diff options
author | Andrey Konovalov <andrey.konovalov@linaro.org> | 2012-05-21 15:20:33 +0400 |
---|---|---|
committer | Andrey Konovalov <andrey.konovalov@linaro.org> | 2012-05-21 15:20:33 +0400 |
commit | 8e7922bcbd2d1e87abace7c4e130ac93b1ed54a8 (patch) | |
tree | 852c33c95478cbc7ec90a95d79066a88bfc6f357 | |
parent | d51d01166ef5be6f048d6f121b48224fcf1241e5 (diff) | |
parent | 4cd7db43d454d815c57d2cc171758c1caf540dd9 (diff) |
Automatically merging rebase-umm-wip into merge-linux-linaro-core-tracking
Conflicting files:
83 files changed, 3633 insertions, 481 deletions
diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml index bce97c50391b..2a2083d5caac 100644 --- a/Documentation/DocBook/media/v4l/compat.xml +++ b/Documentation/DocBook/media/v4l/compat.xml @@ -2523,6 +2523,10 @@ ioctls.</para> <listitem> <para>Selection API. <xref linkend="selection-api" /></para> </listitem> + <listitem> + <para>Importing DMABUF file descriptors as a new IO method described + in <xref linkend="dmabuf" />.</para> + </listitem> </itemizedlist> </section> diff --git a/Documentation/DocBook/media/v4l/io.xml b/Documentation/DocBook/media/v4l/io.xml index b815929b5bba..f8fb5590368c 100644 --- a/Documentation/DocBook/media/v4l/io.xml +++ b/Documentation/DocBook/media/v4l/io.xml @@ -472,6 +472,162 @@ rest should be evident.</para> </footnote></para> </section> + <section id="dmabuf"> + <title>Streaming I/O (DMA buffer importing)</title> + + <note> + <title>Experimental</title> + <para>This is an <link linkend="experimental"> experimental </link> + interface and may change in the future.</para> + </note> + +<para>The DMABUF framework provides a generic mean for sharing buffers between + multiple devices. Device drivers that support DMABUF can export a DMA buffer +to userspace as a file descriptor (known as the exporter role), import a DMA +buffer from userspace using a file descriptor previously exported for a +different or the same device (known as the importer role), or both. This +section describes the DMABUF importer role API in V4L2.</para> + +<para>Input and output devices support the streaming I/O method when the +<constant>V4L2_CAP_STREAMING</constant> flag in the +<structfield>capabilities</structfield> field of &v4l2-capability; returned by +the &VIDIOC-QUERYCAP; ioctl is set. Whether importing DMA buffers through +DMABUF file descriptors is supported is determined by calling the +&VIDIOC-REQBUFS; ioctl with the memory type set to +<constant>V4L2_MEMORY_DMABUF</constant>.</para> + + <para>This I/O method is dedicated for sharing DMA buffers between V4L and +other APIs. Buffers (planes) are allocated by a driver on behalf of the +application, and exported to the application as file descriptors using an API +specific to the allocator driver. Only those file descriptor are exchanged, +these files and meta-information are passed in &v4l2-buffer; (or in +&v4l2-plane; in the multi-planar API case). The driver must be switched into +DMABUF I/O mode by calling the &VIDIOC-REQBUFS; with the desired buffer type. +No buffers (planes) are allocated beforehand, consequently they are not indexed +and cannot be queried like mapped buffers with the +<constant>VIDIOC_QUERYBUF</constant> ioctl.</para> + + <example> + <title>Initiating streaming I/O with DMABUF file descriptors</title> + + <programlisting> +&v4l2-requestbuffers; reqbuf; + +memset (&reqbuf, 0, sizeof (reqbuf)); +reqbuf.type = V4L2_BUF_TYPE_VIDEO_CAPTURE; +reqbuf.memory = V4L2_MEMORY_DMABUF; + +if (ioctl (fd, &VIDIOC-REQBUFS;, &reqbuf) == -1) { + if (errno == EINVAL) + printf ("Video capturing or DMABUF streaming is not supported\n"); + else + perror ("VIDIOC_REQBUFS"); + + exit (EXIT_FAILURE); +} + </programlisting> + </example> + + <para>Buffer (plane) file is passed on the fly with the &VIDIOC-QBUF; +ioctl. In case of multiplanar buffers, every plane can be associated with a +different DMABUF descriptor.Although buffers are commonly cycled, applications +can pass different DMABUF descriptor at each <constant>VIDIOC_QBUF</constant> +call.</para> + + <example> + <title>Queueing DMABUF using single plane API</title> + + <programlisting> +int buffer_queue(int v4lfd, int index, int dmafd) +{ + &v4l2-buffer; buf; + + memset(&buf, 0, sizeof buf); + buf.type = V4L2_BUF_TYPE_VIDEO_CAPTURE; + buf.memory = V4L2_MEMORY_DMABUF; + buf.index = index; + buf.m.fd = dmafd; + + if (ioctl (v4lfd, &VIDIOC-QBUF;, &buf) == -1) { + perror ("VIDIOC_QBUF"); + return -1; + } + + return 0; +} + </programlisting> + </example> + + <example> + <title>Queueing DMABUF using multi plane API</title> + + <programlisting> +int buffer_queue_mp(int v4lfd, int index, int dmafd[], int n_planes) +{ + &v4l2-buffer; buf; + &v4l2-plane; planes[VIDEO_MAX_PLANES]; + int i; + + memset(&buf, 0, sizeof buf); + buf.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE; + buf.memory = V4L2_MEMORY_DMABUF; + buf.index = index; + buf.m.planes = planes; + buf.length = n_planes; + + memset(&planes, 0, sizeof planes); + + for (i = 0; i < n_planes; ++i) + buf.m.planes[i].m.fd = dmafd[i]; + + if (ioctl (v4lfd, &VIDIOC-QBUF;, &buf) == -1) { + perror ("VIDIOC_QBUF"); + return -1; + } + + return 0; +} + </programlisting> + </example> + + <para>Filled or displayed buffers are dequeued with the +&VIDIOC-DQBUF; ioctl. The driver can unlock the buffer at any +time between the completion of the DMA and this ioctl. The memory is +also unlocked when &VIDIOC-STREAMOFF; is called, &VIDIOC-REQBUFS;, or +when the device is closed.</para> + + <para>For capturing applications it is customary to enqueue a +number of empty buffers, to start capturing and enter the read loop. +Here the application waits until a filled buffer can be dequeued, and +re-enqueues the buffer when the data is no longer needed. Output +applications fill and enqueue buffers, when enough buffers are stacked +up output is started. In the write loop, when the application +runs out of free buffers it must wait until an empty buffer can be +dequeued and reused. Two methods exist to suspend execution of the +application until one or more buffers can be dequeued. By default +<constant>VIDIOC_DQBUF</constant> blocks when no buffer is in the +outgoing queue. When the <constant>O_NONBLOCK</constant> flag was +given to the &func-open; function, <constant>VIDIOC_DQBUF</constant> +returns immediately with an &EAGAIN; when no buffer is available. The +&func-select; or &func-poll; function are always available.</para> + + <para>To start and stop capturing or output applications call the +&VIDIOC-STREAMON; and &VIDIOC-STREAMOFF; ioctls. Note that +<constant>VIDIOC_STREAMOFF</constant> removes all buffers from both queues and +unlocks all buffers as a side effect. Since there is no notion of doing +anything "now" on a multitasking system, if an application needs to synchronize +with another event it should examine the &v4l2-buffer; +<structfield>timestamp</structfield> of captured buffers, or set the field +before enqueuing buffers for output.</para> + + <para>Drivers implementing DMABUF importing I/O must support the +<constant>VIDIOC_REQBUFS</constant>, <constant>VIDIOC_QBUF</constant>, +<constant>VIDIOC_DQBUF</constant>, <constant>VIDIOC_STREAMON</constant> and +<constant>VIDIOC_STREAMOFF</constant> ioctl, the <function>select()</function> +and <function>poll()</function> function.</para> + + </section> + <section id="async"> <title>Asynchronous I/O</title> @@ -671,6 +827,14 @@ memory, set by the application. See <xref linkend="userp" /> for details. <structname>v4l2_buffer</structname> structure.</entry> </row> <row> + <entry></entry> + <entry>int</entry> + <entry><structfield>fd</structfield></entry> + <entry>For the single-plane API and when +<structfield>memory</structfield> is <constant>V4L2_MEMORY_DMABUF</constant> this +is the file descriptor associated with a DMABUF buffer.</entry> + </row> + <row> <entry>__u32</entry> <entry><structfield>length</structfield></entry> <entry></entry> @@ -746,6 +910,15 @@ should set this to 0.</entry> </entry> </row> <row> + <entry></entry> + <entry>int</entry> + <entry><structfield>fd</structfield></entry> + <entry>When the memory type in the containing &v4l2-buffer; is + <constant>V4L2_MEMORY_DMABUF</constant>, this is a file + descriptor associated with a DMABUF buffer, similar to the + <structfield>fd</structfield> field in &v4l2-buffer;.</entry> + </row> + <row> <entry>__u32</entry> <entry><structfield>data_offset</structfield></entry> <entry></entry> @@ -980,6 +1153,12 @@ pointer</link> I/O.</entry> <entry>3</entry> <entry>[to do]</entry> </row> + <row> + <entry><constant>V4L2_MEMORY_DMABUF</constant></entry> + <entry>2</entry> + <entry>The buffer is used for <link linkend="dmabuf">DMA shared +buffer</link> I/O.</entry> + </row> </tbody> </tgroup> </table> diff --git a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml index 73ae8a6cd004..adc92be17192 100644 --- a/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml +++ b/Documentation/DocBook/media/v4l/vidioc-create-bufs.xml @@ -98,6 +98,7 @@ information.</para> <entry><structfield>memory</structfield></entry> <entry>Applications set this field to <constant>V4L2_MEMORY_MMAP</constant> or +<constant>V4L2_MEMORY_DMABUF</constant> or <constant>V4L2_MEMORY_USERPTR</constant>.</entry> </row> <row> diff --git a/Documentation/DocBook/media/v4l/vidioc-qbuf.xml b/Documentation/DocBook/media/v4l/vidioc-qbuf.xml index 9caa49af580f..cb5f5ff80769 100644 --- a/Documentation/DocBook/media/v4l/vidioc-qbuf.xml +++ b/Documentation/DocBook/media/v4l/vidioc-qbuf.xml @@ -112,6 +112,21 @@ they cannot be swapped out to disk. Buffers remain locked until dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl is called, or until the device is closed.</para> + <para>To enqueue a <link linkend="dmabuf">DMABUF</link> buffer applications +set the <structfield>memory</structfield> field to +<constant>V4L2_MEMORY_DMABUF</constant> and the <structfield>m.fd</structfield> +to a file descriptor associated with a DMABUF buffer. When the multi-planar API is +used and <structfield>m.fd</structfield> of the passed array of &v4l2-plane; +have to be used instead. When <constant>VIDIOC_QBUF</constant> is called with a +pointer to this structure the driver sets the +<constant>V4L2_BUF_FLAG_QUEUED</constant> flag and clears the +<constant>V4L2_BUF_FLAG_MAPPED</constant> and +<constant>V4L2_BUF_FLAG_DONE</constant> flags in the +<structfield>flags</structfield> field, or it returns an error code. This +ioctl locks the buffer. Buffers remain locked until dequeued, +until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl is called, or until the +device is closed.</para> + <para>Applications call the <constant>VIDIOC_DQBUF</constant> ioctl to dequeue a filled (capturing) or displayed (output) buffer from the driver's outgoing queue. They just set the diff --git a/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml b/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml index 7be4b1d29b90..e3e709be7de9 100644 --- a/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml +++ b/Documentation/DocBook/media/v4l/vidioc-reqbufs.xml @@ -48,28 +48,30 @@ <refsect1> <title>Description</title> - <para>This ioctl is used to initiate <link linkend="mmap">memory -mapped</link> or <link linkend="userp">user pointer</link> -I/O. Memory mapped buffers are located in device memory and must be -allocated with this ioctl before they can be mapped into the -application's address space. User buffers are allocated by -applications themselves, and this ioctl is merely used to switch the -driver into user pointer I/O mode and to setup some internal structures.</para> +<para>This ioctl is used to initiate <link linkend="mmap">memory mapped</link>, +<link linkend="userp">user pointer</link> or <link +linkend="dmabuf">DMABUF</link> based I/O. Memory mapped buffers are located in +device memory and must be allocated with this ioctl before they can be mapped +into the application's address space. User buffers are allocated by +applications themselves, and this ioctl is merely used to switch the driver +into user pointer I/O mode and to setup some internal structures. +Similarly, DMABUF buffers are allocated by applications through a device +driver, and this ioctl only configures the driver into DMABUF I/O mode without +performing any direct allocation.</para> - <para>To allocate device buffers applications initialize all -fields of the <structname>v4l2_requestbuffers</structname> structure. -They set the <structfield>type</structfield> field to the respective -stream or buffer type, the <structfield>count</structfield> field to -the desired number of buffers, <structfield>memory</structfield> -must be set to the requested I/O method and the <structfield>reserved</structfield> array -must be zeroed. When the ioctl -is called with a pointer to this structure the driver will attempt to allocate -the requested number of buffers and it stores the actual number -allocated in the <structfield>count</structfield> field. It can be -smaller than the number requested, even zero, when the driver runs out -of free memory. A larger number is also possible when the driver requires -more buffers to function correctly. For example video output requires at least two buffers, -one displayed and one filled by the application.</para> + <para>To allocate device buffers applications initialize all fields of the +<structname>v4l2_requestbuffers</structname> structure. They set the +<structfield>type</structfield> field to the respective stream or buffer type, +the <structfield>count</structfield> field to the desired number of buffers, +<structfield>memory</structfield> must be set to the requested I/O method and +the <structfield>reserved</structfield> array must be zeroed. When the ioctl is +called with a pointer to this structure the driver will attempt to allocate the +requested number of buffers and it stores the actual number allocated in the +<structfield>count</structfield> field. It can be smaller than the number +requested, even zero, when the driver runs out of free memory. A larger number +is also possible when the driver requires more buffers to function correctly. +For example video output requires at least two buffers, one displayed and one +filled by the application.</para> <para>When the I/O method is not supported the ioctl returns an &EINVAL;.</para> @@ -102,7 +104,8 @@ as the &v4l2-format; <structfield>type</structfield> field. See <xref <entry>&v4l2-memory;</entry> <entry><structfield>memory</structfield></entry> <entry>Applications set this field to -<constant>V4L2_MEMORY_MMAP</constant> or +<constant>V4L2_MEMORY_MMAP</constant>, +<constant>V4L2_MEMORY_DMABUF</constant> or <constant>V4L2_MEMORY_USERPTR</constant>.</entry> </row> <row> diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt index 3bbd5c51605a..5ff4d2b84f72 100644 --- a/Documentation/dma-buf-sharing.txt +++ b/Documentation/dma-buf-sharing.txt @@ -29,13 +29,6 @@ The buffer-user in memory, mapped into its own address space, so it can access the same area of memory. -*IMPORTANT*: [see https://lkml.org/lkml/2011/12/20/211 for more details] -For this first version, A buffer shared using the dma_buf sharing API: -- *may* be exported to user space using "mmap" *ONLY* by exporter, outside of - this framework. -- with this new iteration of the dma-buf api cpu access from the kernel has been - enable, see below for the details. - dma-buf operations for device dma only -------------------------------------- @@ -313,6 +306,83 @@ Access to a dma_buf from the kernel context involves three steps: enum dma_data_direction dir); +Direct Userspace Access/mmap Support +------------------------------------ + +Being able to mmap an export dma-buf buffer object has 2 main use-cases: +- CPU fallback processing in a pipeline and +- supporting existing mmap interfaces in importers. + +1. CPU fallback processing in a pipeline + + In many processing pipelines it is sometimes required that the cpu can access + the data in a dma-buf (e.g. for thumbnail creation, snapshots, ...). To avoid + the need to handle this specially in userspace frameworks for buffer sharing + it's ideal if the dma_buf fd itself can be used to access the backing storage + from userspace using mmap. + + Furthermore Android's ION framework already supports this (and is otherwise + rather similar to dma-buf from a userspace consumer side with using fds as + handles, too). So it's beneficial to support this in a similar fashion on + dma-buf to have a good transition path for existing Android userspace. + + No special interfaces, userspace simply calls mmap on the dma-buf fd. + +2. Supporting existing mmap interfaces in exporters + + Similar to the motivation for kernel cpu access it is again important that + the userspace code of a given importing subsystem can use the same interfaces + with a imported dma-buf buffer object as with a native buffer object. This is + especially important for drm where the userspace part of contemporary OpenGL, + X, and other drivers is huge, and reworking them to use a different way to + mmap a buffer rather invasive. + + The assumption in the current dma-buf interfaces is that redirecting the + initial mmap is all that's needed. A survey of some of the existing + subsystems shows that no driver seems to do any nefarious thing like syncing + up with outstanding asynchronous processing on the device or allocating + special resources at fault time. So hopefully this is good enough, since + adding interfaces to intercept pagefaults and allow pte shootdowns would + increase the complexity quite a bit. + + Interface: + int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, + unsigned long); + + If the importing subsystem simply provides a special-purpose mmap call to set + up a mapping in userspace, calling do_mmap with dma_buf->file will equally + achieve that for a dma-buf object. + +3. Implementation notes for exporters + + Because dma-buf buffers have invariant size over their lifetime, the dma-buf + core checks whether a vma is too large and rejects such mappings. The + exporter hence does not need to duplicate this check. + + Because existing importing subsystems might presume coherent mappings for + userspace, the exporter needs to set up a coherent mapping. If that's not + possible, it needs to fake coherency by manually shooting down ptes when + leaving the cpu domain and flushing caches at fault time. Note that all the + dma_buf files share the same anon inode, hence the exporter needs to replace + the dma_buf file stored in vma->vm_file with it's own if pte shootdown is + requred. This is because the kernel uses the underlying inode's address_space + for vma tracking (and hence pte tracking at shootdown time with + unmap_mapping_range). + + If the above shootdown dance turns out to be too expensive in certain + scenarios, we can extend dma-buf with a more explicit cache tracking scheme + for userspace mappings. But the current assumption is that using mmap is + always a slower path, so some inefficiencies should be acceptable. + + Exporters that shoot down mappings (for any reasons) shall not do any + synchronization at fault time with outstanding device operations. + Synchronization is an orthogonal issue to sharing the backing storage of a + buffer and hence should not be handled by dma-buf itself. This is explictly + mentioned here because many people seem to want something like this, but if + different exporters handle this differently, buffer sharing can fail in + interesting ways depending upong the exporter (if userspace starts depending + upon this implicit synchronization). + Miscellaneous notes ------------------- @@ -336,6 +406,20 @@ Miscellaneous notes the exporting driver to create a dmabuf fd must provide a way to let userspace control setting of O_CLOEXEC flag passed in to dma_buf_fd(). +- If an exporter needs to manually flush caches and hence needs to fake + coherency for mmap support, it needs to be able to zap all the ptes pointing + at the backing storage. Now linux mm needs a struct address_space associated + with the struct file stored in vma->vm_file to do that with the function + unmap_mapping_range. But the dma_buf framework only backs every dma_buf fd + with the anon_file struct file, i.e. all dma_bufs share the same file. + + Hence exporters need to setup their own file (and address_space) association + by setting vma->vm_file and adjusting vma->vm_pgoff in the dma_buf mmap + callback. In the specific case of a gem driver the exporter could use the + shmem file already provided by gem (and set vm_pgoff = 0). Exporters can then + zap ptes by unmapping the corresponding range of the struct address_space + associated with their own file. + References: [1] struct dma_buf_ops in include/linux/dma-buf.h [2] All interfaces mentioned above defined in include/linux/dma-buf.h diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1601e5a8b71..41996c68a5cd 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -508,6 +508,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits. + cma=nn[MG] [ARM,KNL] + Sets the size of kernel global memory area for contiguous + memory allocations. For more information, see + include/linux/dma-contiguous.h + cmo_free_hint= [PPC] Format: { yes | no } Specify whether pages are marked as being inactive when they are freed. This is used in CMO environments @@ -515,6 +520,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. a hypervisor. Default: yes + coherent_pool=nn[KMG] [ARM,KNL] + Sets the size of memory pool for coherent, atomic dma + allocations if Contiguous Memory Allocator (CMA) is used. + code_bytes [X86] How many bytes of object code to print in an oops report. Range: 0 - 8192 diff --git a/arch/Kconfig b/arch/Kconfig index 684eb5af439d..0a3ffe46e567 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -142,6 +142,9 @@ config HAVE_ARCH_TRACEHOOK config HAVE_DMA_ATTRS bool +config HAVE_DMA_CONTIGUOUS + bool + config USE_GENERIC_SMP_HELPERS bool diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 12ce924abeb2..b6ede2af9438 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -4,6 +4,8 @@ config ARM select HAVE_AOUT select HAVE_DMA_API_DEBUG select HAVE_IDE if PCI || ISA || PCMCIA + select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7) + select CMA if (CPU_V6 || CPU_V6K || CPU_V7) select HAVE_MEMBLOCK select RTC_LIB select SYS_SUPPORTS_APM_EMULATION diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h new file mode 100644 index 000000000000..3ed37b4d93da --- /dev/null +++ b/arch/arm/include/asm/dma-contiguous.h @@ -0,0 +1,15 @@ +#ifndef ASMARM_DMA_CONTIGUOUS_H +#define ASMARM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ +#ifdef CONFIG_CMA + +#include <linux/types.h> +#include <asm-generic/dma-contiguous.h> + +void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size); + +#endif +#endif + +#endif diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h index b36f3654bf54..a6efcdd6fd25 100644 --- a/arch/arm/include/asm/mach/map.h +++ b/arch/arm/include/asm/mach/map.h @@ -30,6 +30,7 @@ struct map_desc { #define MT_MEMORY_DTCM 12 #define MT_MEMORY_ITCM 13 #define MT_MEMORY_SO 14 +#define MT_MEMORY_DMA_READY 15 #ifdef CONFIG_MMU extern void iotable_init(struct map_desc *, int); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ebfac782593f..1b3096dfb964 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -81,6 +81,7 @@ __setup("fpe=", fpe_setup); extern void paging_init(struct machine_desc *desc); extern void sanity_check_meminfo(void); extern void reboot_setup(char *str); +extern void setup_dma_zone(struct machine_desc *desc); unsigned int processor_id; EXPORT_SYMBOL(processor_id); @@ -939,12 +940,8 @@ void __init setup_arch(char **cmdline_p) machine_desc = mdesc; machine_name = mdesc->name; -#ifdef CONFIG_ZONE_DMA - if (mdesc->dma_zone_size) { - extern unsigned long arm_dma_zone_size; - arm_dma_zone_size = mdesc->dma_zone_size; - } -#endif + setup_dma_zone(mdesc); + if (mdesc->restart_mode) reboot_setup(&mdesc->restart_mode); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index db23ae4aaaab..302f5bfb17f4 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -17,7 +17,9 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/dma-contiguous.h> #include <linux/highmem.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <asm/memory.h> @@ -26,6 +28,9 @@ #include <asm/tlbflush.h> #include <asm/sizes.h> #include <asm/mach/arch.h> +#include <asm/mach/map.h> +#include <asm/system_info.h> +#include <asm/dma-contiguous.h> #include "mm.h" @@ -56,6 +61,19 @@ static u64 get_coherent_dma_mask(struct device *dev) return mask; } +static void __dma_clear_buffer(struct page *page, size_t size) +{ + void *ptr; + /* + * Ensure that the allocated pages are zeroed, and that any data + * lurking in the kernel direct-mapped region is invalidated. + */ + ptr = page_address(page); + memset(ptr, 0, size); + dmac_flush_range(ptr, ptr + size); + outer_flush_range(__pa(ptr), __pa(ptr) + size); +} + /* * Allocate a DMA buffer for 'dev' of size 'size' using the * specified gfp mask. Note that 'size' must be page aligned. @@ -64,23 +82,6 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf { unsigned long order = get_order(size); struct page *page, *p, *e; - void *ptr; - u64 mask = get_coherent_dma_mask(dev); - -#ifdef CONFIG_DMA_API_DEBUG - u64 limit = (mask + 1) & ~mask; - if (limit && size >= limit) { - dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n", - size, mask); - return NULL; - } -#endif - - if (!mask) - return NULL; - - if (mask < 0xffffffffULL) - gfp |= GFP_DMA; page = alloc_pages(gfp, order); if (!page) @@ -93,14 +94,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++) __free_page(p); - /* - * Ensure that the allocated pages are zeroed, and that any data - * lurking in the kernel direct-mapped region is invalidated. - */ - ptr = page_address(page); - memset(ptr, 0, size); - dmac_flush_range(ptr, ptr + size); - outer_flush_range(__pa(ptr), __pa(ptr) + size); + __dma_clear_buffer(page, size); return page; } @@ -170,6 +164,9 @@ static int __init consistent_init(void) unsigned long base = consistent_base; unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT; + if (cpu_architecture() >= CPU_ARCH_ARMv6) + return 0; + consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL); if (!consistent_pte) { pr_err("%s: no memory\n", __func__); @@ -210,9 +207,101 @@ static int __init consistent_init(void) return ret; } - core_initcall(consistent_init); +static void *__alloc_from_contiguous(struct device *dev, size_t size, + pgprot_t prot, struct page **ret_page); + +static struct arm_vmregion_head coherent_head = { + .vm_lock = __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock), + .vm_list = LIST_HEAD_INIT(coherent_head.vm_list), +}; + +size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8; + +static int __init early_coherent_pool(char *p) +{ + coherent_pool_size = memparse(p, &p); + return 0; +} +early_param("coherent_pool", early_coherent_pool); + +/* + * Initialise the coherent pool for atomic allocations. + */ +static int __init coherent_init(void) +{ + pgprot_t prot = pgprot_dmacoherent(pgprot_kernel); + size_t size = coherent_pool_size; + struct page *page; + void *ptr; + + if (cpu_architecture() < CPU_ARCH_ARMv6) + return 0; + + ptr = __alloc_from_contiguous(NULL, size, prot, &page); + if (ptr) { + coherent_head.vm_start = (unsigned long) ptr; + coherent_head.vm_end = (unsigned long) ptr + size; + printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n", + (unsigned)size / 1024); + return 0; + } + printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n", + (unsigned)size / 1024); + return -ENOMEM; +} +/* + * CMA is activated by core_initcall, so we must be called after it. + */ +postcore_initcall(coherent_init); + +struct dma_contig_early_reserve { + phys_addr_t base; + unsigned long size; +}; + +static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata; + +static int dma_mmu_remap_num __initdata; + +void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) +{ + dma_mmu_remap[dma_mmu_remap_num].base = base; + dma_mmu_remap[dma_mmu_remap_num].size = size; + dma_mmu_remap_num++; +} + +void __init dma_contiguous_remap(void) +{ + int i; + for (i = 0; i < dma_mmu_remap_num; i++) { + phys_addr_t start = dma_mmu_remap[i].base; + phys_addr_t end = start + dma_mmu_remap[i].size; + struct map_desc map; + unsigned long addr; + + if (end > arm_lowmem_limit) + end = arm_lowmem_limit; + if (start >= end) + return; + + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY_DMA_READY; + + /* + * Clear previous low-memory mapping + */ + for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); + addr += PGDIR_SIZE) + pmd_clear(pmd_off_k(addr)); + + iotable_init(&map, 1); + } +} + static void * __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot, const void *caller) @@ -319,20 +408,173 @@ static void __dma_free_remap(void *cpu_addr, size_t size) arm_vmregion_free(&consistent_head, c); } +static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr, + void *data) +{ + struct page *page = virt_to_page(addr); + pgprot_t prot = *(pgprot_t *)data; + + set_pte_ext(pte, mk_pte(page, prot), 0); + return 0; +} + +static void __dma_remap(struct page *page, size_t size, pgprot_t prot) +{ + unsigned long start = (unsigned long) page_address(page); + unsigned end = start + size; + + apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot); + dsb(); + flush_tlb_kernel_range(start, end); +} + +static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp, + pgprot_t prot, struct page **ret_page, + const void *caller) +{ + struct page *page; + void *ptr; + page = __dma_alloc_buffer(dev, size, gfp); + if (!page) + return NULL; + + ptr = __dma_alloc_remap(page, size, gfp, prot, caller); + if (!ptr) { + __dma_free_buffer(page, size); + return NULL; + } + + *ret_page = page; + return ptr; +} + +static void *__alloc_from_pool(struct device *dev, size_t size, + struct page **ret_page, const void *caller) +{ + struct arm_vmregion *c; + size_t align; + + if (!coherent_head.vm_start) { + printk(KERN_ERR "%s: coherent pool not initialised!\n", + __func__); + dump_stack(); + return NULL; + } + + /* + * Align the region allocation - allocations from pool are rather + * small, so align them to their order in pages, minimum is a page + * size. This helps reduce fragmentation of the DMA space. + */ + align = PAGE_SIZE << get_order(size); + c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller); + if (c) { + void *ptr = (void *)c->vm_start; + struct page *page = virt_to_page(ptr); + *ret_page = page; + return ptr; + } + return NULL; +} + +static int __free_from_pool(void *cpu_addr, size_t size) +{ + unsigned long start = (unsigned long)cpu_addr; + unsigned long end = start + size; + struct arm_vmregion *c; + + if (start < coherent_head.vm_start || end > coherent_head.vm_end) + return 0; + + c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start); + + if ((c->vm_end - c->vm_start) != size) { + printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n", + __func__, c->vm_end - c->vm_start, size); + dump_stack(); + size = c->vm_end - c->vm_start; + } + + arm_vmregion_free(&coherent_head, c); + return 1; +} + +static void *__alloc_from_contiguous(struct device *dev, size_t size, + pgprot_t prot, struct page **ret_page) +{ + unsigned long order = get_order(size); + size_t count = size >> PAGE_SHIFT; + struct page *page; + + page = dma_alloc_from_contiguous(dev, count, order); + if (!page) + return NULL; + + __dma_clear_buffer(page, size); + __dma_remap(page, size, prot); + + *ret_page = page; + return page_address(page); +} + +static void __free_from_contiguous(struct device *dev, struct page *page, + size_t size) +{ + __dma_remap(page, size, pgprot_kernel); + dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); +} + +#define nommu() 0 + #else /* !CONFIG_MMU */ -#define __dma_alloc_remap(page, size, gfp, prot, c) page_address(page) -#define __dma_free_remap(addr, size) do { } while (0) +#define nommu() 1 + +#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c) NULL +#define __alloc_from_pool(dev, size, ret_page, c) NULL +#define __alloc_from_contiguous(dev, size, prot, ret) NULL +#define __free_from_pool(cpu_addr, size) 0 +#define __free_from_contiguous(dev, page, size) do { } while (0) +#define __dma_free_remap(cpu_addr, size) do { } while (0) #endif /* CONFIG_MMU */ -static void * -__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, - pgprot_t prot, const void *caller) +static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp, + struct page **ret_page) { struct page *page; + page = __dma_alloc_buffer(dev, size, gfp); + if (!page) + return NULL; + + *ret_page = page; + return page_address(page); +} + + + +static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, pgprot_t prot, const void *caller) +{ + u64 mask = get_coherent_dma_mask(dev); + struct page *page; void *addr; +#ifdef CONFIG_DMA_API_DEBUG + u64 limit = (mask + 1) & ~mask; + if (limit && size >= limit) { + dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n", + size, mask); + return NULL; + } +#endif + + if (!mask) + return NULL; + + if (mask < 0xffffffffULL) + gfp |= GFP_DMA; + /* * Following is a work-around (a.k.a. hack) to prevent pages * with __GFP_COMP being passed to split_page() which cannot @@ -345,19 +587,17 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, *handle = ~0; size = PAGE_ALIGN(size); - page = __dma_alloc_buffer(dev, size, gfp); - if (!page) - return NULL; - - if (!arch_is_coherent()) - addr = __dma_alloc_remap(page, size, gfp, prot, caller); + if (arch_is_coherent() || nommu()) + addr = __alloc_simple_buffer(dev, size, gfp, &page); + else if (cpu_architecture() < CPU_ARCH_ARMv6) + addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); + else if (gfp & GFP_ATOMIC) + addr = __alloc_from_pool(dev, size, &page, caller); else - addr = page_address(page); + addr = __alloc_from_contiguous(dev, size, prot, &page); if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); - else - __dma_free_buffer(page, size); return addr; } @@ -366,8 +606,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, * Allocate DMA-coherent memory space and return both the kernel remapped * virtual and bus address for that space. */ -void * -dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp) +void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp) { void *memory; @@ -398,25 +638,11 @@ static int dma_mmap(struct device *dev, struct vm_area_struct *vma, { int ret = -ENXIO; #ifdef CONFIG_MMU - unsigned long user_size, kern_size; - struct arm_vmregion *c; - - user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; - - c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr); - if (c) { - unsigned long off = vma->vm_pgoff; - - kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT; - - if (off < kern_size && - user_size <= (kern_size - off)) { - ret = remap_pfn_range(vma, vma->vm_start, - page_to_pfn(c->vm_pages) + off, - user_size << PAGE_SHIFT, - vma->vm_page_prot); - } - } + unsigned long pfn = dma_to_pfn(dev, dma_addr); + ret = remap_pfn_range(vma, vma->vm_start, + pfn + vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot); #endif /* CONFIG_MMU */ return ret; @@ -438,23 +664,33 @@ int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma, } EXPORT_SYMBOL(dma_mmap_writecombine); + /* - * free a page as defined by the above mapping. - * Must not be called with IRQs disabled. + * Free a buffer as defined by the above mapping. */ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle) { - WARN_ON(irqs_disabled()); + struct page *page = pfn_to_page(dma_to_pfn(dev, handle)); if (dma_release_from_coherent(dev, get_order(size), cpu_addr)) return; size = PAGE_ALIGN(size); - if (!arch_is_coherent()) + if (arch_is_coherent() || nommu()) { + __dma_free_buffer(page, size); + } else if (cpu_architecture() < CPU_ARCH_ARMv6) { __dma_free_remap(cpu_addr, size); - - __dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size); + __dma_free_buffer(page, size); + } else { + if (__free_from_pool(cpu_addr, size)) + return; + /* + * Non-atomic allocations cannot be freed with IRQs disabled + */ + WARN_ON(irqs_disabled()); + __free_from_contiguous(dev, page, size); + } } EXPORT_SYMBOL(dma_free_coherent); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 8f5813bbffb5..c21d06c7dd7e 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -20,6 +20,7 @@ #include <linux/highmem.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/dma-contiguous.h> #include <asm/mach-types.h> #include <asm/memblock.h> @@ -226,6 +227,17 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, } #endif +void __init setup_dma_zone(struct machine_desc *mdesc) +{ +#ifdef CONFIG_ZONE_DMA + if (mdesc->dma_zone_size) { + arm_dma_zone_size = mdesc->dma_zone_size; + arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; + } else + arm_dma_limit = 0xffffffff; +#endif +} + static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, unsigned long max_high) { @@ -273,12 +285,9 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, * Adjust the sizes according to any special requirements for * this machine type. */ - if (arm_dma_zone_size) { + if (arm_dma_zone_size) arm_adjust_dma_zone(zone_size, zhole_size, arm_dma_zone_size >> PAGE_SHIFT); - arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; - } else - arm_dma_limit = 0xffffffff; #endif free_area_init_node(0, zone_size, min, zhole_size); @@ -364,6 +373,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) if (mdesc->reserve) mdesc->reserve(); + /* + * reserve memory for DMA contigouos allocations, + * must come from DMA area inside low memory + */ + dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit)); + arm_memblock_steal_permitted = false; memblock_allow_resize(); memblock_dump_all(); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 27f4a619b35d..93dc0c17cdcb 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -67,5 +67,8 @@ extern u32 arm_dma_limit; #define arm_dma_limit ((u32)~0) #endif +extern phys_addr_t arm_lowmem_limit; + void __init bootmem_init(void); void arm_mm_memblock_reserve(void); +void dma_contiguous_remap(void); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 137858b29741..707cb9927f18 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -288,6 +288,11 @@ static struct mem_type mem_types[] = { PMD_SECT_UNCACHED | PMD_SECT_XN, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_DMA_READY] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, + .prot_l1 = PMD_TYPE_TABLE, + .domain = DOMAIN_KERNEL, + }, }; const struct mem_type *get_mem_type(unsigned int type) @@ -429,6 +434,7 @@ static void __init build_mem_type_table(void) if (arch_is_coherent() && cpu_is_xsc3()) { mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; } @@ -460,6 +466,7 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; } @@ -512,6 +519,7 @@ static void __init build_mem_type_table(void) mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; mem_types[MT_MEMORY].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; @@ -617,7 +625,8 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr, * L1 entries, whereas PGDs refer to a group of L1 entries making * up one logical pointer to an L2 table. */ - if (((addr | end | phys) & ~SECTION_MASK) == 0 && !force_pages) { + if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0 && + !force_pages) { pmd_t *p = pmd; #ifndef CONFIG_ARM_LPAE @@ -836,7 +845,7 @@ static int __init early_vmalloc(char *arg) } early_param("vmalloc", early_vmalloc); -static phys_addr_t lowmem_limit __initdata = 0; +phys_addr_t arm_lowmem_limit __initdata = 0; void __init sanity_check_meminfo(void) { @@ -919,8 +928,8 @@ void __init sanity_check_meminfo(void) bank->size = newsize; } #endif - if (!bank->highmem && bank->start + bank->size > lowmem_limit) - lowmem_limit = bank->start + bank->size; + if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit) + arm_lowmem_limit = bank->start + bank->size; j++; } @@ -945,8 +954,8 @@ void __init sanity_check_meminfo(void) } #endif meminfo.nr_banks = j; - high_memory = __va(lowmem_limit - 1) + 1; - memblock_set_current_limit(lowmem_limit); + high_memory = __va(arm_lowmem_limit - 1) + 1; + memblock_set_current_limit(arm_lowmem_limit); } static inline void prepare_page_table(void) @@ -971,8 +980,8 @@ static inline void prepare_page_table(void) * Find the end of the first block of lowmem. */ end = memblock.memory.regions[0].base + memblock.memory.regions[0].size; - if (end >= lowmem_limit) - end = lowmem_limit; + if (end >= arm_lowmem_limit) + end = arm_lowmem_limit; /* * Clear out all the kernel space mappings, except for the first @@ -1118,8 +1127,8 @@ static void __init map_lowmem(void) start = reg->base; end = start + reg->size; - if (end > lowmem_limit) - end = lowmem_limit; + if (end > arm_lowmem_limit) + end = arm_lowmem_limit; if (start >= end) break; @@ -1152,11 +1161,12 @@ void __init paging_init(struct machine_desc *mdesc) { void *zero_page; - memblock_set_current_limit(lowmem_limit); + memblock_set_current_limit(arm_lowmem_limit); build_mem_type_table(); prepare_page_table(); map_lowmem(); + dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c9866b0b77d8..7cbdfdac3c7c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -31,6 +31,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS + select HAVE_DMA_CONTIGUOUS if !SWIOTLB select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h new file mode 100644 index 000000000000..c09241659971 --- /dev/null +++ b/arch/x86/include/asm/dma-contiguous.h @@ -0,0 +1,13 @@ +#ifndef ASMX86_DMA_CONTIGUOUS_H +#define ASMX86_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <asm-generic/dma-contiguous.h> + +static inline void +dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } + +#endif +#endif diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 4b4331d71935..7b9227b44b9b 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -13,6 +13,7 @@ #include <asm/io.h> #include <asm/swiotlb.h> #include <asm-generic/dma-coherent.h> +#include <linux/dma-contiguous.h> #ifdef CONFIG_ISA # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24) @@ -62,6 +63,10 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, struct dma_attrs *attrs); +extern void dma_generic_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs); + static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { if (!dev->dma_mask) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 3003250ac51d..62c9457ccd2f 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,14 +100,18 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, struct dma_attrs *attrs) { unsigned long dma_mask; - struct page *page; + struct page *page = NULL; + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; dma_addr_t addr; dma_mask = dma_alloc_coherent_mask(dev, flag); flag |= __GFP_ZERO; again: - page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); + if (!(flag & GFP_ATOMIC)) + page = dma_alloc_from_contiguous(dev, count, get_order(size)); + if (!page) + page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) return NULL; @@ -127,6 +131,16 @@ again: return page_address(page); } +void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_addr, struct dma_attrs *attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct page *page = virt_to_page(vaddr); + + if (!dma_release_from_contiguous(dev, page, count)) + free_pages((unsigned long)vaddr, get_order(size)); +} + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index f96050685b46..871be4a84c7d 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -74,12 +74,6 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return nents; } -static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, struct dma_attrs *attrs) -{ - free_pages((unsigned long)vaddr, get_order(size)); -} - static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) @@ -97,7 +91,7 @@ static void nommu_sync_sg_for_device(struct device *dev, struct dma_map_ops nommu_dma_ops = { .alloc = dma_generic_alloc_coherent, - .free = nommu_free_coherent, + .free = dma_generic_free_coherent, .map_sg = nommu_map_sg, .map_page = nommu_map_page, .sync_single_for_device = nommu_sync_single_for_device, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1a2901562059..d6c956e674cc 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include <asm/pci-direct.h> #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> +#include <linux/dma-contiguous.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -934,6 +935,7 @@ void __init setup_arch(char **cmdline_p) } #endif memblock.current_limit = get_max_mapped(); + dma_contiguous_reserve(0); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 1131dd73d5d0..3df339c031a8 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -218,4 +218,94 @@ config SW_SYNC_USER Provides a user space API to the sw sync object. *WARNING* improper use of this can result in deadlocking kernel drivers from userspace. + +config CMA + bool "Contiguous Memory Allocator (EXPERIMENTAL)" + depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL + select MIGRATION + help + This enables the Contiguous Memory Allocator which allows drivers + to allocate big physically-contiguous blocks of memory for use with + hardware components that do not support I/O map nor scatter-gather. + + For more information see <include/linux/dma-contiguous.h>. + If unsure, say "n". + +if CMA + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +comment "Default contiguous memory area size:" + +config CMA_SIZE_MBYTES + int "Size in Mega Bytes" + depends on !CMA_SIZE_SEL_PERCENTAGE + default 16 + help + Defines the size (in MiB) of the default memory area for Contiguous + Memory Allocator. + +config CMA_SIZE_PERCENTAGE + int "Percentage of total memory" + depends on !CMA_SIZE_SEL_MBYTES + default 10 + help + Defines the size of the default memory area for Contiguous Memory + Allocator as a percentage of the total memory in the system. + +choice + prompt "Selected region size" + default CMA_SIZE_SEL_ABSOLUTE + +config CMA_SIZE_SEL_MBYTES + bool "Use mega bytes value only" + +config CMA_SIZE_SEL_PERCENTAGE + bool "Use percentage value only" + +config CMA_SIZE_SEL_MIN + bool "Use lower value (minimum)" + +config CMA_SIZE_SEL_MAX + bool "Use higher value (maximum)" + +endchoice + +config CMA_ALIGNMENT + int "Maximum PAGE_SIZE order of alignment for contiguous buffers" + range 4 9 + default 8 + help + DMA mapping framework by default aligns all buffers to the smallest + PAGE_SIZE order which is greater than or equal to the requested buffer + size. This works well for buffers up to a few hundreds kilobytes, but + for larger buffers it just a memory waste. With this parameter you can + specify the maximum PAGE_SIZE order for contiguous buffers. Larger + buffers will be aligned only to this specified order. The order is + expressed as a power of two multiplied by the PAGE_SIZE. + + For example, if your system defaults to 4KiB pages, the order value + of 8 means that the buffers will be aligned up to 1MiB only. + + If unsure, leave the default value "8". + +config CMA_AREAS + int "Maximum count of the CMA device-private areas" + default 7 + help + CMA allows to create CMA areas for particular devices. This parameter + sets the maximum number of such device private CMA areas in the + system. + + If unsure, leave the default value "7". + +endif + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 0e4d3dadd6b1..1128a612e24d 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,6 +6,7 @@ obj-y := core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o +obj-$(CONFIG_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 07cbbc6fddb4..7e72631035a2 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -44,8 +44,26 @@ static int dma_buf_release(struct inode *inode, struct file *file) return 0; } +static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) +{ + struct dma_buf *dmabuf; + + if (!is_dma_buf_file(file)) + return -EINVAL; + + dmabuf = file->private_data; + + /* check for overflowing the buffer's size */ + if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) > + dmabuf->size >> PAGE_SHIFT) + return -EINVAL; + + return dmabuf->ops->mmap(dmabuf, vma); +} + static const struct file_operations dma_buf_fops = { .release = dma_buf_release, + .mmap = dma_buf_mmap_internal, }; /* @@ -82,7 +100,8 @@ struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops, || !ops->unmap_dma_buf || !ops->release || !ops->kmap_atomic - || !ops->kmap)) { + || !ops->kmap + || !ops->mmap)) { return ERR_PTR(-EINVAL); } @@ -293,7 +312,7 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific * preparations. Coherency is only guaranteed in the specified range for the * specified access direction. - * @dma_buf: [in] buffer to prepare cpu access for. + * @dmabuf: [in] buffer to prepare cpu access for. * @start: [in] start of range for cpu access. * @len: [in] length of range for cpu access. * @direction: [in] length of range for cpu access. @@ -320,7 +339,7 @@ EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access); * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific * actions. Coherency is only guaranteed in the specified range for the * specified access direction. - * @dma_buf: [in] buffer to complete cpu access for. + * @dmabuf: [in] buffer to complete cpu access for. * @start: [in] start of range for cpu access. * @len: [in] length of range for cpu access. * @direction: [in] length of range for cpu access. @@ -340,7 +359,7 @@ EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access); /** * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address * space. The same restrictions as for kmap_atomic and friends apply. - * @dma_buf: [in] buffer to map page from. + * @dmabuf: [in] buffer to map page from. * @page_num: [in] page in PAGE_SIZE units to map. * * This call must always succeed, any necessary preparations that might fail @@ -356,7 +375,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic); /** * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic. - * @dma_buf: [in] buffer to unmap page from. + * @dmabuf: [in] buffer to unmap page from. * @page_num: [in] page in PAGE_SIZE units to unmap. * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap_atomic. * @@ -375,7 +394,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic); /** * dma_buf_kmap - Map a page of the buffer object into kernel address space. The * same restrictions as for kmap and friends apply. - * @dma_buf: [in] buffer to map page from. + * @dmabuf: [in] buffer to map page from. * @page_num: [in] page in PAGE_SIZE units to map. * * This call must always succeed, any necessary preparations that might fail @@ -391,7 +410,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kmap); /** * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap. - * @dma_buf: [in] buffer to unmap page from. + * @dmabuf: [in] buffer to unmap page from. * @page_num: [in] page in PAGE_SIZE units to unmap. * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap. * @@ -406,3 +425,77 @@ void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num, dmabuf->ops->kunmap(dmabuf, page_num, vaddr); } EXPORT_SYMBOL_GPL(dma_buf_kunmap); + +/** + * dma_buf_mmap - Setup up a userspace mmap with the given vma + * @dmabuf: [in] buffer that should back the vma + * @vma: [in] vma for the mmap + * @pgoff: [in] offset in pages where this mmap should start within the + * dma-buf buffer. + * + * This function adjusts the passed in vma so that it points at the file of the + * dma_buf operation. It alsog adjusts the starting pgoff and does bounds + * checking on the size of the vma. Then it calls the exporters mmap function to + * set up the mapping. + * + * Can return negative error values, returns 0 on success. + */ +int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, + unsigned long pgoff) +{ + if (WARN_ON(!dmabuf || !vma)) + return -EINVAL; + + /* check for offset overflow */ + if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff) + return -EOVERFLOW; + + /* check for overflowing the buffer's size */ + if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) > + dmabuf->size >> PAGE_SHIFT) + return -EINVAL; + + /* readjust the vma */ + if (vma->vm_file) + fput(vma->vm_file); + + vma->vm_file = dmabuf->file; + get_file(vma->vm_file); + + vma->vm_pgoff = pgoff; + + return dmabuf->ops->mmap(dmabuf, vma); +} +EXPORT_SYMBOL_GPL(dma_buf_mmap); + +/** + * dma_buf_vmap - Create virtual mapping for the buffer object into kernel address space. The same restrictions as for vmap and friends apply. + * @dmabuf: [in] buffer to vmap + * + * This call may fail due to lack of virtual mapping address space. + * These calls are optional in drivers. The intended use for them + * is for mapping objects linear in kernel space for high use objects. + * Please attempt to use kmap/kunmap before thinking about these interfaces. + */ +void *dma_buf_vmap(struct dma_buf *dmabuf) +{ + WARN_ON(!dmabuf); + + if (dmabuf->ops->vmap) + return dmabuf->ops->vmap(dmabuf); + return NULL; +} +EXPORT_SYMBOL_GPL(dma_buf_vmap); + +/** + * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap. + * @dmabuf: [in] buffer to vmap + */ +void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ + WARN_ON(!dmabuf); + + if (dmabuf->ops->vunmap) + dmabuf->ops->vunmap(dmabuf, vaddr); +} +EXPORT_SYMBOL_GPL(dma_buf_vunmap); diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c new file mode 100644 index 000000000000..78efb0306a44 --- /dev/null +++ b/drivers/base/dma-contiguous.c @@ -0,0 +1,401 @@ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski <m.szyprowski@samsung.com> + * Michal Nazarewicz <mina86@mina86.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include <asm/page.h> +#include <asm/dma-contiguous.h> + +#include <linux/memblock.h> +#include <linux/err.h> +#include <linux/mm.h> +#include <linux/mutex.h> +#include <linux/page-isolation.h> +#include <linux/slab.h> +#include <linux/swap.h> +#include <linux/mm_types.h> +#include <linux/dma-contiguous.h> + +#ifndef SZ_1M +#define SZ_1M (1 << 20) +#endif + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; +}; + +struct cma *dma_contiguous_default_area; + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is usefull mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M; +static long size_cmdline = -1; + +static int __init early_cma(char *p) +{ + pr_debug("%s(%s)\n", __func__, p); + size_cmdline = memparse(p, &p); + return 0; +} +early_param("cma", early_cma); + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE + +static unsigned long __init __maybe_unused cma_early_percent_memory(void) +{ + struct memblock_region *reg; + unsigned long total_pages = 0; + + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + total_pages += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + + return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; +} + +#else + +static inline __maybe_unused unsigned long cma_early_percent_memory(void) +{ + return 0; +} + +#endif + +/** + * dma_contiguous_reserve() - reserve area for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + unsigned long selected_size = 0; + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + if (size_cmdline != -1) { + selected_size = size_cmdline; + } else { +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = cma_early_percent_memory(); +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, cma_early_percent_memory()); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, cma_early_percent_memory()); +#endif + } + + if (selected_size) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + selected_size / SZ_1M); + + dma_declare_contiguous(NULL, selected_size, 0, limit); + } +}; + +static DEFINE_MUTEX(cma_mutex); + +static __init int cma_activate_area(unsigned long base_pfn, unsigned long count) +{ + unsigned long pfn = base_pfn; + unsigned i = count >> pageblock_order; + struct zone *zone; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + + do { + unsigned j; + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + if (page_zone(pfn_to_page(pfn)) != zone) + return -EINVAL; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + return 0; +} + +static __init struct cma *cma_create_area(unsigned long base_pfn, + unsigned long count) +{ + int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct cma *cma; + int ret = -ENOMEM; + + pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count); + + cma = kmalloc(sizeof *cma, GFP_KERNEL); + if (!cma) + return ERR_PTR(-ENOMEM); + + cma->base_pfn = base_pfn; + cma->count = count; + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + + if (!cma->bitmap) + goto no_mem; + + ret = cma_activate_area(base_pfn, count); + if (ret) + goto error; + + pr_debug("%s: returned %p\n", __func__, (void *)cma); + return cma; + +error: + kfree(cma->bitmap); +no_mem: + kfree(cma); + return ERR_PTR(ret); +} + +static struct cma_reserved { + phys_addr_t start; + unsigned long size; + struct device *dev; +} cma_reserved[MAX_CMA_AREAS] __initdata; +static unsigned cma_reserved_count __initdata; + +static int __init cma_init_reserved_areas(void) +{ + struct cma_reserved *r = cma_reserved; + unsigned i = cma_reserved_count; + + pr_debug("%s()\n", __func__); + + for (; i; --i, ++r) { + struct cma *cma; + cma = cma_create_area(PFN_DOWN(r->start), + r->size >> PAGE_SHIFT); + if (!IS_ERR(cma)) + dev_set_cma_area(r->dev, cma); + } + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * dma_declare_contiguous() - reserve area for contiguous memory handling + * for particular device + * @dev: Pointer to device structure. + * @size: Size of the reserved memory. + * @base: Start address of the reserved memory (optional, 0 for any). + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory for specified device. It should be + * called by board specific code when early allocator (memblock or bootmem) + * is still activate. + */ +int __init dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + struct cma_reserved *r = &cma_reserved[cma_reserved_count]; + unsigned long alignment; + + pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__, + (unsigned long)size, (unsigned long)base, + (unsigned long)limit); + + /* Sanity checks */ + if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + /* Sanitise input arguments */ + alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order); + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + /* Reserve memory */ + if (base) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + base = -EBUSY; + goto err; + } + } else { + /* + * Use __memblock_alloc_base() since + * memblock_alloc_base() panic()s. + */ + phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + if (!addr) { + base = -ENOMEM; + goto err; + } else if (addr + size > ~(unsigned long)0) { + memblock_free(addr, size); + base = -EINVAL; + goto err; + } else { + base = addr; + } + } + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + r->start = base; + r->size = size; + r->dev = dev; + cma_reserved_count++; + pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M, + (unsigned long)base); + + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(base, size); + return 0; +err: + pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M); + return base; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * + * This function allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific get_dev_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int align) +{ + unsigned long mask, pfn, pageno, start = 0; + struct cma *cma = dev_get_cma_area(dev); + int ret; + + if (!cma || !cma->count) + return NULL; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = (1 << align) - 1; + + mutex_lock(&cma_mutex); + + for (;;) { + pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count, + start, count, mask); + if (pageno >= cma->count) { + ret = -ENOMEM; + goto error; + } + + pfn = cma->base_pfn + pageno; + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + if (ret == 0) { + bitmap_set(cma->bitmap, pageno, count); + break; + } else if (ret != -EBUSY) { + goto error; + } + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = pageno + mask + 1; + } + + mutex_unlock(&cma_mutex); + + pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn)); + return pfn_to_page(pfn); +error: + mutex_unlock(&cma_mutex); + return NULL; +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by dma_alloc_from_contiguous(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + struct cma *cma = dev_get_cma_area(dev); + unsigned long pfn; + + if (!cma || !pages) + return false; + + pr_debug("%s(page %p)\n", __func__, (void *)pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return false; + + VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); + + mutex_lock(&cma_mutex); + bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count); + free_contig_range(pfn, count); + mutex_unlock(&cma_mutex); + + return true; +} diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index ce7fc77678b4..72d1293eac8f 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -34,7 +34,8 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \ dvo_ch7017.o \ dvo_ivch.o \ dvo_tfp410.o \ - dvo_sil164.o + dvo_sil164.o \ + i915_gem_dmabuf.o i915-$(CONFIG_COMPAT) += i915_ioc32.o diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ae8a64f9f845..30b013251127 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -901,7 +901,7 @@ static struct drm_driver driver = { */ .driver_features = DRIVER_USE_AGP | DRIVER_REQUIRE_AGP | /* DRIVER_USE_MTRR |*/ - DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM, + DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | DRIVER_PRIME, .load = i915_driver_load, .unload = i915_driver_unload, .open = i915_driver_open, @@ -924,6 +924,12 @@ static struct drm_driver driver = { .gem_init_object = i915_gem_init_object, .gem_free_object = i915_gem_free_object, .gem_vm_ops = &i915_gem_vm_ops, + + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_export = i915_gem_prime_export, + .gem_prime_import = i915_gem_prime_import, + .dumb_create = i915_gem_dumb_create, .dumb_map_offset = i915_gem_mmap_gtt, .dumb_destroy = i915_gem_dumb_destroy, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 5fabc6c31fec..0d25b3bfd83d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -890,6 +890,11 @@ struct drm_i915_gem_object { struct scatterlist *sg_list; int num_sg; + /* prime dma-buf support */ + struct sg_table *sg_table; + void *dma_buf_vmapping; + int vmapping_count; + /** * Used for performing relocations during execbuffer insertion. */ @@ -1205,6 +1210,8 @@ int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj); void i915_gem_release_mmap(struct drm_i915_gem_object *obj); void i915_gem_lastclose(struct drm_device *dev); +int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj, + gfp_t gfpmask); int __must_check i915_mutex_lock_interruptible(struct drm_device *dev); int __must_check i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj); void i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, @@ -1301,6 +1308,13 @@ i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev, int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level); +struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf); + +struct dma_buf *i915_gem_prime_export(struct drm_device *dev, + struct drm_gem_object *gem_obj, int flags); + + /* i915_gem_gtt.c */ int __must_check i915_gem_init_aliasing_ppgtt(struct drm_device *dev); void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 0d1e4b7b4b99..06ca09b8eee2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/swap.h> #include <linux/pci.h> +#include <linux/dma-buf.h> static __must_check int i915_gem_object_flush_gpu_write_domain(struct drm_i915_gem_object *obj); static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj); @@ -1374,8 +1375,7 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data, return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset); } - -static int +int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj, gfp_t gfpmask) { @@ -1384,6 +1384,8 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj, struct inode *inode; struct page *page; + if (obj->pages || obj->sg_table) + return 0; /* Get the list of pages out of our struct file. They'll be pinned * at this point until we release them. */ @@ -1425,6 +1427,8 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj) int page_count = obj->base.size / PAGE_SIZE; int i; + if (!obj->pages) + return; BUG_ON(obj->madv == __I915_MADV_PURGED); if (i915_gem_object_needs_bit17_swizzle(obj)) @@ -3680,6 +3684,9 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) if (obj->phys_obj) i915_gem_detach_phys_object(dev, obj); + if (gem_obj->import_attach) + drm_prime_gem_destroy(gem_obj, obj->sg_table); + i915_gem_free_object_tail(obj); } diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c new file mode 100644 index 000000000000..86ec4943980e --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -0,0 +1,225 @@ +/* + * Copyright 2012 Red Hat Inc + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Authors: + * Dave Airlie <airlied@redhat.com> + */ +#include "drmP.h" +#include "i915_drv.h" +#include <linux/dma-buf.h> + +struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction dir) +{ + struct drm_i915_gem_object *obj = attachment->dmabuf->priv; + struct drm_device *dev = obj->base.dev; + int npages = obj->base.size / PAGE_SIZE; + struct sg_table *sg = NULL; + int ret; + int nents; + + ret = i915_mutex_lock_interruptible(dev); + if (ret) + return NULL; + + if (!obj->pages) { + ret = i915_gem_object_get_pages_gtt(obj, __GFP_NORETRY | __GFP_NOWARN); + if (ret) + goto out; + } + + /* link the pages into an SG then map the sg */ + sg = drm_prime_pages_to_sg(obj->pages, npages); + nents = dma_map_sg(attachment->dev, sg->sgl, sg->nents, dir); +out: + mutex_unlock(&dev->struct_mutex); + return sg; +} + +void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *sg, enum dma_data_direction dir) +{ + dma_unmap_sg(attachment->dev, sg->sgl, sg->nents, dir); + sg_free_table(sg); + kfree(sg); +} + +void i915_gem_dmabuf_release(struct dma_buf *dma_buf) +{ + struct drm_i915_gem_object *obj = dma_buf->priv; + + if (obj->base.export_dma_buf == dma_buf) { + /* drop the reference on the export fd holds */ + obj->base.export_dma_buf = NULL; + drm_gem_object_unreference_unlocked(&obj->base); + } +} + +static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf) +{ + struct drm_i915_gem_object *obj = dma_buf->priv; + struct drm_device *dev = obj->base.dev; + int ret; + + ret = i915_mutex_lock_interruptible(dev); + if (ret) + return NULL; + + if (obj->dma_buf_vmapping) { + obj->vmapping_count++; + goto out_unlock; + } + + if (!obj->pages) { + ret = i915_gem_object_get_pages_gtt(obj, __GFP_NORETRY | __GFP_NOWARN); + if (ret) + return NULL; + } + + obj->dma_buf_vmapping = vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL); + if (!obj->dma_buf_vmapping) { + DRM_ERROR("failed to vmap object\n"); + goto out_unlock; + } + + obj->vmapping_count = 1; +out_unlock: + mutex_unlock(&dev->struct_mutex); + return obj->dma_buf_vmapping; +} + +static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) +{ + struct drm_i915_gem_object *obj = dma_buf->priv; + struct drm_device *dev = obj->base.dev; + int ret; + + ret = i915_mutex_lock_interruptible(dev); + if (ret) + return; + + --obj->dma_buf_vmapping; + if (obj->dma_buf_vmapping == 0) { + vunmap(obj->dma_buf_vmapping); + obj->dma_buf_vmapping = NULL; + } + mutex_unlock(&dev->struct_mutex); +} + +static void *i915_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num) +{ + return NULL; +} + +static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr) +{ + +} +static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) +{ + return NULL; +} + +static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr) +{ + +} + +struct dma_buf_ops i915_dmabuf_ops = { + .map_dma_buf = i915_gem_map_dma_buf, + .unmap_dma_buf = i915_gem_unmap_dma_buf, + .release = i915_gem_dmabuf_release, + .kmap = i915_gem_dmabuf_kmap, + .kmap_atomic = i915_gem_dmabuf_kmap_atomic, + .kunmap = i915_gem_dmabuf_kunmap, + .kunmap_atomic = i915_gem_dmabuf_kunmap_atomic, + .vmap = i915_gem_dmabuf_vmap, + .vunmap = i915_gem_dmabuf_vunmap, +}; + +struct dma_buf *i915_gem_prime_export(struct drm_device *dev, + struct drm_gem_object *gem_obj, int flags) +{ + struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); + + return dma_buf_export(obj, &i915_dmabuf_ops, + obj->base.size, 0600); +} + +struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct dma_buf_attachment *attach; + struct sg_table *sg; + struct drm_i915_gem_object *obj; + int npages; + int size; + int ret; + + /* is this one of own objects? */ + if (dma_buf->ops == &i915_dmabuf_ops) { + obj = dma_buf->priv; + /* is it from our device? */ + if (obj->base.dev == dev) { + drm_gem_object_reference(&obj->base); + return &obj->base; + } + } + + /* need to attach */ + attach = dma_buf_attach(dma_buf, dev->dev); + if (IS_ERR(attach)) + return ERR_PTR(-EINVAL); + + sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL); + if (IS_ERR(sg)) { + ret = PTR_ERR(sg); + goto fail_detach; + } + + size = dma_buf->size; + npages = size / PAGE_SIZE; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (obj == NULL) { + ret = -ENOMEM; + goto fail_unmap; + } + + ret = drm_gem_private_object_init(dev, &obj->base, size); + if (ret) { + ret = -ENOMEM; + kfree(obj); + goto fail_unmap; + } + + obj->sg_table = sg; + obj->base.import_attach = attach; + + return &obj->base; + +fail_unmap: + dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL); +fail_detach: + dma_buf_detach(dma_buf, attach); + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index a135c61f4119..f776cc441d43 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -359,7 +359,12 @@ int i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj) unsigned int agp_type = cache_level_to_agp_type(dev, obj->cache_level); int ret; - if (dev_priv->mm.gtt->needs_dmar) { + if (obj->sg_table) { + intel_gtt_insert_sg_entries(obj->sg_table->sgl, + obj->sg_table->nents, + obj->gtt_space->start >> PAGE_SHIFT, + agp_type); + } else if (dev_priv->mm.gtt->needs_dmar) { ret = intel_gtt_map_memory(obj->pages, obj->base.size >> PAGE_SHIFT, &obj->sg_list, @@ -387,7 +392,12 @@ void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj, struct drm_i915_private *dev_priv = dev->dev_private; unsigned int agp_type = cache_level_to_agp_type(dev, cache_level); - if (dev_priv->mm.gtt->needs_dmar) { + if (obj->sg_table) { + intel_gtt_insert_sg_entries(obj->sg_table->sgl, + obj->sg_table->nents, + obj->gtt_space->start >> PAGE_SHIFT, + agp_type); + } else if (dev_priv->mm.gtt->needs_dmar) { BUG_ON(!obj->sg_list); intel_gtt_insert_sg_entries(obj->sg_list, @@ -412,7 +422,9 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj) intel_gtt_clear_range(obj->gtt_space->start >> PAGE_SHIFT, obj->base.size >> PAGE_SHIFT); - if (obj->sg_list) { + if (obj->sg_table) { + intel_gtt_unmap_memory(obj->sg_table->sgl, obj->sg_table->nents); + } else if (obj->sg_list) { intel_gtt_unmap_memory(obj->sg_list, obj->num_sg); obj->sg_list = NULL; } diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile index 1a2ad7eb1734..01f13351a473 100644 --- a/drivers/gpu/drm/nouveau/Makefile +++ b/drivers/gpu/drm/nouveau/Makefile @@ -37,7 +37,7 @@ nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \ nv50_calc.o \ nv04_pm.o nv40_pm.o nv50_pm.o nva3_pm.o nvc0_pm.o \ nv50_vram.o nvc0_vram.o \ - nv50_vm.o nvc0_vm.o + nv50_vm.o nvc0_vm.o nouveau_prime.o nouveau-$(CONFIG_DRM_NOUVEAU_DEBUG) += nouveau_debugfs.o nouveau-$(CONFIG_COMPAT) += nouveau_ioc32.o diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 7d15a774f9c9..4daf1dde7703 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -89,12 +89,17 @@ nouveau_bo_fixup_align(struct nouveau_bo *nvbo, u32 flags, int nouveau_bo_new(struct drm_device *dev, int size, int align, uint32_t flags, uint32_t tile_mode, uint32_t tile_flags, + struct sg_table *sg, struct nouveau_bo **pnvbo) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_bo *nvbo; size_t acc_size; int ret; + int type = ttm_bo_type_device; + + if (sg) + type = ttm_bo_type_sg; nvbo = kzalloc(sizeof(struct nouveau_bo), GFP_KERNEL); if (!nvbo) @@ -120,8 +125,8 @@ nouveau_bo_new(struct drm_device *dev, int size, int align, sizeof(struct nouveau_bo)); ret = ttm_bo_init(&dev_priv->ttm.bdev, &nvbo->bo, size, - ttm_bo_type_device, &nvbo->placement, - align >> PAGE_SHIFT, 0, false, NULL, acc_size, + type, &nvbo->placement, + align >> PAGE_SHIFT, 0, false, NULL, acc_size, sg, nouveau_bo_del_ttm); if (ret) { /* ttm will call nouveau_bo_del_ttm if it fails.. */ @@ -817,9 +822,14 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem) } else if (new_mem && new_mem->mem_type == TTM_PL_TT && nvbo->page_shift == vma->vm->spg_shift) { - nouveau_vm_map_sg(vma, 0, new_mem-> - num_pages << PAGE_SHIFT, - new_mem->mm_node); + if (((struct nouveau_mem *)new_mem->mm_node)->sg) + nouveau_vm_map_sg_table(vma, 0, new_mem-> + num_pages << PAGE_SHIFT, + new_mem->mm_node); + else + nouveau_vm_map_sg(vma, 0, new_mem-> + num_pages << PAGE_SHIFT, + new_mem->mm_node); } else { nouveau_vm_unmap(vma); } @@ -1058,10 +1068,16 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) struct drm_device *dev; unsigned i; int r; + bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); if (ttm->state != tt_unpopulated) return 0; + if (slave && ttm->sg) { + ttm->state = tt_unbound; + return 0; + } + dev_priv = nouveau_bdev(ttm->bdev); dev = dev_priv->dev; @@ -1106,6 +1122,10 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm) struct drm_nouveau_private *dev_priv; struct drm_device *dev; unsigned i; + bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + + if (slave) + return; dev_priv = nouveau_bdev(ttm->bdev); dev = dev_priv->dev; @@ -1181,9 +1201,12 @@ nouveau_bo_vma_add(struct nouveau_bo *nvbo, struct nouveau_vm *vm, if (nvbo->bo.mem.mem_type == TTM_PL_VRAM) nouveau_vm_map(vma, nvbo->bo.mem.mm_node); - else - if (nvbo->bo.mem.mem_type == TTM_PL_TT) - nouveau_vm_map_sg(vma, 0, size, node); + else if (nvbo->bo.mem.mem_type == TTM_PL_TT) { + if (node->sg) + nouveau_vm_map_sg_table(vma, 0, size, node); + else + nouveau_vm_map_sg(vma, 0, size, node); + } list_add_tail(&vma->head, &nvbo->vma_list); vma->refcount = 1; diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c index 846afb0bfef4..730bbb249b01 100644 --- a/drivers/gpu/drm/nouveau/nouveau_channel.c +++ b/drivers/gpu/drm/nouveau/nouveau_channel.c @@ -38,7 +38,7 @@ nouveau_channel_pushbuf_init(struct nouveau_channel *chan) int ret; /* allocate buffer object */ - ret = nouveau_bo_new(dev, 65536, 0, mem, 0, 0, &chan->pushbuf_bo); + ret = nouveau_bo_new(dev, 65536, 0, mem, 0, 0, NULL, &chan->pushbuf_bo); if (ret) goto out; diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.c b/drivers/gpu/drm/nouveau/nouveau_drv.c index 4f2030bd5676..b394ecf787f6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.c +++ b/drivers/gpu/drm/nouveau/nouveau_drv.c @@ -408,7 +408,7 @@ static struct drm_driver driver = { .driver_features = DRIVER_USE_AGP | DRIVER_PCI_DMA | DRIVER_SG | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | - DRIVER_MODESET, + DRIVER_MODESET | DRIVER_PRIME, .load = nouveau_load, .firstopen = nouveau_firstopen, .lastclose = nouveau_lastclose, @@ -430,6 +430,12 @@ static struct drm_driver driver = { .reclaim_buffers = drm_core_reclaim_buffers, .ioctls = nouveau_ioctls, .fops = &nouveau_driver_fops, + + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_export = nouveau_gem_prime_export, + .gem_prime_import = nouveau_gem_prime_import, + .gem_init_object = nouveau_gem_object_new, .gem_free_object = nouveau_gem_object_del, .gem_open_object = nouveau_gem_object_open, diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 3aef353a926c..92c9a8a648de 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -86,6 +86,7 @@ struct nouveau_mem { u32 memtype; u64 offset; u64 size; + struct sg_table *sg; }; struct nouveau_tile_reg { @@ -1416,7 +1417,9 @@ extern int nv04_crtc_create(struct drm_device *, int index); extern struct ttm_bo_driver nouveau_bo_driver; extern int nouveau_bo_new(struct drm_device *, int size, int align, uint32_t flags, uint32_t tile_mode, - uint32_t tile_flags, struct nouveau_bo **); + uint32_t tile_flags, + struct sg_table *sg, + struct nouveau_bo **); extern int nouveau_bo_pin(struct nouveau_bo *, uint32_t flags); extern int nouveau_bo_unpin(struct nouveau_bo *); extern int nouveau_bo_map(struct nouveau_bo *); @@ -1501,6 +1504,11 @@ extern int nouveau_gem_ioctl_cpu_fini(struct drm_device *, void *, extern int nouveau_gem_ioctl_info(struct drm_device *, void *, struct drm_file *); +extern struct dma_buf *nouveau_gem_prime_export(struct drm_device *dev, + struct drm_gem_object *obj, int flags); +extern struct drm_gem_object *nouveau_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf); + /* nouveau_display.c */ int nouveau_display_create(struct drm_device *dev); void nouveau_display_destroy(struct drm_device *dev); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index c1dc20f6cb85..965e3d2e8a7d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -573,7 +573,7 @@ nouveau_fence_init(struct drm_device *dev) /* Create a shared VRAM heap for cross-channel sync. */ if (USE_SEMA(dev)) { ret = nouveau_bo_new(dev, size, 0, TTM_PL_FLAG_VRAM, - 0, 0, &dev_priv->fence.bo); + 0, 0, NULL, &dev_priv->fence.bo); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index ed52a6f41613..666dad0717a9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -23,6 +23,7 @@ * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. * */ +#include <linux/dma-buf.h> #include "drmP.h" #include "drm.h" @@ -53,6 +54,9 @@ nouveau_gem_object_del(struct drm_gem_object *gem) nouveau_bo_unpin(nvbo); } + if (gem->import_attach) + drm_prime_gem_destroy(gem, nvbo->bo.sg); + ttm_bo_unref(&bo); drm_gem_object_release(gem); @@ -139,7 +143,7 @@ nouveau_gem_new(struct drm_device *dev, int size, int align, uint32_t domain, flags |= TTM_PL_FLAG_SYSTEM; ret = nouveau_bo_new(dev, size, align, flags, tile_mode, - tile_flags, pnvbo); + tile_flags, NULL, pnvbo); if (ret) return ret; nvbo = *pnvbo; diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index b08065f981df..bb2f0a43f590 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -416,7 +416,7 @@ nouveau_mem_vram_init(struct drm_device *dev) if (dev_priv->card_type < NV_50) { ret = nouveau_bo_new(dev, 256*1024, 0, TTM_PL_FLAG_VRAM, - 0, 0, &dev_priv->vga_ram); + 0, 0, NULL, &dev_priv->vga_ram); if (ret == 0) ret = nouveau_bo_pin(dev_priv->vga_ram, TTM_PL_FLAG_VRAM); diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c new file mode 100644 index 000000000000..4fbbb17396ab --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -0,0 +1,132 @@ + +#include "drmP.h" +#include "drm.h" + +#include "nouveau_drv.h" +#include "nouveau_drm.h" +#include "nouveau_dma.h" + +#include <linux/dma-buf.h> + +static struct sg_table *nouveau_gem_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction dir) +{ + struct nouveau_bo *nvbo = attachment->dmabuf->priv; + struct drm_device *dev = nvbo->gem->dev; + int npages = nvbo->bo.num_pages; + struct sg_table *sg; + int nents; + + mutex_lock(&dev->struct_mutex); + sg = drm_prime_pages_to_sg(nvbo->bo.ttm->pages, npages); + nents = dma_map_sg(attachment->dev, sg->sgl, sg->nents, dir); + mutex_unlock(&dev->struct_mutex); + return sg; +} + +static void nouveau_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *sg, enum dma_data_direction dir) +{ + dma_unmap_sg(attachment->dev, sg->sgl, sg->nents, dir); + sg_free_table(sg); + kfree(sg); +} + +static void nouveau_gem_dmabuf_release(struct dma_buf *dma_buf) +{ + struct nouveau_bo *nvbo = dma_buf->priv; + + if (nvbo->gem->export_dma_buf == dma_buf) { + DRM_ERROR("unreference dmabuf %p\n", nvbo->gem); + nvbo->gem->export_dma_buf = NULL; + drm_gem_object_unreference_unlocked(nvbo->gem); + } +} + +struct dma_buf_ops nouveau_dmabuf_ops = { + .map_dma_buf = nouveau_gem_map_dma_buf, + .unmap_dma_buf = nouveau_gem_unmap_dma_buf, + .release = nouveau_gem_dmabuf_release, +}; + +static int +nouveau_prime_new(struct drm_device *dev, + size_t size, + struct sg_table *sg, + struct nouveau_bo **pnvbo) +{ + struct nouveau_bo *nvbo; + u32 flags = 0; + int ret; + + flags = TTM_PL_FLAG_TT; + + ret = nouveau_bo_new(dev, size, 0, flags, 0, 0, + sg, pnvbo); + if (ret) + return ret; + nvbo = *pnvbo; + + /* we restrict allowed domains on nv50+ to only the types + * that were requested at creation time. not possibly on + * earlier chips without busting the ABI. + */ + nvbo->valid_domains = NOUVEAU_GEM_DOMAIN_GART; + nvbo->gem = drm_gem_object_alloc(dev, nvbo->bo.mem.size); + if (!nvbo->gem) { + nouveau_bo_ref(NULL, pnvbo); + return -ENOMEM; + } + + nvbo->gem->driver_private = nvbo; + return 0; +} + +struct dma_buf *nouveau_gem_prime_export(struct drm_device *dev, + struct drm_gem_object *obj, int flags) +{ + struct nouveau_bo *nvbo = nouveau_gem_object(obj); + int ret = 0; + + /* pin buffer into GTT */ + ret = nouveau_bo_pin(nvbo, TTM_PL_FLAG_TT); + if (ret) + return ERR_PTR(-EINVAL); + + return dma_buf_export(nvbo, &nouveau_dmabuf_ops, obj->size, flags); +} + +struct drm_gem_object *nouveau_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct dma_buf_attachment *attach; + struct sg_table *sg; + struct nouveau_bo *nvbo; + int ret; + + /* need to attach */ + attach = dma_buf_attach(dma_buf, dev->dev); + if (IS_ERR(attach)) + return ERR_PTR(PTR_ERR(attach)); + + sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL); + if (IS_ERR(sg)) { + ret = PTR_ERR(sg); + goto fail_detach; + } + + ret = nouveau_prime_new(dev, dma_buf->size, sg, &nvbo); + if (ret) + goto fail_unmap; + + nvbo->gem->import_attach = attach; + + return nvbo->gem; + +fail_unmap: + dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL); +fail_detach: + dma_buf_detach(dma_buf, attach); + return ERR_PTR(ret); +} + diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index 47f245edf538..27aac9ada73a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -290,7 +290,10 @@ nv50_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *mem) struct nouveau_mem *node = mem->mm_node; /* noop: bound in move_notify() */ - node->pages = nvbe->ttm.dma_address; + if (ttm->sg) { + node->sg = ttm->sg; + } else + node->pages = nvbe->ttm.dma_address; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_vm.c b/drivers/gpu/drm/nouveau/nouveau_vm.c index 2bf6c0350b4b..11edd5e91a0a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vm.c @@ -77,6 +77,63 @@ nouveau_vm_map(struct nouveau_vma *vma, struct nouveau_mem *node) } void +nouveau_vm_map_sg_table(struct nouveau_vma *vma, u64 delta, u64 length, + struct nouveau_mem *mem) +{ + struct nouveau_vm *vm = vma->vm; + int big = vma->node->type != vm->spg_shift; + u32 offset = vma->node->offset + (delta >> 12); + u32 bits = vma->node->type - 12; + u32 num = length >> vma->node->type; + u32 pde = (offset >> vm->pgt_bits) - vm->fpde; + u32 pte = (offset & ((1 << vm->pgt_bits) - 1)) >> bits; + u32 max = 1 << (vm->pgt_bits - bits); + unsigned m, sglen; + u32 end, len; + int i; + struct scatterlist *sg; + + for_each_sg(mem->sg->sgl, sg, mem->sg->nents, i) { + struct nouveau_gpuobj *pgt = vm->pgt[pde].obj[big]; + sglen = sg_dma_len(sg) >> PAGE_SHIFT; + + end = pte + sglen; + if (unlikely(end >= max)) + end = max; + len = end - pte; + + for (m = 0; m < len; m++) { + dma_addr_t addr = sg_dma_address(sg) + (m << PAGE_SHIFT); + + vm->map_sg(vma, pgt, mem, pte, 1, &addr); + num--; + pte++; + + if (num == 0) + goto finish; + } + if (unlikely(end >= max)) { + pde++; + pte = 0; + } + if (m < sglen) { + for (; m < sglen; m++) { + dma_addr_t addr = sg_dma_address(sg) + (m << PAGE_SHIFT); + + vm->map_sg(vma, pgt, mem, pte, 1, &addr); + num--; + pte++; + if (num == 0) + goto finish; + } + } + + } +finish: + vm->flush(vm); +} + +void nouveau_vm_map_sg(struct nouveau_vma *vma, u64 delta, u64 length, struct nouveau_mem *mem) { diff --git a/drivers/gpu/drm/nouveau/nouveau_vm.h b/drivers/gpu/drm/nouveau/nouveau_vm.h index 4fb6e728734d..a8246e7e4a89 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vm.h +++ b/drivers/gpu/drm/nouveau/nouveau_vm.h @@ -72,6 +72,9 @@ struct nouveau_vm { u64 phys, u64 delta); void (*map_sg)(struct nouveau_vma *, struct nouveau_gpuobj *, struct nouveau_mem *, u32 pte, u32 cnt, dma_addr_t *); + + void (*map_sg_table)(struct nouveau_vma *, struct nouveau_gpuobj *, + struct nouveau_mem *, u32 pte, u32 cnt, dma_addr_t *); void (*unmap)(struct nouveau_gpuobj *pgt, u32 pte, u32 cnt); void (*flush)(struct nouveau_vm *); }; @@ -90,7 +93,8 @@ void nouveau_vm_unmap(struct nouveau_vma *); void nouveau_vm_unmap_at(struct nouveau_vma *, u64 offset, u64 length); void nouveau_vm_map_sg(struct nouveau_vma *, u64 offset, u64 length, struct nouveau_mem *); - +void nouveau_vm_map_sg_table(struct nouveau_vma *vma, u64 delta, u64 length, + struct nouveau_mem *mem); /* nv50_vm.c */ void nv50_vm_map_pgt(struct nouveau_gpuobj *pgd, u32 pde, struct nouveau_gpuobj *pgt[2]); diff --git a/drivers/gpu/drm/nouveau/nv04_crtc.c b/drivers/gpu/drm/nouveau/nv04_crtc.c index 728d07584d39..4c31c63e5528 100644 --- a/drivers/gpu/drm/nouveau/nv04_crtc.c +++ b/drivers/gpu/drm/nouveau/nv04_crtc.c @@ -1047,7 +1047,7 @@ nv04_crtc_create(struct drm_device *dev, int crtc_num) drm_mode_crtc_set_gamma_size(&nv_crtc->base, 256); ret = nouveau_bo_new(dev, 64*64*4, 0x100, TTM_PL_FLAG_VRAM, - 0, 0x0000, &nv_crtc->cursor.nvbo); + 0, 0x0000, NULL, &nv_crtc->cursor.nvbo); if (!ret) { ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM); if (!ret) diff --git a/drivers/gpu/drm/nouveau/nv50_crtc.c b/drivers/gpu/drm/nouveau/nv50_crtc.c index 701b927998bf..cad2abd11756 100644 --- a/drivers/gpu/drm/nouveau/nv50_crtc.c +++ b/drivers/gpu/drm/nouveau/nv50_crtc.c @@ -769,7 +769,7 @@ nv50_crtc_create(struct drm_device *dev, int index) nv_crtc->lut.depth = 0; ret = nouveau_bo_new(dev, 4096, 0x100, TTM_PL_FLAG_VRAM, - 0, 0x0000, &nv_crtc->lut.nvbo); + 0, 0x0000, NULL, &nv_crtc->lut.nvbo); if (!ret) { ret = nouveau_bo_pin(nv_crtc->lut.nvbo, TTM_PL_FLAG_VRAM); if (!ret) @@ -795,7 +795,7 @@ nv50_crtc_create(struct drm_device *dev, int index) drm_mode_crtc_set_gamma_size(&nv_crtc->base, 256); ret = nouveau_bo_new(dev, 64*64*4, 0x100, TTM_PL_FLAG_VRAM, - 0, 0x0000, &nv_crtc->cursor.nvbo); + 0, 0x0000, NULL, &nv_crtc->cursor.nvbo); if (!ret) { ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM); if (!ret) diff --git a/drivers/gpu/drm/nouveau/nv50_evo.c b/drivers/gpu/drm/nouveau/nv50_evo.c index 9b962e989d7c..ddcd55595824 100644 --- a/drivers/gpu/drm/nouveau/nv50_evo.c +++ b/drivers/gpu/drm/nouveau/nv50_evo.c @@ -117,7 +117,7 @@ nv50_evo_channel_new(struct drm_device *dev, int chid, evo->user_get = 4; evo->user_put = 0; - ret = nouveau_bo_new(dev, 4096, 0, TTM_PL_FLAG_VRAM, 0, 0, + ret = nouveau_bo_new(dev, 4096, 0, TTM_PL_FLAG_VRAM, 0, 0, NULL, &evo->pushbuf_bo); if (ret == 0) ret = nouveau_bo_pin(evo->pushbuf_bo, TTM_PL_FLAG_VRAM); @@ -333,7 +333,7 @@ nv50_evo_create(struct drm_device *dev) goto err; ret = nouveau_bo_new(dev, 4096, 0x1000, TTM_PL_FLAG_VRAM, - 0, 0x0000, &dispc->sem.bo); + 0, 0x0000, NULL, &dispc->sem.bo); if (!ret) { ret = nouveau_bo_pin(dispc->sem.bo, TTM_PL_FLAG_VRAM); if (!ret) diff --git a/drivers/gpu/drm/nouveau/nvd0_display.c b/drivers/gpu/drm/nouveau/nvd0_display.c index 0247250939e8..1f3a9b1240e8 100644 --- a/drivers/gpu/drm/nouveau/nvd0_display.c +++ b/drivers/gpu/drm/nouveau/nvd0_display.c @@ -882,7 +882,7 @@ nvd0_crtc_create(struct drm_device *dev, int index) drm_mode_crtc_set_gamma_size(crtc, 256); ret = nouveau_bo_new(dev, 64 * 64 * 4, 0x100, TTM_PL_FLAG_VRAM, - 0, 0x0000, &nv_crtc->cursor.nvbo); + 0, 0x0000, NULL, &nv_crtc->cursor.nvbo); if (!ret) { ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM); if (!ret) @@ -895,7 +895,7 @@ nvd0_crtc_create(struct drm_device *dev, int index) goto out; ret = nouveau_bo_new(dev, 8192, 0x100, TTM_PL_FLAG_VRAM, - 0, 0x0000, &nv_crtc->lut.nvbo); + 0, 0x0000, NULL, &nv_crtc->lut.nvbo); if (!ret) { ret = nouveau_bo_pin(nv_crtc->lut.nvbo, TTM_PL_FLAG_VRAM); if (!ret) @@ -2030,7 +2030,7 @@ nvd0_display_create(struct drm_device *dev) /* small shared memory area we use for notifiers and semaphores */ ret = nouveau_bo_new(dev, 4096, 0x1000, TTM_PL_FLAG_VRAM, - 0, 0x0000, &disp->sync); + 0, 0x0000, NULL, &disp->sync); if (!ret) { ret = nouveau_bo_pin(disp->sync, TTM_PL_FLAG_VRAM); if (!ret) diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index df6a4dbd93f8..1affbc954c56 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -155,7 +155,7 @@ retry: mutex_lock(&rdev->vram_mutex); r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type, &bo->placement, page_align, 0, !kernel, NULL, - acc_size, &radeon_ttm_bo_destroy); + acc_size, NULL, &radeon_ttm_bo_destroy); mutex_unlock(&rdev->vram_mutex); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) { diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index f493c6403af5..e83aee2ced99 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -614,10 +614,17 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm) struct radeon_ttm_tt *gtt = (void *)ttm; unsigned i; int r; + bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); if (ttm->state != tt_unpopulated) return 0; + /* SG has pages already in correct space */ + if (slave && ttm->sg) { + ttm->state = tt_unbound; + return 0; + } + rdev = radeon_get_rdev(ttm->bdev); #if __OS_HAS_AGP if (rdev->flags & RADEON_IS_AGP) { @@ -658,6 +665,12 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm) struct radeon_device *rdev; struct radeon_ttm_tt *gtt = (void *)ttm; unsigned i; + bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + + if (slave) { + ttm->state = tt_unpopulated; + return; + } rdev = radeon_get_rdev(ttm->bdev); #if __OS_HAS_AGP diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 1f5c67c579cf..289e27bf8a8e 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -343,6 +343,16 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc) if (unlikely(bo->ttm == NULL)) ret = -ENOMEM; break; + case ttm_bo_type_sg: + bo->ttm = bdev->driver->ttm_tt_create(bdev, bo->num_pages << PAGE_SHIFT, + page_flags | TTM_PAGE_FLAG_SG, + glob->dummy_read_page); + if (unlikely(bo->ttm == NULL)) { + ret = -ENOMEM; + break; + } + bo->ttm->sg = bo->sg; + break; default: pr_err("Illegal buffer object type\n"); ret = -EINVAL; @@ -1169,6 +1179,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev, bool interruptible, struct file *persistent_swap_storage, size_t acc_size, + struct sg_table *sg, void (*destroy) (struct ttm_buffer_object *)) { int ret = 0; @@ -1223,6 +1234,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev, bo->seq_valid = false; bo->persistent_swap_storage = persistent_swap_storage; bo->acc_size = acc_size; + bo->sg = sg; atomic_inc(&bo->glob->bo_count); ret = ttm_bo_check_placement(bo, placement); @@ -1312,7 +1324,7 @@ int ttm_bo_create(struct ttm_bo_device *bdev, ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment, buffer_start, interruptible, - persistent_swap_storage, acc_size, NULL); + persistent_swap_storage, acc_size, NULL, NULL); if (likely(ret == 0)) *p_bo = bo; diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c index 53673907a6a0..8e4178e9aa92 100644 --- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -57,7 +57,7 @@ static const struct file_operations udl_driver_fops = { }; static struct drm_driver driver = { - .driver_features = DRIVER_MODESET | DRIVER_GEM, + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME, .load = udl_driver_load, .unload = udl_driver_unload, @@ -70,6 +70,10 @@ static struct drm_driver driver = { .dumb_map_offset = udl_gem_mmap, .dumb_destroy = udl_dumb_destroy, .fops = &udl_driver_fops, + + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import = udl_gem_prime_import, + .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h index 96820d03a303..fccd361f7b50 100644 --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -66,6 +66,7 @@ struct udl_gem_object { struct drm_gem_object base; struct page **pages; void *vmapping; + struct sg_table *sg; }; #define to_udl_bo(x) container_of(x, struct udl_gem_object, base) @@ -118,6 +119,8 @@ int udl_gem_init_object(struct drm_gem_object *obj); void udl_gem_free_object(struct drm_gem_object *gem_obj); struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev, size_t size); +struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf); int udl_gem_vmap(struct udl_gem_object *obj); void udl_gem_vunmap(struct udl_gem_object *obj); diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index 4d9c3a5d8a45..ce9a61179925 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -156,8 +156,17 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y, if (!fb->active_16) return 0; - if (!fb->obj->vmapping) - udl_gem_vmap(fb->obj); + if (!fb->obj->vmapping) { + ret = udl_gem_vmap(fb->obj); + if (ret == -ENOMEM) { + DRM_ERROR("failed to vmap fb\n"); + return 0; + } + if (!fb->obj->vmapping) { + DRM_ERROR("failed to vmapping\n"); + return 0; + } + } start_cycles = get_cycles(); @@ -593,11 +602,20 @@ udl_fb_user_fb_create(struct drm_device *dev, struct drm_gem_object *obj; struct udl_framebuffer *ufb; int ret; + uint32_t size; obj = drm_gem_object_lookup(dev, file, mode_cmd->handles[0]); if (obj == NULL) return ERR_PTR(-ENOENT); + size = mode_cmd->pitches[0] * mode_cmd->height; + size = ALIGN(size, PAGE_SIZE); + + if (size > obj->size) { + DRM_ERROR("object size not sufficient for fb %d %zu %d %d\n", size, obj->size, mode_cmd->pitches[0], mode_cmd->height); + return ERR_PTR(-ENOMEM); + } + ufb = kzalloc(sizeof(*ufb), GFP_KERNEL); if (ufb == NULL) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index 92f19ef329b0..56afdfe88e0d 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -9,6 +9,7 @@ #include "drmP.h" #include "udl_drv.h" #include <linux/shmem_fs.h> +#include <linux/dma-buf.h> struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev, size_t size) @@ -161,6 +162,12 @@ static void udl_gem_put_pages(struct udl_gem_object *obj) int page_count = obj->base.size / PAGE_SIZE; int i; + if (obj->base.import_attach) { + drm_free_large(obj->pages); + obj->pages = NULL; + return; + } + for (i = 0; i < page_count; i++) page_cache_release(obj->pages[i]); @@ -173,6 +180,18 @@ int udl_gem_vmap(struct udl_gem_object *obj) int page_count = obj->base.size / PAGE_SIZE; int ret; + if (obj->base.import_attach) { + ret = dma_buf_begin_cpu_access(obj->base.import_attach->dmabuf, + 0, obj->base.size, DMA_BIDIRECTIONAL); + if (ret) + return -EINVAL; + + obj->vmapping = dma_buf_vmap(obj->base.import_attach->dmabuf); + if (!obj->vmapping) + return -ENOMEM; + return 0; + } + ret = udl_gem_get_pages(obj, GFP_KERNEL); if (ret) return ret; @@ -185,6 +204,13 @@ int udl_gem_vmap(struct udl_gem_object *obj) void udl_gem_vunmap(struct udl_gem_object *obj) { + if (obj->base.import_attach) { + dma_buf_vunmap(obj->base.import_attach->dmabuf, obj->vmapping); + dma_buf_end_cpu_access(obj->base.import_attach->dmabuf, 0, + obj->base.size, DMA_BIDIRECTIONAL); + return; + } + if (obj->vmapping) vunmap(obj->vmapping); @@ -198,6 +224,9 @@ void udl_gem_free_object(struct drm_gem_object *gem_obj) if (obj->vmapping) udl_gem_vunmap(obj); + if (gem_obj->import_attach) + drm_prime_gem_destroy(gem_obj, obj->sg); + if (obj->pages) udl_gem_put_pages(obj); @@ -239,3 +268,69 @@ unlock: mutex_unlock(&dev->struct_mutex); return ret; } + +static int udl_prime_create(struct drm_device *dev, + size_t size, + struct sg_table *sg, + struct udl_gem_object **obj_p) +{ + struct udl_gem_object *obj; + int npages; + int i; + struct scatterlist *iter; + + npages = size / PAGE_SIZE; + + *obj_p = NULL; + obj = udl_gem_alloc_object(dev, npages * PAGE_SIZE); + if (!obj) + return -ENOMEM; + + obj->sg = sg; + obj->pages = drm_malloc_ab(npages, sizeof(struct page *)); + if (obj->pages == NULL) { + DRM_ERROR("obj pages is NULL %d\n", npages); + return -ENOMEM; + } + + for_each_sg(sg->sgl, iter, npages, i) + obj->pages[i] = sg_page(iter); + + *obj_p = obj; + return 0; +} + +struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct dma_buf_attachment *attach; + struct sg_table *sg; + struct udl_gem_object *uobj; + int ret; + + /* need to attach */ + attach = dma_buf_attach(dma_buf, dev->dev); + if (IS_ERR(attach)) + return ERR_PTR(PTR_ERR(attach)); + + sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL); + if (IS_ERR(sg)) { + ret = PTR_ERR(sg); + goto fail_detach; + } + + ret = udl_prime_create(dev, dma_buf->size, sg, &uobj); + if (ret) { + goto fail_unmap; + } + + uobj->base.import_attach = attach; + + return &uobj->base; + +fail_unmap: + dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL); +fail_detach: + dma_buf_detach(dma_buf, attach); + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index a37abb581cbb..22bf9a21ec71 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -1567,7 +1567,7 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv, ret = ttm_bo_init(bdev, &vmw_bo->base, size, ttm_bo_type_device, placement, 0, 0, interruptible, - NULL, acc_size, bo_free); + NULL, acc_size, NULL, bo_free); return ret; } diff --git a/drivers/media/video/Kconfig b/drivers/media/video/Kconfig index ce1e7ba940f6..837e55c7d0b8 100644 --- a/drivers/media/video/Kconfig +++ b/drivers/media/video/Kconfig @@ -1133,6 +1133,7 @@ config VIDEO_SAMSUNG_S5P_FIMC VIDEO_V4L2_SUBDEV_API && EXPERIMENTAL select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV + select DMA_SHARED_BUFFER ---help--- This is a v4l2 driver for Samsung S5P and EXYNOS4 camera host interface and video postprocessor. diff --git a/drivers/media/video/s5p-fimc/fimc-capture.c b/drivers/media/video/s5p-fimc/fimc-capture.c index 7e9b2c612b03..da7147323507 100644 --- a/drivers/media/video/s5p-fimc/fimc-capture.c +++ b/drivers/media/video/s5p-fimc/fimc-capture.c @@ -1539,7 +1539,7 @@ int fimc_register_capture_device(struct fimc_dev *fimc, q = &fimc->vid_cap.vbq; memset(q, 0, sizeof(*q)); q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE; - q->io_modes = VB2_MMAP | VB2_USERPTR; + q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF; q->drv_priv = fimc->vid_cap.ctx; q->ops = &fimc_capture_qops; q->mem_ops = &vb2_dma_contig_memops; diff --git a/drivers/media/video/s5p-tv/Kconfig b/drivers/media/video/s5p-tv/Kconfig index f248b2856720..2e80126a115d 100644 --- a/drivers/media/video/s5p-tv/Kconfig +++ b/drivers/media/video/s5p-tv/Kconfig @@ -10,6 +10,7 @@ config VIDEO_SAMSUNG_S5P_TV bool "Samsung TV driver for S5P platform (experimental)" depends on PLAT_S5P && PM_RUNTIME depends on EXPERIMENTAL + select DMA_SHARED_BUFFER default n ---help--- Say Y here to enable selecting the TV output devices for diff --git a/drivers/media/video/s5p-tv/mixer_video.c b/drivers/media/video/s5p-tv/mixer_video.c index f7ca5cc143c6..6b45d934a5f7 100644 --- a/drivers/media/video/s5p-tv/mixer_video.c +++ b/drivers/media/video/s5p-tv/mixer_video.c @@ -1074,7 +1074,7 @@ struct mxr_layer *mxr_base_layer_create(struct mxr_device *mdev, layer->vb_queue = (struct vb2_queue) { .type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE, - .io_modes = VB2_MMAP | VB2_USERPTR, + .io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF, .drv_priv = layer, .buf_struct_size = sizeof(struct mxr_buffer), .ops = &mxr_video_qops, diff --git a/drivers/media/video/videobuf-core.c b/drivers/media/video/videobuf-core.c index de4fa4eb8844..b457c8bcc7e1 100644 --- a/drivers/media/video/videobuf-core.c +++ b/drivers/media/video/videobuf-core.c @@ -335,6 +335,9 @@ static void videobuf_status(struct videobuf_queue *q, struct v4l2_buffer *b, case V4L2_MEMORY_OVERLAY: b->m.offset = vb->boff; break; + case V4L2_MEMORY_DMABUF: + /* DMABUF is not handled in videobuf framework */ + break; } b->flags = 0; @@ -411,6 +414,7 @@ int __videobuf_mmap_setup(struct videobuf_queue *q, break; case V4L2_MEMORY_USERPTR: case V4L2_MEMORY_OVERLAY: + case V4L2_MEMORY_DMABUF: /* nothing */ break; } diff --git a/drivers/media/video/videobuf2-core.c b/drivers/media/video/videobuf2-core.c index 2e8f1df775b6..b431dc6d592e 100644 --- a/drivers/media/video/videobuf2-core.c +++ b/drivers/media/video/videobuf2-core.c @@ -106,6 +106,36 @@ static void __vb2_buf_userptr_put(struct vb2_buffer *vb) } /** + * __vb2_plane_dmabuf_put() - release memory associated with + * a DMABUF shared plane + */ +static void __vb2_plane_dmabuf_put(struct vb2_queue *q, struct vb2_plane *p) +{ + if (!p->mem_priv) + return; + + if (p->dbuf_mapped) + call_memop(q, unmap_dmabuf, p->mem_priv); + + call_memop(q, detach_dmabuf, p->mem_priv); + dma_buf_put(p->dbuf); + memset(p, 0, sizeof *p); +} + +/** + * __vb2_buf_dmabuf_put() - release memory associated with + * a DMABUF shared buffer + */ +static void __vb2_buf_dmabuf_put(struct vb2_buffer *vb) +{ + struct vb2_queue *q = vb->vb2_queue; + unsigned int plane; + + for (plane = 0; plane < vb->num_planes; ++plane) + __vb2_plane_dmabuf_put(q, &vb->planes[plane]); +} + +/** * __setup_offsets() - setup unique offsets ("cookies") for every plane in * every buffer on the queue */ @@ -227,6 +257,8 @@ static void __vb2_free_mem(struct vb2_queue *q, unsigned int buffers) /* Free MMAP buffers or release USERPTR buffers */ if (q->memory == V4L2_MEMORY_MMAP) __vb2_buf_mem_free(vb); + else if (q->memory == V4L2_MEMORY_DMABUF) + __vb2_buf_dmabuf_put(vb); else __vb2_buf_userptr_put(vb); } @@ -349,6 +381,12 @@ static int __fill_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b) */ memcpy(b->m.planes, vb->v4l2_planes, b->length * sizeof(struct v4l2_plane)); + + if (q->memory == V4L2_MEMORY_DMABUF) { + unsigned int plane; + for (plane = 0; plane < vb->num_planes; ++plane) + b->m.planes[plane].m.fd = 0; + } } else { /* * We use length and offset in v4l2_planes array even for @@ -360,6 +398,8 @@ static int __fill_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b) b->m.offset = vb->v4l2_planes[0].m.mem_offset; else if (q->memory == V4L2_MEMORY_USERPTR) b->m.userptr = vb->v4l2_planes[0].m.userptr; + else if (q->memory == V4L2_MEMORY_DMABUF) + b->m.fd = 0; } /* @@ -451,6 +491,20 @@ static int __verify_mmap_ops(struct vb2_queue *q) } /** + * __verify_dmabuf_ops() - verify that all memory operations required for + * DMABUF queue type have been provided + */ +static int __verify_dmabuf_ops(struct vb2_queue *q) +{ + if (!(q->io_modes & VB2_DMABUF) || !q->mem_ops->attach_dmabuf || + !q->mem_ops->detach_dmabuf || !q->mem_ops->map_dmabuf || + !q->mem_ops->unmap_dmabuf) + return -EINVAL; + + return 0; +} + +/** * vb2_reqbufs() - Initiate streaming * @q: videobuf2 queue * @req: struct passed from userspace to vidioc_reqbufs handler in driver @@ -483,8 +537,9 @@ int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) return -EBUSY; } - if (req->memory != V4L2_MEMORY_MMAP - && req->memory != V4L2_MEMORY_USERPTR) { + if (req->memory != V4L2_MEMORY_MMAP && + req->memory != V4L2_MEMORY_DMABUF && + req->memory != V4L2_MEMORY_USERPTR) { dprintk(1, "reqbufs: unsupported memory type\n"); return -EINVAL; } @@ -513,6 +568,11 @@ int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) return -EINVAL; } + if (req->memory == V4L2_MEMORY_DMABUF && __verify_dmabuf_ops(q)) { + dprintk(1, "reqbufs: DMABUF for current setup unsupported\n"); + return -EINVAL; + } + if (req->count == 0 || q->num_buffers != 0 || q->memory != req->memory) { /* * We already have buffers allocated, so first check if they @@ -619,8 +679,9 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) return -EBUSY; } - if (create->memory != V4L2_MEMORY_MMAP - && create->memory != V4L2_MEMORY_USERPTR) { + if (create->memory != V4L2_MEMORY_MMAP && + create->memory != V4L2_MEMORY_USERPTR && + create->memory != V4L2_MEMORY_DMABUF) { dprintk(1, "%s(): unsupported memory type\n", __func__); return -EINVAL; } @@ -644,6 +705,11 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) return -EINVAL; } + if (create->memory == V4L2_MEMORY_DMABUF && __verify_dmabuf_ops(q)) { + dprintk(1, "%s(): DMABUF for current setup unsupported\n", __func__); + return -EINVAL; + } + if (q->num_buffers == VIDEO_MAX_FRAME) { dprintk(1, "%s(): maximum number of buffers already allocated\n", __func__); @@ -776,6 +842,7 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state) { struct vb2_queue *q = vb->vb2_queue; unsigned long flags; + unsigned int plane; if (vb->state != VB2_BUF_STATE_ACTIVE) return; @@ -786,6 +853,10 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state) dprintk(4, "Done processing on buffer %d, state: %d\n", vb->v4l2_buf.index, vb->state); + /* sync buffers */ + for (plane = 0; plane < vb->num_planes; ++plane) + call_memop(q, finish, vb->planes[plane].mem_priv); + /* Add the buffer to the done buffers list */ spin_lock_irqsave(&q->done_lock, flags); vb->state = state; @@ -839,6 +910,14 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, const struct v4l2_buffer *b, b->m.planes[plane].length; } } + if (b->memory == V4L2_MEMORY_DMABUF) { + for (plane = 0; plane < vb->num_planes; ++plane) { + v4l2_planes[plane].bytesused = + b->m.planes[plane].bytesused; + v4l2_planes[plane].m.fd = + b->m.planes[plane].m.fd; + } + } } else { /* * Single-planar buffers do not use planes array, @@ -853,6 +932,10 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, const struct v4l2_buffer *b, v4l2_planes[0].m.userptr = b->m.userptr; v4l2_planes[0].length = b->length; } + + if (b->memory == V4L2_MEMORY_DMABUF) + v4l2_planes[0].m.fd = b->m.fd; + } vb->v4l2_buf.field = b->field; @@ -957,14 +1040,114 @@ static int __qbuf_mmap(struct vb2_buffer *vb, const struct v4l2_buffer *b) } /** + * __qbuf_dmabuf() - handle qbuf of a DMABUF buffer + */ +static int __qbuf_dmabuf(struct vb2_buffer *vb, const struct v4l2_buffer *b) +{ + struct v4l2_plane planes[VIDEO_MAX_PLANES]; + struct vb2_queue *q = vb->vb2_queue; + void *mem_priv; + unsigned int plane; + int ret; + int write = !V4L2_TYPE_IS_OUTPUT(q->type); + + /* Verify and copy relevant information provided by the userspace */ + ret = __fill_vb2_buffer(vb, b, planes); + if (ret) + return ret; + + for (plane = 0; plane < vb->num_planes; ++plane) { + struct dma_buf *dbuf = dma_buf_get(planes[plane].m.fd); + + if (IS_ERR_OR_NULL(dbuf)) { + dprintk(1, "qbuf: invalid dmabuf fd for " + "plane %d\n", plane); + ret = -EINVAL; + goto err; + } + + /* Skip the plane if already verified */ + if (dbuf == vb->planes[plane].dbuf) { + planes[plane].length = dbuf->size; + dma_buf_put(dbuf); + continue; + } + + dprintk(3, "qbuf: buffer description for plane %d changed, " + "reattaching dma buf\n", plane); + + /* Release previously acquired memory if present */ + __vb2_plane_dmabuf_put(q, &vb->planes[plane]); + + /* Acquire each plane's memory */ + mem_priv = call_memop(q, attach_dmabuf, q->alloc_ctx[plane], + dbuf, q->plane_sizes[plane], write); + if (IS_ERR(mem_priv)) { + dprintk(1, "qbuf: failed acquiring dmabuf " + "memory for plane %d\n", plane); + ret = PTR_ERR(mem_priv); + goto err; + } + + planes[plane].length = dbuf->size; + vb->planes[plane].dbuf = dbuf; + vb->planes[plane].mem_priv = mem_priv; + } + + /* TODO: This pins the buffer(s) with dma_buf_map_attachment()).. but + * really we want to do this just before the DMA, not while queueing + * the buffer(s).. + */ + for (plane = 0; plane < vb->num_planes; ++plane) { + ret = call_memop(q, map_dmabuf, vb->planes[plane].mem_priv); + if (ret) { + dprintk(1, "qbuf: failed mapping dmabuf " + "memory for plane %d\n", plane); + goto err; + } + vb->planes[plane].dbuf_mapped = 1; + } + + /* + * Call driver-specific initialization on the newly acquired buffer, + * if provided. + */ + ret = call_qop(q, buf_init, vb); + if (ret) { + dprintk(1, "qbuf: buffer initialization failed\n"); + goto err; + } + + /* + * Now that everything is in order, copy relevant information + * provided by userspace. + */ + for (plane = 0; plane < vb->num_planes; ++plane) + vb->v4l2_planes[plane] = planes[plane]; + + return 0; +err: + /* In case of errors, release planes that were already acquired */ + __vb2_buf_dmabuf_put(vb); + + return ret; +} + +/** * __enqueue_in_driver() - enqueue a vb2_buffer in driver for processing */ static void __enqueue_in_driver(struct vb2_buffer *vb) { struct vb2_queue *q = vb->vb2_queue; + unsigned int plane; vb->state = VB2_BUF_STATE_ACTIVE; atomic_inc(&q->queued_count); + + /* sync buffers */ + for (plane = 0; plane < vb->num_planes; ++plane) + call_memop(q, prepare, vb->planes[plane].mem_priv); + q->ops->buf_queue(vb); } @@ -980,6 +1163,9 @@ static int __buf_prepare(struct vb2_buffer *vb, const struct v4l2_buffer *b) case V4L2_MEMORY_USERPTR: ret = __qbuf_userptr(vb, b); break; + case V4L2_MEMORY_DMABUF: + ret = __qbuf_dmabuf(vb, b); + break; default: WARN(1, "Invalid queue type\n"); ret = -EINVAL; @@ -1335,6 +1521,19 @@ int vb2_dqbuf(struct vb2_queue *q, struct v4l2_buffer *b, bool nonblocking) return ret; } + /* TODO: this unpins the buffer(dma_buf_unmap_attachment()).. but + * really we want to do this just after DMA, not when the + * buffer is dequeued.. + */ + if (q->memory == V4L2_MEMORY_DMABUF) { + unsigned int i; + + for (i = 0; i < vb->num_planes; ++i) { + call_memop(q, unmap_dmabuf, vb->planes[i].mem_priv); + vb->planes[i].dbuf_mapped = 0; + } + } + switch (vb->state) { case VB2_BUF_STATE_DONE: dprintk(3, "dqbuf: Returning done buffer\n"); diff --git a/drivers/media/video/videobuf2-dma-contig.c b/drivers/media/video/videobuf2-dma-contig.c index 4b7132660a93..266ae7d6df2b 100644 --- a/drivers/media/video/videobuf2-dma-contig.c +++ b/drivers/media/video/videobuf2-dma-contig.c @@ -10,7 +10,10 @@ * the Free Software Foundation. */ +#include <linux/dma-buf.h> #include <linux/module.h> +#include <linux/scatterlist.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/dma-mapping.h> @@ -18,71 +21,126 @@ #include <media/videobuf2-dma-contig.h> #include <media/videobuf2-memops.h> -struct vb2_dc_conf { - struct device *dev; -}; - struct vb2_dc_buf { - struct vb2_dc_conf *conf; + struct device *dev; void *vaddr; - dma_addr_t dma_addr; unsigned long size; - struct vm_area_struct *vma; - atomic_t refcount; + dma_addr_t dma_addr; + enum dma_data_direction dma_dir; + struct sg_table *dma_sgt; + + /* MMAP related */ struct vb2_vmarea_handler handler; + atomic_t refcount; + + /* USERPTR related */ + struct vm_area_struct *vma; + + /* DMABUF related */ + struct dma_buf_attachment *db_attach; }; -static void vb2_dma_contig_put(void *buf_priv); +/*********************************************/ +/* scatterlist table functions */ +/*********************************************/ -static void *vb2_dma_contig_alloc(void *alloc_ctx, unsigned long size) +static struct sg_table *vb2_dc_pages_to_sgt(struct page **pages, + unsigned int n_pages, unsigned long offset, unsigned long size) { - struct vb2_dc_conf *conf = alloc_ctx; - struct vb2_dc_buf *buf; + struct sg_table *sgt; + unsigned int chunks; + unsigned int i; + unsigned int cur_page; + int ret; + struct scatterlist *s; - buf = kzalloc(sizeof *buf, GFP_KERNEL); - if (!buf) + sgt = kzalloc(sizeof *sgt, GFP_KERNEL); + if (!sgt) return ERR_PTR(-ENOMEM); - buf->vaddr = dma_alloc_coherent(conf->dev, size, &buf->dma_addr, - GFP_KERNEL); - if (!buf->vaddr) { - dev_err(conf->dev, "dma_alloc_coherent of size %ld failed\n", - size); - kfree(buf); + /* compute number of chunks */ + chunks = 1; + for (i = 1; i < n_pages; ++i) + if (pages[i] != pages[i - 1] + 1) + ++chunks; + + ret = sg_alloc_table(sgt, chunks, GFP_KERNEL); + if (ret) { + kfree(sgt); return ERR_PTR(-ENOMEM); } - buf->conf = conf; - buf->size = size; - - buf->handler.refcount = &buf->refcount; - buf->handler.put = vb2_dma_contig_put; - buf->handler.arg = buf; + /* merging chunks and putting them into the scatterlist */ + cur_page = 0; + for_each_sg(sgt->sgl, s, sgt->orig_nents, i) { + unsigned long chunk_size; + unsigned int j; + + for (j = cur_page + 1; j < n_pages; ++j) + if (pages[j] != pages[j - 1] + 1) + break; + + chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset; + sg_set_page(s, pages[cur_page], min(size, chunk_size), offset); + size -= chunk_size; + offset = 0; + cur_page = j; + } - atomic_inc(&buf->refcount); + return sgt; +} - return buf; +static void vb2_dc_release_sgtable(struct sg_table *sgt) +{ + sg_free_table(sgt); + kfree(sgt); } -static void vb2_dma_contig_put(void *buf_priv) +static void vb2_dc_sgt_foreach_page(struct sg_table *sgt, + void (*cb)(struct page *pg)) { - struct vb2_dc_buf *buf = buf_priv; + struct scatterlist *s; + unsigned int i; - if (atomic_dec_and_test(&buf->refcount)) { - dma_free_coherent(buf->conf->dev, buf->size, buf->vaddr, - buf->dma_addr); - kfree(buf); + for_each_sg(sgt->sgl, s, sgt->nents, i) { + struct page *page = sg_page(s); + unsigned int n_pages = PAGE_ALIGN(s->offset + s->length) + >> PAGE_SHIFT; + unsigned int j; + + for (j = 0; j < n_pages; ++j, ++page) + cb(page); + } +} + +static unsigned long vb2_dc_get_contiguous_size(struct sg_table *sgt) +{ + struct scatterlist *s; + dma_addr_t expected = sg_dma_address(sgt->sgl); + unsigned int i; + unsigned long size = 0; + + for_each_sg(sgt->sgl, s, sgt->nents, i) { + if (sg_dma_address(s) != expected) + break; + expected = sg_dma_address(s) + sg_dma_len(s); + size += sg_dma_len(s); } + return size; } -static void *vb2_dma_contig_cookie(void *buf_priv) +/*********************************************/ +/* callbacks for all buffers */ +/*********************************************/ + +static void *vb2_dc_cookie(void *buf_priv) { struct vb2_dc_buf *buf = buf_priv; return &buf->dma_addr; } -static void *vb2_dma_contig_vaddr(void *buf_priv) +static void *vb2_dc_vaddr(void *buf_priv) { struct vb2_dc_buf *buf = buf_priv; if (!buf) @@ -91,14 +149,79 @@ static void *vb2_dma_contig_vaddr(void *buf_priv) return buf->vaddr; } -static unsigned int vb2_dma_contig_num_users(void *buf_priv) +static unsigned int vb2_dc_num_users(void *buf_priv) { struct vb2_dc_buf *buf = buf_priv; return atomic_read(&buf->refcount); } -static int vb2_dma_contig_mmap(void *buf_priv, struct vm_area_struct *vma) +static void vb2_dc_prepare(void *buf_priv) +{ + struct vb2_dc_buf *buf = buf_priv; + struct sg_table *sgt = buf->dma_sgt; + + if (!sgt) + return; + + dma_sync_sg_for_device(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); +} + +static void vb2_dc_finish(void *buf_priv) +{ + struct vb2_dc_buf *buf = buf_priv; + struct sg_table *sgt = buf->dma_sgt; + + if (!sgt) + return; + + dma_sync_sg_for_cpu(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); +} + +/*********************************************/ +/* callbacks for MMAP buffers */ +/*********************************************/ + +static void vb2_dc_put(void *buf_priv) +{ + struct vb2_dc_buf *buf = buf_priv; + + if (!atomic_dec_and_test(&buf->refcount)) + return; + + dma_free_coherent(buf->dev, buf->size, buf->vaddr, buf->dma_addr); + kfree(buf); +} + +static void *vb2_dc_alloc(void *alloc_ctx, unsigned long size) +{ + struct device *dev = alloc_ctx; + struct vb2_dc_buf *buf; + + buf = kzalloc(sizeof *buf, GFP_KERNEL); + if (!buf) + return ERR_PTR(-ENOMEM); + + buf->vaddr = dma_alloc_coherent(dev, size, &buf->dma_addr, GFP_KERNEL); + if (!buf->vaddr) { + dev_err(dev, "dma_alloc_coherent of size %ld failed\n", size); + kfree(buf); + return ERR_PTR(-ENOMEM); + } + + buf->dev = dev; + buf->size = size; + + buf->handler.refcount = &buf->refcount; + buf->handler.put = vb2_dc_put; + buf->handler.arg = buf; + + atomic_inc(&buf->refcount); + + return buf; +} + +static int vb2_dc_mmap(void *buf_priv, struct vm_area_struct *vma) { struct vb2_dc_buf *buf = buf_priv; @@ -111,73 +234,335 @@ static int vb2_dma_contig_mmap(void *buf_priv, struct vm_area_struct *vma) &vb2_common_vm_ops, &buf->handler); } -static void *vb2_dma_contig_get_userptr(void *alloc_ctx, unsigned long vaddr, - unsigned long size, int write) +/*********************************************/ +/* callbacks for USERPTR buffers */ +/*********************************************/ + +static inline int vma_is_io(struct vm_area_struct *vma) +{ + return !!(vma->vm_flags & (VM_IO | VM_PFNMAP)); +} + +static struct vm_area_struct *vb2_dc_get_user_vma( + unsigned long start, unsigned long size) { - struct vb2_dc_buf *buf; struct vm_area_struct *vma; - dma_addr_t dma_addr = 0; - int ret; + + /* current->mm->mmap_sem is taken by videobuf2 core */ + vma = find_vma(current->mm, start); + if (!vma) { + printk(KERN_ERR "no vma for address %lu\n", start); + return ERR_PTR(-EFAULT); + } + + if (vma->vm_end - vma->vm_start < size) { + printk(KERN_ERR "vma at %lu is too small for %lu bytes\n", + start, size); + return ERR_PTR(-EFAULT); + } + + vma = vb2_get_vma(vma); + if (!vma) { + printk(KERN_ERR "failed to copy vma\n"); + return ERR_PTR(-ENOMEM); + } + + return vma; +} + +static int vb2_dc_get_user_pages(unsigned long start, struct page **pages, + int n_pages, struct vm_area_struct *vma, int write) +{ + if (vma_is_io(vma)) { + unsigned int i; + + for (i = 0; i < n_pages; ++i, start += PAGE_SIZE) { + unsigned long pfn; + int ret = follow_pfn(vma, start, &pfn); + + if (ret) { + printk(KERN_ERR "no page for address %lu\n", + start); + return ret; + } + pages[i] = pfn_to_page(pfn); + } + } else { + unsigned int n; + + n = get_user_pages(current, current->mm, start & PAGE_MASK, + n_pages, write, 1, pages, NULL); + if (n != n_pages) { + printk(KERN_ERR "got only %d of %d user pages\n", + n, n_pages); + while (n) + put_page(pages[--n]); + return -EFAULT; + } + } + + return 0; +} + +static void vb2_dc_put_dirty_page(struct page *page) +{ + set_page_dirty_lock(page); + put_page(page); +} + +static void vb2_dc_put_userptr(void *buf_priv) +{ + struct vb2_dc_buf *buf = buf_priv; + struct sg_table *sgt = buf->dma_sgt; + + dma_unmap_sg(buf->dev, sgt->sgl, sgt->orig_nents, buf->dma_dir); + if (!vma_is_io(buf->vma)) + vb2_dc_sgt_foreach_page(sgt, vb2_dc_put_dirty_page); + + vb2_dc_release_sgtable(sgt); + vb2_put_vma(buf->vma); + kfree(buf); +} + +static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr, + unsigned long size, int write) +{ + struct vb2_dc_buf *buf; + unsigned long start; + unsigned long end; + unsigned long offset; + struct page **pages; + int n_pages; + int ret = 0; + struct sg_table *sgt; + unsigned long contig_size; buf = kzalloc(sizeof *buf, GFP_KERNEL); if (!buf) return ERR_PTR(-ENOMEM); - ret = vb2_get_contig_userptr(vaddr, size, &vma, &dma_addr); + buf->dev = alloc_ctx; + buf->dma_dir = write ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + + start = vaddr & PAGE_MASK; + offset = vaddr & ~PAGE_MASK; + end = PAGE_ALIGN(vaddr + size); + n_pages = (end - start) >> PAGE_SHIFT; + + pages = kmalloc(n_pages * sizeof pages[0], GFP_KERNEL); + if (!pages) { + ret = -ENOMEM; + printk(KERN_ERR "failed to allocate pages table\n"); + goto fail_buf; + } + + buf->vma = vb2_dc_get_user_vma(start, size); + if (IS_ERR(buf->vma)) { + printk(KERN_ERR "failed to get VMA\n"); + ret = PTR_ERR(buf->vma); + goto fail_pages; + } + + /* extract page list from userspace mapping */ + ret = vb2_dc_get_user_pages(start, pages, n_pages, buf->vma, write); if (ret) { - printk(KERN_ERR "Failed acquiring VMA for vaddr 0x%08lx\n", - vaddr); - kfree(buf); - return ERR_PTR(ret); + printk(KERN_ERR "failed to get user pages\n"); + goto fail_vma; + } + + sgt = vb2_dc_pages_to_sgt(pages, n_pages, offset, size); + if (IS_ERR(sgt)) { + printk(KERN_ERR "failed to create scatterlist table\n"); + ret = -ENOMEM; + goto fail_get_user_pages; + } + + /* pages are no longer needed */ + kfree(pages); + pages = NULL; + + sgt->nents = dma_map_sg(buf->dev, sgt->sgl, sgt->orig_nents, + buf->dma_dir); + if (sgt->nents <= 0) { + printk(KERN_ERR "failed to map scatterlist\n"); + ret = -EIO; + goto fail_sgt; + } + + contig_size = vb2_dc_get_contiguous_size(sgt); + if (contig_size < size) { + printk(KERN_ERR "contiguous mapping is too small %lu/%lu\n", + contig_size, size); + ret = -EFAULT; + goto fail_map_sg; } + buf->dma_addr = sg_dma_address(sgt->sgl); buf->size = size; - buf->dma_addr = dma_addr; - buf->vma = vma; + buf->dma_sgt = sgt; return buf; + +fail_map_sg: + dma_unmap_sg(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); + +fail_sgt: + if (!vma_is_io(buf->vma)) + vb2_dc_sgt_foreach_page(sgt, put_page); + vb2_dc_release_sgtable(sgt); + +fail_get_user_pages: + if (pages && !vma_is_io(buf->vma)) + while (n_pages) + put_page(pages[--n_pages]); + +fail_vma: + vb2_put_vma(buf->vma); + +fail_pages: + kfree(pages); /* kfree is NULL-proof */ + +fail_buf: + kfree(buf); + + return ERR_PTR(ret); } -static void vb2_dma_contig_put_userptr(void *mem_priv) +/*********************************************/ +/* callbacks for DMABUF buffers */ +/*********************************************/ + +static int vb2_dc_map_dmabuf(void *mem_priv) { struct vb2_dc_buf *buf = mem_priv; + struct sg_table *sgt; + unsigned long contig_size; - if (!buf) + if (WARN_ON(!buf->db_attach)) { + printk(KERN_ERR "trying to pin a non attached buffer\n"); + return -EINVAL; + } + + if (WARN_ON(buf->dma_sgt)) { + printk(KERN_ERR "dmabuf buffer is already pinned\n"); + return 0; + } + + /* get the associated scatterlist for this buffer */ + sgt = dma_buf_map_attachment(buf->db_attach, buf->dma_dir); + if (IS_ERR_OR_NULL(sgt)) { + printk(KERN_ERR "Error getting dmabuf scatterlist\n"); + return -EINVAL; + } + + /* checking if dmabuf is big enough to store contiguous chunk */ + contig_size = vb2_dc_get_contiguous_size(sgt); + if (contig_size < buf->size) { + printk(KERN_ERR "contiguous chunk is too small %lu/%lu b\n", + contig_size, buf->size); + dma_buf_unmap_attachment(buf->db_attach, sgt, buf->dma_dir); + return -EFAULT; + } + + buf->dma_addr = sg_dma_address(sgt->sgl); + buf->dma_sgt = sgt; + + return 0; +} + +static void vb2_dc_unmap_dmabuf(void *mem_priv) +{ + struct vb2_dc_buf *buf = mem_priv; + struct sg_table *sgt = buf->dma_sgt; + + if (WARN_ON(!buf->db_attach)) { + printk(KERN_ERR "trying to unpin a not attached buffer\n"); return; + } - vb2_put_vma(buf->vma); + if (WARN_ON(!sgt)) { + printk(KERN_ERR "dmabuf buffer is already unpinned\n"); + return; + } + + dma_buf_unmap_attachment(buf->db_attach, sgt, buf->dma_dir); + + buf->dma_addr = 0; + buf->dma_sgt = NULL; +} + +static void vb2_dc_detach_dmabuf(void *mem_priv) +{ + struct vb2_dc_buf *buf = mem_priv; + + /* if vb2 works correctly you should never detach mapped buffer */ + if (WARN_ON(buf->dma_addr)) + vb2_dc_unmap_dmabuf(buf); + + /* detach this attachment */ + dma_buf_detach(buf->db_attach->dmabuf, buf->db_attach); kfree(buf); } +static void *vb2_dc_attach_dmabuf(void *alloc_ctx, struct dma_buf *dbuf, + unsigned long size, int write) +{ + struct vb2_dc_buf *buf; + struct dma_buf_attachment *dba; + + if (dbuf->size < size) + return ERR_PTR(-EFAULT); + + buf = kzalloc(sizeof *buf, GFP_KERNEL); + if (!buf) + return ERR_PTR(-ENOMEM); + + buf->dev = alloc_ctx; + /* create attachment for the dmabuf with the user device */ + dba = dma_buf_attach(dbuf, buf->dev); + if (IS_ERR(dba)) { + printk(KERN_ERR "failed to attach dmabuf\n"); + kfree(buf); + return dba; + } + + buf->dma_dir = write ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + buf->size = size; + buf->db_attach = dba; + + return buf; +} + +/*********************************************/ +/* DMA CONTIG exported functions */ +/*********************************************/ + const struct vb2_mem_ops vb2_dma_contig_memops = { - .alloc = vb2_dma_contig_alloc, - .put = vb2_dma_contig_put, - .cookie = vb2_dma_contig_cookie, - .vaddr = vb2_dma_contig_vaddr, - .mmap = vb2_dma_contig_mmap, - .get_userptr = vb2_dma_contig_get_userptr, - .put_userptr = vb2_dma_contig_put_userptr, - .num_users = vb2_dma_contig_num_users, + .alloc = vb2_dc_alloc, + .put = vb2_dc_put, + .cookie = vb2_dc_cookie, + .vaddr = vb2_dc_vaddr, + .mmap = vb2_dc_mmap, + .get_userptr = vb2_dc_get_userptr, + .put_userptr = vb2_dc_put_userptr, + .prepare = vb2_dc_prepare, + .finish = vb2_dc_finish, + .map_dmabuf = vb2_dc_map_dmabuf, + .unmap_dmabuf = vb2_dc_unmap_dmabuf, + .attach_dmabuf = vb2_dc_attach_dmabuf, + .detach_dmabuf = vb2_dc_detach_dmabuf, + .num_users = vb2_dc_num_users, }; EXPORT_SYMBOL_GPL(vb2_dma_contig_memops); void *vb2_dma_contig_init_ctx(struct device *dev) { - struct vb2_dc_conf *conf; - - conf = kzalloc(sizeof *conf, GFP_KERNEL); - if (!conf) - return ERR_PTR(-ENOMEM); - - conf->dev = dev; - - return conf; + return dev; } EXPORT_SYMBOL_GPL(vb2_dma_contig_init_ctx); void vb2_dma_contig_cleanup_ctx(void *alloc_ctx) { - kfree(alloc_ctx); } EXPORT_SYMBOL_GPL(vb2_dma_contig_cleanup_ctx); diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h new file mode 100644 index 000000000000..c544356b374b --- /dev/null +++ b/include/asm-generic/dma-contiguous.h @@ -0,0 +1,28 @@ +#ifndef ASM_DMA_CONTIGUOUS_H +#define ASM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ +#ifdef CONFIG_CMA + +#include <linux/device.h> +#include <linux/dma-contiguous.h> + +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) +{ + if (dev) + dev->cma_area = cma; + if (!dev || !dma_contiguous_default_area) + dma_contiguous_default_area = cma; +} + +#endif +#endif + +#endif diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 974c8f801c39..e15f2a89a270 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -124,11 +124,15 @@ struct ttm_mem_reg { * * @ttm_bo_type_kernel: These buffers are like ttm_bo_type_device buffers, * but they cannot be accessed from user-space. For kernel-only use. + * + * @ttm_bo_type_sg: Buffer made from dmabuf sg table shared with another + * driver. */ enum ttm_bo_type { ttm_bo_type_device, - ttm_bo_type_kernel + ttm_bo_type_kernel, + ttm_bo_type_sg }; struct ttm_tt; @@ -271,6 +275,8 @@ struct ttm_buffer_object { unsigned long offset; uint32_t cur_placement; + + struct sg_table *sg; }; /** @@ -503,6 +509,7 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev, bool interrubtible, struct file *persistent_swap_storage, size_t acc_size, + struct sg_table *sg, void (*destroy) (struct ttm_buffer_object *)); /** diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index d43e892307ff..a05f1b55714d 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -81,6 +81,7 @@ struct ttm_backend_func { #define TTM_PAGE_FLAG_PERSISTENT_SWAP (1 << 5) #define TTM_PAGE_FLAG_ZERO_ALLOC (1 << 6) #define TTM_PAGE_FLAG_DMA32 (1 << 7) +#define TTM_PAGE_FLAG_SG (1 << 8) enum ttm_caching_state { tt_uncached, @@ -116,6 +117,7 @@ struct ttm_tt { struct page **pages; uint32_t page_flags; unsigned long num_pages; + struct sg_table *sg; /* for SG objects via dma-buf */ struct ttm_bo_global *glob; struct ttm_backend *be; struct file *swap_storage; diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd71..e3399290436e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -661,6 +661,10 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ +#ifdef CONFIG_CMA + struct cma *cma_area; /* contiguous memory area for dma + allocations */ +#endif /* arch specific additions */ struct dev_archdata archdata; diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 3efbfc2145c3..8fe719fbb281 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -61,6 +61,10 @@ struct dma_buf_attachment; * This Callback must not sleep. * @kmap: maps a page from the buffer into kernel address space. * @kunmap: [optional] unmaps a page from the buffer. + * @mmap: used to expose the backing storage to userspace. Note that the + * mapping needs to be coherent - if the exporter doesn't directly + * support this, it needs to fake coherency by shooting down any ptes + * when transitioning away from the cpu domain. */ struct dma_buf_ops { int (*attach)(struct dma_buf *, struct device *, @@ -92,6 +96,10 @@ struct dma_buf_ops { void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*kmap)(struct dma_buf *, unsigned long); void (*kunmap)(struct dma_buf *, unsigned long, void *); + + int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); + void *(*vmap)(struct dma_buf *); + void (*vunmap)(struct dma_buf *, void *vaddr); }; /** @@ -167,6 +175,11 @@ void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); void *dma_buf_kmap(struct dma_buf *, unsigned long); void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); + +int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, + unsigned long); +void *dma_buf_vmap(struct dma_buf *); +void dma_buf_vunmap(struct dma_buf *, void *vaddr); #else static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, @@ -248,6 +261,21 @@ static inline void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long pnum, void *vaddr) { } + +static inline int dma_buf_mmap(struct dma_buf *dmabuf, + struct vm_area_struct *vma, + unsigned long pgoff) +{ + return -ENODEV; +} + +static inline void *dma_buf_vmap(struct dma_buf *dmabuf) +{ +} + +static inline void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr); +{ +} #endif /* CONFIG_DMA_SHARED_BUFFER */ #endif /* __DMA_BUF_H__ */ diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h new file mode 100644 index 000000000000..2f303e4b7ed3 --- /dev/null +++ b/include/linux/dma-contiguous.h @@ -0,0 +1,110 @@ +#ifndef __LINUX_CMA_H +#define __LINUX_CMA_H + +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski <m.szyprowski@samsung.com> + * Michal Nazarewicz <mina86@mina86.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +/* + * Contiguous Memory Allocator + * + * The Contiguous Memory Allocator (CMA) makes it possible to + * allocate big contiguous chunks of memory after the system has + * booted. + * + * Why is it needed? + * + * Various devices on embedded systems have no scatter-getter and/or + * IO map support and require contiguous blocks of memory to + * operate. They include devices such as cameras, hardware video + * coders, etc. + * + * Such devices often require big memory buffers (a full HD frame + * is, for instance, more then 2 mega pixels large, i.e. more than 6 + * MB of memory), which makes mechanisms such as kmalloc() or + * alloc_page() ineffective. + * + * At the same time, a solution where a big memory region is + * reserved for a device is suboptimal since often more memory is + * reserved then strictly required and, moreover, the memory is + * inaccessible to page system even if device drivers don't use it. + * + * CMA tries to solve this issue by operating on memory regions + * where only movable pages can be allocated from. This way, kernel + * can use the memory for pagecache and when device driver requests + * it, allocated pages can be migrated. + * + * Driver usage + * + * CMA should not be used by the device drivers directly. It is + * only a helper framework for dma-mapping subsystem. + * + * For more information, see kernel-docs in drivers/base/dma-contiguous.c + */ + +#ifdef __KERNEL__ + +struct cma; +struct page; +struct device; + +#ifdef CONFIG_CMA + +/* + * There is always at least global CMA area and a few optional device + * private areas configured in kernel .config. + */ +#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) + +extern struct cma *dma_contiguous_default_area; + +void dma_contiguous_reserve(phys_addr_t addr_limit); +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit); + +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order); +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count); + +#else + +#define MAX_CMA_AREAS (0) + +static inline void dma_contiguous_reserve(phys_addr_t limit) { } + +static inline +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + return -ENOSYS; +} + +static inline +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order) +{ + return NULL; +} + +static inline +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return false; +} + +#endif + +#endif + +#endif diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 581e74b7df95..1e49be49d324 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -391,4 +391,16 @@ static inline bool pm_suspended_storage(void) } #endif /* CONFIG_PM_SLEEP */ +#ifdef CONFIG_CMA + +/* The below functions must be run on a range from a single zone. */ +extern int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype); +extern void free_contig_range(unsigned long pfn, unsigned nr_pages); + +/* CMA stuff */ +extern void init_cma_reserved_pageblock(struct page *page); + +#endif + #endif /* __LINUX_GFP_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index dff711509661..26f2040b8b04 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -35,13 +35,39 @@ */ #define PAGE_ALLOC_COSTLY_ORDER 3 -#define MIGRATE_UNMOVABLE 0 -#define MIGRATE_RECLAIMABLE 1 -#define MIGRATE_MOVABLE 2 -#define MIGRATE_PCPTYPES 3 /* the number of types on the pcp lists */ -#define MIGRATE_RESERVE 3 -#define MIGRATE_ISOLATE 4 /* can't allocate from here */ -#define MIGRATE_TYPES 5 +enum { + MIGRATE_UNMOVABLE, + MIGRATE_RECLAIMABLE, + MIGRATE_MOVABLE, + MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ + MIGRATE_RESERVE = MIGRATE_PCPTYPES, +#ifdef CONFIG_CMA + /* + * MIGRATE_CMA migration type is designed to mimic the way + * ZONE_MOVABLE works. Only movable pages can be allocated + * from MIGRATE_CMA pageblocks and page allocator never + * implicitly change migration type of MIGRATE_CMA pageblock. + * + * The way to use it is to change migratetype of a range of + * pageblocks to MIGRATE_CMA which can be done by + * __free_pageblock_cma() function. What is important though + * is that a range of pageblocks must be aligned to + * MAX_ORDER_NR_PAGES should biggest page be bigger then + * a single pageblock. + */ + MIGRATE_CMA, +#endif + MIGRATE_ISOLATE, /* can't allocate from here */ + MIGRATE_TYPES +}; + +#ifdef CONFIG_CMA +# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define cma_wmark_pages(zone) zone->min_cma_pages +#else +# define is_migrate_cma(migratetype) false +# define cma_wmark_pages(zone) 0 +#endif #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ @@ -347,6 +373,13 @@ struct zone { /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif +#ifdef CONFIG_CMA + /* + * CMA needs to increase watermark levels during the allocation + * process to make sure that the system is not starved. + */ + unsigned long min_cma_pages; +#endif struct free_area free_area[MAX_ORDER]; #ifndef CONFIG_SPARSEMEM diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 051c1b1ede4e..3bdcab30ca41 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -3,7 +3,7 @@ /* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. - * If specified range includes migrate types other than MOVABLE, + * If specified range includes migrate types other than MOVABLE or CMA, * this will fail with -EBUSY. * * For isolating all pages in the range finally, the caller have to @@ -11,27 +11,27 @@ * test it. */ extern int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); +start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype); /* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. * target range is [start_pfn, end_pfn) */ extern int -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); +undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype); /* - * test all pages in [start_pfn, end_pfn)are isolated or not. + * Test all pages in [start_pfn, end_pfn) are isolated or not. */ -extern int -test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); +int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); /* - * Internal funcs.Changes pageblock's migrate type. - * Please use make_pagetype_isolated()/make_pagetype_movable(). + * Internal functions. Changes pageblock's migrate type. */ extern int set_migratetype_isolate(struct page *page); -extern void unset_migratetype_isolate(struct page *page); +extern void unset_migratetype_isolate(struct page *page, unsigned migratetype); #endif diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index c9c9a4680cc5..d884d4ac8481 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -185,6 +185,7 @@ enum v4l2_memory { V4L2_MEMORY_MMAP = 1, V4L2_MEMORY_USERPTR = 2, V4L2_MEMORY_OVERLAY = 3, + V4L2_MEMORY_DMABUF = 4, }; /* see also http://vektor.theorem.ca/graphics/ycbcr/ */ @@ -588,6 +589,8 @@ struct v4l2_requestbuffers { * should be passed to mmap() called on the video node) * @userptr: when memory is V4L2_MEMORY_USERPTR, a userspace pointer * pointing to this plane + * @fd: when memory is V4L2_MEMORY_DMABUF, a userspace file + * descriptor associated with this plane * @data_offset: offset in the plane to the start of data; usually 0, * unless there is a header in front of the data * @@ -602,6 +605,7 @@ struct v4l2_plane { union { __u32 mem_offset; unsigned long userptr; + int fd; } m; __u32 data_offset; __u32 reserved[11]; @@ -624,6 +628,8 @@ struct v4l2_plane { * (or a "cookie" that should be passed to mmap() as offset) * @userptr: for non-multiplanar buffers with memory == V4L2_MEMORY_USERPTR; * a userspace pointer pointing to this buffer + * @fd: for non-multiplanar buffers with memory == V4L2_MEMORY_DMABUF; + * a userspace file descriptor associated with this buffer * @planes: for multiplanar buffers; userspace pointer to the array of plane * info structs for this buffer * @length: size in bytes of the buffer (NOT its payload) for single-plane @@ -650,6 +656,7 @@ struct v4l2_buffer { __u32 offset; unsigned long userptr; struct v4l2_plane *planes; + int fd; } m; __u32 length; __u32 input; diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index a15d1f1b319e..d079f92b6030 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -16,6 +16,7 @@ #include <linux/mutex.h> #include <linux/poll.h> #include <linux/videodev2.h> +#include <linux/dma-buf.h> struct vb2_alloc_ctx; struct vb2_fileio_data; @@ -41,6 +42,24 @@ struct vb2_fileio_data; * argument to other ops in this structure * @put_userptr: inform the allocator that a USERPTR buffer will no longer * be used + * @attach_dmabuf: attach a shared struct dma_buf for a hardware operation; + * used for DMABUF memory types; alloc_ctx is the alloc context + * dbuf is the shared dma_buf; returns NULL on failure; + * allocator private per-buffer structure on success; + * this needs to be used for further accesses to the buffer + * @detach_dmabuf: inform the exporter of the buffer that the current DMABUF + * buffer is no longer used; the buf_priv argument is the + * allocator private per-buffer structure previously returned + * from the attach_dmabuf callback + * @map_dmabuf: request for access to the dmabuf from allocator; the allocator + * of dmabuf is informed that this driver is going to use the + * dmabuf + * @unmap_dmabuf: releases access control to the dmabuf - allocator is notified + * that this driver is done using the dmabuf for now + * @prepare: called everytime the buffer is passed from userspace to the + * driver, usefull for cache synchronisation, optional + * @finish: called everytime the buffer is passed back from the driver + * to the userspace, also optional * @vaddr: return a kernel virtual address to a given memory buffer * associated with the passed private structure or NULL if no * such mapping exists @@ -56,6 +75,8 @@ struct vb2_fileio_data; * Required ops for USERPTR types: get_userptr, put_userptr. * Required ops for MMAP types: alloc, put, num_users, mmap. * Required ops for read/write access types: alloc, put, num_users, vaddr + * Required ops for DMABUF types: attach_dmabuf, detach_dmabuf, map_dmabuf, + * unmap_dmabuf. */ struct vb2_mem_ops { void *(*alloc)(void *alloc_ctx, unsigned long size); @@ -65,6 +86,15 @@ struct vb2_mem_ops { unsigned long size, int write); void (*put_userptr)(void *buf_priv); + void (*prepare)(void *buf_priv); + void (*finish)(void *buf_priv); + + void *(*attach_dmabuf)(void *alloc_ctx, struct dma_buf *dbuf, + unsigned long size, int write); + void (*detach_dmabuf)(void *buf_priv); + int (*map_dmabuf)(void *buf_priv); + void (*unmap_dmabuf)(void *buf_priv); + void *(*vaddr)(void *buf_priv); void *(*cookie)(void *buf_priv); @@ -75,6 +105,8 @@ struct vb2_mem_ops { struct vb2_plane { void *mem_priv; + struct dma_buf *dbuf; + unsigned int dbuf_mapped; }; /** @@ -83,12 +115,14 @@ struct vb2_plane { * @VB2_USERPTR: driver supports USERPTR with streaming API * @VB2_READ: driver supports read() style access * @VB2_WRITE: driver supports write() style access + * @VB2_DMABUF: driver supports DMABUF with streaming API */ enum vb2_io_modes { VB2_MMAP = (1 << 0), VB2_USERPTR = (1 << 1), VB2_READ = (1 << 2), VB2_WRITE = (1 << 3), + VB2_DMABUF = (1 << 4), }; /** diff --git a/mm/Kconfig b/mm/Kconfig index e338407f1225..39220026c797 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -198,7 +198,7 @@ config COMPACTION config MIGRATION bool "Page migration" def_bool y - depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION + depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful in diff --git a/mm/Makefile b/mm/Makefile index 50ec00ef2a0e..8aada89efbbb 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -13,7 +13,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o mmu_context.o percpu.o \ - $(mmu-y) + compaction.o $(mmu-y) obj-y += init-mm.o ifdef CONFIG_NO_BOOTMEM @@ -32,7 +32,6 @@ obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o obj-$(CONFIG_SLOB) += slob.o -obj-$(CONFIG_COMPACTION) += compaction.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_KSM) += ksm.o obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o diff --git a/mm/compaction.c b/mm/compaction.c index 74a8c825ff28..da7d35ea5103 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -16,30 +16,11 @@ #include <linux/sysfs.h> #include "internal.h" +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + #define CREATE_TRACE_POINTS #include <trace/events/compaction.h> -/* - * compact_control is used to track pages being migrated and the free pages - * they are being migrated to during memory compaction. The free_pfn starts - * at the end of a zone and migrate_pfn begins at the start. Movable pages - * are moved to the end of a zone during a compaction run and the run - * completes when free_pfn <= migrate_pfn - */ -struct compact_control { - struct list_head freepages; /* List of free pages to migrate to */ - struct list_head migratepages; /* List of pages being migrated */ - unsigned long nr_freepages; /* Number of isolated free pages */ - unsigned long nr_migratepages; /* Number of pages to migrate */ - unsigned long free_pfn; /* isolate_freepages search base */ - unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ - - int order; /* order a direct compactor needs */ - int migratetype; /* MOVABLE, RECLAIMABLE etc */ - struct zone *zone; -}; - static unsigned long release_freepages(struct list_head *freelist) { struct page *page, *next; @@ -54,24 +35,35 @@ static unsigned long release_freepages(struct list_head *freelist) return count; } -/* Isolate free pages onto a private freelist. Must hold zone->lock */ -static unsigned long isolate_freepages_block(struct zone *zone, - unsigned long blockpfn, - struct list_head *freelist) +static void map_pages(struct list_head *list) +{ + struct page *page; + + list_for_each_entry(page, list, lru) { + arch_alloc_page(page, 0); + kernel_map_pages(page, 1, 1); + } +} + +static inline bool migrate_async_suitable(int migratetype) +{ + return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE; +} + +/* + * Isolate free pages onto a private freelist. Caller must hold zone->lock. + * If @strict is true, will abort returning 0 on any invalid PFNs or non-free + * pages inside of the pageblock (even though it may still end up isolating + * some pages). + */ +static unsigned long isolate_freepages_block(unsigned long blockpfn, + unsigned long end_pfn, + struct list_head *freelist, + bool strict) { - unsigned long zone_end_pfn, end_pfn; int nr_scanned = 0, total_isolated = 0; struct page *cursor; - /* Get the last PFN we should scan for free pages at */ - zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; - end_pfn = min(blockpfn + pageblock_nr_pages, zone_end_pfn); - - /* Find the first usable PFN in the block to initialse page cursor */ - for (; blockpfn < end_pfn; blockpfn++) { - if (pfn_valid_within(blockpfn)) - break; - } cursor = pfn_to_page(blockpfn); /* Isolate free pages. This assumes the block is valid */ @@ -79,15 +71,23 @@ static unsigned long isolate_freepages_block(struct zone *zone, int isolated, i; struct page *page = cursor; - if (!pfn_valid_within(blockpfn)) + if (!pfn_valid_within(blockpfn)) { + if (strict) + return 0; continue; + } nr_scanned++; - if (!PageBuddy(page)) + if (!PageBuddy(page)) { + if (strict) + return 0; continue; + } /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); + if (!isolated && strict) + return 0; total_isolated += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); @@ -105,114 +105,71 @@ static unsigned long isolate_freepages_block(struct zone *zone, return total_isolated; } -/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) -{ - - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) - return false; - - /* If the page is a large free page, then allow migration */ - if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; - - /* If the block is MIGRATE_MOVABLE, allow migration */ - if (migratetype == MIGRATE_MOVABLE) - return true; - - /* Otherwise skip the block */ - return false; -} - -/* - * Based on information in the current compact_control, find blocks - * suitable for isolating free pages from and then isolate them. +/** + * isolate_freepages_range() - isolate free pages. + * @start_pfn: The first PFN to start isolating. + * @end_pfn: The one-past-last PFN. + * + * Non-free pages, invalid PFNs, or zone boundaries within the + * [start_pfn, end_pfn) range are considered errors, cause function to + * undo its actions and return zero. + * + * Otherwise, function returns one-past-the-last PFN of isolated page + * (which may be greater then end_pfn if end fell in a middle of + * a free page). */ -static void isolate_freepages(struct zone *zone, - struct compact_control *cc) +unsigned long +isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn) { - struct page *page; - unsigned long high_pfn, low_pfn, pfn; - unsigned long flags; - int nr_freepages = cc->nr_freepages; - struct list_head *freelist = &cc->freepages; - - /* - * Initialise the free scanner. The starting point is where we last - * scanned from (or the end of the zone if starting). The low point - * is the end of the pageblock the migration scanner is using. - */ - pfn = cc->free_pfn; - low_pfn = cc->migrate_pfn + pageblock_nr_pages; + unsigned long isolated, pfn, block_end_pfn, flags; + struct zone *zone = NULL; + LIST_HEAD(freelist); - /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - /* - * Isolate free pages until enough are available to migrate the - * pages on cc->migratepages. We stop searching if the migrate - * and free page scanners meet or enough free pages are isolated. - */ - for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { - unsigned long isolated; + if (pfn_valid(start_pfn)) + zone = page_zone(pfn_to_page(start_pfn)); - if (!pfn_valid(pfn)) - continue; + for (pfn = start_pfn; pfn < end_pfn; pfn += isolated) { + if (!pfn_valid(pfn) || zone != page_zone(pfn_to_page(pfn))) + break; /* - * Check for overlapping nodes/zones. It's possible on some - * configurations to have a setup like - * node0 node1 node0 - * i.e. it's possible that all pages within a zones range of - * pages do not belong to a single zone. + * On subsequent iterations ALIGN() is actually not needed, + * but we keep it that we not to complicate the code. */ - page = pfn_to_page(pfn); - if (page_zone(page) != zone) - continue; + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); - /* Check the block is suitable for migration */ - if (!suitable_migration_target(page)) - continue; + spin_lock_irqsave(&zone->lock, flags); + isolated = isolate_freepages_block(pfn, block_end_pfn, + &freelist, true); + spin_unlock_irqrestore(&zone->lock, flags); /* - * Found a block suitable for isolating free pages from. Now - * we disabled interrupts, double check things are ok and - * isolate the pages. This is to minimise the time IRQs - * are disabled + * In strict mode, isolate_freepages_block() returns 0 if + * there are any holes in the block (ie. invalid PFNs or + * non-free pages). */ - isolated = 0; - spin_lock_irqsave(&zone->lock, flags); - if (suitable_migration_target(page)) { - isolated = isolate_freepages_block(zone, pfn, freelist); - nr_freepages += isolated; - } - spin_unlock_irqrestore(&zone->lock, flags); + if (!isolated) + break; /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator + * If we managed to isolate pages, it is always (1 << n) * + * pageblock_nr_pages for some non-negative n. (Max order + * page may span two pageblocks). */ - if (isolated) - high_pfn = max(high_pfn, pfn); } /* split_free_page does not map the pages */ - list_for_each_entry(page, freelist, lru) { - arch_alloc_page(page, 0); - kernel_map_pages(page, 1, 1); + map_pages(&freelist); + + if (pfn < end_pfn) { + /* Loop terminated early, cleanup. */ + release_freepages(&freelist); + return 0; } - cc->free_pfn = high_pfn; - cc->nr_freepages = nr_freepages; + /* We don't use freelists for anything. */ + return pfn; } /* Update the number of anon and file isolated pages in the zone */ @@ -243,38 +200,34 @@ static bool too_many_isolated(struct zone *zone) return isolated > (inactive + active) / 2; } -/* possible outcome of isolate_migratepages */ -typedef enum { - ISOLATE_ABORT, /* Abort compaction now */ - ISOLATE_NONE, /* No pages isolated, continue scanning */ - ISOLATE_SUCCESS, /* Pages isolated, migrate */ -} isolate_migrate_t; - -/* - * Isolate all pages that can be migrated from the block pointed to by - * the migrate scanner within compact_control. +/** + * isolate_migratepages_range() - isolate all migrate-able pages in range. + * @zone: Zone pages are in. + * @cc: Compaction control structure. + * @low_pfn: The first PFN of the range. + * @end_pfn: The one-past-the-last PFN of the range. + * + * Isolate all pages that can be migrated from the range specified by + * [low_pfn, end_pfn). Returns zero if there is a fatal signal + * pending), otherwise PFN of the first page that was not scanned + * (which may be both less, equal to or more then end_pfn). + * + * Assumes that cc->migratepages is empty and cc->nr_migratepages is + * zero. + * + * Apart from cc->migratepages and cc->nr_migratetypes this function + * does not modify any cc's fields, in particular it does not modify + * (or read for that matter) cc->migrate_pfn. */ -static isolate_migrate_t isolate_migratepages(struct zone *zone, - struct compact_control *cc) +unsigned long +isolate_migratepages_range(struct zone *zone, struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn) { - unsigned long low_pfn, end_pfn; unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE; - /* Do not scan outside zone boundaries */ - low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); - - /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); - - /* Do not cross the free scanner or scan within a memory hole */ - if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { - cc->migrate_pfn = end_pfn; - return ISOLATE_NONE; - } - /* * Ensure that there are not too many pages isolated from the LRU * list by either parallel reclaimers or compaction. If there are, @@ -283,12 +236,12 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ if (!cc->sync) - return ISOLATE_ABORT; + return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); if (fatal_signal_pending(current)) - return ISOLATE_ABORT; + return 0; } /* Time to isolate some pages for migration */ @@ -351,7 +304,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, */ pageblock_nr = low_pfn >> pageblock_order; if (!cc->sync && last_pageblock_nr != pageblock_nr && - get_pageblock_migratetype(page) != MIGRATE_MOVABLE) { + !migrate_async_suitable(get_pageblock_migratetype(page))) { low_pfn += pageblock_nr_pages; low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; last_pageblock_nr = pageblock_nr; @@ -396,11 +349,124 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, acct_isolated(zone, cc); spin_unlock_irq(&zone->lru_lock); - cc->migrate_pfn = low_pfn; trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); - return ISOLATE_SUCCESS; + return low_pfn; +} + +#endif /* CONFIG_COMPACTION || CONFIG_CMA */ +#ifdef CONFIG_COMPACTION + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct page *page) +{ + + int migratetype = get_pageblock_migratetype(page); + + /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ + if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) + return false; + + /* If the page is a large free page, then allow migration */ + if (PageBuddy(page) && page_order(page) >= pageblock_order) + return true; + + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ + if (migrate_async_suitable(migratetype)) + return true; + + /* Otherwise skip the block */ + return false; +} + +/* + * Based on information in the current compact_control, find blocks + * suitable for isolating free pages from and then isolate them. + */ +static void isolate_freepages(struct zone *zone, + struct compact_control *cc) +{ + struct page *page; + unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn; + unsigned long flags; + int nr_freepages = cc->nr_freepages; + struct list_head *freelist = &cc->freepages; + + /* + * Initialise the free scanner. The starting point is where we last + * scanned from (or the end of the zone if starting). The low point + * is the end of the pageblock the migration scanner is using. + */ + pfn = cc->free_pfn; + low_pfn = cc->migrate_pfn + pageblock_nr_pages; + + /* + * Take care that if the migration scanner is at the end of the zone + * that the free scanner does not accidentally move to the next zone + * in the next isolation cycle. + */ + high_pfn = min(low_pfn, pfn); + + zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + + /* + * Isolate free pages until enough are available to migrate the + * pages on cc->migratepages. We stop searching if the migrate + * and free page scanners meet or enough free pages are isolated. + */ + for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; + pfn -= pageblock_nr_pages) { + unsigned long isolated; + + if (!pfn_valid(pfn)) + continue; + + /* + * Check for overlapping nodes/zones. It's possible on some + * configurations to have a setup like + * node0 node1 node0 + * i.e. it's possible that all pages within a zones range of + * pages do not belong to a single zone. + */ + page = pfn_to_page(pfn); + if (page_zone(page) != zone) + continue; + + /* Check the block is suitable for migration */ + if (!suitable_migration_target(page)) + continue; + + /* + * Found a block suitable for isolating free pages from. Now + * we disabled interrupts, double check things are ok and + * isolate the pages. This is to minimise the time IRQs + * are disabled + */ + isolated = 0; + spin_lock_irqsave(&zone->lock, flags); + if (suitable_migration_target(page)) { + end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); + isolated = isolate_freepages_block(pfn, end_pfn, + freelist, false); + nr_freepages += isolated; + } + spin_unlock_irqrestore(&zone->lock, flags); + + /* + * Record the highest PFN we isolated pages from. When next + * looking for free pages, the search will restart here as + * page migration may have returned some pages to the allocator + */ + if (isolated) + high_pfn = max(high_pfn, pfn); + } + + /* split_free_page does not map the pages */ + map_pages(freelist); + + cc->free_pfn = high_pfn; + cc->nr_freepages = nr_freepages; } /* @@ -449,6 +515,44 @@ static void update_nr_listpages(struct compact_control *cc) cc->nr_freepages = nr_freepages; } +/* possible outcome of isolate_migratepages */ +typedef enum { + ISOLATE_ABORT, /* Abort compaction now */ + ISOLATE_NONE, /* No pages isolated, continue scanning */ + ISOLATE_SUCCESS, /* Pages isolated, migrate */ +} isolate_migrate_t; + +/* + * Isolate all pages that can be migrated from the block pointed to by + * the migrate scanner within compact_control. + */ +static isolate_migrate_t isolate_migratepages(struct zone *zone, + struct compact_control *cc) +{ + unsigned long low_pfn, end_pfn; + + /* Do not scan outside zone boundaries */ + low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); + + /* Only scan within a pageblock boundary */ + end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); + + /* Do not cross the free scanner or scan within a memory hole */ + if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { + cc->migrate_pfn = end_pfn; + return ISOLATE_NONE; + } + + /* Perform the isolation */ + low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn); + if (!low_pfn) + return ISOLATE_ABORT; + + cc->migrate_pfn = low_pfn; + + return ISOLATE_SUCCESS; +} + static int compact_finished(struct zone *zone, struct compact_control *cc) { @@ -795,3 +899,5 @@ void compaction_unregister_node(struct node *node) return device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ + +#endif /* CONFIG_COMPACTION */ diff --git a/mm/internal.h b/mm/internal.h index 2189af491783..aee4761cf9a9 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -100,6 +100,39 @@ extern void prep_compound_page(struct page *page, unsigned long order); extern bool is_free_buddy_page(struct page *page); #endif +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + +/* + * in mm/compaction.c + */ +/* + * compact_control is used to track pages being migrated and the free pages + * they are being migrated to during memory compaction. The free_pfn starts + * at the end of a zone and migrate_pfn begins at the start. Movable pages + * are moved to the end of a zone during a compaction run and the run + * completes when free_pfn <= migrate_pfn + */ +struct compact_control { + struct list_head freepages; /* List of free pages to migrate to */ + struct list_head migratepages; /* List of pages being migrated */ + unsigned long nr_freepages; /* Number of isolated free pages */ + unsigned long nr_migratepages; /* Number of pages to migrate */ + unsigned long free_pfn; /* isolate_freepages search base */ + unsigned long migrate_pfn; /* isolate_migratepages search base */ + bool sync; /* Synchronous migration */ + + int order; /* order a direct compactor needs */ + int migratetype; /* MOVABLE, RECLAIMABLE etc */ + struct zone *zone; +}; + +unsigned long +isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn); +unsigned long +isolate_migratepages_range(struct zone *zone, struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn); + +#endif /* * function for dealing with page's order in buddy system. diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 97cc2733551a..c99ad4e6b88c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1404,7 +1404,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) /* Not a free page */ ret = 1; } - unset_migratetype_isolate(p); + unset_migratetype_isolate(p, MIGRATE_MOVABLE); unlock_memory_hotplug(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6629fafd6ce4..fc898cb4fe8f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -891,7 +891,7 @@ static int __ref offline_pages(unsigned long start_pfn, nr_pages = end_pfn - start_pfn; /* set above range as isolated */ - ret = start_isolate_page_range(start_pfn, end_pfn); + ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); if (ret) goto out; @@ -956,7 +956,7 @@ repeat: We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); /* reset pagetype flags and makes migrate type to be MOVABLE */ - undo_isolate_page_range(start_pfn, end_pfn); + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); /* removal success */ zone->present_pages -= offlined_pages; zone->zone_pgdat->node_present_pages -= offlined_pages; @@ -981,7 +981,7 @@ failed_removal: start_pfn, end_pfn); memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ - undo_isolate_page_range(start_pfn, end_pfn); + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); out: unlock_memory_hotplug(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 716061f48fd3..29392759f073 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -57,6 +57,7 @@ #include <linux/ftrace_event.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/migrate.h> #include <linux/page-debug-flags.h> #include <asm/tlbflush.h> @@ -514,10 +515,10 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * free pages of length of (1 << order) and marked with _mapcount -2. Page's * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the - * other. That is, if we allocate a small block, and both were - * free, the remainder of the region must be split into blocks. + * other. That is, if we allocate a small block, and both were + * free, the remainder of the region must be split into blocks. * If a block is freed, and its buddy is also free, then this - * triggers coalescing into a block of larger size. + * triggers coalescing into a block of larger size. * * -- wli */ @@ -750,6 +751,24 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order) __free_pages(page, order); } +#ifdef CONFIG_CMA +/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */ +void __init init_cma_reserved_pageblock(struct page *page) +{ + unsigned i = pageblock_nr_pages; + struct page *p = page; + + do { + __ClearPageReserved(p); + set_page_count(p, 0); + } while (++p, --i); + + set_page_refcounted(page); + set_pageblock_migratetype(page, MIGRATE_CMA); + __free_pages(page, pageblock_order); + totalram_pages += pageblock_nr_pages; +} +#endif /* * The order of subdivision here is critical for the IO subsystem. @@ -875,11 +894,17 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted */ -static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = { - [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RESERVE] = { MIGRATE_RESERVE, MIGRATE_RESERVE, MIGRATE_RESERVE }, /* Never used */ +static int fallbacks[MIGRATE_TYPES][4] = { + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, +#ifdef CONFIG_CMA + [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, + [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ +#else + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, +#endif + [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ + [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ }; /* @@ -974,12 +999,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) /* Find the largest possible block of pages in the other list */ for (current_order = MAX_ORDER-1; current_order >= order; --current_order) { - for (i = 0; i < MIGRATE_TYPES - 1; i++) { + for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; /* MIGRATE_RESERVE handled later if necessary */ if (migratetype == MIGRATE_RESERVE) - continue; + break; area = &(zone->free_area[current_order]); if (list_empty(&area->free_list[migratetype])) @@ -994,11 +1019,18 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) * pages to the preferred allocation list. If falling * back for a reclaimable kernel allocation, be more * aggressive about taking ownership of free pages + * + * On the other hand, never change migration + * type of MIGRATE_CMA pageblocks nor move CMA + * pages on different free lists. We don't + * want unmovable pages to be allocated from + * MIGRATE_CMA areas. */ - if (unlikely(current_order >= (pageblock_order >> 1)) || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled) { - unsigned long pages; + if (!is_migrate_cma(migratetype) && + (unlikely(current_order >= pageblock_order / 2) || + start_migratetype == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled)) { + int pages; pages = move_freepages_block(zone, page, start_migratetype); @@ -1016,11 +1048,14 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) rmv_page_order(page); /* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order) + if (current_order >= pageblock_order && + !is_migrate_cma(migratetype)) change_pageblock_range(page, current_order, start_migratetype); - expand(zone, page, order, current_order, area, migratetype); + expand(zone, page, order, current_order, area, + is_migrate_cma(migratetype) + ? migratetype : start_migratetype); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, migratetype); @@ -1062,17 +1097,17 @@ retry_reserve: return page; } -/* +/* * Obtain a specified number of elements from the buddy allocator, all under * a single hold of the lock, for efficiency. Add them to the supplied list. * Returns the number of new pages which were placed at *list. */ -static int rmqueue_bulk(struct zone *zone, unsigned int order, +static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, int cold) { - int i; - + int mt = migratetype, i; + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype); @@ -1092,7 +1127,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, list_add(&page->lru, list); else list_add_tail(&page->lru, list); - set_page_private(page, migratetype); + if (IS_ENABLED(CONFIG_CMA)) { + mt = get_pageblock_migratetype(page); + if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE) + mt = migratetype; + } + set_page_private(page, mt); list = &page->lru; } __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); @@ -1372,8 +1412,12 @@ int split_free_page(struct page *page) if (order >= pageblock_order - 1) { struct page *endpage = page + (1 << order) - 1; - for (; page < endpage; page += pageblock_nr_pages) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); + for (; page < endpage; page += pageblock_nr_pages) { + int mt = get_pageblock_migratetype(page); + if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt)) + set_pageblock_migratetype(page, + MIGRATE_MOVABLE); + } } return 1 << order; @@ -2087,16 +2131,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, } #endif /* CONFIG_COMPACTION */ -/* The really slow allocator path where we enter direct reclaim */ -static inline struct page * -__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress) +/* Perform direct synchronous page reclaim */ +static int +__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, + nodemask_t *nodemask) { - struct page *page = NULL; struct reclaim_state reclaim_state; - bool drained = false; + int progress; cond_resched(); @@ -2107,7 +2148,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, reclaim_state.reclaimed_slab = 0; current->reclaim_state = &reclaim_state; - *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); @@ -2115,6 +2156,21 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, cond_resched(); + return progress; +} + +/* The really slow allocator path where we enter direct reclaim */ +static inline struct page * +__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + int migratetype, unsigned long *did_some_progress) +{ + struct page *page = NULL; + bool drained = false; + + *did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, + nodemask); if (unlikely(!(*did_some_progress))) return NULL; @@ -4302,7 +4358,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, init_waitqueue_head(&pgdat->kswapd_wait); pgdat->kswapd_max_order = 0; pgdat_page_cgroup_init(pgdat); - + for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize, memmap_pages; @@ -4977,14 +5033,7 @@ static void setup_per_zone_lowmem_reserve(void) calculate_totalreserve_pages(); } -/** - * setup_per_zone_wmarks - called when min_free_kbytes changes - * or when memory is hot-{added|removed} - * - * Ensures that the watermark[min,low,high] values for each zone are set - * correctly with respect to min_free_kbytes. - */ -void setup_per_zone_wmarks(void) +static void __setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; @@ -5031,6 +5080,11 @@ void setup_per_zone_wmarks(void) zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); + + zone->watermark[WMARK_MIN] += cma_wmark_pages(zone); + zone->watermark[WMARK_LOW] += cma_wmark_pages(zone); + zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone); + setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -5039,6 +5093,20 @@ void setup_per_zone_wmarks(void) calculate_totalreserve_pages(); } +/** + * setup_per_zone_wmarks - called when min_free_kbytes changes + * or when memory is hot-{added|removed} + * + * Ensures that the watermark[min,low,high] values for each zone are set + * correctly with respect to min_free_kbytes. + */ +void setup_per_zone_wmarks(void) +{ + mutex_lock(&zonelists_mutex); + __setup_per_zone_wmarks(); + mutex_unlock(&zonelists_mutex); +} + /* * The inactive anon list should be small enough that the VM never has to * do too much work, but large enough that each inactive page has a chance @@ -5413,14 +5481,16 @@ static int __count_immobile_pages(struct zone *zone, struct page *page, int count) { unsigned long pfn, iter, found; + int mt; + /* * For avoiding noise data, lru_add_drain_all() should be called * If ZONE_MOVABLE, the zone never contains immobile pages */ if (zone_idx(zone) == ZONE_MOVABLE) return true; - - if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE) + mt = get_pageblock_migratetype(page); + if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) return true; pfn = page_to_pfn(page); @@ -5537,7 +5607,7 @@ out: return ret; } -void unset_migratetype_isolate(struct page *page) +void unset_migratetype_isolate(struct page *page, unsigned migratetype) { struct zone *zone; unsigned long flags; @@ -5545,12 +5615,259 @@ void unset_migratetype_isolate(struct page *page) spin_lock_irqsave(&zone->lock, flags); if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) goto out; - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(zone, page, MIGRATE_MOVABLE); + set_pageblock_migratetype(page, migratetype); + move_freepages_block(zone, page, migratetype); out: spin_unlock_irqrestore(&zone->lock, flags); } +#ifdef CONFIG_CMA + +static unsigned long pfn_max_align_down(unsigned long pfn) +{ + return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages) - 1); +} + +static unsigned long pfn_max_align_up(unsigned long pfn) +{ + return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES, + pageblock_nr_pages)); +} + +static struct page * +__alloc_contig_migrate_alloc(struct page *page, unsigned long private, + int **resultp) +{ + return alloc_page(GFP_HIGHUSER_MOVABLE); +} + +/* [start, end) must belong to a single zone. */ +static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) +{ + /* This function is based on compact_zone() from compaction.c. */ + + unsigned long pfn = start; + unsigned int tries = 0; + int ret = 0; + + struct compact_control cc = { + .nr_migratepages = 0, + .order = -1, + .zone = page_zone(pfn_to_page(start)), + .sync = true, + }; + INIT_LIST_HEAD(&cc.migratepages); + + migrate_prep_local(); + + while (pfn < end || !list_empty(&cc.migratepages)) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + + if (list_empty(&cc.migratepages)) { + cc.nr_migratepages = 0; + pfn = isolate_migratepages_range(cc.zone, &cc, + pfn, end); + if (!pfn) { + ret = -EINTR; + break; + } + tries = 0; + } else if (++tries == 5) { + ret = ret < 0 ? ret : -EBUSY; + break; + } + + ret = migrate_pages(&cc.migratepages, + __alloc_contig_migrate_alloc, + 0, false, true); + } + + putback_lru_pages(&cc.migratepages); + return ret > 0 ? 0 : ret; +} + +/* + * Update zone's cma pages counter used for watermark level calculation. + */ +static inline void __update_cma_watermarks(struct zone *zone, int count) +{ + unsigned long flags; + spin_lock_irqsave(&zone->lock, flags); + zone->min_cma_pages += count; + spin_unlock_irqrestore(&zone->lock, flags); + setup_per_zone_wmarks(); +} + +/* + * Trigger memory pressure bump to reclaim some pages in order to be able to + * allocate 'count' pages in single page units. Does similar work as + *__alloc_pages_slowpath() function. + */ +static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count) +{ + enum zone_type high_zoneidx = gfp_zone(gfp_mask); + struct zonelist *zonelist = node_zonelist(0, gfp_mask); + int did_some_progress = 0; + int order = 1; + + /* + * Increase level of watermarks to force kswapd do his job + * to stabilise at new watermark level. + */ + __update_cma_watermarks(zone, count); + + /* Obey watermarks as if the page was being allocated */ + while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) { + wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone)); + + did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, + NULL); + if (!did_some_progress) { + /* Exhausted what can be done so it's blamo time */ + out_of_memory(zonelist, gfp_mask, order, NULL, false); + } + } + + /* Restore original watermark levels. */ + __update_cma_watermarks(zone, -count); + + return count; +} + +/** + * alloc_contig_range() -- tries to allocate given range of pages + * @start: start PFN to allocate + * @end: one-past-the-last PFN to allocate + * @migratetype: migratetype of the underlaying pageblocks (either + * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks + * in range must have the same migratetype and it must + * be either of the two. + * + * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES + * aligned, however it's the caller's responsibility to guarantee that + * we are the only thread that changes migrate type of pageblocks the + * pages fall in. + * + * The PFN range must belong to a single zone. + * + * Returns zero on success or negative error code. On success all + * pages which PFN is in [start, end) are allocated for the caller and + * need to be freed with free_contig_range(). + */ +int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype) +{ + struct zone *zone = page_zone(pfn_to_page(start)); + unsigned long outer_start, outer_end; + int ret = 0, order; + + /* + * What we do here is we mark all pageblocks in range as + * MIGRATE_ISOLATE. Because pageblock and max order pages may + * have different sizes, and due to the way page allocator + * work, we align the range to biggest of the two pages so + * that page allocator won't try to merge buddies from + * different pageblocks and change MIGRATE_ISOLATE to some + * other migration type. + * + * Once the pageblocks are marked as MIGRATE_ISOLATE, we + * migrate the pages from an unaligned range (ie. pages that + * we are interested in). This will put all the pages in + * range back to page allocator as MIGRATE_ISOLATE. + * + * When this is done, we take the pages in range from page + * allocator removing them from the buddy system. This way + * page allocator will never consider using them. + * + * This lets us mark the pageblocks back as + * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the + * aligned range but not in the unaligned, original range are + * put back to page allocator so that buddy can use them. + */ + + ret = start_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype); + if (ret) + goto done; + + ret = __alloc_contig_migrate_range(start, end); + if (ret) + goto done; + + /* + * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * aligned blocks that are marked as MIGRATE_ISOLATE. What's + * more, all pages in [start, end) are free in page allocator. + * What we are going to do is to allocate all pages from + * [start, end) (that is remove them from page allocator). + * + * The only problem is that pages at the beginning and at the + * end of interesting range may be not aligned with pages that + * page allocator holds, ie. they can be part of higher order + * pages. Because of this, we reserve the bigger range and + * once this is done free the pages we are not interested in. + * + * We don't have to hold zone->lock here because the pages are + * isolated thus they won't get removed from buddy. + */ + + lru_add_drain_all(); + drain_all_pages(); + + order = 0; + outer_start = start; + while (!PageBuddy(pfn_to_page(outer_start))) { + if (++order >= MAX_ORDER) { + ret = -EBUSY; + goto done; + } + outer_start &= ~0UL << order; + } + + /* Make sure the range is really isolated. */ + if (test_pages_isolated(outer_start, end)) { + pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n", + outer_start, end); + ret = -EBUSY; + goto done; + } + + /* + * Reclaim enough pages to make sure that contiguous allocation + * will not starve the system. + */ + __reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start); + + /* Grab isolated pages from freelists. */ + outer_end = isolate_freepages_range(outer_start, end); + if (!outer_end) { + ret = -EBUSY; + goto done; + } + + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + +done: + undo_isolate_page_range(pfn_max_align_down(start), + pfn_max_align_up(end), migratetype); + return ret; +} + +void free_contig_range(unsigned long pfn, unsigned nr_pages) +{ + for (; nr_pages--; ++pfn) + __free_page(pfn_to_page(pfn)); +} +#endif + #ifdef CONFIG_MEMORY_HOTREMOVE /* * All pages in the range must be isolated before calling this. diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 4ae42bb40892..c9f04774f2b8 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -24,6 +24,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * to be MIGRATE_ISOLATE. * @start_pfn: The lower PFN of the range to be isolated. * @end_pfn: The upper PFN of the range to be isolated. + * @migratetype: migrate type to set in error recovery. * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the @@ -32,8 +33,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * start_pfn/end_pfn must be aligned to pageblock_order. * Returns 0 on success and -EBUSY if any part of range cannot be isolated. */ -int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) +int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) { unsigned long pfn; unsigned long undo_pfn; @@ -56,7 +57,7 @@ undo: for (pfn = start_pfn; pfn < undo_pfn; pfn += pageblock_nr_pages) - unset_migratetype_isolate(pfn_to_page(pfn)); + unset_migratetype_isolate(pfn_to_page(pfn), migratetype); return -EBUSY; } @@ -64,8 +65,8 @@ undo: /* * Make isolated pages available again. */ -int -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) +int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) { unsigned long pfn; struct page *page; @@ -77,7 +78,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) page = __first_valid_page(pfn, pageblock_nr_pages); if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE) continue; - unset_migratetype_isolate(page); + unset_migratetype_isolate(page, migratetype); } return 0; } @@ -86,7 +87,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) * all pages in [start_pfn...end_pfn) must be in the same zone. * zone->lock must be held before call this. * - * Returns 1 if all pages in the range is isolated. + * Returns 1 if all pages in the range are isolated. */ static int __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn) diff --git a/mm/vmstat.c b/mm/vmstat.c index 7db1b9bab492..0dad31dc1618 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -613,6 +613,9 @@ static char * const migratetype_names[MIGRATE_TYPES] = { "Reclaimable", "Movable", "Reserve", +#ifdef CONFIG_CMA + "CMA", +#endif "Isolate", }; |