stacktrace, lockdep: Fix address, newline ugliness
Since KERN_CONT became meaningful again, lockdep stack traces have had
annoying extra newlines, like this:
[ 5.561122] -> #1 (B){+.+...}:
[ 5.561528]
[ 5.561532] [<
ffffffff810d8873>] lock_acquire+0xc3/0x210
[ 5.562178]
[ 5.562181] [<
ffffffff816f6414>] mutex_lock_nested+0x74/0x6d0
[ 5.562861]
[ 5.562880] [<
ffffffffa01aa3c3>] init_btrfs_fs+0x21/0x196 [btrfs]
[ 5.563717]
[ 5.563721] [<
ffffffff81000472>] do_one_initcall+0x52/0x1b0
[ 5.564554]
[ 5.564559] [<
ffffffff811a3af6>] do_init_module+0x5f/0x209
[ 5.565357]
[ 5.565361] [<
ffffffff81122f4d>] load_module+0x218d/0x2b80
[ 5.566020]
[ 5.566021] [<
ffffffff81123beb>] SyS_finit_module+0xeb/0x120
[ 5.566694]
[ 5.566696] [<
ffffffff816fd241>] entry_SYSCALL_64_fastpath+0x1f/0xc2
That's happening because each printk() call now gets printed on its own
line, and we do a separate call to print the spaces before the symbol.
Fix it by doing the printk() directly instead of using the
print_ip_sym() helper.
Additionally, the symbol address isn't very helpful, so let's get rid of
that, too. The final result looks like this:
[ 5.194518] -> #1 (B){+.+...}:
[ 5.195002] lock_acquire+0xc3/0x210
[ 5.195439] mutex_lock_nested+0x74/0x6d0
[ 5.196491] do_one_initcall+0x52/0x1b0
[ 5.196939] do_init_module+0x5f/0x209
[ 5.197355] load_module+0x218d/0x2b80
[ 5.197792] SyS_finit_module+0xeb/0x120
[ 5.198251] entry_SYSCALL_64_fastpath+0x1f/0xc2
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@fb.com
Fixes:
4bcc595ccd80 ("printk: reinstate KERN_CONT for printing continuation lines")
Link: http://lkml.kernel.org/r/43b4e114724b2bdb0308fa86cb33aa07d3d67fad.1486510315.git.osandov@fb.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>