linux/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
Felix Kuehling a2f14820e3 drm/amdgpu: Track pending retry faults in IH and VM (v2)
IH tracks pending retry faults in a hash table for fast lookup in
interrupt context. Each VM has a short FIFO of pending VM faults for
processing in a bottom half.

The IH prescreening stage adds retry faults and filters out repeated
retry interrupts to minimize the impact of interrupt storms.

It's the VM's responsibility remove pending faults once they are
handled. For now this is only done when the VM is destroyed.

v2:
- Made the hash table smaller and the FIFO longer. I never want the
  FIFO to fill up, because that would make prescreen take longer.
  128 pending page faults should be enough to keep migrations busy.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com> (v1)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-09-26 14:53:20 -04:00

126 lines
3.9 KiB
C

/*
* Copyright 2014 Advanced Micro Devices, 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 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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.
*
*/
#ifndef __AMDGPU_IH_H__
#define __AMDGPU_IH_H__
#include <linux/chash.h>
struct amdgpu_device;
/*
* vega10+ IH clients
*/
enum amdgpu_ih_clientid
{
AMDGPU_IH_CLIENTID_IH = 0x00,
AMDGPU_IH_CLIENTID_ACP = 0x01,
AMDGPU_IH_CLIENTID_ATHUB = 0x02,
AMDGPU_IH_CLIENTID_BIF = 0x03,
AMDGPU_IH_CLIENTID_DCE = 0x04,
AMDGPU_IH_CLIENTID_ISP = 0x05,
AMDGPU_IH_CLIENTID_PCIE0 = 0x06,
AMDGPU_IH_CLIENTID_RLC = 0x07,
AMDGPU_IH_CLIENTID_SDMA0 = 0x08,
AMDGPU_IH_CLIENTID_SDMA1 = 0x09,
AMDGPU_IH_CLIENTID_SE0SH = 0x0a,
AMDGPU_IH_CLIENTID_SE1SH = 0x0b,
AMDGPU_IH_CLIENTID_SE2SH = 0x0c,
AMDGPU_IH_CLIENTID_SE3SH = 0x0d,
AMDGPU_IH_CLIENTID_SYSHUB = 0x0e,
AMDGPU_IH_CLIENTID_THM = 0x0f,
AMDGPU_IH_CLIENTID_UVD = 0x10,
AMDGPU_IH_CLIENTID_VCE0 = 0x11,
AMDGPU_IH_CLIENTID_VMC = 0x12,
AMDGPU_IH_CLIENTID_XDMA = 0x13,
AMDGPU_IH_CLIENTID_GRBM_CP = 0x14,
AMDGPU_IH_CLIENTID_ATS = 0x15,
AMDGPU_IH_CLIENTID_ROM_SMUIO = 0x16,
AMDGPU_IH_CLIENTID_DF = 0x17,
AMDGPU_IH_CLIENTID_VCE1 = 0x18,
AMDGPU_IH_CLIENTID_PWR = 0x19,
AMDGPU_IH_CLIENTID_UTCL2 = 0x1b,
AMDGPU_IH_CLIENTID_EA = 0x1c,
AMDGPU_IH_CLIENTID_UTCL2LOG = 0x1d,
AMDGPU_IH_CLIENTID_MP0 = 0x1e,
AMDGPU_IH_CLIENTID_MP1 = 0x1f,
AMDGPU_IH_CLIENTID_MAX,
AMDGPU_IH_CLIENTID_VCN = AMDGPU_IH_CLIENTID_UVD
};
#define AMDGPU_IH_CLIENTID_LEGACY 0
#define AMDGPU_PAGEFAULT_HASH_BITS 8
struct amdgpu_retryfault_hashtable {
DECLARE_CHASH_TABLE(hash, AMDGPU_PAGEFAULT_HASH_BITS, 8, 0);
spinlock_t lock;
int count;
};
/*
* R6xx+ IH ring
*/
struct amdgpu_ih_ring {
struct amdgpu_bo *ring_obj;
volatile uint32_t *ring;
unsigned rptr;
unsigned ring_size;
uint64_t gpu_addr;
uint32_t ptr_mask;
atomic_t lock;
bool enabled;
unsigned wptr_offs;
unsigned rptr_offs;
u32 doorbell_index;
bool use_doorbell;
bool use_bus_addr;
dma_addr_t rb_dma_addr; /* only used when use_bus_addr = true */
struct amdgpu_retryfault_hashtable *faults;
};
#define AMDGPU_IH_SRC_DATA_MAX_SIZE_DW 4
struct amdgpu_iv_entry {
unsigned client_id;
unsigned src_id;
unsigned ring_id;
unsigned vm_id;
unsigned vm_id_src;
uint64_t timestamp;
unsigned timestamp_src;
unsigned pas_id;
unsigned pasid_src;
unsigned src_data[AMDGPU_IH_SRC_DATA_MAX_SIZE_DW];
const uint32_t *iv_entry;
};
int amdgpu_ih_ring_init(struct amdgpu_device *adev, unsigned ring_size,
bool use_bus_addr);
void amdgpu_ih_ring_fini(struct amdgpu_device *adev);
int amdgpu_ih_process(struct amdgpu_device *adev);
int amdgpu_ih_add_fault(struct amdgpu_device *adev, u64 key);
void amdgpu_ih_clear_fault(struct amdgpu_device *adev, u64 key);
#endif