |= wm & 0x1ff; + I915_WRITE(DSPFW3, reg); + + /* cursor HPLL off SR */ + wm = intel_calculate_wm(clock, &igd_cursor_hplloff_wm, pixel_size, + latency->cursor_hpll_disable); + reg = I915_READ(DSPFW3); + reg &= ~(0x3f << 16); + reg |= (wm & 0x3f) << 16; + I915_WRITE(DSPFW3, reg); + DRM_DEBUG("DSPFW3 register is %x\n", reg); + + /* activate cxsr */ + reg = I915_READ(DSPFW3); + reg |= IGD_SELF_REFRESH_EN; + I915_WRITE(DSPFW3, reg); + + DRM_INFO("Big FIFO is enabled\n"); + + return; +} + +const static int latency_ns = 5000; /* default for non-igd platforms */ + + +static void i965_update_wm(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + DRM_DEBUG("Setting FIFO watermarks - A: 8, B: 8, C: 8, SR 8\n"); + + /* 965 has limitations... */ + I915_WRITE(DSPFW1, (8 << 16) | (8 << 8) | (8 << 0)); + I915_WRITE(DSPFW2, (8 << 8) | (8 << 0)); +} + +static void i9xx_update_wm(struct drm_device *dev, int planea_clock, + int planeb_clock, int sr_hdisplay, int pixel_size) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t fwater_lo = I915_READ(FW_BLC) & MM_FIFO_WATERMARK; + uint32_t fwater_hi = I915_READ(FW_BLC2) & LM_FIFO_WATERMARK; + int bsize, asize, cwm, bwm = 1, awm = 1, srwm = 1; + uint32_t dsparb = I915_READ(DSPARB); + int planea_entries, planeb_entries; + struct intel_watermark_params *wm_params; + unsigned long line_time_us; + int sr_clock, sr_entries = 0; + + if (IS_I965GM(dev) || IS_I945GM(dev)) + wm_params = &i945_wm_info; + else if (IS_I9XX(dev)) + wm_params = &i915_wm_info; + else + wm_params = &i855_wm_info; + + planea_entries = intel_calculate_wm(planea_clock, wm_params, + pixel_size, latency_ns); + planeb_entries = intel_calculate_wm(planeb_clock, wm_params, + pixel_size, latency_ns); + + DRM_DEBUG("FIFO entries - A: %d, B: %d\n", planea_entries, + planeb_entries); + + if (IS_I9XX(dev)) { + asize = dsparb & 0x7f; + bsize = (dsparb >> DSPARB_CSTART_SHIFT) & 0x7f; + } else { + asize = dsparb & 0x1ff; + bsize = (dsparb >> DSPARB_BEND_SHIFT) & 0x1ff; + } + DRM_DEBUG("FIFO size - A: %d, B: %d\n", asize, bsize); + + /* Two extra entries for padding */ + awm = asize - (planea_entries + 2); + bwm = bsize - (planeb_entries + 2); + + /* Sanity check against potentially bad FIFO allocations */ + if (awm <= 0) { + /* pipe is on but has too few FIFO entries */ + if (planea_entries != 0) + DRM_DEBUG("plane A needs more FIFO entries\n"); + awm = 1; + } + if (bwm <= 0) { + if (planeb_entries != 0) + DRM_DEBUG("plane B needs more FIFO entries\n"); + bwm = 1; + } + + /* + * Overlay gets an aggressive default since video jitter is bad. + */ + cwm = 2; + + /* Calc sr entries for one pipe configs */ + if (!planea_clock || !planeb_clock) { + sr_clock = planea_clock ? planea_clock : planeb_clock; + line_time_us = (sr_hdisplay * 1000) / sr_clock; + sr_entries = (((latency_ns / line_time_us) + 1) * pixel_size * + sr_hdisplay) / 1000; + sr_entries = roundup(sr_entries / wm_params->cacheline_size, 1); + if (sr_entries < wm_params->fifo_size) + srwm = wm_params->fifo_size - sr_entries; + } + + DRM_DEBUG("Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n", + awm, bwm, cwm, srwm); + + fwater_lo = fwater_lo | ((bwm & 0x3f) << 16) | (awm & 0x3f); + fwater_hi = fwater_hi | (cwm & 0x1f); + + I915_WRITE(FW_BLC, fwater_lo); + I915_WRITE(FW_BLC2, fwater_hi); + if (IS_I9XX(dev)) + I915_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN | (srwm & 0x3f)); +} + +static void i830_update_wm(struct drm_device *dev, int planea_clock, + int pixel_size) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t dsparb = I915_READ(DSPARB); + uint32_t fwater_lo = I915_READ(FW_BLC) & MM_FIFO_WATERMARK; + unsigned int asize, awm; + int planea_entries; + + planea_entries = intel_calculate_wm(planea_clock, &i830_wm_info, + pixel_size, latency_ns); + + asize = dsparb & 0x7f; + + awm = asize - planea_entries; + + fwater_lo = fwater_lo | awm; + + I915_WRITE(FW_BLC, fwater_lo); +} + +/** + * intel_update_watermarks - update FIFO watermark values based on current modes + * + * Calculate watermark values for the various WM regs based on current mode + * and plane configuration. + * + * There are several cases to deal with here: + * - normal (i.e. non-self-refresh) + * - self-refresh (SR) mode + * - lines are large relative to FIFO size (buffer can hold up to 2) + * - lines are small relative to FIFO size (buffer can hold more than 2 + * lines), so need to account for TLB latency + * + * The normal calculation is: + * watermark = dotclock * bytes per pixel * latency + * where latency is platform & configuration dependent (we assume pessimal + * values here). + * + * The SR calculation is: + * watermark = (trunc(latency/line time)+1) * surface width * + * bytes per pixel + * where + * line time = htotal / dotclock + * and latency is assumed to be high, as above. + * + * The final value programmed to the register should always be rounded up, + * and include an extra 2 entries to account for clock crossings. + * + * We don't use the sprite, so we can ignore that. And on Crestline we have + * to set the non-SR watermarks to 8. + */ +static void intel_update_watermarks(struct drm_device *dev) +{ + struct drm_crtc *crtc; + struct intel_crtc *intel_crtc; + int sr_hdisplay = 0; + unsigned long planea_clock = 0, planeb_clock = 0, sr_clock = 0; + int enabled = 0, pixel_size = 0; + + if (DSPARB_HWCONTROL(dev)) + return; + + /* Get the clock config from both planes */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + intel_crtc = to_intel_crtc(crtc); + if (crtc->enabled) { + enabled++; + if (intel_crtc->plane == 0) { + DRM_DEBUG("plane A (pipe %d) clock: %d\n", + intel_crtc->pipe, crtc->mode.clock); + planea_clock = crtc->mode.clock; + } else { + DRM_DEBUG("plane B (pipe %d) clock: %d\n", + intel_crtc->pipe, crtc->mode.clock); + planeb_clock = crtc->mode.clock; + } + sr_hdisplay = crtc->mode.hdisplay; + sr_clock = crtc->mode.clock; + if (crtc->fb) + pixel_size = crtc->fb->bits_per_pixel / 8; + else + pixel_size = 4; /* by default */ + } + } + + if (enabled <= 0) + return; + + /* Single pipe configs can enable self refresh */ + if (enabled == 1 && IS_IGD(dev)) + igd_enable_cxsr(dev, sr_clock, pixel_size); + else if (IS_IGD(dev)) + igd_disable_cxsr(dev); + + if (IS_I965G(dev)) + i965_update_wm(dev); + else if (IS_I9XX(dev) || IS_MOBILE(dev)) + i9xx_update_wm(dev, planea_clock, planeb_clock, sr_hdisplay, + pixel_size); + else + i830_update_wm(dev, planea_clock, pixel_size); +} + static int intel_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode, @@ -1951,6 +2368,9 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, /* Flush the plane changes */ ret = intel_pipe_set_base(crtc, x, y, old_fb); + + intel_update_watermarks(dev); + drm_vblank_post_modeset(dev, pipe); return ret; @@ -2439,6 +2859,7 @@ static void intel_crtc_init(struct drm_device *dev, int pipe) drm_mode_crtc_set_gamma_size(&intel_crtc->base, 256); intel_crtc->pipe = pipe; + intel_crtc->plane = pipe; for (i = 0; i < 256; i++) { intel_crtc->lut_r[i] = i; intel_crtc->lut_g[i] = i; From 6ff4fd05676bc5b5c930bef25901e489f7843660 Mon Sep 17 00:00:00 2001 From: "ling.ma@intel.com" Date: Thu, 25 Jun 2009 10:59:22 +0800 Subject: [PATCH 0090/1346] drm/i915: Set SSC frequency for 8xx chips correctly All 8xx class chips have the 66/48 split, not just 855. Signed-off-by: Ma Ling Reviewed-by: Jesse Barnes Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/intel_bios.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 716409a5724..da22863c05c 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -195,10 +195,12 @@ parse_general_features(struct drm_i915_private *dev_priv, dev_priv->lvds_use_ssc = general->enable_ssc; if (dev_priv->lvds_use_ssc) { - if (IS_I855(dev_priv->dev)) - dev_priv->lvds_ssc_freq = general->ssc_freq ? 66 : 48; - else - dev_priv->lvds_ssc_freq = general->ssc_freq ? 100 : 96; + if (IS_I85X(dev_priv->dev)) + dev_priv->lvds_ssc_freq = + general->ssc_freq ? 66 : 48; + else + dev_priv->lvds_ssc_freq = + general->ssc_freq ? 100 : 96; } } } From 12682a971160959072c4970da9b7778709f60bc9 Mon Sep 17 00:00:00 2001 From: "ling.ma@intel.com" Date: Tue, 30 Jun 2009 11:35:35 +0800 Subject: [PATCH 0091/1346] drm/i915: enable sdvo lvds scaling function. Currently we implemented basic sdvo lvds function, But except for sdvo lvds fixed mode, we can not switch to other modes, otherwise display get black. The patch handle three operations to enable sdvo lvds. At first duplicate sdvo fixed mode for adjustment, then according to fixed mode line valid all modes, at last adjust input mode to fit our requirement. Acked by Li Peng Signed-off-by: Ma Ling Reviewed-by: Ian Romanick Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/intel_sdvo.c | 114 ++++++++++++++++++++++--- drivers/gpu/drm/i915/intel_sdvo_regs.h | 1 + 2 files changed, 103 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index f03473779fe..4f0c30948bc 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -68,11 +68,22 @@ struct intel_sdvo_priv { * This is set if we treat the device as HDMI, instead of DVI. */ bool is_hdmi; + /** * This is set if we detect output of sdvo device as LVDS. */ bool is_lvds; + /** + * This is sdvo flags for input timing. + */ + uint8_t sdvo_flags; + + /** + * This is sdvo fixed pannel mode pointer + */ + struct drm_display_mode *sdvo_lvds_fixed_mode; + /** * Returned SDTV resolutions allowed for the current format, if the * device reported it. @@ -592,6 +603,7 @@ intel_sdvo_create_preferred_input_timing(struct intel_output *output, uint16_t height) { struct intel_sdvo_preferred_input_timing_args args; + struct intel_sdvo_priv *sdvo_priv = output->dev_priv; uint8_t status; memset(&args, 0, sizeof(args)); @@ -599,7 +611,12 @@ intel_sdvo_create_preferred_input_timing(struct intel_output *output, args.width = width; args.height = height; args.interlace = 0; - args.scaled = 0; + + if (sdvo_priv->is_lvds && + (sdvo_priv->sdvo_lvds_fixed_mode->hdisplay != width || + sdvo_priv->sdvo_lvds_fixed_mode->vdisplay != height)) + args.scaled = 1; + intel_sdvo_write_cmd(output, SDVO_CMD_CREATE_PREFERRED_INPUT_TIMING, &args, sizeof(args)); status = intel_sdvo_read_response(output, NULL, 0); @@ -944,12 +961,7 @@ static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder, struct intel_output *output = enc_to_intel_output(encoder); struct intel_sdvo_priv *dev_priv = output->dev_priv; - if (!dev_priv->is_tv) { - /* Make the CRTC code factor in the SDVO pixel multiplier. The - * SDVO device will be told of the multiplier during mode_set. - */ - adjusted_mode->clock *= intel_sdvo_get_pixel_multiplier(mode); - } else { + if (dev_priv->is_tv) { struct intel_sdvo_dtd output_dtd; bool success; @@ -980,6 +992,7 @@ static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder, intel_sdvo_get_preferred_input_timing(output, &input_dtd); intel_sdvo_get_mode_from_dtd(adjusted_mode, &input_dtd); + dev_priv->sdvo_flags = input_dtd.part2.sdvo_flags; drm_mode_set_crtcinfo(adjusted_mode, 0); @@ -990,6 +1003,52 @@ static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder, } else { return false; } + } else if (dev_priv->is_lvds) { + struct intel_sdvo_dtd output_dtd; + bool success; + + drm_mode_set_crtcinfo(dev_priv->sdvo_lvds_fixed_mode, 0); + /* Set output timings */ + intel_sdvo_get_dtd_from_mode(&output_dtd, + dev_priv->sdvo_lvds_fixed_mode); + + intel_sdvo_set_target_output(output, + dev_priv->controlled_output); + intel_sdvo_set_output_timing(output, &output_dtd); + + /* Set the input timing to the screen. Assume always input 0. */ + intel_sdvo_set_target_input(output, true, false); + + + success = intel_sdvo_create_preferred_input_timing( + output, + mode->clock / 10, + mode->hdisplay, + mode->vdisplay); + + if (success) { + struct intel_sdvo_dtd input_dtd; + + intel_sdvo_get_preferred_input_timing(output, + &input_dtd); + intel_sdvo_get_mode_from_dtd(adjusted_mode, &input_dtd); + dev_priv->sdvo_flags = input_dtd.part2.sdvo_flags; + + drm_mode_set_crtcinfo(adjusted_mode, 0); + + mode->clock = adjusted_mode->clock; + + adjusted_mode->clock *= + intel_sdvo_get_pixel_multiplier(mode); + } else { + return false; + } + + } else { + /* Make the CRTC code factor in the SDVO pixel multiplier. The + * SDVO device will be told of the multiplier during mode_set. + */ + adjusted_mode->clock *= intel_sdvo_get_pixel_multiplier(mode); } return true; } @@ -1033,15 +1092,16 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder, /* We have tried to get input timing in mode_fixup, and filled into adjusted_mode */ - if (sdvo_priv->is_tv) + if (sdvo_priv->is_tv || sdvo_priv->is_lvds) { intel_sdvo_get_dtd_from_mode(&input_dtd, adjusted_mode); - else + input_dtd.part2.sdvo_flags = sdvo_priv->sdvo_flags; + } else intel_sdvo_get_dtd_from_mode(&input_dtd, mode); /* If it's a TV, we already set the output timing in mode_fixup. * Otherwise, the output timing is equal to the input timing. */ - if (!sdvo_priv->is_tv) { + if (!sdvo_priv->is_tv && !sdvo_priv->is_lvds) { /* Set the output timing to the screen */ intel_sdvo_set_target_output(output, sdvo_priv->controlled_output); @@ -1116,6 +1176,8 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder, sdvox |= (sdvo_pixel_multiply - 1) << SDVO_PORT_MULTIPLY_SHIFT; } + if (sdvo_priv->sdvo_flags & SDVO_NEED_TO_STALL) + sdvox |= SDVO_STALL_SELECT; intel_sdvo_write_sdvox(output, sdvox); } @@ -1276,6 +1338,17 @@ static int intel_sdvo_mode_valid(struct drm_connector *connector, if (sdvo_priv->pixel_clock_max < mode->clock) return MODE_CLOCK_HIGH; + if (sdvo_priv->is_lvds == true) { + if (sdvo_priv->sdvo_lvds_fixed_mode == NULL) + return MODE_PANEL; + + if (mode->hdisplay > sdvo_priv->sdvo_lvds_fixed_mode->hdisplay) + return MODE_PANEL; + + if (mode->vdisplay > sdvo_priv->sdvo_lvds_fixed_mode->vdisplay) + return MODE_PANEL; + } + return MODE_OK; } @@ -1549,6 +1622,8 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); struct drm_i915_private *dev_priv = connector->dev->dev_private; + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; + struct drm_display_mode *newmode; /* * Attempt to get the mode list from DDC. @@ -1557,11 +1632,10 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector) */ intel_ddc_get_modes(intel_output); if (list_empty(&connector->probed_modes) == false) - return; + goto end; /* Fetch modes from VBT */ if (dev_priv->sdvo_lvds_vbt_mode != NULL) { - struct drm_display_mode *newmode; newmode = drm_mode_duplicate(connector->dev, dev_priv->sdvo_lvds_vbt_mode); if (newmode != NULL) { @@ -1571,6 +1645,16 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector) drm_mode_probed_add(connector, newmode); } } + +end: + list_for_each_entry(newmode, &connector->probed_modes, head) { + if (newmode->type & DRM_MODE_TYPE_PREFERRED) { + sdvo_priv->sdvo_lvds_fixed_mode = + drm_mode_duplicate(connector->dev, newmode); + break; + } + } + } static int intel_sdvo_get_modes(struct drm_connector *connector) @@ -1593,14 +1677,20 @@ static int intel_sdvo_get_modes(struct drm_connector *connector) static void intel_sdvo_destroy(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; if (intel_output->i2c_bus) intel_i2c_destroy(intel_output->i2c_bus); if (intel_output->ddc_bus) intel_i2c_destroy(intel_output->ddc_bus); + if (sdvo_priv->sdvo_lvds_fixed_mode != NULL) + drm_mode_destroy(connector->dev, + sdvo_priv->sdvo_lvds_fixed_mode); + drm_sysfs_connector_remove(connector); drm_connector_cleanup(connector); + kfree(intel_output); } diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h index 193938b7d7f..ba5cdf8ae40 100644 --- a/drivers/gpu/drm/i915/intel_sdvo_regs.h +++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h @@ -715,6 +715,7 @@ struct intel_sdvo_enhancements_arg { #define SDVO_HBUF_TX_ONCE (2 << 6) #define SDVO_HBUF_TX_VSYNC (3 << 6) #define SDVO_CMD_GET_AUDIO_TX_INFO 0x9c +#define SDVO_NEED_TO_STALL (1 << 7) struct intel_sdvo_encode{ u8 dvi_rev; From 43cbcd8acb4c992cbd22d1ec8a08c0591be5d719 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 1 Jul 2009 12:28:37 -0300 Subject: [PATCH 0092/1346] perf_counter tools: Share rbtree.with the kernel The tools/perf/util/rbtree.c copy already drifted by three csets: 4b324126e0c6c3a5080ca3ec0981e8766ed6f1ee 4c60117811171d867d4f27f17ea07d7419d45dae 16c047add3ceaf0ab882e3e094d1ec904d02312d So remove the copy and use the lib/rbtree.c directly, sharing the source code while still generating a separate object file, since tools/perf uses a far more agressive -O6 switch. Signed-off-by: Arnaldo Carvalho de Melo Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Frederic Weisbecker LKML-Reference: <20090701152837.GG15682@ghostprotocols.net> Signed-off-by: Ingo Molnar --- tools/perf/Makefile | 7 +- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/util/callchain.h | 2 +- tools/perf/util/include/linux/kernel.h | 21 ++ tools/perf/util/include/linux/module.h | 6 + tools/perf/util/include/linux/rbtree.h | 1 + tools/perf/util/rbtree.c | 383 ------------------------- tools/perf/util/rbtree.h | 171 ----------- tools/perf/util/strlist.h | 2 +- tools/perf/util/symbol.h | 2 +- 12 files changed, 39 insertions(+), 562 deletions(-) create mode 100644 tools/perf/util/include/linux/kernel.h create mode 100644 tools/perf/util/include/linux/module.h create mode 100644 tools/perf/util/include/linux/rbtree.h delete mode 100644 tools/perf/util/rbtree.c delete mode 100644 tools/perf/util/rbtree.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index eddf076b19d..c4f48825a6e 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -223,7 +223,7 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ # Those must not be GNU-specific; they are shared with perl/ which may # be built by a different compiler. (Note that this is an artifact now # but it still might be nice to keep that distinction.) -BASIC_CFLAGS = +BASIC_CFLAGS = -Iutil/include BASIC_LDFLAGS = # Guard against environment variables @@ -289,10 +289,10 @@ export PERL_PATH LIB_FILE=libperf.a LIB_H += ../../include/linux/perf_counter.h +LIB_H += ../../include/linux/rbtree.h LIB_H += perf.h LIB_H += util/types.h LIB_H += util/list.h -LIB_H += util/rbtree.h LIB_H += util/levenshtein.h LIB_H += util/parse-options.h LIB_H += util/parse-events.h @@ -691,6 +691,9 @@ builtin-init-db.o: builtin-init-db.c PERF-CFLAGS util/config.o: util/config.c PERF-CFLAGS $(QUIET_CC)$(CC) -o $*.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +util/rbtree.o: ../../lib/rbtree.c PERF-CFLAGS + $(QUIET_CC)$(CC) -o util/rbtree.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + perf-%$X: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 6cba70daf12..1960c22b816 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -12,7 +12,7 @@ #include "util/color.h" #include "util/list.h" #include "util/cache.h" -#include "util/rbtree.h" +#include #include "util/symbol.h" #include "util/string.h" diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 007363db3b1..0d35e2b8881 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -12,7 +12,7 @@ #include "util/color.h" #include "util/list.h" #include "util/cache.h" -#include "util/rbtree.h" +#include #include "util/symbol.h" #include "util/string.h" #include "util/callchain.h" diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5f5e7df8302..cdc74cfb151 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -23,7 +23,7 @@ #include "util/symbol.h" #include "util/color.h" #include "util/util.h" -#include "util/rbtree.h" +#include #include "util/parse-options.h" #include "util/parse-events.h" diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 251d99ecd22..0606b8fd05a 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -3,7 +3,7 @@ #include "../perf.h" #include "list.h" -#include "rbtree.h" +#include #include "symbol.h" diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h new file mode 100644 index 00000000000..99c1b3d1edd --- /dev/null +++ b/tools/perf/util/include/linux/kernel.h @@ -0,0 +1,21 @@ +#ifndef PERF_LINUX_KERNEL_H_ +#define PERF_LINUX_KERNEL_H_ + +#ifndef offsetof +#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) +#endif + +#ifndef container_of +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + const typeof(((type *)0)->member) * __mptr = (ptr); \ + (type *)((char *)__mptr - offsetof(type, member)); }) +#endif + +#endif diff --git a/tools/perf/util/include/linux/module.h b/tools/perf/util/include/linux/module.h new file mode 100644 index 00000000000..b43e2dc21e0 --- /dev/null +++ b/tools/perf/util/include/linux/module.h @@ -0,0 +1,6 @@ +#ifndef PERF_LINUX_MODULE_H +#define PERF_LINUX_MODULE_H + +#define EXPORT_SYMBOL(name) + +#endif diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h new file mode 100644 index 00000000000..7a243a14303 --- /dev/null +++ b/tools/perf/util/include/linux/rbtree.h @@ -0,0 +1 @@ +#include "../../../../include/linux/rbtree.h" diff --git a/tools/perf/util/rbtree.c b/tools/perf/util/rbtree.c deleted file mode 100644 index b15ba9c7cb3..00000000000 --- a/tools/perf/util/rbtree.c +++ /dev/null @@ -1,383 +0,0 @@ -/* - Red Black Trees - (C) 1999 Andrea Arcangeli - (C) 2002 David Woodhouse - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - - linux/lib/rbtree.c -*/ - -#include "rbtree.h" - -static void __rb_rotate_left(struct rb_node *node, struct rb_root *root) -{ - struct rb_node *right = node->rb_right; - struct rb_node *parent = rb_parent(node); - - if ((node->rb_right = right->rb_left)) - rb_set_parent(right->rb_left, node); - right->rb_left = node; - - rb_set_parent(right, parent); - - if (parent) - { - if (node == parent->rb_left) - parent->rb_left = right; - else - parent->rb_right = right; - } - else - root->rb_node = right; - rb_set_parent(node, right); -} - -static void __rb_rotate_right(struct rb_node *node, struct rb_root *root) -{ - struct rb_node *left = node->rb_left; - struct rb_node *parent = rb_parent(node); - - if ((node->rb_left = left->rb_right)) - rb_set_parent(left->rb_right, node); - left->rb_right = node; - - rb_set_parent(left, parent); - - if (parent) - { - if (node == parent->rb_right) - parent->rb_right = left; - else - parent->rb_left = left; - } - else - root->rb_node = left; - rb_set_parent(node, left); -} - -void rb_insert_color(struct rb_node *node, struct rb_root *root) -{ - struct rb_node *parent, *gparent; - - while ((parent = rb_parent(node)) && rb_is_red(parent)) - { - gparent = rb_parent(parent); - - if (parent == gparent->rb_left) - { - { - register struct rb_node *uncle = gparent->rb_right; - if (uncle && rb_is_red(uncle)) - { - rb_set_black(uncle); - rb_set_black(parent); - rb_set_red(gparent); - node = gparent; - continue; - } - } - - if (parent->rb_right == node) - { - register struct rb_node *tmp; - __rb_rotate_left(parent, root); - tmp = parent; - parent = node; - node = tmp; - } - - rb_set_black(parent); - rb_set_red(gparent); - __rb_rotate_right(gparent, root); - } else { - { - register struct rb_node *uncle = gparent->rb_left; - if (uncle && rb_is_red(uncle)) - { - rb_set_black(uncle); - rb_set_black(parent); - rb_set_red(gparent); - node = gparent; - continue; - } - } - - if (parent->rb_left == node) - { - register struct rb_node *tmp; - __rb_rotate_right(parent, root); - tmp = parent; - parent = node; - node = tmp; - } - - rb_set_black(parent); - rb_set_red(gparent); - __rb_rotate_left(gparent, root); - } - } - - rb_set_black(root->rb_node); -} - -static void __rb_erase_color(struct rb_node *node, struct rb_node *parent, - struct rb_root *root) -{ - struct rb_node *other; - - while ((!node || rb_is_black(node)) && node != root->rb_node) - { - if (parent->rb_left == node) - { - other = parent->rb_right; - if (rb_is_red(other)) - { - rb_set_black(other); - rb_set_red(parent); - __rb_rotate_left(parent, root); - other = parent->rb_right; - } - if ((!other->rb_left || rb_is_black(other->rb_left)) && - (!other->rb_right || rb_is_black(other->rb_right))) - { - rb_set_red(other); - node = parent; - parent = rb_parent(node); - } - else - { - if (!other->rb_right || rb_is_black(other->rb_right)) - { - rb_set_black(other->rb_left); - rb_set_red(other); - __rb_rotate_right(other, root); - other = parent->rb_right; - } - rb_set_color(other, rb_color(parent)); - rb_set_black(parent); - rb_set_black(other->rb_right); - __rb_rotate_left(parent, root); - node = root->rb_node; - break; - } - } - else - { - other = parent->rb_left; - if (rb_is_red(other)) - { - rb_set_black(other); - rb_set_red(parent); - __rb_rotate_right(parent, root); - other = parent->rb_left; - } - if ((!other->rb_left || rb_is_black(other->rb_left)) && - (!other->rb_right || rb_is_black(other->rb_right))) - { - rb_set_red(other); - node = parent; - parent = rb_parent(node); - } - else - { - if (!other->rb_left || rb_is_black(other->rb_left)) - { - rb_set_black(other->rb_right); - rb_set_red(other); - __rb_rotate_left(other, root); - other = parent->rb_left; - } - rb_set_color(other, rb_color(parent)); - rb_set_black(parent); - rb_set_black(other->rb_left); - __rb_rotate_right(parent, root); - node = root->rb_node; - break; - } - } - } - if (node) - rb_set_black(node); -} - -void rb_erase(struct rb_node *node, struct rb_root *root) -{ - struct rb_node *child, *parent; - int color; - - if (!node->rb_left) - child = node->rb_right; - else if (!node->rb_right) - child = node->rb_left; - else - { - struct rb_node *old = node, *left; - - node = node->rb_right; - while ((left = node->rb_left) != NULL) - node = left; - child = node->rb_right; - parent = rb_parent(node); - color = rb_color(node); - - if (child) - rb_set_parent(child, parent); - if (parent == old) { - parent->rb_right = child; - parent = node; - } else - parent->rb_left = child; - - node->rb_parent_color = old->rb_parent_color; - node->rb_right = old->rb_right; - node->rb_left = old->rb_left; - - if (rb_parent(old)) - { - if (rb_parent(old)->rb_left == old) - rb_parent(old)->rb_left = node; - else - rb_parent(old)->rb_right = node; - } else - root->rb_node = node; - - rb_set_parent(old->rb_left, node); - if (old->rb_right) - rb_set_parent(old->rb_right, node); - goto color; - } - - parent = rb_parent(node); - color = rb_color(node); - - if (child) - rb_set_parent(child, parent); - if (parent) - { - if (parent->rb_left == node) - parent->rb_left = child; - else - parent->rb_right = child; - } - else - root->rb_node = child; - - color: - if (color == RB_BLACK) - __rb_erase_color(child, parent, root); -} - -/* - * This function returns the first node (in sort order) of the tree. - */ -struct rb_node *rb_first(const struct rb_root *root) -{ - struct rb_node *n; - - n = root->rb_node; - if (!n) - return NULL; - while (n->rb_left) - n = n->rb_left; - return n; -} - -struct rb_node *rb_last(const struct rb_root *root) -{ - struct rb_node *n; - - n = root->rb_node; - if (!n) - return NULL; - while (n->rb_right) - n = n->rb_right; - return n; -} - -struct rb_node *rb_next(const struct rb_node *node) -{ - struct rb_node *parent; - - if (rb_parent(node) == node) - return NULL; - - /* If we have a right-hand child, go down and then left as far - as we can. */ - if (node->rb_right) { - node = node->rb_right; - while (node->rb_left) - node=node->rb_left; - return (struct rb_node *)node; - } - - /* No right-hand children. Everything down and left is - smaller than us, so any 'next' node must be in the general - direction of our parent. Go up the tree; any time the - ancestor is a right-hand child of its parent, keep going - up. First time it's a left-hand child of its parent, said - parent is our 'next' node. */ - while ((parent = rb_parent(node)) && node == parent->rb_right) - node = parent; - - return parent; -} - -struct rb_node *rb_prev(const struct rb_node *node) -{ - struct rb_node *parent; - - if (rb_parent(node) == node) - return NULL; - - /* If we have a left-hand child, go down and then right as far - as we can. */ - if (node->rb_left) { - node = node->rb_left; - while (node->rb_right) - node=node->rb_right; - return (struct rb_node *)node; - } - - /* No left-hand children. Go up till we find an ancestor which - is a right-hand child of its parent */ - while ((parent = rb_parent(node)) && node == parent->rb_left) - node = parent; - - return parent; -} - -void rb_replace_node(struct rb_node *victim, struct rb_node *new, - struct rb_root *root) -{ - struct rb_node *parent = rb_parent(victim); - - /* Set the surrounding nodes to point to the replacement */ - if (parent) { - if (victim == parent->rb_left) - parent->rb_left = new; - else - parent->rb_right = new; - } else { - root->rb_node = new; - } - if (victim->rb_left) - rb_set_parent(victim->rb_left, new); - if (victim->rb_right) - rb_set_parent(victim->rb_right, new); - - /* Copy the pointers/colour from the victim to the replacement */ - *new = *victim; -} diff --git a/tools/perf/util/rbtree.h b/tools/perf/util/rbtree.h deleted file mode 100644 index 6bdc488a47f..00000000000 --- a/tools/perf/util/rbtree.h +++ /dev/null @@ -1,171 +0,0 @@ -/* - Red Black Trees - (C) 1999 Andrea Arcangeli - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - - linux/include/linux/rbtree.h - - To use rbtrees you'll have to implement your own insert and search cores. - This will avoid us to use callbacks and to drop drammatically performances. - I know it's not the cleaner way, but in C (not in C++) to get - performances and genericity... - - Some example of insert and search follows here. The search is a plain - normal search over an ordered tree. The insert instead must be implemented - int two steps: as first thing the code must insert the element in - order as a red leaf in the tree, then the support library function - rb_insert_color() must be called. Such function will do the - not trivial work to rebalance the rbtree if necessary. - ------------------------------------------------------------------------ -static inline struct page * rb_search_page_cache(struct inode * inode, - unsigned long offset) -{ - struct rb_node * n = inode->i_rb_page_cache.rb_node; - struct page * page; - - while (n) - { - page = rb_entry(n, struct page, rb_page_cache); - - if (offset < page->offset) - n = n->rb_left; - else if (offset > page->offset) - n = n->rb_right; - else - return page; - } - return NULL; -} - -static inline struct page * __rb_insert_page_cache(struct inode * inode, - unsigned long offset, - struct rb_node * node) -{ - struct rb_node ** p = &inode->i_rb_page_cache.rb_node; - struct rb_node * parent = NULL; - struct page * page; - - while (*p) - { - parent = *p; - page = rb_entry(parent, struct page, rb_page_cache); - - if (offset < page->offset) - p = &(*p)->rb_left; - else if (offset > page->offset) - p = &(*p)->rb_right; - else - return page; - } - - rb_link_node(node, parent, p); - - return NULL; -} - -static inline struct page * rb_insert_page_cache(struct inode * inode, - unsigned long offset, - struct rb_node * node) -{ - struct page * ret; - if ((ret = __rb_insert_page_cache(inode, offset, node))) - goto out; - rb_insert_color(node, &inode->i_rb_page_cache); - out: - return ret; -} ------------------------------------------------------------------------ -*/ - -#ifndef _LINUX_RBTREE_H -#define _LINUX_RBTREE_H - -#include - -/** - * container_of - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) - -struct rb_node -{ - unsigned long rb_parent_color; -#define RB_RED 0 -#define RB_BLACK 1 - struct rb_node *rb_right; - struct rb_node *rb_left; -} __attribute__((aligned(sizeof(long)))); - /* The alignment might seem pointless, but allegedly CRIS needs it */ - -struct rb_root -{ - struct rb_node *rb_node; -}; - - -#define rb_parent(r) ((struct rb_node *)((r)->rb_parent_color & ~3)) -#define rb_color(r) ((r)->rb_parent_color & 1) -#define rb_is_red(r) (!rb_color(r)) -#define rb_is_black(r) rb_color(r) -#define rb_set_red(r) do { (r)->rb_parent_color &= ~1; } while (0) -#define rb_set_black(r) do { (r)->rb_parent_color |= 1; } while (0) - -static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) -{ - rb->rb_parent_color = (rb->rb_parent_color & 3) | (unsigned long)p; -} -static inline void rb_set_color(struct rb_node *rb, int color) -{ - rb->rb_parent_color = (rb->rb_parent_color & ~1) | color; -} - -#define RB_ROOT (struct rb_root) { NULL, } -#define rb_entry(ptr, type, member) container_of(ptr, type, member) - -#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL) -#define RB_EMPTY_NODE(node) (rb_parent(node) == node) -#define RB_CLEAR_NODE(node) (rb_set_parent(node, node)) - -extern void rb_insert_color(struct rb_node *, struct rb_root *); -extern void rb_erase(struct rb_node *, struct rb_root *); - -/* Find logical next and previous nodes in a tree */ -extern struct rb_node *rb_next(const struct rb_node *); -extern struct rb_node *rb_prev(const struct rb_node *); -extern struct rb_node *rb_first(const struct rb_root *); -extern struct rb_node *rb_last(const struct rb_root *); - -/* Fast replacement of a single node without remove/rebalance/add/rebalance */ -extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, - struct rb_root *root); - -static inline void rb_link_node(struct rb_node * node, struct rb_node * parent, - struct rb_node ** rb_link) -{ - node->rb_parent_color = (unsigned long )parent; - node->rb_left = node->rb_right = NULL; - - *rb_link = node; -} - -#endif /* _LINUX_RBTREE_H */ diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 2fb117fb4b6..2fdcfee8758 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -1,7 +1,7 @@ #ifndef STRLIST_H_ #define STRLIST_H_ -#include "rbtree.h" +#include #include struct str_node { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2c48ace8203..3a275db1fa6 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -4,7 +4,7 @@ #include #include "types.h" #include "list.h" -#include "rbtree.h" +#include struct symbol { struct rb_node rb_node; From 5da50258584469ddfee6545feb4eb2252a8d7e7b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 1 Jul 2009 14:46:08 -0300 Subject: [PATCH 0093/1346] perf_counter tools: Share list.h with the kernel The copy we were using came from another copy I did for the dwarves (pahole) package, that came from the kernel years ago. The only function that is used by the perf tools and that isn't in the kernel is list_del_range, that I'm leaving in the perf tools only for now. Signed-off-by: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras LKML-Reference: <20090701174608.GA5823@ghostprotocols.net> Signed-off-by: Ingo Molnar --- tools/perf/Makefile | 3 +- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/util/callchain.h | 2 +- tools/perf/util/include/asm/system.h | 1 + tools/perf/util/include/linux/list.h | 18 + tools/perf/util/include/linux/poison.h | 1 + tools/perf/util/include/linux/prefetch.h | 6 + tools/perf/util/list.h | 603 ----------------------- tools/perf/util/symbol.h | 2 +- 10 files changed, 32 insertions(+), 608 deletions(-) create mode 100644 tools/perf/util/include/asm/system.h create mode 100644 tools/perf/util/include/linux/list.h create mode 100644 tools/perf/util/include/linux/poison.h create mode 100644 tools/perf/util/include/linux/prefetch.h delete mode 100644 tools/perf/util/list.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index c4f48825a6e..8f7fd1b050a 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -290,9 +290,10 @@ LIB_FILE=libperf.a LIB_H += ../../include/linux/perf_counter.h LIB_H += ../../include/linux/rbtree.h +LIB_H += ../../include/linux/list.h +LIB_H += util/include/linux/list.h LIB_H += perf.h LIB_H += util/types.h -LIB_H += util/list.h LIB_H += util/levenshtein.h LIB_H += util/parse-options.h LIB_H += util/parse-events.h diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 1960c22b816..132de8b28db 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -10,7 +10,7 @@ #include "util/util.h" #include "util/color.h" -#include "util/list.h" +#include #include "util/cache.h" #include #include "util/symbol.h" diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0d35e2b8881..be1b7584796 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -10,7 +10,7 @@ #include "util/util.h" #include "util/color.h" -#include "util/list.h" +#include #include "util/cache.h" #include #include "util/symbol.h" diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 0606b8fd05a..e9bd5e882f3 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -2,7 +2,7 @@ #define __PERF_CALLCHAIN_H #include "../perf.h" -#include "list.h" +#include #include #include "symbol.h" diff --git a/tools/perf/util/include/asm/system.h b/tools/perf/util/include/asm/system.h new file mode 100644 index 00000000000..710cecca972 --- /dev/null +++ b/tools/perf/util/include/asm/system.h @@ -0,0 +1 @@ +/* Empty */ diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h new file mode 100644 index 00000000000..dbe4b814382 --- /dev/null +++ b/tools/perf/util/include/linux/list.h @@ -0,0 +1,18 @@ +#include "../../../../include/linux/list.h" + +#ifndef PERF_LIST_H +#define PERF_LIST_H +/** + * list_del_range - deletes range of entries from list. + * @begin: first element in the range to delete from the list. + * @end: last element in the range to delete from the list. + * Note: list_empty on the range of entries does not return true after this, + * the entries is in an undefined state. + */ +static inline void list_del_range(struct list_head *begin, + struct list_head *end) +{ + begin->prev->next = end->next; + end->next->prev = begin->prev; +} +#endif diff --git a/tools/perf/util/include/linux/poison.h b/tools/perf/util/include/linux/poison.h new file mode 100644 index 00000000000..fef6dbc9ce1 --- /dev/null +++ b/tools/perf/util/include/linux/poison.h @@ -0,0 +1 @@ +#include "../../../../include/linux/poison.h" diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h new file mode 100644 index 00000000000..7841e485d8c --- /dev/null +++ b/tools/perf/util/include/linux/prefetch.h @@ -0,0 +1,6 @@ +#ifndef PERF_LINUX_PREFETCH_H +#define PERF_LINUX_PREFETCH_H + +static inline void prefetch(void *a __attribute__((unused))) { } + +#endif diff --git a/tools/perf/util/list.h b/tools/perf/util/list.h deleted file mode 100644 index e2548e8072c..00000000000 --- a/tools/perf/util/list.h +++ /dev/null @@ -1,603 +0,0 @@ -#ifndef _LINUX_LIST_H -#define _LINUX_LIST_H -/* - Copyright (C) Cast of dozens, comes from the Linux kernel - - This program is free software; you can redistribute it and/or modify it - under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. -*/ - -#include - -/* - * These are non-NULL pointers that will result in page faults - * under normal circumstances, used to verify that nobody uses - * non-initialized list entries. - */ -#define LIST_POISON1 ((void *)0x00100100) -#define LIST_POISON2 ((void *)0x00200200) - -/** - * container_of - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) - -/* - * Simple doubly linked list implementation. - * - * Some of the internal functions ("__xxx") are useful when - * manipulating whole lists rather than single entries, as - * sometimes we already know the next/prev entries and we can - * generate better code by using them directly rather than - * using the generic single-entry routines. - */ - -struct list_head { - struct list_head *next, *prev; -}; - -#define LIST_HEAD_INIT(name) { &(name), &(name) } - -#define LIST_HEAD(name) \ - struct list_head name = LIST_HEAD_INIT(name) - -static inline void INIT_LIST_HEAD(struct list_head *list) -{ - list->next = list; - list->prev = list; -} - -/* - * Insert a new entry between two known consecutive entries. - * - * This is only for internal list manipulation where we know - * the prev/next entries already! - */ -static inline void __list_add(struct list_head *new, - struct list_head *prev, - struct list_head *next) -{ - next->prev = new; - new->next = next; - new->prev = prev; - prev->next = new; -} - -/** - * list_add - add a new entry - * @new: new entry to be added - * @head: list head to add it after - * - * Insert a new entry after the specified head. - * This is good for implementing stacks. - */ -static inline void list_add(struct list_head *new, struct list_head *head) -{ - __list_add(new, head, head->next); -} - -/** - * list_add_tail - add a new entry - * @new: new entry to be added - * @head: list head to add it before - * - * Insert a new entry before the specified head. - * This is useful for implementing queues. - */ -static inline void list_add_tail(struct list_head *new, struct list_head *head) -{ - __list_add(new, head->prev, head); -} - -/* - * Delete a list entry by making the prev/next entries - * point to each other. - * - * This is only for internal list manipulation where we know - * the prev/next entries already! - */ -static inline void __list_del(struct list_head * prev, struct list_head * next) -{ - next->prev = prev; - prev->next = next; -} - -/** - * list_del - deletes entry from list. - * @entry: the element to delete from the list. - * Note: list_empty on entry does not return true after this, the entry is - * in an undefined state. - */ -static inline void list_del(struct list_head *entry) -{ - __list_del(entry->prev, entry->next); - entry->next = LIST_POISON1; - entry->prev = LIST_POISON2; -} - -/** - * list_del_range - deletes range of entries from list. - * @beging: first element in the range to delete from the list. - * @beging: first element in the range to delete from the list. - * Note: list_empty on the range of entries does not return true after this, - * the entries is in an undefined state. - */ -static inline void list_del_range(struct list_head *begin, - struct list_head *end) -{ - begin->prev->next = end->next; - end->next->prev = begin->prev; -} - -/** - * list_replace - replace old entry by new one - * @old : the element to be replaced - * @new : the new element to insert - * Note: if 'old' was empty, it will be overwritten. - */ -static inline void list_replace(struct list_head *old, - struct list_head *new) -{ - new->next = old->next; - new->next->prev = new; - new->prev = old->prev; - new->prev->next = new; -} - -static inline void list_replace_init(struct list_head *old, - struct list_head *new) -{ - list_replace(old, new); - INIT_LIST_HEAD(old); -} - -/** - * list_del_init - deletes entry from list and reinitialize it. - * @entry: the element to delete from the list. - */ -static inline void list_del_init(struct list_head *entry) -{ - __list_del(entry->prev, entry->next); - INIT_LIST_HEAD(entry); -} - -/** - * list_move - delete from one list and add as another's head - * @list: the entry to move - * @head: the head that will precede our entry - */ -static inline void list_move(struct list_head *list, struct list_head *head) -{ - __list_del(list->prev, list->next); - list_add(list, head); -} - -/** - * list_move_tail - delete from one list and add as another's tail - * @list: the entry to move - * @head: the head that will follow our entry - */ -static inline void list_move_tail(struct list_head *list, - struct list_head *head) -{ - __list_del(list->prev, list->next); - list_add_tail(list, head); -} - -/** - * list_is_last - tests whether @list is the last entry in list @head - * @list: the entry to test - * @head: the head of the list - */ -static inline int list_is_last(const struct list_head *list, - const struct list_head *head) -{ - return list->next == head; -} - -/** - * list_empty - tests whether a list is empty - * @head: the list to test. - */ -static inline int list_empty(const struct list_head *head) -{ - return head->next == head; -} - -/** - * list_empty_careful - tests whether a list is empty and not being modified - * @head: the list to test - * - * Description: - * tests whether a list is empty _and_ checks that no other CPU might be - * in the process of modifying either member (next or prev) - * - * NOTE: using list_empty_careful() without synchronization - * can only be safe if the only activity that can happen - * to the list entry is list_del_init(). Eg. it cannot be used - * if another CPU could re-list_add() it. - */ -static inline int list_empty_careful(const struct list_head *head) -{ - struct list_head *next = head->next; - return (next == head) && (next == head->prev); -} - -static inline void __list_splice(struct list_head *list, - struct list_head *head) -{ - struct list_head *first = list->next; - struct list_head *last = list->prev; - struct list_head *at = head->next; - - first->prev = head; - head->next = first; - - last->next = at; - at->prev = last; -} - -/** - * list_splice - join two lists - * @list: the new list to add. - * @head: the place to add it in the first list. - */ -static inline void list_splice(struct list_head *list, struct list_head *head) -{ - if (!list_empty(list)) - __list_splice(list, head); -} - -/** - * list_splice_init - join two lists and reinitialise the emptied list. - * @list: the new list to add. - * @head: the place to add it in the first list. - * - * The list at @list is reinitialised - */ -static inline void list_splice_init(struct list_head *list, - struct list_head *head) -{ - if (!list_empty(list)) { - __list_splice(list, head); - INIT_LIST_HEAD(list); - } -} - -/** - * list_entry - get the struct for this entry - * @ptr: the &struct list_head pointer. - * @type: the type of the struct this is embedded in. - * @member: the name of the list_struct within the struct. - */ -#define list_entry(ptr, type, member) \ - container_of(ptr, type, member) - -/** - * list_first_entry - get the first element from a list - * @ptr: the list head to take the element from. - * @type: the type of the struct this is embedded in. - * @member: the name of the list_struct within the struct. - * - * Note, that list is expected to be not empty. - */ -#define list_first_entry(ptr, type, member) \ - list_entry((ptr)->next, type, member) - -/** - * list_for_each - iterate over a list - * @pos: the &struct list_head to use as a loop cursor. - * @head: the head for your list. - */ -#define list_for_each(pos, head) \ - for (pos = (head)->next; pos != (head); \ - pos = pos->next) - -/** - * __list_for_each - iterate over a list - * @pos: the &struct list_head to use as a loop cursor. - * @head: the head for your list. - * - * This variant differs from list_for_each() in that it's the - * simplest possible list iteration code, no prefetching is done. - * Use this for code that knows the list to be very short (empty - * or 1 entry) most of the time. - */ -#define __list_for_each(pos, head) \ - for (pos = (head)->next; pos != (head); pos = pos->next) - -/** - * list_for_each_prev - iterate over a list backwards - * @pos: the &struct list_head to use as a loop cursor. - * @head: the head for your list. - */ -#define list_for_each_prev(pos, head) \ - for (pos = (head)->prev; pos != (head); \ - pos = pos->prev) - -/** - * list_for_each_safe - iterate over a list safe against removal of list entry - * @pos: the &struct list_head to use as a loop cursor. - * @n: another &struct list_head to use as temporary storage - * @head: the head for your list. - */ -#define list_for_each_safe(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = n, n = pos->next) - -/** - * list_for_each_entry - iterate over list of given type - * @pos: the type * to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - */ -#define list_for_each_entry(pos, head, member) \ - for (pos = list_entry((head)->next, typeof(*pos), member); \ - &pos->member != (head); \ - pos = list_entry(pos->member.next, typeof(*pos), member)) - -/** - * list_for_each_entry_reverse - iterate backwards over list of given type. - * @pos: the type * to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - */ -#define list_for_each_entry_reverse(pos, head, member) \ - for (pos = list_entry((head)->prev, typeof(*pos), member); \ - &pos->member != (head); \ - pos = list_entry(pos->member.prev, typeof(*pos), member)) - -/** - * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue - * @pos: the type * to use as a start point - * @head: the head of the list - * @member: the name of the list_struct within the struct. - * - * Prepares a pos entry for use as a start point in list_for_each_entry_continue. - */ -#define list_prepare_entry(pos, head, member) \ - ((pos) ? : list_entry(head, typeof(*pos), member)) - -/** - * list_for_each_entry_continue - continue iteration over list of given type - * @pos: the type * to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - * - * Continue to iterate over list of given type, continuing after - * the current position. - */ -#define list_for_each_entry_continue(pos, head, member) \ - for (pos = list_entry(pos->member.next, typeof(*pos), member); \ - &pos->member != (head); \ - pos = list_entry(pos->member.next, typeof(*pos), member)) - -/** - * list_for_each_entry_from - iterate over list of given type from the current point - * @pos: the type * to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - * - * Iterate over list of given type, continuing from current position. - */ -#define list_for_each_entry_from(pos, head, member) \ - for (; &pos->member != (head); \ - pos = list_entry(pos->member.next, typeof(*pos), member)) - -/** - * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry - * @pos: the type * to use as a loop cursor. - * @n: another type * to use as temporary storage - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - */ -#define list_for_each_entry_safe(pos, n, head, member) \ - for (pos = list_entry((head)->next, typeof(*pos), member), \ - n = list_entry(pos->member.next, typeof(*pos), member); \ - &pos->member != (head); \ - pos = n, n = list_entry(n->member.next, typeof(*n), member)) - -/** - * list_for_each_entry_safe_continue - * @pos: the type * to use as a loop cursor. - * @n: another type * to use as temporary storage - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - * - * Iterate over list of given type, continuing after current point, - * safe against removal of list entry. - */ -#define list_for_each_entry_safe_continue(pos, n, head, member) \ - for (pos = list_entry(pos->member.next, typeof(*pos), member), \ - n = list_entry(pos->member.next, typeof(*pos), member); \ - &pos->member != (head); \ - pos = n, n = list_entry(n->member.next, typeof(*n), member)) - -/** - * list_for_each_entry_safe_from - * @pos: the type * to use as a loop cursor. - * @n: another type * to use as temporary storage - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - * - * Iterate over list of given type from current point, safe against - * removal of list entry. - */ -#define list_for_each_entry_safe_from(pos, n, head, member) \ - for (n = list_entry(pos->member.next, typeof(*pos), member); \ - &pos->member != (head); \ - pos = n, n = list_entry(n->member.next, typeof(*n), member)) - -/** - * list_for_each_entry_safe_reverse - * @pos: the type * to use as a loop cursor. - * @n: another type * to use as temporary storage - * @head: the head for your list. - * @member: the name of the list_struct within the struct. - * - * Iterate backwards over list of given type, safe against removal - * of list entry. - */ -#define list_for_each_entry_safe_reverse(pos, n, head, member) \ - for (pos = list_entry((head)->prev, typeof(*pos), member), \ - n = list_entry(pos->member.prev, typeof(*pos), member); \ - &pos->member != (head); \ - pos = n, n = list_entry(n->member.prev, typeof(*n), member)) - -/* - * Double linked lists with a single pointer list head. - * Mostly useful for hash tables where the two pointer list head is - * too wasteful. - * You lose the ability to access the tail in O(1). - */ - -struct hlist_head { - struct hlist_node *first; -}; - -struct hlist_node { - struct hlist_node *next, **pprev; -}; - -#define HLIST_HEAD_INIT { .first = NULL } -#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } -#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) -static inline void INIT_HLIST_NODE(struct hlist_node *h) -{ - h->next = NULL; - h->pprev = NULL; -} - -static inline int hlist_unhashed(const struct hlist_node *h) -{ - return !h->pprev; -} - -static inline int hlist_empty(const struct hlist_head *h) -{ - return !h->first; -} - -static inline void __hlist_del(struct hlist_node *n) -{ - struct hlist_node *next = n->next; - struct hlist_node **pprev = n->pprev; - *pprev = next; - if (next) - next->pprev = pprev; -} - -static inline void hlist_del(struct hlist_node *n) -{ - __hlist_del(n); - n->next = LIST_POISON1; - n->pprev = LIST_POISON2; -} - -static inline void hlist_del_init(struct hlist_node *n) -{ - if (!hlist_unhashed(n)) { - __hlist_del(n); - INIT_HLIST_NODE(n); - } -} - -static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) -{ - struct hlist_node *first = h->first; - n->next = first; - if (first) - first->pprev = &n->next; - h->first = n; - n->pprev = &h->first; -} - -/* next must be != NULL */ -static inline void hlist_add_before(struct hlist_node *n, - struct hlist_node *next) -{ - n->pprev = next->pprev; - n->next = next; - next->pprev = &n->next; - *(n->pprev) = n; -} - -static inline void hlist_add_after(struct hlist_node *n, - struct hlist_node *next) -{ - next->next = n->next; - n->next = next; - next->pprev = &n->next; - - if(next->next) - next->next->pprev = &next->next; -} - -#define hlist_entry(ptr, type, member) container_of(ptr,type,member) - -#define hlist_for_each(pos, head) \ - for (pos = (head)->first; pos; \ - pos = pos->next) - -#define hlist_for_each_safe(pos, n, head) \ - for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ - pos = n) - -/** - * hlist_for_each_entry - iterate over list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. - * @head: the head for your list. - * @member: the name of the hlist_node within the struct. - */ -#define hlist_for_each_entry(tpos, pos, head, member) \ - for (pos = (head)->first; \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) - -/** - * hlist_for_each_entry_continue - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. - * @member: the name of the hlist_node within the struct. - */ -#define hlist_for_each_entry_continue(tpos, pos, member) \ - for (pos = (pos)->next; \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) - -/** - * hlist_for_each_entry_from - iterate over a hlist continuing from current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. - * @member: the name of the hlist_node within the struct. - */ -#define hlist_for_each_entry_from(tpos, pos, member) \ - for (; pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) - -/** - * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. - * @n: another &struct hlist_node to use as temporary storage - * @head: the head for your list. - * @member: the name of the hlist_node within the struct. - */ -#define hlist_for_each_entry_safe(tpos, pos, n, head, member) \ - for (pos = (head)->first; \ - pos && ({ n = pos->next; 1; }) && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = n) - -#endif diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 3a275db1fa6..65a8449b91f 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -3,7 +3,7 @@ #include #include "types.h" -#include "list.h" +#include #include struct symbol { From 0406ca6d8e849d9dd027c8cb6791448e81411aef Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 1 Jul 2009 21:02:09 +0200 Subject: [PATCH 0094/1346] perf_counter: Ignore the nmi call frames in the x86-64 backtraces About every callchains recorded with perf record are filled up including the internal perfcounter nmi frame: perf_callchain perf_counter_overflow intel_pmu_handle_irq perf_counter_nmi_handler notifier_call_chain atomic_notifier_call_chain notify_die do_nmi nmi We want ignore this frame as it's not interesting for instrumentation. To solve this, we simply ignore every frames from nmi context. New example of "perf report -s sym -c" after this patch: 9.59% [k] search_by_key 4.88% search_by_key reiserfs_read_locked_inode reiserfs_iget reiserfs_lookup do_lookup __link_path_walk path_walk do_path_lookup user_path_at vfs_fstatat vfs_lstat sys_newlstat system_call_fastpath __lxstat 0x406fb1 3.19% search_by_key search_by_entry_key reiserfs_find_entry reiserfs_lookup do_lookup __link_path_walk path_walk do_path_lookup user_path_at vfs_fstatat vfs_lstat sys_newlstat system_call_fastpath __lxstat 0x406fb1 [...] For now this patch only solves the problem in x86-64. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246474930-6088-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 2 ++ arch/x86/kernel/cpu/perf_counter.c | 8 +++++++- arch/x86/kernel/dumpstack_32.c | 6 ++++++ arch/x86/kernel/dumpstack_64.c | 22 +++++++++++++++------- 4 files changed, 30 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f517944b2b1..cf86a5e7381 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -3,6 +3,8 @@ extern int kstack_depth_to_print; +int x86_is_stack_id(int id, char *name); + /* Generic stack tracer with callbacks */ struct stacktrace_ops { diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c index d4cf4ce19aa..36c3dc7b899 100644 --- a/arch/x86/kernel/cpu/perf_counter.c +++ b/arch/x86/kernel/cpu/perf_counter.c @@ -1561,6 +1561,7 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip) static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry); static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry); +static DEFINE_PER_CPU(int, in_nmi_frame); static void @@ -1576,7 +1577,9 @@ static void backtrace_warning(void *data, char *msg) static int backtrace_stack(void *data, char *name) { - /* Process all stacks: */ + per_cpu(in_nmi_frame, smp_processor_id()) = + x86_is_stack_id(NMI_STACK, name); + return 0; } @@ -1584,6 +1587,9 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; + if (per_cpu(in_nmi_frame, smp_processor_id())) + return; + if (reliable) callchain_store(entry, addr); } diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index d593cd1f58d..bca5fba91c9 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -19,6 +19,12 @@ #include "dumpstack.h" +/* Just a stub for now */ +int x86_is_stack_id(int id, char *name) +{ + return 0; +} + void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index d35db5993fd..54b0a327676 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -19,10 +19,8 @@ #include "dumpstack.h" -static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, char **idp) -{ - static char ids[][8] = { + +static char x86_stack_ids[][8] = { [DEBUG_STACK - 1] = "#DB", [NMI_STACK - 1] = "NMI", [DOUBLEFAULT_STACK - 1] = "#DF", @@ -33,6 +31,15 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]" #endif }; + +int x86_is_stack_id(int id, char *name) +{ + return x86_stack_ids[id - 1] == name; +} + +static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, + unsigned *usedp, char **idp) +{ unsigned k; /* @@ -61,7 +68,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, if (*usedp & (1U << k)) break; *usedp |= 1U << k; - *idp = ids[k]; + *idp = x86_stack_ids[k]; return (unsigned long *)end; } /* @@ -81,12 +88,13 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, do { ++j; end -= EXCEPTION_STKSZ; - ids[j][4] = '1' + (j - N_EXCEPTION_STACKS); + x86_stack_ids[j][4] = '1' + + (j - N_EXCEPTION_STACKS); } while (stack < end - EXCEPTION_STKSZ); if (*usedp & (1U << j)) break; *usedp |= 1U << j; - *idp = ids[j]; + *idp = x86_stack_ids[j]; return (unsigned long *)end; } #endif From a92bef0f216bbf3d05c0c0709ea02e267f2b920e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 1 Jul 2009 21:02:10 +0200 Subject: [PATCH 0095/1346] perf stat: Handle pipe read failures in perf stat MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building builtin-stat.c reports the following errors: cc1: warnings being treated as errors builtin-stat.c: In function ‘run_perf_stat’: builtin-stat.c:242: erreur: ignoring return value of ‘read’, declared with attribute warn_unused_result builtin-stat.c:255: erreur: ignoring return value of ‘read’, declared with attribute warn_unused_result make: *** [builtin-stat.o] Erreur 1 This patch handles the possible pipe read failures. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246474930-6088-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 01cc07efb72..27921a8ce1a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -239,7 +239,8 @@ static int run_perf_stat(int argc __used, const char **argv) /* * Wait until the parent tells us to go. */ - read(go_pipe[0], &buf, 1); + if (read(go_pipe[0], &buf, 1) == -1) + perror("unable to read pipe"); execvp(argv[0], (char **)argv); @@ -252,7 +253,8 @@ static int run_perf_stat(int argc __used, const char **argv) */ close(child_ready_pipe[1]); close(go_pipe[0]); - read(child_ready_pipe[0], &buf, 1); + if (read(child_ready_pipe[0], &buf, 1) == -1) + perror("unable to read pipe"); close(child_ready_pipe[0]); for (counter = 0; counter < nr_counters; counter++) From 46b952a3c3a94afa339bd4961a4f3d1482436599 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 1 Jul 2009 14:24:30 -0700 Subject: [PATCH 0096/1346] PCI: Fix IRQ swizzling for ARI-enabled devices For many purposes, including interrupt-swizzling, devices with ARI enabled behave as if they have one device (number 0) and 256 functions. This probably hasn't bitten us in practice because all ARI devices I've seen are also IOV devices, and IOV devices are required to use MSI. This isn't guaranteed, and there are legitimate reasons to use ARI without IOV, and hence potentially use pin-based interrupts. Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- drivers/pci/pci.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d5d6f5667d8..dbd0f947f49 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1517,11 +1517,20 @@ void pci_enable_ari(struct pci_dev *dev) * * Perform INTx swizzling for a device behind one level of bridge. This is * required by section 9.1 of the PCI-to-PCI bridge specification for devices - * behind bridges on add-in cards. + * behind bridges on add-in cards. For devices with ARI enabled, the slot + * number is always 0 (see the Implementation Note in section 2.2.8.1 of + * the PCI Express Base Specification, Revision 2.1) */ u8 pci_swizzle_interrupt_pin(struct pci_dev *dev, u8 pin) { - return (((pin - 1) + PCI_SLOT(dev->devfn)) % 4) + 1; + int slot; + + if (pci_ari_enabled(dev->bus)) + slot = 0; + else + slot = PCI_SLOT(dev->devfn); + + return (((pin - 1) + slot) % 4) + 1; } int From cc0bad7552308e8905d6ea56e6b7811fa67e716d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 25 Jun 2009 00:56:52 -0400 Subject: [PATCH 0097/1346] cifs: add new cifs_iget function and convert unix codepath to use it cifs: add new cifs_iget function and convert unix codepath to use it In order to unify some codepaths, introduce a common cifs_fattr struct for storing inode attributes. The different codepaths (unix, legacy, normal, etc...) can fill out this struct with inode info. It can then be passed as an arg to a common set of routines to get and update inodes. Add a new cifs_iget function that uses iget5_locked to identify inodes. This will compare inodes based on the uniqueid value in a cifs_fattr struct. Rather than filling out an already-created inode, have cifs_get_inode_info_unix instead fill out cifs_fattr and hand that off to cifs_iget. cifs_iget can then properly look for hardlinked inodes. On the readdir side, add a new cifs_readdir_lookup function that spawns populated dentries. Redefine FILE_UNIX_INFO so that it's basically a FILE_UNIX_BASIC_INFO that has a few fields wrapped around it. This allows us to more easily use the same function for filling out the fattr as the non-readdir codepath. With this, we should then have proper hardlink detection and can eventually get rid of some nasty CIFS-specific hacks for handing them. Signed-off-by: Jeff Layton Reviewed-by: Christoph Hellwig Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 13 ++ fs/cifs/cifsglob.h | 25 +++ fs/cifs/cifspdu.h | 14 +- fs/cifs/cifsproto.h | 9 +- fs/cifs/dir.c | 22 +-- fs/cifs/inode.c | 416 ++++++++++++++++++++++---------------------- fs/cifs/readdir.c | 253 ++++++++++----------------- 7 files changed, 357 insertions(+), 395 deletions(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 9570a0e8023..586df24c9ab 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -24,6 +24,19 @@ #define ROOT_I 2 +/* + * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down + * so that it will fit. + */ +static inline ino_t +cifs_uniqueid_to_ino_t(u64 fileid) +{ + ino_t ino = (ino_t) fileid; + if (sizeof(ino_t) < sizeof(u64)) + ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8; + return ino; +} + extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; extern const struct address_space_operations cifs_addr_ops_smallbuf; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index e1225e6ded2..e6435cba811 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -371,6 +371,7 @@ struct cifsInodeInfo { bool oplockPending:1; bool delete_pending:1; /* DELETE_ON_CLOSE is set */ u64 server_eof; /* current file size on server */ + u64 uniqueid; /* server inode number */ struct inode vfs_inode; }; @@ -472,6 +473,30 @@ struct dfs_info3_param { char *node_name; }; +/* + * common struct for holding inode info when searching for or updating an + * inode with new info + */ + +#define CIFS_FATTR_DFS_REFERRAL 0x1 + +struct cifs_fattr { + u32 cf_flags; + u32 cf_cifsattrs; + u64 cf_uniqueid; + u64 cf_eof; + u64 cf_bytes; + uid_t cf_uid; + gid_t cf_gid; + umode_t cf_mode; + dev_t cf_rdev; + unsigned int cf_nlink; + unsigned int cf_dtype; + struct timespec cf_atime; + struct timespec cf_mtime; + struct timespec cf_ctime; +}; + static inline void free_dfs_info_param(struct dfs_info3_param *param) { if (param) { diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index a785f69dbc9..2d07f890a84 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -2328,19 +2328,7 @@ struct file_attrib_tag { typedef struct { __le32 NextEntryOffset; __u32 ResumeKey; /* as with FileIndex - no need to convert */ - __le64 EndOfFile; - __le64 NumOfBytes; - __le64 LastStatusChange; /*SNIA specs DCE time for the 3 time fields */ - __le64 LastAccessTime; - __le64 LastModificationTime; - __le64 Uid; - __le64 Gid; - __le32 Type; - __le64 DevMajor; - __le64 DevMinor; - __le64 UniqueId; - __le64 Permissions; - __le64 Nlinks; + FILE_UNIX_BASIC_INFO basic; char FileName[1]; } __attribute__((packed)) FILE_UNIX_INFO; /* level 0x202 */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index c419416a42e..b2bd83fd2aa 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -98,9 +98,14 @@ extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, extern int cifs_posix_open(char *full_path, struct inode **pinode, struct super_block *sb, int mode, int oflags, int *poplock, __u16 *pnetfid, int xid); -extern void posix_fill_in_inode(struct inode *tmp_inode, - FILE_UNIX_BASIC_INFO *pData, int isNewInode); +extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, + FILE_UNIX_BASIC_INFO *info, + struct cifs_sb_info *cifs_sb); +extern void cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); extern struct inode *cifs_new_inode(struct super_block *sb, __u64 *inum); +extern struct inode *cifs_iget(struct super_block *sb, + struct cifs_fattr *fattr); + extern int cifs_get_inode_info(struct inode **pinode, const unsigned char *search_path, FILE_ALL_INFO *pfile_info, diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 7dc6b74f9de..a40054faed7 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -188,6 +188,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode, FILE_UNIX_BASIC_INFO *presp_data; __u32 posix_flags = 0; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + struct cifs_fattr fattr; cFYI(1, ("posix open %s", full_path)); @@ -236,22 +237,21 @@ int cifs_posix_open(char *full_path, struct inode **pinode, if (presp_data->Type == cpu_to_le32(-1)) goto posix_open_ret; /* open ok, caller does qpathinfo */ - /* get new inode and set it up */ if (!pinode) goto posix_open_ret; /* caller does not need info */ + cifs_unix_basic_to_fattr(&fattr, presp_data, cifs_sb); + + /* get new inode and set it up */ if (*pinode == NULL) { - __u64 unique_id = le64_to_cpu(presp_data->UniqueId); - *pinode = cifs_new_inode(sb, &unique_id); + *pinode = cifs_iget(sb, &fattr); + if (!*pinode) { + rc = -ENOMEM; + goto posix_open_ret; + } + } else { + cifs_fattr_to_inode(*pinode, &fattr); } - /* else an inode was passed in. Update its info, don't create one */ - - /* We do not need to close the file if new_inode fails since - the caller will retry qpathinfo as long as inode is null */ - if (*pinode == NULL) - goto posix_open_ret; - - posix_fill_in_inode(*pinode, presp_data, 1); cifs_fill_fileinfo(*pinode, *pnetfid, cifs_sb->tcon, write_only); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 155c9e785d0..b22379610d7 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -77,127 +77,146 @@ static void cifs_set_ops(struct inode *inode, const bool is_dfs_referral) } } -static void cifs_unix_info_to_inode(struct inode *inode, - FILE_UNIX_BASIC_INFO *info, int force_uid_gid) +/* populate an inode with info from a cifs_fattr struct */ +void +cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) { - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct cifsInodeInfo *cifsInfo = CIFS_I(inode); - __u64 num_of_bytes = le64_to_cpu(info->NumOfBytes); - __u64 end_of_file = le64_to_cpu(info->EndOfFile); + struct cifsInodeInfo *cifs_i = CIFS_I(inode); + unsigned long now = jiffies; - inode->i_atime = cifs_NTtimeToUnix(info->LastAccessTime); - inode->i_mtime = - cifs_NTtimeToUnix(info->LastModificationTime); - inode->i_ctime = cifs_NTtimeToUnix(info->LastStatusChange); - inode->i_mode = le64_to_cpu(info->Permissions); + inode->i_atime = fattr->cf_atime; + inode->i_mtime = fattr->cf_mtime; + inode->i_ctime = fattr->cf_ctime; + inode->i_mode = fattr->cf_mode; + inode->i_rdev = fattr->cf_rdev; + inode->i_nlink = fattr->cf_nlink; + inode->i_uid = fattr->cf_uid; + inode->i_gid = fattr->cf_gid; + + cifs_i->cifsAttrs = fattr->cf_cifsattrs; + cifs_i->uniqueid = fattr->cf_uniqueid; + + cFYI(1, ("inode 0x%p old_time=%ld new_time=%ld", inode, + cifs_i->time, now)); + cifs_i->time = now; /* - * Since we set the inode type below we need to mask off - * to avoid strange results if bits set above. + * Can't safely change the file size here if the client is writing to + * it due to potential races. */ - inode->i_mode &= ~S_IFMT; - switch (le32_to_cpu(info->Type)) { - case UNIX_FILE: - inode->i_mode |= S_IFREG; - break; - case UNIX_SYMLINK: - inode->i_mode |= S_IFLNK; - break; - case UNIX_DIR: - inode->i_mode |= S_IFDIR; - break; - case UNIX_CHARDEV: - inode->i_mode |= S_IFCHR; - inode->i_rdev = MKDEV(le64_to_cpu(info->DevMajor), - le64_to_cpu(info->DevMinor) & MINORMASK); - break; - case UNIX_BLOCKDEV: - inode->i_mode |= S_IFBLK; - inode->i_rdev = MKDEV(le64_to_cpu(info->DevMajor), - le64_to_cpu(info->DevMinor) & MINORMASK); - break; - case UNIX_FIFO: - inode->i_mode |= S_IFIFO; - break; - case UNIX_SOCKET: - inode->i_mode |= S_IFSOCK; - break; - default: - /* safest to call it a file if we do not know */ - inode->i_mode |= S_IFREG; - cFYI(1, ("unknown type %d", le32_to_cpu(info->Type))); - break; - } - - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) && - !force_uid_gid) - inode->i_uid = cifs_sb->mnt_uid; - else - inode->i_uid = le64_to_cpu(info->Uid); - - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) && - !force_uid_gid) - inode->i_gid = cifs_sb->mnt_gid; - else - inode->i_gid = le64_to_cpu(info->Gid); - - inode->i_nlink = le64_to_cpu(info->Nlinks); - - cifsInfo->server_eof = end_of_file; spin_lock(&inode->i_lock); - if (is_size_safe_to_change(cifsInfo, end_of_file)) { - /* - * We can not safely change the file size here if the client - * is writing to it due to potential races. - */ - i_size_write(inode, end_of_file); + if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) { + i_size_write(inode, fattr->cf_eof); /* * i_blocks is not related to (i_size / i_blksize), * but instead 512 byte (2**9) size is required for * calculating num blocks. */ - inode->i_blocks = (512 - 1 + num_of_bytes) >> 9; + inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9; } spin_unlock(&inode->i_lock); + + cifs_set_ops(inode, fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL); } +/* Fill a cifs_fattr struct with info from FILE_UNIX_BASIC_INFO. */ +void +cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, + struct cifs_sb_info *cifs_sb) +{ + memset(fattr, 0, sizeof(*fattr)); + fattr->cf_uniqueid = le64_to_cpu(info->UniqueId); + fattr->cf_bytes = le64_to_cpu(info->NumOfBytes); + fattr->cf_eof = le64_to_cpu(info->EndOfFile); + + fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime); + fattr->cf_mtime = cifs_NTtimeToUnix(info->LastModificationTime); + fattr->cf_ctime = cifs_NTtimeToUnix(info->LastStatusChange); + fattr->cf_mode = le64_to_cpu(info->Permissions); + + /* + * Since we set the inode type below we need to mask off + * to avoid strange results if bits set above. + */ + fattr->cf_mode &= ~S_IFMT; + switch (le32_to_cpu(info->Type)) { + case UNIX_FILE: + fattr->cf_mode |= S_IFREG; + fattr->cf_dtype = DT_REG; + break; + case UNIX_SYMLINK: + fattr->cf_mode |= S_IFLNK; + fattr->cf_dtype = DT_LNK; + break; + case UNIX_DIR: + fattr->cf_mode |= S_IFDIR; + fattr->cf_dtype = DT_DIR; + break; + case UNIX_CHARDEV: + fattr->cf_mode |= S_IFCHR; + fattr->cf_dtype = DT_CHR; + fattr->cf_rdev = MKDEV(le64_to_cpu(info->DevMajor), + le64_to_cpu(info->DevMinor) & MINORMASK); + break; + case UNIX_BLOCKDEV: + fattr->cf_mode |= S_IFBLK; + fattr->cf_dtype = DT_BLK; + fattr->cf_rdev = MKDEV(le64_to_cpu(info->DevMajor), + le64_to_cpu(info->DevMinor) & MINORMASK); + break; + case UNIX_FIFO: + fattr->cf_mode |= S_IFIFO; + fattr->cf_dtype = DT_FIFO; + break; + case UNIX_SOCKET: + fattr->cf_mode |= S_IFSOCK; + fattr->cf_dtype = DT_SOCK; + break; + default: + /* safest to call it a file if we do not know */ + fattr->cf_mode |= S_IFREG; + fattr->cf_dtype = DT_REG; + cFYI(1, ("unknown type %d", le32_to_cpu(info->Type))); + break; + } + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) + fattr->cf_uid = cifs_sb->mnt_uid; + else + fattr->cf_uid = le64_to_cpu(info->Uid); + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) + fattr->cf_gid = cifs_sb->mnt_gid; + else + fattr->cf_gid = le64_to_cpu(info->Gid); + + fattr->cf_nlink = le64_to_cpu(info->Nlinks); +} /* - * Needed to setup inode data for the directory which is the - * junction to the new submount (ie to setup the fake directory - * which represents a DFS referral) + * Fill a cifs_fattr struct with fake inode info. + * + * Needed to setup cifs_fattr data for the directory which is the + * junction to the new submount (ie to setup the fake directory + * which represents a DFS referral). */ -static void fill_fake_finddataunix(FILE_UNIX_BASIC_INFO *pfnd_dat, - struct super_block *sb) +void +cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb) { - struct inode *pinode = NULL; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - memset(pfnd_dat, 0, sizeof(FILE_UNIX_BASIC_INFO)); + cFYI(1, ("creating fake fattr for DFS referral")); -/* __le64 pfnd_dat->EndOfFile = cpu_to_le64(0); - __le64 pfnd_dat->NumOfBytes = cpu_to_le64(0); - __u64 UniqueId = 0; */ - pfnd_dat->LastStatusChange = - cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); - pfnd_dat->LastAccessTime = - cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); - pfnd_dat->LastModificationTime = - cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); - pfnd_dat->Type = cpu_to_le32(UNIX_DIR); - pfnd_dat->Permissions = cpu_to_le64(S_IXUGO | S_IRWXU); - pfnd_dat->Nlinks = cpu_to_le64(2); - if (sb->s_root) - pinode = sb->s_root->d_inode; - if (pinode == NULL) - return; - - /* fill in default values for the remaining based on root - inode since we can not query the server for this inode info */ - pfnd_dat->DevMajor = cpu_to_le64(MAJOR(pinode->i_rdev)); - pfnd_dat->DevMinor = cpu_to_le64(MINOR(pinode->i_rdev)); - pfnd_dat->Uid = cpu_to_le64(pinode->i_uid); - pfnd_dat->Gid = cpu_to_le64(pinode->i_gid); + memset(fattr, 0, sizeof(*fattr)); + fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU; + fattr->cf_uid = cifs_sb->mnt_uid; + fattr->cf_gid = cifs_sb->mnt_gid; + fattr->cf_atime = CURRENT_TIME; + fattr->cf_ctime = CURRENT_TIME; + fattr->cf_mtime = CURRENT_TIME; + fattr->cf_nlink = 2; + fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL; } /** @@ -244,66 +263,42 @@ cifs_new_inode(struct super_block *sb, __u64 *inum) } int cifs_get_inode_info_unix(struct inode **pinode, - const unsigned char *full_path, struct super_block *sb, int xid) + const unsigned char *full_path, + struct super_block *sb, int xid) { - int rc = 0; + int rc; FILE_UNIX_BASIC_INFO find_data; - struct cifsTconInfo *pTcon; - struct inode *inode; + struct cifs_fattr fattr; + struct cifsTconInfo *tcon; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - bool is_dfs_referral = false; - struct cifsInodeInfo *cifsInfo; - __u64 num_of_bytes; - __u64 end_of_file; - pTcon = cifs_sb->tcon; + tcon = cifs_sb->tcon; cFYI(1, ("Getting info on %s", full_path)); /* could have done a find first instead but this returns more info */ - rc = CIFSSMBUnixQPathInfo(xid, pTcon, full_path, &find_data, + rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc == -EREMOTE && !is_dfs_referral) { - is_dfs_referral = true; - cFYI(DBG2, ("DFS ref")); - /* for DFS, server does not give us real inode data */ - fill_fake_finddataunix(&find_data, sb); + + if (!rc) { + cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb); + } else if (rc == -EREMOTE) { + cifs_create_dfs_fattr(&fattr, sb); rc = 0; - } else if (rc) - goto cgiiu_exit; - - num_of_bytes = le64_to_cpu(find_data.NumOfBytes); - end_of_file = le64_to_cpu(find_data.EndOfFile); - - /* get new inode */ - if (*pinode == NULL) { - __u64 unique_id = le64_to_cpu(find_data.UniqueId); - *pinode = cifs_new_inode(sb, &unique_id); - if (*pinode == NULL) { - rc = -ENOMEM; - goto cgiiu_exit; - } + } else { + return rc; } - inode = *pinode; - cifsInfo = CIFS_I(inode); + if (*pinode == NULL) { + /* get new inode */ + *pinode = cifs_iget(sb, &fattr); + if (!*pinode) + rc = -ENOMEM; + } else { + /* we already have inode, update it */ + cifs_fattr_to_inode(*pinode, &fattr); + } - cFYI(1, ("Old time %ld", cifsInfo->time)); - cifsInfo->time = jiffies; - cFYI(1, ("New time %ld", cifsInfo->time)); - /* this is ok to set on every inode revalidate */ - atomic_set(&cifsInfo->inUse, 1); - - cifs_unix_info_to_inode(inode, &find_data, 0); - - if (num_of_bytes < end_of_file) - cFYI(1, ("allocation size less than end of file")); - cFYI(1, ("Size %ld and blocks %llu", - (unsigned long) inode->i_size, - (unsigned long long)inode->i_blocks)); - - cifs_set_ops(inode, is_dfs_referral); -cgiiu_exit: return rc; } @@ -695,33 +690,85 @@ char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb) return full_path; } +static int +cifs_find_inode(struct inode *inode, void *opaque) +{ + struct cifs_fattr *fattr = (struct cifs_fattr *) opaque; + + if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid) + return 0; + + return 1; +} + +static int +cifs_init_inode(struct inode *inode, void *opaque) +{ + struct cifs_fattr *fattr = (struct cifs_fattr *) opaque; + + CIFS_I(inode)->uniqueid = fattr->cf_uniqueid; + return 0; +} + +/* Given fattrs, get a corresponding inode */ +struct inode * +cifs_iget(struct super_block *sb, struct cifs_fattr *fattr) +{ + unsigned long hash; + struct inode *inode; + + cFYI(1, ("looking for uniqueid=%llu", fattr->cf_uniqueid)); + + /* hash down to 32-bits on 32-bit arch */ + hash = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid); + + inode = iget5_locked(sb, hash, cifs_find_inode, cifs_init_inode, fattr); + + /* we have fattrs in hand, update the inode */ + if (inode) { + cifs_fattr_to_inode(inode, fattr); + if (sb->s_flags & MS_NOATIME) + inode->i_flags |= S_NOATIME | S_NOCMTIME; + if (inode->i_state & I_NEW) { + inode->i_ino = hash; + unlock_new_inode(inode); + } + } + + return inode; +} + /* gets root inode */ struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) { int xid; struct cifs_sb_info *cifs_sb; - struct inode *inode; + struct inode *inode = NULL; long rc; char *full_path; - inode = iget_locked(sb, ino); - if (!inode) - return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) - return inode; - - cifs_sb = CIFS_SB(inode->i_sb); + cifs_sb = CIFS_SB(sb); full_path = cifs_build_path_to_root(cifs_sb); if (full_path == NULL) return ERR_PTR(-ENOMEM); xid = GetXid(); - if (cifs_sb->tcon->unix_ext) - rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb, - xid); - else + if (cifs_sb->tcon->unix_ext) { + rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid); + if (!inode) + return ERR_PTR(-ENOMEM); + } else { + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + rc = cifs_get_inode_info(&inode, full_path, NULL, inode->i_sb, xid, NULL); + unlock_new_inode(inode); + } + if (rc && cifs_sb->tcon->ipc) { cFYI(1, ("ipc connection - fake read inode")); inode->i_mode |= S_IFDIR; @@ -737,7 +784,6 @@ struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) return ERR_PTR(rc); } - unlock_new_inode(inode); kfree(full_path); /* can not call macro FreeXid here since in a void func @@ -1063,44 +1109,6 @@ out_reval: return rc; } -void posix_fill_in_inode(struct inode *tmp_inode, - FILE_UNIX_BASIC_INFO *pData, int isNewInode) -{ - struct cifsInodeInfo *cifsInfo = CIFS_I(tmp_inode); - loff_t local_size; - struct timespec local_mtime; - - cifsInfo->time = jiffies; - atomic_inc(&cifsInfo->inUse); - - /* save mtime and size */ - local_mtime = tmp_inode->i_mtime; - local_size = tmp_inode->i_size; - - cifs_unix_info_to_inode(tmp_inode, pData, 1); - cifs_set_ops(tmp_inode, false); - - if (!S_ISREG(tmp_inode->i_mode)) - return; - - /* - * No sense invalidating pages for new inode - * since we we have not started caching - * readahead file data yet. - */ - if (isNewInode) - return; - - if (timespec_equal(&tmp_inode->i_mtime, &local_mtime) && - (local_size == tmp_inode->i_size)) { - cFYI(1, ("inode exists but unchanged")); - } else { - /* file may have changed on server */ - cFYI(1, ("invalidate inode, readdir detected change")); - invalidate_remote_inode(tmp_inode); - } -} - int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) { int rc = 0, tmprc; @@ -1109,6 +1117,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) struct cifsTconInfo *pTcon; char *full_path = NULL; struct inode *newinode = NULL; + struct cifs_fattr fattr; cFYI(1, ("In cifs_mkdir, mode = 0x%x inode = 0x%p", mode, inode)); @@ -1148,7 +1157,6 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) cFYI(1, ("posix mkdir returned 0x%x", rc)); d_drop(direntry); } else { - __u64 unique_id; if (pInfo->Type == cpu_to_le32(-1)) { /* no return info, go query for it */ kfree(pInfo); @@ -1162,20 +1170,15 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) else direntry->d_op = &cifs_dentry_ops; - unique_id = le64_to_cpu(pInfo->UniqueId); - newinode = cifs_new_inode(inode->i_sb, &unique_id); - if (newinode == NULL) { + cifs_unix_basic_to_fattr(&fattr, pInfo, cifs_sb); + newinode = cifs_iget(inode->i_sb, &fattr); + if (!newinode) { kfree(pInfo); goto mkdir_get_info; } - newinode->i_nlink = 2; d_instantiate(direntry, newinode); - /* we already checked in POSIXCreate whether - frame was long enough */ - posix_fill_in_inode(direntry->d_inode, - pInfo, 1 /* NewInode */); #ifdef CONFIG_CIFS_DEBUG2 cFYI(1, ("instantiated dentry %p %s to inode %p", direntry, direntry->d_name.name, newinode)); @@ -1622,6 +1625,7 @@ int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry, if (!err) { generic_fillattr(dentry->d_inode, stat); stat->blksize = CIFS_MAX_MSGSIZE; + stat->ino = CIFS_I(dentry->d_inode)->uniqueid; } return err; } diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 86d0055dc52..231aa6953f8 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -63,6 +63,55 @@ static inline void dump_cifs_file_struct(struct file *file, char *label) } #endif /* DEBUG2 */ +/* + * Find the dentry that matches "name". If there isn't one, create one. If it's + * a negative dentry or the uniqueid changed, then drop it and recreate it. + */ +static struct dentry * +cifs_readdir_lookup(struct dentry *parent, struct qstr *name, + struct cifs_fattr *fattr) +{ + struct dentry *dentry, *alias; + struct inode *inode; + struct super_block *sb = parent->d_inode->i_sb; + + cFYI(1, ("For %s", name->name)); + + dentry = d_lookup(parent, name); + if (dentry) { + /* FIXME: check for inode number changes? */ + if (dentry->d_inode != NULL) + return dentry; + d_drop(dentry); + dput(dentry); + } + + dentry = d_alloc(parent, name); + if (dentry == NULL) + return NULL; + + inode = cifs_iget(sb, fattr); + if (!inode) { + dput(dentry); + return NULL; + } + + if (CIFS_SB(sb)->tcon->nocase) + dentry->d_op = &cifs_ci_dentry_ops; + else + dentry->d_op = &cifs_dentry_ops; + + alias = d_materialise_unique(dentry, inode); + if (alias != NULL) { + dput(dentry); + if (IS_ERR(alias)) + return NULL; + dentry = alias; + } + + return dentry; +} + /* Returns 1 if new inode created, 2 if both dentry and inode were */ /* Might check in the future if inode number changed so we can rehash inode */ static int @@ -76,7 +125,6 @@ construct_dentry(struct qstr *qstring, struct file *file, cFYI(1, ("For %s", qstring->name)); - qstring->hash = full_name_hash(qstring->name, qstring->len); tmp_dentry = d_lookup(file->f_path.dentry, qstring); if (tmp_dentry) { /* BB: overwrite old name? i.e. tmp_dentry->d_name and @@ -299,140 +347,6 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, } } -static void unix_fill_in_inode(struct inode *tmp_inode, - FILE_UNIX_INFO *pfindData, unsigned int *pobject_type, int isNewInode) -{ - loff_t local_size; - struct timespec local_mtime; - - struct cifsInodeInfo *cifsInfo = CIFS_I(tmp_inode); - struct cifs_sb_info *cifs_sb = CIFS_SB(tmp_inode->i_sb); - - __u32 type = le32_to_cpu(pfindData->Type); - __u64 num_of_bytes = le64_to_cpu(pfindData->NumOfBytes); - __u64 end_of_file = le64_to_cpu(pfindData->EndOfFile); - cifsInfo->time = jiffies; - atomic_inc(&cifsInfo->inUse); - - /* save mtime and size */ - local_mtime = tmp_inode->i_mtime; - local_size = tmp_inode->i_size; - - tmp_inode->i_atime = - cifs_NTtimeToUnix(pfindData->LastAccessTime); - tmp_inode->i_mtime = - cifs_NTtimeToUnix(pfindData->LastModificationTime); - tmp_inode->i_ctime = - cifs_NTtimeToUnix(pfindData->LastStatusChange); - - tmp_inode->i_mode = le64_to_cpu(pfindData->Permissions); - /* since we set the inode type below we need to mask off type - to avoid strange results if bits above were corrupt */ - tmp_inode->i_mode &= ~S_IFMT; - if (type == UNIX_FILE) { - *pobject_type = DT_REG; - tmp_inode->i_mode |= S_IFREG; - } else if (type == UNIX_SYMLINK) { - *pobject_type = DT_LNK; - tmp_inode->i_mode |= S_IFLNK; - } else if (type == UNIX_DIR) { - *pobject_type = DT_DIR; - tmp_inode->i_mode |= S_IFDIR; - } else if (type == UNIX_CHARDEV) { - *pobject_type = DT_CHR; - tmp_inode->i_mode |= S_IFCHR; - tmp_inode->i_rdev = MKDEV(le64_to_cpu(pfindData->DevMajor), - le64_to_cpu(pfindData->DevMinor) & MINORMASK); - } else if (type == UNIX_BLOCKDEV) { - *pobject_type = DT_BLK; - tmp_inode->i_mode |= S_IFBLK; - tmp_inode->i_rdev = MKDEV(le64_to_cpu(pfindData->DevMajor), - le64_to_cpu(pfindData->DevMinor) & MINORMASK); - } else if (type == UNIX_FIFO) { - *pobject_type = DT_FIFO; - tmp_inode->i_mode |= S_IFIFO; - } else if (type == UNIX_SOCKET) { - *pobject_type = DT_SOCK; - tmp_inode->i_mode |= S_IFSOCK; - } else { - /* safest to just call it a file */ - *pobject_type = DT_REG; - tmp_inode->i_mode |= S_IFREG; - cFYI(1, ("unknown inode type %d", type)); - } - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) - tmp_inode->i_uid = cifs_sb->mnt_uid; - else - tmp_inode->i_uid = le64_to_cpu(pfindData->Uid); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) - tmp_inode->i_gid = cifs_sb->mnt_gid; - else - tmp_inode->i_gid = le64_to_cpu(pfindData->Gid); - tmp_inode->i_nlink = le64_to_cpu(pfindData->Nlinks); - - cifsInfo->server_eof = end_of_file; - spin_lock(&tmp_inode->i_lock); - if (is_size_safe_to_change(cifsInfo, end_of_file)) { - /* can not safely change the file size here if the - client is writing to it due to potential races */ - i_size_write(tmp_inode, end_of_file); - - /* 512 bytes (2**9) is the fake blocksize that must be used */ - /* for this calculation, not the real blocksize */ - tmp_inode->i_blocks = (512 - 1 + num_of_bytes) >> 9; - } - spin_unlock(&tmp_inode->i_lock); - - if (S_ISREG(tmp_inode->i_mode)) { - cFYI(1, ("File inode")); - tmp_inode->i_op = &cifs_file_inode_ops; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) - tmp_inode->i_fop = &cifs_file_direct_nobrl_ops; - else - tmp_inode->i_fop = &cifs_file_direct_ops; - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) - tmp_inode->i_fop = &cifs_file_nobrl_ops; - else - tmp_inode->i_fop = &cifs_file_ops; - - if ((cifs_sb->tcon) && (cifs_sb->tcon->ses) && - (cifs_sb->tcon->ses->server->maxBuf < - PAGE_CACHE_SIZE + MAX_CIFS_HDR_SIZE)) - tmp_inode->i_data.a_ops = &cifs_addr_ops_smallbuf; - else - tmp_inode->i_data.a_ops = &cifs_addr_ops; - - if (isNewInode) - return; /* No sense invalidating pages for new inode - since we have not started caching readahead - file data for it yet */ - - if (timespec_equal(&tmp_inode->i_mtime, &local_mtime) && - (local_size == tmp_inode->i_size)) { - cFYI(1, ("inode exists but unchanged")); - } else { - /* file may have changed on server */ - cFYI(1, ("invalidate inode, readdir detected change")); - invalidate_remote_inode(tmp_inode); - } - } else if (S_ISDIR(tmp_inode->i_mode)) { - cFYI(1, ("Directory inode")); - tmp_inode->i_op = &cifs_dir_inode_ops; - tmp_inode->i_fop = &cifs_dir_ops; - } else if (S_ISLNK(tmp_inode->i_mode)) { - cFYI(1, ("Symbolic Link inode")); - tmp_inode->i_op = &cifs_symlink_inode_ops; -/* tmp_inode->i_fop = *//* do not need to set to anything */ - } else { - cFYI(1, ("Special inode")); - init_special_inode(tmp_inode, tmp_inode->i_mode, - tmp_inode->i_rdev); - } -} - /* BB eventually need to add the following helper function to resolve NT_STATUS_STOPPED_ON_SYMLINK return code when we try to do FindFirst on (NTFS) directory symlinks */ @@ -872,7 +786,7 @@ static int cifs_get_name_from_search_buf(struct qstr *pqst, len = strnlen(filename, PATH_MAX); } - *pinum = le64_to_cpu(pFindData->UniqueId); + *pinum = le64_to_cpu(pFindData->basic.UniqueId); } else if (level == SMB_FIND_FILE_DIRECTORY_INFO) { FILE_DIRECTORY_INFO *pFindData = (FILE_DIRECTORY_INFO *)current_entry; @@ -934,9 +848,11 @@ static int cifs_filldir(char *pfindEntry, struct file *file, filldir_t filldir, struct cifsFileInfo *pCifsF; unsigned int obj_type; __u64 inum; + ino_t ino; struct cifs_sb_info *cifs_sb; struct inode *tmp_inode; struct dentry *tmp_dentry; + struct cifs_fattr fattr; /* get filename and len into qstring */ /* get dentry */ @@ -967,39 +883,49 @@ static int cifs_filldir(char *pfindEntry, struct file *file, filldir_t filldir, return rc; /* only these two infolevels return valid inode numbers */ - if (pCifsF->srch_inf.info_level == SMB_FIND_FILE_UNIX || - pCifsF->srch_inf.info_level == SMB_FIND_FILE_ID_FULL_DIR_INFO) - rc = construct_dentry(&qstring, file, &tmp_inode, &tmp_dentry, - &inum); - else - rc = construct_dentry(&qstring, file, &tmp_inode, &tmp_dentry, - NULL); + if (pCifsF->srch_inf.info_level == SMB_FIND_FILE_UNIX) { + cifs_unix_basic_to_fattr(&fattr, + &((FILE_UNIX_INFO *) pfindEntry)->basic, + cifs_sb); + tmp_dentry = cifs_readdir_lookup(file->f_dentry, &qstring, + &fattr); + obj_type = fattr.cf_dtype; + ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid); + } else { + if (pCifsF->srch_inf.info_level == + SMB_FIND_FILE_ID_FULL_DIR_INFO) + rc = construct_dentry(&qstring, file, &tmp_inode, + &tmp_dentry, &inum); + else + rc = construct_dentry(&qstring, file, &tmp_inode, + &tmp_dentry, NULL); - if ((tmp_inode == NULL) || (tmp_dentry == NULL)) - return -ENOMEM; + if ((tmp_inode == NULL) || (tmp_dentry == NULL)) { + rc = -ENOMEM; + goto out; + } - /* we pass in rc below, indicating whether it is a new inode, - so we can figure out whether to invalidate the inode cached - data if the file has changed */ - if (pCifsF->srch_inf.info_level == SMB_FIND_FILE_UNIX) - unix_fill_in_inode(tmp_inode, - (FILE_UNIX_INFO *)pfindEntry, - &obj_type, rc); - else if (pCifsF->srch_inf.info_level == SMB_FIND_FILE_INFO_STANDARD) - fill_in_inode(tmp_inode, 0 /* old level 1 buffer type */, - pfindEntry, &obj_type, rc); - else - fill_in_inode(tmp_inode, 1 /* NT */, pfindEntry, &obj_type, rc); + /* we pass in rc below, indicating whether it is a new inode, + * so we can figure out whether to invalidate the inode cached + * data if the file has changed + */ + if (pCifsF->srch_inf.info_level == SMB_FIND_FILE_INFO_STANDARD) + fill_in_inode(tmp_inode, 0, pfindEntry, &obj_type, rc); + else + fill_in_inode(tmp_inode, 1, pfindEntry, &obj_type, rc); - if (rc) /* new inode - needs to be tied to dentry */ { - d_instantiate(tmp_dentry, tmp_inode); - if (rc == 2) - d_rehash(tmp_dentry); + /* new inode - needs to be tied to dentry */ + if (rc) { + d_instantiate(tmp_dentry, tmp_inode); + if (rc == 2) + d_rehash(tmp_dentry); + } + + ino = cifs_uniqueid_to_ino_t(tmp_inode->i_ino); } - rc = filldir(direntry, qstring.name, qstring.len, file->f_pos, - tmp_inode->i_ino, obj_type); + ino, obj_type); if (rc) { cFYI(1, ("filldir rc = %d", rc)); /* we can not return filldir errors to the caller @@ -1008,6 +934,7 @@ static int cifs_filldir(char *pfindEntry, struct file *file, filldir_t filldir, rc = -EOVERFLOW; } +out: dput(tmp_dentry); return rc; } From daf4219dbcbb2efcd638fcd3c29a622e1c18cc38 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 1 Jul 2009 16:12:53 -0700 Subject: [PATCH 0098/1346] dmaengine: move HIGHMEM64G restriction to ASYNC_TX_DMA On HIGHMEM64G systems dma_addr_t is known to be larger than (void *) which precludes async_xor from performing dma address conversions by reusing the input parameter address list. However, other parts of the dmaengine infrastructure do not suffer this constraint, so the HIGHMEM64G restriction can be down-levelled. Signed-off-by: Dan Williams --- crypto/async_tx/async_xor.c | 2 +- drivers/dma/Kconfig | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 95fe2c8d6c5..90dd3f8bd28 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -300,7 +300,7 @@ EXPORT_SYMBOL_GPL(async_xor_zero_sum); static int __init async_xor_init(void) { - #ifdef CONFIG_DMA_ENGINE + #ifdef CONFIG_ASYNC_TX_DMA /* To conserve stack space the input src_list (array of page pointers) * is reused to hold the array of dma addresses passed to the driver. * This conversion is only possible when dma_addr_t is less than the diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 3b3c01b6f1e..babf214a509 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -4,7 +4,7 @@ menuconfig DMADEVICES bool "DMA Engine support" - depends on !HIGHMEM64G && HAS_DMA + depends on HAS_DMA help DMA engines can do asynchronous data transfers without involving the host CPU. Currently, this framework can be @@ -100,7 +100,7 @@ config NET_DMA config ASYNC_TX_DMA bool "Async_tx: Offload support for the async_tx api" - depends on DMA_ENGINE + depends on DMA_ENGINE && !HIGHMEM64G help This allows the async_tx api to take advantage of offload engines for memcpy, memset, xor, and raid6 p+q operations. If your platform has From 956dba3caaf66b84fe5f6180e0e4dd03902c7980 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 1 Jul 2009 15:20:59 +0100 Subject: [PATCH 0099/1346] drm/i915: fix up a raw 64bit divide We are seeing compilation failures on i386 in some environments due to an undefined reference as below: ERROR: "__udivdi3" [drivers/gpu/drm/i915/i915.ko] undefined! This is generated due to a raw 64 bit divide in the i915 driver. Fix up this raw divide. Signed-off-by: Andy Whitcroft Acked-by: Jesse Barnes Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/intel_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index a84ac05ef04..59de4951b6e 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1577,7 +1577,7 @@ igdng_compute_m_n(int bytes_per_pixel, int nlanes, temp = (u64) DATA_N * pixel_clock; temp = div_u64(temp, link_clock); - m_n->gmch_m = (temp * bytes_per_pixel) / nlanes; + m_n->gmch_m = div_u64(temp * bytes_per_pixel, nlanes); m_n->gmch_n = DATA_N; fdi_reduce_ratio(&m_n->gmch_m, &m_n->gmch_n); From 1ae8c0a56eeb3ed358b78ccadd024d6b721f26bc Mon Sep 17 00:00:00 2001 From: Keith Packard Date: Sun, 28 Jun 2009 15:42:17 -0700 Subject: [PATCH 0100/1346] drm/i915: Make driver less chatty Convert many printk calls to DRM_DEBUG calls to reduce kernel log noise for normal activities. Switch other printk calls to DRM_ERROR or DRM_INFO. Signed-off-by: Keith Packard Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/i915_dma.c | 2 +- drivers/gpu/drm/i915/i915_drv.c | 4 ++-- drivers/gpu/drm/i915/intel_dp.c | 11 +++++++---- drivers/gpu/drm/i915/intel_dp_i2c.c | 11 ++++++----- drivers/gpu/drm/i915/intel_fb.c | 18 +++++++++--------- drivers/gpu/drm/i915/intel_lvds.c | 4 ++-- 6 files changed, 27 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 6096600aff6..0e704bb26e9 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -846,7 +846,7 @@ static int i915_set_status_page(struct drm_device *dev, void *data, return 0; } - printk(KERN_DEBUG "set status page addr 0x%08x\n", (u32)hws->addr); + DRM_DEBUG("set status page addr 0x%08x\n", (u32)hws->addr); dev_priv->status_gfx_addr = hws->addr & (0x1ffff<<12); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index e3cb4025e32..aef2a261a83 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -57,8 +57,8 @@ static int i915_suspend(struct drm_device *dev, pm_message_t state) struct drm_i915_private *dev_priv = dev->dev_private; if (!dev || !dev_priv) { - printk(KERN_ERR "dev: %p, dev_priv: %p\n", dev, dev_priv); - printk(KERN_ERR "DRM not initialized, aborting suspend.\n"); + DRM_ERROR("dev: %p, dev_priv: %p\n", dev, dev_priv); + DRM_ERROR("DRM not initialized, aborting suspend.\n"); return -ENODEV; } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 8f8d37d5663..6770ae88370 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -246,7 +246,7 @@ intel_dp_aux_ch(struct intel_output *intel_output, } if ((status & DP_AUX_CH_CTL_DONE) == 0) { - printk(KERN_ERR "dp_aux_ch not done status 0x%08x\n", status); + DRM_ERROR("dp_aux_ch not done status 0x%08x\n", status); return -EBUSY; } @@ -254,11 +254,14 @@ intel_dp_aux_ch(struct intel_output *intel_output, * Timeouts occur when the sink is not connected */ if (status & DP_AUX_CH_CTL_RECEIVE_ERROR) { - printk(KERN_ERR "dp_aux_ch receive error status 0x%08x\n", status); + DRM_ERROR("dp_aux_ch receive error status 0x%08x\n", status); return -EIO; } + + /* Timeouts occur when the device isn't connected, so they're + * "normal" -- don't fill the kernel log with these */ if (status & DP_AUX_CH_CTL_TIME_OUT_ERROR) { - printk(KERN_ERR "dp_aux_ch timeout status 0x%08x\n", status); + DRM_DEBUG("dp_aux_ch timeout status 0x%08x\n", status); return -ETIMEDOUT; } @@ -411,7 +414,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, dp_priv->link_bw = bws[clock]; dp_priv->lane_count = lane_count; adjusted_mode->clock = intel_dp_link_clock(dp_priv->link_bw); - printk(KERN_ERR "link bw %02x lane count %d clock %d\n", + DRM_DEBUG("Display port link bw %02x lane count %d clock %d\n", dp_priv->link_bw, dp_priv->lane_count, adjusted_mode->clock); return true; diff --git a/drivers/gpu/drm/i915/intel_dp_i2c.c b/drivers/gpu/drm/i915/intel_dp_i2c.c index 4e60f14b1a6..a63b6f57d2d 100644 --- a/drivers/gpu/drm/i915/intel_dp_i2c.c +++ b/drivers/gpu/drm/i915/intel_dp_i2c.c @@ -29,6 +29,7 @@ #include #include #include "intel_dp.h" +#include "drmP.h" /* Run a single AUX_CH I2C transaction, writing/reading data as necessary */ @@ -84,7 +85,7 @@ i2c_algo_dp_aux_transaction(struct i2c_adapter *adapter, int mode, msg, msg_bytes, reply, reply_bytes); if (ret < 0) { - printk(KERN_ERR "aux_ch failed %d\n", ret); + DRM_DEBUG("aux_ch failed %d\n", ret); return ret; } switch (reply[0] & AUX_I2C_REPLY_MASK) { @@ -94,14 +95,14 @@ i2c_algo_dp_aux_transaction(struct i2c_adapter *adapter, int mode, } return reply_bytes - 1; case AUX_I2C_REPLY_NACK: - printk(KERN_ERR "aux_ch nack\n"); + DRM_DEBUG("aux_ch nack\n"); return -EREMOTEIO; case AUX_I2C_REPLY_DEFER: - printk(KERN_ERR "aux_ch defer\n"); + DRM_DEBUG("aux_ch defer\n"); udelay(100); break; default: - printk(KERN_ERR "aux_ch invalid reply 0x%02x\n", reply[0]); + DRM_ERROR("aux_ch invalid reply 0x%02x\n", reply[0]); return -EREMOTEIO; } } @@ -223,7 +224,7 @@ i2c_algo_dp_aux_xfer(struct i2c_adapter *adapter, if (ret >= 0) ret = num; i2c_algo_dp_aux_stop(adapter, reading); - printk(KERN_ERR "dp_aux_xfer return %d\n", ret); + DRM_DEBUG("dp_aux_xfer return %d\n", ret); return ret; } diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 1af7d68e380..1d30802e773 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -453,7 +453,7 @@ static int intelfb_create(struct drm_device *dev, uint32_t fb_width, size = ALIGN(size, PAGE_SIZE); fbo = drm_gem_object_alloc(dev, size); if (!fbo) { - printk(KERN_ERR "failed to allocate framebuffer\n"); + DRM_ERROR("failed to allocate framebuffer\n"); ret = -ENOMEM; goto out; } @@ -610,8 +610,8 @@ static int intelfb_create(struct drm_device *dev, uint32_t fb_width, par->dev = dev; /* To allow resizeing without swapping buffers */ - printk("allocated %dx%d fb: 0x%08x, bo %p\n", intel_fb->base.width, - intel_fb->base.height, obj_priv->gtt_offset, fbo); + DRM_DEBUG("allocated %dx%d fb: 0x%08x, bo %p\n", intel_fb->base.width, + intel_fb->base.height, obj_priv->gtt_offset, fbo); mutex_unlock(&dev->struct_mutex); return 0; @@ -698,13 +698,13 @@ static int intelfb_multi_fb_probe_crtc(struct drm_device *dev, struct drm_crtc * } else intelfb_set_par(info); - printk(KERN_INFO "fb%d: %s frame buffer device\n", info->node, + DRM_INFO("fb%d: %s frame buffer device\n", info->node, info->fix.id); /* Switch back to kernel console on panic */ kernelfb_mode = *modeset; atomic_notifier_chain_register(&panic_notifier_list, &paniced); - printk(KERN_INFO "registered panic notifier\n"); + DRM_DEBUG("registered panic notifier\n"); return 0; } @@ -852,13 +852,13 @@ static int intelfb_single_fb_probe(struct drm_device *dev) } else intelfb_set_par(info); - printk(KERN_INFO "fb%d: %s frame buffer device\n", info->node, + DRM_INFO("fb%d: %s frame buffer device\n", info->node, info->fix.id); /* Switch back to kernel console on panic */ kernelfb_mode = *modeset; atomic_notifier_chain_register(&panic_notifier_list, &paniced); - printk(KERN_INFO "registered panic notifier\n"); + DRM_DEBUG("registered panic notifier\n"); return 0; } @@ -872,8 +872,8 @@ void intelfb_restore(void) { int ret; if ((ret = drm_crtc_helper_set_config(&kernelfb_mode)) != 0) { - printk(KERN_ERR "Failed to restore crtc configuration: %d\n", - ret); + DRM_ERROR("Failed to restore crtc configuration: %d\n", + ret); } } diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 9564ca44a97..f65044b1647 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -252,14 +252,14 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, /* Should never happen!! */ if (!IS_I965G(dev) && intel_crtc->pipe == 0) { - printk(KERN_ERR "Can't support LVDS on pipe A\n"); + DRM_ERROR("Can't support LVDS on pipe A\n"); return false; } /* Should never happen!! */ list_for_each_entry(tmp_encoder, &dev->mode_config.encoder_list, head) { if (tmp_encoder != encoder && tmp_encoder->crtc == encoder->crtc) { - printk(KERN_ERR "Can't enable LVDS and another " + DRM_ERROR("Can't enable LVDS and another " "encoder on the same pipe\n"); return false; } From 9974f496782b7612e36a143bedda858f1cb953d4 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 2 Jul 2009 08:05:58 +0200 Subject: [PATCH 0101/1346] perf_counter tools: Make symbol loading consistently return number of loaded symbols perf_counter tools: Make symbol loading consistently return number of loaded symbols. Signed-off-by: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246514758.13293.42.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/util/symbol.c | 9 ++++++--- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 132de8b28db..3becc8a35be 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -172,7 +172,7 @@ static int load_kernel(void) return -1; err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); - if (err) { + if (err <= 0) { dso__delete(kernel_dso); kernel_dso = NULL; } else diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index be1b7584796..58d1612894f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -189,7 +189,7 @@ static int load_kernel(void) return -1; err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); - if (err) { + if (err <= 0) { dso__delete(kernel_dso); kernel_dso = NULL; } else diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index cdc74cfb151..97fde1d8436 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -364,7 +364,7 @@ static int parse_symbols(void) if (kernel_dso == NULL) return -1; - if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) != 0) + if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) <= 0) goto out_delete_dso; node = rb_first(&kernel_dso->syms); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 78c2efde01b..c077b6a1469 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -146,6 +146,7 @@ static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verb char *line = NULL; size_t n; FILE *file = fopen("/proc/kallsyms", "r"); + int count = 0; if (file == NULL) goto out_failure; @@ -188,8 +189,10 @@ static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verb if (filter && filter(self, sym)) symbol__delete(sym, self->sym_priv_size); - else + else { dso__insert_symbol(self, sym); + count++; + } } /* @@ -212,7 +215,7 @@ static int dso__load_kallsyms(struct dso *self, symbol_filter_t filter, int verb free(line); fclose(file); - return 0; + return count; out_delete_line: free(line); @@ -639,7 +642,7 @@ int dso__load_kernel(struct dso *self, const char *vmlinux, if (vmlinux) err = dso__load_vmlinux(self, vmlinux, filter, verbose); - if (err < 0) + if (err <= 0) err = dso__load_kallsyms(self, filter, verbose); return err; From 208b4b4a59351011b7f212e273f2b7bc47a9c482 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 2 Jul 2009 08:07:10 +0200 Subject: [PATCH 0102/1346] perf_counter tools: Add infrastructure to support loading of kernel module symbols Add infrastructure for module path discovery and section load addresses. Signed-off-by: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246514830.13293.44.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- tools/perf/Makefile | 2 + tools/perf/util/module.c | 509 +++++++++++++++++++++++++++++++++++++++ tools/perf/util/module.h | 53 ++++ 3 files changed, 564 insertions(+) create mode 100644 tools/perf/util/module.c create mode 100644 tools/perf/util/module.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 8f7fd1b050a..7822b3d6bac 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -306,6 +306,7 @@ LIB_H += util/strlist.h LIB_H += util/run-command.h LIB_H += util/sigchain.h LIB_H += util/symbol.h +LIB_H += util/module.h LIB_H += util/color.h LIB_OBJS += util/abspath.o @@ -329,6 +330,7 @@ LIB_OBJS += util/usage.o LIB_OBJS += util/wrapper.o LIB_OBJS += util/sigchain.o LIB_OBJS += util/symbol.o +LIB_OBJS += util/module.o LIB_OBJS += util/color.o LIB_OBJS += util/pager.o LIB_OBJS += util/header.o diff --git a/tools/perf/util/module.c b/tools/perf/util/module.c new file mode 100644 index 00000000000..ddabe925d65 --- /dev/null +++ b/tools/perf/util/module.c @@ -0,0 +1,509 @@ +#include "util.h" +#include "../perf.h" +#include "string.h" +#include "module.h" + +#include +#include +#include +#include +#include + +static unsigned int crc32(const char *p, unsigned int len) +{ + int i; + unsigned int crc = 0; + + while (len--) { + crc ^= *p++; + for (i = 0; i < 8; i++) + crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0); + } + return crc; +} + +/* module section methods */ + +struct sec_dso *sec_dso__new_dso(const char *name) +{ + struct sec_dso *self = malloc(sizeof(*self) + strlen(name) + 1); + + if (self != NULL) { + strcpy(self->name, name); + self->secs = RB_ROOT; + self->find_section = sec_dso__find_section; + } + + return self; +} + +static void sec_dso__delete_section(struct section *self) +{ + free(((void *)self)); +} + +void sec_dso__delete_sections(struct sec_dso *self) +{ + struct section *pos; + struct rb_node *next = rb_first(&self->secs); + + while (next) { + pos = rb_entry(next, struct section, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &self->secs); + sec_dso__delete_section(pos); + } +} + +void sec_dso__delete_self(struct sec_dso *self) +{ + sec_dso__delete_sections(self); + free(self); +} + +static void sec_dso__insert_section(struct sec_dso *self, struct section *sec) +{ + struct rb_node **p = &self->secs.rb_node; + struct rb_node *parent = NULL; + const u64 hash = sec->hash; + struct section *s; + + while (*p != NULL) { + parent = *p; + s = rb_entry(parent, struct section, rb_node); + if (hash < s->hash) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&sec->rb_node, parent, p); + rb_insert_color(&sec->rb_node, &self->secs); +} + +struct section *sec_dso__find_section(struct sec_dso *self, const char *name) +{ + struct rb_node *n; + u64 hash; + int len; + + if (self == NULL) + return NULL; + + len = strlen(name); + hash = crc32(name, len); + + n = self->secs.rb_node; + + while (n) { + struct section *s = rb_entry(n, struct section, rb_node); + + if (hash < s->hash) + n = n->rb_left; + else if (hash > s->hash) + n = n->rb_right; + else { + if (!strcmp(name, s->name)) + return s; + else + n = rb_next(&s->rb_node); + } + } + + return NULL; +} + +static size_t sec_dso__fprintf_section(struct section *self, FILE *fp) +{ + return fprintf(fp, "name:%s vma:%llx path:%s\n", + self->name, self->vma, self->path); +} + +size_t sec_dso__fprintf(struct sec_dso *self, FILE *fp) +{ + size_t ret = fprintf(fp, "dso: %s\n", self->name); + + struct rb_node *nd; + for (nd = rb_first(&self->secs); nd; nd = rb_next(nd)) { + struct section *pos = rb_entry(nd, struct section, rb_node); + ret += sec_dso__fprintf_section(pos, fp); + } + + return ret; +} + +static struct section *section__new(const char *name, const char *path) +{ + struct section *self = calloc(1, sizeof(*self)); + + if (!self) + goto out_failure; + + self->name = calloc(1, strlen(name) + 1); + if (!self->name) + goto out_failure; + + self->path = calloc(1, strlen(path) + 1); + if (!self->path) + goto out_failure; + + strcpy(self->name, name); + strcpy(self->path, path); + self->hash = crc32(self->name, strlen(name)); + + return self; + +out_failure: + if (self) { + if (self->name) + free(self->name); + if (self->path) + free(self->path); + free(self); + } + + return NULL; +} + +/* module methods */ + +struct mod_dso *mod_dso__new_dso(const char *name) +{ + struct mod_dso *self = malloc(sizeof(*self) + strlen(name) + 1); + + if (self != NULL) { + strcpy(self->name, name); + self->mods = RB_ROOT; + self->find_module = mod_dso__find_module; + } + + return self; +} + +static void mod_dso__delete_module(struct module *self) +{ + free(((void *)self)); +} + +void mod_dso__delete_modules(struct mod_dso *self) +{ + struct module *pos; + struct rb_node *next = rb_first(&self->mods); + + while (next) { + pos = rb_entry(next, struct module, rb_node); + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &self->mods); + mod_dso__delete_module(pos); + } +} + +void mod_dso__delete_self(struct mod_dso *self) +{ + mod_dso__delete_modules(self); + free(self); +} + +static void mod_dso__insert_module(struct mod_dso *self, struct module *mod) +{ + struct rb_node **p = &self->mods.rb_node; + struct rb_node *parent = NULL; + const u64 hash = mod->hash; + struct module *m; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct module, rb_node); + if (hash < m->hash) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&mod->rb_node, parent, p); + rb_insert_color(&mod->rb_node, &self->mods); +} + +struct module *mod_dso__find_module(struct mod_dso *self, const char *name) +{ + struct rb_node *n; + u64 hash; + int len; + + if (self == NULL) + return NULL; + + len = strlen(name); + hash = crc32(name, len); + + n = self->mods.rb_node; + + while (n) { + struct module *m = rb_entry(n, struct module, rb_node); + + if (hash < m->hash) + n = n->rb_left; + else if (hash > m->hash) + n = n->rb_right; + else { + if (!strcmp(name, m->name)) + return m; + else + n = rb_next(&m->rb_node); + } + } + + return NULL; +} + +static size_t mod_dso__fprintf_module(struct module *self, FILE *fp) +{ + return fprintf(fp, "name:%s path:%s\n", self->name, self->path); +} + +size_t mod_dso__fprintf(struct mod_dso *self, FILE *fp) +{ + struct rb_node *nd; + size_t ret; + + ret = fprintf(fp, "dso: %s\n", self->name); + + for (nd = rb_first(&self->mods); nd; nd = rb_next(nd)) { + struct module *pos = rb_entry(nd, struct module, rb_node); + + ret += mod_dso__fprintf_module(pos, fp); + } + + return ret; +} + +static struct module *module__new(const char *name, const char *path) +{ + struct module *self = calloc(1, sizeof(*self)); + + if (!self) + goto out_failure; + + self->name = calloc(1, strlen(name) + 1); + if (!self->name) + goto out_failure; + + self->path = calloc(1, strlen(path) + 1); + if (!self->path) + goto out_failure; + + strcpy(self->name, name); + strcpy(self->path, path); + self->hash = crc32(self->name, strlen(name)); + + return self; + +out_failure: + if (self) { + if (self->name) + free(self->name); + if (self->path) + free(self->path); + free(self); + } + + return NULL; +} + +static int mod_dso__load_sections(struct module *mod) +{ + int count = 0, path_len; + struct dirent *entry; + char *line = NULL; + char *dir_path; + DIR *dir; + size_t n; + + path_len = strlen("/sys/module/"); + path_len += strlen(mod->name); + path_len += strlen("/sections/"); + + dir_path = calloc(1, path_len + 1); + if (dir_path == NULL) + goto out_failure; + + strcat(dir_path, "/sys/module/"); + strcat(dir_path, mod->name); + strcat(dir_path, "/sections/"); + + dir = opendir(dir_path); + if (dir == NULL) + goto out_free; + + while ((entry = readdir(dir))) { + struct section *section; + char *path, *vma; + int line_len; + FILE *file; + + if (!strcmp(".", entry->d_name) || !strcmp("..", entry->d_name)) + continue; + + path = calloc(1, path_len + strlen(entry->d_name) + 1); + if (path == NULL) + break; + strcat(path, dir_path); + strcat(path, entry->d_name); + + file = fopen(path, "r"); + if (file == NULL) { + free(path); + break; + } + + line_len = getline(&line, &n, file); + if (line_len < 0) { + free(path); + fclose(file); + break; + } + + if (!line) { + free(path); + fclose(file); + break; + } + + line[--line_len] = '\0'; /* \n */ + + vma = strstr(line, "0x"); + if (!vma) { + free(path); + fclose(file); + break; + } + vma += 2; + + section = section__new(entry->d_name, path); + if (!section) { + fprintf(stderr, "load_sections: allocation error\n"); + free(path); + fclose(file); + break; + } + + hex2u64(vma, §ion->vma); + sec_dso__insert_section(mod->sections, section); + + free(path); + fclose(file); + count++; + } + + closedir(dir); + free(line); + free(dir_path); + + return count; + +out_free: + free(dir_path); + +out_failure: + return count; +} + +static int mod_dso__load_module_paths(struct mod_dso *self) +{ + struct utsname uts; + int count = 0, len; + char *line = NULL; + FILE *file; + char *path; + size_t n; + + if (uname(&uts) < 0) + goto out_failure; + + len = strlen("/lib/modules/"); + len += strlen(uts.release); + len += strlen("/modules.dep"); + + path = calloc(1, len); + if (path == NULL) + goto out_failure; + + strcat(path, "/lib/modules/"); + strcat(path, uts.release); + strcat(path, "/modules.dep"); + + file = fopen(path, "r"); + free(path); + if (file == NULL) + goto out_failure; + + while (!feof(file)) { + char *path, *name, *tmp; + struct module *module; + int line_len, len; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + path = strtok(line, ":"); + if (!path) + goto out_failure; + + name = strdup(path); + name = strtok(name, "/"); + + tmp = name; + + while (tmp) { + tmp = strtok(NULL, "/"); + if (tmp) + name = tmp; + } + name = strsep(&name, "."); + + /* Quirk: replace '-' with '_' in sound modules */ + for (len = strlen(name); len; len--) { + if (*(name+len) == '-') + *(name+len) = '_'; + } + + module = module__new(name, path); + if (!module) { + fprintf(stderr, "load_module_paths: allocation error\n"); + goto out_failure; + } + mod_dso__insert_module(self, module); + + module->sections = sec_dso__new_dso("sections"); + if (!module->sections) { + fprintf(stderr, "load_module_paths: allocation error\n"); + goto out_failure; + } + + module->active = mod_dso__load_sections(module); + + if (module->active > 0) + count++; + } + + free(line); + fclose(file); + + return count; + +out_failure: + return -1; +} + +int mod_dso__load_modules(struct mod_dso *dso) +{ + int err; + + err = mod_dso__load_module_paths(dso); + + return err; +} diff --git a/tools/perf/util/module.h b/tools/perf/util/module.h new file mode 100644 index 00000000000..8a592ef641c --- /dev/null +++ b/tools/perf/util/module.h @@ -0,0 +1,53 @@ +#ifndef _PERF_MODULE_ +#define _PERF_MODULE_ 1 + +#include +#include "../types.h" +#include +#include + +struct section { + struct rb_node rb_node; + u64 hash; + u64 vma; + char *name; + char *path; +}; + +struct sec_dso { + struct list_head node; + struct rb_root secs; + struct section *(*find_section)(struct sec_dso *, const char *name); + char name[0]; +}; + +struct module { + struct rb_node rb_node; + u64 hash; + char *name; + char *path; + struct sec_dso *sections; + int active; +}; + +struct mod_dso { + struct list_head node; + struct rb_root mods; + struct module *(*find_module)(struct mod_dso *, const char *name); + char name[0]; +}; + +struct sec_dso *sec_dso__new_dso(const char *name); +void sec_dso__delete_sections(struct sec_dso *self); +void sec_dso__delete_self(struct sec_dso *self); +size_t sec_dso__fprintf(struct sec_dso *self, FILE *fp); +struct section *sec_dso__find_section(struct sec_dso *self, const char *name); + +struct mod_dso *mod_dso__new_dso(const char *name); +void mod_dso__delete_modules(struct mod_dso *self); +void mod_dso__delete_self(struct mod_dso *self); +size_t mod_dso__fprintf(struct mod_dso *self, FILE *fp); +struct module *mod_dso__find_module(struct mod_dso *self, const char *name); +int mod_dso__load_modules(struct mod_dso *dso); + +#endif /* _PERF_MODULE_ */ From 6cfcc53ed4f3ecb9319e73a03f34f1eddcb644dd Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 2 Jul 2009 08:08:36 +0200 Subject: [PATCH 0103/1346] perf_counter tools: Connect module support infrastructure to symbol loading infrastructure Signed-off-by: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246514916.13293.46.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/util/symbol.c | 159 +++++++++++++++++++++++++++++++--- tools/perf/util/symbol.h | 5 +- 5 files changed, 156 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 3becc8a35be..88205686eb6 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -171,7 +171,7 @@ static int load_kernel(void) if (!kernel_dso) return -1; - err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, 0); if (err <= 0) { dso__delete(kernel_dso); kernel_dso = NULL; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 58d1612894f..38d136fedfb 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -188,7 +188,7 @@ static int load_kernel(void) if (!kernel_dso) return -1; - err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose); + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, 0); if (err <= 0) { dso__delete(kernel_dso); kernel_dso = NULL; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 97fde1d8436..9bb25fc3d4c 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -364,7 +364,7 @@ static int parse_symbols(void) if (kernel_dso == NULL) return -1; - if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1) <= 0) + if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1, 0) <= 0) goto out_delete_dso; node = rb_first(&kernel_dso->syms); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index c077b6a1469..98a13114de7 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -35,7 +35,7 @@ static struct symbol *symbol__new(u64 start, u64 len, self = ((void *)self) + priv_size; } self->start = start; - self->end = start + len - 1; + self->end = len ? start + len - 1 : start; memcpy(self->name, name, namelen); return self; @@ -48,8 +48,12 @@ static void symbol__delete(struct symbol *self, unsigned int priv_size) static size_t symbol__fprintf(struct symbol *self, FILE *fp) { - return fprintf(fp, " %llx-%llx %s\n", + if (!self->module) + return fprintf(fp, " %llx-%llx %s\n", self->start, self->end, self->name); + else + return fprintf(fp, " %llx-%llx %s \t[%s]\n", + self->start, self->end, self->name, self->module->name); } struct dso *dso__new(const char *name, unsigned int sym_priv_size) @@ -310,6 +314,26 @@ static inline int elf_sym__is_function(const GElf_Sym *sym) sym->st_size != 0; } +static inline int elf_sym__is_label(const GElf_Sym *sym) +{ + return elf_sym__type(sym) == STT_NOTYPE && + sym->st_name != 0 && + sym->st_shndx != SHN_UNDEF && + sym->st_shndx != SHN_ABS; +} + +static inline const char *elf_sec__name(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return secstrs->d_buf + shdr->sh_name; +} + +static inline int elf_sec__is_text(const GElf_Shdr *shdr, + const Elf_Data *secstrs) +{ + return strstr(elf_sec__name(shdr, secstrs), "text") != NULL; +} + static inline const char *elf_sym__name(const GElf_Sym *sym, const Elf_Data *symstrs) { @@ -451,9 +475,9 @@ static int dso__synthesize_plt_symbols(struct dso *self, Elf *elf, } static int dso__load_sym(struct dso *self, int fd, const char *name, - symbol_filter_t filter, int verbose) + symbol_filter_t filter, int verbose, struct module *mod) { - Elf_Data *symstrs; + Elf_Data *symstrs, *secstrs; uint32_t nr_syms; int err = -1; uint32_t index; @@ -461,7 +485,7 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, GElf_Shdr shdr; Elf_Data *syms; GElf_Sym sym; - Elf_Scn *sec, *sec_dynsym; + Elf_Scn *sec, *sec_dynsym, *sec_strndx; Elf *elf; size_t dynsym_idx; int nr = 0; @@ -520,6 +544,14 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, if (symstrs == NULL) goto out_elf_end; + sec_strndx = elf_getscn(elf, ehdr.e_shstrndx); + if (sec_strndx == NULL) + goto out_elf_end; + + secstrs = elf_getdata(sec_strndx, NULL); + if (symstrs == NULL) + goto out_elf_end; + nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); @@ -529,8 +561,11 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, elf_symtab__for_each_symbol(syms, nr_syms, index, sym) { struct symbol *f; u64 obj_start; + struct section *section = NULL; + int is_label = elf_sym__is_label(&sym); + const char *section_name; - if (!elf_sym__is_function(&sym)) + if (!is_label && !elf_sym__is_function(&sym)) continue; sec = elf_getscn(elf, sym.st_shndx); @@ -538,6 +573,11 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, goto out_elf_end; gelf_getshdr(sec, &shdr); + + if (is_label && !elf_sec__is_text(&shdr, secstrs)) + continue; + + section_name = elf_sec__name(&shdr, secstrs); obj_start = sym.st_value; if (self->prelinked) { @@ -548,6 +588,17 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, sym.st_value -= shdr.sh_addr - shdr.sh_offset; } + if (mod) { + section = mod->sections->find_section(mod->sections, section_name); + if (section) + sym.st_value += section->vma; + else { + fprintf(stderr, "dso__load_sym() module %s lookup of %s failed\n", + mod->name, section_name); + goto out_elf_end; + } + } + f = symbol__new(sym.st_value, sym.st_size, elf_sym__name(&sym, symstrs), self->sym_priv_size, obj_start, verbose); @@ -557,6 +608,7 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, if (filter && filter(self, f)) symbol__delete(f, self->sym_priv_size); else { + f->module = mod; dso__insert_symbol(self, f); nr++; } @@ -606,7 +658,7 @@ more: fd = open(name, O_RDONLY); } while (fd < 0); - ret = dso__load_sym(self, fd, name, filter, verbose); + ret = dso__load_sym(self, fd, name, filter, verbose, NULL); close(fd); /* @@ -620,6 +672,86 @@ out: return ret; } +static int dso__load_module(struct dso *self, struct mod_dso *mods, const char *name, + symbol_filter_t filter, int verbose) +{ + struct module *mod = mod_dso__find_module(mods, name); + int err = 0, fd; + + if (mod == NULL || !mod->active) + return err; + + fd = open(mod->path, O_RDONLY); + + if (fd < 0) + return err; + + err = dso__load_sym(self, fd, name, filter, verbose, mod); + close(fd); + + return err; +} + +int dso__load_modules(struct dso *self, symbol_filter_t filter, int verbose) +{ + struct mod_dso *mods = mod_dso__new_dso("modules"); + struct module *pos; + struct rb_node *next; + int err; + + err = mod_dso__load_modules(mods); + + if (err <= 0) + return err; + + /* + * Iterate over modules, and load active symbols. + */ + next = rb_first(&mods->mods); + while (next) { + pos = rb_entry(next, struct module, rb_node); + err = dso__load_module(self, mods, pos->name, filter, verbose); + + if (err < 0) + break; + + next = rb_next(&pos->rb_node); + } + + if (err < 0) { + mod_dso__delete_modules(mods); + mod_dso__delete_self(mods); + } + + return err; +} + +static inline void dso__fill_symbol_holes(struct dso *self) +{ + struct symbol *prev = NULL; + struct rb_node *nd; + + for (nd = rb_last(&self->syms); nd; nd = rb_prev(nd)) { + struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + + if (prev) { + u64 hole = 0; + int alias = pos->start == prev->start; + + if (!alias) + hole = prev->start - pos->end - 1; + + if (hole || alias) { + if (alias) + pos->end = prev->end; + else if (hole) + pos->end = prev->start - 1; + } + } + prev = pos; + } +} + static int dso__load_vmlinux(struct dso *self, const char *vmlinux, symbol_filter_t filter, int verbose) { @@ -628,19 +760,26 @@ static int dso__load_vmlinux(struct dso *self, const char *vmlinux, if (fd < 0) return -1; - err = dso__load_sym(self, fd, vmlinux, filter, verbose); + err = dso__load_sym(self, fd, vmlinux, filter, verbose, NULL); + + if (err > 0) + dso__fill_symbol_holes(self); + close(fd); return err; } int dso__load_kernel(struct dso *self, const char *vmlinux, - symbol_filter_t filter, int verbose) + symbol_filter_t filter, int verbose, int modules) { int err = -1; - if (vmlinux) + if (vmlinux) { err = dso__load_vmlinux(self, vmlinux, filter, verbose); + if (err > 0 && modules) + err = dso__load_modules(self, filter, verbose); + } if (err <= 0) err = dso__load_kallsyms(self, filter, verbose); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 65a8449b91f..4e141a30911 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -5,6 +5,7 @@ #include "types.h" #include #include +#include "module.h" struct symbol { struct rb_node rb_node; @@ -13,6 +14,7 @@ struct symbol { u64 obj_start; u64 hist_sum; u64 *hist; + struct module *module; void *priv; char name[0]; }; @@ -41,7 +43,8 @@ static inline void *dso__sym_priv(struct dso *self, struct symbol *sym) struct symbol *dso__find_symbol(struct dso *self, u64 ip); int dso__load_kernel(struct dso *self, const char *vmlinux, - symbol_filter_t filter, int verbose); + symbol_filter_t filter, int verbose, int modules); +int dso__load_modules(struct dso *self, symbol_filter_t filter, int verbose); int dso__load(struct dso *self, symbol_filter_t filter, int verbose); size_t dso__fprintf(struct dso *self, FILE *fp); From 429764873cf3fc3e73142872a674bb27cda589c1 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 2 Jul 2009 08:09:46 +0200 Subject: [PATCH 0104/1346] perf_counter tools: Enable kernel module symbol loading in tools Add the -m/--modules option to perf report and perf annotate, which enables live module symbol/image loading. To be used with -k/--vmlinux. (Also give perf annotate a -P/--full-paths option.) Signed-off-by: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246514986.13293.48.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- tools/perf/builtin-annotate.c | 25 ++++++++++++++++++++----- tools/perf/builtin-report.c | 9 ++++++++- tools/perf/builtin-top.c | 12 ++++++++++-- 3 files changed, 38 insertions(+), 8 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 88205686eb6..08ea6c5329d 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -43,6 +43,10 @@ static int dump_trace = 0; static int verbose; +static int modules; + +static int full_paths; + static int print_line; static unsigned long page_size; @@ -171,7 +175,7 @@ static int load_kernel(void) if (!kernel_dso) return -1; - err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, 0); + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, modules); if (err <= 0) { dso__delete(kernel_dso); kernel_dso = NULL; @@ -1268,19 +1272,25 @@ static void print_summary(char *filename) static void annotate_sym(struct dso *dso, struct symbol *sym) { - char *filename = dso->name; + char *filename = dso->name, *d_filename; u64 start, end, len; char command[PATH_MAX*2]; FILE *file; if (!filename) return; - if (dso == kernel_dso) + if (sym->module) + filename = sym->module->path; + else if (dso == kernel_dso) filename = vmlinux; start = sym->obj_start; if (!start) start = sym->start; + if (full_paths) + d_filename = filename; + else + d_filename = basename(filename); end = start + sym->end - sym->start + 1; len = sym->end - sym->start; @@ -1291,13 +1301,14 @@ static void annotate_sym(struct dso *dso, struct symbol *sym) } printf("\n\n------------------------------------------------\n"); - printf(" Percent | Source code & Disassembly of %s\n", filename); + printf(" Percent | Source code & Disassembly of %s\n", d_filename); printf("------------------------------------------------\n"); if (verbose >= 2) printf("annotating [%p] %30s : [%p] %30s\n", dso, dso->name, sym, sym->name); - sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", (u64)start, (u64)end, filename); + sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s", + (u64)start, (u64)end, filename, filename); if (verbose >= 3) printf("doing: %s\n", command); @@ -1472,8 +1483,12 @@ static const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), + OPT_BOOLEAN('m', "modules", &modules, + "load module symbols - WARNING: use only with -k and LIVE kernel"), OPT_BOOLEAN('l', "print-line", &print_line, "print matching source lines (may be slow)"), + OPT_BOOLEAN('P', "full-paths", &full_paths, + "Don't shorten the displayed pathnames"), OPT_END() }; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 38d136fedfb..b44476ca239 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -46,6 +46,8 @@ static int dump_trace = 0; static int verbose; #define eprintf(x...) do { if (verbose) fprintf(stderr, x); } while (0) +static int modules; + static int full_paths; static unsigned long page_size; @@ -188,7 +190,7 @@ static int load_kernel(void) if (!kernel_dso) return -1; - err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, 0); + err = dso__load_kernel(kernel_dso, vmlinux, NULL, verbose, modules); if (err <= 0) { dso__delete(kernel_dso); kernel_dso = NULL; @@ -648,6 +650,9 @@ sort__sym_print(FILE *fp, struct hist_entry *self) ret += fprintf(fp, "[%c] %s", self->dso == kernel_dso ? 'k' : self->dso == hypervisor_dso ? 'h' : '.', self->sym->name); + + if (self->sym->module) + ret += fprintf(fp, "\t[%s]", self->sym->module->name); } else { ret += fprintf(fp, "%#016llx", (u64)self->ip); } @@ -1710,6 +1715,8 @@ static const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), + OPT_BOOLEAN('m', "modules", &modules, + "load module symbols - WARNING: use only with -k and LIVE kernel"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): pid, comm, dso, symbol, parent"), OPT_BOOLEAN('P', "full-paths", &full_paths, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 9bb25fc3d4c..aa044ea1482 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -66,6 +66,7 @@ static unsigned int page_size; static unsigned int mmap_pages = 16; static int freq = 0; static int verbose = 0; +static char *vmlinux = NULL; static char *sym_filter; static unsigned long filter_start; @@ -265,7 +266,10 @@ static void print_sym_table(void) printf("%9.1f %10ld - ", syme->weight, syme->snap_count); color_fprintf(stdout, color, "%4.1f%%", pcnt); - printf(" - %016llx : %s\n", sym->start, sym->name); + printf(" - %016llx : %s", sym->start, sym->name); + if (sym->module) + printf("\t[%s]", sym->module->name); + printf("\n"); } } @@ -359,12 +363,13 @@ static int parse_symbols(void) { struct rb_node *node; struct symbol *sym; + int modules = vmlinux ? 1 : 0; kernel_dso = dso__new("[kernel]", sizeof(struct sym_entry)); if (kernel_dso == NULL) return -1; - if (dso__load_kernel(kernel_dso, NULL, symbol_filter, 1, 0) <= 0) + if (dso__load_kernel(kernel_dso, vmlinux, symbol_filter, verbose, modules) <= 0) goto out_delete_dso; node = rb_first(&kernel_dso->syms); @@ -680,6 +685,7 @@ static const struct option options[] = { "system-wide collection from all CPUs"), OPT_INTEGER('C', "CPU", &profile_cpu, "CPU to profile on"), + OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"), OPT_INTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"), OPT_INTEGER('r', "realtime", &realtime_prio, @@ -709,6 +715,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) { int counter; + symbol__init(); + page_size = sysconf(_SC_PAGE_SIZE); argc = parse_options(argc, argv, options, top_usage, 0); From e1af3aec3e2e7d21d4b3054323779d478c19d907 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 1 Jul 2009 16:50:25 +0800 Subject: [PATCH 0105/1346] tracing: Fix trace_print_seq() We will lose something if trace_seq->buffer[0] is 0, because the copy length is calculated by strlen() in seq_puts(), so using seq_write() instead of seq_puts(). There have a example: after reboot: # echo kmemtrace > current_tracer # echo 0 > options/kmem_minimalistic # cat trace # tracer: kmemtrace # # Nothing is exported, because the first byte of trace_seq->buffer[ ] is KMEMTRACE_USER_ALLOC. ( the value of KMEMTRACE_USER_ALLOC is zero, seeing kmemtrace_print_alloc_user() in kernel/trace/kmemtrace.c) Signed-off-by: Xiao Guangrong Acked-by: Frederic Weisbecker Acked-by: Pekka Enberg Acked-by: Eduard - Gabriel Munteanu Cc: Steven Rostedt LKML-Reference: <4A4B2351.5010300@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/trace/trace_output.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 7938f3ae93e..e0c2545622e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -27,8 +27,7 @@ void trace_print_seq(struct seq_file *m, struct trace_seq *s) { int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len; - s->buffer[len] = 0; - seq_puts(m, s->buffer); + seq_write(m, s->buffer, len); trace_seq_init(s); } From 251e1e44b97852aa5e53e71c4b47e55b2dfd054e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 2 Jul 2009 08:54:01 +0200 Subject: [PATCH 0106/1346] x86: Fix printk call in print_local_apic() Instead of this: [ 75.690022] <7>printing local APIC contents on CPU#0/0: [ 75.704406] ... APIC ID: 00000000 (0) [ 75.707905] ... APIC VERSION: 00060015 [ 75.722551] ... APIC TASKPRI: 00000000 (00) [ 75.725473] ... APIC PROCPRI: 00000000 [ 75.728592] ... APIC LDR: 00000001 [ 75.742137] ... APIC SPIV: 000001ff [ 75.744101] ... APIC ISR field: [ 75.746648] 0123456789abcdef0123456789abcdef [ 75.746649] <7>00000000000000000000000000000000 Improve the code to be saner and simpler and just print out the bitfield in a single line using hexa values - not as a (rather pointless) binary bitfield. Partially reused Linus's initial fix for this. Reported-and-Tested-by: Yinghai Lu Signed-off-by: Yinghai Lu Cc: Linus Torvalds Cc: Andrew Morton LKML-Reference: <4A4C43BC.90506@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/io_apic.c | 31 +++++++++++++------------------ 1 file changed, 13 insertions(+), 18 deletions(-) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 4d0216fcb36..8fd1efb5a0b 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1716,25 +1716,19 @@ __apicdebuginit(void) print_IO_APIC(void) return; } -__apicdebuginit(void) print_APIC_bitfield(int base) +__apicdebuginit(void) print_APIC_field(int base) { - unsigned int v; - int i, j; + int i; if (apic_verbosity == APIC_QUIET) return; - printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG); - for (i = 0; i < 8; i++) { - v = apic_read(base + i*0x10); - for (j = 0; j < 32; j++) { - if (v & (1< 3) /* Due to the Pentium erratum 3AP. */ From 7a6a3a086fe60bb3b739f66e47dc5bbc8f530d32 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 2 Jul 2009 12:23:23 +0200 Subject: [PATCH 0107/1346] amd-iommu: handle alias entries correctly in init code An alias entry in the ACPI table means that the device can send requests to the IOMMU with both device ids, its own and the alias. This is not handled properly in the ACPI init code. This patch fixes the issue. Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu_init.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 10b2accd12e..ec72c7779d6 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -691,6 +691,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, devid = e->devid; devid_to = e->ext >> 8; + set_dev_entry_from_acpi(iommu, devid , e->flags, 0); set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0); amd_iommu_alias_table[devid] = devid_to; break; @@ -749,11 +750,13 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, devid = e->devid; for (dev_i = devid_start; dev_i <= devid; ++dev_i) { - if (alias) + if (alias) { amd_iommu_alias_table[dev_i] = devid_to; - set_dev_entry_from_acpi(iommu, - amd_iommu_alias_table[dev_i], - flags, ext_flags); + set_dev_entry_from_acpi(iommu, + devid_to, flags, ext_flags); + } + set_dev_entry_from_acpi(iommu, dev_i, + flags, ext_flags); } break; default: From 9be4b17c4c900f634ab9be3d13e116aa31edb7cb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 1 Jul 2009 23:41:12 +0100 Subject: [PATCH 0108/1346] [ARM] 5579/1: Updated U300 defconfig This defconfig update selects all the new U300 drivers merged for 2.6.31-rc1 in the merge window and add defaults for the new config options. It compiles and boots nicely from initramfs on the U300. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/configs/u300_defconfig | 92 +++++++++++++++++++-------------- 1 file changed, 53 insertions(+), 39 deletions(-) diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig index 2d827e12114..4762d900129 100644 --- a/arch/arm/configs/u300_defconfig +++ b/arch/arm/configs/u300_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.30-rc6 -# Mon Jun 1 09:18:22 2009 +# Linux kernel version: 2.6.31-rc1 +# Thu Jul 2 00:16:59 2009 # CONFIG_ARM=y CONFIG_SYS_SUPPORTS_APM_EMULATION=y @@ -9,7 +9,7 @@ CONFIG_GENERIC_GPIO=y CONFIG_GENERIC_TIME=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_MMU=y -# CONFIG_NO_IOPORT is not set +CONFIG_HAVE_TCM=y CONFIG_GENERIC_HARDIRQS=y CONFIG_STACKTRACE_SUPPORT=y CONFIG_HAVE_LATENCYTOP_SUPPORT=y @@ -18,13 +18,12 @@ CONFIG_TRACE_IRQFLAGS_SUPPORT=y CONFIG_HARDIRQS_SW_RESEND=y CONFIG_GENERIC_IRQ_PROBE=y CONFIG_RWSEM_GENERIC_SPINLOCK=y -# CONFIG_ARCH_HAS_ILOG2_U32 is not set -# CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y CONFIG_VECTORS_BASE=0xffff0000 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +CONFIG_CONSTRUCTORS=y # # General setup @@ -68,7 +67,6 @@ CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_ALL is not set # CONFIG_KALLSYMS_EXTRA_PASS is not set -# CONFIG_STRIP_ASM_SYMS is not set CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y @@ -81,8 +79,13 @@ CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y # CONFIG_AIO is not set + +# +# Performance Counters +# # CONFIG_VM_EVENT_COUNTERS is not set CONFIG_SLUB_DEBUG=y +# CONFIG_STRIP_ASM_SYMS is not set CONFIG_COMPAT_BRK=y # CONFIG_SLAB is not set CONFIG_SLUB=y @@ -94,6 +97,10 @@ CONFIG_HAVE_OPROFILE=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_CLK=y + +# +# GCOV-based kernel profiling +# # CONFIG_SLOW_WORK is not set CONFIG_HAVE_GENERIC_DMA_COHERENT=y CONFIG_SLABINFO=y @@ -106,7 +113,7 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_BLOCK=y -# CONFIG_LBD is not set +CONFIG_LBDAF=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_BLK_DEV_INTEGRITY is not set @@ -138,9 +145,9 @@ CONFIG_DEFAULT_IOSCHED="deadline" # CONFIG_ARCH_EP93XX is not set # CONFIG_ARCH_FOOTBRIDGE is not set # CONFIG_ARCH_MXC is not set +# CONFIG_ARCH_STMP3XXX is not set # CONFIG_ARCH_NETX is not set # CONFIG_ARCH_H720X is not set -# CONFIG_ARCH_IMX is not set # CONFIG_ARCH_IOP13XX is not set # CONFIG_ARCH_IOP32X is not set # CONFIG_ARCH_IOP33X is not set @@ -216,8 +223,8 @@ CONFIG_ARM_THUMB=y # CONFIG_CPU_DCACHE_DISABLE is not set # CONFIG_CPU_DCACHE_WRITETHROUGH is not set # CONFIG_CPU_CACHE_ROUND_ROBIN is not set -# CONFIG_OUTER_CACHE is not set CONFIG_ARM_VIC=y +CONFIG_ARM_VIC_NR=2 CONFIG_COMMON_CLKDEV=y # @@ -243,7 +250,6 @@ CONFIG_PREEMPT=y CONFIG_HZ=100 CONFIG_AEABI=y CONFIG_OABI_COMPAT=y -CONFIG_ARCH_FLATMEM_HAS_HOLES=y # CONFIG_ARCH_SPARSEMEM_DEFAULT is not set # CONFIG_ARCH_SELECT_MEMORY_MODEL is not set # CONFIG_HIGHMEM is not set @@ -258,17 +264,18 @@ CONFIG_SPLIT_PTLOCK_CPUS=4096 # CONFIG_PHYS_ADDR_T_64BIT is not set CONFIG_ZONE_DMA_FLAG=0 CONFIG_VIRT_TO_BUS=y -CONFIG_UNEVICTABLE_LRU=y CONFIG_HAVE_MLOCK=y CONFIG_HAVE_MLOCKED_PAGE_BIT=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 CONFIG_ALIGNMENT_TRAP=y +# CONFIG_UACCESS_WITH_MEMCPY is not set # # Boot options # CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="root=/dev/mtdblock2 rw rootfstype=yaffs2 console=ttyAMA0,115200n8 ab3100.force=0,0x48 mtdparts=u300nand:128k@0x0(bootrecords)ro,8064k@128k(free)ro,253952k@8192k(platform) lpj=515072" +CONFIG_CMDLINE="root=/dev/ram0 rw rootfstype=rootfs console=ttyAMA0,115200n8 lpj=515072" # CONFIG_XIP_KERNEL is not set # CONFIG_KEXEC is not set @@ -359,6 +366,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set # CONFIG_PHONET is not set +# CONFIG_IEEE802154 is not set # CONFIG_NET_SCHED is not set # CONFIG_DCB is not set @@ -497,6 +505,7 @@ CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_AT24 is not set # CONFIG_EEPROM_AT25 is not set # CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_MAX6875 is not set # CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -538,6 +547,7 @@ CONFIG_INPUT_KEYBOARD=y # CONFIG_KEYBOARD_XTKBD is not set # CONFIG_KEYBOARD_NEWTON is not set # CONFIG_KEYBOARD_STOWAWAY is not set +# CONFIG_KEYBOARD_LM8323 is not set # CONFIG_KEYBOARD_GPIO is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_INPUT_JOYSTICK is not set @@ -597,9 +607,11 @@ CONFIG_I2C_HELPER_AUTO=y # # I2C system bus drivers (mostly embedded / system-on-chip) # +# CONFIG_I2C_DESIGNWARE is not set # CONFIG_I2C_GPIO is not set # CONFIG_I2C_OCORES is not set # CONFIG_I2C_SIMTEC is not set +CONFIG_I2C_STU300=y # # External I2C/SMBus adapter drivers @@ -620,7 +632,6 @@ CONFIG_I2C_HELPER_AUTO=y # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set -# CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set # CONFIG_I2C_DEBUG_ALGO is not set @@ -635,6 +646,7 @@ CONFIG_SPI_MASTER=y # # CONFIG_SPI_BITBANG is not set # CONFIG_SPI_GPIO is not set +CONFIG_SPI_PL022=y # # SPI Protocol Masters @@ -647,6 +659,7 @@ CONFIG_POWER_SUPPLY=y # CONFIG_PDA_POWER is not set # CONFIG_BATTERY_DS2760 is not set # CONFIG_BATTERY_BQ27x00 is not set +# CONFIG_BATTERY_MAX17040 is not set # CONFIG_HWMON is not set # CONFIG_THERMAL is not set # CONFIG_THERMAL_HWMON is not set @@ -657,6 +670,7 @@ CONFIG_WATCHDOG=y # Watchdog Device Drivers # # CONFIG_SOFT_WATCHDOG is not set +CONFIG_COH901327_WATCHDOG=y CONFIG_SSB_POSSIBLE=y # @@ -678,22 +692,9 @@ CONFIG_SSB_POSSIBLE=y # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set # CONFIG_MFD_PCF50633 is not set - -# -# Multimedia devices -# - -# -# Multimedia core support -# -# CONFIG_VIDEO_DEV is not set -# CONFIG_DVB_CORE is not set -# CONFIG_VIDEO_MEDIA is not set - -# -# Multimedia drivers -# -# CONFIG_DAB is not set +CONFIG_AB3100_CORE=y +# CONFIG_EZX_PCAP is not set +# CONFIG_MEDIA_SUPPORT is not set # # Graphics support @@ -760,6 +761,11 @@ CONFIG_SND_JACK=y # CONFIG_SND_VERBOSE_PROCFS is not set # CONFIG_SND_VERBOSE_PRINTK is not set # CONFIG_SND_DEBUG is not set +# CONFIG_SND_RAWMIDI_SEQ is not set +# CONFIG_SND_OPL3_LIB_SEQ is not set +# CONFIG_SND_OPL4_LIB_SEQ is not set +# CONFIG_SND_SBAWE_SEQ is not set +# CONFIG_SND_EMU10K1_SEQ is not set # CONFIG_SND_DRIVERS is not set # CONFIG_SND_ARM is not set # CONFIG_SND_SPI is not set @@ -770,7 +776,7 @@ CONFIG_SND_SOC_I2C_AND_SPI=y # CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_MMC=y -# CONFIG_MMC_DEBUG is not set +CONFIG_MMC_DEBUG=y # CONFIG_MMC_UNSAFE_RESUME is not set # @@ -797,7 +803,7 @@ CONFIG_LEDS_CLASS=y # # CONFIG_LEDS_PCA9532 is not set # CONFIG_LEDS_GPIO is not set -# CONFIG_LEDS_LP5521 is not set +# CONFIG_LEDS_LP3944 is not set # CONFIG_LEDS_PCA955X is not set # CONFIG_LEDS_DAC124S085 is not set # CONFIG_LEDS_BD2802 is not set @@ -845,6 +851,7 @@ CONFIG_RTC_INTF_DEV=y # CONFIG_RTC_DRV_S35390A is not set # CONFIG_RTC_DRV_FM3130 is not set # CONFIG_RTC_DRV_RX8581 is not set +# CONFIG_RTC_DRV_RX8025 is not set # # SPI RTC drivers @@ -887,7 +894,10 @@ CONFIG_REGULATOR=y # CONFIG_REGULATOR_DEBUG is not set # CONFIG_REGULATOR_FIXED_VOLTAGE is not set # CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set +# CONFIG_REGULATOR_USERSPACE_CONSUMER is not set # CONFIG_REGULATOR_BQ24022 is not set +# CONFIG_REGULATOR_MAX1586 is not set +# CONFIG_REGULATOR_LP3971 is not set # CONFIG_UIO is not set # CONFIG_STAGING is not set @@ -900,16 +910,20 @@ CONFIG_REGULATOR=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set # CONFIG_FS_POSIX_ACL is not set -CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set +# CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_BTRFS_FS is not set +CONFIG_FILE_LOCKING=y +CONFIG_FSNOTIFY=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY is not set +CONFIG_INOTIFY_USER=y # CONFIG_QUOTA is not set # CONFIG_AUTOFS_FS is not set # CONFIG_AUTOFS4_FS is not set CONFIG_FUSE_FS=y +# CONFIG_CUSE is not set # # Caches @@ -1033,6 +1047,7 @@ CONFIG_TIMER_STATS=y # CONFIG_DEBUG_OBJECTS is not set # CONFIG_SLUB_DEBUG_ON is not set # CONFIG_SLUB_STATS is not set +# CONFIG_DEBUG_KMEMLEAK is not set # CONFIG_DEBUG_PREEMPT is not set # CONFIG_DEBUG_RT_MUTEXES is not set # CONFIG_RT_MUTEX_TESTER is not set @@ -1063,18 +1078,16 @@ CONFIG_DEBUG_INFO=y # CONFIG_PAGE_POISONING is not set CONFIG_HAVE_FUNCTION_TRACER=y CONFIG_TRACING_SUPPORT=y - -# -# Tracers -# +CONFIG_FTRACE=y # CONFIG_FUNCTION_TRACER is not set # CONFIG_IRQSOFF_TRACER is not set # CONFIG_PREEMPT_TRACER is not set # CONFIG_SCHED_TRACER is not set -# CONFIG_CONTEXT_SWITCH_TRACER is not set -# CONFIG_EVENT_TRACER is not set +# CONFIG_ENABLE_DEFAULT_TRACERS is not set # CONFIG_BOOT_TRACER is not set -# CONFIG_TRACE_BRANCH_PROFILING is not set +CONFIG_BRANCH_PROFILE_NONE=y +# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set +# CONFIG_PROFILE_ALL_BRANCHES is not set # CONFIG_STACK_TRACER is not set # CONFIG_KMEMTRACE is not set # CONFIG_WORKQUEUE_TRACER is not set @@ -1109,6 +1122,7 @@ CONFIG_GENERIC_FIND_LAST_BIT=y # CONFIG_CRC32 is not set # CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set +CONFIG_GENERIC_ALLOCATOR=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y From 4ebfc3dba59fb84b315ebb0059347dc9342a32f1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 2 Jul 2009 00:27:57 +0100 Subject: [PATCH 0109/1346] [ARM] 5581/1: U300 clock updates This adds a few default locks to the clocks (the clocks were used before the locks were initialized by code), then renames the clocks a bit to fit with the latest driver names (some changed during review). Lastly it moves the initialization of the clock debugfs entry to module_init() initcall level since the debugfs isn't up in core_initcall(). Signed-off-by: Linus Walleij Signed-off-by: Russell King --- arch/arm/mach-u300/clock.c | 121 ++++++++++++++++++++++++------------- 1 file changed, 80 insertions(+), 41 deletions(-) diff --git a/arch/arm/mach-u300/clock.c b/arch/arm/mach-u300/clock.c index 5cd04d6751b..111f7ea32b3 100644 --- a/arch/arm/mach-u300/clock.c +++ b/arch/arm/mach-u300/clock.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -702,6 +703,7 @@ static struct clk amba_clk = { .rate = 52000000, /* this varies! */ .hw_ctrld = true, .reset = false, + .lock = __SPIN_LOCK_UNLOCKED(amba_clk.lock), }; /* @@ -720,6 +722,7 @@ static struct clk cpu_clk = { .set_rate = clk_set_rate_cpuclk, .get_rate = clk_get_rate_cpuclk, .round_rate = clk_round_rate_cpuclk, + .lock = __SPIN_LOCK_UNLOCKED(cpu_clk.lock), }; static struct clk nandif_clk = { @@ -732,6 +735,7 @@ static struct clk nandif_clk = { .clk_val = U300_SYSCON_SBCER_NANDIF_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(nandif_clk.lock), }; static struct clk semi_clk = { @@ -744,6 +748,7 @@ static struct clk semi_clk = { .clk_val = U300_SYSCON_SBCER_SEMI_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(semi_clk.lock), }; #ifdef CONFIG_MACH_U300_BS335 @@ -758,6 +763,7 @@ static struct clk isp_clk = { .clk_val = U300_SYSCON_SBCER_ISP_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(isp_clk.lock), }; static struct clk cds_clk = { @@ -771,6 +777,7 @@ static struct clk cds_clk = { .clk_val = U300_SYSCON_SBCER_CDS_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(cds_clk.lock), }; #endif @@ -785,6 +792,7 @@ static struct clk dma_clk = { .clk_val = U300_SYSCON_SBCER_DMAC_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(dma_clk.lock), }; static struct clk aaif_clk = { @@ -798,6 +806,7 @@ static struct clk aaif_clk = { .clk_val = U300_SYSCON_SBCER_AAIF_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(aaif_clk.lock), }; static struct clk apex_clk = { @@ -811,6 +820,7 @@ static struct clk apex_clk = { .clk_val = U300_SYSCON_SBCER_APEX_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(apex_clk.lock), }; static struct clk video_enc_clk = { @@ -825,6 +835,7 @@ static struct clk video_enc_clk = { .clk_val = U300_SYSCON_SBCER_VIDEO_ENC_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(video_enc_clk.lock), }; static struct clk xgam_clk = { @@ -839,6 +850,7 @@ static struct clk xgam_clk = { .get_rate = clk_get_rate_xgamclk, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(xgam_clk.lock), }; /* This clock is used to activate the video encoder */ @@ -854,6 +866,7 @@ static struct clk ahb_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_ahb_clk, + .lock = __SPIN_LOCK_UNLOCKED(ahb_clk.lock), }; @@ -871,6 +884,7 @@ static struct clk ahb_subsys_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_ahb_clk, + .lock = __SPIN_LOCK_UNLOCKED(ahb_subsys_clk.lock), }; static struct clk intcon_clk = { @@ -882,6 +896,8 @@ static struct clk intcon_clk = { .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, .res_mask = U300_SYSCON_RRR_INTCON_RESET_EN, /* INTCON can be reset but not clock-gated */ + .lock = __SPIN_LOCK_UNLOCKED(intcon_clk.lock), + }; static struct clk mspro_clk = { @@ -895,6 +911,7 @@ static struct clk mspro_clk = { .clk_val = U300_SYSCON_SBCER_MSPRO_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(mspro_clk.lock), }; static struct clk emif_clk = { @@ -909,6 +926,7 @@ static struct clk emif_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_emif_clk, + .lock = __SPIN_LOCK_UNLOCKED(emif_clk.lock), }; @@ -926,6 +944,7 @@ static struct clk fast_clk = { .clk_val = U300_SYSCON_SBCER_FAST_BRIDGE_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(fast_clk.lock), }; static struct clk mmcsd_clk = { @@ -942,6 +961,7 @@ static struct clk mmcsd_clk = { .round_rate = clk_round_rate_mclk, .disable = syscon_clk_disable, .enable = syscon_clk_enable, + .lock = __SPIN_LOCK_UNLOCKED(mmcsd_clk.lock), }; static struct clk i2s0_clk = { @@ -956,6 +976,7 @@ static struct clk i2s0_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_i2s_i2c_spi, + .lock = __SPIN_LOCK_UNLOCKED(i2s0_clk.lock), }; static struct clk i2s1_clk = { @@ -970,6 +991,7 @@ static struct clk i2s1_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_i2s_i2c_spi, + .lock = __SPIN_LOCK_UNLOCKED(i2s1_clk.lock), }; static struct clk i2c0_clk = { @@ -984,6 +1006,7 @@ static struct clk i2c0_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_i2s_i2c_spi, + .lock = __SPIN_LOCK_UNLOCKED(i2c0_clk.lock), }; static struct clk i2c1_clk = { @@ -998,6 +1021,7 @@ static struct clk i2c1_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_i2s_i2c_spi, + .lock = __SPIN_LOCK_UNLOCKED(i2c1_clk.lock), }; static struct clk spi_clk = { @@ -1012,6 +1036,7 @@ static struct clk spi_clk = { .enable = syscon_clk_enable, .disable = syscon_clk_disable, .get_rate = clk_get_rate_i2s_i2c_spi, + .lock = __SPIN_LOCK_UNLOCKED(spi_clk.lock), }; #ifdef CONFIG_MACH_U300_BS335 @@ -1026,6 +1051,7 @@ static struct clk uart1_clk = { .clk_val = U300_SYSCON_SBCER_UART1_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(uart1_clk.lock), }; #endif @@ -1044,6 +1070,7 @@ static struct clk slow_clk = { .clk_val = U300_SYSCON_SBCER_SLOW_BRIDGE_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(slow_clk.lock), }; /* TODO: implement SYSCON clock? */ @@ -1055,6 +1082,7 @@ static struct clk wdog_clk = { .rate = 32768, .reset = false, /* This is always on, cannot be enabled/disabled or reset */ + .lock = __SPIN_LOCK_UNLOCKED(wdog_clk.lock), }; /* This one is hardwired to PLL13 */ @@ -1069,6 +1097,7 @@ static struct clk uart_clk = { .clk_val = U300_SYSCON_SBCER_UART_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(uart_clk.lock), }; static struct clk keypad_clk = { @@ -1082,6 +1111,7 @@ static struct clk keypad_clk = { .clk_val = U300_SYSCON_SBCER_KEYPAD_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(keypad_clk.lock), }; static struct clk gpio_clk = { @@ -1095,6 +1125,7 @@ static struct clk gpio_clk = { .clk_val = U300_SYSCON_SBCER_GPIO_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(gpio_clk.lock), }; static struct clk rtc_clk = { @@ -1106,6 +1137,7 @@ static struct clk rtc_clk = { .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, .res_mask = U300_SYSCON_RSR_RTC_RESET_EN, /* This clock is always on, cannot be enabled/disabled */ + .lock = __SPIN_LOCK_UNLOCKED(rtc_clk.lock), }; static struct clk bustr_clk = { @@ -1119,6 +1151,7 @@ static struct clk bustr_clk = { .clk_val = U300_SYSCON_SBCER_BTR_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(bustr_clk.lock), }; static struct clk evhist_clk = { @@ -1132,6 +1165,7 @@ static struct clk evhist_clk = { .clk_val = U300_SYSCON_SBCER_EH_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(evhist_clk.lock), }; static struct clk timer_clk = { @@ -1145,6 +1179,7 @@ static struct clk timer_clk = { .clk_val = U300_SYSCON_SBCER_ACC_TMR_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(timer_clk.lock), }; static struct clk app_timer_clk = { @@ -1158,6 +1193,7 @@ static struct clk app_timer_clk = { .clk_val = U300_SYSCON_SBCER_APP_TMR_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(app_timer_clk.lock), }; #ifdef CONFIG_MACH_U300_BS335 @@ -1172,6 +1208,7 @@ static struct clk ppm_clk = { .clk_val = U300_SYSCON_SBCER_PPM_CLK_EN, .enable = syscon_clk_enable, .disable = syscon_clk_disable, + .lock = __SPIN_LOCK_UNLOCKED(ppm_clk.lock), }; #endif @@ -1187,53 +1224,53 @@ static struct clk ppm_clk = { */ static struct clk_lookup lookups[] = { /* Connected directly to the AMBA bus */ - DEF_LOOKUP("amba", &amba_clk), - DEF_LOOKUP("cpu", &cpu_clk), - DEF_LOOKUP("nandif", &nandif_clk), - DEF_LOOKUP("semi", &semi_clk), + DEF_LOOKUP("amba", &amba_clk), + DEF_LOOKUP("cpu", &cpu_clk), + DEF_LOOKUP("fsmc", &nandif_clk), + DEF_LOOKUP("semi", &semi_clk), #ifdef CONFIG_MACH_U300_BS335 - DEF_LOOKUP("isp", &isp_clk), - DEF_LOOKUP("cds", &cds_clk), + DEF_LOOKUP("isp", &isp_clk), + DEF_LOOKUP("cds", &cds_clk), #endif - DEF_LOOKUP("dma", &dma_clk), - DEF_LOOKUP("aaif", &aaif_clk), - DEF_LOOKUP("apex", &apex_clk), + DEF_LOOKUP("dma", &dma_clk), + DEF_LOOKUP("msl", &aaif_clk), + DEF_LOOKUP("apex", &apex_clk), DEF_LOOKUP("video_enc", &video_enc_clk), - DEF_LOOKUP("xgam", &xgam_clk), - DEF_LOOKUP("ahb", &ahb_clk), + DEF_LOOKUP("xgam", &xgam_clk), + DEF_LOOKUP("ahb", &ahb_clk), /* AHB bridge clocks */ - DEF_LOOKUP("ahb", &ahb_subsys_clk), - DEF_LOOKUP("intcon", &intcon_clk), - DEF_LOOKUP("mspro", &mspro_clk), - DEF_LOOKUP("pl172", &emif_clk), + DEF_LOOKUP("ahb_subsys", &ahb_subsys_clk), + DEF_LOOKUP("intcon", &intcon_clk), + DEF_LOOKUP("mspro", &mspro_clk), + DEF_LOOKUP("pl172", &emif_clk), /* FAST bridge clocks */ - DEF_LOOKUP("fast", &fast_clk), - DEF_LOOKUP("mmci", &mmcsd_clk), + DEF_LOOKUP("fast", &fast_clk), + DEF_LOOKUP("mmci", &mmcsd_clk), /* * The .0 and .1 identifiers on these comes from the platform device * .id field and are assigned when the platform devices are registered. */ - DEF_LOOKUP("i2s.0", &i2s0_clk), - DEF_LOOKUP("i2s.1", &i2s1_clk), - DEF_LOOKUP("stddci2c.0", &i2c0_clk), - DEF_LOOKUP("stddci2c.1", &i2c1_clk), - DEF_LOOKUP("pl022", &spi_clk), + DEF_LOOKUP("i2s.0", &i2s0_clk), + DEF_LOOKUP("i2s.1", &i2s1_clk), + DEF_LOOKUP("stu300.0", &i2c0_clk), + DEF_LOOKUP("stu300.1", &i2c1_clk), + DEF_LOOKUP("pl022", &spi_clk), #ifdef CONFIG_MACH_U300_BS335 - DEF_LOOKUP("uart1", &uart1_clk), + DEF_LOOKUP("uart1", &uart1_clk), #endif /* SLOW bridge clocks */ - DEF_LOOKUP("slow", &slow_clk), - DEF_LOOKUP("wdog", &wdog_clk), - DEF_LOOKUP("uart0", &uart_clk), - DEF_LOOKUP("apptimer", &app_timer_clk), - DEF_LOOKUP("keypad", &keypad_clk), + DEF_LOOKUP("slow", &slow_clk), + DEF_LOOKUP("coh901327_wdog", &wdog_clk), + DEF_LOOKUP("uart0", &uart_clk), + DEF_LOOKUP("apptimer", &app_timer_clk), + DEF_LOOKUP("coh901461-keypad", &keypad_clk), DEF_LOOKUP("u300-gpio", &gpio_clk), - DEF_LOOKUP("rtc0", &rtc_clk), - DEF_LOOKUP("bustr", &bustr_clk), - DEF_LOOKUP("evhist", &evhist_clk), - DEF_LOOKUP("timer", &timer_clk), + DEF_LOOKUP("rtc-coh901331", &rtc_clk), + DEF_LOOKUP("bustr", &bustr_clk), + DEF_LOOKUP("evhist", &evhist_clk), + DEF_LOOKUP("timer", &timer_clk), #ifdef CONFIG_MACH_U300_BS335 - DEF_LOOKUP("ppm", &ppm_clk), + DEF_LOOKUP("ppm", &ppm_clk), #endif }; @@ -1427,16 +1464,20 @@ static const struct file_operations u300_clocks_operations = { .release = single_release, }; -static void init_clk_read_procfs(void) +static int __init init_clk_read_debugfs(void) { /* Expose a simple debugfs interface to view all clocks */ (void) debugfs_create_file("u300_clocks", S_IFREG | S_IRUGO, - NULL, NULL, &u300_clocks_operations); -} -#else -static inline void init_clk_read_procfs(void) -{ + NULL, NULL, + &u300_clocks_operations); + return 0; } +/* + * This needs to come in after the core_initcall() for the + * overall clocks, because debugfs is not available until + * the subsystems come up. + */ +module_init(init_clk_read_debugfs); #endif static int __init u300_clock_init(void) @@ -1462,8 +1503,6 @@ static int __init u300_clock_init(void) clk_register(); - init_clk_read_procfs(); - /* * Some of these may be on when we boot the system so make sure they * are turned OFF. From 1bc6f83813441d15a74dfa97966fb68fa1bdec76 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 2 Jul 2009 18:32:05 +0200 Subject: [PATCH 0110/1346] amd-iommu: set evt_buf_size correctly The setting of this variable got lost during the suspend/resume implementation. But keeping this variable zero causes a divide-by-zero error in the interrupt handler. This patch fixes this. Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu_init.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index ec72c7779d6..c1b17e97252 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -472,6 +472,8 @@ static u8 * __init alloc_event_buffer(struct amd_iommu *iommu) if (iommu->evt_buf == NULL) return NULL; + iommu->evt_buf_size = EVT_BUFFER_SIZE; + return iommu->evt_buf; } From 14f4654cbd531d48651e005cf05907c14bddb193 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 2 Jul 2009 17:58:19 +0200 Subject: [PATCH 0111/1346] perf_counter tools: Create new chain_for_each_child() iterator Iterating through children of a node in the callchain tree shows something that may be quite confusing at a first glance. The head is the children field of the parent and the list nodes are in the brothers field of the children. This is because the childs are linked to the parent as a list of "brothers" using the "children" list of the parent as a head: --------------- | Parent (head) |------------------------------------- --------------- | | | children | | | ----------- ----------- | | 1st child |---brother---| 2nd child |---brother----- ----------- ----------- This makes the following strange pattern often occuring: list_for_each_entry(child, &parent->children, brothers) { // do something with children } Abstract it to chain_for_each_child() to factorize and simplify this pattern. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246550301-8954-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/util/callchain.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 3dceabd9b5e..3c4a91fea62 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -16,6 +16,9 @@ #include "callchain.h" +#define chain_for_each_child(child, parent) \ + list_for_each_entry(child, &parent->children, brothers) + static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) @@ -46,7 +49,7 @@ void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node) { struct callchain_node *child; - list_for_each_entry(child, &node->children, brothers) + chain_for_each_child(child, node) sort_chain_to_rbtree(rb_root, child); if (node->hit) @@ -77,7 +80,7 @@ create_child(struct callchain_node *parent, bool inherit_children) list_splice(&parent->children, &new->children); INIT_LIST_HEAD(&parent->children); - list_for_each_entry(next, &new->children, brothers) + chain_for_each_child(next, new) next->parent = new; } list_add_tail(&new->brothers, &parent->children); @@ -173,7 +176,7 @@ __append_chain_children(struct callchain_node *root, struct ip_callchain *chain, struct callchain_node *rnode; /* lookup in childrens */ - list_for_each_entry(rnode, &root->children, brothers) { + chain_for_each_child(rnode, root) { unsigned int ret = __append_chain(rnode, chain, start, syms); if (!ret) From 5a4b181721375700124513cdd9f97056e1c66675 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 2 Jul 2009 17:58:20 +0200 Subject: [PATCH 0112/1346] perf_counter tools: Add new OPT_CALLBACK_DEFAULT option There is no predefined macro to create an option that can have a custom value or a default one if none is given. This patch provides a new helper OPT_CALLBACK_DEFAULT() which defines such kind of option. For example, considering an option -c, we want to get the default value in the following cases: perf command -c -d perf command -d -c And the foo value when it's given: perf command -c foo -d perf command -d -c foo That's also why PARSE_OPT_LASTARG_DEFAULT is extended here to support default values whatever the position of the option, not only in the end. Should it now be renamed to PARSE_OPT_ARG_DEFAULT ? Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo Cc: git@vger.kernel.org LKML-Reference: <1246550301-8954-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/util/parse-options.c | 3 ++- tools/perf/util/parse-options.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 9a897b7cce7..1bf67190c82 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -20,7 +20,8 @@ static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt, if (p->opt) { *arg = p->opt; p->opt = NULL; - } else if (p->argc == 1 && (opt->flags & PARSE_OPT_LASTARG_DEFAULT)) { + } else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 || + **(p->argv + 1) == '-')) { *arg = (const char *)opt->defval; } else if (p->argc > 1) { p->argc--; diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 15c8aba9c62..8aa3464c709 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -104,6 +104,8 @@ struct option { { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } #define OPT_CALLBACK(s, l, v, a, h, f) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) } +#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \ + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. From 4eb3e4788b8a5e220a0aeb590f88c28850726ebe Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 2 Jul 2009 17:58:21 +0200 Subject: [PATCH 0113/1346] perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 141 ++++++++++++++++++++++++++++++++++-- tools/perf/util/callchain.c | 51 ++++++++++--- tools/perf/util/callchain.h | 11 ++- 3 files changed, 185 insertions(+), 18 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b44476ca239..0ca46386d93 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -59,6 +59,7 @@ static regex_t parent_regex; static int exclude_other = 1; static int callchain; +static enum chain_mode callchain_mode; static u64 sample_type; @@ -787,8 +788,103 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) return cmp; } +static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask) +{ + int i; + size_t ret = 0; + + ret += fprintf(fp, "%s", " "); + + for (i = 0; i < depth; i++) + if (depth_mask & (1 << i)) + ret += fprintf(fp, "| "); + else + ret += fprintf(fp, " "); + + ret += fprintf(fp, "\n"); + + return ret; +} static size_t -callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples) +ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth, + int depth_mask, int count, u64 total_samples, + int hits) +{ + int i; + size_t ret = 0; + + ret += fprintf(fp, "%s", " "); + for (i = 0; i < depth; i++) { + if (depth_mask & (1 << i)) + ret += fprintf(fp, "|"); + else + ret += fprintf(fp, " "); + if (!count && i == depth - 1) { + double percent; + + percent = hits * 100.0 / total_samples; + ret += fprintf(fp, "--%2.2f%%-- ", percent); + } else + ret += fprintf(fp, "%s", " "); + } + if (chain->sym) + ret += fprintf(fp, "%s\n", chain->sym->name); + else + ret += fprintf(fp, "%p\n", (void *)(long)chain->ip); + + return ret; +} + +static size_t +callchain__fprintf_graph(FILE *fp, struct callchain_node *self, + u64 total_samples, int depth, int depth_mask) +{ + struct rb_node *node, *next; + struct callchain_node *child; + struct callchain_list *chain; + int new_depth_mask = depth_mask; + size_t ret = 0; + int i; + + node = rb_first(&self->rb_root); + while (node) { + child = rb_entry(node, struct callchain_node, rb_node); + + /* + * The depth mask manages the output of pipes that show + * the depth. We don't want to keep the pipes of the current + * level for the last child of this depth + */ + next = rb_next(node); + if (!next) + new_depth_mask &= ~(1 << (depth - 1)); + + /* + * But we keep the older depth mask for the line seperator + * to keep the level link until we reach the last child + */ + ret += ipchain__fprintf_graph_line(fp, depth, depth_mask); + i = 0; + list_for_each_entry(chain, &child->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + ret += ipchain__fprintf_graph(fp, chain, depth, + new_depth_mask, i++, + total_samples, + child->cumul_hit); + } + ret += callchain__fprintf_graph(fp, child, total_samples, + depth + 1, + new_depth_mask | (1 << depth)); + node = next; + } + + return ret; +} + +static size_t +callchain__fprintf_flat(FILE *fp, struct callchain_node *self, + u64 total_samples) { struct callchain_list *chain; size_t ret = 0; @@ -796,7 +892,7 @@ callchain__fprintf(FILE *fp, struct callchain_node *self, u64 total_samples) if (!self) return 0; - ret += callchain__fprintf(fp, self->parent, total_samples); + ret += callchain__fprintf_flat(fp, self->parent, total_samples); list_for_each_entry(chain, &self->val, list) { @@ -826,8 +922,13 @@ hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, chain = rb_entry(rb_node, struct callchain_node, rb_node); percent = chain->hit * 100.0 / total_samples; - ret += fprintf(fp, " %6.2f%%\n", percent); - ret += callchain__fprintf(fp, chain, total_samples); + if (callchain_mode == FLAT) { + ret += fprintf(fp, " %6.2f%%\n", percent); + ret += callchain__fprintf_flat(fp, chain, total_samples); + } else if (callchain_mode == GRAPH) { + ret += callchain__fprintf_graph(fp, chain, + total_samples, 1, 1); + } ret += fprintf(fp, "\n"); rb_node = rb_next(rb_node); } @@ -1129,8 +1230,12 @@ static void output__insert_entry(struct hist_entry *he) struct rb_node *parent = NULL; struct hist_entry *iter; - if (callchain) - sort_chain_to_rbtree(&he->sorted_chain, &he->callchain); + if (callchain) { + if (callchain_mode == FLAT) + sort_chain_flat(&he->sorted_chain, &he->callchain); + else if (callchain_mode == GRAPH) + sort_chain_graph(&he->sorted_chain, &he->callchain); + } while (*p != NULL) { parent = *p; @@ -1702,6 +1807,26 @@ done: return rc; } +static int +parse_callchain_opt(const struct option *opt __used, const char *arg, + int unset __used) +{ + callchain = 1; + + if (!arg) + return 0; + + if (!strncmp(arg, "graph", strlen(arg))) + callchain_mode = GRAPH; + + else if (!strncmp(arg, "flat", strlen(arg))) + callchain_mode = FLAT; + else + return -1; + + return 0; +} + static const char * const report_usage[] = { "perf report [] ", NULL @@ -1725,7 +1850,9 @@ static const struct option options[] = { "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &exclude_other, "Only display entries with parent-match"), - OPT_BOOLEAN('c', "callchain", &callchain, "Display callchains"), + OPT_CALLBACK_DEFAULT('c', "callchain", NULL, "output_type", + "Display callchains with output_type: flat, graph. " + "Default to flat", &parse_callchain_opt, "flat"), OPT_STRING('d', "dsos", &dso_list_str, "dso[,dso...]", "only consider symbols in these dsos"), OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]", diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 3c4a91fea62..a9873aafcd9 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -19,9 +19,9 @@ #define chain_for_each_child(child, parent) \ list_for_each_entry(child, &parent->children, brothers) - static void -rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) +rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, + enum chain_mode mode) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -31,10 +31,22 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) parent = *p; rnode = rb_entry(parent, struct callchain_node, rb_node); - if (rnode->hit < chain->hit) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; + switch (mode) { + case FLAT: + if (rnode->hit < chain->hit) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + break; + case GRAPH: + if (rnode->cumul_hit < chain->cumul_hit) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + break; + default: + break; + } } rb_link_node(&chain->rb_node, parent, p); @@ -45,15 +57,36 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain) * Once we get every callchains from the stream, we can now * sort them by hit */ -void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node) +void sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node) { struct callchain_node *child; chain_for_each_child(child, node) - sort_chain_to_rbtree(rb_root, child); + sort_chain_flat(rb_root, child); if (node->hit) - rb_insert_callchain(rb_root, node); + rb_insert_callchain(rb_root, node, FLAT); +} + +static void __sort_chain_graph(struct callchain_node *node) +{ + struct callchain_node *child; + + node->rb_root = RB_ROOT; + node->cumul_hit = node->hit; + + chain_for_each_child(child, node) { + __sort_chain_graph(child); + rb_insert_callchain(&node->rb_root, child, GRAPH); + node->cumul_hit += child->cumul_hit; + } +} + +void +sort_chain_graph(struct rb_root *rb_root, struct callchain_node *chain_root) +{ + __sort_chain_graph(chain_root); + rb_root->rb_node = chain_root->rb_root.rb_node; } /* diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index e9bd5e882f3..dfa56008d9a 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -6,15 +6,21 @@ #include #include "symbol.h" +enum chain_mode { + FLAT, + GRAPH +}; struct callchain_node { struct callchain_node *parent; struct list_head brothers; struct list_head children; struct list_head val; - struct rb_node rb_node; + struct rb_node rb_node; /* to sort nodes in an rbtree */ + struct rb_root rb_root; /* sorted tree of children */ unsigned int val_nr; u64 hit; + u64 cumul_hit; /* hit + hits of children */ }; struct callchain_list { @@ -32,5 +38,6 @@ static inline void callchain_init(struct callchain_node *node) void append_chain(struct callchain_node *root, struct ip_callchain *chain, struct symbol **syms); -void sort_chain_to_rbtree(struct rb_root *rb_root, struct callchain_node *node); +void sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node); +void sort_chain_graph(struct rb_root *rb_root, struct callchain_node *node); #endif From af2719415a5ceae06f2a6d33e78b555e64697fc8 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Tue, 30 Jun 2009 20:27:59 +0200 Subject: [PATCH 0114/1346] firewire: sbp2: add support for disks >2 TB (and 16 bytes long CDBs) Increase the command ORB data structure to transport up to 16 bytes long CDBs (instead of 12 bytes), and tell the SCSI mid layer about it. This is notably necessary for READ CAPACITY(16) and friends, i.e. support of large disks. Signed-off-by: Stefan Richter --- drivers/firewire/sbp2.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 2353643721c..d27cb058da8 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -200,6 +200,12 @@ static struct fw_device *target_device(struct sbp2_target *tgt) #define SBP2_RETRY_LIMIT 0xf /* 15 retries */ #define SBP2_CYCLE_LIMIT (0xc8 << 12) /* 200 125us cycles */ +/* + * There is no transport protocol limit to the CDB length, but we implement + * a fixed length only. 16 bytes is enough for disks larger than 2 TB. + */ +#define SBP2_MAX_CDB_SIZE 16 + /* * The default maximum s/g segment size of a FireWire controller is * usually 0x10000, but SBP-2 only allows 0xffff. Since buffers have to @@ -312,7 +318,7 @@ struct sbp2_command_orb { struct sbp2_pointer next; struct sbp2_pointer data_descriptor; __be32 misc; - u8 command_block[12]; + u8 command_block[SBP2_MAX_CDB_SIZE]; } request; struct scsi_cmnd *cmd; scsi_done_fn_t done; @@ -1146,6 +1152,8 @@ static int sbp2_probe(struct device *dev) if (fw_device_enable_phys_dma(device) < 0) goto fail_shost_put; + shost->max_cmd_len = SBP2_MAX_CDB_SIZE; + if (scsi_add_host(shost, &unit->device) < 0) goto fail_shost_put; From ebbb16bffa646f853899ef3fdc0ac7abab888703 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Tue, 30 Jun 2009 20:28:31 +0200 Subject: [PATCH 0115/1346] ieee1394: sbp2: add support for disks >2 TB (and 16 bytes long CDBs) Increase the command ORB data structure to transport up to 16 bytes long CDBs (instead of 12 bytes), and tell the SCSI mid layer about it. This is notably necessary for READ CAPACITY(16) and friends, i.e. support of large disks. Signed-off-by: Stefan Richter --- drivers/ieee1394/sbp2.c | 1 + drivers/ieee1394/sbp2.h | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c index a51ab233342..f599f493473 100644 --- a/drivers/ieee1394/sbp2.c +++ b/drivers/ieee1394/sbp2.c @@ -880,6 +880,7 @@ static struct sbp2_lu *sbp2_alloc_device(struct unit_directory *ud) } shost->hostdata[0] = (unsigned long)lu; + shost->max_cmd_len = SBP2_MAX_CDB_SIZE; if (!scsi_add_host(shost, &ud->device)) { lu->shost = shost; diff --git a/drivers/ieee1394/sbp2.h b/drivers/ieee1394/sbp2.h index c5036f1cc5b..64a3a66a8a3 100644 --- a/drivers/ieee1394/sbp2.h +++ b/drivers/ieee1394/sbp2.h @@ -24,6 +24,12 @@ #define SBP2_DEVICE_NAME "sbp2" +/* + * There is no transport protocol limit to the CDB length, but we implement + * a fixed length only. 16 bytes is enough for disks larger than 2 TB. + */ +#define SBP2_MAX_CDB_SIZE 16 + /* * SBP-2 specific definitions */ @@ -51,7 +57,7 @@ struct sbp2_command_orb { u32 data_descriptor_hi; u32 data_descriptor_lo; u32 misc; - u8 cdb[12]; + u8 cdb[SBP2_MAX_CDB_SIZE]; } __attribute__((packed)); #define SBP2_LOGIN_REQUEST 0x0 From c20ab37ef30f4a874cf27e84c12c73e584e6f5cc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 2 Jul 2009 20:14:33 +0200 Subject: [PATCH 0116/1346] perf_counter tools: Set the minimum percent for callchains to be displayed Callchains output may become a burden on a trace because even rarely hit site are exposed. This can be too much information. Let the user set a threshold as a minimum percent of hits using the new pattern for the -c option: -c mode,min_percent Example: $ perf report -s sym -c flat,4 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 5.39% [k] search_by_key 4.63% 0x00000000009e0a 2.36% [k] memcpy_c [...] $ perf report -s sym -c graph,2 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | --4.19%-- sys_pread64 | system_call_fastpath | pread64 | --3.24%-- generic_file_buffered_write __generic_file_aio_write_nolock generic_file_aio_write do_sync_write reiserfs_file_write vfs_write | --3.14%-- sys_pwrite64 system_call_fastpath __pwrite64 5.39% [k] search_by_key | --2.23%-- reiserfs_update_sd_size 4.63% 0x00000000009e0a 2.36% [k] memcpy_c [...] You can also omit it and it will default to 0. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246558475-10624-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 45 ++++++++++++++++++++++++++++--------- tools/perf/util/callchain.c | 19 +++++++++------- tools/perf/util/callchain.h | 6 +++-- 3 files changed, 49 insertions(+), 21 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0ca46386d93..e8c98179fe4 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -60,6 +60,7 @@ static regex_t parent_regex; static int exclude_other = 1; static int callchain; static enum chain_mode callchain_mode; +static double callchain_min_percent = 0.0; static u64 sample_type; @@ -1224,7 +1225,7 @@ static void collapse__resort(void) static struct rb_root output_hists; -static void output__insert_entry(struct hist_entry *he) +static void output__insert_entry(struct hist_entry *he, u64 min_callchain_hits) { struct rb_node **p = &output_hists.rb_node; struct rb_node *parent = NULL; @@ -1232,9 +1233,11 @@ static void output__insert_entry(struct hist_entry *he) if (callchain) { if (callchain_mode == FLAT) - sort_chain_flat(&he->sorted_chain, &he->callchain); + sort_chain_flat(&he->sorted_chain, &he->callchain, + min_callchain_hits); else if (callchain_mode == GRAPH) - sort_chain_graph(&he->sorted_chain, &he->callchain); + sort_chain_graph(&he->sorted_chain, &he->callchain, + min_callchain_hits); } while (*p != NULL) { @@ -1251,11 +1254,14 @@ static void output__insert_entry(struct hist_entry *he) rb_insert_color(&he->rb_node, &output_hists); } -static void output__resort(void) +static void output__resort(u64 total_samples) { struct rb_node *next; struct hist_entry *n; struct rb_root *tree = &hist; + u64 min_callchain_hits; + + min_callchain_hits = total_samples * (callchain_min_percent / 100); if (sort__need_collapse) tree = &collapse_hists; @@ -1267,7 +1273,7 @@ static void output__resort(void) next = rb_next(&n->rb_node); rb_erase(&n->rb_node, tree); - output__insert_entry(n); + output__insert_entry(n, min_callchain_hits); } } @@ -1801,7 +1807,7 @@ done: dsos__fprintf(stdout); collapse__resort(); - output__resort(); + output__resort(total); output__fprintf(stdout, total); return rc; @@ -1811,19 +1817,36 @@ static int parse_callchain_opt(const struct option *opt __used, const char *arg, int unset __used) { + char *tok; + char *endptr; + callchain = 1; if (!arg) return 0; - if (!strncmp(arg, "graph", strlen(arg))) + tok = strtok((char *)arg, ","); + if (!tok) + return -1; + + /* get the output mode */ + if (!strncmp(tok, "graph", strlen(arg))) callchain_mode = GRAPH; - else if (!strncmp(arg, "flat", strlen(arg))) + else if (!strncmp(tok, "flat", strlen(arg))) callchain_mode = FLAT; else return -1; + /* get the min percentage */ + tok = strtok(NULL, ","); + if (!tok) + return 0; + + callchain_min_percent = strtod(tok, &endptr); + if (tok == endptr) + return -1; + return 0; } @@ -1850,9 +1873,9 @@ static const struct option options[] = { "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &exclude_other, "Only display entries with parent-match"), - OPT_CALLBACK_DEFAULT('c', "callchain", NULL, "output_type", - "Display callchains with output_type: flat, graph. " - "Default to flat", &parse_callchain_opt, "flat"), + OPT_CALLBACK_DEFAULT('c', "callchain", NULL, "output_type,min_percent", + "Display callchains using output_type and min percent threshold. " + "Default: flat,0", &parse_callchain_opt, "flat,100"), OPT_STRING('d', "dsos", &dso_list_str, "dso[,dso...]", "only consider symbols in these dsos"), OPT_STRING('C', "comms", &comm_list_str, "comm[,comm...]", diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index a9873aafcd9..c9900fe6b8b 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -57,18 +57,19 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, * Once we get every callchains from the stream, we can now * sort them by hit */ -void sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node) +void sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node, + u64 min_hit) { struct callchain_node *child; chain_for_each_child(child, node) - sort_chain_flat(rb_root, child); + sort_chain_flat(rb_root, child, min_hit); - if (node->hit) + if (node->hit && node->hit >= min_hit) rb_insert_callchain(rb_root, node, FLAT); } -static void __sort_chain_graph(struct callchain_node *node) +static void __sort_chain_graph(struct callchain_node *node, u64 min_hit) { struct callchain_node *child; @@ -76,16 +77,18 @@ static void __sort_chain_graph(struct callchain_node *node) node->cumul_hit = node->hit; chain_for_each_child(child, node) { - __sort_chain_graph(child); - rb_insert_callchain(&node->rb_root, child, GRAPH); + __sort_chain_graph(child, min_hit); + if (child->cumul_hit >= min_hit) + rb_insert_callchain(&node->rb_root, child, GRAPH); node->cumul_hit += child->cumul_hit; } } void -sort_chain_graph(struct rb_root *rb_root, struct callchain_node *chain_root) +sort_chain_graph(struct rb_root *rb_root, struct callchain_node *chain_root, + u64 min_hit) { - __sort_chain_graph(chain_root); + __sort_chain_graph(chain_root, min_hit); rb_root->rb_node = chain_root->rb_root.rb_node; } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index dfa56008d9a..f3e4776e743 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -38,6 +38,8 @@ static inline void callchain_init(struct callchain_node *node) void append_chain(struct callchain_node *root, struct ip_callchain *chain, struct symbol **syms); -void sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node); -void sort_chain_graph(struct rb_root *rb_root, struct callchain_node *node); +void sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node, + u64 min_hit); +void sort_chain_graph(struct rb_root *rb_root, struct callchain_node *node, + u64 min_hit); #endif From 1e11fd82d247e4e48a1d6c49402214434538d3fd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 2 Jul 2009 20:14:34 +0200 Subject: [PATCH 0117/1346] perf_counter tools: Provide helper to print percents color Among perf annotate, perf report and perf top, we can find the common colored printing of percents according to the following rules: High overhead = > 5%, colored in red Mid overhead = > 0.5%, colored in green Low overhead = < 0.5%, default color Factorize these multiple checks in a single function named percent_color_fprintf() and also provide a get_percent_color() for sites which print percentages and other things at the same time. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246558475-10624-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-annotate.c | 26 ++------------------------ tools/perf/builtin-report.c | 21 +++------------------ tools/perf/builtin-top.c | 15 +-------------- tools/perf/util/color.c | 27 +++++++++++++++++++++++++++ tools/perf/util/color.h | 5 +++++ 5 files changed, 38 insertions(+), 56 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 08ea6c5329d..5f9eefecc57 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -25,10 +25,6 @@ #define SHOW_USER 2 #define SHOW_HV 4 -#define MIN_GREEN 0.5 -#define MIN_RED 5.0 - - static char const *input_name = "perf.data"; static char *vmlinux = "vmlinux"; @@ -1047,24 +1043,6 @@ process_event(event_t *event, unsigned long offset, unsigned long head) return 0; } -static char *get_color(double percent) -{ - char *color = PERF_COLOR_NORMAL; - - /* - * We color high-overhead entries in red, mid-overhead - * entries in green - and keep the low overhead places - * normal: - */ - if (percent >= MIN_RED) - color = PERF_COLOR_RED; - else { - if (percent > MIN_GREEN) - color = PERF_COLOR_GREEN; - } - return color; -} - static int parse_line(FILE *file, struct symbol *sym, u64 start, u64 len) { @@ -1126,7 +1104,7 @@ parse_line(FILE *file, struct symbol *sym, u64 start, u64 len) } else if (sym->hist_sum) percent = 100.0 * hits / sym->hist_sum; - color = get_color(percent); + color = get_percent_color(percent); /* * Also color the filename and line if needed, with @@ -1262,7 +1240,7 @@ static void print_summary(char *filename) sym_ext = rb_entry(node, struct sym_ext, node); percent = sym_ext->percent; - color = get_color(percent); + color = get_percent_color(percent); path = sym_ext->path; color_fprintf(stdout, color, " %7.2f %s", percent, path); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index e8c98179fe4..c9dbe331549 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -947,25 +947,10 @@ hist_entry__fprintf(FILE *fp, struct hist_entry *self, u64 total_samples) if (exclude_other && !self->parent) return 0; - if (total_samples) { - double percent = self->count * 100.0 / total_samples; - char *color = PERF_COLOR_NORMAL; - - /* - * We color high-overhead entries in red, mid-overhead - * entries in green - and keep the low overhead places - * normal: - */ - if (percent >= 5.0) { - color = PERF_COLOR_RED; - } else { - if (percent >= 0.5) - color = PERF_COLOR_GREEN; - } - - ret = color_fprintf(fp, color, " %6.2f%%", + if (total_samples) + ret = percent_color_fprintf(fp, " %6.2f%%", (self->count * 100.0) / total_samples); - } else + else ret = fprintf(fp, "%12Ld ", self->count); list_for_each_entry(se, &hist_entry__sort_list, list) { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index aa044ea1482..95d5c0ae375 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -239,7 +239,6 @@ static void print_sym_table(void) for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) { struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node); struct symbol *sym = (struct symbol *)(syme + 1); - char *color = PERF_COLOR_NORMAL; double pcnt; if (++printed > print_entries || syme->snap_count < count_filter) @@ -248,24 +247,12 @@ static void print_sym_table(void) pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) / sum_ksamples)); - /* - * We color high-overhead entries in red, mid-overhead - * entries in green - and keep the low overhead places - * normal: - */ - if (pcnt >= 5.0) { - color = PERF_COLOR_RED; - } else { - if (pcnt >= 0.5) - color = PERF_COLOR_GREEN; - } - if (nr_counters == 1) printf("%20.2f - ", syme->weight); else printf("%9.1f %10ld - ", syme->weight, syme->snap_count); - color_fprintf(stdout, color, "%4.1f%%", pcnt); + percent_color_fprintf(stdout, "%4.1f%%", pcnt); printf(" - %016llx : %s", sym->start, sym->name); if (sym->module) printf("\t[%s]", sym->module->name); diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 26f82318b86..90a044d1fe7 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -242,4 +242,31 @@ int color_fwrite_lines(FILE *fp, const char *color, return 0; } +char *get_percent_color(double percent) +{ + char *color = PERF_COLOR_NORMAL; + /* + * We color high-overhead entries in red, mid-overhead + * entries in green - and keep the low overhead places + * normal: + */ + if (percent >= MIN_RED) + color = PERF_COLOR_RED; + else { + if (percent > MIN_GREEN) + color = PERF_COLOR_GREEN; + } + return color; +} + +int percent_color_fprintf(FILE *fp, const char *fmt, double percent) +{ + int r; + char *color; + + color = get_percent_color(percent); + r = color_fprintf(fp, color, fmt, percent); + + return r; +} diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 5abfd379582..706cec50bd2 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -15,6 +15,9 @@ #define PERF_COLOR_CYAN "\033[36m" #define PERF_COLOR_BG_RED "\033[41m" +#define MIN_GREEN 0.5 +#define MIN_RED 5.0 + /* * This variable stores the value of color.ui */ @@ -32,5 +35,7 @@ void color_parse_mem(const char *value, int len, const char *var, char *dst); int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); +int percent_color_fprintf(FILE *fp, const char *fmt, double percent); +char *get_percent_color(double percent); #endif /* COLOR_H */ From 24b57c6988c5791628c89a8838910991abc9cc1e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 2 Jul 2009 20:14:35 +0200 Subject: [PATCH 0118/1346] perf_counter tools: Display percents of hits in callchain with overhead colors This adds the use of colors to signal at a glance the important overhead thresholds in callchains hit rates. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Anton Blanchard Cc: Arnaldo Carvalho de Melo LKML-Reference: <1246558475-10624-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c9dbe331549..283773d91aa 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -824,7 +824,7 @@ ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth, double percent; percent = hits * 100.0 / total_samples; - ret += fprintf(fp, "--%2.2f%%-- ", percent); + ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent); } else ret += fprintf(fp, "%s", " "); } @@ -924,7 +924,8 @@ hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, chain = rb_entry(rb_node, struct callchain_node, rb_node); percent = chain->hit * 100.0 / total_samples; if (callchain_mode == FLAT) { - ret += fprintf(fp, " %6.2f%%\n", percent); + ret += percent_color_fprintf(fp, " %6.2f%%\n", + percent); ret += callchain__fprintf_flat(fp, chain, total_samples); } else if (callchain_mode == GRAPH) { ret += callchain__fprintf_graph(fp, chain, From 66d9e2102af038bcd3286a6efce83e1877e5997b Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Sun, 28 Jun 2009 11:19:39 +0100 Subject: [PATCH 0119/1346] [ARM] 5576/1: Update kb9202_defconfig The default configuration file for the KwikByte kb9202 board was based on a 2.6.13-rc2 kernel and doesn't produce a bootable kernel. Update the configuration in order to produce a bootable image. Signed-off-by: Matthias Kaehlcke Signed-off-by: Russell King --- arch/arm/configs/kb9202_defconfig | 1206 +++++++++++++++++++++-------- 1 file changed, 866 insertions(+), 340 deletions(-) diff --git a/arch/arm/configs/kb9202_defconfig b/arch/arm/configs/kb9202_defconfig index 8e74c66f239..605a8462f17 100644 --- a/arch/arm/configs/kb9202_defconfig +++ b/arch/arm/configs/kb9202_defconfig @@ -1,109 +1,246 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.13-rc2 -# Sun Aug 14 19:26:59 2005 +# Linux kernel version: 2.6.30-rc8 +# Wed Jun 3 13:52:33 2009 # CONFIG_ARM=y +CONFIG_SYS_SUPPORTS_APM_EMULATION=y +CONFIG_GENERIC_GPIO=y +CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_MMU=y -CONFIG_UID16=y +# CONFIG_NO_IOPORT is not set +CONFIG_GENERIC_HARDIRQS=y +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_HAVE_LATENCYTOP_SUPPORT=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +CONFIG_HARDIRQS_SW_RESEND=y +CONFIG_GENERIC_IRQ_PROBE=y CONFIG_RWSEM_GENERIC_SPINLOCK=y +# CONFIG_ARCH_HAS_ILOG2_U32 is not set +# CONFIG_ARCH_HAS_ILOG2_U64 is not set +CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y - -# -# Code maturity level options -# -# CONFIG_EXPERIMENTAL is not set -CONFIG_CLEAN_COMPILE=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_INIT_ENV_ARG_LIMIT=32 +CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y +CONFIG_VECTORS_BASE=0xffff0000 +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # # General setup # +CONFIG_EXPERIMENTAL=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 CONFIG_LOCALVERSION="" +CONFIG_LOCALVERSION_AUTO=y # CONFIG_SWAP is not set -# CONFIG_SYSVIPC is not set -# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +CONFIG_POSIX_MQUEUE=y +CONFIG_POSIX_MQUEUE_SYSCTL=y +CONFIG_BSD_PROCESS_ACCT=y +# CONFIG_BSD_PROCESS_ACCT_V3 is not set +# CONFIG_TASKSTATS is not set +CONFIG_AUDIT=y + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=17 +# CONFIG_GROUP_SCHED is not set +# CONFIG_CGROUPS is not set +# CONFIG_SYSFS_DEPRECATED_V2 is not set +# CONFIG_RELAY is not set +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_IPC_NS is not set +# CONFIG_USER_NS is not set +# CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_RD_GZIP=y +CONFIG_RD_BZIP2=y +CONFIG_RD_LZMA=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -# CONFIG_KOBJECT_UEVENT is not set -# CONFIG_IKCONFIG is not set +CONFIG_ANON_INODES=y # CONFIG_EMBEDDED is not set +CONFIG_UID16=y +CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_KALLSYMS_EXTRA_PASS=y +# CONFIG_STRIP_ASM_SYMS is not set +CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y +CONFIG_ELF_CORE=y CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y -CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y +CONFIG_EVENTFD=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set +CONFIG_AIO=y +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLUB_DEBUG=y +CONFIG_COMPAT_BRK=y +# CONFIG_SLAB is not set +CONFIG_SLUB=y +# CONFIG_SLOB is not set +# CONFIG_PROFILING is not set +CONFIG_TRACEPOINTS=y +CONFIG_MARKERS=y +CONFIG_HAVE_OPROFILE=y +# CONFIG_KPROBES is not set +CONFIG_HAVE_KPROBES=y +CONFIG_HAVE_KRETPROBES=y +CONFIG_HAVE_CLK=y +# CONFIG_SLOW_WORK is not set +CONFIG_HAVE_GENERIC_DMA_COHERENT=y +CONFIG_SLABINFO=y +CONFIG_RT_MUTEXES=y CONFIG_BASE_SMALL=0 +CONFIG_MODULES=y +# CONFIG_MODULE_FORCE_LOAD is not set +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_BLOCK=y +# CONFIG_LBD is not set +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_BLK_DEV_INTEGRITY is not set # -# Loadable module support +# IO Schedulers # -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_OBSOLETE_MODPARM=y -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y +CONFIG_IOSCHED_NOOP=y +# CONFIG_IOSCHED_AS is not set +# CONFIG_IOSCHED_DEADLINE is not set +CONFIG_IOSCHED_CFQ=y +# CONFIG_DEFAULT_AS is not set +# CONFIG_DEFAULT_DEADLINE is not set +CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="cfq" +# CONFIG_FREEZER is not set # # System Type # -# CONFIG_ARCH_CLPS7500 is not set -# CONFIG_ARCH_CLPS711X is not set -# CONFIG_ARCH_CO285 is not set -# CONFIG_ARCH_EBSA110 is not set -# CONFIG_ARCH_FOOTBRIDGE is not set +# CONFIG_ARCH_AAEC2000 is not set # CONFIG_ARCH_INTEGRATOR is not set -# CONFIG_ARCH_IOP3XX is not set -# CONFIG_ARCH_IXP4XX is not set +# CONFIG_ARCH_REALVIEW is not set +# CONFIG_ARCH_VERSATILE is not set +CONFIG_ARCH_AT91=y +# CONFIG_ARCH_CLPS711X is not set +# CONFIG_ARCH_EBSA110 is not set +# CONFIG_ARCH_EP93XX is not set +# CONFIG_ARCH_GEMINI is not set +# CONFIG_ARCH_FOOTBRIDGE is not set +# CONFIG_ARCH_NETX is not set +# CONFIG_ARCH_H720X is not set +# CONFIG_ARCH_IMX is not set +# CONFIG_ARCH_IOP13XX is not set +# CONFIG_ARCH_IOP32X is not set +# CONFIG_ARCH_IOP33X is not set +# CONFIG_ARCH_IXP23XX is not set # CONFIG_ARCH_IXP2000 is not set +# CONFIG_ARCH_IXP4XX is not set # CONFIG_ARCH_L7200 is not set +# CONFIG_ARCH_KIRKWOOD is not set +# CONFIG_ARCH_KS8695 is not set +# CONFIG_ARCH_NS9XXX is not set +# CONFIG_ARCH_LOKI is not set +# CONFIG_ARCH_MV78XX0 is not set +# CONFIG_ARCH_MXC is not set +# CONFIG_ARCH_ORION5X is not set +# CONFIG_ARCH_PNX4008 is not set # CONFIG_ARCH_PXA is not set +# CONFIG_ARCH_MMP is not set # CONFIG_ARCH_RPC is not set # CONFIG_ARCH_SA1100 is not set # CONFIG_ARCH_S3C2410 is not set +# CONFIG_ARCH_S3C64XX is not set # CONFIG_ARCH_SHARK is not set # CONFIG_ARCH_LH7A40X is not set +# CONFIG_ARCH_DAVINCI is not set # CONFIG_ARCH_OMAP is not set -# CONFIG_ARCH_VERSATILE is not set -# CONFIG_ARCH_IMX is not set -# CONFIG_ARCH_H720X is not set -# CONFIG_ARCH_AAEC2000 is not set -CONFIG_ARCH_AT91=y -CONFIG_ARCH_AT91RM9200=y +# CONFIG_ARCH_MSM is not set +# CONFIG_ARCH_W90X900 is not set # -# AT91RM9200 Implementations +# Atmel AT91 System-on-Chip # +CONFIG_ARCH_AT91RM9200=y +# CONFIG_ARCH_AT91SAM9260 is not set +# CONFIG_ARCH_AT91SAM9261 is not set +# CONFIG_ARCH_AT91SAM9263 is not set +# CONFIG_ARCH_AT91SAM9RL is not set +# CONFIG_ARCH_AT91SAM9G20 is not set +# CONFIG_ARCH_AT91CAP9 is not set +# CONFIG_ARCH_AT91X40 is not set +CONFIG_AT91_PMC_UNIT=y + +# +# AT91RM9200 Board Type +# +# CONFIG_MACH_ONEARM is not set # CONFIG_ARCH_AT91RM9200DK is not set # CONFIG_MACH_AT91RM9200EK is not set # CONFIG_MACH_CSB337 is not set # CONFIG_MACH_CSB637 is not set # CONFIG_MACH_CARMEVA is not set +# CONFIG_MACH_ATEB9200 is not set CONFIG_MACH_KB9200=y +# CONFIG_MACH_PICOTUX2XX is not set +# CONFIG_MACH_KAFA is not set +# CONFIG_MACH_ECBAT91 is not set +# CONFIG_MACH_YL9200 is not set + +# +# AT91 Board Options +# + +# +# AT91 Feature Selections +# +CONFIG_AT91_PROGRAMMABLE_CLOCKS=y +CONFIG_AT91_TIMER_HZ=128 +CONFIG_AT91_EARLY_DBGU=y +# CONFIG_AT91_EARLY_USART0 is not set +# CONFIG_AT91_EARLY_USART1 is not set +# CONFIG_AT91_EARLY_USART2 is not set +# CONFIG_AT91_EARLY_USART3 is not set +# CONFIG_AT91_EARLY_USART4 is not set +# CONFIG_AT91_EARLY_USART5 is not set # # Processor Type # CONFIG_CPU_32=y CONFIG_CPU_ARM920T=y -CONFIG_CPU_32v4=y +CONFIG_CPU_32v4T=y CONFIG_CPU_ABRT_EV4T=y +CONFIG_CPU_PABRT_NOIFAR=y CONFIG_CPU_CACHE_V4WT=y CONFIG_CPU_CACHE_VIVT=y CONFIG_CPU_COPY_V4WB=y CONFIG_CPU_TLB_V4WBI=y +CONFIG_CPU_CP15=y +CONFIG_CPU_CP15_MMU=y # # Processor Features @@ -112,23 +249,48 @@ CONFIG_ARM_THUMB=y # CONFIG_CPU_ICACHE_DISABLE is not set # CONFIG_CPU_DCACHE_DISABLE is not set # CONFIG_CPU_DCACHE_WRITETHROUGH is not set +# CONFIG_OUTER_CACHE is not set # # Bus support # -CONFIG_ISA_DMA_API=y - -# -# PCCARD (PCMCIA/CardBus) support -# +# CONFIG_PCI_SYSCALL is not set +# CONFIG_ARCH_SUPPORTS_MSI is not set # CONFIG_PCCARD is not set # # Kernel Features # -# CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set +CONFIG_TICK_ONESHOT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y +CONFIG_VMSPLIT_3G=y +# CONFIG_VMSPLIT_2G is not set +# CONFIG_VMSPLIT_1G is not set +CONFIG_PAGE_OFFSET=0xC0000000 +CONFIG_PREEMPT=y +CONFIG_HZ=128 +CONFIG_AEABI=y +CONFIG_OABI_COMPAT=y +# CONFIG_ARCH_HAS_HOLES_MEMORYMODEL is not set +# CONFIG_ARCH_SPARSEMEM_DEFAULT is not set +# CONFIG_ARCH_SELECT_MEMORY_MODEL is not set +# CONFIG_HIGHMEM is not set +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set CONFIG_FLATMEM=y CONFIG_FLAT_NODE_MEM_MAP=y +CONFIG_PAGEFLAGS_EXTENDED=y +CONFIG_SPLIT_PTLOCK_CPUS=4096 +# CONFIG_PHYS_ADDR_T_64BIT is not set +CONFIG_ZONE_DMA_FLAG=0 +CONFIG_VIRT_TO_BUS=y +CONFIG_UNEVICTABLE_LRU=y +CONFIG_HAVE_MLOCK=y +CONFIG_HAVE_MLOCKED_PAGE_BIT=y # CONFIG_LEDS is not set CONFIG_ALIGNMENT_TRAP=y @@ -137,8 +299,16 @@ CONFIG_ALIGNMENT_TRAP=y # CONFIG_ZBOOT_ROM_TEXT=0x10000000 CONFIG_ZBOOT_ROM_BSS=0x20040000 -CONFIG_ZBOOT_ROM=y -CONFIG_CMDLINE="console=ttyS0,115200 root=/dev/ram rw initrd=0x20210000,654933" +# CONFIG_ZBOOT_ROM is not set +CONFIG_CMDLINE="noinitrd root=/dev/mtdblock0 rootfstype=jffs2 mem=64M" +# CONFIG_XIP_KERNEL is not set +CONFIG_KEXEC=y +CONFIG_ATAGS_PROC=y + +# +# CPU Power Management +# +# CONFIG_CPU_IDLE is not set # # Floating point emulation @@ -149,19 +319,93 @@ CONFIG_CMDLINE="console=ttyS0,115200 root=/dev/ram rw initrd=0x20210000,654933" # CONFIG_FPE_NWFPE=y # CONFIG_FPE_NWFPE_XP is not set +# CONFIG_FPE_FASTFPE is not set # # Userspace binary formats # CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_AOUT=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_HAVE_AOUT=y +# CONFIG_BINFMT_AOUT is not set CONFIG_BINFMT_MISC=y -# CONFIG_ARTHUR is not set # # Power management options # # CONFIG_PM is not set +CONFIG_ARCH_SUSPEND_POSSIBLE=y +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_FIB_HASH=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set +# CONFIG_INET_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +# CONFIG_INET_DIAG is not set +# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" +# CONFIG_TCP_MD5SIG is not set +# CONFIG_IPV6 is not set +# CONFIG_NETWORK_SECMARK is not set +# CONFIG_NETFILTER is not set +# CONFIG_IP_DCCP is not set +# CONFIG_IP_SCTP is not set +# CONFIG_TIPC is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_NET_DSA is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set +# CONFIG_PHONET is not set +# CONFIG_NET_SCHED is not set +# CONFIG_DCB is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_NET_DROP_MONITOR is not set +# CONFIG_HAMRADIO is not set +# CONFIG_CAN is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +# CONFIG_AF_RXRPC is not set +# CONFIG_WIRELESS is not set +# CONFIG_WIMAX is not set +# CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set # # Device Drivers @@ -170,53 +414,156 @@ CONFIG_BINFMT_MISC=y # # Generic Driver Options # +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set -CONFIG_DEBUG_DRIVER=y +CONFIG_FW_LOADER=y +# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_EXTRA_FIRMWARE="" +# CONFIG_DEBUG_DRIVER is not set +# CONFIG_DEBUG_DEVRES is not set +# CONFIG_SYS_HYPERVISOR is not set +# CONFIG_CONNECTOR is not set +CONFIG_MTD=y +# CONFIG_MTD_DEBUG is not set +CONFIG_MTD_CONCAT=y +CONFIG_MTD_PARTITIONS=y +# CONFIG_MTD_TESTS is not set +# CONFIG_MTD_REDBOOT_PARTS is not set +CONFIG_MTD_CMDLINE_PARTS=y +# CONFIG_MTD_AFS_PARTS is not set +# CONFIG_MTD_AR7_PARTS is not set # -# Memory Technology Devices (MTD) +# User Modules And Translation Layers # -# CONFIG_MTD is not set +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLKDEVS=y +CONFIG_MTD_BLOCK=y +# CONFIG_FTL is not set +# CONFIG_NFTL is not set +# CONFIG_INFTL is not set +# CONFIG_RFD_FTL is not set +# CONFIG_SSFDC is not set +# CONFIG_MTD_OOPS is not set # -# Parallel port support +# RAM/ROM/Flash chip drivers # +CONFIG_MTD_CFI=y +# CONFIG_MTD_JEDECPROBE is not set +CONFIG_MTD_GEN_PROBE=y +# CONFIG_MTD_CFI_ADV_OPTIONS is not set +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +# CONFIG_MTD_CFI_I4 is not set +# CONFIG_MTD_CFI_I8 is not set +CONFIG_MTD_CFI_INTELEXT=y +# CONFIG_MTD_CFI_AMDSTD is not set +# CONFIG_MTD_CFI_STAA is not set +CONFIG_MTD_CFI_UTIL=y +# CONFIG_MTD_RAM is not set +# CONFIG_MTD_ROM is not set +# CONFIG_MTD_ABSENT is not set + +# +# Mapping drivers for chip access +# +CONFIG_MTD_COMPLEX_MAPPINGS=y +CONFIG_MTD_PHYSMAP=y +# CONFIG_MTD_PHYSMAP_COMPAT is not set +# CONFIG_MTD_ARM_INTEGRATOR is not set +# CONFIG_MTD_PLATRAM is not set + +# +# Self-contained MTD device drivers +# +# CONFIG_MTD_SLRAM is not set +# CONFIG_MTD_PHRAM is not set +# CONFIG_MTD_MTDRAM is not set +# CONFIG_MTD_BLOCK2MTD is not set + +# +# Disk-On-Chip Device Drivers +# +# CONFIG_MTD_DOC2000 is not set +# CONFIG_MTD_DOC2001 is not set +# CONFIG_MTD_DOC2001PLUS is not set +CONFIG_MTD_NAND=y +# CONFIG_MTD_NAND_VERIFY_WRITE is not set +# CONFIG_MTD_NAND_ECC_SMC is not set +# CONFIG_MTD_NAND_MUSEUM_IDS is not set +# CONFIG_MTD_NAND_GPIO is not set +CONFIG_MTD_NAND_IDS=y +# CONFIG_MTD_NAND_DISKONCHIP is not set +CONFIG_MTD_NAND_ATMEL=y +# CONFIG_MTD_NAND_ATMEL_ECC_HW is not set +CONFIG_MTD_NAND_ATMEL_ECC_SOFT=y +# CONFIG_MTD_NAND_ATMEL_ECC_NONE is not set +# CONFIG_MTD_NAND_NANDSIM is not set +# CONFIG_MTD_NAND_PLATFORM is not set +# CONFIG_MTD_ALAUDA is not set +# CONFIG_MTD_ONENAND is not set + +# +# LPDDR flash memory drivers +# +# CONFIG_MTD_LPDDR is not set + +# +# UBI - Unsorted block images +# +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_WL_THRESHOLD=4096 +CONFIG_MTD_UBI_BEB_RESERVE=1 +CONFIG_MTD_UBI_GLUEBI=y + +# +# UBI debugging options +# +# CONFIG_MTD_UBI_DEBUG is not set # CONFIG_PARPORT is not set - -# -# Plug and Play support -# - -# -# Block devices -# +CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_COW_COMMON is not set CONFIG_BLK_DEV_LOOP=y # CONFIG_BLK_DEV_CRYPTOLOOP is not set -CONFIG_BLK_DEV_NBD=y +# CONFIG_BLK_DEV_NBD is not set # CONFIG_BLK_DEV_UB is not set CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" +CONFIG_BLK_DEV_RAM_SIZE=16384 +# CONFIG_BLK_DEV_XIP is not set # CONFIG_CDROM_PKTCDVD is not set +# CONFIG_ATA_OVER_ETH is not set +CONFIG_MISC_DEVICES=y +CONFIG_ATMEL_TCLIB=y +CONFIG_ATMEL_TCB_CLKSRC=y +CONFIG_ATMEL_TCB_CLKSRC_BLOCK=0 +CONFIG_ATMEL_SSC=y +# CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_C2PORT is not set # -# IO Schedulers +# EEPROM support # -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set +# CONFIG_EEPROM_93CX6 is not set +CONFIG_HAVE_IDE=y +# CONFIG_IDE is not set # # SCSI device support # +# CONFIG_RAID_ATTRS is not set CONFIG_SCSI=y +CONFIG_SCSI_DMA=y +# CONFIG_SCSI_TGT is not set +# CONFIG_SCSI_NETLINK is not set CONFIG_SCSI_PROC_FS=y # @@ -232,145 +579,87 @@ CONFIG_CHR_DEV_SG=y # # Some SCSI devices (e.g. CD jukebox) support multiple LUNs # -# CONFIG_SCSI_MULTI_LUN is not set -# CONFIG_SCSI_CONSTANTS is not set -# CONFIG_SCSI_LOGGING is not set +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y +# CONFIG_SCSI_SCAN_ASYNC is not set +CONFIG_SCSI_WAIT_SCAN=m # -# SCSI Transport Attributes +# SCSI Transports # -# CONFIG_SCSI_SPI_ATTRS is not set +CONFIG_SCSI_SPI_ATTRS=m # CONFIG_SCSI_FC_ATTRS is not set # CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -# CONFIG_SCSI_SATA is not set -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# +# CONFIG_SCSI_SAS_LIBSAS is not set +# CONFIG_SCSI_SRP_ATTRS is not set +# CONFIG_SCSI_LOWLEVEL is not set +# CONFIG_SCSI_DH is not set +# CONFIG_SCSI_OSD_INITIATOR is not set +# CONFIG_ATA is not set # CONFIG_MD is not set - -# -# Fusion MPT device support -# -# CONFIG_FUSION is not set - -# -# IEEE 1394 (FireWire) support -# - -# -# I2O device support -# - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -# CONFIG_NET_KEY is not set -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -# CONFIG_IP_ADVANCED_ROUTER is not set -CONFIG_IP_FIB_HASH=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_IP_MROUTE is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -# CONFIG_IP_TCPDIAG is not set -# CONFIG_IP_TCPDIAG_IPV6 is not set -# CONFIG_TCP_CONG_ADVANCED is not set -CONFIG_TCP_CONG_BIC=y -# CONFIG_IPV6 is not set -# CONFIG_NETFILTER is not set -# CONFIG_BRIDGE is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set CONFIG_NETDEVICES=y +CONFIG_COMPAT_NET_DEV_OPS=y # CONFIG_DUMMY is not set # CONFIG_BONDING is not set +# CONFIG_MACVLAN is not set # CONFIG_EQUALIZER is not set # CONFIG_TUN is not set - -# -# Ethernet (10 or 100Mbit) -# +# CONFIG_VETH is not set +# CONFIG_PHYLIB is not set CONFIG_NET_ETHERNET=y CONFIG_MII=y CONFIG_ARM_AT91_ETHER=y +# CONFIG_AX88796 is not set # CONFIG_SMC91X is not set # CONFIG_DM9000 is not set +# CONFIG_ETHOC is not set +# CONFIG_SMC911X is not set +# CONFIG_SMSC911X is not set +# CONFIG_DNET is not set +# CONFIG_IBM_NEW_EMAC_ZMII is not set +# CONFIG_IBM_NEW_EMAC_RGMII is not set +# CONFIG_IBM_NEW_EMAC_TAH is not set +# CONFIG_IBM_NEW_EMAC_EMAC4 is not set +# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set +# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set +# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set +# CONFIG_B44 is not set +# CONFIG_NETDEV_1000 is not set +# CONFIG_NETDEV_10000 is not set # -# Ethernet (1000 Mbit) +# Wireless LAN +# +# CONFIG_WLAN_PRE80211 is not set +# CONFIG_WLAN_80211 is not set + +# +# Enable WiMAX (Networking options) to see the WiMAX drivers # # -# Ethernet (10000 Mbit) -# - -# -# Token Ring devices -# - -# -# Wireless LAN (non-hamradio) -# -# CONFIG_NET_RADIO is not set - -# -# Wan interfaces +# USB Network Adapters # +# CONFIG_USB_CATC is not set +# CONFIG_USB_KAWETH is not set +# CONFIG_USB_PEGASUS is not set +# CONFIG_USB_RTL8150 is not set +# CONFIG_USB_USBNET is not set # CONFIG_WAN is not set # CONFIG_PPP is not set # CONFIG_SLIP is not set - -# -# ISDN subsystem -# +# CONFIG_NETCONSOLE is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set # CONFIG_ISDN is not set # # Input device support # CONFIG_INPUT=y +# CONFIG_INPUT_FF_MEMLESS is not set +# CONFIG_INPUT_POLLDEV is not set # # Userland interfaces @@ -380,7 +669,6 @@ CONFIG_INPUT_MOUSEDEV=y CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 # CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set # CONFIG_INPUT_EVDEV is not set # CONFIG_INPUT_EVBUG is not set @@ -390,23 +678,25 @@ CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TABLET is not set # CONFIG_INPUT_TOUCHSCREEN is not set # CONFIG_INPUT_MISC is not set # # Hardware I/O ports # -CONFIG_SERIO=y -# CONFIG_SERIO_SERPORT is not set -# CONFIG_SERIO_RAW is not set +# CONFIG_SERIO is not set # CONFIG_GAMEPORT is not set # # Character devices # CONFIG_VT=y +CONFIG_CONSOLE_TRANSLATIONS=y CONFIG_VT_CONSOLE=y CONFIG_HW_CONSOLE=y +# CONFIG_VT_HW_CONSOLE_BINDING is not set +CONFIG_DEVKMEM=y # CONFIG_SERIAL_NONSTANDARD is not set # @@ -419,159 +709,232 @@ CONFIG_HW_CONSOLE=y # CONFIG_SERIAL_ATMEL=y CONFIG_SERIAL_ATMEL_CONSOLE=y +CONFIG_SERIAL_ATMEL_PDC=y +# CONFIG_SERIAL_ATMEL_TTYAT is not set CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# +# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set +# CONFIG_LEGACY_PTYS is not set # CONFIG_IPMI_HANDLER is not set - -# -# Watchdog Cards -# -# CONFIG_WATCHDOG is not set -# CONFIG_NVRAM is not set -# CONFIG_RTC is not set -# CONFIG_AT91RM9200_RTC is not set -# CONFIG_DTLK is not set +# CONFIG_HW_RANDOM is not set # CONFIG_R3964 is not set - -# -# Ftape, the floppy tape device driver -# # CONFIG_RAW_DRIVER is not set - -# -# TPM devices -# -# CONFIG_AT91_SPI is not set - -# -# I2C support -# +# CONFIG_TCG_TPM is not set # CONFIG_I2C is not set +# CONFIG_SPI is not set +CONFIG_ARCH_REQUIRE_GPIOLIB=y +CONFIG_GPIOLIB=y +# CONFIG_DEBUG_GPIO is not set +# CONFIG_GPIO_SYSFS is not set # -# Misc devices +# Memory mapped GPIO expanders: # +# +# I2C GPIO expanders: +# + +# +# PCI GPIO expanders: +# + +# +# SPI GPIO expanders: +# +# CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set +# CONFIG_HWMON is not set +# CONFIG_THERMAL is not set +# CONFIG_THERMAL_HWMON is not set +CONFIG_WATCHDOG=y +# CONFIG_WATCHDOG_NOWAYOUT is not set + +# +# Watchdog Device Drivers +# +# CONFIG_SOFT_WATCHDOG is not set +CONFIG_AT91RM9200_WATCHDOG=y + +# +# USB-based Watchdog Cards +# +# CONFIG_USBPCWATCHDOG is not set +CONFIG_SSB_POSSIBLE=y + +# +# Sonics Silicon Backplane +# +# CONFIG_SSB is not set + +# +# Multifunction device drivers +# +# CONFIG_MFD_CORE is not set +# CONFIG_MFD_SM501 is not set +# CONFIG_MFD_ASIC3 is not set +# CONFIG_HTC_EGPIO is not set +# CONFIG_HTC_PASIC3 is not set +# CONFIG_MFD_TMIO is not set +# CONFIG_MFD_T7L66XB is not set +# CONFIG_MFD_TC6387XB is not set +# CONFIG_MFD_TC6393XB is not set + # # Multimedia devices # -# CONFIG_VIDEO_DEV is not set # -# Digital Video Broadcasting Devices +# Multimedia core support # -# CONFIG_DVB is not set +# CONFIG_VIDEO_DEV is not set +# CONFIG_DVB_CORE is not set +# CONFIG_VIDEO_MEDIA is not set + +# +# Multimedia drivers +# +# CONFIG_DAB is not set # # Graphics support # -# CONFIG_FB is not set +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +CONFIG_FB=y +# CONFIG_FIRMWARE_EDID is not set +# CONFIG_FB_DDC is not set +# CONFIG_FB_BOOT_VESA_SUPPORT is not set +# CONFIG_FB_CFB_FILLRECT is not set +# CONFIG_FB_CFB_COPYAREA is not set +# CONFIG_FB_CFB_IMAGEBLIT is not set +# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set +# CONFIG_FB_SYS_FILLRECT is not set +# CONFIG_FB_SYS_COPYAREA is not set +# CONFIG_FB_SYS_IMAGEBLIT is not set +# CONFIG_FB_FOREIGN_ENDIAN is not set +# CONFIG_FB_SYS_FOPS is not set +# CONFIG_FB_SVGALIB is not set +# CONFIG_FB_MACMODES is not set +# CONFIG_FB_BACKLIGHT is not set +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y + +# +# Frame buffer hardware drivers +# +# CONFIG_FB_S1D13XXX is not set +# CONFIG_FB_VIRTUAL is not set +# CONFIG_FB_METRONOME is not set +# CONFIG_FB_MB862XX is not set +# CONFIG_FB_BROADSHEET is not set +CONFIG_BACKLIGHT_LCD_SUPPORT=y +# CONFIG_LCD_CLASS_DEVICE is not set +CONFIG_BACKLIGHT_CLASS_DEVICE=y +# CONFIG_BACKLIGHT_GENERIC is not set + +# +# Display device support +# +# CONFIG_DISPLAY_SUPPORT is not set # # Console display driver support # # CONFIG_VGA_CONSOLE is not set CONFIG_DUMMY_CONSOLE=y - -# -# Sound -# +CONFIG_FRAMEBUFFER_CONSOLE=y +# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set +# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set +CONFIG_FONTS=y +# CONFIG_FONT_8x8 is not set +# CONFIG_FONT_8x16 is not set +# CONFIG_FONT_6x11 is not set +# CONFIG_FONT_7x14 is not set +# CONFIG_FONT_PEARL_8x8 is not set +# CONFIG_FONT_ACORN_8x8 is not set +CONFIG_FONT_MINI_4x6=y +# CONFIG_FONT_SUN8x16 is not set +# CONFIG_FONT_SUN12x22 is not set +# CONFIG_FONT_10x18 is not set +# CONFIG_LOGO is not set # CONFIG_SOUND is not set - -# -# USB support -# +# CONFIG_HID_SUPPORT is not set +CONFIG_USB_SUPPORT=y CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB_ARCH_HAS_OHCI=y +# CONFIG_USB_ARCH_HAS_EHCI is not set CONFIG_USB=y -CONFIG_USB_DEBUG=y +# CONFIG_USB_DEBUG is not set +# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set # # Miscellaneous USB options # CONFIG_USB_DEVICEFS=y +CONFIG_USB_DEVICE_CLASS=y +# CONFIG_USB_DYNAMIC_MINORS is not set +# CONFIG_USB_OTG is not set +# CONFIG_USB_MON is not set +# CONFIG_USB_WUSB is not set +# CONFIG_USB_WUSB_CBAF is not set # # USB Host Controller Drivers # +# CONFIG_USB_C67X00_HCD is not set +# CONFIG_USB_OXU210HP_HCD is not set # CONFIG_USB_ISP116X_HCD is not set +# CONFIG_USB_ISP1760_HCD is not set CONFIG_USB_OHCI_HCD=y -# CONFIG_USB_OHCI_BIG_ENDIAN is not set +# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set +# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set CONFIG_USB_OHCI_LITTLE_ENDIAN=y # CONFIG_USB_SL811_HCD is not set +# CONFIG_USB_R8A66597_HCD is not set +# CONFIG_USB_HWA_HCD is not set +# CONFIG_USB_MUSB_HDRC is not set # # USB Device Class drivers # -# CONFIG_USB_BLUETOOTH_TTY is not set # CONFIG_USB_ACM is not set # CONFIG_USB_PRINTER is not set +# CONFIG_USB_WDM is not set +# CONFIG_USB_TMC is not set # -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information +# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may +# + +# +# also be needed; see USB_STORAGE Help for more info # CONFIG_USB_STORAGE=y -CONFIG_USB_STORAGE_DEBUG=y +# CONFIG_USB_STORAGE_DEBUG is not set +# CONFIG_USB_STORAGE_DATAFAB is not set # CONFIG_USB_STORAGE_FREECOM is not set -# CONFIG_USB_STORAGE_DPCM is not set - -# -# USB Input Devices -# -# CONFIG_USB_HID is not set - -# -# USB HID Boot Protocol drivers -# -# CONFIG_USB_KBD is not set -# CONFIG_USB_MOUSE is not set -# CONFIG_USB_AIPTEK is not set -# CONFIG_USB_WACOM is not set -# CONFIG_USB_ACECAD is not set -# CONFIG_USB_KBTAB is not set -# CONFIG_USB_POWERMATE is not set -# CONFIG_USB_MTOUCH is not set -# CONFIG_USB_ITMTOUCH is not set -# CONFIG_USB_EGALAX is not set -# CONFIG_USB_XPAD is not set -# CONFIG_USB_ATI_REMOTE is not set +# CONFIG_USB_STORAGE_ISD200 is not set +# CONFIG_USB_STORAGE_USBAT is not set +# CONFIG_USB_STORAGE_SDDR09 is not set +# CONFIG_USB_STORAGE_SDDR55 is not set +# CONFIG_USB_STORAGE_JUMPSHOT is not set +# CONFIG_USB_STORAGE_ALAUDA is not set +# CONFIG_USB_STORAGE_ONETOUCH is not set +# CONFIG_USB_STORAGE_KARMA is not set +# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set +CONFIG_USB_LIBUSUAL=y # # USB Imaging devices # +# CONFIG_USB_MDC800 is not set # CONFIG_USB_MICROTEK is not set -# -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set - -# -# Video4Linux support is needed for USB Multimedia device support -# - -# -# USB Network Adapters -# -# CONFIG_USB_KAWETH is not set -# CONFIG_USB_PEGASUS is not set -# CONFIG_USB_USBNET is not set -# CONFIG_USB_MON is not set - # # USB port drivers # - -# -# USB Serial Converter support -# # CONFIG_USB_SERIAL is not set # @@ -579,55 +942,129 @@ CONFIG_USB_STORAGE_DEBUG=y # # CONFIG_USB_EMI62 is not set # CONFIG_USB_EMI26 is not set +# CONFIG_USB_ADUTUX is not set +# CONFIG_USB_SEVSEG is not set +# CONFIG_USB_RIO500 is not set +# CONFIG_USB_LEGOTOWER is not set # CONFIG_USB_LCD is not set +# CONFIG_USB_BERRY_CHARGE is not set # CONFIG_USB_LED is not set +# CONFIG_USB_CYPRESS_CY7C63 is not set # CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGETKIT is not set -# CONFIG_USB_PHIDGETSERVO is not set # CONFIG_USB_IDMOUSE is not set - -# -# USB DSL modem support -# - -# -# USB Gadget Support -# +# CONFIG_USB_FTDI_ELAN is not set +# CONFIG_USB_APPLEDISPLAY is not set +# CONFIG_USB_LD is not set +# CONFIG_USB_TRANCEVIBRATOR is not set +# CONFIG_USB_IOWARRIOR is not set +# CONFIG_USB_TEST is not set +# CONFIG_USB_ISIGHTFW is not set +# CONFIG_USB_VST is not set # CONFIG_USB_GADGET is not set # -# MMC/SD Card support +# OTG and related infrastructure # -# CONFIG_MMC is not set +# CONFIG_USB_GPIO_VBUS is not set +# CONFIG_NOP_USB_XCEIV is not set +CONFIG_MMC=y +# CONFIG_MMC_DEBUG is not set +# CONFIG_MMC_UNSAFE_RESUME is not set + +# +# MMC/SD/SDIO Card Drivers +# +CONFIG_MMC_BLOCK=y +CONFIG_MMC_BLOCK_BOUNCE=y +# CONFIG_SDIO_UART is not set +# CONFIG_MMC_TEST is not set + +# +# MMC/SD/SDIO Host Controller Drivers +# +# CONFIG_MMC_SDHCI is not set +CONFIG_MMC_AT91=y +# CONFIG_MEMSTICK is not set +# CONFIG_ACCESSIBILITY is not set +# CONFIG_NEW_LEDS is not set +CONFIG_RTC_LIB=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_HCTOSYS=y +CONFIG_RTC_HCTOSYS_DEVICE="rtc0" +# CONFIG_RTC_DEBUG is not set + +# +# RTC interfaces +# +CONFIG_RTC_INTF_SYSFS=y +CONFIG_RTC_INTF_PROC=y +CONFIG_RTC_INTF_DEV=y +# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set +# CONFIG_RTC_DRV_TEST is not set + +# +# SPI RTC drivers +# + +# +# Platform RTC drivers +# +# CONFIG_RTC_DRV_CMOS is not set +# CONFIG_RTC_DRV_DS1286 is not set +# CONFIG_RTC_DRV_DS1511 is not set +# CONFIG_RTC_DRV_DS1553 is not set +# CONFIG_RTC_DRV_DS1742 is not set +# CONFIG_RTC_DRV_STK17TA8 is not set +# CONFIG_RTC_DRV_M48T86 is not set +# CONFIG_RTC_DRV_M48T35 is not set +# CONFIG_RTC_DRV_M48T59 is not set +# CONFIG_RTC_DRV_BQ4802 is not set +# CONFIG_RTC_DRV_V3020 is not set + +# +# on-CPU RTC drivers +# +CONFIG_RTC_DRV_AT91RM9200=y +# CONFIG_DMADEVICES is not set +# CONFIG_AUXDISPLAY is not set +# CONFIG_REGULATOR is not set +# CONFIG_UIO is not set +# CONFIG_STAGING is not set # # File systems # CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -# CONFIG_EXT2_FS_POSIX_ACL is not set -# CONFIG_EXT2_FS_SECURITY is not set +# CONFIG_EXT2_FS_XATTR is not set # CONFIG_EXT2_FS_XIP is not set CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set CONFIG_EXT3_FS_XATTR=y # CONFIG_EXT3_FS_POSIX_ACL is not set # CONFIG_EXT3_FS_SECURITY is not set +# CONFIG_EXT4_FS is not set CONFIG_JBD=y # CONFIG_JBD_DEBUG is not set CONFIG_FS_MBCACHE=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set +# CONFIG_FS_POSIX_ACL is not set +CONFIG_FILE_LOCKING=y +# CONFIG_XFS_FS is not set +# CONFIG_OCFS2_FS is not set +# CONFIG_BTRFS_FS is not set +# CONFIG_DNOTIFY is not set +CONFIG_INOTIFY=y +CONFIG_INOTIFY_USER=y +# CONFIG_QUOTA is not set +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set # -# XFS support +# Caches # -# CONFIG_XFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=y -CONFIG_AUTOFS4_FS=y +# CONFIG_FSCACHE is not set # # CD-ROM/DVD Filesystems @@ -639,7 +1076,7 @@ CONFIG_AUTOFS4_FS=y # DOS/FAT/NT Filesystems # CONFIG_FAT_FS=y -CONFIG_MSDOS_FS=y +# CONFIG_MSDOS_FS is not set CONFIG_VFAT_FS=y CONFIG_FAT_DEFAULT_CODEPAGE=437 CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" @@ -649,53 +1086,70 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" # Pseudo filesystems # CONFIG_PROC_FS=y +CONFIG_PROC_SYSCTL=y +CONFIG_PROC_PAGE_MONITOR=y CONFIG_SYSFS=y -CONFIG_DEVPTS_FS_XATTR=y -# CONFIG_DEVPTS_FS_SECURITY is not set CONFIG_TMPFS=y -# CONFIG_TMPFS_XATTR is not set +# CONFIG_TMPFS_POSIX_ACL is not set # CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# +CONFIG_CONFIGFS_FS=y +CONFIG_MISC_FILESYSTEMS=y +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set # CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +CONFIG_JFFS2_FS=y +CONFIG_JFFS2_FS_DEBUG=0 +CONFIG_JFFS2_FS_WRITEBUFFER=y +# CONFIG_JFFS2_FS_WBUF_VERIFY is not set +# CONFIG_JFFS2_SUMMARY is not set +# CONFIG_JFFS2_FS_XATTR is not set +# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set +CONFIG_JFFS2_ZLIB=y +# CONFIG_JFFS2_LZO is not set +CONFIG_JFFS2_RTIME=y +# CONFIG_JFFS2_RUBIN is not set +# CONFIG_UBIFS_FS is not set # CONFIG_CRAMFS is not set +# CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_OMFS_FS is not set # CONFIG_HPFS_FS is not set # CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set - -# -# Network File Systems -# +# CONFIG_NILFS2_FS is not set +CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y # CONFIG_NFS_V3_ACL is not set -# CONFIG_NFSD is not set +# CONFIG_NFS_V4 is not set CONFIG_ROOT_NFS=y +# CONFIG_NFSD is not set CONFIG_LOCKD=y CONFIG_LOCKD_V4=y CONFIG_NFS_COMMON=y CONFIG_SUNRPC=y +# CONFIG_RPCSEC_GSS_KRB5 is not set +# CONFIG_RPCSEC_GSS_SPKM3 is not set # CONFIG_SMB_FS is not set # CONFIG_CIFS is not set # CONFIG_NCP_FS is not set # CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set # # Partition Types # # CONFIG_PARTITION_ADVANCED is not set CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# CONFIG_NLS=y -CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_DEFAULT="iso8859-1" CONFIG_NLS_CODEPAGE_437=y # CONFIG_NLS_CODEPAGE_737 is not set # CONFIG_NLS_CODEPAGE_775 is not set @@ -719,7 +1173,7 @@ CONFIG_NLS_CODEPAGE_437=y # CONFIG_NLS_ISO8859_8 is not set # CONFIG_NLS_CODEPAGE_1250 is not set # CONFIG_NLS_CODEPAGE_1251 is not set -CONFIG_NLS_ASCII=y +# CONFIG_NLS_ASCII is not set # CONFIG_NLS_ISO8859_1 is not set # CONFIG_NLS_ISO8859_2 is not set # CONFIG_NLS_ISO8859_3 is not set @@ -733,47 +1187,119 @@ CONFIG_NLS_ASCII=y # CONFIG_NLS_ISO8859_15 is not set # CONFIG_NLS_KOI8_R is not set # CONFIG_NLS_KOI8_U is not set -# CONFIG_NLS_UTF8 is not set +CONFIG_NLS_UTF8=y +# CONFIG_DLM is not set # # Kernel hacking # # CONFIG_PRINTK_TIME is not set +CONFIG_ENABLE_WARN_DEPRECATED=y +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_WARN=1024 +CONFIG_MAGIC_SYSRQ=y +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_DEBUG_FS=y +# CONFIG_HEADERS_CHECK is not set CONFIG_DEBUG_KERNEL=y -# CONFIG_MAGIC_SYSRQ is not set -CONFIG_LOG_BUF_SHIFT=14 +# CONFIG_DEBUG_SHIRQ is not set +CONFIG_DETECT_SOFTLOCKUP=y +# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 +CONFIG_DETECT_HUNG_TASK=y +# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 +# CONFIG_SCHED_DEBUG is not set # CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set +# CONFIG_TIMER_STATS is not set +# CONFIG_DEBUG_OBJECTS is not set +# CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set +# CONFIG_DEBUG_PREEMPT is not set +# CONFIG_DEBUG_RT_MUTEXES is not set +# CONFIG_RT_MUTEX_TESTER is not set # CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_MUTEXES is not set +# CONFIG_DEBUG_LOCK_ALLOC is not set +# CONFIG_PROVE_LOCKING is not set +# CONFIG_LOCK_STAT is not set # CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set # CONFIG_DEBUG_KOBJECT is not set CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -CONFIG_FRAME_POINTER=y -CONFIG_DEBUG_USER=y -CONFIG_DEBUG_ERRORS=y -CONFIG_DEBUG_LL=y -# CONFIG_DEBUG_ICEDCC is not set +# CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set +CONFIG_DEBUG_MEMORY_INIT=y +# CONFIG_DEBUG_LIST is not set +# CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set +# CONFIG_BOOT_PRINTK_DELAY is not set +# CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_RCU_CPU_STALL_DETECTOR is not set +# CONFIG_BACKTRACE_SELF_TEST is not set +# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set +# CONFIG_FAULT_INJECTION is not set +# CONFIG_LATENCYTOP is not set +# CONFIG_SYSCTL_SYSCALL_CHECK is not set +# CONFIG_PAGE_POISONING is not set +CONFIG_HAVE_FUNCTION_TRACER=y +CONFIG_TRACING_SUPPORT=y + +# +# Tracers +# +# CONFIG_FUNCTION_TRACER is not set +# CONFIG_IRQSOFF_TRACER is not set +# CONFIG_PREEMPT_TRACER is not set +# CONFIG_SCHED_TRACER is not set +# CONFIG_CONTEXT_SWITCH_TRACER is not set +# CONFIG_EVENT_TRACER is not set +# CONFIG_BOOT_TRACER is not set +# CONFIG_TRACE_BRANCH_PROFILING is not set +# CONFIG_STACK_TRACER is not set +# CONFIG_KMEMTRACE is not set +# CONFIG_WORKQUEUE_TRACER is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_DYNAMIC_DEBUG is not set +# CONFIG_SAMPLES is not set +CONFIG_HAVE_ARCH_KGDB=y +# CONFIG_KGDB is not set +CONFIG_ARM_UNWIND=y +# CONFIG_DEBUG_USER is not set +# CONFIG_DEBUG_ERRORS is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_DEBUG_LL is not set # # Security options # # CONFIG_KEYS is not set # CONFIG_SECURITY is not set - -# -# Cryptographic options -# +# CONFIG_SECURITYFS is not set +# CONFIG_SECURITY_FILE_CAPABILITIES is not set # CONFIG_CRYPTO is not set - -# -# Hardware crypto devices -# +# CONFIG_BINARY_PRINTF is not set # # Library routines # +CONFIG_BITREVERSE=y +CONFIG_GENERIC_FIND_LAST_BIT=y # CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +# CONFIG_CRC_T10DIF is not set +# CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y +# CONFIG_CRC7 is not set # CONFIG_LIBCRC32C is not set +CONFIG_AUDIT_GENERIC=y +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=y +CONFIG_DECOMPRESS_GZIP=y +CONFIG_DECOMPRESS_BZIP2=y +CONFIG_DECOMPRESS_LZMA=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_IOPORT=y +CONFIG_HAS_DMA=y +CONFIG_NLATTR=y From b3d254955fb5797232ec329b136c363aa4fdaa05 Mon Sep 17 00:00:00 2001 From: Keith Packard Date: Wed, 24 Jun 2009 23:09:15 -0700 Subject: [PATCH 0120/1346] drm/i915: Adjust DisplayPort clocks to use 96MHz reference For some reason, the DP clocks were based off a 100MHz reference instead of the standard 96MHz reference. This caused some DP monitors to fail to lock to the signal. Signed-off-by: Keith Packard Signed-off-by: Eric Anholt --- drivers/gpu/drm/i915/intel_display.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 59de4951b6e..508838ee31e 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -816,24 +816,21 @@ intel_find_pll_g4x_dp(const intel_limit_t *limit, struct drm_crtc *crtc, { intel_clock_t clock; if (target < 200000) { - clock.dot = 161670; - clock.p = 20; clock.p1 = 2; clock.p2 = 10; - clock.n = 0x01; - clock.m = 97; - clock.m1 = 0x10; - clock.m2 = 0x05; + clock.n = 2; + clock.m1 = 23; + clock.m2 = 8; } else { - clock.dot = 270000; - clock.p = 10; clock.p1 = 1; clock.p2 = 10; - clock.n = 0x02; - clock.m = 108; - clock.m1 = 0x12; - clock.m2 = 0x06; + clock.n = 1; + clock.m1 = 14; + clock.m2 = 2; } + clock.m = 5 * (clock.m1 + 2) + (clock.m2 + 2); + clock.p = (clock.p1 * clock.p2); + clock.dot = 96000 * clock.m / (clock.n + 2) / clock.p; memcpy(best_clock, &clock, sizeof(intel_clock_t)); return true; } From 47220f623c3216ca276bad517ed208ea2ffceaa2 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 3 Jul 2009 13:08:28 +0900 Subject: [PATCH 0121/1346] sh: define PERF_COUNTER_INDEX_OFFSET. Fixes up recent build breakage. Signed-off-by: Paul Mundt --- arch/sh/include/asm/perf_counter.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/sh/include/asm/perf_counter.h b/arch/sh/include/asm/perf_counter.h index 61c2b40c802..d8e6bb9c0cc 100644 --- a/arch/sh/include/asm/perf_counter.h +++ b/arch/sh/include/asm/perf_counter.h @@ -4,4 +4,6 @@ /* SH only supports software counters through this interface. */ static inline void set_perf_counter_pending(void) {} +#define PERF_COUNTER_INDEX_OFFSET 0 + #endif /* __ASM_SH_PERF_COUNTER_H */ From 7eeff4814224646c896303ba2c2b7ac3c4240cd2 Mon Sep 17 00:00:00 2001 From: Matt Reimer Date: Mon, 15 Jun 2009 13:21:25 -0700 Subject: [PATCH 0122/1346] pxamci: correct DMA flow control The DMA flow control in pxamci_setup_data() is backwards; fix it. Signed-off-by: Matt Reimer Acked-by: Robert Jarzmik Signed-off-by: Eric Miao --- drivers/mmc/host/pxamci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index d7d7109ef47..e55ac792d68 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -168,12 +168,12 @@ static void pxamci_setup_data(struct pxamci_host *host, struct mmc_data *data) if (data->flags & MMC_DATA_READ) { host->dma_dir = DMA_FROM_DEVICE; - dcmd = DCMD_INCTRGADDR | DCMD_FLOWTRG; + dcmd = DCMD_INCTRGADDR | DCMD_FLOWSRC; DRCMR(host->dma_drcmrtx) = 0; DRCMR(host->dma_drcmrrx) = host->dma | DRCMR_MAPVLD; } else { host->dma_dir = DMA_TO_DEVICE; - dcmd = DCMD_INCSRCADDR | DCMD_FLOWSRC; + dcmd = DCMD_INCSRCADDR | DCMD_FLOWTRG; DRCMR(host->dma_drcmrrx) = 0; DRCMR(host->dma_drcmrtx) = host->dma | DRCMR_MAPVLD; } From 5c68b09900f04c3de55af43155435b9392f03844 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 22 Jun 2009 21:01:58 +0200 Subject: [PATCH 0123/1346] [ARM] pxa: correct I2CPWR clock for pxa3xx In commit f23d4911319fd, the pwr-i2c device name changed due to the newly introduced device table. This patch fixes the clock so the driver's probe will succeed again. Signed-off-by: Daniel Mack Acked-by: Russell King Signed-off-by: Eric Miao --- arch/arm/mach-pxa/pxa3xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c index 6f678d93bf4..09b7b1a10ca 100644 --- a/arch/arm/mach-pxa/pxa3xx.c +++ b/arch/arm/mach-pxa/pxa3xx.c @@ -250,7 +250,7 @@ static DEFINE_PXA3_CKEN(pxa3xx_mmc2, MMC2, 19500000, 0); static struct clk_lookup pxa3xx_clkregs[] = { INIT_CLKREG(&clk_pxa3xx_pout, NULL, "CLK_POUT"), /* Power I2C clock is always on */ - INIT_CLKREG(&clk_dummy, "pxa2xx-i2c.1", NULL), + INIT_CLKREG(&clk_dummy, "pxa3xx-pwri2c.1", NULL), INIT_CLKREG(&clk_pxa3xx_lcd, "pxa2xx-fb", NULL), INIT_CLKREG(&clk_pxa3xx_camera, NULL, "CAMCLK"), INIT_CLKREG(&clk_pxa3xx_ac97, NULL, "AC97CLK"), From 4aa78264d14bb0e87897acb90941c368248e20ce Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 19 Jun 2009 22:56:09 +0200 Subject: [PATCH 0124/1346] [ARM] pxa: use kzalloc() in pxa_init_gpio_chip() As slab is available early now, use kzalloc() rather than alloc_bootmem_low() in pxa_init_gpio_chip(). This removes the following boot time warning: <4>------------[ cut here ]------------ <4>WARNING: at mm/bootmem.c:535 alloc_arch_preferred_bootmem+0x2c/0x54() Modules linked in: [] (unwind_backtrace+0x0/0xdc) from [] (warn_slowpath_common+0x4c/0x80) [] (warn_slowpath_common+0x4c/0x80) from [] (alloc_arch_preferred_bootmem+0x2c/0x54) [] (alloc_arch_preferred_bootmem+0x2c/0x54) from [] (___alloc_bootmem_nopanic+0x34/0xd0) [] (___alloc_bootmem_nopanic+0x34/0xd0) from [] (___alloc_bootmem+0xc/0x34) [] (___alloc_bootmem+0xc/0x34) from [] (pxa_init_gpio+0x48/0x228) [] (pxa_init_gpio+0x48/0x228) from [] (init_IRQ+0x34/0x44) [] (init_IRQ+0x34/0x44) from [] (start_kernel+0x144/0x264) [] (start_kernel+0x144/0x264) from [] (0xa0008034) <4>---[ end trace 1b75b31a2719ed1c ]--- Signed-off-by: Daniel Mack Signed-off-by: Eric Miao --- arch/arm/plat-pxa/gpio.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/arm/plat-pxa/gpio.c b/arch/arm/plat-pxa/gpio.c index abc79d44aca..98548c6903a 100644 --- a/arch/arm/plat-pxa/gpio.c +++ b/arch/arm/plat-pxa/gpio.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include @@ -112,17 +112,12 @@ static int __init pxa_init_gpio_chip(int gpio_end) int i, gpio, nbanks = gpio_to_bank(gpio_end) + 1; struct pxa_gpio_chip *chips; - /* this is early, we have to use bootmem allocator, and we really - * want this to be allocated dynamically for different 'gpio_end' - */ - chips = alloc_bootmem_low(nbanks * sizeof(struct pxa_gpio_chip)); + chips = kzalloc(nbanks * sizeof(struct pxa_gpio_chip), GFP_KERNEL); if (chips == NULL) { pr_err("%s: failed to allocate GPIO chips\n", __func__); return -ENOMEM; } - memset(chips, 0, nbanks * sizeof(struct pxa_gpio_chip)); - for (i = 0, gpio = 0; i < nbanks; i++, gpio += 32) { struct gpio_chip *c = &chips[i].chip; From 82e8b54229fb121946151b82e8ff3c3284bd723f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Jun 2009 10:50:54 +0200 Subject: [PATCH 0125/1346] backlight: fix pwm_bl.c to notify platform code when suspending When suspending, pwm-bl sets duty cycle to 0, and shuts down the pwm device. This patch ensure that the platform code is called before that (through the notify callback_, leaving a chance for the platform code to configure GPIOs (shutting off the backlight, for example), much like it is done during normal operations. Signed-off-by: Marc Zyngier Signed-off-by: Eric Miao --- drivers/video/backlight/pwm_bl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index e641584e212..88716626744 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -145,6 +145,8 @@ static int pwm_backlight_suspend(struct platform_device *pdev, struct backlight_device *bl = platform_get_drvdata(pdev); struct pwm_bl_data *pb = dev_get_drvdata(&bl->dev); + if (pb->notify) + pb->notify(0); pwm_config(pb->pwm, 0, pb->period); pwm_disable(pb->pwm); return 0; From 30d7a77dd5a9720430af72f6f62f5156fe073e55 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 2 Jul 2009 21:24:14 -0300 Subject: [PATCH 0126/1346] perf_counter tools: Adjust symbols in ET_EXEC files too Ingo Molnar wrote: > i just bisected a 'perf report' bug that would cause us to not > resolve all user-space symbols in a 'git gc' run to: > > f5812a7a336fb952d819e4427b9a2dce02368e82 is first bad commit > commit f5812a7a336fb952d819e4427b9a2dce02368e82 > Author: Arnaldo Carvalho de Melo > Date: Tue Jun 30 11:43:17 2009 -0300 > > perf_counter tools: Adjust only prelinked symbol's addresses Rename ->prelinked to ->adjust_symbols and making what was done only for prelinked libraries also to ET_EXEC binaries, such as /usr/bin/git: [acme@doppio pahole]$ readelf -h /usr/bin/git | grep Type Type: EXEC (Executable file) [acme@doppio pahole]$ And after installing the 'git-debuginfo' package, I get correct results: [acme@doppio linux-2.6-tip]$ perf report --sort comm,dso,symbol -d /usr/bin/git | head -20 # # (1139614 samples) # # Overhead Command Shared Object Symbol # ........ ................ ......................... ...... # 34.98% git /usr/bin/git [.] send_sideband 33.39% git /usr/bin/git [.] enter_repo 6.81% git /usr/bin/git [.] diff_opt_parse 4.95% git /usr/bin/git [.] is_repository_shallow 3.24% git /usr/bin/git [.] odb_mkstemp 1.39% git /usr/bin/git [.] output 1.34% git /usr/bin/git [.] xmmap 1.25% git /usr/bin/git [.] receive_pack_config 1.16% git /usr/bin/git [.] git_pathdup 0.90% git /usr/bin/git [.] read_object_with_reference 0.86% git /usr/bin/git [.] show_patch_diff 0.85% git /usr/bin/git 0x00000000095e2e 0.69% git /usr/bin/git [.] display [acme@doppio linux-2.6-tip]$ I'll check what are the last cases where we can't resolve symbols, like this 0x00000000095e2e later. And I guess this will fix the problems Mike were seeing too: [acme@doppio linux-2.6-tip]$ readelf -h ../build/perf/vmlinux | grep Type Type: EXEC (Executable file) [acme@doppio linux-2.6-tip]$ Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- tools/perf/util/symbol.c | 11 ++++++----- tools/perf/util/symbol.h | 2 +- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 98a13114de7..4683b67b5ee 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -555,9 +555,10 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); - self->prelinked = elf_section_by_name(elf, &ehdr, &shdr, - ".gnu.prelink_undo", - NULL) != NULL; + self->adjust_symbols = (ehdr.e_type == ET_EXEC || + elf_section_by_name(elf, &ehdr, &shdr, + ".gnu.prelink_undo", + NULL) != NULL); elf_symtab__for_each_symbol(syms, nr_syms, index, sym) { struct symbol *f; u64 obj_start; @@ -580,7 +581,7 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, section_name = elf_sec__name(&shdr, secstrs); obj_start = sym.st_value; - if (self->prelinked) { + if (self->adjust_symbols) { if (verbose >= 2) printf("adjusting symbol: st_value: %Lx sh_addr: %Lx sh_offset: %Lx\n", (u64)sym.st_value, (u64)shdr.sh_addr, (u64)shdr.sh_offset); @@ -632,7 +633,7 @@ int dso__load(struct dso *self, symbol_filter_t filter, int verbose) if (!name) return -1; - self->prelinked = 0; + self->adjust_symbols = 0; if (strncmp(self->name, "/tmp/perf-", 10) == 0) return dso__load_perf_map(self, filter, verbose); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 4e141a30911..7918cffb23c 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -24,7 +24,7 @@ struct dso { struct rb_root syms; struct symbol *(*find_symbol)(struct dso *, u64 ip); unsigned int sym_priv_size; - unsigned char prelinked; + unsigned char adjust_symbols; char name[0]; }; From 44e18e9eda1f5c318a888989d929188eea93c8dc Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 3 Jul 2009 08:39:34 +0000 Subject: [PATCH 0127/1346] sh-sci: update receive error handling for muxed irqs This patch updates the receive error code for muxed interrupts in the sh-sci driver. Receive error interrupts may be generated by the hardware if RE or REIE bits in SCSCR are set. Update the muxed interrupt handling code to acknowledge error interrupts if RE or REIE is set, instead of only acknowledging if REIE is set. Without this patch error interrupts may be generated but never acked resulting in a "nobody cared" crash. Signed-off-by: Magnus Damm Signed-off-by: Paul Mundt --- drivers/serial/sh-sci.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c index 66f52674ca0..12bd64684f1 100644 --- a/drivers/serial/sh-sci.c +++ b/drivers/serial/sh-sci.c @@ -707,12 +707,13 @@ static irqreturn_t sci_br_interrupt(int irq, void *ptr) static irqreturn_t sci_mpxed_interrupt(int irq, void *ptr) { - unsigned short ssr_status, scr_status; + unsigned short ssr_status, scr_status, err_enabled; struct uart_port *port = ptr; irqreturn_t ret = IRQ_NONE; ssr_status = sci_in(port, SCxSR); scr_status = sci_in(port, SCSCR); + err_enabled = scr_status & (SCI_CTRL_FLAGS_REIE | SCI_CTRL_FLAGS_RIE); /* Tx Interrupt */ if ((ssr_status & 0x0020) && (scr_status & SCI_CTRL_FLAGS_TIE)) @@ -721,10 +722,10 @@ static irqreturn_t sci_mpxed_interrupt(int irq, void *ptr) if ((ssr_status & 0x0002) && (scr_status & SCI_CTRL_FLAGS_RIE)) ret = sci_rx_interrupt(irq, ptr); /* Error Interrupt */ - if ((ssr_status & 0x0080) && (scr_status & SCI_CTRL_FLAGS_REIE)) + if ((ssr_status & 0x0080) && err_enabled) ret = sci_er_interrupt(irq, ptr); /* Break Interrupt */ - if ((ssr_status & 0x0010) && (scr_status & SCI_CTRL_FLAGS_REIE)) + if ((ssr_status & 0x0010) && err_enabled) ret = sci_br_interrupt(irq, ptr); return ret; From 1df892cba45f9856d369a6a317ad2d1e44bca423 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 3 Jul 2009 10:33:39 +0100 Subject: [PATCH 0128/1346] ASoC: Fix register cache initialisation for WM8753 The wrong register cache variable was being used to provide the size for the memcpy(), resulting in a copy of only a void * of data. Reported-by: Lars-Peter Clausen Signed-off-by: Mark Brown Cc: stable@kernel.org --- sound/soc/codecs/wm8753.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c index d28eeaceb85..e06b0cfe4f2 100644 --- a/sound/soc/codecs/wm8753.c +++ b/sound/soc/codecs/wm8753.c @@ -1664,7 +1664,7 @@ static int wm8753_register(struct wm8753_priv *wm8753) codec->reg_cache = &wm8753->reg_cache; codec->private_data = wm8753; - memcpy(codec->reg_cache, wm8753_reg, sizeof(codec->reg_cache)); + memcpy(codec->reg_cache, wm8753_reg, sizeof(wm8753->reg_cache)); INIT_DELAYED_WORK(&codec->delayed_work, wm8753_work); ret = wm8753_reset(codec); From 07573534b0b030226ee5ab560e53aac7e6c0dd84 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 2 Jul 2009 11:57:19 -0600 Subject: [PATCH 0129/1346] ASoC: Fix mpc5200-psc-ac97 to ensure the data ready bit is cleared When doing register reads, it is possible for there to be a stale data ready bit set which will cause subsequent reads to return prematurely with incorrect data. This patch fixes the issues by ensuring stale data is cleared before starting another transaction. Signed-off-by: Grant Likely Acked-by: Jon Smirl Signed-off-by: Mark Brown --- sound/soc/fsl/mpc5200_psc_ac97.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/fsl/mpc5200_psc_ac97.c b/sound/soc/fsl/mpc5200_psc_ac97.c index 794a247b3eb..9b8503f2d68 100644 --- a/sound/soc/fsl/mpc5200_psc_ac97.c +++ b/sound/soc/fsl/mpc5200_psc_ac97.c @@ -41,6 +41,10 @@ static unsigned short psc_ac97_read(struct snd_ac97 *ac97, unsigned short reg) pr_err("timeout on ac97 bus (rdy)\n"); return -ENODEV; } + + /* Force clear the data valid bit */ + in_be32(&psc_dma->psc_regs->ac97_data); + /* Send the read */ out_be32(&psc_dma->psc_regs->ac97_cmd, (1<<31) | ((reg & 0x7f) << 24)); From 0827d6ba0b76be398a3c4298afd41f4965d2cdcb Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 2 Jul 2009 11:57:25 -0600 Subject: [PATCH 0130/1346] ASoC: add locking to mpc5200-psc-ac97 driver AC97 bus register read/write hooks need to provide locking, but the mpc5200-psc-ac97 driver does not. This patch adds a mutex around the register access routines. Signed-off-by: Grant Likely Acked-by: Jon Smirl Signed-off-by: Mark Brown --- sound/soc/fsl/mpc5200_dma.c | 1 + sound/soc/fsl/mpc5200_dma.h | 1 + sound/soc/fsl/mpc5200_psc_ac97.c | 13 ++++++++++++- 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c index efec33a1c5b..f0a2d407199 100644 --- a/sound/soc/fsl/mpc5200_dma.c +++ b/sound/soc/fsl/mpc5200_dma.c @@ -456,6 +456,7 @@ int mpc5200_audio_dma_create(struct of_device *op) return -ENODEV; spin_lock_init(&psc_dma->lock); + mutex_init(&psc_dma->mutex); psc_dma->id = be32_to_cpu(*prop); psc_dma->irq = irq; psc_dma->psc_regs = regs; diff --git a/sound/soc/fsl/mpc5200_dma.h b/sound/soc/fsl/mpc5200_dma.h index 2000803f06a..8d396bb9d9f 100644 --- a/sound/soc/fsl/mpc5200_dma.h +++ b/sound/soc/fsl/mpc5200_dma.h @@ -55,6 +55,7 @@ struct psc_dma { unsigned int irq; struct device *dev; spinlock_t lock; + struct mutex mutex; u32 sicr; uint sysclk; int imr; diff --git a/sound/soc/fsl/mpc5200_psc_ac97.c b/sound/soc/fsl/mpc5200_psc_ac97.c index 9b8503f2d68..7eb549985d4 100644 --- a/sound/soc/fsl/mpc5200_psc_ac97.c +++ b/sound/soc/fsl/mpc5200_psc_ac97.c @@ -34,11 +34,14 @@ static unsigned short psc_ac97_read(struct snd_ac97 *ac97, unsigned short reg) int status; unsigned int val; + mutex_lock(&psc_dma->mutex); + /* Wait for command send status zero = ready */ status = spin_event_timeout(!(in_be16(&psc_dma->psc_regs->sr_csr.status) & MPC52xx_PSC_SR_CMDSEND), 100, 0); if (status == 0) { pr_err("timeout on ac97 bus (rdy)\n"); + mutex_unlock(&psc_dma->mutex); return -ENODEV; } @@ -54,16 +57,19 @@ static unsigned short psc_ac97_read(struct snd_ac97 *ac97, unsigned short reg) if (status == 0) { pr_err("timeout on ac97 read (val) %x\n", in_be16(&psc_dma->psc_regs->sr_csr.status)); + mutex_unlock(&psc_dma->mutex); return -ENODEV; } /* Get the data */ val = in_be32(&psc_dma->psc_regs->ac97_data); if (((val >> 24) & 0x7f) != reg) { pr_err("reg echo error on ac97 read\n"); + mutex_unlock(&psc_dma->mutex); return -ENODEV; } val = (val >> 8) & 0xffff; + mutex_unlock(&psc_dma->mutex); return (unsigned short) val; } @@ -72,16 +78,21 @@ static void psc_ac97_write(struct snd_ac97 *ac97, { int status; + mutex_lock(&psc_dma->mutex); + /* Wait for command status zero = ready */ status = spin_event_timeout(!(in_be16(&psc_dma->psc_regs->sr_csr.status) & MPC52xx_PSC_SR_CMDSEND), 100, 0); if (status == 0) { pr_err("timeout on ac97 bus (write)\n"); - return; + goto out; } /* Write data */ out_be32(&psc_dma->psc_regs->ac97_cmd, ((reg & 0x7f) << 24) | (val << 8)); + + out: + mutex_unlock(&psc_dma->mutex); } static void psc_ac97_warm_reset(struct snd_ac97 *ac97) From 029e5b1636d0511ef143af3a20c83c48e44c03f3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 13:17:28 +0200 Subject: [PATCH 0131/1346] perf report: Annotate variable initialization MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Certain versions of GCC dont see the initialization that is done here: builtin-report.c: In function ‘__cmd_report’: builtin-report.c:1038: warning: ‘syms’ may be used uninitialized in this function So annotate it with a NULL initialization. Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- tools/perf/builtin-report.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 283773d91aa..fa937f5c3c3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1035,7 +1035,7 @@ resolve_callchain(struct thread *thread, struct map *map __used, struct ip_callchain *chain, struct hist_entry *entry) { u64 context = PERF_CONTEXT_MAX; - struct symbol **syms; + struct symbol **syms = NULL; unsigned int i; if (callchain) { From bbf2a330d92c5afccfd17592ba9ccd50f41cf748 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Jul 2009 00:08:26 +0200 Subject: [PATCH 0132/1346] x86: atomic64: The atomic64_t data type should be 8 bytes aligned on 32-bit too Locked instructions on two cache lines at once are painful. If atomic64_t uses two cache lines, my test program is 10x slower. The chance for that is significant: 4/32 or 12.5%. Make sure an atomic64_t is 8 bytes aligned. Signed-off-by: Eric Dumazet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: [ changed it to __aligned(8) as per Andrew's suggestion ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic_32.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index 2503d4e64c2..ae0fbb5b057 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -250,7 +250,7 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) /* An 64bit atomic type */ typedef struct { - unsigned long long counter; + unsigned long long __aligned(8) counter; } atomic64_t; #define ATOMIC64_INIT(val) { (val) } From b7882b7c65abb00194bdb3d4a22d27d70fcc59ba Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 13:26:39 +0200 Subject: [PATCH 0133/1346] x86: atomic64: Move the 32-bit atomic64_t implementation to a .c file Linus noted that the atomic64_t primitives are all inlines currently which is crazy because these functions have a large register footprint anyway. Move them to a separate file: arch/x86/lib/atomic64_32.c Also, while at it, rename all uses of 'unsigned long long' to the much shorter u64. This makes the appearance of the prototypes a lot nicer - and it also uncovered a few bugs where (yet unused) API variants had 'long' as their return type instead of u64. [ More intrusive changes are not yet done in this patch. ] Reported-by: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic_32.h | 137 +++----------------- arch/x86/lib/Makefile | 1 + arch/x86/lib/atomic64_32.c | 216 +++++++++++++++++++++++++++++++ 3 files changed, 237 insertions(+), 117 deletions(-) create mode 100644 arch/x86/lib/atomic64_32.c diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index ae0fbb5b057..311a43e47c0 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -250,7 +250,7 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) /* An 64bit atomic type */ typedef struct { - unsigned long long __aligned(8) counter; + u64 __aligned(8) counter; } atomic64_t; #define ATOMIC64_INIT(val) { (val) } @@ -264,31 +264,7 @@ typedef struct { */ #define __atomic64_read(ptr) ((ptr)->counter) -static inline unsigned long long -cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new) -{ - asm volatile( - - LOCK_PREFIX "cmpxchg8b (%[ptr])\n" - - : "=A" (old) - - : [ptr] "D" (ptr), - "A" (old), - "b" (ll_low(new)), - "c" (ll_high(new)) - - : "memory"); - - return old; -} - -static inline unsigned long long -atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val, - unsigned long long new_val) -{ - return cmpxchg8b(&ptr->counter, old_val, new_val); -} +extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val); /** * atomic64_xchg - xchg atomic64 variable @@ -298,18 +274,7 @@ atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val, * Atomically xchgs the value of @ptr to @new_val and returns * the old value. */ - -static inline unsigned long long -atomic64_xchg(atomic64_t *ptr, unsigned long long new_val) -{ - unsigned long long old_val; - - do { - old_val = atomic_read(ptr); - } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); - - return old_val; -} +extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val); /** * atomic64_set - set atomic64 variable @@ -318,10 +283,7 @@ atomic64_xchg(atomic64_t *ptr, unsigned long long new_val) * * Atomically sets the value of @ptr to @new_val. */ -static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val) -{ - atomic64_xchg(ptr, new_val); -} +extern void atomic64_set(atomic64_t *ptr, u64 new_val); /** * atomic64_read - read atomic64 variable @@ -329,16 +291,7 @@ static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val) * * Atomically reads the value of @ptr and returns it. */ -static inline unsigned long long atomic64_read(atomic64_t *ptr) -{ - unsigned long long curr_val; - - do { - curr_val = __atomic64_read(ptr); - } while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val); - - return curr_val; -} +extern u64 atomic64_read(atomic64_t *ptr); /** * atomic64_add_return - add and return @@ -347,34 +300,14 @@ static inline unsigned long long atomic64_read(atomic64_t *ptr) * * Atomically adds @delta to @ptr and returns @delta + *@ptr */ -static inline unsigned long long -atomic64_add_return(unsigned long long delta, atomic64_t *ptr) -{ - unsigned long long old_val, new_val; +extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr); - do { - old_val = atomic_read(ptr); - new_val = old_val + delta; - - } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); - - return new_val; -} - -static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr) -{ - return atomic64_add_return(-delta, ptr); -} - -static inline long atomic64_inc_return(atomic64_t *ptr) -{ - return atomic64_add_return(1, ptr); -} - -static inline long atomic64_dec_return(atomic64_t *ptr) -{ - return atomic64_sub_return(1, ptr); -} +/* + * Other variants with different arithmetic operators: + */ +extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr); +extern u64 atomic64_inc_return(atomic64_t *ptr); +extern u64 atomic64_dec_return(atomic64_t *ptr); /** * atomic64_add - add integer to atomic64 variable @@ -383,10 +316,7 @@ static inline long atomic64_dec_return(atomic64_t *ptr) * * Atomically adds @delta to @ptr. */ -static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr) -{ - atomic64_add_return(delta, ptr); -} +extern void atomic64_add(u64 delta, atomic64_t *ptr); /** * atomic64_sub - subtract the atomic64 variable @@ -395,10 +325,7 @@ static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr) * * Atomically subtracts @delta from @ptr. */ -static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr) -{ - atomic64_add(-delta, ptr); -} +extern void atomic64_sub(u64 delta, atomic64_t *ptr); /** * atomic64_sub_and_test - subtract value from variable and test result @@ -409,13 +336,7 @@ static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr) * true if the result is zero, or false for all * other cases. */ -static inline int -atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr) -{ - unsigned long long old_val = atomic64_sub_return(delta, ptr); - - return old_val == 0; -} +extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr); /** * atomic64_inc - increment atomic64 variable @@ -423,10 +344,7 @@ atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr) * * Atomically increments @ptr by 1. */ -static inline void atomic64_inc(atomic64_t *ptr) -{ - atomic64_add(1, ptr); -} +extern void atomic64_inc(atomic64_t *ptr); /** * atomic64_dec - decrement atomic64 variable @@ -434,10 +352,7 @@ static inline void atomic64_inc(atomic64_t *ptr) * * Atomically decrements @ptr by 1. */ -static inline void atomic64_dec(atomic64_t *ptr) -{ - atomic64_sub(1, ptr); -} +extern void atomic64_dec(atomic64_t *ptr); /** * atomic64_dec_and_test - decrement and test @@ -447,10 +362,7 @@ static inline void atomic64_dec(atomic64_t *ptr) * returns true if the result is 0, or false for all other * cases. */ -static inline int atomic64_dec_and_test(atomic64_t *ptr) -{ - return atomic64_sub_and_test(1, ptr); -} +extern int atomic64_dec_and_test(atomic64_t *ptr); /** * atomic64_inc_and_test - increment and test @@ -460,10 +372,7 @@ static inline int atomic64_dec_and_test(atomic64_t *ptr) * and returns true if the result is zero, or false for all * other cases. */ -static inline int atomic64_inc_and_test(atomic64_t *ptr) -{ - return atomic64_sub_and_test(-1, ptr); -} +extern int atomic64_inc_and_test(atomic64_t *ptr); /** * atomic64_add_negative - add and test if negative @@ -474,13 +383,7 @@ static inline int atomic64_inc_and_test(atomic64_t *ptr) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline int -atomic64_add_negative(unsigned long long delta, atomic64_t *ptr) -{ - long long old_val = atomic64_add_return(delta, ptr); - - return old_val < 0; -} +extern int atomic64_add_negative(u64 delta, atomic64_t *ptr); #include #endif /* _ASM_X86_ATOMIC_32_H */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f9d35632666..c3c657c8bb8 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -10,6 +10,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o ifeq ($(CONFIG_X86_32),y) + lib-y += atomic64_32.o lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c new file mode 100644 index 00000000000..d21e725d3d8 --- /dev/null +++ b/arch/x86/lib/atomic64_32.c @@ -0,0 +1,216 @@ +#include +#include +#include +#include +#include + +static inline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new) +{ + asm volatile( + + LOCK_PREFIX "cmpxchg8b (%[ptr])\n" + + : "=A" (old) + + : [ptr] "D" (ptr), + "A" (old), + "b" (ll_low(new)), + "c" (ll_high(new)) + + : "memory"); + + return old; +} + +u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val) +{ + return cmpxchg8b(&ptr->counter, old_val, new_val); +} + +/** + * atomic64_xchg - xchg atomic64 variable + * @ptr: pointer to type atomic64_t + * @new_val: value to assign + * + * Atomically xchgs the value of @ptr to @new_val and returns + * the old value. + */ + +u64 atomic64_xchg(atomic64_t *ptr, u64 new_val) +{ + u64 old_val; + + do { + old_val = atomic_read(ptr); + } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); + + return old_val; +} + +/** + * atomic64_set - set atomic64 variable + * @ptr: pointer to type atomic64_t + * @new_val: value to assign + * + * Atomically sets the value of @ptr to @new_val. + */ +void atomic64_set(atomic64_t *ptr, u64 new_val) +{ + atomic64_xchg(ptr, new_val); +} + +/** + * atomic64_read - read atomic64 variable + * @ptr: pointer to type atomic64_t + * + * Atomically reads the value of @ptr and returns it. + */ +u64 atomic64_read(atomic64_t *ptr) +{ + u64 curr_val; + + do { + curr_val = __atomic64_read(ptr); + } while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val); + + return curr_val; +} + +/** + * atomic64_add_return - add and return + * @delta: integer value to add + * @ptr: pointer to type atomic64_t + * + * Atomically adds @delta to @ptr and returns @delta + *@ptr + */ +u64 atomic64_add_return(u64 delta, atomic64_t *ptr) +{ + u64 old_val, new_val; + + do { + old_val = atomic_read(ptr); + new_val = old_val + delta; + + } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); + + return new_val; +} + +u64 atomic64_sub_return(u64 delta, atomic64_t *ptr) +{ + return atomic64_add_return(-delta, ptr); +} + +u64 atomic64_inc_return(atomic64_t *ptr) +{ + return atomic64_add_return(1, ptr); +} + +u64 atomic64_dec_return(atomic64_t *ptr) +{ + return atomic64_sub_return(1, ptr); +} + +/** + * atomic64_add - add integer to atomic64 variable + * @delta: integer value to add + * @ptr: pointer to type atomic64_t + * + * Atomically adds @delta to @ptr. + */ +void atomic64_add(u64 delta, atomic64_t *ptr) +{ + atomic64_add_return(delta, ptr); +} + +/** + * atomic64_sub - subtract the atomic64 variable + * @delta: integer value to subtract + * @ptr: pointer to type atomic64_t + * + * Atomically subtracts @delta from @ptr. + */ +void atomic64_sub(u64 delta, atomic64_t *ptr) +{ + atomic64_add(-delta, ptr); +} + +/** + * atomic64_sub_and_test - subtract value from variable and test result + * @delta: integer value to subtract + * @ptr: pointer to type atomic64_t + * + * Atomically subtracts @delta from @ptr and returns + * true if the result is zero, or false for all + * other cases. + */ +int atomic64_sub_and_test(u64 delta, atomic64_t *ptr) +{ + u64 old_val = atomic64_sub_return(delta, ptr); + + return old_val == 0; +} + +/** + * atomic64_inc - increment atomic64 variable + * @ptr: pointer to type atomic64_t + * + * Atomically increments @ptr by 1. + */ +void atomic64_inc(atomic64_t *ptr) +{ + atomic64_add(1, ptr); +} + +/** + * atomic64_dec - decrement atomic64 variable + * @ptr: pointer to type atomic64_t + * + * Atomically decrements @ptr by 1. + */ +void atomic64_dec(atomic64_t *ptr) +{ + atomic64_sub(1, ptr); +} + +/** + * atomic64_dec_and_test - decrement and test + * @ptr: pointer to type atomic64_t + * + * Atomically decrements @ptr by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +int atomic64_dec_and_test(atomic64_t *ptr) +{ + return atomic64_sub_and_test(1, ptr); +} + +/** + * atomic64_inc_and_test - increment and test + * @ptr: pointer to type atomic64_t + * + * Atomically increments @ptr by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +int atomic64_inc_and_test(atomic64_t *ptr) +{ + return atomic64_sub_and_test(-1, ptr); +} + +/** + * atomic64_add_negative - add and test if negative + * @delta: integer value to add + * @ptr: pointer to type atomic64_t + * + * Atomically adds @delta to @ptr and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +int atomic64_add_negative(u64 delta, atomic64_t *ptr) +{ + long long old_val = atomic64_add_return(delta, ptr); + + return old_val < 0; +} From aacf682fd8c66b57383c407eecd9d4a28264ee91 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Jul 2009 12:14:27 +0200 Subject: [PATCH 0134/1346] x86: atomic64: Improve atomic64_read() Linus noticed that the 32-bit version of atomic64_read() was being overly complex with re-reading the value and doing a retry loop over that. Instead we can just rely on cmpxchg8b returning either the new value or returning the current value. We can use any 'old' value, which will be faster as it can be loaded via immediates. Using some value that is not equal to the real value in memory the instruction gets faster. This also has the advantage that the CPU could avoid dirtying the cacheline. Reported-by: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index d21e725d3d8..afa5d444918 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -67,13 +67,9 @@ void atomic64_set(atomic64_t *ptr, u64 new_val) */ u64 atomic64_read(atomic64_t *ptr) { - u64 curr_val; + u64 old = 1LL << 32; - do { - curr_val = __atomic64_read(ptr); - } while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val); - - return curr_val; + return cmpxchg8b(&ptr->counter, old, old); } /** From 69237f94e65d3d7f539f1adb98ef68685c595004 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Jul 2009 13:26:41 +0200 Subject: [PATCH 0135/1346] x86: atomic64: Improve cmpxchg8b() Rewrite cmpxchg8b() to not use %edi register but a generic "+m" constraint, to increase compiler freedom in code generation and possibly better code. Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index afa5d444918..5fc1e2caa54 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -6,19 +6,14 @@ static inline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new) { + u32 low = new; + u32 high = new >> 32; + asm volatile( - - LOCK_PREFIX "cmpxchg8b (%[ptr])\n" - - : "=A" (old) - - : [ptr] "D" (ptr), - "A" (old), - "b" (ll_low(new)), - "c" (ll_high(new)) - - : "memory"); - + LOCK_PREFIX "cmpxchg8b %1\n" + : "+A" (old), "+m" (*ptr) + : "b" (low), "c" (high) + ); return old; } From 824975ef190e7dcb77718d1cc2cb53769b16d918 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 12:39:07 +0200 Subject: [PATCH 0136/1346] x86: atomic64: Improve atomic64_add_return() Linus noted (based on Eric Dumazet's numbers) that we would probably be better off not trying an atomic_read() in atomic64_add_return() but intead intentionally let the first cmpxchg8b fail - to get a cache-friendly 'give me ownership of this cacheline' transaction. That can then be followed by the real cmpxchg8b which sets the value local to the CPU. Reported-by: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index 5fc1e2caa54..61959627e1e 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -76,13 +76,22 @@ u64 atomic64_read(atomic64_t *ptr) */ u64 atomic64_add_return(u64 delta, atomic64_t *ptr) { - u64 old_val, new_val; + /* + * Try first with a (probably incorrect) assumption about + * what we have there. We'll do two loops most likely, + * but we'll get an ownership MESI transaction straight away + * instead of a read transaction followed by a + * flush-for-ownership transaction: + */ + u64 old_val, new_val, real_val = 1ULL << 32; do { - old_val = atomic_read(ptr); + old_val = real_val; new_val = old_val + delta; - } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); + real_val = atomic64_cmpxchg(ptr, old_val, new_val); + + } while (real_val != old_val); return new_val; } From 3ac805d2afd3fa4a07cb5bcf352fd7fa83f28935 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 12:51:19 +0200 Subject: [PATCH 0137/1346] x86: atomic64: Reduce size of functions cmpxchg8b is a huge instruction in terms of register footprint, we almost never want to inline it, not even within the same code module. GCC 4.3 still messes up for two functions, under-judging the true cost of this instruction - so annotate two key functions to reduce the bloat: arch/x86/lib/atomic64_32.o: text data bss dec hex filename 1763 0 0 1763 6e3 atomic64_32.o.before 435 0 0 435 1b3 atomic64_32.o.after Cc: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index 61959627e1e..a910238a776 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -4,7 +4,7 @@ #include #include -static inline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new) +static noinline u64 cmpxchg8b(u64 *ptr, u64 old, u64 new) { u32 low = new; u32 high = new >> 32; @@ -74,7 +74,7 @@ u64 atomic64_read(atomic64_t *ptr) * * Atomically adds @delta to @ptr and returns @delta + *@ptr */ -u64 atomic64_add_return(u64 delta, atomic64_t *ptr) +noinline u64 atomic64_add_return(u64 delta, atomic64_t *ptr) { /* * Try first with a (probably incorrect) assumption about From 3217120873598533234b6dedda9c371ce30001d0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 13:06:01 +0200 Subject: [PATCH 0138/1346] x86: atomic64: Make atomic_read() type-safe MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Linus noticed that atomic64_xchg() uses atomic_read(), which happens to work because atomic_read() is a macro so the .counter value gets u64-read on 32-bit too - but this is really bogus and serious bugs are waiting to happen. Change atomic_read() to be a type-safe inline, and this exposes the atomic64 bogosity as well: arch/x86/lib/atomic64_32.c: In function ‘atomic64_xchg’: arch/x86/lib/atomic64_32.c:39: warning: passing argument 1 of ‘atomic_read’ from incompatible pointer type Reported-by: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic_32.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index 311a43e47c0..b551bb1ae3c 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -19,7 +19,10 @@ * * Atomically reads the value of @v. */ -#define atomic_read(v) ((v)->counter) +static inline int atomic_read(const atomic_t *v) +{ + return v->counter; +} /** * atomic_set - set atomic variable From 199e23780a7e75c63a9e3d1108804e3af450ea3e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 13:02:39 +0200 Subject: [PATCH 0139/1346] x86: atomic64: Fix unclean type use in atomic64_xchg() Linus noticed that atomic64_xchg() uses atomic_read(), which happens to work because atomic_read() is a macro so the .counter value gets u64-read on 32-bit too - but this is really bogus and serious bugs are waiting to happen. Fix atomic64_xchg() to use __atomic64_read() instead. No code changed: arch/x86/lib/atomic64_32.o: text data bss dec hex filename 435 0 0 435 1b3 atomic64_32.o.before 435 0 0 435 1b3 atomic64_32.o.after md5: bd8ab95e69c93518578bfaf0ea3be4d9 atomic64_32.o.before.asm bd8ab95e69c93518578bfaf0ea3be4d9 atomic64_32.o.after.asm Reported-by: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index a910238a776..fd28fd3fb74 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -36,7 +36,7 @@ u64 atomic64_xchg(atomic64_t *ptr, u64 new_val) u64 old_val; do { - old_val = atomic_read(ptr); + old_val = __atomic64_read(ptr); } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); return old_val; From 12b9d7ccb841805e347fec8f733f368f43ddba40 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 1 Jul 2009 17:37:22 -0400 Subject: [PATCH 0140/1346] x86: Fix fixmap page order for FIX_TEXT_POKE0,1 Masami reported: > Since the fixmap pages are assigned higher address to lower, > text_poke() has to use it with inverted order (FIX_TEXT_POKE1 > to FIX_TEXT_POKE0). I prefer to just invert the order of the fixmap declaration. It's simpler and more straightforward. Backward fixmaps seems to be used by both x86 32 and 64. It's really rare but a nasty bug, because it only hurts when instructions to patch are crossing a page boundary. If this happens, the fixmap write accesses will spill on the following fixmap, which may very well crash the system. And this does not crash the system, it could leave illegal instructions in place. Thanks Masami for finding this. It seems to have crept into the 2.6.30-rc series, so this calls for a -stable inclusion. Signed-off-by: Mathieu Desnoyers Acked-by: Masami Hiramatsu Cc: LKML-Reference: <20090701213722.GH19926@Krystal> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fixmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 3eb0f79a532..7b2d71df39a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -111,8 +111,8 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif - FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ - FIX_TEXT_POKE1, + FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */ + FIX_TEXT_POKE0, /* first page is last, because allocation is backward */ __end_of_permanent_fixed_addresses, /* * 256 temporary boot-time mappings, used by early_ioremap(), From 3fd382cedfb4fb742a8cc17ba15288ec03131db1 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 2 Jul 2009 07:27:20 +0200 Subject: [PATCH 0141/1346] x86: Add missing annotation to arch/x86/lib/copy_user_64.S::copy_to_user While examining symbol generation in perf_counter tools, I noticed that copy_to_user() had no size in vmlinux's symtab. Signed-off-by: Mike Galbraith Acked-by: Alexander van Heukelum Acked-by: Cyrill Gorcunov LKML-Reference: <1246512440.13293.3.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- arch/x86/lib/copy_user_64.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index f118c110af3..6ba0f7bb85e 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -75,6 +75,7 @@ ENTRY(copy_to_user) jae bad_to_user ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC +ENDPROC(copy_to_user) /* Standard copy_from_user with segment limit checking */ ENTRY(copy_from_user) From d3ac88157c1e9153f37cd2b9313117ae11735063 Mon Sep 17 00:00:00 2001 From: Rakib Mullick Date: Thu, 2 Jul 2009 11:40:36 +0600 Subject: [PATCH 0142/1346] x86, kvm: Fix section mismatches in kvm.c The function paravirt_ops_setup() has been refering the variable no_timer_check, which is a __initdata. Thus generates the following warning. paravirt_ops_setup() function is called from kvm_guest_init() which is a __init function. So to fix this we mark paravirt_ops_setup as __init. The sections-check output that warned us about this was: LD arch/x86/built-in.o WARNING: arch/x86/built-in.o(.text+0x166ce): Section mismatch in reference from the function paravirt_ops_setup() to the variable .init.data:no_timer_check The function paravirt_ops_setup() references the variable __initdata no_timer_check. This is often because paravirt_ops_setup lacks a __initdata annotation or the annotation of no_timer_check is wrong. Signed-off-by: Rakib Mullick Acked-by: Avi Kivity Cc: Andrew Morton LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/kvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a78ecad0c90..c664d515f61 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -200,7 +200,7 @@ static void kvm_leave_lazy_mmu(void) state->mode = paravirt_get_lazy_mode(); } -static void paravirt_ops_setup(void) +static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; pv_info.paravirt_enabled = 1; From 23d0cd8e718723f1ddda37637bc6b7c34caec64a Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Thu, 2 Jul 2009 22:33:59 +0530 Subject: [PATCH 0143/1346] x86: Remove unused variable disable_x2apic setup_nox2apic() is writing 1 to disable_x2apic but no one is reading it. Signed-off-by: Jaswinder Singh Rajput Cc: Yinghai Lu Cc: Cyrill Gorcunov LKML-Reference: <1246554239.2242.27.camel@jaswinder.satnam> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/apic.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 8c7c042ecad..0a1c2830ec6 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -140,7 +140,6 @@ int x2apic_mode; #ifdef CONFIG_X86_X2APIC /* x2apic enabled before OS handover */ static int x2apic_preenabled; -static int disable_x2apic; static __init int setup_nox2apic(char *str) { if (x2apic_enabled()) { @@ -149,7 +148,6 @@ static __init int setup_nox2apic(char *str) return 0; } - disable_x2apic = 1; setup_clear_cpu_cap(X86_FEATURE_X2APIC); return 0; } From c7210e1ff8a95a0a6dba0d04a95b3ddd9d165fab Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Thu, 2 Jul 2009 22:35:35 +0530 Subject: [PATCH 0144/1346] x86: Remove unused function lapic_watchdog_ok() lapic_watchdog_ok() is a global function but no one is using it. Signed-off-by: Jaswinder Singh Rajput Cc: Andi Kleen Cc: Yinghai Lu LKML-Reference: <1246554335.2242.29.camel@jaswinder.satnam> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/nmi.h | 1 - arch/x86/kernel/cpu/perfctr-watchdog.c | 5 ----- 2 files changed, 6 deletions(-) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index c9726440993..c86e5ed4af5 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -72,7 +72,6 @@ void lapic_watchdog_stop(void); int lapic_watchdog_init(unsigned nmi_hz); int lapic_wd_event(unsigned nmi_hz); unsigned lapic_adjust_nmi_hz(unsigned hz); -int lapic_watchdog_ok(void); void disable_lapic_nmi_watchdog(void); void enable_lapic_nmi_watchdog(void); void stop_nmi(void); diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 5c481f6205b..e60ed740d2b 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -803,8 +803,3 @@ int __kprobes lapic_wd_event(unsigned nmi_hz) wd_ops->rearm(wd, nmi_hz); return 1; } - -int lapic_watchdog_ok(void) -{ - return wd_ops != NULL; -} From 8e049ef054f1cc765f05f13e1396bb9a17c19e66 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 2 Jul 2009 08:57:12 +1000 Subject: [PATCH 0145/1346] x86: atomic64: Code atomic(64)_read and atomic(64)_set in C not CPP Occasionally we get bugs where atomic_read or atomic_set are used on atomic64_t variables or vice versa. These bugs don't generate warnings on x86 because atomic_read and atomic_set are coded as macros rather than C functions, so we don't get any type-checking on their arguments; similarly for atomic64_read and atomic64_set in 64-bit kernels. This converts them to C functions so that the arguments are type-checked and bugs like this will get caught more easily. It also converts atomic_cmpxchg and atomic_xchg, and atomic64_cmpxchg and atomic64_xchg on 64-bit, so we get type-checking on their arguments too. Compiling a typical 64-bit x86 config, this generates no new warnings, and the vmlinux text is 86 bytes smaller. Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic_32.h | 16 +++++++++--- arch/x86/include/asm/atomic_64.h | 42 ++++++++++++++++++++++++++------ 2 files changed, 47 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index b551bb1ae3c..aa045deb2e7 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -31,7 +31,10 @@ static inline int atomic_read(const atomic_t *v) * * Atomically sets the value of @v to @i. */ -#define atomic_set(v, i) (((v)->counter) = (i)) +static inline void atomic_set(atomic_t *v, int i) +{ + v->counter = i; +} /** * atomic_add - add integer to atomic variable @@ -203,8 +206,15 @@ static inline int atomic_sub_return(int i, atomic_t *v) return atomic_add_return(-i, v); } -#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) +static inline int atomic_cmpxchg(atomic_t *v, int old, int new) +{ + return cmpxchg(&v->counter, old, new); +} + +static inline int atomic_xchg(atomic_t *v, int new) +{ + return xchg(&v->counter, new); +} /** * atomic_add_unless - add unless the number is already a given value diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h index 0d636022000..d605dc268e7 100644 --- a/arch/x86/include/asm/atomic_64.h +++ b/arch/x86/include/asm/atomic_64.h @@ -18,7 +18,10 @@ * * Atomically reads the value of @v. */ -#define atomic_read(v) ((v)->counter) +static inline int atomic_read(const atomic_t *v) +{ + return v->counter; +} /** * atomic_set - set atomic variable @@ -27,7 +30,10 @@ * * Atomically sets the value of @v to @i. */ -#define atomic_set(v, i) (((v)->counter) = (i)) +static inline void atomic_set(atomic_t *v, int i) +{ + v->counter = i; +} /** * atomic_add - add integer to atomic variable @@ -192,7 +198,10 @@ static inline int atomic_sub_return(int i, atomic_t *v) * Atomically reads the value of @v. * Doesn't imply a read memory barrier. */ -#define atomic64_read(v) ((v)->counter) +static inline long atomic64_read(const atomic64_t *v) +{ + return v->counter; +} /** * atomic64_set - set atomic64 variable @@ -201,7 +210,10 @@ static inline int atomic_sub_return(int i, atomic_t *v) * * Atomically sets the value of @v to @i. */ -#define atomic64_set(v, i) (((v)->counter) = (i)) +static inline void atomic64_set(atomic64_t *v, long i) +{ + v->counter = i; +} /** * atomic64_add - add integer to atomic64 variable @@ -355,11 +367,25 @@ static inline long atomic64_sub_return(long i, atomic64_t *v) #define atomic64_inc_return(v) (atomic64_add_return(1, (v))) #define atomic64_dec_return(v) (atomic64_sub_return(1, (v))) -#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) +static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new) +{ + return cmpxchg(&v->counter, old, new); +} -#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new))) -#define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) +static inline long atomic64_xchg(atomic64_t *v, long new) +{ + return xchg(&v->counter, new); +} + +static inline long atomic_cmpxchg(atomic_t *v, int old, int new) +{ + return cmpxchg(&v->counter, old, new); +} + +static inline long atomic_xchg(atomic_t *v, int new) +{ + return xchg(&v->counter, new); +} /** * atomic_add_unless - add unless the number is a given value From 67d7178f8fc64b7f68d7dd8a1b21dfa0d42c220c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Jul 2009 13:23:02 +0200 Subject: [PATCH 0146/1346] x86: atomic64: Improve atomic64_read() Optimize atomic64_read() as a special open-coded cmpxchg8b variant. This generates nicer code: arch/x86/lib/atomic64_32.o: text data bss dec hex filename 435 0 0 435 1b3 atomic64_32.o.before 431 0 0 431 1af atomic64_32.o.after md5: bd8ab95e69c93518578bfaf0ea3be4d9 atomic64_32.o.before.asm 2bdfd4bd1f6b7b61b7fc127aef90ce3b atomic64_32.o.after.asm Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index fd28fd3fb74..cd11803f944 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -62,9 +62,17 @@ void atomic64_set(atomic64_t *ptr, u64 new_val) */ u64 atomic64_read(atomic64_t *ptr) { - u64 old = 1LL << 32; + u64 res; - return cmpxchg8b(&ptr->counter, old, old); + asm volatile( + "mov %%ebx, %%eax\n\t" + "mov %%ecx, %%edx\n\t" + LOCK_PREFIX "cmpxchg8b %1\n" + : "+A" (res) + : "m" (*ptr) + ); + + return res; } /** From 637a935aaba2f05e2178c9d1b714d7a2c36c8b44 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Fri, 3 Jul 2009 01:04:16 +0200 Subject: [PATCH 0147/1346] ASoC: Fix wm8753 register cache size and initialization Register cache space was not being allocated for the final register, causing bugs when it was used. Allocate space for it. Also ensure that the final register is displayed in sysfs. [Commit message rewritten to document actual issue. -- broonie] Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- sound/soc/codecs/wm8753.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c index e06b0cfe4f2..49c4b2898af 100644 --- a/sound/soc/codecs/wm8753.c +++ b/sound/soc/codecs/wm8753.c @@ -79,7 +79,7 @@ static const u16 wm8753_reg[] = { 0x0097, 0x0097, 0x0000, 0x0004, 0x0000, 0x0083, 0x0024, 0x01ba, 0x0000, 0x0083, 0x0024, 0x01ba, - 0x0000, 0x0000 + 0x0000, 0x0000, 0x0000 }; /* codec private data */ @@ -1660,7 +1660,7 @@ static int wm8753_register(struct wm8753_priv *wm8753) codec->set_bias_level = wm8753_set_bias_level; codec->dai = wm8753_dai; codec->num_dai = 2; - codec->reg_cache_size = ARRAY_SIZE(wm8753->reg_cache); + codec->reg_cache_size = ARRAY_SIZE(wm8753->reg_cache) + 1; codec->reg_cache = &wm8753->reg_cache; codec->private_data = wm8753; From 1fde902d52ee13ab9fab155bbae757fdf7daf0c1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 17:28:57 +0200 Subject: [PATCH 0148/1346] x86: atomic64: Export APIs to modules atomic64_t primitives are used by a handful of drivers, so export the APIs consistently. These were inlined before. Also mark atomic64_32.o a core object, so that the symbols are available even if not linked to core kernel pieces. Cc: Eric Dumazet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/Makefile | 2 +- arch/x86/lib/atomic64_32.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index c3c657c8bb8..07c31899c9c 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -10,7 +10,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o ifeq ($(CONFIG_X86_32),y) - lib-y += atomic64_32.o + obj-y += atomic64_32.o lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index cd11803f944..6722a092e40 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -1,5 +1,7 @@ #include +#include #include + #include #include #include @@ -21,6 +23,7 @@ u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val) { return cmpxchg8b(&ptr->counter, old_val, new_val); } +EXPORT_SYMBOL(atomic64_cmpxchg); /** * atomic64_xchg - xchg atomic64 variable @@ -41,6 +44,7 @@ u64 atomic64_xchg(atomic64_t *ptr, u64 new_val) return old_val; } +EXPORT_SYMBOL(atomic64_xchg); /** * atomic64_set - set atomic64 variable @@ -53,6 +57,7 @@ void atomic64_set(atomic64_t *ptr, u64 new_val) { atomic64_xchg(ptr, new_val); } +EXPORT_SYMBOL(atomic64_read); /** * atomic64_read - read atomic64 variable @@ -74,6 +79,7 @@ u64 atomic64_read(atomic64_t *ptr) return res; } +EXPORT_SYMBOL(atomic64_read); /** * atomic64_add_return - add and return @@ -103,21 +109,25 @@ noinline u64 atomic64_add_return(u64 delta, atomic64_t *ptr) return new_val; } +EXPORT_SYMBOL(atomic64_add_return); u64 atomic64_sub_return(u64 delta, atomic64_t *ptr) { return atomic64_add_return(-delta, ptr); } +EXPORT_SYMBOL(atomic64_sub_return); u64 atomic64_inc_return(atomic64_t *ptr) { return atomic64_add_return(1, ptr); } +EXPORT_SYMBOL(atomic64_inc_return); u64 atomic64_dec_return(atomic64_t *ptr) { return atomic64_sub_return(1, ptr); } +EXPORT_SYMBOL(atomic64_dec_return); /** * atomic64_add - add integer to atomic64 variable @@ -130,6 +140,7 @@ void atomic64_add(u64 delta, atomic64_t *ptr) { atomic64_add_return(delta, ptr); } +EXPORT_SYMBOL(atomic64_add); /** * atomic64_sub - subtract the atomic64 variable @@ -142,6 +153,7 @@ void atomic64_sub(u64 delta, atomic64_t *ptr) { atomic64_add(-delta, ptr); } +EXPORT_SYMBOL(atomic64_sub); /** * atomic64_sub_and_test - subtract value from variable and test result @@ -158,6 +170,7 @@ int atomic64_sub_and_test(u64 delta, atomic64_t *ptr) return old_val == 0; } +EXPORT_SYMBOL(atomic64_sub_and_test); /** * atomic64_inc - increment atomic64 variable @@ -169,6 +182,7 @@ void atomic64_inc(atomic64_t *ptr) { atomic64_add(1, ptr); } +EXPORT_SYMBOL(atomic64_inc); /** * atomic64_dec - decrement atomic64 variable @@ -180,6 +194,7 @@ void atomic64_dec(atomic64_t *ptr) { atomic64_sub(1, ptr); } +EXPORT_SYMBOL(atomic64_dec); /** * atomic64_dec_and_test - decrement and test @@ -193,6 +208,7 @@ int atomic64_dec_and_test(atomic64_t *ptr) { return atomic64_sub_and_test(1, ptr); } +EXPORT_SYMBOL(atomic64_dec_and_test); /** * atomic64_inc_and_test - increment and test @@ -206,6 +222,7 @@ int atomic64_inc_and_test(atomic64_t *ptr) { return atomic64_sub_and_test(-1, ptr); } +EXPORT_SYMBOL(atomic64_inc_and_test); /** * atomic64_add_negative - add and test if negative @@ -222,3 +239,4 @@ int atomic64_add_negative(u64 delta, atomic64_t *ptr) return old_val < 0; } +EXPORT_SYMBOL(atomic64_add_negative); From 3a8d1788b37435baf6c296f4ea8beb4fa4955f44 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 19:56:36 +0200 Subject: [PATCH 0149/1346] x86: atomic64: Improve atomic64_xchg() Remove the read-first logic from atomic64_xchg() and simplify the loop. This function was the last user of __atomic64_read() - remove it. Also, change the 'real_val' assumption from the somewhat quirky 1ULL << 32 value to the (just as arbitrary, but simpler) value of 0. Reported-by: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic_32.h | 9 --------- arch/x86/lib/atomic64_32.c | 21 +++++++++++++++------ 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index aa045deb2e7..d7c8849b8c6 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -268,15 +268,6 @@ typedef struct { #define ATOMIC64_INIT(val) { (val) } -/** - * atomic64_read - read atomic64 variable - * @ptr: pointer of type atomic64_t - * - * Atomically reads the value of @v. - * Doesn't imply a read memory barrier. - */ -#define __atomic64_read(ptr) ((ptr)->counter) - extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val); /** diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index 6722a092e40..a804f96e90e 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -33,14 +33,23 @@ EXPORT_SYMBOL(atomic64_cmpxchg); * Atomically xchgs the value of @ptr to @new_val and returns * the old value. */ - u64 atomic64_xchg(atomic64_t *ptr, u64 new_val) { - u64 old_val; + /* + * Try first with a (possibly incorrect) assumption about + * what we have there. We'll do two loops most likely, + * but we'll get an ownership MESI transaction straight away + * instead of a read transaction followed by a + * flush-for-ownership transaction: + */ + u64 old_val, real_val = 0; do { - old_val = __atomic64_read(ptr); - } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val); + old_val = real_val; + + real_val = atomic64_cmpxchg(ptr, old_val, new_val); + + } while (real_val != old_val); return old_val; } @@ -91,13 +100,13 @@ EXPORT_SYMBOL(atomic64_read); noinline u64 atomic64_add_return(u64 delta, atomic64_t *ptr) { /* - * Try first with a (probably incorrect) assumption about + * Try first with a (possibly incorrect) assumption about * what we have there. We'll do two loops most likely, * but we'll get an ownership MESI transaction straight away * instead of a read transaction followed by a * flush-for-ownership transaction: */ - u64 old_val, new_val, real_val = 1ULL << 32; + u64 old_val, new_val, real_val = 0; do { old_val = real_val; From ddf9a003d32f720805ac30bcc15755e9289073de Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 3 Jul 2009 20:11:30 +0200 Subject: [PATCH 0150/1346] x86: atomic64: Clean up atomic64_sub_and_test() and atomic64_add_negative() Linus noticed that the variable name 'old_val' is confusingly named in these functions - the correct naming is 'new_val'. Reported-by: Linus Torvalds Cc: Eric Dumazet Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/lib/atomic64_32.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index a804f96e90e..1d98c9eb6ea 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -175,9 +175,9 @@ EXPORT_SYMBOL(atomic64_sub); */ int atomic64_sub_and_test(u64 delta, atomic64_t *ptr) { - u64 old_val = atomic64_sub_return(delta, ptr); + u64 new_val = atomic64_sub_return(delta, ptr); - return old_val == 0; + return new_val == 0; } EXPORT_SYMBOL(atomic64_sub_and_test); @@ -244,8 +244,8 @@ EXPORT_SYMBOL(atomic64_inc_and_test); */ int atomic64_add_negative(u64 delta, atomic64_t *ptr) { - long long old_val = atomic64_add_return(delta, ptr); + s64 new_val = atomic64_add_return(delta, ptr); - return old_val < 0; + return new_val < 0; } EXPORT_SYMBOL(atomic64_add_negative); From 5a5e02a614e59db7536cd11029e6674adc41b191 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Jul 2009 09:35:44 +0100 Subject: [PATCH 0151/1346] intel-iommu: Fix dma vs. mm page confusion with aligned_nrpages() The aligned_nrpages() function rounds up to the next VM page, but returns its result as a number of DMA pages. Purely theoretical except on IA64, which doesn't boot with VT-d right now anyway. Signed-off-by: David Woodhouse --- drivers/pci/intel-iommu.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 53075424a43..ad85e95d2dc 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2368,15 +2368,15 @@ error: return ret; } +/* Returns a number of VTD pages, but aligned to MM page size */ static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size) { host_addr &= ~PAGE_MASK; - host_addr += size + PAGE_SIZE - 1; - - return host_addr >> VTD_PAGE_SHIFT; + return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; } +/* This takes a number of _MM_ pages, not VTD pages */ static struct iova *intel_alloc_iova(struct device *dev, struct dmar_domain *domain, unsigned long nrpages, uint64_t dma_mask) @@ -2506,7 +2506,8 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, iommu = domain_get_iommu(domain); size = aligned_nrpages(paddr, size); - iova = intel_alloc_iova(hwdev, domain, size, pdev->dma_mask); + iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), + pdev->dma_mask); if (!iova) goto error; @@ -2797,7 +2798,8 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne for_each_sg(sglist, sg, nelems, i) size += aligned_nrpages(sg->offset, sg->length); - iova = intel_alloc_iova(hwdev, domain, size, pdev->dma_mask); + iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), + pdev->dma_mask); if (!iova) { sglist->dma_length = 0; return 0; From 1e4c64c46d413de84cc0b786bd6a9b555ba7d111 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Jul 2009 10:40:38 +0100 Subject: [PATCH 0152/1346] intel-iommu: Don't set identity mapping for bypassed graphics devices We should check iommu_dummy() _first_, because that means it's attached to an iommu that we've just disabled completely. At the moment, we might try to put the device into the identity mapping domain. Signed-off-by: David Woodhouse --- drivers/pci/intel-iommu.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index ad85e95d2dc..3e3910127fc 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2447,8 +2447,11 @@ static int iommu_no_mapping(struct pci_dev *pdev) { int found; + if (iommu_dummy(pdev)) + return 1; + if (!iommu_identity_mapping) - return iommu_dummy(pdev); + return 0; found = identity_mapping(pdev); if (found) { @@ -2480,7 +2483,7 @@ static int iommu_no_mapping(struct pci_dev *pdev) } } - return iommu_dummy(pdev); + return 0; } static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, From a79f0da80a508448434476b77f9d3d1a469eab67 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Jul 2009 16:50:10 +0200 Subject: [PATCH 0153/1346] x86: atomic64: Inline atomic64_read() again Now atomic64_read() is light weight (no register pressure and small icache), we can inline it again. Also use "=&A" constraint instead of "+A" to avoid warning about unitialized 'res' variable. (gcc had to force 0 in eax/edx) $ size vmlinux.prev vmlinux.after text data bss dec hex filename 4908667 451676 1684868 7045211 6b805b vmlinux.prev 4908651 451676 1684868 7045195 6b804b vmlinux.after Signed-off-by: Eric Dumazet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: David Howells Cc: Andrew Morton Cc: Arnd Bergmann LKML-Reference: <4A4E1AA2.30002@gmail.com> [ Also fix typo in atomic64_set() export ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/atomic_32.h | 22 ++++++++++++++++++++++ arch/x86/lib/atomic64_32.c | 23 +---------------------- 2 files changed, 23 insertions(+), 22 deletions(-) diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h index d7c8849b8c6..dc5a667ff79 100644 --- a/arch/x86/include/asm/atomic_32.h +++ b/arch/x86/include/asm/atomic_32.h @@ -295,6 +295,28 @@ extern void atomic64_set(atomic64_t *ptr, u64 new_val); * * Atomically reads the value of @ptr and returns it. */ +static inline u64 atomic64_read(atomic64_t *ptr) +{ + u64 res; + + /* + * Note, we inline this atomic64_t primitive because + * it only clobbers EAX/EDX and leaves the others + * untouched. We also (somewhat subtly) rely on the + * fact that cmpxchg8b returns the current 64-bit value + * of the memory location we are touching: + */ + asm volatile( + "mov %%ebx, %%eax\n\t" + "mov %%ecx, %%edx\n\t" + LOCK_PREFIX "cmpxchg8b %1\n" + : "=&A" (res) + : "m" (*ptr) + ); + + return res; +} + extern u64 atomic64_read(atomic64_t *ptr); /** diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c index 1d98c9eb6ea..824fa0be55a 100644 --- a/arch/x86/lib/atomic64_32.c +++ b/arch/x86/lib/atomic64_32.c @@ -66,31 +66,10 @@ void atomic64_set(atomic64_t *ptr, u64 new_val) { atomic64_xchg(ptr, new_val); } -EXPORT_SYMBOL(atomic64_read); +EXPORT_SYMBOL(atomic64_set); /** - * atomic64_read - read atomic64 variable - * @ptr: pointer to type atomic64_t - * - * Atomically reads the value of @ptr and returns it. - */ -u64 atomic64_read(atomic64_t *ptr) -{ - u64 res; - - asm volatile( - "mov %%ebx, %%eax\n\t" - "mov %%ecx, %%edx\n\t" - LOCK_PREFIX "cmpxchg8b %1\n" - : "+A" (res) - : "m" (*ptr) - ); - - return res; -} EXPORT_SYMBOL(atomic64_read); - -/** * atomic64_add_return - add and return * @delta: integer value to add * @ptr: pointer to type atomic64_t From 1b7bc0a1618b4de1e6f55c6d95b790f4ab6fcd9e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Jul 2009 10:49:46 +0100 Subject: [PATCH 0154/1346] intel-iommu: Fix reattaching of devices to identity mapping domain When we reattach a device to the si_domain (because it's been removed from a VM), we weren't calling domain_context_mapping() to actually tell the hardware about that. We should really put the call to domain_context_mapping() into domain_add_dev_info() -- we never call the latter without also doing the former, and we can keep the error paths simple that way. But that's a cleanup which can wait for 2.6.32 now. Signed-off-by: David Woodhouse --- drivers/pci/intel-iommu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 3e3910127fc..73a5c71dd37 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2475,6 +2475,9 @@ static int iommu_no_mapping(struct pci_dev *pdev) if (pdev->dma_mask > DMA_BIT_MASK(32)) { int ret; ret = domain_add_dev_info(si_domain, pdev); + if (ret) + return 0; + ret = domain_context_mapping(si_domain, pdev, CONTEXT_TT_MULTI_LEVEL); if (!ret) { printk(KERN_INFO "64bit %s uses identity mapping\n", pci_name(pdev)); From 40e4aa34324bff3938a900014254f88943d05e15 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Jul 2009 10:55:41 +0100 Subject: [PATCH 0155/1346] intel-iommu: Add iommu_should_identity_map() function We do this twice, and it's about to get more complicated. This makes the code slightly clearer about what it's doing, too. Signed-off-by: David Woodhouse --- drivers/pci/intel-iommu.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 73a5c71dd37..ae5ccdf8b19 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2442,6 +2442,11 @@ static int iommu_dummy(struct pci_dev *pdev) return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; } +static int iommu_should_identity_map(struct pci_dev *pdev) +{ + return pdev->dma_mask > DMA_BIT_MASK(32); +} + /* Check if the pdev needs to go through non-identity map and unmap process.*/ static int iommu_no_mapping(struct pci_dev *pdev) { @@ -2455,7 +2460,7 @@ static int iommu_no_mapping(struct pci_dev *pdev) found = identity_mapping(pdev); if (found) { - if (pdev->dma_mask > DMA_BIT_MASK(32)) + if (iommu_should_identity_map(pdev)) return 1; else { /* @@ -2472,7 +2477,7 @@ static int iommu_no_mapping(struct pci_dev *pdev) * In case of a detached 64 bit DMA device from vm, the device * is put into si_domain for identity mapping. */ - if (pdev->dma_mask > DMA_BIT_MASK(32)) { + if (iommu_should_identity_map(pdev)) { int ret; ret = domain_add_dev_info(si_domain, pdev); if (ret) From 62edf5dc4a524e4cb525e6020b955a1ad593d9ba Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Jul 2009 10:59:46 +0100 Subject: [PATCH 0156/1346] intel-iommu: Restore DMAR_BROKEN_GFX_WA option for broken graphics drivers We need to give people a little more time to fix the broken drivers. Re-introduce this, but tied in properly with the 'iommu=pt' support this time. Change the config option name and make it default to 'no' too. Signed-off-by: David Woodhouse --- arch/x86/Kconfig | 12 ++++++++++++ drivers/pci/intel-iommu.c | 29 +++++++++++++++++++---------- 2 files changed, 31 insertions(+), 10 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c07f7220590..738bdc6b0f8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1913,6 +1913,18 @@ config DMAR_DEFAULT_ON recommended you say N here while the DMAR code remains experimental. +config DMAR_BROKEN_GFX_WA + def_bool n + prompt "Workaround broken graphics drivers (going away soon)" + depends on DMAR + ---help--- + Current Graphics drivers tend to use physical address + for DMA and avoid using DMA APIs. Setting this config + option permits the IOMMU driver to set a unity map for + all the OS-visible memory. Hence the driver can continue + to use physical addresses for DMA, at least until this + option is removed in the 2.6.32 kernel. + config DMAR_FLOPPY_WA def_bool y depends on DMAR diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index ae5ccdf8b19..5ee8305257e 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2127,16 +2127,18 @@ static int iommu_prepare_static_identity_mapping(void) return -EFAULT; for_each_pci_dev(pdev) { - printk(KERN_INFO "IOMMU: identity mapping for device %s\n", - pci_name(pdev)); + if (iommu_identity_mapping == 1 || IS_GFX_DEVICE(pdev)) { + printk(KERN_INFO "IOMMU: identity mapping for device %s\n", + pci_name(pdev)); - ret = domain_context_mapping(si_domain, pdev, - CONTEXT_TT_MULTI_LEVEL); - if (ret) - return ret; - ret = domain_add_dev_info(si_domain, pdev); - if (ret) - return ret; + ret = domain_context_mapping(si_domain, pdev, + CONTEXT_TT_MULTI_LEVEL); + if (ret) + return ret; + ret = domain_add_dev_info(si_domain, pdev); + if (ret) + return ret; + } } return 0; @@ -2291,6 +2293,10 @@ int __init init_dmars(void) * identity mapping if iommu_identity_mapping is set. */ if (!iommu_pass_through) { +#ifdef CONFIG_DMAR_BROKEN_GFX_WA + if (!iommu_identity_mapping) + iommu_identity_mapping = 2; +#endif if (iommu_identity_mapping) iommu_prepare_static_identity_mapping(); /* @@ -2444,7 +2450,10 @@ static int iommu_dummy(struct pci_dev *pdev) static int iommu_should_identity_map(struct pci_dev *pdev) { - return pdev->dma_mask > DMA_BIT_MASK(32); + if (iommu_identity_mapping == 2) + return IS_GFX_DEVICE(pdev); + else + return pdev->dma_mask > DMA_BIT_MASK(32); } /* Check if the pdev needs to go through non-identity map and unmap process.*/ From 02358fcfa54ce018a0bb56ca9f5a898de574a9d3 Mon Sep 17 00:00:00 2001 From: Herton Ronaldo Krzesinski Date: Sat, 4 Jul 2009 01:44:59 -0300 Subject: [PATCH 0157/1346] ALSA: hda - move 8086:fb30 quirk (stac9205) to the proper section Signed-off-by: Herton Ronaldo Krzesinski Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_sigmatel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 14f3c3e0f62..41b5b3a18c1 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1590,8 +1590,6 @@ static struct snd_pci_quirk stac9200_cfg_tbl[] = { /* SigmaTel reference board */ SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x2668, "DFI LanParty", STAC_REF), - SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0xfb30, - "SigmaTel",STAC_9205_REF), SND_PCI_QUIRK(PCI_VENDOR_ID_DFI, 0x3101, "DFI LanParty", STAC_REF), /* Dell laptops have BIOS problem */ @@ -2344,6 +2342,8 @@ static struct snd_pci_quirk stac9205_cfg_tbl[] = { /* SigmaTel reference board */ SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x2668, "DFI LanParty", STAC_9205_REF), + SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0xfb30, + "SigmaTel", STAC_9205_REF), SND_PCI_QUIRK(PCI_VENDOR_ID_DFI, 0x3101, "DFI LanParty", STAC_9205_REF), /* Dell */ From 736768325efcbee7b0861d62670d01a54c2d158b Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 4 Jul 2009 14:08:36 +0100 Subject: [PATCH 0158/1346] intel-iommu: No mapping for non-PCI devices This should fix kernel.org bug #11821, where the dcdbas driver makes up a platform device and then uses dma_alloc_coherent() on it, in an attempt to get memory < 4GiB. Signed-off-by: David Woodhouse --- drivers/pci/intel-iommu.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 5ee8305257e..fa052dd8991 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2457,10 +2457,15 @@ static int iommu_should_identity_map(struct pci_dev *pdev) } /* Check if the pdev needs to go through non-identity map and unmap process.*/ -static int iommu_no_mapping(struct pci_dev *pdev) +static int iommu_no_mapping(struct device *dev) { + struct pci_dev *pdev; int found; + if (unlikely(dev->bus != &pci_bus_type)) + return 1; + + pdev = to_pci_dev(dev); if (iommu_dummy(pdev)) return 1; @@ -2516,7 +2521,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, BUG_ON(dir == DMA_NONE); - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(hwdev)) return paddr; domain = get_valid_domain_for_dev(pdev); @@ -2656,7 +2661,7 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, struct iova *iova; struct intel_iommu *iommu; - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(dev)) return; domain = find_domain(pdev); @@ -2747,7 +2752,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist, struct iova *iova; struct intel_iommu *iommu; - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(hwdev)) return; domain = find_domain(pdev); @@ -2806,7 +2811,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); - if (iommu_no_mapping(pdev)) + if (iommu_no_mapping(hwdev)) return intel_nontranslate_map_sg(hwdev, sglist, nelems, dir); domain = get_valid_domain_for_dev(pdev); From 64614e66fbfcaa57598c1678d699520dfbf4f531 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 3 Jul 2009 09:12:46 +0000 Subject: [PATCH 0159/1346] usb: allow sh7724 to enable on-chip r8a66597 The sh7724 processor has two on-chip r8a66597 blocks, so add it to the list of processors for SUPERH_ON_CHIP_R8A66597. Signed-off-by: Magnus Damm Signed-off-by: Paul Mundt --- drivers/usb/host/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index 1576a0520ad..0c03471f0d4 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -337,10 +337,10 @@ config USB_R8A66597_HCD config SUPERH_ON_CHIP_R8A66597 boolean "Enable SuperH on-chip R8A66597 USB" - depends on USB_R8A66597_HCD && (CPU_SUBTYPE_SH7366 || CPU_SUBTYPE_SH7723) + depends on USB_R8A66597_HCD && (CPU_SUBTYPE_SH7366 || CPU_SUBTYPE_SH7723 || CPU_SUBTYPE_SH7724) help This driver enables support for the on-chip R8A66597 in the - SH7366 and SH7723 processors. + SH7366, SH7723 and SH7724 processors. config USB_WHCI_HCD tristate "Wireless USB Host Controller Interface (WHCI) driver (EXPERIMENTAL)" From 9731f4a202f29ff402ea2ddad7ff6f3a559c0c82 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 3 Jul 2009 09:40:03 +0000 Subject: [PATCH 0160/1346] sh: add r8a66597 usb0 host to the se7724 board Add USB host support for port CN27 on the Solution Engine 7724 board. The r8a66597-hcd driver is hooked up as a platform device and some registers are configured to enable the USB host function. The hardware driving the USB port is the on-chip USB0 block in the sh7724 processor configured as USB host controller. Signed-off-by: Magnus Damm Signed-off-by: Paul Mundt --- arch/sh/boards/mach-se/7724/setup.c | 38 +++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index c050a8d76df..8fed45a2fb8 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -19,6 +19,7 @@ #include #include #include +#include #include