| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 19 Sep 2013 11:14:53 +0200
From: Ingo Molnar <mingo@...nel.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Vince Weaver <vince@...ter.net>, hpa@...or.com,
linux-kernel@...r.kernel.org, adrian.hunter@...el.com,
tglx@...utronix.de, linux-tip-commits@...r.kernel.org,
eranian@...glemail.com
Subject: [PATCH] perf: Always set bit 0 in the capabilities field of 'struct
perf_event_mmap_page' to 0, to maintain the ABI
* Peter Zijlstra <peterz@...radead.org> wrote:
> On Wed, Sep 18, 2013 at 04:07:52PM -0400, Vince Weaver wrote:
>
> > It would be nice if there was some way to detect this change; I liked
> > the idea of a "cap_usr_fixed" bit.
>
> How about we start using the version field for this? Arguably we should
> have incremented that value every time we changed the thing but we might
> as well start now.
But version fields are really fragile, the way we usually iterate ABIs is
a self-maintaining size field - which is missing here.
So I think the best solution would be to make it all explicit and
self-contained:
- 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.
- 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.
- 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.
I.e. something like the patch below. (untested)
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.
Thanks,
Ingo
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84..3ab624c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1883,9 +1883,9 @@ static struct pmu pmu = {
void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
- userpg->cap_usr_time = 0;
- userpg->cap_usr_time_zero = 0;
- userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+ userpg->cap_usr_time_used = 0;
+ userpg->cap_usr_time_zero_used = 0;
+ userpg->cap_usr_rdpmc_available = x86_pmu.attr_rdpmc;
userpg->pmc_width = x86_pmu.cntval_bits;
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
- userpg->cap_usr_time = 1;
+ userpg->cap_usr_time_used = 1;
userpg->time_mult = this_cpu_read(cyc2ns);
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
if (sched_clock_stable && !check_tsc_disabled()) {
- userpg->cap_usr_time_zero = 1;
+ userpg->cap_usr_time_zero_used = 1;
userpg->time_zero = this_cpu_read(cyc2ns_offset);
}
}
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 40a1fb8..515d7d2 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -380,10 +380,13 @@ struct perf_event_mmap_page {
union {
__u64 capabilities;
struct {
- __u64 cap_usr_time : 1,
- cap_usr_rdpmc : 1,
- cap_usr_time_zero : 1,
- cap_____res : 61;
+ __u64 cap_bit0 : 1, /* Deprecated, always zero, see commit 860f085b74e9 */
+ cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */
+
+ cap_usr_rdpmc_available : 1, /* The RDPMC instruction can be used to read counts */
+ cap_usr_time_used : 1, /* The time_* fields are uses */
+ cap_usr_time_zero_used : 1, /* The time_zero field is used */
+ cap_____res : 59;
};
};
@@ -442,12 +445,14 @@ struct perf_event_mmap_page {
* ((rem * time_mult) >> time_shift);
*/
__u64 time_zero;
+ __u32 size; /* Header size up to this point */
+ __u32 __reserved0; /* 4 byte hole */
/*
* Hole for extension of the self monitor capabilities
*/
- __u64 __reserved[119]; /* align to 1k */
+ __u64 __reserved[118]; /* align to 1k */
/*
* Control data for the mmap() data buffer.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b6..27d339f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
*running = ctx_time - event->tstamp_running;
}
+static void perf_event_init_userpage(struct perf_event *event)
+{
+ struct perf_event_mmap_page *userpg;
+ struct ring_buffer *rb;
+
+ rcu_read_lock();
+ rb = rcu_dereference(event->rb);
+ if (!rb)
+ goto unlock;
+
+ userpg = rb->user_page;
+
+ /* Allow new userspace to detect that bit 0 is deprecated */
+ userpg->cap_bit0_is_deprecated = 1;
+ userpg->size = offsetof(struct perf_event_mmap_page, size);
+
+unlock:
+ rcu_read_unlock();
+}
+
void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
}
@@ -4044,6 +4064,7 @@ again:
ring_buffer_attach(event, rb);
rcu_assign_pointer(event->rb, rb);
+ perf_event_init_userpage(event);
perf_event_update_userpage(event);
unlock:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists