#include <linux/proc_ns.h>
#include <linux/mount.h>
#include <linux/min_heap.h>
+#include <linux/highmem.h>
+#include <linux/pgtable.h>
#include "internal.h"
* function.
*
* Lock order:
- * exec_update_mutex
+ * exec_update_lock
* task_struct::perf_event_mutex
* perf_event_context::mutex
* perf_event::child_mutex;
if (sample_type & PERF_SAMPLE_PERIOD)
size += sizeof(data->period);
- if (sample_type & PERF_SAMPLE_WEIGHT)
- size += sizeof(data->weight);
+ if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+ size += sizeof(data->weight.full);
if (sample_type & PERF_SAMPLE_READ)
size += event->read_size;
if (sample_type & PERF_SAMPLE_CGROUP)
size += sizeof(data->cgroup);
+ if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+ size += sizeof(data->data_page_size);
+
+ if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+ size += sizeof(data->code_page_size);
+
event->header_size = size;
}
data->regs_user.regs);
}
- if (sample_type & PERF_SAMPLE_WEIGHT)
- perf_output_put(handle, data->weight);
+ if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+ perf_output_put(handle, data->weight.full);
if (sample_type & PERF_SAMPLE_DATA_SRC)
perf_output_put(handle, data->data_src.val);
if (sample_type & PERF_SAMPLE_CGROUP)
perf_output_put(handle, data->cgroup);
+ if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+ perf_output_put(handle, data->data_page_size);
+
+ if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+ perf_output_put(handle, data->code_page_size);
+
if (sample_type & PERF_SAMPLE_AUX) {
perf_output_put(handle, data->aux_size);
return phys_addr;
}
+/*
+ * Return the pagetable size of a given virtual address.
+ */
+static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr)
+{
+ u64 size = 0;
+
+#ifdef CONFIG_HAVE_FAST_GUP
+ pgd_t *pgdp, pgd;
+ p4d_t *p4dp, p4d;
+ pud_t *pudp, pud;
+ pmd_t *pmdp, pmd;
+ pte_t *ptep, pte;
+
+ pgdp = pgd_offset(mm, addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ return 0;
+
+ if (pgd_leaf(pgd))
+ return pgd_leaf_size(pgd);
+
+ p4dp = p4d_offset_lockless(pgdp, pgd, addr);
+ p4d = READ_ONCE(*p4dp);
+ if (!p4d_present(p4d))
+ return 0;
+
+ if (p4d_leaf(p4d))
+ return p4d_leaf_size(p4d);
+
+ pudp = pud_offset_lockless(p4dp, p4d, addr);
+ pud = READ_ONCE(*pudp);
+ if (!pud_present(pud))
+ return 0;
+
+ if (pud_leaf(pud))
+ return pud_leaf_size(pud);
+
+ pmdp = pmd_offset_lockless(pudp, pud, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (!pmd_present(pmd))
+ return 0;
+
+ if (pmd_leaf(pmd))
+ return pmd_leaf_size(pmd);
+
+ ptep = pte_offset_map(&pmd, addr);
+ pte = ptep_get_lockless(ptep);
+ if (pte_present(pte))
+ size = pte_leaf_size(pte);
+ pte_unmap(ptep);
+#endif /* CONFIG_HAVE_FAST_GUP */
+
+ return size;
+}
+
+static u64 perf_get_page_size(unsigned long addr)
+{
+ struct mm_struct *mm;
+ unsigned long flags;
+ u64 size;
+
+ if (!addr)
+ return 0;
+
+ /*
+ * Software page-table walkers must disable IRQs,
+ * which prevents any tear down of the page tables.
+ */
+ local_irq_save(flags);
+
+ mm = current->mm;
+ if (!mm) {
+ /*
+ * For kernel threads and the like, use init_mm so that
+ * we can find kernel memory.
+ */
+ mm = &init_mm;
+ }
+
+ size = perf_get_pgtable_size(mm, addr);
+
+ local_irq_restore(flags);
+
+ return size;
+}
+
static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
struct perf_callchain_entry *
__perf_event_header__init_id(header, data, event);
- if (sample_type & PERF_SAMPLE_IP)
+ if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
data->ip = perf_instruction_pointer(regs);
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
}
#endif
+ /*
+ * PERF_DATA_PAGE_SIZE requires PERF_SAMPLE_ADDR. If the user doesn't
+ * require PERF_SAMPLE_ADDR, kernel implicitly retrieve the data->addr,
+ * but the value will not dump to the userspace.
+ */
+ if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+ data->data_page_size = perf_get_page_size(data->addr);
+
+ if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+ data->code_page_size = perf_get_page_size(data->ip);
+
if (sample_type & PERF_SAMPLE_AUX) {
u64 size;
if (attr->sample_type & PERF_SAMPLE_CGROUP)
return -EINVAL;
#endif
+ if ((attr->sample_type & PERF_SAMPLE_WEIGHT) &&
+ (attr->sample_type & PERF_SAMPLE_WEIGHT_STRUCT))
+ return -EINVAL;
out:
return ret;
goto err_task;
}
- if (task) {
- err = mutex_lock_interruptible(&task->signal->exec_update_mutex);
- if (err)
- goto err_task;
-
- /*
- * Preserve ptrace permission check for backwards compatibility.
- *
- * We must hold exec_update_mutex across this and any potential
- * perf_install_in_context() call for this new event to
- * serialize against exec() altering our credentials (and the
- * perf_event_exit_task() that could imply).
- */
- err = -EACCES;
- if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
- goto err_cred;
- }
-
if (flags & PERF_FLAG_PID_CGROUP)
cgroup_fd = pid;
NULL, NULL, cgroup_fd);
if (IS_ERR(event)) {
err = PTR_ERR(event);
- goto err_cred;
+ goto err_task;
}
if (is_sampling_event(event)) {
goto err_context;
}
+ if (task) {
+ err = down_read_interruptible(&task->signal->exec_update_lock);
+ if (err)
+ goto err_file;
+
+ /*
+ * Preserve ptrace permission check for backwards compatibility.
+ *
+ * We must hold exec_update_lock across this and any potential
+ * perf_install_in_context() call for this new event to
+ * serialize against exec() altering our credentials (and the
+ * perf_event_exit_task() that could imply).
+ */
+ err = -EACCES;
+ if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+ goto err_cred;
+ }
+
if (move_group) {
gctx = __perf_event_ctx_lock_double(group_leader, ctx);
mutex_unlock(&ctx->mutex);
if (task) {
- mutex_unlock(&task->signal->exec_update_mutex);
+ up_read(&task->signal->exec_update_lock);
put_task_struct(task);
}
if (move_group)
perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(&ctx->mutex);
-/* err_file: */
+err_cred:
+ if (task)
+ up_read(&task->signal->exec_update_lock);
+err_file:
fput(event_file);
err_context:
perf_unpin_context(ctx);
*/
if (!event_file)
free_event(event);
-err_cred:
- if (task)
- mutex_unlock(&task->signal->exec_update_mutex);
err_task:
if (task)
put_task_struct(task);
/*
* When a child task exits, feed back event values to parent events.
*
- * Can be called with exec_update_mutex held when called from
+ * Can be called with exec_update_lock held when called from
* setup_new_exec().
*/
void perf_event_exit_task(struct task_struct *child)