ff083a2d97
Protect perf_guest_cbs with RCU to fix multiple possible errors. Luckily,
all paths that read perf_guest_cbs already require RCU protection, e.g. to
protect the callback chains, so only the direct perf_guest_cbs touchpoints
need to be modified.
Bug #1 is a simple lack of WRITE_ONCE/READ_ONCE behavior to ensure
perf_guest_cbs isn't reloaded between a !NULL check and a dereference.
Fixed via the READ_ONCE() in rcu_dereference().
Bug #2 is that on weakly-ordered architectures, updates to the callbacks
themselves are not guaranteed to be visible before the pointer is made
visible to readers. Fixed by the smp_store_release() in
rcu_assign_pointer() when the new pointer is non-NULL.
Bug #3 is that, because the callbacks are global, it's possible for
readers to run in parallel with an unregisters, and thus a module
implementing the callbacks can be unloaded while readers are in flight,
resulting in a use-after-free. Fixed by a synchronize_rcu() call when
unregistering callbacks.
Bug #1 escaped notice because it's extremely unlikely a compiler will
reload perf_guest_cbs in this sequence. perf_guest_cbs does get reloaded
for future derefs, e.g. for ->is_user_mode(), but the ->is_in_guest()
guard all but guarantees the consumer will win the race, e.g. to nullify
perf_guest_cbs, KVM has to completely exit the guest and teardown down
all VMs before KVM start its module unload / unregister sequence. This
also makes it all but impossible to encounter bug #3.
Bug #2 has not been a problem because all architectures that register
callbacks are strongly ordered and/or have a static set of callbacks.
But with help, unloading kvm_intel can trigger bug #1 e.g. wrapping
perf_guest_cbs with READ_ONCE in perf_misc_flags() while spamming
kvm_intel module load/unload leads to:
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 6 PID: 1825 Comm: stress Not tainted 5.14.0-rc2+ #459
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:perf_misc_flags+0x1c/0x70
Call Trace:
perf_prepare_sample+0x53/0x6b0
perf_event_output_forward+0x67/0x160
__perf_event_overflow+0x52/0xf0
handle_pmi_common+0x207/0x300
intel_pmu_handle_irq+0xcf/0x410
perf_event_nmi_handler+0x28/0x50
nmi_handle+0xc7/0x260
default_do_nmi+0x6b/0x170
exc_nmi+0x103/0x130
asm_exc_nmi+0x76/0xbf
Fixes: 39447b386c ("perf: Enhance perf to allow for guest statistic collection from host")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20211111020738.2512932-2-seanjc@google.com
92 lines
2.4 KiB
C
92 lines
2.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */
|
|
|
|
#include <linux/perf_event.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/stacktrace.h>
|
|
|
|
/*
|
|
* Get the return address for a single stackframe and return a pointer to the
|
|
* next frame tail.
|
|
*/
|
|
static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
|
|
unsigned long fp, unsigned long reg_ra)
|
|
{
|
|
struct stackframe buftail;
|
|
unsigned long ra = 0;
|
|
unsigned long *user_frame_tail =
|
|
(unsigned long *)(fp - sizeof(struct stackframe));
|
|
|
|
/* Check accessibility of one struct frame_tail beyond */
|
|
if (!access_ok(user_frame_tail, sizeof(buftail)))
|
|
return 0;
|
|
if (__copy_from_user_inatomic(&buftail, user_frame_tail,
|
|
sizeof(buftail)))
|
|
return 0;
|
|
|
|
if (reg_ra != 0)
|
|
ra = reg_ra;
|
|
else
|
|
ra = buftail.ra;
|
|
|
|
fp = buftail.fp;
|
|
if (ra != 0)
|
|
perf_callchain_store(entry, ra);
|
|
else
|
|
return 0;
|
|
|
|
return fp;
|
|
}
|
|
|
|
/*
|
|
* This will be called when the target is in user mode
|
|
* This function will only be called when we use
|
|
* "PERF_SAMPLE_CALLCHAIN" in
|
|
* kernel/events/core.c:perf_prepare_sample()
|
|
*
|
|
* How to trigger perf_callchain_[user/kernel] :
|
|
* $ perf record -e cpu-clock --call-graph fp ./program
|
|
* $ perf report --call-graph
|
|
*
|
|
* On RISC-V platform, the program being sampled and the C library
|
|
* need to be compiled with -fno-omit-frame-pointer, otherwise
|
|
* the user stack will not contain function frame.
|
|
*/
|
|
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
|
|
struct pt_regs *regs)
|
|
{
|
|
struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
|
|
unsigned long fp = 0;
|
|
|
|
/* RISC-V does not support perf in guest mode. */
|
|
if (guest_cbs && guest_cbs->is_in_guest())
|
|
return;
|
|
|
|
fp = regs->s0;
|
|
perf_callchain_store(entry, regs->epc);
|
|
|
|
fp = user_backtrace(entry, fp, regs->ra);
|
|
while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
|
|
fp = user_backtrace(entry, fp, 0);
|
|
}
|
|
|
|
static bool fill_callchain(void *entry, unsigned long pc)
|
|
{
|
|
return perf_callchain_store(entry, pc);
|
|
}
|
|
|
|
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
|
|
struct pt_regs *regs)
|
|
{
|
|
struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
|
|
|
|
/* RISC-V does not support perf in guest mode. */
|
|
if (guest_cbs && guest_cbs->is_in_guest()) {
|
|
pr_warn("RISC-V does not support perf in guest mode!");
|
|
return;
|
|
}
|
|
|
|
walk_stackframe(NULL, regs, fill_callchain, entry);
|
|
}
|