mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 20:55:29 +07:00
a1d2a63399
- 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 <eric@anholt.net> Cc: Rob Herring <robh@kernel.org> Cc: Christian König <ckoenig.leichtzumerken@gmail.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Alex Deucher <alexdeucher@gmail.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Rob Clark <robdclark@gmail.com> Cc: Dave Airlie <airlied@gmail.com> Signed-off-by: Andreas Baierl <ichgeh@imkreisrum.de> Signed-off-by: Erico Nunes <nunes.erico@gmail.com> Signed-off-by: Heiko Stuebner <heiko@sntech.de> Signed-off-by: Marek Vasut <marex@denx.de> Signed-off-by: Neil Armstrong <narmstrong@baylibre.com> Signed-off-by: Simon Shields <simon@lineageos.org> Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com> Signed-off-by: Qiang Yu <yuq825@gmail.com> Reviewed-by: Eric Anholt <eric@anholt.net> Reviewed-by: Rob Herring <robh@kerrnel.org> Signed-off-by: Eric Anholt <eric@anholt.net> Link: https://patchwork.freedesktop.org/patch/291200/
284 lines
6.6 KiB
C
284 lines
6.6 KiB
C
// SPDX-License-Identifier: GPL-2.0 OR MIT
|
|
/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
|
|
|
|
#include <linux/interrupt.h>
|
|
#include <linux/iopoll.h>
|
|
#include <linux/device.h>
|
|
#include <linux/slab.h>
|
|
|
|
#include <drm/lima_drm.h>
|
|
|
|
#include "lima_device.h"
|
|
#include "lima_gp.h"
|
|
#include "lima_regs.h"
|
|
|
|
#define gp_write(reg, data) writel(data, ip->iomem + reg)
|
|
#define gp_read(reg) readl(ip->iomem + reg)
|
|
|
|
static irqreturn_t lima_gp_irq_handler(int irq, void *data)
|
|
{
|
|
struct lima_ip *ip = data;
|
|
struct lima_device *dev = ip->dev;
|
|
struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
|
|
u32 state = gp_read(LIMA_GP_INT_STAT);
|
|
u32 status = gp_read(LIMA_GP_STATUS);
|
|
bool done = false;
|
|
|
|
/* for shared irq case */
|
|
if (!state)
|
|
return IRQ_NONE;
|
|
|
|
if (state & LIMA_GP_IRQ_MASK_ERROR) {
|
|
dev_err(dev->dev, "gp error irq state=%x status=%x\n",
|
|
state, status);
|
|
|
|
/* mask all interrupts before hard reset */
|
|
gp_write(LIMA_GP_INT_MASK, 0);
|
|
|
|
pipe->error = true;
|
|
done = true;
|
|
} else {
|
|
bool valid = state & (LIMA_GP_IRQ_VS_END_CMD_LST |
|
|
LIMA_GP_IRQ_PLBU_END_CMD_LST);
|
|
bool active = status & (LIMA_GP_STATUS_VS_ACTIVE |
|
|
LIMA_GP_STATUS_PLBU_ACTIVE);
|
|
done = valid && !active;
|
|
}
|
|
|
|
gp_write(LIMA_GP_INT_CLEAR, state);
|
|
|
|
if (done)
|
|
lima_sched_pipe_task_done(pipe);
|
|
|
|
return IRQ_HANDLED;
|
|
}
|
|
|
|
static void lima_gp_soft_reset_async(struct lima_ip *ip)
|
|
{
|
|
if (ip->data.async_reset)
|
|
return;
|
|
|
|
gp_write(LIMA_GP_INT_MASK, 0);
|
|
gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_RESET_COMPLETED);
|
|
gp_write(LIMA_GP_CMD, LIMA_GP_CMD_SOFT_RESET);
|
|
ip->data.async_reset = true;
|
|
}
|
|
|
|
static int lima_gp_soft_reset_async_wait(struct lima_ip *ip)
|
|
{
|
|
struct lima_device *dev = ip->dev;
|
|
int err;
|
|
u32 v;
|
|
|
|
if (!ip->data.async_reset)
|
|
return 0;
|
|
|
|
err = readl_poll_timeout(ip->iomem + LIMA_GP_INT_RAWSTAT, v,
|
|
v & LIMA_GP_IRQ_RESET_COMPLETED,
|
|
0, 100);
|
|
if (err) {
|
|
dev_err(dev->dev, "gp soft reset time out\n");
|
|
return err;
|
|
}
|
|
|
|
gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_MASK_ALL);
|
|
gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED);
|
|
|
|
ip->data.async_reset = false;
|
|
return 0;
|
|
}
|
|
|
|
static int lima_gp_task_validate(struct lima_sched_pipe *pipe,
|
|
struct lima_sched_task *task)
|
|
{
|
|
struct drm_lima_gp_frame *frame = task->frame;
|
|
u32 *f = frame->frame;
|
|
(void)pipe;
|
|
|
|
if (f[LIMA_GP_VSCL_START_ADDR >> 2] >
|
|
f[LIMA_GP_VSCL_END_ADDR >> 2] ||
|
|
f[LIMA_GP_PLBUCL_START_ADDR >> 2] >
|
|
f[LIMA_GP_PLBUCL_END_ADDR >> 2] ||
|
|
f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2] >
|
|
f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2])
|
|
return -EINVAL;
|
|
|
|
if (f[LIMA_GP_VSCL_START_ADDR >> 2] ==
|
|
f[LIMA_GP_VSCL_END_ADDR >> 2] &&
|
|
f[LIMA_GP_PLBUCL_START_ADDR >> 2] ==
|
|
f[LIMA_GP_PLBUCL_END_ADDR >> 2])
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void lima_gp_task_run(struct lima_sched_pipe *pipe,
|
|
struct lima_sched_task *task)
|
|
{
|
|
struct lima_ip *ip = pipe->processor[0];
|
|
struct drm_lima_gp_frame *frame = task->frame;
|
|
u32 *f = frame->frame;
|
|
u32 cmd = 0;
|
|
int i;
|
|
|
|
if (f[LIMA_GP_VSCL_START_ADDR >> 2] !=
|
|
f[LIMA_GP_VSCL_END_ADDR >> 2])
|
|
cmd |= LIMA_GP_CMD_START_VS;
|
|
if (f[LIMA_GP_PLBUCL_START_ADDR >> 2] !=
|
|
f[LIMA_GP_PLBUCL_END_ADDR >> 2])
|
|
cmd |= LIMA_GP_CMD_START_PLBU;
|
|
|
|
/* before any hw ops, wait last success task async soft reset */
|
|
lima_gp_soft_reset_async_wait(ip);
|
|
|
|
for (i = 0; i < LIMA_GP_FRAME_REG_NUM; i++)
|
|
writel(f[i], ip->iomem + LIMA_GP_VSCL_START_ADDR + i * 4);
|
|
|
|
gp_write(LIMA_GP_CMD, LIMA_GP_CMD_UPDATE_PLBU_ALLOC);
|
|
gp_write(LIMA_GP_CMD, cmd);
|
|
}
|
|
|
|
static int lima_gp_hard_reset_poll(struct lima_ip *ip)
|
|
{
|
|
gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC01A0000);
|
|
return gp_read(LIMA_GP_PERF_CNT_0_LIMIT) == 0xC01A0000;
|
|
}
|
|
|
|
static int lima_gp_hard_reset(struct lima_ip *ip)
|
|
{
|
|
struct lima_device *dev = ip->dev;
|
|
int ret;
|
|
|
|
gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC0FFE000);
|
|
gp_write(LIMA_GP_INT_MASK, 0);
|
|
gp_write(LIMA_GP_CMD, LIMA_GP_CMD_RESET);
|
|
ret = lima_poll_timeout(ip, lima_gp_hard_reset_poll, 10, 100);
|
|
if (ret) {
|
|
dev_err(dev->dev, "gp hard reset timeout\n");
|
|
return ret;
|
|
}
|
|
|
|
gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0);
|
|
gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_MASK_ALL);
|
|
gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED);
|
|
return 0;
|
|
}
|
|
|
|
static void lima_gp_task_fini(struct lima_sched_pipe *pipe)
|
|
{
|
|
lima_gp_soft_reset_async(pipe->processor[0]);
|
|
}
|
|
|
|
static void lima_gp_task_error(struct lima_sched_pipe *pipe)
|
|
{
|
|
struct lima_ip *ip = pipe->processor[0];
|
|
|
|
dev_err(ip->dev->dev, "gp task error int_state=%x status=%x\n",
|
|
gp_read(LIMA_GP_INT_STAT), gp_read(LIMA_GP_STATUS));
|
|
|
|
lima_gp_hard_reset(ip);
|
|
}
|
|
|
|
static void lima_gp_task_mmu_error(struct lima_sched_pipe *pipe)
|
|
{
|
|
lima_sched_pipe_task_done(pipe);
|
|
}
|
|
|
|
static void lima_gp_print_version(struct lima_ip *ip)
|
|
{
|
|
u32 version, major, minor;
|
|
char *name;
|
|
|
|
version = gp_read(LIMA_GP_VERSION);
|
|
major = (version >> 8) & 0xFF;
|
|
minor = version & 0xFF;
|
|
switch (version >> 16) {
|
|
case 0xA07:
|
|
name = "mali200";
|
|
break;
|
|
case 0xC07:
|
|
name = "mali300";
|
|
break;
|
|
case 0xB07:
|
|
name = "mali400";
|
|
break;
|
|
case 0xD07:
|
|
name = "mali450";
|
|
break;
|
|
default:
|
|
name = "unknown";
|
|
break;
|
|
}
|
|
dev_info(ip->dev->dev, "%s - %s version major %d minor %d\n",
|
|
lima_ip_name(ip), name, major, minor);
|
|
}
|
|
|
|
static struct kmem_cache *lima_gp_task_slab;
|
|
static int lima_gp_task_slab_refcnt;
|
|
|
|
int lima_gp_init(struct lima_ip *ip)
|
|
{
|
|
struct lima_device *dev = ip->dev;
|
|
int err;
|
|
|
|
lima_gp_print_version(ip);
|
|
|
|
ip->data.async_reset = false;
|
|
lima_gp_soft_reset_async(ip);
|
|
err = lima_gp_soft_reset_async_wait(ip);
|
|
if (err)
|
|
return err;
|
|
|
|
err = devm_request_irq(dev->dev, ip->irq, lima_gp_irq_handler,
|
|
IRQF_SHARED, lima_ip_name(ip), ip);
|
|
if (err) {
|
|
dev_err(dev->dev, "gp %s fail to request irq\n",
|
|
lima_ip_name(ip));
|
|
return err;
|
|
}
|
|
|
|
dev->gp_version = gp_read(LIMA_GP_VERSION);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void lima_gp_fini(struct lima_ip *ip)
|
|
{
|
|
|
|
}
|
|
|
|
int lima_gp_pipe_init(struct lima_device *dev)
|
|
{
|
|
int frame_size = sizeof(struct drm_lima_gp_frame);
|
|
struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
|
|
|
|
if (!lima_gp_task_slab) {
|
|
lima_gp_task_slab = kmem_cache_create_usercopy(
|
|
"lima_gp_task", sizeof(struct lima_sched_task) + frame_size,
|
|
0, SLAB_HWCACHE_ALIGN, sizeof(struct lima_sched_task),
|
|
frame_size, NULL);
|
|
if (!lima_gp_task_slab)
|
|
return -ENOMEM;
|
|
}
|
|
lima_gp_task_slab_refcnt++;
|
|
|
|
pipe->frame_size = frame_size;
|
|
pipe->task_slab = lima_gp_task_slab;
|
|
|
|
pipe->task_validate = lima_gp_task_validate;
|
|
pipe->task_run = lima_gp_task_run;
|
|
pipe->task_fini = lima_gp_task_fini;
|
|
pipe->task_error = lima_gp_task_error;
|
|
pipe->task_mmu_error = lima_gp_task_mmu_error;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void lima_gp_pipe_fini(struct lima_device *dev)
|
|
{
|
|
if (!--lima_gp_task_slab_refcnt) {
|
|
kmem_cache_destroy(lima_gp_task_slab);
|
|
lima_gp_task_slab = NULL;
|
|
}
|
|
}
|