From a1d2a6339961efc078208dc3b2f006e9e9a8e119 Mon Sep 17 00:00:00 2001 From: Qiang Yu Date: Sat, 9 Mar 2019 20:20:12 +0800 Subject: drm/lima: driver for ARM Mali4xx GPUs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Mali 4xx GPUs have two kinds of processors GP and PP. GP is for OpenGL vertex shader processing and PP is for fragment shader processing. Each processor has its own MMU so prcessors work in virtual address space. - There's only one GP but multiple PP (max 4 for mali 400 and 8 for mali 450) in the same mali 4xx GPU. All PPs are grouped togather to handle a single fragment shader task divided by FB output tiled pixels. Mali 400 user space driver is responsible for assign target tiled pixels to each PP, but mali 450 has a HW module called DLBU to dynamically balance each PP's load. - User space driver allocate buffer object and map into GPU virtual address space, upload command stream and draw data with CPU mmap of the buffer object, then submit task to GP/PP with a register frame indicating where is the command stream and misc settings. - There's no command stream validation/relocation due to each user process has its own GPU virtual address space. GP/PP's MMU switch virtual address space before running two tasks from different user process. Error or evil user space code just get MMU fault or GP/PP error IRQ, then the HW/SW will be recovered. - Use GEM+shmem for MM. Currently just alloc and pin memory when gem object creation. GPU vm map of the buffer is also done in the alloc stage in kernel space. We may delay the memory allocation and real GPU vm map to command submission stage in the furture as improvement. - Use drm_sched for GPU task schedule. Each OpenGL context should have a lima context object in the kernel to distinguish tasks from different user. drm_sched gets task from each lima context in a fair way. mesa driver can be found here before upstreamed: https://gitlab.freedesktop.org/lima/mesa v8: - add comments for in_sync - fix ctx free miss mutex unlock v7: - remove lima_fence_ops with default value - move fence slab create to device probe - check pad ioctl args to be zero - add comments for user/kernel interface v6: - fix comments by checkpatch.pl v5: - export gp/pp version to userspace - rebase on drm-misc-next v4: - use get param interface to get info - separate context create/free ioctl - remove unused max sched task param - update copyright time - use xarray instead of idr - stop using drmP.h v3: - fix comments from kbuild robot - restrict supported arch to tested ones v2: - fix syscall argument check - fix job finish fence leak since kernel 5.0 - use drm syncobj to replace native fence - move buffer object GPU va map into kernel - reserve syscall argument space for future info - remove kernel gem modifier - switch TTM back to GEM+shmem MM - use time based io poll - use whole register name - adopt gem reservation obj integration - use drm_timeout_abs_to_jiffies Cc: Eric Anholt Cc: Rob Herring Cc: Christian König Cc: Daniel Vetter Cc: Alex Deucher Cc: Sam Ravnborg Cc: Rob Clark Cc: Dave Airlie Signed-off-by: Andreas Baierl Signed-off-by: Erico Nunes Signed-off-by: Heiko Stuebner Signed-off-by: Marek Vasut Signed-off-by: Neil Armstrong Signed-off-by: Simon Shields Signed-off-by: Vasily Khoruzhick Signed-off-by: Qiang Yu Reviewed-by: Eric Anholt Reviewed-by: Rob Herring Signed-off-by: Eric Anholt Link: https://patchwork.freedesktop.org/patch/291200/ --- drivers/gpu/drm/lima/lima_l2_cache.c | 80 ++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) create mode 100644 drivers/gpu/drm/lima/lima_l2_cache.c (limited to 'drivers/gpu/drm/lima/lima_l2_cache.c') diff --git a/drivers/gpu/drm/lima/lima_l2_cache.c b/drivers/gpu/drm/lima/lima_l2_cache.c new file mode 100644 index 000000000000..6873a7af5a5c --- /dev/null +++ b/drivers/gpu/drm/lima/lima_l2_cache.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu */ + +#include +#include + +#include "lima_device.h" +#include "lima_l2_cache.h" +#include "lima_regs.h" + +#define l2_cache_write(reg, data) writel(data, ip->iomem + reg) +#define l2_cache_read(reg) readl(ip->iomem + reg) + +static int lima_l2_cache_wait_idle(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + u32 v; + + err = readl_poll_timeout(ip->iomem + LIMA_L2_CACHE_STATUS, v, + !(v & LIMA_L2_CACHE_STATUS_COMMAND_BUSY), + 0, 1000); + if (err) { + dev_err(dev->dev, "l2 cache wait command timeout\n"); + return err; + } + return 0; +} + +int lima_l2_cache_flush(struct lima_ip *ip) +{ + int ret; + + spin_lock(&ip->data.lock); + l2_cache_write(LIMA_L2_CACHE_COMMAND, LIMA_L2_CACHE_COMMAND_CLEAR_ALL); + ret = lima_l2_cache_wait_idle(ip); + spin_unlock(&ip->data.lock); + return ret; +} + +int lima_l2_cache_init(struct lima_ip *ip) +{ + int i, err; + u32 size; + struct lima_device *dev = ip->dev; + + /* l2_cache2 only exists when one of PP4-7 present */ + if (ip->id == lima_ip_l2_cache2) { + for (i = lima_ip_pp4; i <= lima_ip_pp7; i++) { + if (dev->ip[i].present) + break; + } + if (i > lima_ip_pp7) + return -ENODEV; + } + + spin_lock_init(&ip->data.lock); + + size = l2_cache_read(LIMA_L2_CACHE_SIZE); + dev_info(dev->dev, "l2 cache %uK, %u-way, %ubyte cache line, %ubit external bus\n", + 1 << (((size >> 16) & 0xff) - 10), + 1 << ((size >> 8) & 0xff), + 1 << (size & 0xff), + 1 << ((size >> 24) & 0xff)); + + err = lima_l2_cache_flush(ip); + if (err) + return err; + + l2_cache_write(LIMA_L2_CACHE_ENABLE, + LIMA_L2_CACHE_ENABLE_ACCESS|LIMA_L2_CACHE_ENABLE_READ_ALLOCATE); + l2_cache_write(LIMA_L2_CACHE_MAX_READS, 0x1c); + + return 0; +} + +void lima_l2_cache_fini(struct lima_ip *ip) +{ + +} -- cgit v1.2.3