fa73158710
Solve the problems around the broken definition of perf_event_mmap_page::
cap_usr_time and cap_usr_rdpmc fields which used to overlap, partially
fixed by:
860f085b74 ("perf: Fix broken union in 'struct perf_event_mmap_page'")
The problem with the fix (merged in v3.12-rc1 and not yet released
officially), noticed by Vince Weaver is that the new behavior is
not detectable by new user-space, and that due to the reuse of the
field names it's easy to mis-compile a binary if old headers are used
on a new kernel or new headers are used on an old kernel.
To solve all that make this change explicit, detectable and self-contained,
by iterating the ABI the following way:
- Always clear bit 0, and rename it to usrpage->cap_bit0, to at least not
confuse old user-space binaries. RDPMC will be marked as unavailable
to old binaries but that's within the ABI, this is a capability bit.
- Rename bit 1 to ->cap_bit0_is_deprecated and always set it to 1, so new
libraries can reliably detect that bit 0 is deprecated and perma-zero
without having to check the kernel version.
- Use bits 2, 3, 4 for the newly defined, correct functionality:
cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */
cap_user_time : 1, /* The time_* fields are used */
cap_user_time_zero : 1, /* The time_zero field is used */
- Rename all the bitfield names in perf_event.h to be different from the
old names, to make sure it's not possible to mis-compile it
accidentally with old assumptions.
The 'size' field can then be used in the future to add new fields and it
will act as a natural ABI version indicator as well.
Also adjust tools/perf/ userspace for the new definitions, noticed by
Adrian Hunter.
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Also-Fixed-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/n/tip-zr03yxjrpXesOzzupszqglbv@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
59 lines
1.2 KiB
C
59 lines
1.2 KiB
C
#include <stdbool.h>
|
|
#include <errno.h>
|
|
|
|
#include <linux/perf_event.h>
|
|
|
|
#include "../../perf.h"
|
|
#include "../../util/types.h"
|
|
#include "../../util/debug.h"
|
|
#include "tsc.h"
|
|
|
|
u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
|
|
{
|
|
u64 t, quot, rem;
|
|
|
|
t = ns - tc->time_zero;
|
|
quot = t / tc->time_mult;
|
|
rem = t % tc->time_mult;
|
|
return (quot << tc->time_shift) +
|
|
(rem << tc->time_shift) / tc->time_mult;
|
|
}
|
|
|
|
u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
|
|
{
|
|
u64 quot, rem;
|
|
|
|
quot = cyc >> tc->time_shift;
|
|
rem = cyc & ((1 << tc->time_shift) - 1);
|
|
return tc->time_zero + quot * tc->time_mult +
|
|
((rem * tc->time_mult) >> tc->time_shift);
|
|
}
|
|
|
|
int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
|
|
struct perf_tsc_conversion *tc)
|
|
{
|
|
bool cap_user_time_zero;
|
|
u32 seq;
|
|
int i = 0;
|
|
|
|
while (1) {
|
|
seq = pc->lock;
|
|
rmb();
|
|
tc->time_mult = pc->time_mult;
|
|
tc->time_shift = pc->time_shift;
|
|
tc->time_zero = pc->time_zero;
|
|
cap_user_time_zero = pc->cap_user_time_zero;
|
|
rmb();
|
|
if (pc->lock == seq && !(seq & 1))
|
|
break;
|
|
if (++i > 10000) {
|
|
pr_debug("failed to get perf_event_mmap_page lock\n");
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
|
|
if (!cap_user_time_zero)
|
|
return -EOPNOTSUPP;
|
|
|
|
return 0;
|
|
}
|