Re: [PATCH V7 04/15] kprobes: Add perf ksymbol events for kprobe insn pages
From: Peter Zijlstra
Date: Wed May 27 2020 - 13:22:46 EST
On Wed, May 27, 2020 at 06:17:32PM +0200, Peter Zijlstra wrote:
> On Tue, May 12, 2020 at 03:19:11PM +0300, Adrian Hunter wrote:
> > @@ -202,6 +207,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
> > * next time somebody inserts a probe.
> > */
> > if (!list_is_singular(&kip->list)) {
> > + /*
> > + * Record perf ksymbol unregister event before removing
> > + * the page.
> > + */
> > + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
> > + (u64)kip->insns, PAGE_SIZE, true,
> > + kip->cache->sym);
> > list_del_rcu(&kip->list);
> > synchronize_rcu();
> > kip->cache->free(kip->insns);
>
> My manual build script haz complaints:
>
> i386-defconfig ../kernel/kprobes.c: In function â__get_insn_slotâ:
> ../kernel/kprobes.c:190:51: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
> perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (u64)kip->insns,
> ^
> ../kernel/kprobes.c: In function âcollect_one_slotâ:
> ../kernel/kprobes.c:215:9: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
> (u64)kip->insns, PAGE_SIZE, true,
> ^
> FAIL
>
>
> Now, there's a ton of such warnings elsewhere in the tree, but still I
> feel we should perhaps strive for a clean build.
Fixed those for you. On to cross-builds... :/