| 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
| ||
|
Message-Id: <20221115005902.30458-5-beaub@linux.microsoft.com>
Date: Mon, 14 Nov 2022 16:58:59 -0800
From: Beau Belgrave <beaub@...ux.microsoft.com>
To: rostedt@...dmis.org, mhiramat@...nel.org,
mathieu.desnoyers@...icios.com, dcook@...ux.microsoft.com,
alanau@...ux.microsoft.com
Cc: linux-trace-devel@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [RFC PATCH v2 4/7] tracing/user_events: Fixup enable faults asyncly
When events are enabled within the various tracing facilities, such as
ftrace/perf, the event_mutex is held. As events are enabled pages are
accessed. We do not want page faults to occur under this lock. Instead
queue the fault to a workqueue to be handled in a process context safe
way without the lock.
The enable address is marked faulting while the async fault-in occurs.
This ensures that we don't attempt to fault-in more than is necessary.
Once the page has been faulted in, an address write is re-attempted.
If the page couldn't fault-in, then we wait until the next time the
event is enabled to prevent any potential infinite loops.
Signed-off-by: Beau Belgrave <beaub@...ux.microsoft.com>
---
kernel/trace/trace_events_user.c | 115 +++++++++++++++++++++++++++++--
1 file changed, 110 insertions(+), 5 deletions(-)
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index d5e926fe7dae..569e97f713da 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -99,11 +99,25 @@ struct user_event_enabler {
/* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */
#define ENABLE_VAL_BIT_MASK 0x3F
+/* Bit 6 is for faulting status of enablement */
+#define ENABLE_VAL_FAULTING_BIT 6
+
/* Only duplicate the bit value */
#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK
#define ENABLE_VALUE_BITS(e) ((e)->values & ENABLE_VAL_BIT_MASK)
+#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values)
+
+/* Used for asynchronous faulting in of pages */
+struct user_event_enabler_fault {
+ struct work_struct work;
+ struct user_event_mm *mm;
+ struct user_event_enabler *enabler;
+};
+
+static struct kmem_cache *fault_cache;
+
/* Global list of memory descriptors using user_events */
static LIST_HEAD(user_event_mms);
static DEFINE_SPINLOCK(user_event_mms_lock);
@@ -259,7 +273,85 @@ static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr)
}
static int user_event_enabler_write(struct user_event_mm *mm,
- struct user_event_enabler *enabler)
+ struct user_event_enabler *enabler,
+ bool fixup_fault);
+
+static void user_event_enabler_fault_fixup(struct work_struct *work)
+{
+ struct user_event_enabler_fault *fault = container_of(
+ work, struct user_event_enabler_fault, work);
+ struct user_event_enabler *enabler = fault->enabler;
+ struct user_event_mm *mm = fault->mm;
+ unsigned long uaddr = enabler->addr;
+ int ret;
+
+ ret = user_event_mm_fault_in(mm, uaddr);
+
+ if (ret) {
+ struct user_event *user = enabler->event;
+
+ pr_warn("user_events: Fault for mm: 0x%pK @ 0x%llx event: %s\n",
+ mm->mm, (unsigned long long)uaddr, EVENT_NAME(user));
+ }
+
+ /* Prevent state changes from racing */
+ mutex_lock(&event_mutex);
+
+ /*
+ * If we managed to get the page, re-issue the write. We do not
+ * want to get into a possible infinite loop, which is why we only
+ * attempt again directly if the page came in. If we couldn't get
+ * the page here, then we will try again the next time the event is
+ * enabled/disabled.
+ */
+ clear_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler));
+
+ if (!ret) {
+ mmap_read_lock(mm->mm);
+ user_event_enabler_write(mm, enabler, true);
+ mmap_read_unlock(mm->mm);
+ }
+
+ mutex_unlock(&event_mutex);
+
+ /* In all cases we no longer need the mm or fault */
+ user_event_mm_put(mm);
+ kmem_cache_free(fault_cache, fault);
+}
+
+static bool user_event_enabler_queue_fault(struct user_event_mm *mm,
+ struct user_event_enabler *enabler)
+{
+ struct user_event_enabler_fault *fault;
+
+ fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN);
+
+ if (!fault)
+ return false;
+
+ INIT_WORK(&fault->work, user_event_enabler_fault_fixup);
+ fault->mm = user_event_mm_get(mm);
+ fault->enabler = enabler;
+
+ /* Don't try to queue in again while we have a pending fault */
+ set_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler));
+
+ if (!schedule_work(&fault->work)) {
+ /* Allow another attempt later */
+ clear_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler));
+
+ user_event_mm_put(mm);
+ kmem_cache_free(fault_cache, fault);
+
+ return false;
+ }
+
+ return true;
+}
+
+static int user_event_enabler_write(struct user_event_mm *mm,
+ struct user_event_enabler *enabler,
+ bool fixup_fault)
{
unsigned long uaddr = enabler->addr;
unsigned long *ptr;
@@ -270,11 +362,19 @@ static int user_event_enabler_write(struct user_event_mm *mm,
lockdep_assert_held(&event_mutex);
mmap_assert_locked(mm->mm);
+ if (unlikely(test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))))
+ return -EBUSY;
+
ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT,
&page, NULL, NULL);
- if (ret <= 0) {
- pr_warn("user_events: Enable write failed\n");
+ if (unlikely(ret <= 0)) {
+ if (!fixup_fault)
+ return ret;
+
+ if (!user_event_enabler_queue_fault(mm, enabler))
+ pr_warn("user_events: Unable to queue fault handler\n");
+
return ret;
}
@@ -306,7 +406,7 @@ static void user_event_enabler_update(struct user_event *user)
list_for_each_entry_rcu(enabler, &mm->enablers, link)
if (enabler->event == user)
- user_event_enabler_write(mm, enabler);
+ user_event_enabler_write(mm, enabler, true);
rcu_read_unlock();
mmap_read_unlock(mm->mm);
@@ -539,7 +639,7 @@ static struct user_event_enabler
/* Attempt to reflect the current state within the process */
mmap_read_lock(user_mm->mm);
- *write_result = user_event_enabler_write(user_mm, enabler);
+ *write_result = user_event_enabler_write(user_mm, enabler, false);
mmap_read_unlock(user_mm->mm);
/*
@@ -2172,6 +2272,11 @@ static int __init trace_events_user_init(void)
{
int ret;
+ fault_cache = KMEM_CACHE(user_event_enabler_fault, 0);
+
+ if (!fault_cache)
+ return -ENOMEM;
+
init_group = user_event_group_create(&init_user_ns);
if (!init_group)
--
2.25.1
Powered by blists - more mailing lists