x86/resctrl: Introduce AMD QOS feature

Enable QOS feature on AMD.

Following QoS sub-features are supported on AMD if the underlying
hardware supports it:

 - L3 Cache allocation enforcement
 - L3 Cache occupancy monitoring
 - L3 Code-Data Prioritization support
 - Memory Bandwidth Enforcement (Allocation)

The specification is available at:
https://developer.amd.com/wp-content/resources/56375.pdf

There are differences in the way some of the features are implemented.
Separate those functions and add those as vendor specific functions.

The major difference is in MBA feature:

 - AMD uses CPUID leaf 0x80000020 to initialize the MBA features.
 - AMD uses direct bandwidth value instead of delay based on bandwidth values.
 - MSR register base addresses are different for MBA.
 - AMD allows non-contiguous L3 cache bit masks.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: "Chang S. Bae" <chang.seok.bae@intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Dmitry Safonov <dima@arista.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: <linux-doc@vger.kernel.org>
Cc: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Pu Wen <puwen@hygon.cn>
Cc: <qianyue.zj@alibaba-inc.com>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Reinette Chatre <reinette.chatre@intel.com>
Cc: Rian Hunter <rian@alum.mit.edu>
Cc: Sherry Hurwitz <sherry.hurwitz@amd.com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Lendacky <Thomas.Lendacky@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: <xiaochen.shen@intel.com>
Link: https://lkml.kernel.org/r/20181121202811.4492-12-babu.moger@amd.com

3 files changed, 142 insertions, 3 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index ba5a5b8c4681..2ec252be4ed9 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -61,6 +61,9 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
                 struct rdt_resource *r);
 static void
 cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+static void
+mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
+              struct rdt_resource *r);
 
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
@@ -255,7 +258,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
         return false;
 }
 
-static bool __get_mem_config(struct rdt_resource *r)
+static bool __get_mem_config_intel(struct rdt_resource *r)
 {
         union cpuid_0x10_3_eax eax;
         union cpuid_0x10_x_edx edx;
@@ -281,6 +284,30 @@ static bool __get_mem_config(struct rdt_resource *r)
         return true;
 }
 
+static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
+{
+        union cpuid_0x10_3_eax eax;
+        union cpuid_0x10_x_edx edx;
+        u32 ebx, ecx;
+
+        cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full);
+        r->num_closid = edx.split.cos_max + 1;
+        r->default_ctrl = MAX_MBA_BW_AMD;
+
+        /* AMD does not use delay */
+        r->membw.delay_linear = false;
+
+        r->membw.min_bw = 0;
+        r->membw.bw_gran = 1;
+        /* Max value is 2048, Data width should be 4 in decimal */
+        r->data_width = 4;
+
+        r->alloc_capable = true;
+        r->alloc_enabled = true;
+
+        return true;
+}
+
 static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 {
         union cpuid_0x10_1_eax eax;
@@ -340,6 +367,15 @@ static int get_cache_id(int cpu, int level)
         return -1;
 }
 
+static void
+mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+        unsigned int i;
+
+        for (i = m->low; i < m->high; i++)
+                wrmsrl(r->msr_base + i, d->ctrl_val[i]);
+}
+
 /*
  * Map the memory b/w percentage value to delay values
  * that can be written to QOS_MSRs.
@@ -793,8 +829,13 @@ static bool __init rdt_cpu_has(int flag)
 
 static __init bool get_mem_config(void)
 {
-        if (rdt_cpu_has(X86_FEATURE_MBA))
-                return __get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]);
+        if (!rdt_cpu_has(X86_FEATURE_MBA))
+                return false;
+
+        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+                return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]);
+        else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+                return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]);
 
         return false;
 }
@@ -893,10 +934,32 @@ static __init void rdt_init_res_defs_intel(void)
         }
 }
 
+static __init void rdt_init_res_defs_amd(void)
+{
+        struct rdt_resource *r;
+
+        for_each_rdt_resource(r) {
+                if (r->rid == RDT_RESOURCE_L3 ||
+                    r->rid == RDT_RESOURCE_L3DATA ||
+                    r->rid == RDT_RESOURCE_L3CODE ||
+                    r->rid == RDT_RESOURCE_L2 ||
+                    r->rid == RDT_RESOURCE_L2DATA ||
+                    r->rid == RDT_RESOURCE_L2CODE)
+                        r->cbm_validate = cbm_validate_amd;
+                else if (r->rid == RDT_RESOURCE_MBA) {
+                        r->msr_base = MSR_IA32_MBA_BW_BASE;
+                        r->msr_update = mba_wrmsr_amd;
+                        r->parse_ctrlval = parse_bw_amd;
+                }
+        }
+}
+
 static __init void rdt_init_res_defs(void)
 {
         if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
                 rdt_init_res_defs_intel();
+        else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+                rdt_init_res_defs_amd();
 }
 
 static enum cpuhp_state rdt_online;
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index bfd7bdf8a156..43ee3cee6494 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -30,6 +30,53 @@
 
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
+ * checked against the minimum and maximum bandwidth values specified by
+ * the hardware. The allocated bandwidth percentage is rounded to the next
+ * control step available on the hardware.
+ */
+static bool bw_validate_amd(char *buf, unsigned long *data,
+                            struct rdt_resource *r)
+{
+        unsigned long bw;
+        int ret;
+
+        ret = kstrtoul(buf, 10, &bw);
+        if (ret) {
+                rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
+                return false;
+        }
+
+        if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+                rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
+                                    r->membw.min_bw, r->default_ctrl);
+                return false;
+        }
+
+        *data = roundup(bw, (unsigned long)r->membw.bw_gran);
+        return true;
+}
+
+int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
+                 struct rdt_domain *d)
+{
+        unsigned long bw_val;
+
+        if (d->have_new_ctrl) {
+                rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
+                return -EINVAL;
+        }
+
+        if (!bw_validate_amd(data->buf, &bw_val, r))
+                return -EINVAL;
+
+        d->new_ctrl = bw_val;
+        d->have_new_ctrl = true;
+
+        return 0;
+}
+
+/*
+ * Check whether MBA bandwidth percentage value is correct. The value is
  * checked against the minimum and max bandwidth values specified by the
  * hardware. The allocated bandwidth percentage is rounded to the next
  * control step available on the hardware.
@@ -124,6 +171,30 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 }
 
 /*
+ * Check whether a cache bit mask is valid. AMD allows non-contiguous
+ * bitmasks
+ */
+bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
+{
+        unsigned long val;
+        int ret;
+
+        ret = kstrtoul(buf, 16, &val);
+        if (ret) {
+                rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
+                return false;
+        }
+
+        if (val > r->default_ctrl) {
+                rdt_last_cmd_puts("Mask out of range\n");
+                return false;
+        }
+
+        *data = val;
+        return true;
+}
+
+/*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 599cad34a6a8..822b7db634ee 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -11,6 +11,7 @@
 #define MSR_IA32_L3_CBM_BASE            0xc90
 #define MSR_IA32_L2_CBM_BASE            0xd10
 #define MSR_IA32_MBA_THRTL_BASE         0xd50
+#define MSR_IA32_MBA_BW_BASE            0xc0000200
 
 #define MSR_IA32_QM_CTR                 0x0c8e
 #define MSR_IA32_QM_EVTSEL              0x0c8d
@@ -34,6 +35,7 @@
 #define MAX_MBA_BW                      100u
 #define MBA_IS_LINEAR                   0x4
 #define MBA_MAX_MBPS                    U32_MAX
+#define MAX_MBA_BW_AMD                  0x800
 
 #define RMID_VAL_ERROR                  BIT_ULL(63)
 #define RMID_VAL_UNAVAIL                BIT_ULL(62)
@@ -448,6 +450,8 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
               struct rdt_domain *d);
 int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,
                    struct rdt_domain *d);
+int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
+                 struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -579,5 +583,6 @@ void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
+bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */