From 53a08807c01989c6847bb135d8d43f61c5dfdda5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 3 Dec 2008 12:41:26 +0100 Subject: block: internal dequeue shouldn't start timer blkdev_dequeue_request() and elv_dequeue_request() are equivalent and both start the timeout timer. Barrier code dequeues the original barrier request but doesn't passes the request itself to lower level driver, only broken down proxy requests; however, as the original barrier code goes through the same dequeue path and timeout timer is started on it. If barrier sequence takes long enough, this timer expires but the low level driver has no idea about this request and oops follows. Timeout timer shouldn't have been started on the original barrier request as it never goes through actual IO. This patch unexports elv_dequeue_request(), which has no external user anyway, and makes it operate on elevator proper w/o adding the timer and make blkdev_dequeue_request() call elv_dequeue_request() and add timer. Internal users which don't pass the request to driver - barrier code and end_that_request_last() - are converted to use elv_dequeue_request(). Signed-off-by: Tejun Heo Cc: Mike Anderson Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a135256b272c..9cc7cc5fdce1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -786,6 +786,8 @@ static inline void blk_run_address_space(struct address_space *mapping) blk_run_backing_dev(mapping->backing_dev_info, NULL); } +extern void blkdev_dequeue_request(struct request *req); + /* * blk_end_request() and friends. * __blk_end_request() and end_request() must be called with @@ -820,11 +822,6 @@ extern void blk_update_request(struct request *rq, int error, extern unsigned int blk_rq_bytes(struct request *rq); extern unsigned int blk_rq_cur_bytes(struct request *rq); -static inline void blkdev_dequeue_request(struct request *req) -{ - elv_dequeue_request(req->q, req); -} - /* * Access functions for manipulating queue properties */ -- cgit v1.2.3 From 0e435ac26e3f951d83338ed3d4ab7dc0fe0055bc Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Wed, 3 Dec 2008 12:55:08 +0100 Subject: block: fix setting of max_segment_size and seg_boundary mask Fix setting of max_segment_size and seg_boundary mask for stacked md/dm devices. When stacking devices (LVM over MD over SCSI) some of the request queue parameters are not set up correctly in some cases by default, namely max_segment_size and and seg_boundary mask. If you create MD device over SCSI, these attributes are zeroed. Problem become when there is over this mapping next device-mapper mapping - queue attributes are set in DM this way: request_queue max_segment_size seg_boundary_mask SCSI 65536 0xffffffff MD RAID1 0 0 LVM 65536 -1 (64bit) Unfortunately bio_add_page (resp. bio_phys_segments) calculates number of physical segments according to these parameters. During the generic_make_request() is segment cout recalculated and can increase bio->bi_phys_segments count over the allowed limit. (After bio_clone() in stack operation.) Thi is specially problem in CCISS driver, where it produce OOPS here BUG_ON(creq->nr_phys_segments > MAXSGENTRIES); (MAXSEGENTRIES is 31 by default.) Sometimes even this command is enough to cause oops: dd iflag=direct if=/dev// of=/dev/null bs=128000 count=10 This command generates bios with 250 sectors, allocated in 32 4k-pages (last page uses only 1024 bytes). For LVM layer, it allocates bio with 31 segments (still OK for CCISS), unfortunatelly on lower layer it is recalculated to 32 segments and this violates CCISS restriction and triggers BUG_ON(). The patch tries to fix it by: * initializing attributes above in queue request constructor blk_queue_make_request() * make sure that blk_queue_stack_limits() inherits setting (DM uses its own function to set the limits because it blk_queue_stack_limits() was introduced later. It should probably switch to use generic stack limit function too.) * sets the default seg_boundary value in one place (blkdev.h) * use this mask as default in DM (instead of -1, which differs in 64bit) Bugs related to this: https://bugzilla.redhat.com/show_bug.cgi?id=471639 http://bugzilla.kernel.org/show_bug.cgi?id=8672 Signed-off-by: Milan Broz Reviewed-by: Alasdair G Kergon Cc: Neil Brown Cc: FUJITA Tomonori Cc: Tejun Heo Cc: Mike Miller Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- block/blk-settings.c | 4 ++++ drivers/md/dm-table.c | 2 +- include/linux/blkdev.h | 2 ++ 4 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 7a779d7c69c9..c36aa98fafa3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -592,7 +592,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) 1 << QUEUE_FLAG_STACKABLE); q->queue_lock = lock; - blk_queue_segment_boundary(q, 0xffffffff); + blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK); blk_queue_make_request(q, __make_request); blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE); diff --git a/block/blk-settings.c b/block/blk-settings.c index 41392fbe19ff..afa55e14e278 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -125,6 +125,9 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) q->nr_requests = BLKDEV_MAX_RQ; blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS); blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS); + blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK); + blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE); + q->make_request_fn = mfn; q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; @@ -314,6 +317,7 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) /* zero is "infinity" */ t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); + t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask); t->max_phys_segments = min(t->max_phys_segments, b->max_phys_segments); t->max_hw_segments = min(t->max_hw_segments, b->max_hw_segments); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index a63161aec487..04e5fd742c2c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -668,7 +668,7 @@ static void check_for_valid_limits(struct io_restrictions *rs) if (!rs->max_segment_size) rs->max_segment_size = MAX_SEGMENT_SIZE; if (!rs->seg_boundary_mask) - rs->seg_boundary_mask = -1; + rs->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; if (!rs->bounce_pfn) rs->bounce_pfn = -1; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9cc7cc5fdce1..6dcd30d806cd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -918,6 +918,8 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); #define MAX_SEGMENT_SIZE 65536 +#define BLK_SEG_BOUNDARY_MASK 0xFFFFFFFFUL + #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) static inline int queue_hardsect_size(struct request_queue *q) -- cgit v1.2.3 From d253eee20195b25e298bf162a6e72f14bf4803e5 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 3 Dec 2008 15:52:35 -0800 Subject: can: Fix CAN_(EFF|RTR)_FLAG handling in can_filter Due to a wrong safety check in af_can.c it was not possible to filter for SFF frames with a specific CAN identifier without getting the same selected CAN identifier from a received EFF frame also. This fix has a minimum (but user visible) impact on the CAN filter API and therefore the CAN version is set to a new date. Indeed the 'old' API is still working as-is. But when now setting CAN_(EFF|RTR)_FLAG in can_filter.can_mask you might get less traffic than before - but still the stuff that you expected to get for your defined filter ... Thanks to Kurt Van Dijck for pointing at this issue and for the review. Signed-off-by: Oliver Hartkopp Acked-by: Kurt Van Dijck Signed-off-by: David S. Miller --- include/linux/can/core.h | 2 +- net/can/af_can.c | 63 ++++++++++++++++++++++++++++++++++++------------ net/can/bcm.c | 7 +++--- 3 files changed, 53 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index e9ca210ffa5b..f50785ad4781 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -19,7 +19,7 @@ #include #include -#define CAN_VERSION "20071116" +#define CAN_VERSION "20081130" /* increment this number each time you change some user-space interface */ #define CAN_ABI_VERSION "8" diff --git a/net/can/af_can.c b/net/can/af_can.c index 7d4d2b3c137e..d8173e50cb87 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -319,23 +319,52 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev) return n ? d : NULL; } +/** + * find_rcv_list - determine optimal filterlist inside device filter struct + * @can_id: pointer to CAN identifier of a given can_filter + * @mask: pointer to CAN mask of a given can_filter + * @d: pointer to the device filter struct + * + * Description: + * Returns the optimal filterlist to reduce the filter handling in the + * receive path. This function is called by service functions that need + * to register or unregister a can_filter in the filter lists. + * + * A filter matches in general, when + * + * & mask == can_id & mask + * + * so every bit set in the mask (even CAN_EFF_FLAG, CAN_RTR_FLAG) describe + * relevant bits for the filter. + * + * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can + * filter for error frames (CAN_ERR_FLAG bit set in mask). For error frames + * there is a special filterlist and a special rx path filter handling. + * + * Return: + * Pointer to optimal filterlist for the given can_id/mask pair. + * Constistency checked mask. + * Reduced can_id to have a preprocessed filter compare value. + */ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, struct dev_rcv_lists *d) { canid_t inv = *can_id & CAN_INV_FILTER; /* save flag before masking */ - /* filter error frames */ + /* filter for error frames in extra filterlist */ if (*mask & CAN_ERR_FLAG) { - /* clear CAN_ERR_FLAG in list entry */ + /* clear CAN_ERR_FLAG in filter entry */ *mask &= CAN_ERR_MASK; return &d->rx[RX_ERR]; } - /* ensure valid values in can_mask */ - if (*mask & CAN_EFF_FLAG) - *mask &= (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG); - else - *mask &= (CAN_SFF_MASK | CAN_RTR_FLAG); + /* with cleared CAN_ERR_FLAG we have a simple mask/value filterpair */ + +#define CAN_EFF_RTR_FLAGS (CAN_EFF_FLAG | CAN_RTR_FLAG) + + /* ensure valid values in can_mask for 'SFF only' frame filtering */ + if ((*mask & CAN_EFF_FLAG) && !(*can_id & CAN_EFF_FLAG)) + *mask &= (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS); /* reduce condition testing at receive time */ *can_id &= *mask; @@ -348,15 +377,19 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, if (!(*mask)) return &d->rx[RX_ALL]; - /* use extra filterset for the subscription of exactly *ONE* can_id */ - if (*can_id & CAN_EFF_FLAG) { - if (*mask == (CAN_EFF_MASK | CAN_EFF_FLAG)) { - /* RFC: a use-case for hash-tables in the future? */ - return &d->rx[RX_EFF]; + /* extra filterlists for the subscription of a single non-RTR can_id */ + if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS) + && !(*can_id & CAN_RTR_FLAG)) { + + if (*can_id & CAN_EFF_FLAG) { + if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) { + /* RFC: a future use-case for hash-tables? */ + return &d->rx[RX_EFF]; + } + } else { + if (*mask == (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS)) + return &d->rx_sff[*can_id]; } - } else { - if (*mask == CAN_SFF_MASK) - return &d->rx_sff[*can_id]; } /* default: filter via can_id/can_mask */ diff --git a/net/can/bcm.c b/net/can/bcm.c index d0dd382001e2..da0d426c0ce4 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -64,10 +64,11 @@ #define BCM_CAN_DLC_MASK 0x0F /* clean private flags in can_dlc by masking */ /* get best masking value for can_rx_register() for a given single can_id */ -#define REGMASK(id) ((id & CAN_RTR_FLAG) | ((id & CAN_EFF_FLAG) ? \ - (CAN_EFF_MASK | CAN_EFF_FLAG) : CAN_SFF_MASK)) +#define REGMASK(id) ((id & CAN_EFF_FLAG) ? \ + (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ + (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -#define CAN_BCM_VERSION "20080415" +#define CAN_BCM_VERSION CAN_VERSION static __initdata const char banner[] = KERN_INFO "can: broadcast manager protocol (rev " CAN_BCM_VERSION ")\n"; -- cgit v1.2.3 From fd4ce1acd0f8558033b1a6968001552bd7671e6d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 5 Nov 2008 14:58:42 +0100 Subject: [PATCH 1/2] kill FMODE_NDELAY_NOW Update FMODE_NDELAY before each ioctl call so that we can kill the magic FMODE_NDELAY_NOW. It would be even better to do this directly in setfl(), but for that we'd need to have FMODE_NDELAY for all files, not just block special files. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- block/compat_ioctl.c | 8 +++++++- drivers/scsi/sd.c | 2 +- drivers/scsi/sr.c | 2 +- fs/block_dev.c | 10 +++++++++- include/linux/fs.h | 1 - 5 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index d43e6087badc..67eb93cff699 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -722,8 +722,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct backing_dev_info *bdi; loff_t size; + /* + * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have + * to updated it before every ioctl. + */ if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY_NOW; + mode |= FMODE_NDELAY; + else + mode &= ~FMODE_NDELAY; switch (cmd) { case HDIO_GETGEO: diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index c9e1242eaf25..5081b3981d3c 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -757,7 +757,7 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, * access to the device is prohibited. */ error = scsi_nonblockable_ioctl(sdp, cmd, p, - (mode & FMODE_NDELAY_NOW) != 0); + (mode & FMODE_NDELAY) != 0); if (!scsi_block_when_processing_errors(sdp) || !error) return error; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 62b6633e3a97..45b66b98a516 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -521,7 +521,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, * if it doesn't recognise the ioctl */ ret = scsi_nonblockable_ioctl(sdev, cmd, argp, - (mode & FMODE_NDELAY_NOW) != 0); + (mode & FMODE_NDELAY) != 0); if (ret != -ENODEV) return ret; return scsi_ioctl(sdev, cmd, argp); diff --git a/fs/block_dev.c b/fs/block_dev.c index 7c727523bc54..99e0ae1a4c78 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1206,8 +1206,16 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct block_device *bdev = I_BDEV(file->f_mapping->host); fmode_t mode = file->f_mode; + + /* + * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have + * to updated it before every ioctl. + */ if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY_NOW; + mode |= FMODE_NDELAY; + else + mode &= ~FMODE_NDELAY; + return blkdev_ioctl(bdev, mode, cmd, arg); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 0dcdd9458f4b..b3345a90e11a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -79,7 +79,6 @@ extern int dir_notify_enable; #define FMODE_NDELAY ((__force fmode_t)32) #define FMODE_EXCL ((__force fmode_t)64) #define FMODE_WRITE_IOCTL ((__force fmode_t)128) -#define FMODE_NDELAY_NOW ((__force fmode_t)256) #define RW_MASK 1 #define RWA_MASK 2 -- cgit v1.2.3 From fc9161e54d0dbf799beff9692ea1cc6237162b85 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 5 Nov 2008 14:58:46 +0100 Subject: [PATCH 2/2] documnt FMODE_ constants Make sure all FMODE_ constants are documents, and ensure a coherent style for the already existing comments. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b3345a90e11a..4a853ef6fd35 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -63,21 +63,23 @@ extern int dir_notify_enable; #define MAY_ACCESS 16 #define MAY_OPEN 32 -#define FMODE_READ ((__force fmode_t)1) -#define FMODE_WRITE ((__force fmode_t)2) - -/* Internal kernel extensions */ -#define FMODE_LSEEK ((__force fmode_t)4) -#define FMODE_PREAD ((__force fmode_t)8) -#define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */ - -/* File is being opened for execution. Primary users of this flag are - distributed filesystems that can use it to achieve correct ETXTBUSY - behavior for cross-node execution/opening_for_writing of files */ -#define FMODE_EXEC ((__force fmode_t)16) - -#define FMODE_NDELAY ((__force fmode_t)32) -#define FMODE_EXCL ((__force fmode_t)64) +/* file is open for reading */ +#define FMODE_READ ((__force fmode_t)1) +/* file is open for writing */ +#define FMODE_WRITE ((__force fmode_t)2) +/* file is seekable */ +#define FMODE_LSEEK ((__force fmode_t)4) +/* file can be accessed using pread/pwrite */ +#define FMODE_PREAD ((__force fmode_t)8) +#define FMODE_PWRITE FMODE_PREAD /* These go hand in hand */ +/* File is opened for execution with sys_execve / sys_uselib */ +#define FMODE_EXEC ((__force fmode_t)16) +/* File is opened with O_NDELAY (only set for block devices) */ +#define FMODE_NDELAY ((__force fmode_t)32) +/* File is opened with O_EXCL (only set for block devices) */ +#define FMODE_EXCL ((__force fmode_t)64) +/* File is opened using open(.., 3, ..) and is writeable only for ioctls + (specialy hack for floppy.c) */ #define FMODE_WRITE_IOCTL ((__force fmode_t)128) #define RW_MASK 1 -- cgit v1.2.3 From f2f1fa78a155524b849edf359e42a3001ea652c0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 5 Dec 2008 14:49:18 -0800 Subject: Enforce a minimum SG_IO timeout There's no point in having too short SG_IO timeouts, since if the command does end up timing out, we'll end up through the reset sequence that is several seconds long in order to abort the command that timed out. As a result, shorter timeouts than a few seconds simply do not make sense, as the recovery would be longer than the timeout itself. Add a BLK_MIN_SG_TIMEOUT to match the existign BLK_DEFAULT_SG_TIMEOUT. Suggested-by: Alan Cox Acked-by: Tejun Heo Acked-by: Jens Axboe Cc: Jeff Garzik Signed-off-by: Linus Torvalds --- block/bsg.c | 2 ++ block/scsi_ioctl.c | 2 ++ include/linux/blkdev.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include') diff --git a/block/bsg.c b/block/bsg.c index e8bd2475682a..e73e50daf3d0 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -202,6 +202,8 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, rq->timeout = q->sg_timeout; if (!rq->timeout) rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + if (rq->timeout < BLK_MIN_SG_TIMEOUT) + rq->timeout = BLK_MIN_SG_TIMEOUT; return 0; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 5963cf91a3a0..d0bb92cbefb9 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -208,6 +208,8 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq, rq->timeout = q->sg_timeout; if (!rq->timeout) rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + if (rq->timeout < BLK_MIN_SG_TIMEOUT) + rq->timeout = BLK_MIN_SG_TIMEOUT; return 0; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6dcd30d806cd..031a315c0509 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -662,6 +662,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) +#define BLK_MIN_SG_TIMEOUT (7 * HZ) #ifdef CONFIG_BOUNCE extern int init_emergency_isa_pool(void); -- cgit v1.2.3 From a64e64944f4b8ce3288519555dbaa0232414b8ac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Nov 2008 18:37:41 -0500 Subject: [PATCH] return records for fork() both to child and parent Signed-off-by: Al Viro --- include/linux/audit.h | 2 ++ kernel/auditsc.c | 17 +++++++++++++++++ kernel/fork.c | 1 + 3 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 6272a395d43c..1b2a6a5c1876 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -391,6 +391,7 @@ extern int audit_classify_arch(int arch); #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ /* Public API */ +extern void audit_finish_fork(struct task_struct *child); extern int audit_alloc(struct task_struct *task); extern void audit_free(struct task_struct *task); extern void audit_syscall_entry(int arch, @@ -504,6 +505,7 @@ static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) extern int audit_n_rules; extern int audit_signals; #else +#define audit_finish_fork(t) #define audit_alloc(t) ({ 0; }) #define audit_free(t) do { ; } while (0) #define audit_syscall_entry(ta,a,b,c,d,e) do { ; } while (0) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index cf5bc2f5f9c3..de8468050afa 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1548,6 +1548,23 @@ void audit_syscall_entry(int arch, int major, context->ppid = 0; } +void audit_finish_fork(struct task_struct *child) +{ + struct audit_context *ctx = current->audit_context; + struct audit_context *p = child->audit_context; + if (!p || !ctx || !ctx->auditable) + return; + p->arch = ctx->arch; + p->major = ctx->major; + memcpy(p->argv, ctx->argv, sizeof(ctx->argv)); + p->ctime = ctx->ctime; + p->dummy = ctx->dummy; + p->auditable = ctx->auditable; + p->in_syscall = ctx->in_syscall; + p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL); + p->ppid = current->pid; +} + /** * audit_syscall_exit - deallocate audit context after a system call * @tsk: task being audited diff --git a/kernel/fork.c b/kernel/fork.c index 2a372a0e206f..8d6a7dd9282b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1398,6 +1398,7 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } + audit_finish_fork(p); tracehook_report_clone(trace, regs, clone_flags, nr, p); /* -- cgit v1.2.3 From 0b0c940a91f8e6fd0e1be3e01d5e98997446233b Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 18 Nov 2008 15:03:49 +0800 Subject: [PATCH] asm/generic: fix bug - kernel fails to build when enable some common audit code on Blackfin If you enable some common audit code, the kernel fails to build. In file included from lib/audit.c:17: include/asm-generic/audit_write.h:3: error: '__NR_swapon' undeclared here (not in a function) make[1]: *** [lib/audit.o] Error 1 make: *** [lib] Error 2 So do not use __NR_swapon if it isnt defined for a port. Signed-off-by: Mike Frysinger Signed-off-by: Bryan Wu Signed-off-by: Al Viro --- include/asm-generic/audit_write.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/audit_write.h b/include/asm-generic/audit_write.h index f10d367fb2a5..c5f1c2c920e2 100644 --- a/include/asm-generic/audit_write.h +++ b/include/asm-generic/audit_write.h @@ -1,6 +1,8 @@ #include __NR_acct, +#ifdef __NR_swapon __NR_swapon, +#endif __NR_quotactl, __NR_truncate, #ifdef __NR_truncate64 -- cgit v1.2.3 From 48887e63d6e057543067327da6b091297f7fe645 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 6 Dec 2008 01:05:50 -0500 Subject: [PATCH] fix broken timestamps in AVC generated by kernel threads Timestamp in audit_context is valid only if ->in_syscall is set. Signed-off-by: Al Viro --- include/linux/audit.h | 4 ++-- kernel/audit.c | 4 +--- kernel/auditsc.c | 5 ++++- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 1b2a6a5c1876..8f0672d13eb1 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -435,7 +435,7 @@ static inline void audit_ptrace(struct task_struct *t) /* Private API (for audit.c only) */ extern unsigned int audit_serial(void); -extern void auditsc_get_stamp(struct audit_context *ctx, +extern int auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial); extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); #define audit_get_loginuid(t) ((t)->loginuid) @@ -518,7 +518,7 @@ extern int audit_signals; #define audit_inode(n,d) do { ; } while (0) #define audit_inode_child(d,i,p) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) -#define auditsc_get_stamp(c,t,s) do { BUG(); } while (0) +#define auditsc_get_stamp(c,t,s) (0) #define audit_get_loginuid(t) (-1) #define audit_get_sessionid(t) (-1) #define audit_log_task_context(b) do { ; } while (0) diff --git a/kernel/audit.c b/kernel/audit.c index d8646c23b427..ce6d8ea3131e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1121,9 +1121,7 @@ unsigned int audit_serial(void) static inline void audit_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { - if (ctx) - auditsc_get_stamp(ctx, t, serial); - else { + if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { *t = CURRENT_TIME; *serial = audit_serial(); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 0a13d6895494..2a3f0afc4d2a 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1957,15 +1957,18 @@ EXPORT_SYMBOL_GPL(__audit_inode_child); * * Also sets the context as auditable. */ -void auditsc_get_stamp(struct audit_context *ctx, +int auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { + if (!ctx->in_syscall) + return 0; if (!ctx->serial) ctx->serial = audit_serial(); t->tv_sec = ctx->ctime.tv_sec; t->tv_nsec = ctx->ctime.tv_nsec; *serial = ctx->serial; ctx->auditable = 1; + return 1; } /* global counter which is incremented every time something logs in */ -- cgit v1.2.3 From 71c5576fbd809f2015f4eddf72e501e298720cf3 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 9 Dec 2008 13:14:13 -0800 Subject: revert "percpu counter: clean up percpu_counter_sum_and_set()" Revert commit 1f7c14c62ce63805f9574664a6c6de3633d4a354 Author: Mingming Cao Date: Thu Oct 9 12:50:59 2008 -0400 percpu counter: clean up percpu_counter_sum_and_set() Before this patch we had the following: percpu_counter_sum(): return the percpu_counter's value percpu_counter_sum_and_set(): return the percpu_counter's value, copying that value into the central value and zeroing the per-cpu counters before returning. After this patch, percpu_counter_sum_and_set() has gone, and percpu_counter_sum() gets the old percpu_counter_sum_and_set() functionality. Problem is, as Eric points out, the old percpu_counter_sum_and_set() functionality was racy and wrong. It zeroes out counters on "other" cpus, without holding any locks which will prevent races agaist updates from those other CPUS. This patch reverts 1f7c14c62ce63805f9574664a6c6de3633d4a354. This means that percpu_counter_sum_and_set() still has the race, but percpu_counter_sum() does not. Note that this is not a simple revert - ext4 has since started using percpu_counter_sum() for its dirty_blocks counter as well. Note that this revert patch changes percpu_counter_sum() semantics. Before the patch, a call to percpu_counter_sum() will bring the counter's central counter mostly up-to-date, so a following percpu_counter_read() will return a close value. After this patch, a call to percpu_counter_sum() will leave the counter's central accumulator unaltered, so a subsequent call to percpu_counter_read() can now return a significantly inaccurate result. If there is any code in the tree which was introduced after e8ced39d5e8911c662d4d69a342b9d053eaaac4e was merged, and which depends upon the new percpu_counter_sum() semantics, that code will break. Reported-by: Eric Dumazet Cc: "David S. Miller" Cc: Peter Zijlstra Cc: Mingming Cao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/balloc.c | 4 ++-- include/linux/percpu_counter.h | 12 +++++++++--- lib/percpu_counter.c | 8 +++++--- 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index d2003cdc36aa..c17f69bcd7dd 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -609,8 +609,8 @@ int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks) if (free_blocks - (nblocks + root_blocks + dirty_blocks) < EXT4_FREEBLOCKS_WATERMARK) { - free_blocks = percpu_counter_sum(fbc); - dirty_blocks = percpu_counter_sum(dbc); + free_blocks = percpu_counter_sum_and_set(fbc); + dirty_blocks = percpu_counter_sum_and_set(dbc); if (dirty_blocks < 0) { printk(KERN_CRIT "Dirty block accounting " "went wrong %lld\n", diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 9007ccdfc112..208388835357 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc); +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc); + s64 ret = __percpu_counter_sum(fbc, 0); return ret < 0 ? 0 : ret; } +static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) +{ + return __percpu_counter_sum(fbc, 1); +} + + static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc); + return __percpu_counter_sum(fbc, 0); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 71b265c330ce..dba1530a5b29 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add); * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ -s64 __percpu_counter_sum(struct percpu_counter *fbc) +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) { s64 ret; int cpu; @@ -62,9 +62,11 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc) for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; - *pcount = 0; + if (set) + *pcount = 0; } - fbc->count = ret; + if (set) + fbc->count = ret; spin_unlock(&fbc->lock); return ret; -- cgit v1.2.3 From 02d211688727ad02bb4555b1aa8ae2de16b21b39 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 9 Dec 2008 13:14:14 -0800 Subject: revert "percpu_counter: new function percpu_counter_sum_and_set" Revert commit e8ced39d5e8911c662d4d69a342b9d053eaaac4e Author: Mingming Cao Date: Fri Jul 11 19:27:31 2008 -0400 percpu_counter: new function percpu_counter_sum_and_set As described in revert "percpu counter: clean up percpu_counter_sum_and_set()" the new percpu_counter_sum_and_set() is racy against updates to the cpu-local accumulators on other CPUs. Revert that change. This means that ext4 will be slow again. But correct. Reported-by: Eric Dumazet Cc: "David S. Miller" Cc: Peter Zijlstra Cc: Mingming Cao Cc: Cc: [2.6.27.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/balloc.c | 4 ++-- include/linux/percpu_counter.h | 12 +++--------- lib/percpu_counter.c | 7 +------ 3 files changed, 6 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index c17f69bcd7dd..db35cfdb3c8b 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -609,8 +609,8 @@ int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks) if (free_blocks - (nblocks + root_blocks + dirty_blocks) < EXT4_FREEBLOCKS_WATERMARK) { - free_blocks = percpu_counter_sum_and_set(fbc); - dirty_blocks = percpu_counter_sum_and_set(dbc); + free_blocks = percpu_counter_sum_positive(fbc); + dirty_blocks = percpu_counter_sum_positive(dbc); if (dirty_blocks < 0) { printk(KERN_CRIT "Dirty block accounting " "went wrong %lld\n", diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 208388835357..9007ccdfc112 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); +s64 __percpu_counter_sum(struct percpu_counter *fbc); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,19 +44,13 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc, 0); + s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } -static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) -{ - return __percpu_counter_sum(fbc, 1); -} - - static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc, 0); + return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index dba1530a5b29..b255b939bc1b 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add); * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ -s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) +s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; @@ -62,12 +62,7 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; - if (set) - *pcount = 0; } - if (set) - fbc->count = ret; - spin_unlock(&fbc->lock); return ret; } -- cgit v1.2.3 From aa6f14796630c8b03c11e782484aec2aee05e671 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 Dec 2008 13:14:25 -0800 Subject: atomic: fix a typo in atomic_long_xchg() atomic_long_xchg() is not correctly defined for 32bit arches. Signed-off-by: Eric Dumazet Cc: Mathieu Desnoyers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/atomic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 4ec0a296bdec..7abdaa91ccd3 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -251,7 +251,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u) #define atomic_long_cmpxchg(l, old, new) \ (atomic_cmpxchg((atomic_t *)(l), (old), (new))) #define atomic_long_xchg(v, new) \ - (atomic_xchg((atomic_t *)(l), (new))) + (atomic_xchg((atomic_t *)(v), (new))) #endif /* BITS_PER_LONG == 64 */ -- cgit v1.2.3 From 9c24624727f6d6c460e45762a408ca5f5b9b8ef2 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 9 Dec 2008 13:14:27 -0800 Subject: KSYM_SYMBOL_LEN fixes Miles Lane tailing /sys files hit a BUG which Pekka Enberg has tracked to my 966c8c12dc9e77f931e2281ba25d2f0244b06949 sprint_symbol(): use less stack exposing a bug in slub's list_locations() - kallsyms_lookup() writes a 0 to namebuf[KSYM_NAME_LEN-1], but that was beyond the end of page provided. The 100 slop which list_locations() allows at end of page looks roughly enough for all the other stuff it might print after the symbol before it checks again: break out KSYM_SYMBOL_LEN earlier than before. Latencytop and ftrace and are using KSYM_NAME_LEN buffers where they need KSYM_SYMBOL_LEN buffers, and vmallocinfo a 2*KSYM_NAME_LEN buffer where it wants a KSYM_SYMBOL_LEN buffer: fix those before anyone copies them. [akpm@linux-foundation.org: ftrace.h needs module.h] Signed-off-by: Hugh Dickins Cc: Christoph Lameter Cc Miles Lane Acked-by: Pekka Enberg Acked-by: Steven Rostedt Acked-by: Frederic Weisbecker Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 2 +- include/linux/ftrace.h | 3 ++- kernel/latencytop.c | 2 +- mm/slub.c | 2 +- mm/vmalloc.c | 2 +- 5 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/fs/proc/base.c b/fs/proc/base.c index 486cf3fe7139..d4677603c889 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -371,7 +371,7 @@ static int lstats_show_proc(struct seq_file *m, void *v) task->latency_record[i].time, task->latency_record[i].max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { - char sym[KSYM_NAME_LEN]; + char sym[KSYM_SYMBOL_LEN]; char *c; if (!task->latency_record[i].backtrace[q]) break; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 703eb53cfa2b..9c5bc6be2b09 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #ifdef CONFIG_FUNCTION_TRACER @@ -231,7 +232,7 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { } struct boot_trace { pid_t caller; - char func[KSYM_NAME_LEN]; + char func[KSYM_SYMBOL_LEN]; int result; unsigned long long duration; /* usecs */ ktime_t calltime; diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 5e7b45c56923..449db466bdbc 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -191,7 +191,7 @@ static int lstats_show(struct seq_file *m, void *v) latency_record[i].time, latency_record[i].max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { - char sym[KSYM_NAME_LEN]; + char sym[KSYM_SYMBOL_LEN]; char *c; if (!latency_record[i].backtrace[q]) break; diff --git a/mm/slub.c b/mm/slub.c index 749588a50a5a..a2cd47d89e0a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3597,7 +3597,7 @@ static int list_locations(struct kmem_cache *s, char *buf, for (i = 0; i < t.count; i++) { struct location *l = &t.loc[i]; - if (len > PAGE_SIZE - 100) + if (len > PAGE_SIZE - KSYM_SYMBOL_LEN - 100) break; len += sprintf(buf + len, "%7ld ", l->count); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f3f6e0758562..1ddb77ba3995 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1717,7 +1717,7 @@ static int s_show(struct seq_file *m, void *p) v->addr, v->addr + v->size, v->size); if (v->caller) { - char buff[2 * KSYM_NAME_LEN]; + char buff[KSYM_SYMBOL_LEN]; seq_putc(m, ' '); sprint_symbol(buff, (unsigned long)v->caller); -- cgit v1.2.3 From 54b71fba68efbf3ab89721a384df2ce757750979 Mon Sep 17 00:00:00 2001 From: Akira Takeuchi Date: Wed, 10 Dec 2008 12:43:34 +0000 Subject: MN10300: Fix __put_user_asm8() Fix __put_user_asm8() by jumping to the end label (3:) from the exception handler, rather than jumping back to retry the second store instruction (label 2:). Signed-off-by: Akira Takeuchi Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/asm-mn10300/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-mn10300/uaccess.h b/include/asm-mn10300/uaccess.h index 46b9b647f3c3..8a3a4dd55763 100644 --- a/include/asm-mn10300/uaccess.h +++ b/include/asm-mn10300/uaccess.h @@ -266,7 +266,7 @@ extern int __get_user_unknown(void); " .section .fixup,\"ax\" \n" \ "4: \n" \ " mov %5,%0 \n" \ - " jmp 2b \n" \ + " jmp 3b \n" \ " .previous \n" \ " .section __ex_table,\"a\"\n" \ " .balign 4 \n" \ -- cgit v1.2.3 From 6c34bc2976b30dc8b56392c020e25bae1f363cab Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 10 Dec 2008 09:26:17 -0800 Subject: Revert "radeonfb: accelerate imageblit and other improvements" This reverts commit b1ee26bab14886350ba12a5c10cbc0696ac679bf, along with the "fixes" for it that all just caused problems: - c4c6fa9891f3d1bcaae4f39fb751d5302965b566 "radeonfb: fix problem with color expansion & alignment" - f3179748a157c21d44d929fd3779421ebfbeaa93 "radeonfb: Disable new color expand acceleration unless explicitely enabled" because even when disabled, it breaks for people. See http://bugzilla.kernel.org/show_bug.cgi?id=12191 for the latest example. Acked-by: Benjamin Herrenschmidt Acked-by: David S. Miller Cc: Krzysztof Halasa Cc: James Cloos Cc: "Rafael J. Wysocki" Cc: Krzysztof Helt Cc: Jean-Luc Coulon Cc: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/video/aty/radeon_accel.c | 295 ++++++++++------------------------- drivers/video/aty/radeon_backlight.c | 2 +- drivers/video/aty/radeon_base.c | 46 ++---- drivers/video/aty/radeon_pm.c | 6 +- drivers/video/aty/radeonfb.h | 40 ++--- include/video/radeon.h | 18 +-- 6 files changed, 127 insertions(+), 280 deletions(-) (limited to 'include') diff --git a/drivers/video/aty/radeon_accel.c b/drivers/video/aty/radeon_accel.c index 8da5e5ab8547..a469a3d6edcb 100644 --- a/drivers/video/aty/radeon_accel.c +++ b/drivers/video/aty/radeon_accel.c @@ -5,61 +5,61 @@ * --dte */ -#define FLUSH_CACHE_WORKAROUND 1 - -void radeon_fifo_update_and_wait(struct radeonfb_info *rinfo, int entries) +static void radeon_fixup_offset(struct radeonfb_info *rinfo) { - int i; + u32 local_base; + + /* *** Ugly workaround *** */ + /* + * On some platforms, the video memory is mapped at 0 in radeon chip space + * (like PPCs) by the firmware. X will always move it up so that it's seen + * by the chip to be at the same address as the PCI BAR. + * That means that when switching back from X, there is a mismatch between + * the offsets programmed into the engine. This means that potentially, + * accel operations done before radeonfb has a chance to re-init the engine + * will have incorrect offsets, and potentially trash system memory ! + * + * The correct fix is for fbcon to never call any accel op before the engine + * has properly been re-initialized (by a call to set_var), but this is a + * complex fix. This workaround in the meantime, called before every accel + * operation, makes sure the offsets are in sync. + */ - for (i=0; i<2000000; i++) { - rinfo->fifo_free = INREG(RBBM_STATUS) & 0x7f; - if (rinfo->fifo_free >= entries) - return; - udelay(10); - } - printk(KERN_ERR "radeonfb: FIFO Timeout !\n"); - /* XXX Todo: attempt to reset the engine */ -} + radeon_fifo_wait (1); + local_base = INREG(MC_FB_LOCATION) << 16; + if (local_base == rinfo->fb_local_base) + return; -static inline void radeon_fifo_wait(struct radeonfb_info *rinfo, int entries) -{ - if (entries <= rinfo->fifo_free) - rinfo->fifo_free -= entries; - else - radeon_fifo_update_and_wait(rinfo, entries); -} + rinfo->fb_local_base = local_base; -static inline void radeonfb_set_creg(struct radeonfb_info *rinfo, u32 reg, - u32 *cache, u32 new_val) -{ - if (new_val == *cache) - return; - *cache = new_val; - radeon_fifo_wait(rinfo, 1); - OUTREG(reg, new_val); + radeon_fifo_wait (3); + OUTREG(DEFAULT_PITCH_OFFSET, (rinfo->pitch << 0x16) | + (rinfo->fb_local_base >> 10)); + OUTREG(DST_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10)); + OUTREG(SRC_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10)); } static void radeonfb_prim_fillrect(struct radeonfb_info *rinfo, const struct fb_fillrect *region) { - radeonfb_set_creg(rinfo, DP_GUI_MASTER_CNTL, &rinfo->dp_gui_mc_cache, - rinfo->dp_gui_mc_base | GMC_BRUSH_SOLID_COLOR | ROP3_P); - radeonfb_set_creg(rinfo, DP_CNTL, &rinfo->dp_cntl_cache, - DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM); - radeonfb_set_creg(rinfo, DP_BRUSH_FRGD_CLR, &rinfo->dp_brush_fg_cache, - region->color); - - /* Ensure the dst cache is flushed and the engine idle before - * issuing the operation. - * - * This works around engine lockups on some cards - */ -#if FLUSH_CACHE_WORKAROUND - radeon_fifo_wait(rinfo, 2); + radeon_fifo_wait(4); + + OUTREG(DP_GUI_MASTER_CNTL, + rinfo->dp_gui_master_cntl /* contains, like GMC_DST_32BPP */ + | GMC_BRUSH_SOLID_COLOR + | ROP3_P); + if (radeon_get_dstbpp(rinfo->depth) != DST_8BPP) + OUTREG(DP_BRUSH_FRGD_CLR, rinfo->pseudo_palette[region->color]); + else + OUTREG(DP_BRUSH_FRGD_CLR, region->color); + OUTREG(DP_WRITE_MSK, 0xffffffff); + OUTREG(DP_CNTL, (DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM)); + + radeon_fifo_wait(2); OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL); OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE)); -#endif - radeon_fifo_wait(rinfo, 2); + + radeon_fifo_wait(2); OUTREG(DST_Y_X, (region->dy << 16) | region->dx); OUTREG(DST_WIDTH_HEIGHT, (region->width << 16) | region->height); } @@ -70,14 +70,15 @@ void radeonfb_fillrect(struct fb_info *info, const struct fb_fillrect *region) struct fb_fillrect modded; int vxres, vyres; - WARN_ON(rinfo->gfx_mode); - if (info->state != FBINFO_STATE_RUNNING || rinfo->gfx_mode) + if (info->state != FBINFO_STATE_RUNNING) return; if (info->flags & FBINFO_HWACCEL_DISABLED) { cfb_fillrect(info, region); return; } + radeon_fixup_offset(rinfo); + vxres = info->var.xres_virtual; vyres = info->var.yres_virtual; @@ -90,10 +91,6 @@ void radeonfb_fillrect(struct fb_info *info, const struct fb_fillrect *region) if(modded.dx + modded.width > vxres) modded.width = vxres - modded.dx; if(modded.dy + modded.height > vyres) modded.height = vyres - modded.dy; - if (info->fix.visual == FB_VISUAL_TRUECOLOR || - info->fix.visual == FB_VISUAL_DIRECTCOLOR ) - modded.color = ((u32 *) (info->pseudo_palette))[region->color]; - radeonfb_prim_fillrect(rinfo, &modded); } @@ -112,22 +109,22 @@ static void radeonfb_prim_copyarea(struct radeonfb_info *rinfo, if ( xdir < 0 ) { sx += w-1; dx += w-1; } if ( ydir < 0 ) { sy += h-1; dy += h-1; } - radeonfb_set_creg(rinfo, DP_GUI_MASTER_CNTL, &rinfo->dp_gui_mc_cache, - rinfo->dp_gui_mc_base | - GMC_BRUSH_NONE | - GMC_SRC_DATATYPE_COLOR | - ROP3_S | - DP_SRC_SOURCE_MEMORY); - radeonfb_set_creg(rinfo, DP_CNTL, &rinfo->dp_cntl_cache, - (xdir>=0 ? DST_X_LEFT_TO_RIGHT : 0) | - (ydir>=0 ? DST_Y_TOP_TO_BOTTOM : 0)); - -#if FLUSH_CACHE_WORKAROUND - radeon_fifo_wait(rinfo, 2); + radeon_fifo_wait(3); + OUTREG(DP_GUI_MASTER_CNTL, + rinfo->dp_gui_master_cntl /* i.e. GMC_DST_32BPP */ + | GMC_BRUSH_NONE + | GMC_SRC_DSTCOLOR + | ROP3_S + | DP_SRC_SOURCE_MEMORY ); + OUTREG(DP_WRITE_MSK, 0xffffffff); + OUTREG(DP_CNTL, (xdir>=0 ? DST_X_LEFT_TO_RIGHT : 0) + | (ydir>=0 ? DST_Y_TOP_TO_BOTTOM : 0)); + + radeon_fifo_wait(2); OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL); OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE)); -#endif - radeon_fifo_wait(rinfo, 3); + + radeon_fifo_wait(3); OUTREG(SRC_Y_X, (sy << 16) | sx); OUTREG(DST_Y_X, (dy << 16) | dx); OUTREG(DST_HEIGHT_WIDTH, (h << 16) | w); @@ -146,14 +143,15 @@ void radeonfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) modded.width = area->width; modded.height = area->height; - WARN_ON(rinfo->gfx_mode); - if (info->state != FBINFO_STATE_RUNNING || rinfo->gfx_mode) + if (info->state != FBINFO_STATE_RUNNING) return; if (info->flags & FBINFO_HWACCEL_DISABLED) { cfb_copyarea(info, area); return; } + radeon_fixup_offset(rinfo); + vxres = info->var.xres_virtual; vyres = info->var.yres_virtual; @@ -170,116 +168,13 @@ void radeonfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) radeonfb_prim_copyarea(rinfo, &modded); } -static void radeonfb_prim_imageblit(struct radeonfb_info *rinfo, - const struct fb_image *image, - u32 fg, u32 bg) -{ - unsigned int dwords; - u32 *bits; - - radeonfb_set_creg(rinfo, DP_GUI_MASTER_CNTL, &rinfo->dp_gui_mc_cache, - rinfo->dp_gui_mc_base | - GMC_BRUSH_NONE | GMC_DST_CLIP_LEAVE | - GMC_SRC_DATATYPE_MONO_FG_BG | - ROP3_S | - GMC_BYTE_ORDER_MSB_TO_LSB | - DP_SRC_SOURCE_HOST_DATA); - radeonfb_set_creg(rinfo, DP_CNTL, &rinfo->dp_cntl_cache, - DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM); - radeonfb_set_creg(rinfo, DP_SRC_FRGD_CLR, &rinfo->dp_src_fg_cache, fg); - radeonfb_set_creg(rinfo, DP_SRC_BKGD_CLR, &rinfo->dp_src_bg_cache, bg); - - /* Ensure the dst cache is flushed and the engine idle before - * issuing the operation. - * - * This works around engine lockups on some cards - */ -#if FLUSH_CACHE_WORKAROUND - radeon_fifo_wait(rinfo, 2); - OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL); - OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE)); -#endif - - /* X here pads width to a multiple of 32 and uses the clipper to - * adjust the result. Is that really necessary ? Things seem to - * work ok for me without that and the doco doesn't seem to imply] - * there is such a restriction. - */ - radeon_fifo_wait(rinfo, 4); - OUTREG(SC_TOP_LEFT, (image->dy << 16) | image->dx); - OUTREG(SC_BOTTOM_RIGHT, ((image->dy + image->height) << 16) | - (image->dx + image->width)); - OUTREG(DST_Y_X, (image->dy << 16) | image->dx); - - OUTREG(DST_HEIGHT_WIDTH, (image->height << 16) | ((image->width + 31) & ~31)); - - dwords = (image->width + 31) >> 5; - dwords *= image->height; - bits = (u32*)(image->data); - - while(dwords >= 8) { - radeon_fifo_wait(rinfo, 8); -#if BITS_PER_LONG == 64 - __raw_writeq(*((u64 *)(bits)), rinfo->mmio_base + HOST_DATA0); - __raw_writeq(*((u64 *)(bits+2)), rinfo->mmio_base + HOST_DATA2); - __raw_writeq(*((u64 *)(bits+4)), rinfo->mmio_base + HOST_DATA4); - __raw_writeq(*((u64 *)(bits+6)), rinfo->mmio_base + HOST_DATA6); - bits += 8; -#else - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA0); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA1); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA2); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA3); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA4); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA5); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA6); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA7); -#endif - dwords -= 8; - } - while(dwords--) { - radeon_fifo_wait(rinfo, 1); - __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA0); - } -} - void radeonfb_imageblit(struct fb_info *info, const struct fb_image *image) { struct radeonfb_info *rinfo = info->par; - u32 fg, bg; - WARN_ON(rinfo->gfx_mode); - if (info->state != FBINFO_STATE_RUNNING || rinfo->gfx_mode) - return; - - if (!image->width || !image->height) + if (info->state != FBINFO_STATE_RUNNING) return; - - /* We only do 1 bpp color expansion for now */ - if (!accel_cexp || - (info->flags & FBINFO_HWACCEL_DISABLED) || image->depth != 1) - goto fallback; - - /* Fallback if running out of the screen. We may do clipping - * in the future */ - if ((image->dx + image->width) > info->var.xres_virtual || - (image->dy + image->height) > info->var.yres_virtual) - goto fallback; - - if (info->fix.visual == FB_VISUAL_TRUECOLOR || - info->fix.visual == FB_VISUAL_DIRECTCOLOR) { - fg = ((u32*)(info->pseudo_palette))[image->fg_color]; - bg = ((u32*)(info->pseudo_palette))[image->bg_color]; - } else { - fg = image->fg_color; - bg = image->bg_color; - } - - radeonfb_prim_imageblit(rinfo, image, fg, bg); - return; - - fallback: - radeon_engine_idle(rinfo); + radeon_engine_idle(); cfb_imageblit(info, image); } @@ -290,8 +185,7 @@ int radeonfb_sync(struct fb_info *info) if (info->state != FBINFO_STATE_RUNNING) return 0; - - radeon_engine_idle(rinfo); + radeon_engine_idle(); return 0; } @@ -367,10 +261,9 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo) /* disable 3D engine */ OUTREG(RB3D_CNTL, 0); - rinfo->fifo_free = 0; radeonfb_engine_reset(rinfo); - radeon_fifo_wait(rinfo, 1); + radeon_fifo_wait (1); if (IS_R300_VARIANT(rinfo)) { OUTREG(RB2D_DSTCACHE_MODE, INREG(RB2D_DSTCACHE_MODE) | RB2D_DC_AUTOFLUSH_ENABLE | @@ -384,7 +277,7 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo) OUTREG(RB2D_DSTCACHE_MODE, 0); } - radeon_fifo_wait(rinfo, 3); + radeon_fifo_wait (3); /* We re-read MC_FB_LOCATION from card as it can have been * modified by XFree drivers (ouch !) */ @@ -395,57 +288,41 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo) OUTREG(DST_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10)); OUTREG(SRC_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10)); - radeon_fifo_wait(rinfo, 1); -#ifdef __BIG_ENDIAN + radeon_fifo_wait (1); +#if defined(__BIG_ENDIAN) OUTREGP(DP_DATATYPE, HOST_BIG_ENDIAN_EN, ~HOST_BIG_ENDIAN_EN); #else OUTREGP(DP_DATATYPE, 0, ~HOST_BIG_ENDIAN_EN); #endif - radeon_fifo_wait(rinfo, 2); + radeon_fifo_wait (2); OUTREG(DEFAULT_SC_TOP_LEFT, 0); OUTREG(DEFAULT_SC_BOTTOM_RIGHT, (DEFAULT_SC_RIGHT_MAX | DEFAULT_SC_BOTTOM_MAX)); - /* set default DP_GUI_MASTER_CNTL */ temp = radeon_get_dstbpp(rinfo->depth); - rinfo->dp_gui_mc_base = ((temp << 8) | GMC_CLR_CMP_CNTL_DIS); + rinfo->dp_gui_master_cntl = ((temp << 8) | GMC_CLR_CMP_CNTL_DIS); - rinfo->dp_gui_mc_cache = rinfo->dp_gui_mc_base | - GMC_BRUSH_SOLID_COLOR | - GMC_SRC_DATATYPE_COLOR; - radeon_fifo_wait(rinfo, 1); - OUTREG(DP_GUI_MASTER_CNTL, rinfo->dp_gui_mc_cache); + radeon_fifo_wait (1); + OUTREG(DP_GUI_MASTER_CNTL, (rinfo->dp_gui_master_cntl | + GMC_BRUSH_SOLID_COLOR | + GMC_SRC_DATATYPE_COLOR)); + radeon_fifo_wait (7); /* clear line drawing regs */ - radeon_fifo_wait(rinfo, 2); OUTREG(DST_LINE_START, 0); OUTREG(DST_LINE_END, 0); - /* set brush and source color regs */ - rinfo->dp_brush_fg_cache = 0xffffffff; - rinfo->dp_brush_bg_cache = 0x00000000; - rinfo->dp_src_fg_cache = 0xffffffff; - rinfo->dp_src_bg_cache = 0x00000000; - radeon_fifo_wait(rinfo, 4); - OUTREG(DP_BRUSH_FRGD_CLR, rinfo->dp_brush_fg_cache); - OUTREG(DP_BRUSH_BKGD_CLR, rinfo->dp_brush_bg_cache); - OUTREG(DP_SRC_FRGD_CLR, rinfo->dp_src_fg_cache); - OUTREG(DP_SRC_BKGD_CLR, rinfo->dp_src_bg_cache); - - /* Default direction */ - rinfo->dp_cntl_cache = DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM; - radeon_fifo_wait(rinfo, 1); - OUTREG(DP_CNTL, rinfo->dp_cntl_cache); + /* set brush color regs */ + OUTREG(DP_BRUSH_FRGD_CLR, 0xffffffff); + OUTREG(DP_BRUSH_BKGD_CLR, 0x00000000); + + /* set source color regs */ + OUTREG(DP_SRC_FRGD_CLR, 0xffffffff); + OUTREG(DP_SRC_BKGD_CLR, 0x00000000); /* default write mask */ - radeon_fifo_wait(rinfo, 1); OUTREG(DP_WRITE_MSK, 0xffffffff); - /* Default to no swapping of host data */ - radeon_fifo_wait(rinfo, 1); - OUTREG(RBBM_GUICNTL, RBBM_GUICNTL_HOST_DATA_SWAP_NONE); - - /* Make sure it's settled */ - radeon_engine_idle(rinfo); + radeon_engine_idle (); } diff --git a/drivers/video/aty/radeon_backlight.c b/drivers/video/aty/radeon_backlight.c index f343ba83f0ae..1a056adb61c8 100644 --- a/drivers/video/aty/radeon_backlight.c +++ b/drivers/video/aty/radeon_backlight.c @@ -66,7 +66,7 @@ static int radeon_bl_update_status(struct backlight_device *bd) level = bd->props.brightness; del_timer_sync(&rinfo->lvds_timer); - radeon_engine_idle(rinfo); + radeon_engine_idle(); lvds_gen_cntl = INREG(LVDS_GEN_CNTL); if (level > 0) { diff --git a/drivers/video/aty/radeon_base.c b/drivers/video/aty/radeon_base.c index d5b27f9d374d..d0f1a7fc2c9d 100644 --- a/drivers/video/aty/radeon_base.c +++ b/drivers/video/aty/radeon_base.c @@ -282,8 +282,6 @@ static int backlight = 1; static int backlight = 0; #endif -int accel_cexp = 0; - /* * prototypes */ @@ -854,6 +852,7 @@ static int radeonfb_pan_display (struct fb_var_screeninfo *var, if (rinfo->asleep) return 0; + radeon_fifo_wait(2); OUTREG(CRTC_OFFSET, ((var->yoffset * var->xres_virtual + var->xoffset) * var->bits_per_pixel / 8) & ~7); return 0; @@ -883,6 +882,7 @@ static int radeonfb_ioctl (struct fb_info *info, unsigned int cmd, if (rc) return rc; + radeon_fifo_wait(2); if (value & 0x01) { tmp = INREG(LVDS_GEN_CNTL); @@ -940,7 +940,7 @@ int radeon_screen_blank(struct radeonfb_info *rinfo, int blank, int mode_switch) if (rinfo->lock_blank) return 0; - radeon_engine_idle(rinfo); + radeon_engine_idle(); val = INREG(CRTC_EXT_CNTL); val &= ~(CRTC_DISPLAY_DIS | CRTC_HSYNC_DIS | @@ -1048,7 +1048,7 @@ static int radeonfb_blank (int blank, struct fb_info *info) if (rinfo->asleep) return 0; - + return radeon_screen_blank(rinfo, blank, 0); } @@ -1074,6 +1074,8 @@ static int radeon_setcolreg (unsigned regno, unsigned red, unsigned green, pindex = regno; if (!rinfo->asleep) { + radeon_fifo_wait(9); + if (rinfo->bpp == 16) { pindex = regno * 8; @@ -1242,6 +1244,8 @@ static void radeon_write_pll_regs(struct radeonfb_info *rinfo, struct radeon_reg { int i; + radeon_fifo_wait(20); + /* Workaround from XFree */ if (rinfo->is_mobility) { /* A temporal workaround for the occational blanking on certain laptop @@ -1337,7 +1341,7 @@ static void radeon_lvds_timer_func(unsigned long data) { struct radeonfb_info *rinfo = (struct radeonfb_info *)data; - radeon_engine_idle(rinfo); + radeon_engine_idle(); OUTREG(LVDS_GEN_CNTL, rinfo->pending_lvds_gen_cntl); } @@ -1355,11 +1359,10 @@ void radeon_write_mode (struct radeonfb_info *rinfo, struct radeon_regs *mode, if (nomodeset) return; - radeon_engine_idle(rinfo); - if (!regs_only) radeon_screen_blank(rinfo, FB_BLANK_NORMAL, 0); + radeon_fifo_wait(31); for (i=0; i<10; i++) OUTREG(common_regs[i].reg, common_regs[i].val); @@ -1387,6 +1390,7 @@ void radeon_write_mode (struct radeonfb_info *rinfo, struct radeon_regs *mode, radeon_write_pll_regs(rinfo, mode); if ((primary_mon == MT_DFP) || (primary_mon == MT_LCD)) { + radeon_fifo_wait(10); OUTREG(FP_CRTC_H_TOTAL_DISP, mode->fp_crtc_h_total_disp); OUTREG(FP_CRTC_V_TOTAL_DISP, mode->fp_crtc_v_total_disp); OUTREG(FP_H_SYNC_STRT_WID, mode->fp_h_sync_strt_wid); @@ -1401,6 +1405,7 @@ void radeon_write_mode (struct radeonfb_info *rinfo, struct radeon_regs *mode, if (!regs_only) radeon_screen_blank(rinfo, FB_BLANK_UNBLANK, 0); + radeon_fifo_wait(2); OUTPLL(VCLK_ECP_CNTL, mode->vclk_ecp_cntl); return; @@ -1551,7 +1556,7 @@ static int radeonfb_set_par(struct fb_info *info) /* We always want engine to be idle on a mode switch, even * if we won't actually change the mode */ - radeon_engine_idle(rinfo); + radeon_engine_idle(); hSyncStart = mode->xres + mode->right_margin; hSyncEnd = hSyncStart + mode->hsync_len; @@ -1846,6 +1851,7 @@ static int radeonfb_set_par(struct fb_info *info) return 0; } + static struct fb_ops radeonfb_ops = { .owner = THIS_MODULE, .fb_check_var = radeonfb_check_var, @@ -1869,7 +1875,6 @@ static int __devinit radeon_set_fbinfo (struct radeonfb_info *rinfo) info->par = rinfo; info->pseudo_palette = rinfo->pseudo_palette; info->flags = FBINFO_DEFAULT - | FBINFO_HWACCEL_IMAGEBLIT | FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_XPAN @@ -1877,7 +1882,6 @@ static int __devinit radeon_set_fbinfo (struct radeonfb_info *rinfo) info->fbops = &radeonfb_ops; info->screen_base = rinfo->fb_base; info->screen_size = rinfo->mapped_vram; - /* Fill fix common fields */ strlcpy(info->fix.id, rinfo->name, sizeof(info->fix.id)); info->fix.smem_start = rinfo->fb_base_phys; @@ -1892,25 +1896,8 @@ static int __devinit radeon_set_fbinfo (struct radeonfb_info *rinfo) info->fix.mmio_len = RADEON_REGSIZE; info->fix.accel = FB_ACCEL_ATI_RADEON; - /* Allocate colormap */ fb_alloc_cmap(&info->cmap, 256, 0); - /* Setup pixmap used for acceleration */ -#define PIXMAP_SIZE (2048 * 4) - - info->pixmap.addr = kmalloc(PIXMAP_SIZE, GFP_KERNEL); - if (!info->pixmap.addr) { - printk(KERN_ERR "radeonfb: Failed to allocate pixmap !\n"); - noaccel = 1; - goto bail; - } - info->pixmap.size = PIXMAP_SIZE; - info->pixmap.flags = FB_PIXMAP_SYSTEM; - info->pixmap.scan_align = 4; - info->pixmap.buf_align = 4; - info->pixmap.access_align = 32; - -bail: if (noaccel) info->flags |= FBINFO_HWACCEL_DISABLED; @@ -2019,6 +2006,7 @@ static void radeon_identify_vram(struct radeonfb_info *rinfo) u32 tom = INREG(NB_TOM); tmp = ((((tom >> 16) - (tom & 0xffff) + 1) << 6) * 1024); + radeon_fifo_wait(6); OUTREG(MC_FB_LOCATION, tom); OUTREG(DISPLAY_BASE_ADDR, (tom & 0xffff) << 16); OUTREG(CRTC2_DISPLAY_BASE_ADDR, (tom & 0xffff) << 16); @@ -2522,8 +2510,6 @@ static int __init radeonfb_setup (char *options) } else if (!strncmp(this_opt, "ignore_devlist", 14)) { ignore_devlist = 1; #endif - } else if (!strncmp(this_opt, "accel_cexp", 12)) { - accel_cexp = 1; } else mode_option = this_opt; } @@ -2571,8 +2557,6 @@ module_param(monitor_layout, charp, 0); MODULE_PARM_DESC(monitor_layout, "Specify monitor mapping (like XFree86)"); module_param(force_measure_pll, bool, 0); MODULE_PARM_DESC(force_measure_pll, "Force measurement of PLL (debug)"); -module_param(accel_cexp, bool, 0); -MODULE_PARM_DESC(accel_cexp, "Use acceleration engine for color expansion"); #ifdef CONFIG_MTRR module_param(nomtrr, bool, 0); MODULE_PARM_DESC(nomtrr, "bool: disable use of MTRR registers"); diff --git a/drivers/video/aty/radeon_pm.c b/drivers/video/aty/radeon_pm.c index 3df5015f1d13..675abdafc2d8 100644 --- a/drivers/video/aty/radeon_pm.c +++ b/drivers/video/aty/radeon_pm.c @@ -2653,9 +2653,9 @@ int radeonfb_pci_suspend(struct pci_dev *pdev, pm_message_t mesg) if (!(info->flags & FBINFO_HWACCEL_DISABLED)) { /* Make sure engine is reset */ - radeon_engine_idle(rinfo); + radeon_engine_idle(); radeonfb_engine_reset(rinfo); - radeon_engine_idle(rinfo); + radeon_engine_idle(); } /* Blank display and LCD */ @@ -2767,7 +2767,7 @@ int radeonfb_pci_resume(struct pci_dev *pdev) rinfo->asleep = 0; } else - radeon_engine_idle(rinfo); + radeon_engine_idle(); /* Restore display & engine */ radeon_write_mode (rinfo, &rinfo->state, 1); diff --git a/drivers/video/aty/radeonfb.h b/drivers/video/aty/radeonfb.h index 974ca6d86540..3ea1b00fdd22 100644 --- a/drivers/video/aty/radeonfb.h +++ b/drivers/video/aty/radeonfb.h @@ -336,15 +336,7 @@ struct radeonfb_info { int mon2_type; u8 *mon2_EDID; - /* accel bits */ - u32 dp_gui_mc_base; - u32 dp_gui_mc_cache; - u32 dp_cntl_cache; - u32 dp_brush_fg_cache; - u32 dp_brush_bg_cache; - u32 dp_src_fg_cache; - u32 dp_src_bg_cache; - u32 fifo_free; + u32 dp_gui_master_cntl; struct pll_info pll; @@ -356,7 +348,6 @@ struct radeonfb_info { int lock_blank; int dynclk; int no_schedule; - int gfx_mode; enum radeon_pm_mode pm_mode; reinit_function_ptr reinit_func; @@ -401,14 +392,8 @@ static inline void _radeon_msleep(struct radeonfb_info *rinfo, unsigned long ms) #define OUTREG8(addr,val) writeb(val, (rinfo->mmio_base)+addr) #define INREG16(addr) readw((rinfo->mmio_base)+addr) #define OUTREG16(addr,val) writew(val, (rinfo->mmio_base)+addr) - -#ifdef CONFIG_PPC -#define INREG(addr) ({ eieio(); ld_le32(rinfo->mmio_base+(addr)); }) -#define OUTREG(addr,val) do { eieio(); st_le32(rinfo->mmio_base+(addr),(val)); } while(0) -#else #define INREG(addr) readl((rinfo->mmio_base)+addr) #define OUTREG(addr,val) writel(val, (rinfo->mmio_base)+addr) -#endif static inline void _OUTREGP(struct radeonfb_info *rinfo, u32 addr, u32 val, u32 mask) @@ -550,7 +535,17 @@ static inline u32 radeon_get_dstbpp(u16 depth) * 2D Engine helper routines */ -extern void radeon_fifo_update_and_wait(struct radeonfb_info *rinfo, int entries); +static inline void _radeon_fifo_wait(struct radeonfb_info *rinfo, int entries) +{ + int i; + + for (i=0; i<2000000; i++) { + if ((INREG(RBBM_STATUS) & 0x7f) >= entries) + return; + udelay(1); + } + printk(KERN_ERR "radeonfb: FIFO Timeout !\n"); +} static inline void radeon_engine_flush (struct radeonfb_info *rinfo) { @@ -563,7 +558,7 @@ static inline void radeon_engine_flush (struct radeonfb_info *rinfo) /* Ensure FIFO is empty, ie, make sure the flush commands * has reached the cache */ - radeon_fifo_update_and_wait(rinfo, 64); + _radeon_fifo_wait (rinfo, 64); /* Wait for the flush to complete */ for (i=0; i < 2000000; i++) { @@ -575,12 +570,12 @@ static inline void radeon_engine_flush (struct radeonfb_info *rinfo) } -static inline void radeon_engine_idle(struct radeonfb_info *rinfo) +static inline void _radeon_engine_idle(struct radeonfb_info *rinfo) { int i; /* ensure FIFO is empty before waiting for idle */ - radeon_fifo_update_and_wait (rinfo, 64); + _radeon_fifo_wait (rinfo, 64); for (i=0; i<2000000; i++) { if (((INREG(RBBM_STATUS) & GUI_ACTIVE)) == 0) { @@ -593,6 +588,8 @@ static inline void radeon_engine_idle(struct radeonfb_info *rinfo) } +#define radeon_engine_idle() _radeon_engine_idle(rinfo) +#define radeon_fifo_wait(entries) _radeon_fifo_wait(rinfo,entries) #define radeon_msleep(ms) _radeon_msleep(rinfo,ms) @@ -622,7 +619,6 @@ extern void radeonfb_imageblit(struct fb_info *p, const struct fb_image *image); extern int radeonfb_sync(struct fb_info *info); extern void radeonfb_engine_init (struct radeonfb_info *rinfo); extern void radeonfb_engine_reset(struct radeonfb_info *rinfo); -extern void radeon_fixup_mem_offset(struct radeonfb_info *rinfo); /* Other functions */ extern int radeon_screen_blank(struct radeonfb_info *rinfo, int blank, int mode_switch); @@ -638,6 +634,4 @@ static inline void radeonfb_bl_init(struct radeonfb_info *rinfo) {} static inline void radeonfb_bl_exit(struct radeonfb_info *rinfo) {} #endif -extern int accel_cexp; - #endif /* __RADEONFB_H__ */ diff --git a/include/video/radeon.h b/include/video/radeon.h index d5dcaf154ba4..1cd09cc5b169 100644 --- a/include/video/radeon.h +++ b/include/video/radeon.h @@ -525,9 +525,6 @@ #define CRTC_DISPLAY_DIS (1 << 10) #define CRTC_CRT_ON (1 << 15) -/* DSTCACHE_MODE bits constants */ -#define RB2D_DC_AUTOFLUSH_ENABLE (1 << 8) -#define RB2D_DC_DC_DISABLE_IGNORE_PE (1 << 17) /* DSTCACHE_CTLSTAT bit constants */ #define RB2D_DC_FLUSH_2D (1 << 0) @@ -869,10 +866,15 @@ #define GMC_DST_16BPP_YVYU422 0x00000c00 #define GMC_DST_32BPP_AYUV444 0x00000e00 #define GMC_DST_16BPP_ARGB4444 0x00000f00 +#define GMC_SRC_MONO 0x00000000 +#define GMC_SRC_MONO_LBKGD 0x00001000 +#define GMC_SRC_DSTCOLOR 0x00003000 #define GMC_BYTE_ORDER_MSB_TO_LSB 0x00000000 #define GMC_BYTE_ORDER_LSB_TO_MSB 0x00004000 #define GMC_DP_CONVERSION_TEMP_9300 0x00008000 #define GMC_DP_CONVERSION_TEMP_6500 0x00000000 +#define GMC_DP_SRC_RECT 0x02000000 +#define GMC_DP_SRC_HOST 0x03000000 #define GMC_DP_SRC_HOST_BYTEALIGN 0x04000000 #define GMC_3D_FCN_EN_CLR 0x00000000 #define GMC_3D_FCN_EN_SET 0x08000000 @@ -883,9 +885,6 @@ #define GMC_WRITE_MASK_LEAVE 0x00000000 #define GMC_WRITE_MASK_SET 0x40000000 #define GMC_CLR_CMP_CNTL_DIS (1 << 28) -#define GMC_SRC_DATATYPE_MASK (3 << 12) -#define GMC_SRC_DATATYPE_MONO_FG_BG (0 << 12) -#define GMC_SRC_DATATYPE_MONO_FG_LA (1 << 12) #define GMC_SRC_DATATYPE_COLOR (3 << 12) #define ROP3_S 0x00cc0000 #define ROP3_SRCCOPY 0x00cc0000 @@ -894,7 +893,6 @@ #define DP_SRC_SOURCE_MASK (7 << 24) #define GMC_BRUSH_NONE (15 << 4) #define DP_SRC_SOURCE_MEMORY (2 << 24) -#define DP_SRC_SOURCE_HOST_DATA (3 << 24) #define GMC_BRUSH_SOLIDCOLOR 0x000000d0 /* DP_MIX bit constants */ @@ -980,12 +978,6 @@ #define DISP_PWR_MAN_TV_ENABLE_RST (1 << 25) #define DISP_PWR_MAN_AUTO_PWRUP_EN (1 << 26) -/* RBBM_GUICNTL constants */ -#define RBBM_GUICNTL_HOST_DATA_SWAP_NONE (0 << 0) -#define RBBM_GUICNTL_HOST_DATA_SWAP_16BIT (1 << 0) -#define RBBM_GUICNTL_HOST_DATA_SWAP_32BIT (2 << 0) -#define RBBM_GUICNTL_HOST_DATA_SWAP_HDW (3 << 0) - /* masks */ #define CONFIG_MEMSIZE_MASK 0x1f000000 -- cgit v1.2.3