linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Will Deacon <will.deacon@arm.com>
Cc: aneesh.kumar@linux.vnet.ibm.com, akpm@linux-foundation.org,
	npiggin@gmail.com, linux-arch@vger.kernel.org,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux@armlinux.org.uk, heiko.carstens@de.ibm.com,
	riel@surriel.com
Subject: Re: [PATCH 05/18] asm-generic/tlb: Provide generic tlb_flush
Date: Wed, 26 Sep 2018 20:07:27 +0200	[thread overview]
Message-ID: <20180926180727.GA7455@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20180926131141.GA12444@hirez.programming.kicks-ass.net>

On Wed, Sep 26, 2018 at 03:11:41PM +0200, Peter Zijlstra wrote:
> On Wed, Sep 26, 2018 at 01:53:35PM +0100, Will Deacon wrote:

> > > +static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
> > > +{
> > > +	if (tlb->fullmm)
> > > +		return;
> > > +
> > > +	/*
> > > +	 * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
> > > +	 * mips-4k) flush only large pages.
> > > +	 *
> > > +	 * flush_tlb_range() implementations that flush I-TLB also flush D-TLB
> > > +	 * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
> > > +	 * range.
> > > +	 *
> > > +	 * We rely on tlb_end_vma() to issue a flush, such that when we reset
> > > +	 * these values the batch is empty.
> > > +	 */
> > > +	tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
> > > +	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
> > 
> > Hmm, does this result in code generation for archs that don't care about the
> > vm_flags?
> 
> Yes. It's not much code, but if you deeply care we could frob things to
> get rid of it.

Something a little like the below... not particularly pretty but should
work.

--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -305,7 +305,8 @@ static inline void __tlb_reset_range(str
 #error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
 #endif
 
-#define tlb_flush tlb_flush
+#define generic_tlb_flush
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	if (tlb->fullmm || tlb->need_flush_all) {
@@ -391,12 +392,12 @@ static inline unsigned long tlb_get_unma
  * the vmas are adjusted to only cover the region to be torn down.
  */
 #ifndef tlb_start_vma
-#define tlb_start_vma tlb_start_vma
 static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	if (tlb->fullmm)
 		return;
 
+#ifdef generic_tlb_flush
 	/*
 	 * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
 	 * mips-4k) flush only large pages.
@@ -410,13 +411,13 @@ static inline void tlb_start_vma(struct
 	 */
 	tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
 	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
+#endif
 
 	flush_cache_range(vma, vma->vm_start, vma->vm_end);
 }
 #endif
 
 #ifndef tlb_end_vma
-#define tlb_end_vma tlb_end_vma
 static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	if (tlb->fullmm)

  parent reply	other threads:[~2018-09-26 18:07 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-26 11:36 [PATCH 00/18] my generic mmu_gather patches Peter Zijlstra
2018-09-26 11:36 ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 01/18] asm-generic/tlb: Provide a comment Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 02/18] asm-generic/tlb: Provide HAVE_MMU_GATHER_PAGE_SIZE Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 03/18] x86/mm: Page size aware flush_tlb_mm_range() Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 04/18] asm-generic/tlb: Provide generic VIPT cache flush Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 05/18] asm-generic/tlb: Provide generic tlb_flush Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 12:53   ` Will Deacon
2018-09-26 12:53     ` Will Deacon
2018-09-26 13:11     ` Peter Zijlstra
2018-09-26 13:11       ` Peter Zijlstra
2018-09-26 18:07       ` Peter Zijlstra [this message]
2018-09-26 18:07         ` Peter Zijlstra
2018-09-27 12:14         ` Will Deacon
2018-09-27 12:14           ` Will Deacon
2018-09-26 11:36 ` [PATCH 06/18] asm-generic/tlb: Conditionally provide tlb_migrate_finish() Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 12:53   ` Will Deacon
2018-09-26 12:53     ` Will Deacon
2018-09-26 11:36 ` [PATCH 07/18] asm-generic/tlb: Invert HAVE_RCU_TABLE_INVALIDATE Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 08/18] arm/tlb: Convert to generic mmu_gather Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 12:54   ` Will Deacon
2018-09-26 12:54     ` Will Deacon
2018-09-26 11:36 ` [PATCH 09/18] ia64/tlb: Conver " Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 10/18] sh/tlb: Convert SH " Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 11/18] um/tlb: Convert " Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 12/18] arch/tlb: Clean up simple architectures Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-10-03 17:03   ` Vineet Gupta
2018-10-03 17:03     ` Vineet Gupta
2018-10-11 15:04     ` Peter Zijlstra
2018-10-11 15:04       ` Peter Zijlstra
2018-10-12 19:40       ` Vineet Gupta
2018-10-12 19:40         ` Vineet Gupta
2018-10-15 14:14         ` Peter Zijlstra
2018-10-15 14:14           ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 13/18] asm-generic/tlb: Introduce HAVE_MMU_GATHER_NO_GATHER Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-12-11  5:43   ` Aneesh Kumar K.V
2018-12-11  5:43     ` Aneesh Kumar K.V
2018-09-26 11:36 ` [PATCH 14/18] s390/tlb: convert to generic mmu_gather Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 15/18] asm-generic/tlb: Remove arch_tlb*_mmu() Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 16/18] asm-generic/tlb: Remove HAVE_GENERIC_MMU_GATHER Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 17/18] asm-generic/tlb: Remove tlb_flush_mmu_free() Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 11:36 ` [PATCH 18/18] asm-generic/tlb: Remove tlb_table_flush() Peter Zijlstra
2018-09-26 11:36   ` Peter Zijlstra
2018-09-26 12:47 ` [PATCH 00/18] my generic mmu_gather patches Will Deacon
2018-09-26 12:47   ` Will Deacon
2018-12-11  5:50 ` Aneesh Kumar K.V
2018-12-11  5:50   ` Aneesh Kumar K.V

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=20180926180727.GA7455@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@armlinux.org.uk \
    --cc=npiggin@gmail.com \
    --cc=riel@surriel.com \
    --cc=will.deacon@arm.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;
as well as URLs for NNTP newsgroup(s).