[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9DD61F30A802C4429A01CA4200E302A7DCD48573@fmsmsx124.amr.corp.intel.com>
Date: Tue, 21 Apr 2020 00:25:14 +0000
From: "Saleem, Shiraz" <shiraz.saleem@...el.com>
To: Leon Romanovsky <leon@...nel.org>,
"Kirsher, Jeffrey T" <jeffrey.t.kirsher@...el.com>
CC: "gregkh@...uxfoundation.org" <gregkh@...uxfoundation.org>,
"jgg@...pe.ca" <jgg@...pe.ca>,
"Ismail, Mustafa" <mustafa.ismail@...el.com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>,
"nhorman@...hat.com" <nhorman@...hat.com>,
"sassmann@...hat.com" <sassmann@...hat.com>
Subject: RE: [RFC PATCH v5 04/16] RDMA/irdma: Add HMC backing store setup
functions
> Subject: Re: [RFC PATCH v5 04/16] RDMA/irdma: Add HMC backing store setup
> functions
>
> On Fri, Apr 17, 2020 at 10:12:39AM -0700, Jeff Kirsher wrote:
> > From: Mustafa Ismail <mustafa.ismail@...el.com>
> >
> > HW uses host memory as a backing store for a number of protocol
> > context objects and queue state tracking.
> > The Host Memory Cache (HMC) is a component responsible for managing
> > these objects stored in host memory.
> >
> > Add the functions and data structures to manage the allocation of
> > backing pages used by the HMC for the various objects
> >
> > Signed-off-by: Mustafa Ismail <mustafa.ismail@...el.com>
> > Signed-off-by: Shiraz Saleem <shiraz.saleem@...el.com>
[....]
> > diff --git a/drivers/infiniband/hw/irdma/hmc.h
> > b/drivers/infiniband/hw/irdma/hmc.h
> > new file mode 100644
> > index 000000000000..6f3fbf61f048
> > --- /dev/null
> > +++ b/drivers/infiniband/hw/irdma/hmc.h
> > @@ -0,0 +1,217 @@
> > +/* SPDX-License-Identifier: GPL-2.0 or Linux-OpenIB */
> > +/* Copyright (c) 2015 - 2019 Intel Corporation */ #ifndef IRDMA_HMC_H
> > +#define IRDMA_HMC_H
> > +
> > +#include "defs.h"
> > +
> > +#define IRDMA_HMC_MAX_BP_COUNT 512
> > +#define IRDMA_MAX_SD_ENTRIES 11
> > +#define IRDMA_HW_DBG_HMC_INVALID_BP_MARK 0xca
> > +#define IRDMA_HMC_INFO_SIGNATURE 0x484d5347
> > +#define IRDMA_HMC_PD_CNT_IN_SD 512
> > +#define IRDMA_HMC_DIRECT_BP_SIZE 0x200000
> > +#define IRDMA_HMC_MAX_SD_COUNT 8192
> > +#define IRDMA_HMC_PAGED_BP_SIZE 4096
> > +#define IRDMA_HMC_PD_BP_BUF_ALIGNMENT 4096
> > +#define IRDMA_FIRST_VF_FPM_ID 8
> > +#define FPM_MULTIPLIER 1024
> > +
> > +#define IRDMA_INC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt++)
> > +#define IRDMA_INC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt++)
> > +#define IRDMA_INC_BP_REFCNT(bp) ((bp)->ref_cnt++)
> > +
> > +#define IRDMA_DEC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt--)
> > +#define IRDMA_DEC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt--)
> > +#define IRDMA_DEC_BP_REFCNT(bp) ((bp)->ref_cnt--)
>
> It is bad for two reasons, first you obfuscated simple ++/-- and second you called
> it refcnt, while we have special type for that.
>
Agreed on all fronts. Will fix.
Powered by blists - more mailing lists