All of lore.kernel.org
 help / color / mirror / Atom feed
From: Anup Patel <apatel@ventanamicro.com>
To: "Heiko Stübner" <heiko@sntech.de>
Cc: Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Atish Patra <atishp@atishpatra.org>,
	Anup Patel <anup@brainfault.org>,
	linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
	Mayuresh Chitale <mchitale@ventanamicro.com>
Subject: Re: [PATCH v2 3/4] RISC-V: Implement arch specific PMEM APIs
Date: Sat, 3 Sep 2022 21:33:57 +0530	[thread overview]
Message-ID: <CAK9=C2XR+3bezgSAYsr08rZq=B9VLR0Aef3icBQRi9-FNyB8kQ@mail.gmail.com> (raw)
In-Reply-To: <13199249.VsHLxoZxqI@diego>

On Thu, Sep 1, 2022 at 9:08 PM Heiko Stübner <heiko@sntech.de> wrote:
>
> Hi Anup,
>
> Am Dienstag, 30. August 2022, 06:46:41 CEST schrieb Anup Patel:
> > The NVDIMM PMEM driver expects arch specific APIs for cache maintenance
> > and if arch does not provide these APIs then NVDIMM PMEM driver will
> > always use MEMREMAP_WT to map persistent memory which in-turn maps as
> > UC memory type defined by the RISC-V Svpbmt specification.
> >
> > Now that the Svpbmt and Zicbom support is available in RISC-V kernel,
> > we implement PMEM APIs using ALT_CMO_OP() macros so that the NVDIMM
> > PMEM driver can use MEMREMAP_WB to map persistent memory.
>
> Zicbom is detected at runtime, though that kconfig setting changes the
> behaviour for the memremap-type at compile-time. So what happens on
> systems not using zicbom (or another cmo-variant) ?

On a system without Zicbom (or some other cmo-variant), the PMEM read
will always work but PMEM writes will not be reliable.

Currently, the generic PMEM driver has no provision to allow arch code to
disable cacheable mapping at boot-time.

Maybe we can add WARN_ONCE() for the case when arch_xyz_pmem()
is called on a system not having Zicbom ?

Regards,
Anup

>
>
> Heiko
>
> > Co-developed-by: Mayuresh Chitale <mchitale@ventanamicro.com>
> > Signed-off-by: Mayuresh Chitale <mchitale@ventanamicro.com>
> > Signed-off-by: Anup Patel <apatel@ventanamicro.com>
> > ---
> >  arch/riscv/Kconfig     |  1 +
> >  arch/riscv/mm/Makefile |  1 +
> >  arch/riscv/mm/pmem.c   | 21 +++++++++++++++++++++
> >  3 files changed, 23 insertions(+)
> >  create mode 100644 arch/riscv/mm/pmem.c
> >
> > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > index 0ebd8da388d8..37d6370d29c3 100644
> > --- a/arch/riscv/Kconfig
> > +++ b/arch/riscv/Kconfig
> > @@ -25,6 +25,7 @@ config RISCV
> >       select ARCH_HAS_GIGANTIC_PAGE
> >       select ARCH_HAS_KCOV
> >       select ARCH_HAS_MMIOWB
> > +     select ARCH_HAS_PMEM_API
> >       select ARCH_HAS_PTE_SPECIAL
> >       select ARCH_HAS_SET_DIRECT_MAP if MMU
> >       select ARCH_HAS_SET_MEMORY if MMU
> > diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
> > index d76aabf4b94d..3b368e547f83 100644
> > --- a/arch/riscv/mm/Makefile
> > +++ b/arch/riscv/mm/Makefile
> > @@ -31,3 +31,4 @@ endif
> >
> >  obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
> >  obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
> > +obj-$(CONFIG_ARCH_HAS_PMEM_API) += pmem.o
> > diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c
> > new file mode 100644
> > index 000000000000..089df92ae876
> > --- /dev/null
> > +++ b/arch/riscv/mm/pmem.c
> > @@ -0,0 +1,21 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Copyright (C) 2022 Ventana Micro Systems Inc.
> > + */
> > +
> > +#include <linux/export.h>
> > +#include <linux/libnvdimm.h>
> > +
> > +#include <asm/cacheflush.h>
> > +
> > +void arch_wb_cache_pmem(void *addr, size_t size)
> > +{
> > +     ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size);
> > +}
> > +EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
> > +
> > +void arch_invalidate_pmem(void *addr, size_t size)
> > +{
> > +     ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size);
> > +}
> > +EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
> >
>
>
>
>

WARNING: multiple messages have this Message-ID (diff)
From: Anup Patel <apatel@ventanamicro.com>
To: "Heiko Stübner" <heiko@sntech.de>
Cc: Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	 Atish Patra <atishp@atishpatra.org>,
	Anup Patel <anup@brainfault.org>,
	 linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
	 Mayuresh Chitale <mchitale@ventanamicro.com>
Subject: Re: [PATCH v2 3/4] RISC-V: Implement arch specific PMEM APIs
Date: Sat, 3 Sep 2022 21:33:57 +0530	[thread overview]
Message-ID: <CAK9=C2XR+3bezgSAYsr08rZq=B9VLR0Aef3icBQRi9-FNyB8kQ@mail.gmail.com> (raw)
In-Reply-To: <13199249.VsHLxoZxqI@diego>

On Thu, Sep 1, 2022 at 9:08 PM Heiko Stübner <heiko@sntech.de> wrote:
>
> Hi Anup,
>
> Am Dienstag, 30. August 2022, 06:46:41 CEST schrieb Anup Patel:
> > The NVDIMM PMEM driver expects arch specific APIs for cache maintenance
> > and if arch does not provide these APIs then NVDIMM PMEM driver will
> > always use MEMREMAP_WT to map persistent memory which in-turn maps as
> > UC memory type defined by the RISC-V Svpbmt specification.
> >
> > Now that the Svpbmt and Zicbom support is available in RISC-V kernel,
> > we implement PMEM APIs using ALT_CMO_OP() macros so that the NVDIMM
> > PMEM driver can use MEMREMAP_WB to map persistent memory.
>
> Zicbom is detected at runtime, though that kconfig setting changes the
> behaviour for the memremap-type at compile-time. So what happens on
> systems not using zicbom (or another cmo-variant) ?

On a system without Zicbom (or some other cmo-variant), the PMEM read
will always work but PMEM writes will not be reliable.

Currently, the generic PMEM driver has no provision to allow arch code to
disable cacheable mapping at boot-time.

Maybe we can add WARN_ONCE() for the case when arch_xyz_pmem()
is called on a system not having Zicbom ?

Regards,
Anup

>
>
> Heiko
>
> > Co-developed-by: Mayuresh Chitale <mchitale@ventanamicro.com>
> > Signed-off-by: Mayuresh Chitale <mchitale@ventanamicro.com>
> > Signed-off-by: Anup Patel <apatel@ventanamicro.com>
> > ---
> >  arch/riscv/Kconfig     |  1 +
> >  arch/riscv/mm/Makefile |  1 +
> >  arch/riscv/mm/pmem.c   | 21 +++++++++++++++++++++
> >  3 files changed, 23 insertions(+)
> >  create mode 100644 arch/riscv/mm/pmem.c
> >
> > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > index 0ebd8da388d8..37d6370d29c3 100644
> > --- a/arch/riscv/Kconfig
> > +++ b/arch/riscv/Kconfig
> > @@ -25,6 +25,7 @@ config RISCV
> >       select ARCH_HAS_GIGANTIC_PAGE
> >       select ARCH_HAS_KCOV
> >       select ARCH_HAS_MMIOWB
> > +     select ARCH_HAS_PMEM_API
> >       select ARCH_HAS_PTE_SPECIAL
> >       select ARCH_HAS_SET_DIRECT_MAP if MMU
> >       select ARCH_HAS_SET_MEMORY if MMU
> > diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
> > index d76aabf4b94d..3b368e547f83 100644
> > --- a/arch/riscv/mm/Makefile
> > +++ b/arch/riscv/mm/Makefile
> > @@ -31,3 +31,4 @@ endif
> >
> >  obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
> >  obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
> > +obj-$(CONFIG_ARCH_HAS_PMEM_API) += pmem.o
> > diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c
> > new file mode 100644
> > index 000000000000..089df92ae876
> > --- /dev/null
> > +++ b/arch/riscv/mm/pmem.c
> > @@ -0,0 +1,21 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Copyright (C) 2022 Ventana Micro Systems Inc.
> > + */
> > +
> > +#include <linux/export.h>
> > +#include <linux/libnvdimm.h>
> > +
> > +#include <asm/cacheflush.h>
> > +
> > +void arch_wb_cache_pmem(void *addr, size_t size)
> > +{
> > +     ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size);
> > +}
> > +EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
> > +
> > +void arch_invalidate_pmem(void *addr, size_t size)
> > +{
> > +     ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size);
> > +}
> > +EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
> >
>
>
>
>

_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

  reply	other threads:[~2022-09-03 16:04 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-30  4:46 [PATCH v2 0/4] Add PMEM support for RISC-V Anup Patel
2022-08-30  4:46 ` Anup Patel
2022-08-30  4:46 ` [PATCH v2 1/4] RISC-V: Fix ioremap_cache() and ioremap_wc() for systems with Svpbmt Anup Patel
2022-08-30  4:46   ` Anup Patel
2022-09-01 15:25   ` Heiko Stübner
2022-09-01 15:25     ` Heiko Stübner
2022-09-01 16:07   ` Conor.Dooley
2022-09-01 16:07     ` Conor.Dooley
2022-09-09  8:10   ` Anup Patel
2022-09-09  8:10     ` Anup Patel
2022-09-16  2:24   ` Anup Patel
2022-09-16  2:24     ` Anup Patel
2022-09-22 16:35     ` Palmer Dabbelt
2022-09-22 16:35       ` Palmer Dabbelt
2022-09-23 10:35       ` Arnd Bergmann
2022-09-23 10:35         ` Arnd Bergmann
2022-09-23 10:45         ` Palmer Dabbelt
2022-09-23 10:45           ` Palmer Dabbelt
2022-09-28 12:14       ` Christoph Hellwig
2022-09-28 12:14         ` Christoph Hellwig
2022-10-07  3:50         ` Palmer Dabbelt
2022-10-07  3:50           ` Palmer Dabbelt
2022-10-07  5:34           ` Anup Patel
2022-10-07  5:34             ` Anup Patel
2022-08-30  4:46 ` [PATCH v2 2/4] RISC-V: Move riscv_init_cbom_blocksize() to cacheflush.c Anup Patel
2022-08-30  4:46   ` Anup Patel
2022-09-01 15:29   ` Heiko Stübner
2022-09-01 15:29     ` Heiko Stübner
2022-09-01 15:49     ` Conor.Dooley
2022-09-01 15:49       ` Conor.Dooley
2022-08-30  4:46 ` [PATCH v2 3/4] RISC-V: Implement arch specific PMEM APIs Anup Patel
2022-08-30  4:46   ` Anup Patel
2022-09-01 15:38   ` Heiko Stübner
2022-09-01 15:38     ` Heiko Stübner
2022-09-03 16:03     ` Anup Patel [this message]
2022-09-03 16:03       ` Anup Patel
2022-08-30  4:46 ` [PATCH v2 4/4] RISC-V: Enable PMEM drivers Anup Patel
2022-08-30  4:46   ` Anup Patel
2022-09-01 16:11   ` Conor.Dooley
2022-09-01 16:11     ` Conor.Dooley

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAK9=C2XR+3bezgSAYsr08rZq=B9VLR0Aef3icBQRi9-FNyB8kQ@mail.gmail.com' \
    --to=apatel@ventanamicro.com \
    --cc=anup@brainfault.org \
    --cc=atishp@atishpatra.org \
    --cc=heiko@sntech.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=mchitale@ventanamicro.com \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.