Commit
0b34e7b20a48710b6f53716bf7030920b69fdbdd upstream.
The io_tctx_node allocated the first time a task touches a ring, and
the XArray nodes behind tctx->xa and ctx->personalities, are plain
GFP_KERNEL. tctx->xa is indexed by the ring pointer, so nearly every
entry needs nodes of its own, and a task gets one entry per ring it has
used. 642 threads on 4000 rings held 2.3GB with 59MB charged against a
64MB memory.max.
Allocate the node with GFP_KERNEL_ACCOUNT and set XA_FLAGS_ACCOUNT on
both XArrays.
Fixes: 0f2122045b94 ("io_uring: don't rely on weak ->files references")
Signed-off-by: Chris Mason <mason@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
[axboe: 6.18 has kmalloc() for the node, inline in
__io_uring_add_tctx_node()]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
if (ret)
goto free_ref;
init_completion(&ctx->ref_comp);
- xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
+ xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->cq_wait);
init_waitqueue_head(&ctx->poll_wq);
}
tctx->task = task;
- xa_init(&tctx->xa);
+ xa_init_flags(&tctx->xa, XA_FLAGS_ACCOUNT);
init_waitqueue_head(&tctx->wait);
atomic_set(&tctx->in_cancel, 0);
atomic_set(&tctx->inflight_tracked, 0);
if (tctx->io_wq)
io_wq_set_exit_on_idle(tctx->io_wq, false);
if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
- node = kmalloc(sizeof(*node), GFP_KERNEL);
+ node = kmalloc(sizeof(*node), GFP_KERNEL_ACCOUNT);
if (!node)
return -ENOMEM;
node->ctx = ctx;