kprobes, extable: Identify kprobes trampolines as kernel text area

Improve __kernel_text_address()/kernel_text_address() to return
true if the given address is on a kprobe's instruction slot
trampoline.

This can help stacktraces to determine the address is on a
text area or not.

To implement this atomically in is_kprobe_*_slot(), also change
the insn_cache page list to an RCU list.

This changes timings a bit (it delays page freeing to the RCU garbage
collection phase), but none of that is in the hot path.

Note: this change can add small overhead to stack unwinders because
it adds 2 additional checks to __kernel_text_address(). However, the
impact should be very small, because kprobe_insn_pages list has 1 entry
per 256 probes(on x86, on arm/arm64 it will be 1024 probes),
and kprobe_optinsn_pages has 1 entry per 32 probes(on x86).
In most use cases, the number of kprobe events may be less
than 20, which means that is_kprobe_*_slot() will check just one entry.

Tested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/148388747896.6869.6354262871751682264.stgit@devbox
[ Improved the changelog and coding style. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 62 insertions, 20 deletions

diff --git a/kernel/extable.c b/kernel/extable.c
index e3beec4a2339..e1359474baa5 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
+#include <linux/kprobes.h>
 
 #include <asm/sections.h>
 #include <linux/uaccess.h>
@@ -104,6 +105,8 @@ int __kernel_text_address(unsigned long addr)
 		return 1;
 	if (is_ftrace_trampoline(addr))
 		return 1;
+	if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+		return 1;
 	/*
 	 * There might be init symbols in saved stacktraces.
 	 * Give those symbols a chance to be printed in
@@ -123,7 +126,11 @@ int kernel_text_address(unsigned long addr)
 		return 1;
 	if (is_module_text_address(addr))
 		return 1;
-	return is_ftrace_trampoline(addr);
+	if (is_ftrace_trampoline(addr))
+		return 1;
+	if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+		return 1;
+	return 0;
 }
 
 /*
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 43460104f119..ebb4dadca66b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -149,9 +149,11 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	struct kprobe_insn_page *kip;
 	kprobe_opcode_t *slot = NULL;
 
+	/* Since the slot array is not protected by rcu, we need a mutex */
 	mutex_lock(&c->mutex);
  retry:
-	list_for_each_entry(kip, &c->pages, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
 		if (kip->nused < slots_per_page(c)) {
 			int i;
 			for (i = 0; i < slots_per_page(c); i++) {
@@ -159,6 +161,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 					kip->slot_used[i] = SLOT_USED;
 					kip->nused++;
 					slot = kip->insns + (i * c->insn_size);
+					rcu_read_unlock();
 					goto out;
 				}
 			}
@@ -167,6 +170,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 			WARN_ON(1);
 		}
 	}
+	rcu_read_unlock();
 
 	/* If there are any garbage slots, collect it and try again. */
 	if (c->nr_garbage && collect_garbage_slots(c) == 0)
@@ -193,7 +197,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->nused = 1;
 	kip->ngarbage = 0;
 	kip->cache = c;
-	list_add(&kip->list, &c->pages);
+	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
 out:
 	mutex_unlock(&c->mutex);
@@ -213,7 +217,8 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
-			list_del(&kip->list);
+			list_del_rcu(&kip->list);
+			synchronize_rcu();
 			kip->cache->free(kip->insns);
 			kfree(kip);
 		}
@@ -235,8 +240,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
 			continue;
 		kip->ngarbage = 0;	/* we will collect all garbages */
 		for (i = 0; i < slots_per_page(c); i++) {
-			if (kip->slot_used[i] == SLOT_DIRTY &&
-			    collect_one_slot(kip, i))
+			if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i))
 				break;
 		}
 	}
@@ -248,29 +252,60 @@ void __free_insn_slot(struct kprobe_insn_cache *c,
 		      kprobe_opcode_t *slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
+	long idx;
 
 	mutex_lock(&c->mutex);
-	list_for_each_entry(kip, &c->pages, list) {
-		long idx = ((long)slot - (long)kip->insns) /
-				(c->insn_size * sizeof(kprobe_opcode_t));
-		if (idx >= 0 && idx < slots_per_page(c)) {
-			WARN_ON(kip->slot_used[idx] != SLOT_USED);
-			if (dirty) {
-				kip->slot_used[idx] = SLOT_DIRTY;
-				kip->ngarbage++;
-				if (++c->nr_garbage > slots_per_page(c))
-					collect_garbage_slots(c);
-			} else
-				collect_one_slot(kip, idx);
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		idx = ((long)slot - (long)kip->insns) /
+			(c->insn_size * sizeof(kprobe_opcode_t));
+		if (idx >= 0 && idx < slots_per_page(c))
 			goto out;
-		}
 	}
-	/* Could not free this slot. */
+	/* Could not find this slot. */
 	WARN_ON(1);
+	kip = NULL;
 out:
+	rcu_read_unlock();
+	/* Mark and sweep: this may sleep */
+	if (kip) {
+		/* Check double free */
+		WARN_ON(kip->slot_used[idx] != SLOT_USED);
+		if (dirty) {
+			kip->slot_used[idx] = SLOT_DIRTY;
+			kip->ngarbage++;
+			if (++c->nr_garbage > slots_per_page(c))
+				collect_garbage_slots(c);
+		} else {
+			collect_one_slot(kip, idx);
+		}
+	}
 	mutex_unlock(&c->mutex);
 }
 
+/*
+ * Check given address is on the page of kprobe instruction slots.
+ * This will be used for checking whether the address on a stack
+ * is on a text area or not.
+ */
+bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
+{
+	struct kprobe_insn_page *kip;
+	bool ret = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if (addr >= (unsigned long)kip->insns &&
+		    addr < (unsigned long)kip->insns + PAGE_SIZE) {
+			ret = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_OPTPROBES
 /* For optimized_kprobe buffer */
 struct kprobe_insn_cache kprobe_optinsn_slots = {