All of lore.kernel.org
 help / color / mirror / Atom feed
From: Hridya Valsaraju <hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
To: "David Airlie" <airlied-cv59FeDIM0c@public.gmane.org>,
	"Daniel Vetter" <daniel-/w4YWyX8dFk@public.gmane.org>,
	"Maarten Lankhorst"
	<maarten.lankhorst-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>,
	"Maxime Ripard" <mripard-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	"Thomas Zimmermann" <tzimmermann-l3A5Bk7waGM@public.gmane.org>,
	"Jonathan Corbet" <corbet-T1hC0tSOHrs@public.gmane.org>,
	"Greg Kroah-Hartman"
	<gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r@public.gmane.org>,
	"Arve Hjønnevåg" <arve-z5hGa2qSFaRBDgjK7y7TUQ@public.gmane.org>,
	"Todd Kjos" <tkjos-z5hGa2qSFaRBDgjK7y7TUQ@public.gmane.org>,
	"Martijn Coenen" <maco-z5hGa2qSFaRBDgjK7y7TUQ@public.gmane.org>,
	"Joel Fernandes"
	<joel-QYYGw3jwrUn5owFQY34kdNi2O/JbrIOy@public.gmane.org>,
	"Christian Brauner"
	<christian-STijNZzMWpgWenYVfaLwtA@public.gmane.org>,
	"Hridya Valsaraju"
	<hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
	"Suren Baghdasaryan"
	<surenb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
	"Sumit Semwal"
	<sumit.semwal-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>,
	"Benjamin Gaignard"
	<benjamin.gaignard-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>,
	"Liam Mark" <lmark-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>,
	"Laura Abbott" <labbott-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"Brian Starkey" <Brian.Starkey@arm>
Cc: Kenny.Ho-5C7GfCeVMHo@public.gmane.org,
	daniels-ZGY8ohtN/8qB+jHODAdFcQ@public.gmane.org,
	kaleshsingh-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org,
	tjmercier-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org
Subject: [RFC 6/6] android: binder: Add a buffer flag to relinquish ownership of fds
Date: Fri, 14 Jan 2022 17:06:04 -0800	[thread overview]
Message-ID: <20220115010622.3185921-7-hridya__10502.2349905752$1642208956$gmane$org@google.com> (raw)
In-Reply-To: <20220115010622.3185921-1-hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>

This patch introduces a buffer flag BINDER_BUFFER_FLAG_SENDER_NO_NEED
that a process sending an fd array to another process over binder IPC
can set to relinquish ownership of the fds being sent for memory
accounting purposes. If the flag is found to be set during the fd array
translation and the fd is for a DMA-BUF, the buffer is uncharged from
the sender's cgroup and charged to the receiving process's cgroup
instead.

It is upto the sending process to ensure that it closes the fds
regardless of whether the transfer failed or succeeded.

Most graphics shared memory allocations in Android are done by the
graphics allocator HAL process. On requests from clients, the HAL process
allocates memory and sends the fds to the clients over binder IPC.
The graphics allocator HAL will not retain any references to the
buffers. When the HAL sets the BINDER_BUFFER_FLAG_SENDER_NO_NEED for fd
arrays holding DMA-BUF fds, the gpu cgroup controller will be able to
correctly charge the buffers to the client processes instead of the
graphics allocator HAL.

Signed-off-by: Hridya Valsaraju <hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
---
 drivers/android/binder.c            | 32 +++++++++++++++++++++++++++++
 include/uapi/linux/android/binder.h |  1 +
 2 files changed, 33 insertions(+)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 5497797ab258..83082fd1ab6a 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -42,6 +42,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/dma-buf.h>
 #include <linux/fdtable.h>
 #include <linux/file.h>
 #include <linux/freezer.h>
@@ -2482,8 +2483,11 @@ static int binder_translate_fd_array(struct list_head *pf_head,
 {
 	binder_size_t fdi, fd_buf_size;
 	binder_size_t fda_offset;
+	bool transfer_gpu_charge = false;
 	const void __user *sender_ufda_base;
 	struct binder_proc *proc = thread->proc;
+	struct binder_proc *target_proc = t->to_proc;
+
 	int ret;
 
 	fd_buf_size = sizeof(u32) * fda->num_fds;
@@ -2520,8 +2524,15 @@ static int binder_translate_fd_array(struct list_head *pf_head,
 	if (ret)
 		return ret;
 
+	if (IS_ENABLED(CONFIG_CGROUP_GPU) &&
+	    parent->flags & BINDER_BUFFER_FLAG_SENDER_NO_NEED)
+		transfer_gpu_charge = true;
+
 	for (fdi = 0; fdi < fda->num_fds; fdi++) {
 		u32 fd;
+		struct dma_buf *dmabuf;
+		struct gpucg *gpucg;
+
 		binder_size_t offset = fda_offset + fdi * sizeof(fd);
 		binder_size_t sender_uoffset = fdi * sizeof(fd);
 
@@ -2531,6 +2542,27 @@ static int binder_translate_fd_array(struct list_head *pf_head,
 						  in_reply_to);
 		if (ret)
 			return ret > 0 ? -EINVAL : ret;
+
+		if (!transfer_gpu_charge)
+			continue;
+
+		dmabuf = dma_buf_get(fd);
+		if (IS_ERR(dmabuf))
+			continue;
+
+		if (dmabuf->ops->charge_to_cgroup) {
+			gpucg = gpucg_get(target_proc->tsk);
+			ret = dmabuf->ops->charge_to_cgroup(dmabuf, gpucg);
+			if (ret) {
+				pr_warn("%d:%d Unable to transfer DMA-BUF fd charge to %d",
+					proc->pid, thread->pid, target_proc->pid);
+				gpucg_put(gpucg);
+			}
+		} else {
+			pr_warn("%d:%d DMA-BUF exporter %s is not configured correctly for GPU cgroup memory accounting",
+				proc->pid, thread->pid, dmabuf->exp_name);
+		}
+		dma_buf_put(dmabuf);
 	}
 	return 0;
 }
diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
index ad619623571e..c85f0014c341 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -137,6 +137,7 @@ struct binder_buffer_object {
 
 enum {
 	BINDER_BUFFER_FLAG_HAS_PARENT = 0x01,
+	BINDER_BUFFER_FLAG_SENDER_NO_NEED = 0x02,
 };
 
 /* struct binder_fd_array_object - object describing an array of fds in a buffer
-- 
2.34.1.703.g22d0c6ccf7-goog


  parent reply	other threads:[~2022-01-15  1:06 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-15  1:05 [RFC 0/6] Proposal for a GPU cgroup controller Hridya Valsaraju
2022-01-15  1:05 ` Hridya Valsaraju
2022-01-15  1:05 ` Hridya Valsaraju
2022-01-15  1:05 ` [RFC 1/6] gpu: rfc: " Hridya Valsaraju
2022-01-15  1:05   ` Hridya Valsaraju
2022-01-15  1:06 ` [RFC 2/6] cgroup: gpu: Add a cgroup controller for allocator attribution of GPU memory Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju
     [not found]   ` <20220115010622.3185921-3-hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2022-01-19 15:40     ` Randy Dunlap
2022-01-19 15:40   ` Randy Dunlap
2022-01-19 15:40     ` Randy Dunlap
2022-01-19 18:24     ` Hridya Valsaraju
2022-01-19 18:24       ` Hridya Valsaraju
2022-01-19 18:24       ` Hridya Valsaraju
2022-01-15  1:06 ` [RFC 3/6] dmabuf: heaps: Use the GPU cgroup charge/uncharge APIs Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju
     [not found] ` <20220115010622.3185921-1-hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2022-01-15  1:05   ` [RFC 1/6] gpu: rfc: Proposal for a GPU cgroup controller Hridya Valsaraju
2022-01-15  1:06   ` [RFC 2/6] cgroup: gpu: Add a cgroup controller for allocator attribution of GPU memory Hridya Valsaraju
2022-01-15  1:06   ` [RFC 3/6] dmabuf: heaps: Use the GPU cgroup charge/uncharge APIs Hridya Valsaraju
2022-01-15  1:06   ` [RFC 4/6] dma-buf: Add DMA-BUF exporter op to charge a DMA-BUF to a cgroup Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju [this message]
2022-01-15  1:06 ` Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju
2022-01-17  7:46   ` Christian König
2022-01-17  7:46     ` Christian König
2022-01-18 18:54     ` Hridya Valsaraju
2022-01-18 18:54       ` Hridya Valsaraju
2022-01-18 18:54       ` Hridya Valsaraju
2022-01-19 15:54       ` Daniel Vetter
2022-01-19 15:54         ` Daniel Vetter
2022-01-19 15:54         ` Daniel Vetter
2022-01-19 15:58         ` Christian König
2022-01-19 18:21           ` Hridya Valsaraju
2022-01-19 18:21             ` Hridya Valsaraju
2022-01-19 18:21             ` Hridya Valsaraju
     [not found]         ` <Yeg0GGi0tdnnCLHg-dv86pmgwkMBes7Z6vYuT8azUEOm+Xw19@public.gmane.org>
2022-01-19 15:58           ` Christian König
     [not found]   ` <20220115010622.3185921-5-hridya-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2022-01-17  7:46     ` Christian König
2022-01-15  1:06 ` [RFC 5/6] dmabuf: system_heap: implement dma-buf op for GPU cgroup charge transfer Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju
2022-01-15  1:06 ` [RFC 6/6] android: binder: Add a buffer flag to relinquish ownership of fds Hridya Valsaraju
2022-01-15  1:06   ` Hridya Valsaraju

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='20220115010622.3185921-7-hridya__10502.2349905752$1642208956$gmane$org@google.com' \
    --to=hridya-hpiqsd4aklfqt0dzr+alfa@public.gmane.org \
    --cc=Brian.Starkey@arm \
    --cc=Kenny.Ho-5C7GfCeVMHo@public.gmane.org \
    --cc=airlied-cv59FeDIM0c@public.gmane.org \
    --cc=arve-z5hGa2qSFaRBDgjK7y7TUQ@public.gmane.org \
    --cc=benjamin.gaignard-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org \
    --cc=christian-STijNZzMWpgWenYVfaLwtA@public.gmane.org \
    --cc=corbet-T1hC0tSOHrs@public.gmane.org \
    --cc=daniel-/w4YWyX8dFk@public.gmane.org \
    --cc=daniels-ZGY8ohtN/8qB+jHODAdFcQ@public.gmane.org \
    --cc=gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r@public.gmane.org \
    --cc=joel-QYYGw3jwrUn5owFQY34kdNi2O/JbrIOy@public.gmane.org \
    --cc=kaleshsingh-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=labbott-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=lmark-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org \
    --cc=maarten.lankhorst-VuQAYsv1563Yd54FQh9/CA@public.gmane.org \
    --cc=maco-z5hGa2qSFaRBDgjK7y7TUQ@public.gmane.org \
    --cc=mripard-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
    --cc=sumit.semwal-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org \
    --cc=surenb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=tjmercier-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
    --cc=tkjos-z5hGa2qSFaRBDgjK7y7TUQ@public.gmane.org \
    --cc=tzimmermann-l3A5Bk7waGM@public.gmane.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.