[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7e337655-a0ff-0c9f-f074-35ca61b0d934@amd.com>
Date: Sun, 6 Oct 2024 21:15:17 -0700
From: Lizhi Hou <lizhi.hou@....com>
To: Jeffrey Hugo <quic_jhugo@...cinc.com>, <ogabbay@...nel.org>,
<dri-devel@...ts.freedesktop.org>
CC: <linux-kernel@...r.kernel.org>, <min.ma@....com>, <max.zhen@....com>,
<sonal.santan@....com>, <king.tam@....com>, George Yang <George.Yang@....com>
Subject: Re: [PATCH V3 03/11] accel/amdxdna: Support hardware mailbox
On 10/4/24 10:34, Jeffrey Hugo wrote:
> On 9/11/2024 12:05 PM, Lizhi Hou wrote:
>> +struct create_ctx_req {
>> + __u32 aie_type;
>> + __u8 start_col;
>> + __u8 num_col;
>> + __u16 reserved;
>> + __u8 num_cq_pairs_requested;
>> + __u8 reserved1;
>> + __u16 pasid;
>> + __u32 pad[2];
>> + __u32 sec_comm_target_type;
>> + __u32 context_priority;
>
> Alignment
Will fix it.
>
>> +} __packed;
>> +
>> +struct create_ctx_resp {
>> + enum aie2_msg_status status;
>> + __u32 context_id;
>> + __u16 msix_id;
>> + __u8 num_cq_pairs_allocated;
>> + __u8 reserved;
>> + struct cq_pair cq_pair[MAX_CQ_PAIRS];
>> +} __packed;
>> +
>> +struct destroy_ctx_req {
>> + __u32 context_id;
>> +} __packed;
>> +
>> +struct destroy_ctx_resp {
>> + enum aie2_msg_status status;
>> +} __packed;
>> +
>> +struct execute_buffer_req {
>> + __u32 cu_idx;
>> + __u32 payload[19];
>> +} __packed;
>> +
>> +struct exec_dpu_req {
>> + __u64 inst_buf_addr;
>> + __u32 inst_size;
>> + __u32 inst_prop_cnt;
>> + __u32 cu_idx;
>
> Alignment
will fix it.
>
>> + __u32 payload[35];
>> +} __packed;
>> +
>> diff --git a/drivers/accel/amdxdna/aie2_psp.c
>> b/drivers/accel/amdxdna/aie2_psp.c
>> index c87ca322e206..ac5296f4f2ae 100644
>> --- a/drivers/accel/amdxdna/aie2_psp.c
>> +++ b/drivers/accel/amdxdna/aie2_psp.c
>> @@ -8,6 +8,8 @@
>> #include <drm/drm_print.h>
>> #include <linux/iopoll.h>
>> +#include "amdxdna_mailbox.h"
>> +#include "amdxdna_pci_drv.h"
>> #include "aie2_pci.h"
>
> Doesn't look like alphabetical order to me. Also similar instances in
> the *_regs.c files below
aie2 is one type of amdxdna hw platform. I would put amdxdna_*.h ahead
of aie_*.h. Otherwise I probably need to add include in aie2_*.h. Is it
acceptable reason? Or I must use alphabetical for #include?
Thanks,
Lizhi
>
>> #define PSP_STATUS_READY BIT(31)
>
>
Powered by blists - more mailing lists