[-next,v3] drivers: base: cacheinfo: fix shared_cpu_map
Commit Message
The cacheinfo sets up the shared_cpu_map by checking whether the caches
with the same index are shared between CPUs. However, this will trigger
slab-out-of-bounds access if the CPUs do not have the same cache hierarchy.
Another problem is the mismatched shared_cpu_map when the shared cache does
not have the same index between CPUs.
CPU0 I D L3
index 0 1 2 x
^ ^ ^ ^
index 0 1 2 3
CPU1 I D L2 L3
This patch checks each cache is shared with all caches on other CPUs.
Reviewed-by: Pierre Gondois <pierre.gondois@arm.com>
Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
---
drivers/base/cacheinfo.c | 25 +++++++++++++++----------
1 file changed, 15 insertions(+), 10 deletions(-)
base-commit: c76083fac3bae1a87ae3d005b5cb1cbc761e31d5
Comments
On Wed, Dec 28, 2022 at 03:24:19AM +0000, Yong-Xuan Wang wrote:
> The cacheinfo sets up the shared_cpu_map by checking whether the caches
> with the same index are shared between CPUs. However, this will trigger
> slab-out-of-bounds access if the CPUs do not have the same cache hierarchy.
> Another problem is the mismatched shared_cpu_map when the shared cache does
> not have the same index between CPUs.
>
> CPU0 I D L3
> index 0 1 2 x
> ^ ^ ^ ^
> index 0 1 2 3
> CPU1 I D L2 L3
>
> This patch checks each cache is shared with all caches on other CPUs.
>
Just curious to know if this is just Qemu config or a real platform.
I had intentionally not supported this to just to get to know when such
h/w appears in the real world 😁.
> Reviewed-by: Pierre Gondois <pierre.gondois@arm.com>
> Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
> ---
> drivers/base/cacheinfo.c | 25 +++++++++++++++----------
> 1 file changed, 15 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
> index 950b22cdb5f7..dfa804bcf3cc 100644
> --- a/drivers/base/cacheinfo.c
> +++ b/drivers/base/cacheinfo.c
> @@ -256,7 +256,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
> {
> struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
> struct cacheinfo *this_leaf, *sib_leaf;
> - unsigned int index;
> + unsigned int index, sib_index;
> int ret = 0;
>
> if (this_cpu_ci->cpu_map_populated)
> @@ -284,11 +284,12 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
>
> if (i == cpu || !sib_cpu_ci->info_list)
> continue;/* skip if itself or no cacheinfo */
> -
> - sib_leaf = per_cpu_cacheinfo_idx(i, index);
> - if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
> - cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
> - cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
> + for (sib_index = 0; sib_index < cache_leaves(i); sib_index++) {
> + sib_leaf = per_cpu_cacheinfo_idx(i, sib_index);
> + if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
> + cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
> + cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
Does it make sense to break here once we match as it is unlikely to match
with any other indices ?
> + }
> }
> }
> /* record the maximum cache line size */
> @@ -302,7 +303,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
> static void cache_shared_cpu_map_remove(unsigned int cpu)
> {
> struct cacheinfo *this_leaf, *sib_leaf;
> - unsigned int sibling, index;
> + unsigned int sibling, index, sib_index;
>
> for (index = 0; index < cache_leaves(cpu); index++) {
> this_leaf = per_cpu_cacheinfo_idx(cpu, index);
> @@ -313,9 +314,13 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
> if (sibling == cpu || !sib_cpu_ci->info_list)
> continue;/* skip if itself or no cacheinfo */
>
> - sib_leaf = per_cpu_cacheinfo_idx(sibling, index);
> - cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
> - cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
> + for (sib_index = 0; sib_index < cache_leaves(sibling); sib_index++) {
> + sib_leaf = per_cpu_cacheinfo_idx(sibling, sib_index);
> + if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
> + cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
> + cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
Same comment as above.
Hi Sudeep,
> On Wed, Jan 4, 2023 at 6:59 PM Sudeep Holla <sudeep.holla@arm.com> wrote:
>
> On Wed, Dec 28, 2022 at 03:24:19AM +0000, Yong-Xuan Wang wrote:
> > The cacheinfo sets up the shared_cpu_map by checking whether the caches
> > with the same index are shared between CPUs. However, this will trigger
> > slab-out-of-bounds access if the CPUs do not have the same cache hierarchy.
> > Another problem is the mismatched shared_cpu_map when the shared cache does
> > not have the same index between CPUs.
> >
> > CPU0 I D L3
> > index 0 1 2 x
> > ^ ^ ^ ^
> > index 0 1 2 3
> > CPU1 I D L2 L3
> >
> > This patch checks each cache is shared with all caches on other CPUs.
> >
>
> Just curious to know if this is just Qemu config or a real platform.
> I had intentionally not supported this to just to get to know when such
> h/w appears in the real world 😁.
>
We are trying to build such kind of config in QEMU.
> > Reviewed-by: Pierre Gondois <pierre.gondois@arm.com>
> > Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
> > ---
> > drivers/base/cacheinfo.c | 25 +++++++++++++++----------
> > 1 file changed, 15 insertions(+), 10 deletions(-)
> >
> > diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
> > index 950b22cdb5f7..dfa804bcf3cc 100644
> > --- a/drivers/base/cacheinfo.c
> > +++ b/drivers/base/cacheinfo.c
> > @@ -256,7 +256,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
> > {
> > struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
> > struct cacheinfo *this_leaf, *sib_leaf;
> > - unsigned int index;
> > + unsigned int index, sib_index;
> > int ret = 0;
> >
> > if (this_cpu_ci->cpu_map_populated)
> > @@ -284,11 +284,12 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
> >
> > if (i == cpu || !sib_cpu_ci->info_list)
> > continue;/* skip if itself or no cacheinfo */
> > -
> > - sib_leaf = per_cpu_cacheinfo_idx(i, index);
> > - if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
> > - cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
> > - cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
> > + for (sib_index = 0; sib_index < cache_leaves(i); sib_index++) {
> > + sib_leaf = per_cpu_cacheinfo_idx(i, sib_index);
> > + if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
> > + cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
> > + cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
>
> Does it make sense to break here once we match as it is unlikely to match
> with any other indices ?
>
Yeah. We can break here once we find the shared instance. I'll send a
new version to fix it.
Thank you!
> > + }
> > }
> > }
> > /* record the maximum cache line size */
> > @@ -302,7 +303,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
> > static void cache_shared_cpu_map_remove(unsigned int cpu)
> > {
> > struct cacheinfo *this_leaf, *sib_leaf;
> > - unsigned int sibling, index;
> > + unsigned int sibling, index, sib_index;
> >
> > for (index = 0; index < cache_leaves(cpu); index++) {
> > this_leaf = per_cpu_cacheinfo_idx(cpu, index);
> > @@ -313,9 +314,13 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
> > if (sibling == cpu || !sib_cpu_ci->info_list)
> > continue;/* skip if itself or no cacheinfo */
> >
> > - sib_leaf = per_cpu_cacheinfo_idx(sibling, index);
> > - cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
> > - cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
> > + for (sib_index = 0; sib_index < cache_leaves(sibling); sib_index++) {
> > + sib_leaf = per_cpu_cacheinfo_idx(sibling, sib_index);
> > + if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
> > + cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
> > + cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
>
> Same comment as above.
>
> --
> Regards,
> Sudeep
Regards,
Yong-Xuan
@@ -256,7 +256,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
{
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf, *sib_leaf;
- unsigned int index;
+ unsigned int index, sib_index;
int ret = 0;
if (this_cpu_ci->cpu_map_populated)
@@ -284,11 +284,12 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
if (i == cpu || !sib_cpu_ci->info_list)
continue;/* skip if itself or no cacheinfo */
-
- sib_leaf = per_cpu_cacheinfo_idx(i, index);
- if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
- cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
- cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+ for (sib_index = 0; sib_index < cache_leaves(i); sib_index++) {
+ sib_leaf = per_cpu_cacheinfo_idx(i, sib_index);
+ if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+ cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
+ cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+ }
}
}
/* record the maximum cache line size */
@@ -302,7 +303,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu)
static void cache_shared_cpu_map_remove(unsigned int cpu)
{
struct cacheinfo *this_leaf, *sib_leaf;
- unsigned int sibling, index;
+ unsigned int sibling, index, sib_index;
for (index = 0; index < cache_leaves(cpu); index++) {
this_leaf = per_cpu_cacheinfo_idx(cpu, index);
@@ -313,9 +314,13 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
if (sibling == cpu || !sib_cpu_ci->info_list)
continue;/* skip if itself or no cacheinfo */
- sib_leaf = per_cpu_cacheinfo_idx(sibling, index);
- cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
- cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+ for (sib_index = 0; sib_index < cache_leaves(sibling); sib_index++) {
+ sib_leaf = per_cpu_cacheinfo_idx(sibling, sib_index);
+ if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+ cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
+ cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+ }
+ }
}
}
}