From: Will Deacon <will@kernel.org>
To: Nicholas Piggin <npiggin@gmail.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
Catalin Marinas <catalin.marinas@arm.com>,
linux-arm-kernel@lists.infradead.org,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>
Subject: Re: [PATCH v2 4/4] mm/vmalloc: Hugepage vmalloc mappings
Date: Wed, 15 Apr 2020 11:47:56 +0100 [thread overview]
Message-ID: <20200415104755.GD12621@willie-the-truck> (raw)
In-Reply-To: <20200413125303.423864-5-npiggin@gmail.com>
Hi Nick,
On Mon, Apr 13, 2020 at 10:53:03PM +1000, Nicholas Piggin wrote:
> For platforms that define HAVE_ARCH_HUGE_VMAP and support PMD vmap mappings,
> have vmalloc attempt to allocate PMD-sized pages first, before falling back
> to small pages. Allocations which use something other than PAGE_KERNEL
> protections are not permitted to use huge pages yet, not all callers expect
> this (e.g., module allocations vs strict module rwx).
>
> This gives a 6x reduction in dTLB misses for a `git diff` (of linux), from
> 45600 to 6500 and a 2.2% reduction in cycles on a 2-node POWER9.
I wonder if it's worth extending vmap() to handle higher order pages in
a similar way? That might be helpful for tracing PMUs such as Arm SPE,
where the CPU streams tracing data out to a virtually addressed buffer
(see rb_alloc_aux_page()).
> This can result in more internal fragmentation and memory overhead for a
> given allocation. It can also cause greater NUMA unbalance on hashdist
> allocations.
>
> There may be other callers that expect small pages under vmalloc but use
> PAGE_KERNEL, I'm not sure if it's feasible to catch them all. An
> alternative would be a new function or flag which enables large mappings,
> and use that in callers.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> include/linux/vmalloc.h | 2 +
> mm/vmalloc.c | 135 +++++++++++++++++++++++++++++-----------
> 2 files changed, 102 insertions(+), 35 deletions(-)
>
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index 291313a7e663..853b82eac192 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -24,6 +24,7 @@ struct notifier_block; /* in notifier.h */
> #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */
> #define VM_NO_GUARD 0x00000040 /* don't add guard page */
> #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */
> +#define VM_HUGE_PAGES 0x00000100 /* may use huge pages */
Please can you add a check for this in the arm64 change_memory_common()
code? Other architectures might need something similar, but we need to
forbid changing memory attributes for portions of the huge page.
In general, I'm a bit wary of software table walkers tripping over this.
For example, I don't think apply_to_existing_page_range() can handle
huge mappings at all, but the one user (KASAN) only ever uses page mappings
so it's ok there.
> @@ -2325,9 +2356,11 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
> if (unlikely(!size))
> return NULL;
>
> - if (flags & VM_IOREMAP)
> - align = 1ul << clamp_t(int, get_count_order_long(size),
> - PAGE_SHIFT, IOREMAP_MAX_ORDER);
> + if (flags & VM_IOREMAP) {
> + align = max(align,
> + 1ul << clamp_t(int, get_count_order_long(size),
> + PAGE_SHIFT, IOREMAP_MAX_ORDER));
> + }
I don't follow this part. Please could you explain why you're potentially
aligning above IOREMAP_MAX_ORDER? It doesn't seem to follow from the rest
of the patch.
Cheers,
Will
next prev parent reply other threads:[~2020-04-15 10:48 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-13 12:52 [PATCH v2 0/4] huge vmalloc mappings Nicholas Piggin
2020-04-13 12:53 ` [PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings Nicholas Piggin
2020-04-13 13:34 ` Matthew Wilcox
2020-04-14 11:31 ` Nicholas Piggin
2020-04-13 12:53 ` [PATCH v2 2/4] mm: Move ioremap page table mapping function to mm/ Nicholas Piggin
2020-04-13 12:53 ` [PATCH v2 3/4] mm: HUGE_VMAP arch query functions cleanup Nicholas Piggin
2020-04-13 20:17 ` kbuild test robot
2020-04-13 20:29 ` kbuild test robot
2020-04-13 23:56 ` kbuild test robot
2020-04-13 23:56 ` [PATCH] mm: fix boolreturn.cocci warnings kbuild test robot
2020-04-13 12:53 ` [PATCH v2 4/4] mm/vmalloc: Hugepage vmalloc mappings Nicholas Piggin
2020-04-13 13:41 ` Matthew Wilcox
2020-04-14 11:39 ` Nicholas Piggin
2020-04-14 12:28 ` Christophe Leroy
2020-04-14 14:20 ` Matthew Wilcox
2020-04-14 7:23 ` Christoph Hellwig
2020-04-14 12:13 ` Nicholas Piggin
2020-04-14 13:02 ` Christoph Hellwig
2020-04-14 14:48 ` Nicholas Piggin
2020-04-15 10:47 ` Will Deacon [this message]
2020-04-16 2:38 ` Nicholas Piggin
2020-07-01 7:10 ` Zefan Li
2020-07-03 0:15 ` Nicholas Piggin
2020-07-20 2:02 ` Zefan Li
2020-07-20 2:49 ` Nicholas Piggin
2020-04-14 0:27 ` [PATCH v2 0/4] huge " David Rientjes
2020-04-14 12:23 ` Nicholas Piggin
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=20200415104755.GD12621@willie-the-truck \
--to=will@kernel.org \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=hpa@zytor.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mingo@redhat.com \
--cc=npiggin@gmail.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.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).