From: Alistair Popple <alistair@popple.id.au>
To: linuxppc-dev@lists.ozlabs.org
Cc: Balbir Singh <bsingharora@gmail.com>,
Frederic Barrat <fbarrat@linux.vnet.ibm.com>,
clombard@linux.vnet.ibm.com, vaibhav@linux.vnet.ibm.com,
Aneesh Kumar KV <aneesh.kumar@linux.vnet.ibm.com>
Subject: Re: [PATCH v3 1/3] powerpc/mm: Add marker for contexts requiring global TLB invalidations
Date: Tue, 22 Aug 2017 13:11:47 +1000 [thread overview]
Message-ID: <2909611.I3R1v22EFs@new-mexico> (raw)
In-Reply-To: <CAKTCnzk-+UN56QJg9gtCP61nzFb1LL12mZ4gDvaNWLOL_cJT3Q@mail.gmail.com>
For what it's worth this worked fine when testing with the NPU as well.
Tested-by: Alistair Popple <alistair@popple.id.au>
On Thu, 3 Aug 2017 05:16:35 PM Balbir Singh wrote:
> On Thu, Aug 3, 2017 at 6:29 AM, Frederic Barrat
> <fbarrat@linux.vnet.ibm.com> wrote:
> > Introduce a new 'flags' attribute per context and define its first bit
> > to be a marker requiring all TLBIs for that context to be broadcasted
> > globally. Once that marker is set on a context, it cannot be removed.
> >
> > Such a marker is useful for memory contexts used by devices behind the
> > NPU and CAPP/PSL. The NPU and the PSL keep their own translation cache
> > so they need to see all the TLBIs for those contexts.
> >
> > Rename mm_is_thread_local() to mm_is_invalidation_local() to better
> > describe what it's doing.
>
> mm_is_tlb_local? Just nitpicking
>
> >
> > Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
> > ---
> > arch/powerpc/include/asm/book3s/64/mmu.h | 18 ++++++++++++++++++
> > arch/powerpc/include/asm/tlb.h | 27 +++++++++++++++++++++++----
> > arch/powerpc/mm/mmu_context_book3s64.c | 1 +
> > arch/powerpc/mm/tlb-radix.c | 8 ++++----
> > arch/powerpc/mm/tlb_hash64.c | 3 ++-
> > 5 files changed, 48 insertions(+), 9 deletions(-)
> >
> > diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
> > index 5b4023c616f7..03d4515ecfa6 100644
> > --- a/arch/powerpc/include/asm/book3s/64/mmu.h
> > +++ b/arch/powerpc/include/asm/book3s/64/mmu.h
> > @@ -79,8 +79,12 @@ struct spinlock;
> > /* Maximum possible number of NPUs in a system. */
> > #define NV_MAX_NPUS 8
> >
> > +/* Bits definition for the context flags */
> > +#define MM_GLOBAL_TLBIE 0 /* TLBI must be global */
> > +
> > typedef struct {
> > mm_context_id_t id;
> > + unsigned long flags;
> > u16 user_psize; /* page size index */
> >
> > /* NPU NMMU context */
> > @@ -165,5 +169,19 @@ extern void radix_init_pseries(void);
> > static inline void radix_init_pseries(void) { };
> > #endif
> >
> > +/*
> > + * Mark the memory context as requiring global TLBIs, when used by
> > + * GPUs or CAPI accelerators managing their own TLB or ERAT.
> > + */
> > +static inline void mm_context_set_global_tlbi(mm_context_t *ctx)
> > +{
> > + set_bit(MM_GLOBAL_TLBIE, &ctx->flags);
> > +}
> > +
> > +static inline bool mm_context_get_global_tlbi(mm_context_t *ctx)
> > +{
> > + return test_bit(MM_GLOBAL_TLBIE, &ctx->flags);
> > +}
> > +
> > #endif /* __ASSEMBLY__ */
> > #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */
> > diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
> > index 609557569f65..f06dcac82097 100644
> > --- a/arch/powerpc/include/asm/tlb.h
> > +++ b/arch/powerpc/include/asm/tlb.h
> > @@ -69,10 +69,29 @@ static inline int mm_is_core_local(struct mm_struct *mm)
> > topology_sibling_cpumask(smp_processor_id()));
> > }
> >
> > -static inline int mm_is_thread_local(struct mm_struct *mm)
> > +static inline int mm_is_invalidation_local(struct mm_struct *mm)
> > {
> > - return cpumask_equal(mm_cpumask(mm),
> > - cpumask_of(smp_processor_id()));
> > + int rc;
> > +
> > + rc = cpumask_equal(mm_cpumask(mm),
> > + cpumask_of(smp_processor_id()));
> > +#ifdef CONFIG_PPC_BOOK3S_64
> > + if (rc) {
> > + /*
> > + * Check if context requires global TLBI.
> > + *
> > + * We need to make sure the PTE update is happening
> > + * before reading the context global flag. Otherwise,
> > + * reading the flag may be re-ordered and happen
> > + * first, and we could end up in a situation where the
> > + * old PTE was seen by the NPU/PSL/device, but the
> > + * TLBI is local.
> > + */
> > + mb();
>
> smp_mb()?
>
> > + rc = !mm_context_get_global_tlbi(&mm->context);
> > + }
>
> Otherwise looks good!
>
> Acked-by: Balbir Singh <bsingharora@gmail.com>
next prev parent reply other threads:[~2017-08-22 3:11 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-02 20:29 [PATCH v3 0/3] powerpc/mm: Mark memory contexts requiring global TLBIs Frederic Barrat
2017-08-02 20:29 ` [PATCH v3 1/3] powerpc/mm: Add marker for contexts requiring global TLB invalidations Frederic Barrat
2017-08-03 7:16 ` Balbir Singh
2017-08-22 3:11 ` Alistair Popple [this message]
2017-08-02 20:29 ` [PATCH v3 2/3] cxl: Mark context requiring global TLBIs Frederic Barrat
2017-08-03 7:22 ` Balbir Singh
2017-08-22 3:09 ` Alistair Popple
2017-08-02 20:29 ` [PATCH v3 3/3] cxl: Add memory barrier to guarantee TLBI scope Frederic Barrat
2017-08-30 13:29 ` [PATCH v3 0/3] powerpc/mm: Mark memory contexts requiring global TLBIs Frederic Barrat
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=2909611.I3R1v22EFs@new-mexico \
--to=alistair@popple.id.au \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=bsingharora@gmail.com \
--cc=clombard@linux.vnet.ibm.com \
--cc=fbarrat@linux.vnet.ibm.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=vaibhav@linux.vnet.ibm.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox