commit
47663e841f12cbb0647750f5c581151b4a769a4d upstream.
As a temporary storage, staged_config[] in rdt_domain should be cleared
before and after it is used. The stale value in staged_config[] could
cause an MSR access error.
Here is a reproducer on a system with 16 usable CLOSIDs for a 15-way L3
Cache (MBA should be disabled if the number of CLOSIDs for MB is less than
16.) :
mount -t resctrl resctrl -o cdp /sys/fs/resctrl
mkdir /sys/fs/resctrl/p{1..7}
umount /sys/fs/resctrl/
mount -t resctrl resctrl /sys/fs/resctrl
mkdir /sys/fs/resctrl/p{1..8}
An error occurs when creating resource group named p8:
unchecked MSR access error: WRMSR to 0xca0 (tried to write 0x00000000000007ff) at rIP: 0xffffffff82249142 (cat_wrmsr+0x32/0x60)
Call Trace:
<IRQ>
__flush_smp_call_function_queue+0x11d/0x170
__sysvec_call_function+0x24/0xd0
sysvec_call_function+0x89/0xc0
</IRQ>
<TASK>
asm_sysvec_call_function+0x16/0x20
When creating a new resource control group, hardware will be configured
by the following process:
rdtgroup_mkdir()
rdtgroup_mkdir_ctrl_mon()
rdtgroup_init_alloc()
resctrl_arch_update_domains()
resctrl_arch_update_domains() iterates and updates all resctrl_conf_type
whose have_new_ctrl is true. Since staged_config[] holds the same values as
when CDP was enabled, it will continue to update the CDP_CODE and CDP_DATA
configurations. When group p8 is created, get_config_index() called in
resctrl_arch_update_domains() will return 16 and 17 as the CLOSIDs for
CDP_CODE and CDP_DATA, which will be translated to an invalid register -
0xca0 in this scenario.
Fix it by clearing staged_config[] before and after it is used.
[reinette: re-order commit tags]
Fixes: ef07a1531c27 ("x86/resctrl: Allow different CODE/DATA configurations to be staged")
Suggested-by: Xin Hao <xhao@linux.alibaba.com>
Signed-off-by: Shawn Wang <shawnwang@linux.alibaba.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/2fad13f49fbe89687fc40e9a5a61f23a28d1507a.1673988935.git.reinette.chatre%40intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
{
struct resctrl_schema *s;
struct rdtgroup *rdtgrp;
- struct rdt_domain *dom;
struct rdt_resource *r;
char *tok, *resname;
int ret = 0;
goto out;
}
- list_for_each_entry(s, &resctrl_schema_all, list) {
- list_for_each_entry(dom, &s->res->domains, list)
- memset(dom->staged_config, 0, sizeof(dom->staged_config));
- }
+ rdt_staged_configs_clear();
while ((tok = strsep(&buf, "\n")) != NULL) {
resname = strim(strsep(&tok, ":"));
}
out:
+ rdt_staged_configs_clear();
rdtgroup_kn_unlock(of->kn);
cpus_read_unlock();
return ret ?: nbytes;
void __check_limbo(struct rdt_domain *d, bool force_free);
void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
void __init thread_throttle_mode_init(void);
+void rdt_staged_configs_clear(void);
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
va_end(ap);
}
+void rdt_staged_configs_clear(void)
+{
+ struct rdt_resource *r;
+ struct rdt_domain *dom;
+
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ for_each_alloc_capable_rdt_resource(r) {
+ list_for_each_entry(dom, &r->domains, list)
+ memset(dom->staged_config, 0, sizeof(dom->staged_config));
+ }
+}
+
/*
* Trivial allocator for CLOSIDs. Since h/w only supports a small number,
* we can keep a bitmap of free CLOSIDs in a single integer.
{
struct resctrl_schema *s;
struct rdt_resource *r;
- int ret;
+ int ret = 0;
+
+ rdt_staged_configs_clear();
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
} else {
ret = rdtgroup_init_cat(s, rdtgrp->closid);
if (ret < 0)
- return ret;
+ goto out;
}
ret = resctrl_arch_update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("Failed to initialize allocations\n");
- return ret;
+ goto out;
}
}
rdtgrp->mode = RDT_MODE_SHAREABLE;
- return 0;
+out:
+ rdt_staged_configs_clear();
+ return ret;
}
static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,