lkml.org 
[lkml]   [2021]   [Sep]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH v5 2/2] x86/sgx: Add an attribute for the amount of SGX memory in a NUMA node
From
Date
On Wed, 2021-09-22 at 16:30 -0700, Reinette Chatre wrote:
> Hi Jarkko,
>
> On 9/13/2021 8:04 PM, Jarkko Sakkinen wrote:
> > The amount of SGX memory on the system is determined by the BIOS and it
> > varies wildly between systems. It can be from dozens of MB's on desktops
> > or VM's, up to many GB's on servers. Just like for regular memory, it is
> > sometimes useful to know the amount of usable SGX memory in the system.
> >
> > Add an attribute for the amount of SGX memory in bytes to each NUMA
> > node. The path is /sys/devices/system/node/node[0-9]*/sgx/memory_size.
> >
> > Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
> >
> > ---
> > v5: A new patch based on the discussion at
> > https://lore.kernel.org/linux-sgx/3a7cab4115b4f902f3509ad8652e616b91703e1d.camel@kernel.org/T/#t
> > ---
> > Documentation/x86/sgx.rst | 14 ++++++
> > arch/x86/kernel/cpu/sgx/main.c | 90 ++++++++++++++++++++++++++++++++++
> > arch/x86/kernel/cpu/sgx/sgx.h | 2 +
> > 3 files changed, 106 insertions(+)
> >
>
> ...
>
> > diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
> > index a6e313f1a82d..c43b5a0120c1 100644
> > --- a/arch/x86/kernel/cpu/sgx/main.c
> > +++ b/arch/x86/kernel/cpu/sgx/main.c
> > @@ -717,6 +717,7 @@ static bool __init sgx_page_cache_init(void)
> > }
> >
> > sgx_epc_sections[i].node = &sgx_numa_nodes[nid];
> > + sgx_numa_nodes[nid].size += size;
> >
> > sgx_nr_epc_sections++;
> > }
>
> The above memory seems to be uninitialized at the time it is incremented.
>
> I tried this out on a system that reports the following:
>
> $ dmesg | grep EPC
> [ 7.252838] sgx: EPC section 0x1000c00000-0x107f7fffff
> [ 7.256921] sgx: EPC section 0x2000c00000-0x207fffffff
>
> It shows unexpectedly large values:
> $ cat /sys/devices/system/node/node*/sgx/memory_size
> 12421486739271732874
> 16308428754864105707
>
> System reported sane values after adding this fixup:
>
> diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
> index 3380390cc052..d73bbfbfc05d 100644
> --- a/arch/x86/kernel/cpu/sgx/main.c
> +++ b/arch/x86/kernel/cpu/sgx/main.c
> @@ -621,7 +621,7 @@ static bool __init sgx_page_cache_init(void)
> int nid;
> int i;
>
> - sgx_numa_nodes = kmalloc_array(num_possible_nodes(),
> sizeof(*sgx_numa_nodes), GFP_KERNEL);
> + sgx_numa_nodes = kcalloc(num_possible_nodes(),
> sizeof(*sgx_numa_nodes), GFP_KERNEL);
> if (!sgx_numa_nodes)
> return false;
>
>
> After fixup:
> $ cat /sys/devices/system/node/node*/sgx/memory_size
> 2126512128
> 2134900736

Thanks! I did not experience in a VM.

So cat you pick these patches to your patch set, and squash
this fix to it?


/Jarkko

\
 
 \ /
  Last update: 2021-09-23 22:30    [W:0.088 / U:1.944 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site