Merge branch 'for-5.20/io_uring' into for-5.20/io_uring-zerocopy-send

* for-5.20/io_uring: (716 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 194 insertions, 0 deletions

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
new file mode 100644
index 000000000000..b29e2d02216f
--- /dev/null
+++ b/io_uring/fdinfo.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "sqpoll.h"
+#include "fdinfo.h"
+#include "cancel.h"
+#include "rsrc.h"
+
+#ifdef CONFIG_PROC_FS
+static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
+		const struct cred *cred)
+{
+	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, "\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;
+}
+
+static __cold 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;
+	unsigned int sq_head = READ_ONCE(r->sq.head);
+	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_entries, cq_entries;
+	bool has_lock;
+	bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+	unsigned int i;
+
+	if (is_cqe32)
+		cq_shift = 1;
+
+	/*
+	 * we may get imprecise sqe and cqe info if uring is actively running
+	 * since we get cached_sq_head and cached_cq_tail without uring_lock
+	 * and sq_tail and cq_head are changed by userspace. But it's ok since
+	 * we usually use these info when it is stuck.
+	 */
+	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, "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, "SQEs:\t%u\n", sq_tail - ctx->cached_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;
+		unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
+		struct io_uring_sqe *sqe;
+
+		if (sq_idx > sq_mask)
+			continue;
+		sqe = &ctx->sq_sqes[sq_idx];
+		seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n",
+			   sq_idx, sqe->opcode, sqe->fd, sqe->flags,
+			   sqe->user_data);
+	}
+	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];
+
+		if (!is_cqe32) {
+			seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
+			   entry & cq_mask, cqe->user_data, cqe->res,
+			   cqe->flags);
+		} else {
+			seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, "
+				"extra1:%llu, extra2:%llu\n",
+				entry & cq_mask, cqe->user_data, cqe->res,
+				cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]);
+		}
+	}
+
+	/*
+	 * 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;
+	}
+
+	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);
+
+		if (f)
+			seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname);
+		else
+			seq_printf(m, "%5u: <none>\n", i);
+	}
+	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);
+	}
+	if (has_lock && !xa_empty(&ctx->personalities)) {
+		unsigned long index;
+		const struct cred *cred;
+
+		seq_printf(m, "Personalities:\n");
+		xa_for_each(&ctx->personalities, index, cred)
+			io_uring_show_cred(m, index, cred);
+	}
+	if (has_lock)
+		mutex_unlock(&ctx->uring_lock);
+
+	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_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);
+	}
+
+	seq_puts(m, "CqOverflowList:\n");
+	spin_lock(&ctx->completion_lock);
+	list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
+		struct io_uring_cqe *cqe = &ocqe->cqe;
+
+		seq_printf(m, "  user_data=%llu, res=%d, flags=%x\n",
+			   cqe->user_data, cqe->res, cqe->flags);
+
+	}
+
+	spin_unlock(&ctx->completion_lock);
+}
+
+__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct io_ring_ctx *ctx = f->private_data;
+
+	if (percpu_ref_tryget(&ctx->refs)) {
+		__io_uring_show_fdinfo(ctx, m);
+		percpu_ref_put(&ctx->refs);
+	}
+}
+#endif