summaryrefslogtreecommitdiff
path: root/io_uring/fdinfo.c
diff options
context:
space:
mode:
Diffstat (limited to 'io_uring/fdinfo.c')
-rw-r--r--io_uring/fdinfo.c250
1 files changed, 148 insertions, 102 deletions
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 882bd56b01ed..a87d4e26eee8 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -5,53 +5,60 @@
#include <linux/file.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/nospec.h>
#include <linux/io_uring.h>
#include <uapi/linux/io_uring.h>
-#include "io_uring.h"
+#include "filetable.h"
#include "sqpoll.h"
#include "fdinfo.h"
#include "cancel.h"
#include "rsrc.h"
+#include "opdef.h"
-#ifdef CONFIG_PROC_FS
-static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
- const struct cred *cred)
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static __cold void common_tracking_show_fdinfo(struct io_ring_ctx *ctx,
+ struct seq_file *m,
+ const char *tracking_strategy)
{
- struct user_namespace *uns = seq_user_ns(m);
- struct group_info *gi;
- kernel_cap_t cap;
- unsigned __capi;
- int g;
-
- seq_printf(m, "%5d\n", id);
- seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid));
- seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid));
- seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid));
- seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid));
- seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid));
- seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid));
- seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid));
- seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid));
- seq_puts(m, "\n\tGroups:\t");
- gi = cred->group_info;
- for (g = 0; g < gi->ngroups; g++) {
- seq_put_decimal_ull(m, g ? " " : "",
- from_kgid_munged(uns, gi->gid[g]));
+ seq_puts(m, "NAPI:\tenabled\n");
+ seq_printf(m, "napi tracking:\t%s\n", tracking_strategy);
+ seq_printf(m, "napi_busy_poll_dt:\t%llu\n", ctx->napi_busy_poll_dt);
+ if (ctx->napi_prefer_busy_poll)
+ seq_puts(m, "napi_prefer_busy_poll:\ttrue\n");
+ else
+ seq_puts(m, "napi_prefer_busy_poll:\tfalse\n");
+}
+
+static __cold void napi_show_fdinfo(struct io_ring_ctx *ctx,
+ struct seq_file *m)
+{
+ unsigned int mode = READ_ONCE(ctx->napi_track_mode);
+
+ switch (mode) {
+ case IO_URING_NAPI_TRACKING_INACTIVE:
+ seq_puts(m, "NAPI:\tdisabled\n");
+ break;
+ case IO_URING_NAPI_TRACKING_DYNAMIC:
+ common_tracking_show_fdinfo(ctx, m, "dynamic");
+ break;
+ case IO_URING_NAPI_TRACKING_STATIC:
+ common_tracking_show_fdinfo(ctx, m, "static");
+ break;
+ default:
+ seq_printf(m, "NAPI:\tunknown mode (%u)\n", mode);
}
- seq_puts(m, "\n\tCapEff:\t");
- cap = cred->cap_effective;
- CAP_FOR_EACH_U32(__capi)
- seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8);
- seq_putc(m, '\n');
- return 0;
}
+#else
+static inline void napi_show_fdinfo(struct io_ring_ctx *ctx,
+ struct seq_file *m)
+{
+}
+#endif
-static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
- struct seq_file *m)
+static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
{
- struct io_sq_data *sq = NULL;
struct io_overflow_cqe *ocqe;
struct io_rings *r = ctx->rings;
unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
@@ -59,14 +66,12 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
unsigned int sq_tail = READ_ONCE(r->sq.tail);
unsigned int cq_head = READ_ONCE(r->cq.head);
unsigned int cq_tail = READ_ONCE(r->cq.tail);
- unsigned int cq_shift = 0;
unsigned int sq_shift = 0;
- unsigned int sq_entries, cq_entries;
- bool has_lock;
+ unsigned int sq_entries;
+ int sq_pid = -1, sq_cpu = -1;
+ u64 sq_total_time = 0, sq_work_time = 0;
unsigned int i;
- if (ctx->flags & IORING_SETUP_CQE32)
- cq_shift = 1;
if (ctx->flags & IORING_SETUP_SQE128)
sq_shift = 1;
@@ -79,30 +84,57 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
seq_printf(m, "SqMask:\t0x%x\n", sq_mask);
seq_printf(m, "SqHead:\t%u\n", sq_head);
seq_printf(m, "SqTail:\t%u\n", sq_tail);
- seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
+ seq_printf(m, "CachedSqHead:\t%u\n", data_race(ctx->cached_sq_head));
seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
seq_printf(m, "CqHead:\t%u\n", cq_head);
seq_printf(m, "CqTail:\t%u\n", cq_tail);
- seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
+ seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail));
seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head);
sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
for (i = 0; i < sq_entries; i++) {
unsigned int entry = i + sq_head;
struct io_uring_sqe *sqe;
unsigned int sq_idx;
+ bool sqe128 = false;
+ u8 opcode;
- sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
+ if (ctx->flags & IORING_SETUP_NO_SQARRAY)
+ sq_idx = entry & sq_mask;
+ else
+ sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
if (sq_idx > sq_mask)
continue;
+
sqe = &ctx->sq_sqes[sq_idx << sq_shift];
+ opcode = READ_ONCE(sqe->opcode);
+ if (opcode >= IORING_OP_LAST)
+ continue;
+ opcode = array_index_nospec(opcode, IORING_OP_LAST);
+ if (sq_shift) {
+ sqe128 = true;
+ } else if (io_issue_defs[opcode].is_128) {
+ if (!(ctx->flags & IORING_SETUP_SQE_MIXED)) {
+ seq_printf(m,
+ "%5u: invalid sqe, 128B entry on non-mixed sq\n",
+ sq_idx);
+ break;
+ }
+ if ((++sq_head & sq_mask) == 0) {
+ seq_printf(m,
+ "%5u: corrupted sqe, wrapping 128B entry\n",
+ sq_idx);
+ break;
+ }
+ sqe128 = true;
+ }
seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, "
"addr:0x%llx, rw_flags:0x%x, buf_index:%d "
"user_data:%llu",
- sq_idx, io_uring_get_opcode(sqe->opcode), sqe->fd,
+ sq_idx, io_uring_get_opcode(opcode), sqe->fd,
sqe->flags, (unsigned long long) sqe->off,
(unsigned long long) sqe->addr, sqe->rw_flags,
sqe->buf_index, sqe->user_data);
- if (sq_shift) {
+ if (sqe128) {
u64 *sqeb = (void *) (sqe + 1);
int size = sizeof(struct io_uring_sqe) / sizeof(u64);
int j;
@@ -116,83 +148,89 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
seq_printf(m, "\n");
}
seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
- cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
- for (i = 0; i < cq_entries; i++) {
- unsigned int entry = i + cq_head;
- struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift];
+ while (cq_head < cq_tail) {
+ struct io_uring_cqe *cqe;
+ bool cqe32 = false;
- seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x",
- entry & cq_mask, cqe->user_data, cqe->res,
+ cqe = &r->cqes[(cq_head & cq_mask)];
+ if (cqe->flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32)
+ cqe32 = true;
+ seq_printf(m, "%5u: user_data:%llu, res:%d, flags:%x",
+ cq_head & cq_mask, cqe->user_data, cqe->res,
cqe->flags);
- if (cq_shift)
+ if (cqe32)
seq_printf(m, ", extra1:%llu, extra2:%llu\n",
cqe->big_cqe[0], cqe->big_cqe[1]);
seq_printf(m, "\n");
+ cq_head++;
+ if (cqe32)
+ cq_head++;
}
- /*
- * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
- * since fdinfo case grabs it in the opposite direction of normal use
- * cases. If we fail to get the lock, we just don't iterate any
- * structures that could be going away outside the io_uring mutex.
- */
- has_lock = mutex_trylock(&ctx->uring_lock);
-
- if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
- sq = ctx->sq_data;
- if (!sq->thread)
- sq = NULL;
- }
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
+ struct io_sq_data *sq = ctx->sq_data;
+ struct task_struct *tsk;
- seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1);
- seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1);
- seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
- for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
- struct file *f = io_file_from_index(&ctx->file_table, i);
+ rcu_read_lock();
+ tsk = rcu_dereference(sq->thread);
+ /*
+ * sq->thread might be NULL if we raced with the sqpoll
+ * thread termination.
+ */
+ if (tsk) {
+ u64 usec;
- if (f)
- seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname);
- else
- seq_printf(m, "%5u: <none>\n", i);
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ usec = io_sq_cpu_usec(tsk);
+ put_task_struct(tsk);
+ sq_pid = sq->task_pid;
+ sq_cpu = sq->sq_cpu;
+ sq_total_time = usec;
+ sq_work_time = sq->work_time;
+ } else {
+ rcu_read_unlock();
+ }
}
- seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
- for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
- struct io_mapped_ubuf *buf = ctx->user_bufs[i];
- unsigned int len = buf->ubuf_end - buf->ubuf;
- seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len);
+ seq_printf(m, "SqThread:\t%d\n", sq_pid);
+ seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+ seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
+ seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
+ seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr);
+ for (i = 0; i < ctx->file_table.data.nr; i++) {
+ struct file *f = NULL;
+
+ if (ctx->file_table.data.nodes[i])
+ f = io_slot_file(ctx->file_table.data.nodes[i]);
+ if (f) {
+ seq_printf(m, "%5u: ", i);
+ seq_file_path(m, f, " \t\n\\");
+ seq_puts(m, "\n");
+ }
}
- if (has_lock && !xa_empty(&ctx->personalities)) {
- unsigned long index;
- const struct cred *cred;
+ seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);
+ for (i = 0; i < ctx->buf_table.nr; i++) {
+ struct io_mapped_ubuf *buf = NULL;
- seq_printf(m, "Personalities:\n");
- xa_for_each(&ctx->personalities, index, cred)
- io_uring_show_cred(m, index, cred);
+ if (ctx->buf_table.nodes[i])
+ buf = ctx->buf_table.nodes[i]->buf;
+ if (buf)
+ seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, buf->len);
+ else
+ seq_printf(m, "%5u: <none>\n", i);
}
seq_puts(m, "PollList:\n");
for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
- struct io_hash_bucket *hbl = &ctx->cancel_table_locked.hbs[i];
struct io_kiocb *req;
- spin_lock(&hb->lock);
hlist_for_each_entry(req, &hb->list, hash_node)
seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
- task_work_pending(req->task));
- spin_unlock(&hb->lock);
-
- if (!has_lock)
- continue;
- hlist_for_each_entry(req, &hbl->list, hash_node)
- seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
- task_work_pending(req->task));
+ task_work_pending(req->tctx->task));
}
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
-
seq_puts(m, "CqOverflowList:\n");
spin_lock(&ctx->completion_lock);
list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
@@ -202,17 +240,25 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
cqe->user_data, cqe->res, cqe->flags);
}
-
spin_unlock(&ctx->completion_lock);
+ napi_show_fdinfo(ctx, m);
}
-__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
+/*
+ * Caller holds a reference to the file already, we don't need to do
+ * anything else to get an extra reference.
+ */
+__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
{
- struct io_ring_ctx *ctx = f->private_data;
+ struct io_ring_ctx *ctx = file->private_data;
- if (percpu_ref_tryget(&ctx->refs)) {
+ /*
+ * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
+ * since fdinfo case grabs it in the opposite direction of normal use
+ * cases.
+ */
+ if (mutex_trylock(&ctx->uring_lock)) {
__io_uring_show_fdinfo(ctx, m);
- percpu_ref_put(&ctx->refs);
+ mutex_unlock(&ctx->uring_lock);
}
}
-#endif
generated by cgit (git 2.34.1) at 2025-12-21 19:46:38 +0000