ftrace: A couple of fixes to function graph infrastructure

- Fix allocation of idle shadow stack allocation during hotplug
 
   If function graph tracing is started when a CPU is offline, if it were
   come online during the trace then the idle task that represents the CPU
   will not get a shadow stack allocated for it. This means all function
   graph hooks that happen while that idle task is running (including in
   interrupt mode) will have all its events dropped.
 
   Switch over to the CPU hotplug mechanism that will have any newly
   brought on line CPU get a callback that can allocate the shadow stack
   for its idle task.
 
 - Fix allocation size of the ret_stack_list array
 
   When function graph tracing converted over to allowing more than one
   user at a time, it had to convert its shadow stack from an array of
   ret_stack structures to an array of unsigned longs. The shadow stacks
   are allocated in batches of 32 at a time and assigned to every running
   task. The batch is held by the ret_stack_list array. But when the
   conversion happened, instead of allocating an array of 32 pointers, it
   was allocated as a ret_stack itself (PAGE_SIZE). This ret_stack_list
   gets passed to a function that iterates over what it believes is its
   size defined by the FTRACE_RETSTACK_ALLOC_SIZE macro (which is 32).
 
   Luckily (PAGE_SIZE) is greater than 32 * sizeof(long), otherwise this
   would have been an array overflow. This still should be fixed and the
   ret_stack_list should be allocated to the size it is expected to be as
   someday it may end up being bigger than SHADOW_STACK_SIZE.
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZxP8RhQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qmW3AP4qCOvU/g9g6u32gIZmS1oUWqe3q+Rq
 9OKCk0JP6GGc8AD/cF816lbs5vpDiZFdbBvaz5gLHqhfAt35NVU8T5tbJA4=
 =Lh3A
 -----END PGP SIGNATURE-----

Merge tag 'ftrace-v6.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull ftrace fixes from Steven Rostedt:
 "A couple of fixes to function graph infrastructure:

   - Fix allocation of idle shadow stack allocation during hotplug

     If function graph tracing is started when a CPU is offline, if it
     were come online during the trace then the idle task that
     represents the CPU will not get a shadow stack allocated for it.
     This means all function graph hooks that happen while that idle
     task is running (including in interrupt mode) will have all its
     events dropped.

     Switch over to the CPU hotplug mechanism that will have any newly
     brought on line CPU get a callback that can allocate the shadow
     stack for its idle task.

   - Fix allocation size of the ret_stack_list array

     When function graph tracing converted over to allowing more than
     one user at a time, it had to convert its shadow stack from an
     array of ret_stack structures to an array of unsigned longs. The
     shadow stacks are allocated in batches of 32 at a time and assigned
     to every running task. The batch is held by the ret_stack_list
     array.

     But when the conversion happened, instead of allocating an array of
     32 pointers, it was allocated as a ret_stack itself (PAGE_SIZE).
     This ret_stack_list gets passed to a function that iterates over
     what it believes is its size defined by the
     FTRACE_RETSTACK_ALLOC_SIZE macro (which is 32).

     Luckily (PAGE_SIZE) is greater than 32 * sizeof(long), otherwise
     this would have been an array overflow. This still should be fixed
     and the ret_stack_list should be allocated to the size it is
     expected to be as someday it may end up being bigger than
     SHADOW_STACK_SIZE"

* tag 'ftrace-v6.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  fgraph: Allocate ret_stack_list with proper size
  fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks
This commit is contained in:
Linus Torvalds 2024-10-19 12:42:14 -07:00
commit 06526daaff

View File

@ -1160,19 +1160,14 @@ void fgraph_update_pid_func(void)
static int start_graph_tracing(void)
{
unsigned long **ret_stack_list;
int ret, cpu;
int ret;
ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL);
ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
sizeof(*ret_stack_list), GFP_KERNEL);
if (!ret_stack_list)
return -ENOMEM;
/* The cpu_boot init_task->ret_stack will never be freed */
for_each_online_cpu(cpu) {
if (!idle_task(cpu)->ret_stack)
ftrace_graph_init_idle_task(idle_task(cpu), cpu);
}
do {
ret = alloc_retstack_tasklist(ret_stack_list);
} while (ret == -EAGAIN);
@ -1242,14 +1237,34 @@ static void ftrace_graph_disable_direct(bool disable_branch)
fgraph_direct_gops = &fgraph_stub;
}
/* The cpu_boot init_task->ret_stack will never be freed */
static int fgraph_cpu_init(unsigned int cpu)
{
if (!idle_task(cpu)->ret_stack)
ftrace_graph_init_idle_task(idle_task(cpu), cpu);
return 0;
}
int register_ftrace_graph(struct fgraph_ops *gops)
{
static bool fgraph_initialized;
int command = 0;
int ret = 0;
int i = -1;
mutex_lock(&ftrace_lock);
if (!fgraph_initialized) {
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init",
fgraph_cpu_init, NULL);
if (ret < 0) {
pr_warn("fgraph: Error to init cpu hotplug support\n");
return ret;
}
fgraph_initialized = true;
ret = 0;
}
if (!fgraph_array[0]) {
/* The array must always have real data on it */
for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)