All of lore.kernel.org
 help / color / mirror / Atom feed
From: Philipp Tomsich <philipp.tomsich@vrull.eu>
To: Heiko Stuebner <heiko@sntech.de>
Cc: palmer@dabbelt.com, paul.walmsley@sifive.com,
	aou@eecs.berkeley.edu,  linux-riscv@lists.infradead.org,
	linux-kernel@vger.kernel.org,  wefu@redhat.com,
	liush@allwinnertech.com, guoren@kernel.org,
	 atishp@atishpatra.org, anup@brainfault.org,
	drew@beagleboard.org, hch@lst.de,  arnd@arndb.de, wens@csie.org,
	maxime@cerno.tech, gfavor@ventanamicro.com,
	 andrea.mondelli@huawei.com, behrensj@mit.edu,
	xinhaoqu@huawei.com,  mick@ics.forth.gr,
	allen.baum@esperantotech.com, jscheid@ventanamicro.com,
	 rtrauben@gmail.com, samuel@sholland.org, cmuellner@linux.com,
	 Wei Wu <lazyparser@gmail.com>,
	Daniel Lustig <dlustig@nvidia.com>,
	 Bill Huffman <huffman@cadence.com>
Subject: Re: [PATCH v9 09/12] riscv: add RISC-V Svpbmt extension support
Date: Wed, 13 Apr 2022 11:11:09 +0200	[thread overview]
Message-ID: <CAAeLtUDkODLd55EWWKj8PS2sh_TjEO_LDSFik9djgb5BLDJMBw@mail.gmail.com> (raw)
In-Reply-To: <20220413030307.133807-10-heiko@sntech.de>

On Wed, 13 Apr 2022 at 05:03, Heiko Stuebner <heiko@sntech.de> wrote:
>
> Svpbmt (the S should be capitalized) is the
> "Supervisor-mode: page-based memory types" extension
> that specifies attributes for cacheability, idempotency
> and ordering.
>
> The relevant settings are done in special bits in PTEs:
>
> Here is the svpbmt PTE format:
> | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
>   N     MT     RSW    D   A   G   U   X   W   R   V
>         ^
>
> Of the Reserved bits [63:54] in a leaf PTE, the high bit is already
> allocated (as the N bit), so bits [62:61] are used as the MT (aka
> MemType) field. This field specifies one of three memory types that
> are close equivalents (or equivalent in effect) to the three main x86
> and ARMv8 memory types - as shown in the following table.
>
> RISC-V
> Encoding &
> MemType     RISC-V Description
> ----------  ------------------------------------------------
> 00 - PMA    Normal Cacheable, No change to implied PMA memory type
> 01 - NC     Non-cacheable, idempotent, weakly-ordered Main Memory
> 10 - IO     Non-cacheable, non-idempotent, strongly-ordered I/O memory
> 11 - Rsvd   Reserved for future standard use
>
> As the extension will not be present on all implementations,
> implement a method to handle cpufeatures via alternatives
> to not incur runtime penalties on cpu variants not supporting
> specific extensions and patch relevant code parts at runtime.
>
> Co-developed-by: Wei Fu <wefu@redhat.com>
> Signed-off-by: Wei Fu <wefu@redhat.com>
> Co-developed-by: Liu Shaohua <liush@allwinnertech.com>
> Signed-off-by: Liu Shaohua <liush@allwinnertech.com>
> Co-developed-by: Guo Ren <guoren@kernel.org>
> Signed-off-by: Guo Ren <guoren@kernel.org>
> [moved to use the alternatives mechanism]
> Signed-off-by: Heiko Stuebner <heiko@sntech.de>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Arnd Bergmann <arnd@arndb.de>
> Cc: Drew Fustini <drew@beagleboard.org>
> Cc: Wei Fu <wefu@redhat.com>
> Cc: Wei Wu <lazyparser@gmail.com>
> Cc: Chen-Yu Tsai <wens@csie.org>
> Cc: Maxime Ripard <maxime@cerno.tech>
> Cc: Daniel Lustig <dlustig@nvidia.com>
> Cc: Greg Favor <gfavor@ventanamicro.com>
> Cc: Andrea Mondelli <andrea.mondelli@huawei.com>
> Cc: Jonathan Behrens <behrensj@mit.edu>
> Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com>
> Cc: Bill Huffman <huffman@cadence.com>
> Cc: Nick Kossifidis <mick@ics.forth.gr>
> Cc: Allen Baum <allen.baum@esperantotech.com>
> Cc: Josh Scheid <jscheid@ventanamicro.com>
> Cc: Richard Trauben <rtrauben@gmail.com>

Reviewed-by: Philipp Tomsich <philipp.tomsich@vrull.eu>

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

WARNING: multiple messages have this Message-ID (diff)
From: Philipp Tomsich <philipp.tomsich@vrull.eu>
To: Heiko Stuebner <heiko@sntech.de>
Cc: palmer@dabbelt.com, paul.walmsley@sifive.com,
	aou@eecs.berkeley.edu, linux-riscv@lists.infradead.org,
	linux-kernel@vger.kernel.org, wefu@redhat.com,
	liush@allwinnertech.com, guoren@kernel.org,
	atishp@atishpatra.org, anup@brainfault.org, drew@beagleboard.org,
	hch@lst.de, arnd@arndb.de, wens@csie.org, maxime@cerno.tech,
	gfavor@ventanamicro.com, andrea.mondelli@huawei.com,
	behrensj@mit.edu, xinhaoqu@huawei.com, mick@ics.forth.gr,
	allen.baum@esperantotech.com, jscheid@ventanamicro.com,
	rtrauben@gmail.com, samuel@sholland.org, cmuellner@linux.com,
	Wei Wu <lazyparser@gmail.com>, Daniel Lustig <dlustig@nvidia.com>,
	Bill Huffman <huffman@cadence.com>
Subject: Re: [PATCH v9 09/12] riscv: add RISC-V Svpbmt extension support
Date: Wed, 13 Apr 2022 11:11:09 +0200	[thread overview]
Message-ID: <CAAeLtUDkODLd55EWWKj8PS2sh_TjEO_LDSFik9djgb5BLDJMBw@mail.gmail.com> (raw)
In-Reply-To: <20220413030307.133807-10-heiko@sntech.de>

On Wed, 13 Apr 2022 at 05:03, Heiko Stuebner <heiko@sntech.de> wrote:
>
> Svpbmt (the S should be capitalized) is the
> "Supervisor-mode: page-based memory types" extension
> that specifies attributes for cacheability, idempotency
> and ordering.
>
> The relevant settings are done in special bits in PTEs:
>
> Here is the svpbmt PTE format:
> | 63 | 62-61 | 60-8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0
>   N     MT     RSW    D   A   G   U   X   W   R   V
>         ^
>
> Of the Reserved bits [63:54] in a leaf PTE, the high bit is already
> allocated (as the N bit), so bits [62:61] are used as the MT (aka
> MemType) field. This field specifies one of three memory types that
> are close equivalents (or equivalent in effect) to the three main x86
> and ARMv8 memory types - as shown in the following table.
>
> RISC-V
> Encoding &
> MemType     RISC-V Description
> ----------  ------------------------------------------------
> 00 - PMA    Normal Cacheable, No change to implied PMA memory type
> 01 - NC     Non-cacheable, idempotent, weakly-ordered Main Memory
> 10 - IO     Non-cacheable, non-idempotent, strongly-ordered I/O memory
> 11 - Rsvd   Reserved for future standard use
>
> As the extension will not be present on all implementations,
> implement a method to handle cpufeatures via alternatives
> to not incur runtime penalties on cpu variants not supporting
> specific extensions and patch relevant code parts at runtime.
>
> Co-developed-by: Wei Fu <wefu@redhat.com>
> Signed-off-by: Wei Fu <wefu@redhat.com>
> Co-developed-by: Liu Shaohua <liush@allwinnertech.com>
> Signed-off-by: Liu Shaohua <liush@allwinnertech.com>
> Co-developed-by: Guo Ren <guoren@kernel.org>
> Signed-off-by: Guo Ren <guoren@kernel.org>
> [moved to use the alternatives mechanism]
> Signed-off-by: Heiko Stuebner <heiko@sntech.de>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Arnd Bergmann <arnd@arndb.de>
> Cc: Drew Fustini <drew@beagleboard.org>
> Cc: Wei Fu <wefu@redhat.com>
> Cc: Wei Wu <lazyparser@gmail.com>
> Cc: Chen-Yu Tsai <wens@csie.org>
> Cc: Maxime Ripard <maxime@cerno.tech>
> Cc: Daniel Lustig <dlustig@nvidia.com>
> Cc: Greg Favor <gfavor@ventanamicro.com>
> Cc: Andrea Mondelli <andrea.mondelli@huawei.com>
> Cc: Jonathan Behrens <behrensj@mit.edu>
> Cc: Xinhaoqu (Freddie) <xinhaoqu@huawei.com>
> Cc: Bill Huffman <huffman@cadence.com>
> Cc: Nick Kossifidis <mick@ics.forth.gr>
> Cc: Allen Baum <allen.baum@esperantotech.com>
> Cc: Josh Scheid <jscheid@ventanamicro.com>
> Cc: Richard Trauben <rtrauben@gmail.com>

Reviewed-by: Philipp Tomsich <philipp.tomsich@vrull.eu>

  reply	other threads:[~2022-04-13  9:11 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-13  3:02 [PATCH v9 00/12] riscv: support for Svpbmt and D1 memory types Heiko Stuebner
2022-04-13  3:02 ` Heiko Stuebner
2022-04-13  3:02 ` [PATCH v9 01/12] riscv: integrate alternatives better into the main architecture Heiko Stuebner
2022-04-13  3:02   ` Heiko Stuebner
2022-04-13  9:05   ` Philipp Tomsich
2022-04-13  9:05     ` Philipp Tomsich
2022-04-13  3:02 ` [PATCH v9 02/12] riscv: allow different stages with alternatives Heiko Stuebner
2022-04-13  3:02   ` Heiko Stuebner
2022-04-13  9:05   ` Philipp Tomsich
2022-04-13  9:05     ` Philipp Tomsich
2022-04-13  3:02 ` [PATCH v9 03/12] riscv: implement module alternatives Heiko Stuebner
2022-04-13  3:02   ` Heiko Stuebner
2022-04-13  9:07   ` Philipp Tomsich
2022-04-13  9:07     ` Philipp Tomsich
2022-04-13  3:02 ` [PATCH v9 04/12] riscv: implement ALTERNATIVE_2 macro Heiko Stuebner
2022-04-13  3:02   ` Heiko Stuebner
2022-04-13  9:08   ` Philipp Tomsich
2022-04-13  9:08     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 05/12] riscv: extend concatenated alternatives-lines to the same length Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  9:08   ` Philipp Tomsich
2022-04-13  9:08     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 06/12] riscv: prevent compressed instructions in alternatives Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  9:09   ` Philipp Tomsich
2022-04-13  9:09     ` Philipp Tomsich
2022-04-16  5:51   ` kernel test robot
2022-04-13  3:03 ` [PATCH v9 07/12] riscv: move boot alternatives to after fill_hwcap Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  5:46   ` Guo Ren
2022-04-13  5:46     ` Guo Ren
2022-04-13  9:15   ` Philipp Tomsich
2022-04-13  9:15     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 08/12] riscv: Fix accessing pfn bits in PTEs for non-32bit variants Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  9:09   ` Philipp Tomsich
2022-04-13  9:09     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 09/12] riscv: add RISC-V Svpbmt extension support Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  9:11   ` Philipp Tomsich [this message]
2022-04-13  9:11     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 10/12] riscv: remove FIXMAP_PAGE_IO and fall back to its default value Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  5:41   ` Guo Ren
2022-04-13  5:41     ` Guo Ren
2022-04-13  9:14   ` Philipp Tomsich
2022-04-13  9:14     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 11/12] riscv: don't use global static vars to store alternative data Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  5:43   ` Guo Ren
2022-04-13  5:43     ` Guo Ren
2022-04-13  9:16   ` Philipp Tomsich
2022-04-13  9:16     ` Philipp Tomsich
2022-04-13  3:03 ` [PATCH v9 12/12] riscv: add memory-type errata for T-Head Heiko Stuebner
2022-04-13  3:03   ` Heiko Stuebner
2022-04-13  5:41   ` Guo Ren
2022-04-13  5:41     ` Guo Ren
2022-04-13  9:17   ` Philipp Tomsich
2022-04-13  9:17     ` Philipp Tomsich

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=CAAeLtUDkODLd55EWWKj8PS2sh_TjEO_LDSFik9djgb5BLDJMBw@mail.gmail.com \
    --to=philipp.tomsich@vrull.eu \
    --cc=allen.baum@esperantotech.com \
    --cc=andrea.mondelli@huawei.com \
    --cc=anup@brainfault.org \
    --cc=aou@eecs.berkeley.edu \
    --cc=arnd@arndb.de \
    --cc=atishp@atishpatra.org \
    --cc=behrensj@mit.edu \
    --cc=cmuellner@linux.com \
    --cc=dlustig@nvidia.com \
    --cc=drew@beagleboard.org \
    --cc=gfavor@ventanamicro.com \
    --cc=guoren@kernel.org \
    --cc=hch@lst.de \
    --cc=heiko@sntech.de \
    --cc=huffman@cadence.com \
    --cc=jscheid@ventanamicro.com \
    --cc=lazyparser@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=liush@allwinnertech.com \
    --cc=maxime@cerno.tech \
    --cc=mick@ics.forth.gr \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=rtrauben@gmail.com \
    --cc=samuel@sholland.org \
    --cc=wefu@redhat.com \
    --cc=wens@csie.org \
    --cc=xinhaoqu@huawei.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.