linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mike Galbraith <efault@gmx.de>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andy Lutomirski <luto@amacapital.net>,
	Borislav Petkov <bp@suse.de>,
	Cyrill Gorcunov <gorcunov@openvz.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	linux-mm@kvack.org, Ingo Molnar <mingo@kernel.org>
Subject: Re: [PATCH 4.14 023/159] mm/sparsemem: Allocate mem_section at runtime for CONFIG_SPARSEMEM_EXTREME=y
Date: Sun, 07 Jan 2018 06:14:22 +0100	[thread overview]
Message-ID: <1515302062.6507.18.camel@gmx.de> (raw)
In-Reply-To: <20171222084625.007160464@linuxfoundation.org>

On Fri, 2017-12-22 at 09:45 +0100, Greg Kroah-Hartman wrote:
> 4.14-stable review patch.  If anyone has any objections, please let me know.

FYI, this broke kdump, or rather the makedumpfile part thereof.
 Forward looking wreckage is par for the kdump course, but...

> ------------------
> 
> From: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> 
> commit 83e3c48729d9ebb7af5a31a504f3fd6aff0348c4 upstream.
> 
> Size of the mem_section[] array depends on the size of the physical address space.
> 
> In preparation for boot-time switching between paging modes on x86-64
> we need to make the allocation of mem_section[] dynamic, because otherwise
> we waste a lot of RAM: with CONFIG_NODE_SHIFT=10, mem_section[] size is 32kB
> for 4-level paging and 2MB for 5-level paging mode.
> 
> The patch allocates the array on the first call to sparse_memory_present_with_active_regions().
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Andy Lutomirski <luto@amacapital.net>
> Cc: Borislav Petkov <bp@suse.de>
> Cc: Cyrill Gorcunov <gorcunov@openvz.org>
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: linux-mm@kvack.org
> Link: http://lkml.kernel.org/r/20170929140821.37654-2-kirill.shutemov@linux.intel.com
> Signed-off-by: Ingo Molnar <mingo@kernel.org>
> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> 
> ---
>  include/linux/mmzone.h |    6 +++++-
>  mm/page_alloc.c        |   10 ++++++++++
>  mm/sparse.c            |   17 +++++++++++------
>  3 files changed, 26 insertions(+), 7 deletions(-)
> 
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -1152,13 +1152,17 @@ struct mem_section {
>  #define SECTION_ROOT_MASK	(SECTIONS_PER_ROOT - 1)
>  
>  #ifdef CONFIG_SPARSEMEM_EXTREME
> -extern struct mem_section *mem_section[NR_SECTION_ROOTS];
> +extern struct mem_section **mem_section;
>  #else
>  extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
>  #endif
>  
>  static inline struct mem_section *__nr_to_section(unsigned long nr)
>  {
> +#ifdef CONFIG_SPARSEMEM_EXTREME
> +	if (!mem_section)
> +		return NULL;
> +#endif
>  	if (!mem_section[SECTION_NR_TO_ROOT(nr)])
>  		return NULL;
>  	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5651,6 +5651,16 @@ void __init sparse_memory_present_with_a
>  	unsigned long start_pfn, end_pfn;
>  	int i, this_nid;
>  
> +#ifdef CONFIG_SPARSEMEM_EXTREME
> +	if (!mem_section) {
> +		unsigned long size, align;
> +
> +		size = sizeof(struct mem_section) * NR_SECTION_ROOTS;
> +		align = 1 << (INTERNODE_CACHE_SHIFT);
> +		mem_section = memblock_virt_alloc(size, align);
> +	}
> +#endif
> +
>  	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
>  		memory_present(this_nid, start_pfn, end_pfn);
>  }
> --- a/mm/sparse.c
> +++ b/mm/sparse.c
> @@ -23,8 +23,7 @@
>   * 1) mem_section	- memory sections, mem_map's for valid memory
>   */
>  #ifdef CONFIG_SPARSEMEM_EXTREME
> -struct mem_section *mem_section[NR_SECTION_ROOTS]
> -	____cacheline_internodealigned_in_smp;
> +struct mem_section **mem_section;
>  #else
>  struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
>  	____cacheline_internodealigned_in_smp;
> @@ -101,7 +100,7 @@ static inline int sparse_index_init(unsi
>  int __section_nr(struct mem_section* ms)
>  {
>  	unsigned long root_nr;
> -	struct mem_section* root;
> +	struct mem_section *root = NULL;
>  
>  	for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
>  		root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
> @@ -112,7 +111,7 @@ int __section_nr(struct mem_section* ms)
>  		     break;
>  	}
>  
> -	VM_BUG_ON(root_nr == NR_SECTION_ROOTS);
> +	VM_BUG_ON(!root);
>  
>  	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
>  }
> @@ -330,11 +329,17 @@ again:
>  static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
>  {
>  	unsigned long usemap_snr, pgdat_snr;
> -	static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
> -	static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
> +	static unsigned long old_usemap_snr;
> +	static unsigned long old_pgdat_snr;
>  	struct pglist_data *pgdat = NODE_DATA(nid);
>  	int usemap_nid;
>  
> +	/* First call */
> +	if (!old_usemap_snr) {
> +		old_usemap_snr = NR_MEM_SECTIONS;
> +		old_pgdat_snr = NR_MEM_SECTIONS;
> +	}
> +
>  	usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
>  	pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
>  	if (usemap_snr == pgdat_snr)
> 
> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2018-01-07  5:14 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20171222084623.668990192@linuxfoundation.org>
2017-12-22  8:45 ` Greg Kroah-Hartman
2017-12-22 14:18   ` Dan Rue
2017-12-22 14:52     ` Naresh Kamboju
2017-12-22 15:12       ` Greg Kroah-Hartman
2017-12-22 15:03     ` Greg Kroah-Hartman
2018-01-07  5:14   ` Mike Galbraith [this message]
2018-01-07  9:11     ` Greg Kroah-Hartman
2018-01-07  9:21       ` Mike Galbraith
2018-01-07 10:18       ` Michal Hocko
2018-01-07 10:42         ` Greg Kroah-Hartman
2018-01-07 12:44         ` Mike Galbraith
2018-01-07 13:23           ` Michal Hocko
2018-01-08  7:53             ` Greg Kroah-Hartman
2018-01-08  8:15               ` Mike Galbraith
2018-01-08  8:33                 ` Greg Kroah-Hartman
2018-01-08  9:45                   ` Mike Galbraith
2018-01-08  8:47               ` Michal Hocko
2018-01-08  9:10                 ` Greg Kroah-Hartman
2018-01-08  9:27                   ` Greg Kroah-Hartman
2018-01-08 16:04     ` Ingo Molnar
2018-01-08 17:46       ` Kirill A. Shutemov
2018-01-09  0:13         ` Kirill A. Shutemov
2018-01-09  1:09           ` Dave Young
2018-01-09  5:41             ` Baoquan He
2018-01-09  7:24               ` Dave Young
2018-01-09  9:05                 ` Kirill A. Shutemov
2018-01-10  3:08                   ` Dave Young
2018-01-10 11:16                     ` Kirill A. Shutemov
2018-01-11  1:06                       ` Baoquan He
2018-01-12  0:55                       ` Dave Young
2018-01-15  5:57                         ` Omar Sandoval
2018-01-16  8:36                           ` Atsushi Kumagai
2018-01-09  3:44           ` Mike Galbraith
2018-02-07  9:25             ` Dou Liyang
2018-02-07 10:41               ` Kirill A. Shutemov
2018-02-07 10:45                 ` Mike Galbraith
2018-02-07 12:00                   ` Dou Liyang
2018-02-07 12:08                     ` Baoquan He
2018-02-07 12:17                       ` Dou Liyang
2018-02-07 12:27                         ` Baoquan He
2018-02-07 12:34                           ` Dou Liyang
2018-02-07 12:45                             ` Baoquan He
2018-02-08  1:14                               ` Dou Liyang
2018-02-08  1:23                                 ` Baoquan He
2018-02-08  1:44                                   ` Dou Liyang
2018-02-07 11:28               ` Baoquan He
2018-01-17  5:24           ` Baoquan He
2018-01-25 15:50             ` Kirill A. Shutemov
2018-01-26  2:48               ` Baoquan He
2017-12-22  8:45 ` [PATCH 4.14 024/159] x86/kasan: Use the same shadow offset for 4- and 5-level paging Greg Kroah-Hartman
2017-12-22  8:45 ` [PATCH 4.14 025/159] x86/xen: Provide pre-built page tables only for CONFIG_XEN_PV=y and CONFIG_XEN_PVH=y Greg Kroah-Hartman
2017-12-22  8:45 ` [PATCH 4.14 026/159] x86/xen: Drop 5-level paging support code from the XEN_PV code Greg Kroah-Hartman
2017-12-22  8:45 ` [PATCH 4.14 033/159] x86/boot: Relocate definition of the initial state of CR0 Greg Kroah-Hartman
2017-12-22  8:46 ` [PATCH 4.14 097/159] x86/paravirt: Dont patch flush_tlb_single Greg Kroah-Hartman

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=1515302062.6507.18.camel@gmx.de \
    --to=efault@gmx.de \
    --cc=akpm@linux-foundation.org \
    --cc=bp@suse.de \
    --cc=gorcunov@openvz.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@amacapital.net \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=stable@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.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