kernel-hardening.lists.openwall.com archive mirror
 help / color / mirror / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: Rick Edgecombe <rick.p.edgecombe@intel.com>
Cc: dave.hansen@intel.com, luto@kernel.org, peterz@infradead.org,
	x86@kernel.org, akpm@linux-foundation.org, keescook@chromium.org,
	shakeelb@google.com, vbabka@suse.cz, linux-mm@kvack.org,
	linux-hardening@vger.kernel.org,
	kernel-hardening@lists.openwall.com, ira.weiny@intel.com,
	dan.j.williams@intel.com, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH v2 11/19] mm/sparsemem: Use alloc_table() for table allocations
Date: Tue, 31 Aug 2021 11:55:33 +0300	[thread overview]
Message-ID: <YS3uhdT88XFvP9n3@kernel.org> (raw)
In-Reply-To: <20210830235927.6443-12-rick.p.edgecombe@intel.com>

On Mon, Aug 30, 2021 at 04:59:19PM -0700, Rick Edgecombe wrote:
> In order to support allocating PKS protected page tables for vmememap,
> create a new variant of alloc_table(), alloc_table_node() that allows for
> allocation of tables from a specific node. Use it when possible for
> allocating vmemmap tables.
> 
> vmemmap_alloc_block_zero() is currently only used to allocate page
> tables, so fold it into a new function, vmemem_alloc_table() that can
> be free to call alloc_table_node(). Since it is today only called with
> PAGE_SIZE size, drop the size argument.
> 
> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
> ---
>  arch/x86/mm/pgtable.c         | 10 +++++++---
>  include/asm-generic/pgalloc.h |  2 ++
>  include/linux/mm.h            |  5 +++++
>  mm/sparse-vmemmap.c           | 22 +++++++++++++++-------
>  4 files changed, 29 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
> index e65d69ad6e0c..006dc4f81f6d 100644
> --- a/arch/x86/mm/pgtable.c
> +++ b/arch/x86/mm/pgtable.c
> @@ -41,7 +41,7 @@ static struct grouped_page_cache gpc_pks;
>  static bool __ro_after_init pks_tables_inited_val;
>  
>  
> -struct page *alloc_table(gfp_t gfp)
> +struct page *alloc_table_node(gfp_t gfp, int node)
>  {
>  	struct page *table;
>  
> @@ -53,9 +53,9 @@ struct page *alloc_table(gfp_t gfp)
>  	}
>  
>  	if (gfp & GFP_ATOMIC)
> -		table = get_grouped_page_atomic(numa_node_id(), &gpc_pks);
> +		table = get_grouped_page_atomic(node, &gpc_pks);
>  	else
> -		table = get_grouped_page(numa_node_id(), &gpc_pks);
> +		table = get_grouped_page(node, &gpc_pks);
>  	if (!table)
>  		return NULL;
>  	__SetPageTable(table);
> @@ -72,6 +72,10 @@ struct page *alloc_table(gfp_t gfp)
>  
>  	return table;
>  }
> +struct page *alloc_table(gfp_t gfp)
> +{
> +	return alloc_table_node(gfp, numa_node_id());
> +}
>  
>  void free_table(struct page *table_page)
>  {
> diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
> index e576c19abc8c..eb08371db211 100644
> --- a/include/asm-generic/pgalloc.h
> +++ b/include/asm-generic/pgalloc.h
> @@ -14,8 +14,10 @@ static inline struct page *alloc_table(gfp_t gfp)
>  {
>  	return alloc_page(gfp);
>  }
> +/* alloc_table_node() stub defined in mm.h */
>  #else /* __HAVE_ARCH_ALLOC_TABLE */
>  extern struct page *alloc_table(gfp_t gfp);
> +extern struct page *alloc_table_node(gfp_t gfp, int node);
>  #endif /* __HAVE_ARCH_ALLOC_TABLE */
>  
>  #ifdef __HAVE_ARCH_FREE_TABLE
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index ab63d5a201cb..fdb33bc6bba8 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2332,6 +2332,11 @@ static inline void free_table(struct page *table_page)
>  {
>  	__free_pages(table_page, 0);
>  }
> +
> +static inline struct page *alloc_table_node(gfp_t gfp, int node)
> +{
> +	return alloc_pages_node(node, gfp, 0);
> +}
>  #endif /* CONFIG_PKS_PG_TABLES */
>  
>  static inline void pgtable_init(void)
> diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
> index bdce883f9286..4f479c75cc8d 100644
> --- a/mm/sparse-vmemmap.c
> +++ b/mm/sparse-vmemmap.c
> @@ -511,13 +511,21 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
>  	return pte;
>  }
>  
> -static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
> +static void * __meminit vmemmap_alloc_table(int node)
>  {
> -	void *p = vmemmap_alloc_block(size, node);
> +	void *p;
> +	if (slab_is_available()) {
> +		struct page *page = alloc_table_node(GFP_KERNEL | __GFP_ZERO, node);

This change removes __GFP_RETRY_MAYFAIL|__GFP_NOWARN from the original gfp
vmemmap_alloc_block() used.
Not sure __GFP_RETRY_MAYFAIL is really needed in vmemmap_alloc_block_zero()
at the first place, though.

More broadly, maybe it makes sense to split boot time and memory hotplug
paths and use pxd_alloc() for the latter.

> +
> +		if (!page)
> +			return NULL;
> +		return page_address(page);
> +	}
>  
> +	p = __earlyonly_bootmem_alloc(node, PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));

Opportunistically rename to __earlyonly_memblock_alloc()? ;-)

>  	if (!p)
>  		return NULL;
> -	memset(p, 0, size);
> +	memset(p, 0, PAGE_SIZE);
>  
>  	return p;
>  }
> @@ -526,7 +534,7 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
>  {
>  	pmd_t *pmd = pmd_offset(pud, addr);
>  	if (pmd_none(*pmd)) {
> -		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
> +		void *p = vmemmap_alloc_table(node);
>  		if (!p)
>  			return NULL;
>  		pmd_populate_kernel(&init_mm, pmd, p);
> @@ -538,7 +546,7 @@ pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
>  {
>  	pud_t *pud = pud_offset(p4d, addr);
>  	if (pud_none(*pud)) {
> -		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
> +		void *p = vmemmap_alloc_table(node);
>  		if (!p)
>  			return NULL;
>  		pud_populate(&init_mm, pud, p);
> @@ -550,7 +558,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
>  {
>  	p4d_t *p4d = p4d_offset(pgd, addr);
>  	if (p4d_none(*p4d)) {
> -		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
> +		void *p = vmemmap_alloc_table(node);
>  		if (!p)
>  			return NULL;
>  		p4d_populate(&init_mm, p4d, p);
> @@ -562,7 +570,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
>  {
>  	pgd_t *pgd = pgd_offset_k(addr);
>  	if (pgd_none(*pgd)) {
> -		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
> +		void *p = vmemmap_alloc_table(node);
>  		if (!p)
>  			return NULL;
>  		pgd_populate(&init_mm, pgd, p);
> -- 
> 2.17.1
> 

-- 
Sincerely yours,
Mike.

  reply	other threads:[~2021-08-31  8:56 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-30 23:59 [RFC PATCH v2 00/19] PKS write protected page tables Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 01/19] list: Support getting most recent element in list_lru Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 02/19] list: Support list head not in object for list_lru Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 03/19] x86/mm/cpa: Add grouped page allocations Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 04/19] mm: Explicitly zero page table lock ptr Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 05/19] x86, mm: Use cache of page tables Rick Edgecombe
2021-08-31  8:40   ` Mike Rapoport
2021-08-31 19:09     ` Edgecombe, Rick P
2021-08-30 23:59 ` [RFC PATCH v2 06/19] x86/mm/cpa: Add perm callbacks to grouped pages Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 07/19] x86/cpufeatures: Add feature for pks tables Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 08/19] x86/mm/cpa: Add get_grouped_page_atomic() Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 09/19] x86/mm: Support GFP_ATOMIC in alloc_table_node() Rick Edgecombe
2021-08-31  8:32   ` Mike Rapoport
2021-08-30 23:59 ` [RFC PATCH v2 10/19] x86/mm: Use alloc_table() for fill_pte(), etc Rick Edgecombe
2021-08-31  8:47   ` Mike Rapoport
2021-08-31 18:48     ` Edgecombe, Rick P
2021-08-30 23:59 ` [RFC PATCH v2 11/19] mm/sparsemem: Use alloc_table() for table allocations Rick Edgecombe
2021-08-31  8:55   ` Mike Rapoport [this message]
2021-08-31 18:25     ` Edgecombe, Rick P
2021-09-01  7:22       ` Mike Rapoport
2021-09-02 13:56         ` Vlastimil Babka
2021-08-30 23:59 ` [RFC PATCH v2 12/19] x86/mm: Use free_table in unmap path Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 13/19] mm/debug_vm_page_table: Use setters instead of WRITE_ONCE Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 14/19] x86/efi: Toggle table protections when copying Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 15/19] x86/mm/cpa: Add set_memory_pks() Rick Edgecombe
2021-08-30 23:59 ` [RFC PATCH v2 16/19] x86/mm: Protect page tables with PKS Rick Edgecombe
2021-08-31  8:56   ` Mike Rapoport
2021-08-31 17:55     ` Edgecombe, Rick P
2021-08-30 23:59 ` [RFC PATCH v2 17/19] x86/mm/cpa: PKS protect direct map page tables Rick Edgecombe
2021-08-31 10:14   ` Mike Rapoport
2021-08-31 17:58     ` Edgecombe, Rick P
2021-08-30 23:59 ` [RFC PATCH v2 18/19] x86/mm: Add PKS table soft mode Rick Edgecombe
2021-08-31  3:49   ` Randy Dunlap
2021-08-31 17:55     ` Edgecombe, Rick P
2021-08-30 23:59 ` [RFC PATCH v2 19/19] x86/mm: Add PKS table debug checking Rick Edgecombe

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=YS3uhdT88XFvP9n3@kernel.org \
    --to=rppt@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=ira.weiny@intel.com \
    --cc=keescook@chromium.org \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=linux-hardening@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=shakeelb@google.com \
    --cc=vbabka@suse.cz \
    --cc=x86@kernel.org \
    --subject='Re: [RFC PATCH v2 11/19] mm/sparsemem: Use alloc_table() for table allocations' \
    /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

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).