From: "Nicholas Piggin" <npiggin@gmail.com>
To: "Paul Mackerras" <paulus@ozlabs.org>, <linuxppc-dev@lists.ozlabs.org>
Subject: Re: [PATCH 4/5] powerpc: Define config option for processors without broadcast TLBIE
Date: Wed, 29 Jan 2025 16:14:25 +1000 [thread overview]
Message-ID: <D7EC3ZZ2E3YY.5ALSOA646CK4@gmail.com> (raw)
In-Reply-To: <Z5lf-OrrbRe5Q0O-@thinks.paulus.ozlabs.org>
On Wed Jan 29, 2025 at 8:53 AM AEST, Paul Mackerras wrote:
> Power ISA v3.1 implementations in the Linux Compliancy Subset and
> lower are not required to implement broadcast TLBIE, and in fact
> Microwatt doesn't. To avoid the need to specify "disable_tlbie" on
> the kernel command line on SMP Microwatt systems, this defines a
> config option that asserts that broadcast TLBIE should never be used
> (the kernel will instead use IPIs to trigger local TLBIEs on other
> CPUs when required).
>
> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
> ---
> arch/powerpc/mm/book3s64/pgtable.c | 10 ++++++++--
> arch/powerpc/platforms/Kconfig.cputype | 12 ++++++++++++
> arch/powerpc/platforms/microwatt/Kconfig | 1 +
> 3 files changed, 21 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
> index 374542528080..14ee96e2a581 100644
> --- a/arch/powerpc/mm/book3s64/pgtable.c
> +++ b/arch/powerpc/mm/book3s64/pgtable.c
> @@ -588,10 +588,16 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
> }
> #endif
>
> +#ifndef CONFIG_PPC_RADIX_NO_BROADCAST_TLBIE
Hate to bikeshed, but would it be annoying to make this an affirmative
option?
> +#define DEFAULT_TLBIE_ENABLE true
> +#else
> +#define DEFAULT_TLBIE_ENABLE false
> +#endif
> +
> /*
> * Does the CPU support tlbie?
> */
> -bool tlbie_capable __read_mostly = true;
> +bool tlbie_capable __read_mostly = DEFAULT_TLBIE_ENABLE;
> EXPORT_SYMBOL(tlbie_capable);
>
> /*
> @@ -599,7 +605,7 @@ EXPORT_SYMBOL(tlbie_capable);
> * address spaces? tlbie may still be used for nMMU accelerators, and for KVM
> * guest address spaces.
> */
> -bool tlbie_enabled __read_mostly = true;
> +bool tlbie_enabled __read_mostly = DEFAULT_TLBIE_ENABLE;
>
> static int __init setup_disable_tlbie(char *str)
> {
> diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
> index 1453ccc900c4..bd2a4e46ab34 100644
> --- a/arch/powerpc/platforms/Kconfig.cputype
> +++ b/arch/powerpc/platforms/Kconfig.cputype
> @@ -449,6 +449,18 @@ config PPC_RADIX_MMU_DEFAULT
>
> If you're unsure, say Y.
>
> +config PPC_RADIX_NO_BROADCAST_TLBIE
> + depends on PPC_RADIX_MMU
> + help
> + Power ISA v3.1 implementations in the Linux Compliancy Subset
> + and lower are not required to implement broadcast TLBIE
> + instructions, that is, a TLB invalidation instruction
> + performed on one CPU is not required to operate on the TLBs
> + in all CPUs in the system. Instead, the kernel does an IPI
> + to each relevant CPU to get it to do a local TLBIE instruction.
> + Select this option to force global invalidations to be done via
> + IPIs unconditionally.
... when using radix MMU. Hash MMU requires broadcast TLBIE.
Nitpicks aside, looks okay to me.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
> +
> config PPC_KERNEL_PREFIXED
> depends on PPC_HAVE_PREFIXED_SUPPORT
> depends on CC_HAS_PREFIXED
> diff --git a/arch/powerpc/platforms/microwatt/Kconfig b/arch/powerpc/platforms/microwatt/Kconfig
> index 5e41adadac1f..1d5cc1ae3636 100644
> --- a/arch/powerpc/platforms/microwatt/Kconfig
> +++ b/arch/powerpc/platforms/microwatt/Kconfig
> @@ -7,6 +7,7 @@ config PPC_MICROWATT
> select PPC_ICP_NATIVE
> select PPC_UDBG_16550
> select COMMON_CLK
> + select PPC_RADIX_NO_BROADCAST_TLBIE
> help
> This option enables support for FPGA-based Microwatt implementations.
>
next prev parent reply other threads:[~2025-01-29 6:14 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-28 22:49 [PATCH 0/5] Microwatt updates Paul Mackerras
2025-01-28 22:51 ` [PATCH 1/5] powerpc/microwatt: Select COMMON_CLK in order to get the clock framework Paul Mackerras
2025-01-29 5:57 ` Nicholas Piggin
2025-01-28 22:52 ` [PATCH 2/5] powerpc/microwatt: Device-tree updates Paul Mackerras
2025-01-29 6:36 ` Nicholas Piggin
2025-01-29 7:18 ` Paul Mackerras
2025-01-29 8:20 ` Nicholas Piggin
2025-01-31 17:03 ` Segher Boessenkool
2025-01-31 16:55 ` Segher Boessenkool
2025-01-31 16:53 ` Segher Boessenkool
2025-01-31 16:48 ` Segher Boessenkool
2025-01-28 22:52 ` [PATCH 3/5] powerpc/microwatt: Define an idle power-save function Paul Mackerras
2025-01-29 6:06 ` Nicholas Piggin
2025-01-29 6:49 ` Paul Mackerras
2025-01-31 16:32 ` Segher Boessenkool
2025-02-01 1:41 ` Paul Mackerras
2025-01-31 16:25 ` Segher Boessenkool
2025-01-28 22:53 ` [PATCH 4/5] powerpc: Define config option for processors without broadcast TLBIE Paul Mackerras
2025-01-29 6:14 ` Nicholas Piggin [this message]
2025-01-29 7:10 ` Paul Mackerras
2025-01-29 8:17 ` Nicholas Piggin
2025-01-31 17:30 ` Segher Boessenkool
2025-01-31 17:26 ` Segher Boessenkool
2025-01-28 22:55 ` [PATCH 5/5] powerpc/microwatt: Add SMP support Paul Mackerras
2025-01-29 6:21 ` Nicholas Piggin
2025-01-29 6:57 ` Paul Mackerras
2025-01-29 8:12 ` Nicholas Piggin
2025-01-31 1:27 ` Paul Mackerras
2025-01-29 12:50 ` Michael Ellerman
2025-01-31 1:34 ` Paul Mackerras
2025-01-31 16:13 ` [PATCH 0/5] Microwatt updates Segher Boessenkool
2025-02-01 1:22 ` Paul Mackerras
2025-03-02 10:13 ` Gabriel Paubert
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=D7EC3ZZ2E3YY.5ALSOA646CK4@gmail.com \
--to=npiggin@gmail.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=paulus@ozlabs.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).