bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Song Liu <songliubraving@fb.com>
To: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"song@kernel.org" <song@kernel.org>,
	"bpf@vger.kernel.org" <bpf@vger.kernel.org>,
	"x86@kernel.org" <x86@kernel.org>,
	"daniel@iogearbox.net" <daniel@iogearbox.net>,
	"andrii@kernel.org" <andrii@kernel.org>,
	Kernel Team <Kernel-team@fb.com>,
	"pmenzel@molgen.mpg.de" <pmenzel@molgen.mpg.de>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"ast@kernel.org" <ast@kernel.org>
Subject: Re: [PATCH bpf 2/4] vmalloc: introduce HAVE_ARCH_HUGE_VMALLOC_FLAG
Date: Thu, 31 Mar 2022 00:26:07 +0000	[thread overview]
Message-ID: <6DC57B01-BB2A-49DF-A554-B6C8B025B562@fb.com> (raw)
In-Reply-To: <96db8116c0c2680cb5c3b45d19706c1cd064ab6e.camel@intel.com>



> On Mar 30, 2022, at 4:40 PM, Edgecombe, Rick P <rick.p.edgecombe@intel.com> wrote:
> 
> On Wed, 2022-03-30 at 15:56 -0700, Song Liu wrote:
>> With HAVE_ARCH_HUGE_VMALLOC_FLAG, users of __vmalloc_node_range()
>> could
>> use VM_TRY_HUGE_VMAP to (try to) allocate PMD_SIZE pages for
>> size >= PMD_SIZE cases. Similar to HAVE_ARCH_HUGE_VMALLOC, the use
>> can
>> disable huge page by specifying nohugeiomap in kernel command line.
>> 
>> The first user of VM_TRY_HUGE_VMAP will be bpf_prog_pack.
>> 
>> Signed-off-by: Song Liu <song@kernel.org>
>> ---
>> arch/Kconfig            |  9 +++++++++
>> include/linux/vmalloc.h |  9 +++++++--
>> mm/vmalloc.c            | 28 +++++++++++++++++++---------
>> 3 files changed, 35 insertions(+), 11 deletions(-)
>> 
>> diff --git a/arch/Kconfig b/arch/Kconfig
>> index 33e06966f248..23b6e92aebaa 100644
>> --- a/arch/Kconfig
>> +++ b/arch/Kconfig
>> @@ -864,6 +864,15 @@ config HAVE_ARCH_HUGE_VMALLOC
>> 	depends on HAVE_ARCH_HUGE_VMAP
>> 	bool
>> 
>> +#
>> +# HAVE_ARCH_HUGE_VMALLOC_FLAG allows users of __vmalloc_node_range
>> to allocate
>> +# huge page without HAVE_ARCH_HUGE_VMALLOC. To allocate huge pages,
>> the user
>> +# need to call __vmalloc_node_range with VM_TRY_HUGE_VMAP.
>> +#
>> +config HAVE_ARCH_HUGE_VMALLOC_FLAG
>> +	depends on HAVE_ARCH_HUGE_VMAP
>> +	bool
>> +
>> config ARCH_WANT_HUGE_PMD_SHARE
>> 	bool
>> 
>> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
>> index 3b1df7da402d..a48d0690b66f 100644
>> --- a/include/linux/vmalloc.h
>> +++ b/include/linux/vmalloc.h
>> @@ -35,6 +35,11 @@ struct notifier_block;		/* in
>> notifier.h */
>> #define VM_DEFER_KMEMLEAK	0
>> #endif
>> 
>> +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG
>> +#define VM_TRY_HUGE_VMAP	0x00001000	/* Allow for huge
>> pages on HAVE_ARCH_HUGE_VMALLOC_FLAG arch's */
>> +#else
>> +#define VM_TRY_HUGE_VMAP	0
>> +#endif
>> /* bits [20..32] reserved for arch specific ioremap internals */
>> 
>> /*
>> @@ -51,7 +56,7 @@ struct vm_struct {
>> 	unsigned long		size;
>> 	unsigned long		flags;
>> 	struct page		**pages;
>> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
>> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
>> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>> 	unsigned int		page_order;
>> #endif
>> 	unsigned int		nr_pages;
>> @@ -225,7 +230,7 @@ static inline bool is_vm_area_hugepages(const
>> void *addr)
>> 	 * prevents that. This only indicates the size of the physical
>> page
>> 	 * allocated in the vmalloc layer.
>> 	 */
>> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
>> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
>> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
> 
> Since HAVE_ARCH_HUGE_VMALLOC_FLAG depends on HAVE_ARCH_HUGE_VMAP, I
> don't think you need both here.

I think we still need this one (_VMALLOC || _VMALLOC_FLAG)? 
Note that this is not _VMAP || _VMALLOC_FLAG. 

> 
>> 	return find_vm_area(addr)->page_order > 0;
>> #else
>> 	return false;
>> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
>> index e163372d3967..179200bce285 100644
>> --- a/mm/vmalloc.c
>> +++ b/mm/vmalloc.c
>> @@ -46,7 +46,7 @@
>> #include "internal.h"
>> #include "pgalloc-track.h"
>> 
>> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
>> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
>> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
> 
> Same as above.

And this one could be just CONFIG_HAVE_ARCH_HUGE_VMAP?

> 
>> static unsigned int __ro_after_init ioremap_max_page_shift =
>> BITS_PER_LONG - 1;
>> 
>> static int __init set_nohugeiomap(char *str)
>> @@ -55,11 +55,11 @@ static int __init set_nohugeiomap(char *str)
>> 	return 0;
>> }
>> early_param("nohugeiomap", set_nohugeiomap);
>> -#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
>> +#else /* CONFIG_HAVE_ARCH_HUGE_VMAP ||
>> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG */
>> static const unsigned int ioremap_max_page_shift = PAGE_SHIFT;
>> -#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
>> +#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP ||
>> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG*/
> 
> Same here, and for the rest below. I think having
> HAVE_ARCH_HUGE_VMALLOC_FLAG depend on HAVE_ARCH_HUGE_VMAP like you did
> is nice because you don't need to special logic for most of the huge
> page parts. It should shrink this patch.
> 
>> 
>> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
>> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || 
>> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>> static bool __ro_after_init vmap_allow_huge = true;
>> 
>> static int __init set_nohugevmalloc(char *str)
>> @@ -582,8 +582,9 @@ int vmap_pages_range_noflush(unsigned long addr,
>> unsigned long end,
>> 
>> 	WARN_ON(page_shift < PAGE_SHIFT);
>> 
>> -	if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
>> -			page_shift == PAGE_SHIFT)
>> +	if ((!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) &&
>> +	     !IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG)) ||
>> +	    (page_shift == PAGE_SHIFT))
>> 		return vmap_small_pages_range_noflush(addr, end, prot,
>> pages);
>> 
>> 	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
>> @@ -2252,7 +2253,7 @@ static struct vm_struct *vmlist __initdata;
>> 
>> static inline unsigned int vm_area_page_order(struct vm_struct *vm)
>> {
>> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
>> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
>> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>> 	return vm->page_order;
>> #else
>> 	return 0;
>> @@ -2261,7 +2262,7 @@ static inline unsigned int
>> vm_area_page_order(struct vm_struct *vm)
>> 
>> static inline void set_vm_area_page_order(struct vm_struct *vm,
>> unsigned int order)
>> {
>> -#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
>> +#if (defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
>> defined(CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG))
>> 	vm->page_order = order;
>> #else
>> 	BUG_ON(order != 0);
>> @@ -3056,6 +3057,15 @@ static void *__vmalloc_area_node(struct
>> vm_struct *area, gfp_t gfp_mask,
>> 	return NULL;
>> }
>> 
>> +static bool vmalloc_try_huge_page(unsigned long vm_flags)
>> +{
>> +	if (!vmap_allow_huge || (vm_flags & VM_NO_HUGE_VMAP))
>> +		return false;
>> +
>> +	/* VM_TRY_HUGE_VMAP only works for
>> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG */
>> +	return vm_flags & VM_TRY_HUGE_VMAP;
>> +}
>> +
> 
> It won't return true in the case of just CONFIG_HAVE_ARCH_HUGE_VMALLOC
> and vmap_allow_huge. If you have CONFIG_HAVE_ARCH_HUGE_VMALLOC, but not
> CONFIG_HAVE_ARCH_HUGE_VMALLOC_FLAG like powerpc, it should still try
> huge pages like before.

Yeah, I missed this one.. Will fix in the next version. 

> 
>> /**
>>  * __vmalloc_node_range - allocate virtually contiguous memory
>>  * @size:		  allocation size
>> @@ -3106,7 +3116,7 @@ void *__vmalloc_node_range(unsigned long size,
>> unsigned long align,
>> 		return NULL;
>> 	}
>> 
>> -	if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
>> +	if (vmalloc_try_huge_page(vm_flags)) {
>> 		unsigned long size_per_node;
>> 
>> 		/*


  reply	other threads:[~2022-03-31  0:26 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20220330225642.1163897-1-song@kernel.org>
     [not found] ` <20220330225642.1163897-3-song@kernel.org>
2022-03-30 23:40   ` [PATCH bpf 2/4] vmalloc: introduce HAVE_ARCH_HUGE_VMALLOC_FLAG Edgecombe, Rick P
2022-03-31  0:26     ` Song Liu [this message]
     [not found] ` <20220330225642.1163897-2-song@kernel.org>
2022-03-30 23:47   ` [PATCH bpf 1/4] x86: disable HAVE_ARCH_HUGE_VMALLOC Thomas Gleixner
     [not found] ` <20220330225642.1163897-4-song@kernel.org>
2022-03-30 23:54   ` [PATCH bpf 3/4] x86: select HAVE_ARCH_HUGE_VMALLOC_FLAG for X86_64 Thomas Gleixner
2022-03-31  0:30     ` Song Liu
     [not found] ` <20220330225642.1163897-5-song@kernel.org>
2022-03-31  0:00   ` [PATCH bpf 4/4] bpf: use __vmalloc_node_range() with VM_TRY_HUGE_VMAP for bpf_prog_pack Thomas Gleixner
2022-03-31  0:31     ` Song Liu
2022-03-31  0:04 ` [PATCH bpf 0/4] introduce HAVE_ARCH_HUGE_VMALLOC_FLAG " Edgecombe, Rick P
2022-03-31  0:46   ` Song Liu
2022-03-31 16:19     ` Edgecombe, Rick P
2022-03-31  5:37 ` Christoph Hellwig
2022-03-31 23:59   ` Song Liu
2022-04-01 22:22     ` Song Liu
2022-04-05  7:07       ` Christoph Hellwig
2022-04-05 23:54         ` Song Liu
2022-04-07 19:57           ` Song Liu
2022-04-08 10:08             ` Claudio Imbrenda
2022-04-08 21:22               ` Song Liu

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=6DC57B01-BB2A-49DF-A554-B6C8B025B562@fb.com \
    --to=songliubraving@fb.com \
    --cc=Kernel-team@fb.com \
    --cc=akpm@linux-foundation.org \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=linux-mm@kvack.org \
    --cc=netdev@vger.kernel.org \
    --cc=pmenzel@molgen.mpg.de \
    --cc=rick.p.edgecombe@intel.com \
    --cc=song@kernel.org \
    --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).