1. Patchew
  2. linux
  3. [PATCH v3 0/2] Resolve problems with kexec identity mapping
  4. View patch

[PATCH v3 2/2] x86/mm/ident_map: Use gbpages only where full GB page should be mapped.

Steve Wahl posted 2 patches 1 year, 5 months ago
[PATCH v3 2/2] x86/mm/ident_map: Use gbpages only where full GB page should be mapped.
Posted by Steve Wahl 1 year, 5 months ago 
When ident_pud_init() uses only gbpages to create identity maps, large
ranges of addresses not actually requested can be included in the
resulting table; a 4K request will map a full GB.  This can include a
lot of extra address space past that requested, including areas marked
reserved by the BIOS.  That allows processor speculation into reserved
regions, that on UV systems can cause system halts.

Only use gbpages when map creation requests include the full GB page
of space.  Fall back to using smaller 2M pages when only portions of a
GB page are included in the request.

No attempt is made to coalesce mapping requests. If a request requires
a map entry at the 2M (pmd) level, subsequent mapping requests within
the same 1G region will also be at the pmd level, even if adjacent or
overlapping such requests could have been combined to map a full
gbpage.  Existing usage starts with larger regions and then adds
smaller regions, so this should not have any great consequence.

Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Tested-by: Pavin Joseph <me@pavinjoseph.com>
Tested-by: Sarah Brofeldt <srhb@dbc.dk>
Tested-by: Eric Hagberg <ehagberg@gmail.com>
---
 arch/x86/mm/ident_map.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..a204a332c71f 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		if (info->direct_gbpages) {
-			pud_t pudval;
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_leaf(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
 
-			if (pud_present(*pud))
-				continue;
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
-- 
2.26.2
Re: [PATCH v3 2/2] x86/mm/ident_map: Use gbpages only where full GB page should be mapped.
Posted by Steve Wahl 1 year, 4 months ago 
Gentle ping: Can someone please take the time to review this patch?

This patch was previously approved by Dave Hansen, but was reverted.

Full series (of 2 + cover leter) viewable at:

https://lore.kernel.org/all/20240717213121.3064030-1-steve.wahl@hpe.com/

Thanks.

--> Steve Wahl, HPE

On Wed, Jul 17, 2024 at 04:31:21PM -0500, Steve Wahl wrote:
> When ident_pud_init() uses only gbpages to create identity maps, large
> ranges of addresses not actually requested can be included in the
> resulting table; a 4K request will map a full GB.  This can include a
> lot of extra address space past that requested, including areas marked
> reserved by the BIOS.  That allows processor speculation into reserved
> regions, that on UV systems can cause system halts.
> 
> Only use gbpages when map creation requests include the full GB page
> of space.  Fall back to using smaller 2M pages when only portions of a
> GB page are included in the request.
> 
> No attempt is made to coalesce mapping requests. If a request requires
> a map entry at the 2M (pmd) level, subsequent mapping requests within
> the same 1G region will also be at the pmd level, even if adjacent or
> overlapping such requests could have been combined to map a full
> gbpage.  Existing usage starts with larger regions and then adds
> smaller regions, so this should not have any great consequence.
> 
> Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
> Tested-by: Pavin Joseph <me@pavinjoseph.com>
> Tested-by: Sarah Brofeldt <srhb@dbc.dk>
> Tested-by: Eric Hagberg <ehagberg@gmail.com>
> ---
>  arch/x86/mm/ident_map.c | 23 ++++++++++++++++++-----
>  1 file changed, 18 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
> index 968d7005f4a7..a204a332c71f 100644
> --- a/arch/x86/mm/ident_map.c
> +++ b/arch/x86/mm/ident_map.c
> @@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
>  	for (; addr < end; addr = next) {
>  		pud_t *pud = pud_page + pud_index(addr);
>  		pmd_t *pmd;
> +		bool use_gbpage;
>  
>  		next = (addr & PUD_MASK) + PUD_SIZE;
>  		if (next > end)
>  			next = end;
>  
> -		if (info->direct_gbpages) {
> -			pud_t pudval;
> +		/* if this is already a gbpage, this portion is already mapped */
> +		if (pud_leaf(*pud))
> +			continue;
> +
> +		/* Is using a gbpage allowed? */
> +		use_gbpage = info->direct_gbpages;
>  
> -			if (pud_present(*pud))
> -				continue;
> +		/* Don't use gbpage if it maps more than the requested region. */
> +		/* at the begining: */
> +		use_gbpage &= ((addr & ~PUD_MASK) == 0);
> +		/* ... or at the end: */
> +		use_gbpage &= ((next & ~PUD_MASK) == 0);
> +
> +		/* Never overwrite existing mappings */
> +		use_gbpage &= !pud_present(*pud);
> +
> +		if (use_gbpage) {
> +			pud_t pudval;
>  
> -			addr &= PUD_MASK;
>  			pudval = __pud((addr - info->offset) | info->page_flag);
>  			set_pud(pud, pudval);
>  			continue;
> -- 
> 2.26.2
> 

-- 
Steve Wahl, Hewlett Packard Enterprise
[tip: x86/mm] x86/mm/ident_map: Use gbpages only where full GB page should be mapped.
Posted by tip-bot2 for Steve Wahl 1 year, 4 months ago 
The following commit has been merged into the x86/mm branch of tip:

Commit-ID:     cc31744a294584a36bf764a0ffa3255a8e69f036
Gitweb:        https://git.kernel.org/tip/cc31744a294584a36bf764a0ffa3255a8e69f036
Author:        Steve Wahl <steve.wahl@hpe.com>
AuthorDate:    Wed, 17 Jul 2024 16:31:21 -05:00
Committer:     Thomas Gleixner <tglx@linutronix.de>
CommitterDate: Mon, 05 Aug 2024 16:09:31 +02:00

x86/mm/ident_map: Use gbpages only where full GB page should be mapped.

When ident_pud_init() uses only GB pages to create identity maps, large
ranges of addresses not actually requested can be included in the resulting
table; a 4K request will map a full GB.  This can include a lot of extra
address space past that requested, including areas marked reserved by the
BIOS.  That allows processor speculation into reserved regions, that on UV
systems can cause system halts.

Only use GB pages when map creation requests include the full GB page of
space.  Fall back to using smaller 2M pages when only portions of a GB page
are included in the request.

No attempt is made to coalesce mapping requests. If a request requires a
map entry at the 2M (pmd) level, subsequent mapping requests within the
same 1G region will also be at the pmd level, even if adjacent or
overlapping such requests could have been combined to map a full GB page.
Existing usage starts with larger regions and then adds smaller regions, so
this should not have any great consequence.

Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavin Joseph <me@pavinjoseph.com>
Tested-by: Sarah Brofeldt <srhb@dbc.dk>
Tested-by: Eric Hagberg <ehagberg@gmail.com>
Link: https://lore.kernel.org/all/20240717213121.3064030-3-steve.wahl@hpe.com

---
 arch/x86/mm/ident_map.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index c451272..437e96f 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -99,18 +99,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		if (info->direct_gbpages) {
-			pud_t pudval;
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_leaf(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
 
-			if (pud_present(*pud))
-				continue;
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.