All DMA heaps now register a new GPU cgroup bucket upon creation, and the system_heap now exports buffers associated with its GPU cgroup bucket for tracking purposes.

In order to support GPU cgroup charge transfer on a dma-buf, the current GPU cgroup information must be stored inside the dma-buf struct. For tracked buffers, exporters include the struct gpucg and struct gpucg_bucket pointers in the export info which can later be modified if the charge is migrated to another cgroup.

Signed-off-by: Hridya Valsaraju hridya@google.com Signed-off-by: T.J. Mercier tjmercier@google.com

--- v5 changes Merge dmabuf: Use the GPU cgroup charge/uncharge APIs into this patch.

Remove all GPU cgroup code from dma-buf except what's necessary to support charge transfer. Previously charging was done in export, but for non-Android graphics use-cases this is not ideal since there may be a dealy between allocation and export, during which time there is no accounting.

Append "-heap" to gpucg_bucket names.

Charge on allocation instead of export. This should more closely mirror non-Android use-cases where there is potentially a delay between allocation and export.

Put the charge and uncharge code in the same file (system_heap_allocate, system_heap_dma_buf_release) instead of splitting them between the heap and the dma_buf_release.

Move no-op code to header file to match other files in the series.

v3 changes Use more common dual author commit message format per John Stultz.

v2 changes Move dma-buf cgroup charge transfer from a dma_buf_op defined by every heap to a single dma-buf function for all heaps per Daniel Vetter and Christian König. --- drivers/dma-buf/dma-buf.c | 19 +++++++++++++ drivers/dma-buf/dma-heap.c | 39 +++++++++++++++++++++++++++ drivers/dma-buf/heaps/system_heap.c | 28 +++++++++++++++++--- include/linux/dma-buf.h | 41 +++++++++++++++++++++++------ include/linux/dma-heap.h | 15 +++++++++++ 5 files changed, 130 insertions(+), 12 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index df23239b04fc..bc89c44bd9b9 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -462,6 +462,24 @@ static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) * &dma_buf_ops. */

+#ifdef CONFIG_CGROUP_GPU +static void dma_buf_set_gpucg(struct dma_buf *dmabuf, const struct dma_buf_export_info *exp) +{ + dmabuf->gpucg = exp->gpucg; + dmabuf->gpucg_bucket = exp->gpucg_bucket; +} + +void dma_buf_exp_info_set_gpucg(struct dma_buf_export_info *exp_info, + struct gpucg *gpucg, + struct gpucg_bucket *gpucg_bucket) +{ + exp_info->gpucg = gpucg; + exp_info->gpucg_bucket = gpucg_bucket; +} +#else +static void dma_buf_set_gpucg(struct dma_buf *dmabuf, struct dma_buf_export_info *exp) {} +#endif + /** * dma_buf_export - Creates a new dma_buf, and associates an anon file * with this buffer, so it can be exported. @@ -527,6 +545,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) init_waitqueue_head(&dmabuf->poll); dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; dmabuf->cb_in.active = dmabuf->cb_out.active = 0; + dma_buf_set_gpucg(dmabuf, exp_info);

if (!resv) { resv = (struct dma_resv *)&dmabuf[1]; diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 8f5848aa144f..b81015548314 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -7,10 +7,12 @@ */

#include <linux/cdev.h> +#include <linux/cgroup_gpu.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/dma-buf.h> #include <linux/err.h> +#include <linux/kconfig.h> #include <linux/xarray.h> #include <linux/list.h> #include <linux/slab.h> @@ -21,6 +23,7 @@ #include <uapi/linux/dma-heap.h>

#define DEVNAME "dma_heap" +#define HEAP_NAME_SUFFIX "-heap"

#define NUM_HEAP_MINORS 128

@@ -31,6 +34,7 @@ * @heap_devt heap device node * @list list head connecting to list of heaps * @heap_cdev heap char device + * @gpucg_bucket gpu cgroup bucket for memory accounting * * Represents a heap of memory from which buffers can be made. */ @@ -41,6 +45,9 @@ struct dma_heap { dev_t heap_devt; struct list_head list; struct cdev heap_cdev; +#ifdef CONFIG_CGROUP_GPU + struct gpucg_bucket gpucg_bucket; +#endif };

static LIST_HEAD(heap_list); @@ -216,6 +223,19 @@ const char *dma_heap_get_name(struct dma_heap *heap) return heap->name; }

+/** + * dma_heap_get_gpucg_bucket() - get struct gpucg_bucket for the heap. + * @heap: DMA-Heap to get the gpucg_bucket struct for. + * + * Returns: + * The gpucg_bucket struct for the heap. NULL if the GPU cgroup controller is + * not enabled. + */ +struct gpucg_bucket *dma_heap_get_gpucg_bucket(struct dma_heap *heap) +{ + return &heap->gpucg_bucket; +} + struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { struct dma_heap *heap, *h, *err_ret; @@ -228,6 +248,12 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) return ERR_PTR(-EINVAL); }

+ if (IS_ENABLED(CONFIG_CGROUP_GPU) && strlen(exp_info->name) + strlen(HEAP_NAME_SUFFIX) >= + GPUCG_BUCKET_NAME_MAX_LEN) { + pr_err("dma_heap: Name is too long for GPU cgroup\n"); + return ERR_PTR(-ENAMETOOLONG); + } + if (!exp_info->ops || !exp_info->ops->allocate) { pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); return ERR_PTR(-EINVAL); @@ -253,6 +279,19 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) heap->ops = exp_info->ops; heap->priv = exp_info->priv;

+ if (IS_ENABLED(CONFIG_CGROUP_GPU)) { + char gpucg_bucket_name[GPUCG_BUCKET_NAME_MAX_LEN]; + + snprintf(gpucg_bucket_name, sizeof(gpucg_bucket_name), "%s%s", + exp_info->name, HEAP_NAME_SUFFIX); + + ret = gpucg_register_bucket(dma_heap_get_gpucg_bucket(heap), gpucg_bucket_name); + if (ret < 0) { + err_ret = ERR_PTR(ret); + goto err0; + } + } + /* Find unused minor number */ ret = xa_alloc(&dma_heap_minors, &minor, heap, XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index fcf836ba9c1f..27f686faef00 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -297,6 +297,11 @@ static void system_heap_dma_buf_release(struct dma_buf *dmabuf) } sg_free_table(table); kfree(buffer); + + if (dmabuf->gpucg && dmabuf->gpucg_bucket) { + gpucg_uncharge(dmabuf->gpucg, dmabuf->gpucg_bucket, dmabuf->size); + gpucg_put(dmabuf->gpucg); + } }

static const struct dma_buf_ops system_heap_buf_ops = { @@ -346,11 +351,21 @@ static struct dma_buf *system_heap_allocate(struct dma_heap *heap, struct scatterlist *sg; struct list_head pages; struct page *page, *tmp_page; - int i, ret = -ENOMEM; + struct gpucg *gpucg; + struct gpucg_bucket *gpucg_bucket; + int i, ret; + + gpucg = gpucg_get(current); + gpucg_bucket = dma_heap_get_gpucg_bucket(heap); + ret = gpucg_charge(gpucg, gpucg_bucket, len); + if (ret) + goto put_gpucg;

buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); - if (!buffer) - return ERR_PTR(-ENOMEM); + if (!buffer) { + ret = -ENOMEM; + goto uncharge_gpucg; + }

INIT_LIST_HEAD(&buffer->attachments); mutex_init(&buffer->lock); @@ -396,6 +411,8 @@ static struct dma_buf *system_heap_allocate(struct dma_heap *heap, exp_info.size = buffer->len; exp_info.flags = fd_flags; exp_info.priv = buffer; + dma_buf_exp_info_set_gpucg(&exp_info, gpucg, gpucg_bucket); + dmabuf = dma_buf_export(&exp_info); if (IS_ERR(dmabuf)) { ret = PTR_ERR(dmabuf); @@ -414,7 +431,10 @@ static struct dma_buf *system_heap_allocate(struct dma_heap *heap, list_for_each_entry_safe(page, tmp_page, &pages, lru) __free_pages(page, compound_order(page)); kfree(buffer); - +uncharge_gpucg: + gpucg_uncharge(gpucg, gpucg_bucket, len); +put_gpucg: + gpucg_put(gpucg); return ERR_PTR(ret); }

diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 2097760e8e95..8e7c55c830b3 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -13,6 +13,7 @@ #ifndef __DMA_BUF_H__ #define __DMA_BUF_H__

+#include <linux/cgroup_gpu.h> #include <linux/iosys-map.h> #include <linux/file.h> #include <linux/err.h> @@ -303,7 +304,7 @@ struct dma_buf { /** * @size: * - * Size of the buffer; invariant over the lifetime of the buffer. + * Size of the buffer in bytes; invariant over the lifetime of the buffer. */ size_t size;

@@ -453,6 +454,14 @@ struct dma_buf { struct dma_buf *dmabuf; } *sysfs_entry; #endif + +#ifdef CONFIG_CGROUP_GPU + /** @gpucg: Pointer to the GPU cgroup this buffer currently belongs to. */ + struct gpucg *gpucg; + + /* @gpucg_bucket: Pointer to the GPU cgroup bucket whence this buffer originates. */ + struct gpucg_bucket *gpucg_bucket; +#endif };

/** @@ -526,13 +535,15 @@ struct dma_buf_attachment {

/** * struct dma_buf_export_info - holds information needed to export a dma_buf - * @exp_name: name of the exporter - useful for debugging. - * @owner: pointer to exporter module - used for refcounting kernel module - * @ops: Attach allocator-defined dma buf ops to the new buffer - * @size: Size of the buffer - invariant over the lifetime of the buffer - * @flags: mode flags for the file - * @resv: reservation-object, NULL to allocate default one - * @priv: Attach private data of allocator to this buffer + * @exp_name: name of the exporter - useful for debugging. + * @owner: pointer to exporter module - used for refcounting kernel module + * @ops: Attach allocator-defined dma buf ops to the new buffer + * @size: Size of the buffer in bytes - invariant over the lifetime of the buffer + * @flags: mode flags for the file + * @resv: reservation-object, NULL to allocate default one + * @priv: Attach private data of allocator to this buffer + * @gpucg: Pointer to GPU cgroup this buffer is charged to, or NULL if not charged + * @gpucg_bucket: Pointer to GPU cgroup bucket this buffer comes from, or NULL if not charged * * This structure holds the information required to export the buffer. Used * with dma_buf_export() only. @@ -545,6 +556,10 @@ struct dma_buf_export_info { int flags; struct dma_resv *resv; void *priv; +#ifdef CONFIG_CGROUP_GPU + struct gpucg *gpucg; + struct gpucg_bucket *gpucg_bucket; +#endif };

/** @@ -630,4 +645,14 @@ int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map); void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map); + +#ifdef CONFIG_CGROUP_GPU +void dma_buf_exp_info_set_gpucg(struct dma_buf_export_info *exp_info, + struct gpucg *gpucg, + struct gpucg_bucket *gpucg_bucket); +#else/* CONFIG_CGROUP_GPU */ +static inline void dma_buf_exp_info_set_gpucg(struct dma_buf_export_info *exp_info, + struct gpucg *gpucg, + struct gpucg_bucket *gpucg_bucket) {} +#endif /* CONFIG_CGROUP_GPU */ #endif /* __DMA_BUF_H__ */ diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 0c05561cad6e..6321e7636538 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -10,6 +10,7 @@ #define _DMA_HEAPS_H

#include <linux/cdev.h> +#include <linux/cgroup_gpu.h> #include <linux/types.h>

struct dma_heap; @@ -59,6 +60,20 @@ void *dma_heap_get_drvdata(struct dma_heap *heap); */ const char *dma_heap_get_name(struct dma_heap *heap);

+#ifdef CONFIG_CGROUP_GPU +/** + * dma_heap_get_gpucg_bucket() - get a pointer to the struct gpucg_bucket for the heap. + * @heap: DMA-Heap to retrieve gpucg_bucket for + * + * Returns: + * The gpucg_bucket struct for the heap. + */ +struct gpucg_bucket *dma_heap_get_gpucg_bucket(struct dma_heap *heap); +#else /* CONFIG_CGROUP_GPU */ +static inline struct gpucg_bucket *dma_heap_get_gpucg_bucket(struct dma_heap *heap) +{ return NULL; } +#endif /* CONFIG_CGROUP_GPU */ + /** * dma_heap_add - adds a heap to dmabuf heaps * @exp_info: information needed to register this heap

From: Hridya Valsaraju hridya@google.com

This patch introduces flags BINDER_FD_FLAG_SENDER_NO_NEED, and BINDER_FDA_FLAG_SENDER_NO_NEED that a process sending an individual fd or 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 or 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 up to 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 *_FLAG_SENDER_NO_NEED for fd arrays holding DMA-BUF fds, or individual fd objects, the gpu cgroup controller will be able to correctly charge the buffers to the client processes instead of the graphics allocator HAL.

Since this is a new feature exposed to userspace, the kernel and userspace must be compatible for the accounting to work for transfers. In all cases the allocation and transport of DMA buffers via binder will succeed, but only when both the kernel supports, and userspace depends on this feature will the transfer accounting work. The possible scenarios are detailed below:

1. new kernel + old userspace The kernel supports the feature but userspace does not use it. The old userspace won't mount the new cgroup controller, accounting is not performed, charge is not transferred.

2. old kernel + new userspace The new cgroup controller is not supported by the kernel, accounting is not performed, charge is not transferred.

3. old kernel + old userspace Same as #2

4. new kernel + new userspace Cgroup is mounted, feature is supported and used.

Signed-off-by: Hridya Valsaraju hridya@google.com Signed-off-by: T.J. Mercier tjmercier@google.com

--- v5 changes Support both binder_fd_array_object and binder_fd_object. This is necessary because new versions of Android will use binder_fd_object instead of binder_fd_array_object, and we need to support both.

Use the new, simpler dma_buf_transfer_charge API.

v3 changes Remove android from title per Todd Kjos.

Use more common dual author commit message format per John Stultz.

Include details on behavior for all combinations of kernel/userspace versions in changelog (thanks Suren Baghdasaryan) per Greg Kroah-Hartman.

v2 changes Move dma-buf cgroup charge transfer from a dma_buf_op defined by every heap to a single dma-buf function for all heaps per Daniel Vetter and Christian König. --- drivers/android/binder.c | 27 +++++++++++++++++++++++---- drivers/dma-buf/dma-buf.c | 4 ++-- include/linux/dma-buf.h | 2 +- include/uapi/linux/android/binder.h | 23 +++++++++++++++++++---- 4 files changed, 45 insertions(+), 11 deletions(-)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8351c5638880..b07d50fe1c80 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> @@ -2170,7 +2171,7 @@ static int binder_translate_handle(struct flat_binder_object *fp, return ret; }

-static int binder_translate_fd(u32 fd, binder_size_t fd_offset, +static int binder_translate_fd(u32 fd, binder_size_t fd_offset, __u32 flags, struct binder_transaction *t, struct binder_thread *thread, struct binder_transaction *in_reply_to) @@ -2208,6 +2209,23 @@ static int binder_translate_fd(u32 fd, binder_size_t fd_offset, goto err_security; }

+ if (IS_ENABLED(CONFIG_CGROUP_GPU) && (flags & BINDER_FD_FLAG_SENDER_NO_NEED)) { + if (is_dma_buf_file(file)) { + struct dma_buf *dmabuf = file->private_data; + + ret = dma_buf_transfer_charge(dmabuf, target_proc->tsk); + if (ret) + pr_warn("%d:%d Unable to transfer DMA-BUF fd charge to %d\n", + proc->pid, thread->pid, target_proc->pid); + } else { + binder_user_error( + "%d:%d got transaction with SENDER_NO_NEED for non-dmabuf fd, %d\n", + proc->pid, thread->pid, fd); + ret = -EINVAL; + goto err_noneed; + } + } + /* * Add fixup record for this transaction. The allocation * of the fd in the target needs to be done from a @@ -2226,6 +2244,7 @@ static int binder_translate_fd(u32 fd, binder_size_t fd_offset, return ret;

err_alloc: +err_noneed: err_security: fput(file); err_fget: @@ -2528,7 +2547,7 @@ static int binder_translate_fd_array(struct list_head *pf_head,

ret = copy_from_user(&fd, sender_ufda_base + sender_uoffset, sizeof(fd)); if (!ret) - ret = binder_translate_fd(fd, offset, t, thread, + ret = binder_translate_fd(fd, offset, fda->flags, t, thread, in_reply_to); if (ret) return ret > 0 ? -EINVAL : ret; @@ -3179,8 +3198,8 @@ static void binder_transaction(struct binder_proc *proc, struct binder_fd_object *fp = to_binder_fd_object(hdr); binder_size_t fd_offset = object_offset + (uintptr_t)&fp->fd - (uintptr_t)fp; - int ret = binder_translate_fd(fp->fd, fd_offset, t, - thread, in_reply_to); + int ret = binder_translate_fd(fp->fd, fd_offset, fp->flags, + t, thread, in_reply_to);

fp->pad_binder = 0; if (ret < 0 || diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index f3fb844925e2..36ed6cd4ddcc 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -31,7 +31,6 @@

#include "dma-buf-sysfs-stats.h"

-static inline int is_dma_buf_file(struct file *);

struct dma_buf_list { struct list_head head; @@ -400,10 +399,11 @@ static const struct file_operations dma_buf_fops = { /* * is_dma_buf_file - Check if struct file* is associated with dma_buf */ -static inline int is_dma_buf_file(struct file *file) +int is_dma_buf_file(struct file *file) { return file->f_op == &dma_buf_fops; } +EXPORT_SYMBOL_NS_GPL(is_dma_buf_file, DMA_BUF);

static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags) { diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 438ad8577b76..2b9812758fee 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -614,7 +614,7 @@ dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) { return !!attach->importer_ops; } - +int is_dma_buf_file(struct file *file); struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); struct dma_buf_attachment * diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 11157fae8a8e..b263cbb603ea 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -91,14 +91,14 @@ struct flat_binder_object { /** * struct binder_fd_object - describes a filedescriptor to be fixed up. * @hdr: common header structure - * @pad_flags: padding to remain compatible with old userspace code + * @flags: One or more BINDER_FD_FLAG_* flags * @pad_binder: padding to remain compatible with old userspace code * @fd: file descriptor * @cookie: opaque data, used by user-space */ struct binder_fd_object { struct binder_object_header hdr; - __u32 pad_flags; + __u32 flags; union { binder_uintptr_t pad_binder; __u32 fd; @@ -107,6 +107,17 @@ struct binder_fd_object { binder_uintptr_t cookie; };

+enum { + /** + * @BINDER_FD_FLAG_SENDER_NO_NEED + * + * When set, the sender of a binder_fd_object wishes to relinquish ownership of the fd for + * memory accounting purposes. If 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. + */ + BINDER_FD_FLAG_SENDER_NO_NEED = 0x2000, +}; + /* struct binder_buffer_object - object describing a userspace buffer * @hdr: common header structure * @flags: one or more BINDER_BUFFER_* flags @@ -141,7 +152,7 @@ enum {

/* struct binder_fd_array_object - object describing an array of fds in a buffer * @hdr: common header structure - * @pad: padding to ensure correct alignment + * flags: One or more BINDER_FDA_FLAG_* flags * @num_fds: number of file descriptors in the buffer * @parent: index in offset array to buffer holding the fd array * @parent_offset: start offset of fd array in the buffer @@ -162,12 +173,16 @@ enum { */ struct binder_fd_array_object { struct binder_object_header hdr; - __u32 pad; + __u32 flags; binder_size_t num_fds; binder_size_t parent; binder_size_t parent_offset; };

+enum { + BINDER_FDA_FLAG_SENDER_NO_NEED = BINDER_FD_FLAG_SENDER_NO_NEED, +}; + /* * On 64-bit platforms where user code may run in 32-bits the driver must * translate the buffer (and local binder) addresses appropriately.