[PATCH] mm/slub: add sanity check for slub_min/max_order cmdline setup

[PATCH] mm/slub: add sanity check for slub_min/max_order cmdline setup

[Feng Tang]

Currently there are 2 parameters could be setup from kernel cmdline:
slub_min_order and slub_max_order. It's possible that the user
configured slub_min_order is bigger than the default slub_max_order
[1], which can still take effect, as calculate_oder() will use MAX_ORDER
as a fallback to check against, but has some downsides:

* the kernel message about SLUB will be strange in showing min/max
  orders:

    SLUB: HWalign=64, Order=9-3, MinObjects=0, CPUs=16, Nodes=1

* in calculate_order() called by each slab, the 2 loops of
  calc_slab_order() will all be meaningless due to slub_min_order
  is bigger than slub_max_order

* prevent future code cleanup like in [2].

Fix it by adding some sanity check to enforce the min/max semantics.

[1]. https://lore.kernel.org/lkml/21a0ba8b-bf05-0799-7c78-2a35f8c8d52a@os.amperecomputing.com/
[2]. https://lore.kernel.org/lkml/20230908145302.30320-7-vbabka@suse.cz/
Signed-off-by: Feng Tang <feng.tang@intel.com>
---
 mm/slub.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/mm/slub.c b/mm/slub.c
index f7940048138c..b36e5eb0ccb7 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4711,6 +4711,9 @@ static int __init setup_slub_min_order(char *str)
 {
 	get_option(&str, (int *)&slub_min_order);
 
+	if (slub_min_order > slub_max_order)
+		slub_max_order = slub_min_order;
+
 	return 1;
 }
 
@@ -4721,6 +4724,9 @@ static int __init setup_slub_max_order(char *str)
 	get_option(&str, (int *)&slub_max_order);
 	slub_max_order = min_t(unsigned int, slub_max_order, MAX_ORDER);
 
+	if (slub_min_order > slub_max_order)
+		slub_min_order = slub_max_order;
+
 	return 1;
 }
 
-- 
2.27.0

Re: [PATCH] mm/slub: add sanity check for slub_min/max_order cmdline setup

[Vlastimil Babka]

On 9/20/23 09:44, Feng Tang wrote:
> Currently there are 2 parameters could be setup from kernel cmdline:
> slub_min_order and slub_max_order. It's possible that the user
> configured slub_min_order is bigger than the default slub_max_order
> [1], which can still take effect, as calculate_oder() will use MAX_ORDER
> as a fallback to check against, but has some downsides:
> 
> * the kernel message about SLUB will be strange in showing min/max
>   orders:
> 
>     SLUB: HWalign=64, Order=9-3, MinObjects=0, CPUs=16, Nodes=1
> 
> * in calculate_order() called by each slab, the 2 loops of
>   calc_slab_order() will all be meaningless due to slub_min_order
>   is bigger than slub_max_order
> 
> * prevent future code cleanup like in [2].
> 
> Fix it by adding some sanity check to enforce the min/max semantics.
> 
> [1]. https://lore.kernel.org/lkml/21a0ba8b-bf05-0799-7c78-2a35f8c8d52a@os.amperecomputing.com/
> [2]. https://lore.kernel.org/lkml/20230908145302.30320-7-vbabka@suse.cz/
> Signed-off-by: Feng Tang <feng.tang@intel.com>

Thanks, applied!

> ---
>  mm/slub.c | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/mm/slub.c b/mm/slub.c
> index f7940048138c..b36e5eb0ccb7 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -4711,6 +4711,9 @@ static int __init setup_slub_min_order(char *str)
>  {
>  	get_option(&str, (int *)&slub_min_order);
>  
> +	if (slub_min_order > slub_max_order)
> +		slub_max_order = slub_min_order;
> +
>  	return 1;
>  }
>  
> @@ -4721,6 +4724,9 @@ static int __init setup_slub_max_order(char *str)
>  	get_option(&str, (int *)&slub_max_order);
>  	slub_max_order = min_t(unsigned int, slub_max_order, MAX_ORDER);
>  
> +	if (slub_min_order > slub_max_order)
> +		slub_min_order = slub_max_order;
> +
>  	return 1;
>  }
>