linux_dsm_epyc7002/drivers/gpu/drm/lima/lima_mmu.c
Qiang Yu a1d2a63399 drm/lima: driver for ARM Mali4xx GPUs
- 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/
2019-04-01 10:45:20 -07:00

143 lines
3.8 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 "lima_device.h"
#include "lima_mmu.h"
#include "lima_vm.h"
#include "lima_object.h"
#include "lima_regs.h"
#define mmu_write(reg, data) writel(data, ip->iomem + reg)
#define mmu_read(reg) readl(ip->iomem + reg)
#define lima_mmu_send_command(cmd, addr, val, cond) \
({ \
int __ret; \
\
mmu_write(LIMA_MMU_COMMAND, cmd); \
__ret = readl_poll_timeout(ip->iomem + (addr), val, \
cond, 0, 100); \
if (__ret) \
dev_err(dev->dev, \
"mmu command %x timeout\n", cmd); \
__ret; \
})
static irqreturn_t lima_mmu_irq_handler(int irq, void *data)
{
struct lima_ip *ip = data;
struct lima_device *dev = ip->dev;
u32 status = mmu_read(LIMA_MMU_INT_STATUS);
struct lima_sched_pipe *pipe;
/* for shared irq case */
if (!status)
return IRQ_NONE;
if (status & LIMA_MMU_INT_PAGE_FAULT) {
u32 fault = mmu_read(LIMA_MMU_PAGE_FAULT_ADDR);
dev_err(dev->dev, "mmu page fault at 0x%x from bus id %d of type %s on %s\n",
fault, LIMA_MMU_STATUS_BUS_ID(status),
status & LIMA_MMU_STATUS_PAGE_FAULT_IS_WRITE ? "write" : "read",
lima_ip_name(ip));
}
if (status & LIMA_MMU_INT_READ_BUS_ERROR)
dev_err(dev->dev, "mmu %s irq bus error\n", lima_ip_name(ip));
/* mask all interrupts before resume */
mmu_write(LIMA_MMU_INT_MASK, 0);
mmu_write(LIMA_MMU_INT_CLEAR, status);
pipe = dev->pipe + (ip->id == lima_ip_gpmmu ? lima_pipe_gp : lima_pipe_pp);
lima_sched_pipe_mmu_error(pipe);
return IRQ_HANDLED;
}
int lima_mmu_init(struct lima_ip *ip)
{
struct lima_device *dev = ip->dev;
int err;
u32 v;
if (ip->id == lima_ip_ppmmu_bcast)
return 0;
mmu_write(LIMA_MMU_DTE_ADDR, 0xCAFEBABE);
if (mmu_read(LIMA_MMU_DTE_ADDR) != 0xCAFEB000) {
dev_err(dev->dev, "mmu %s dte write test fail\n", lima_ip_name(ip));
return -EIO;
}
mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_HARD_RESET);
err = lima_mmu_send_command(LIMA_MMU_COMMAND_HARD_RESET,
LIMA_MMU_DTE_ADDR, v, v == 0);
if (err)
return err;
err = devm_request_irq(dev->dev, ip->irq, lima_mmu_irq_handler,
IRQF_SHARED, lima_ip_name(ip), ip);
if (err) {
dev_err(dev->dev, "mmu %s fail to request irq\n", lima_ip_name(ip));
return err;
}
mmu_write(LIMA_MMU_INT_MASK, LIMA_MMU_INT_PAGE_FAULT | LIMA_MMU_INT_READ_BUS_ERROR);
mmu_write(LIMA_MMU_DTE_ADDR, dev->empty_vm->pd.dma);
return lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_PAGING,
LIMA_MMU_STATUS, v,
v & LIMA_MMU_STATUS_PAGING_ENABLED);
}
void lima_mmu_fini(struct lima_ip *ip)
{
}
void lima_mmu_switch_vm(struct lima_ip *ip, struct lima_vm *vm)
{
struct lima_device *dev = ip->dev;
u32 v;
lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_STALL,
LIMA_MMU_STATUS, v,
v & LIMA_MMU_STATUS_STALL_ACTIVE);
if (vm)
mmu_write(LIMA_MMU_DTE_ADDR, vm->pd.dma);
/* flush the TLB */
mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_ZAP_CACHE);
lima_mmu_send_command(LIMA_MMU_COMMAND_DISABLE_STALL,
LIMA_MMU_STATUS, v,
!(v & LIMA_MMU_STATUS_STALL_ACTIVE));
}
void lima_mmu_page_fault_resume(struct lima_ip *ip)
{
struct lima_device *dev = ip->dev;
u32 status = mmu_read(LIMA_MMU_STATUS);
u32 v;
if (status & LIMA_MMU_STATUS_PAGE_FAULT_ACTIVE) {
dev_info(dev->dev, "mmu resume\n");
mmu_write(LIMA_MMU_INT_MASK, 0);
mmu_write(LIMA_MMU_DTE_ADDR, 0xCAFEBABE);
lima_mmu_send_command(LIMA_MMU_COMMAND_HARD_RESET,
LIMA_MMU_DTE_ADDR, v, v == 0);
mmu_write(LIMA_MMU_INT_MASK, LIMA_MMU_INT_PAGE_FAULT | LIMA_MMU_INT_READ_BUS_ERROR);
mmu_write(LIMA_MMU_DTE_ADDR, dev->empty_vm->pd.dma);
lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_PAGING,
LIMA_MMU_STATUS, v,
v & LIMA_MMU_STATUS_PAGING_ENABLED);
}
}