1 files changed, 200 insertions, 136 deletions

diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index fc6c8ef92dcc..b3eeb66c0a51 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -18,6 +18,7 @@
 #include <asm/processor.h>
 #include <linux/smp.h>
 #include <asm/k8.h>
+#include <asm/smp.h>
 
 #define LVL_1_INST      1
 #define LVL_1_DATA      2
@@ -31,6 +32,8 @@ struct _cache_table {
         short size;
 };
 
+#define MB(x)   ((x) * 1024)
+
 /* All the cache descriptor types we care about (no TLB or
    trace cache entries) */
 
@@ -44,9 +47,9 @@ static const struct _cache_table __cpuinitconst cache_table[] =
         { 0x0d, LVL_1_DATA, 16 },       /* 4-way set assoc, 64 byte line size */
         { 0x21, LVL_2,      256 },      /* 8-way set assoc, 64 byte line size */
         { 0x22, LVL_3,      512 },      /* 4-way set assoc, sectored cache, 64 byte line size */
-        { 0x23, LVL_3,      1024 },     /* 8-way set assoc, sectored cache, 64 byte line size */
-        { 0x25, LVL_3,      2048 },     /* 8-way set assoc, sectored cache, 64 byte line size */
-        { 0x29, LVL_3,      4096 },     /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x23, LVL_3,      MB(1) },    /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x25, LVL_3,      MB(2) },    /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x29, LVL_3,      MB(4) },    /* 8-way set assoc, sectored cache, 64 byte line size */
         { 0x2c, LVL_1_DATA, 32 },       /* 8-way set assoc, 64 byte line size */
         { 0x30, LVL_1_INST, 32 },       /* 8-way set assoc, 64 byte line size */
         { 0x39, LVL_2,      128 },      /* 4-way set assoc, sectored cache, 64 byte line size */
@@ -59,16 +62,16 @@ static const struct _cache_table __cpuinitconst cache_table[] =
         { 0x41, LVL_2,      128 },      /* 4-way set assoc, 32 byte line size */
         { 0x42, LVL_2,      256 },      /* 4-way set assoc, 32 byte line size */
         { 0x43, LVL_2,      512 },      /* 4-way set assoc, 32 byte line size */
-        { 0x44, LVL_2,      1024 },     /* 4-way set assoc, 32 byte line size */
-        { 0x45, LVL_2,      2048 },     /* 4-way set assoc, 32 byte line size */
-        { 0x46, LVL_3,      4096 },     /* 4-way set assoc, 64 byte line size */
-        { 0x47, LVL_3,      8192 },     /* 8-way set assoc, 64 byte line size */
-        { 0x49, LVL_3,      4096 },     /* 16-way set assoc, 64 byte line size */
-        { 0x4a, LVL_3,      6144 },     /* 12-way set assoc, 64 byte line size */
-        { 0x4b, LVL_3,      8192 },     /* 16-way set assoc, 64 byte line size */
-        { 0x4c, LVL_3,     12288 },     /* 12-way set assoc, 64 byte line size */
-        { 0x4d, LVL_3,     16384 },     /* 16-way set assoc, 64 byte line size */
-        { 0x4e, LVL_2,      6144 },     /* 24-way set assoc, 64 byte line size */
+        { 0x44, LVL_2,      MB(1) },    /* 4-way set assoc, 32 byte line size */
+        { 0x45, LVL_2,      MB(2) },    /* 4-way set assoc, 32 byte line size */
+        { 0x46, LVL_3,      MB(4) },    /* 4-way set assoc, 64 byte line size */
+        { 0x47, LVL_3,      MB(8) },    /* 8-way set assoc, 64 byte line size */
+        { 0x49, LVL_3,      MB(4) },    /* 16-way set assoc, 64 byte line size */
+        { 0x4a, LVL_3,      MB(6) },    /* 12-way set assoc, 64 byte line size */
+        { 0x4b, LVL_3,      MB(8) },    /* 16-way set assoc, 64 byte line size */
+        { 0x4c, LVL_3,      MB(12) },   /* 12-way set assoc, 64 byte line size */
+        { 0x4d, LVL_3,      MB(16) },   /* 16-way set assoc, 64 byte line size */
+        { 0x4e, LVL_2,      MB(6) },    /* 24-way set assoc, 64 byte line size */
         { 0x60, LVL_1_DATA, 16 },       /* 8-way set assoc, sectored cache, 64 byte line size */
         { 0x66, LVL_1_DATA, 8 },        /* 4-way set assoc, sectored cache, 64 byte line size */
         { 0x67, LVL_1_DATA, 16 },       /* 4-way set assoc, sectored cache, 64 byte line size */
@@ -77,34 +80,34 @@ static const struct _cache_table __cpuinitconst cache_table[] =
         { 0x71, LVL_TRACE,  16 },       /* 8-way set assoc */
         { 0x72, LVL_TRACE,  32 },       /* 8-way set assoc */
         { 0x73, LVL_TRACE,  64 },       /* 8-way set assoc */
-        { 0x78, LVL_2,    1024 },       /* 4-way set assoc, 64 byte line size */
-        { 0x79, LVL_2,     128 },       /* 8-way set assoc, sectored cache, 64 byte line size */
-        { 0x7a, LVL_2,     256 },       /* 8-way set assoc, sectored cache, 64 byte line size */
-        { 0x7b, LVL_2,     512 },       /* 8-way set assoc, sectored cache, 64 byte line size */
-        { 0x7c, LVL_2,    1024 },       /* 8-way set assoc, sectored cache, 64 byte line size */
-        { 0x7d, LVL_2,    2048 },       /* 8-way set assoc, 64 byte line size */
-        { 0x7f, LVL_2,     512 },       /* 2-way set assoc, 64 byte line size */
-        { 0x82, LVL_2,     256 },       /* 8-way set assoc, 32 byte line size */
-        { 0x83, LVL_2,     512 },       /* 8-way set assoc, 32 byte line size */
-        { 0x84, LVL_2,    1024 },       /* 8-way set assoc, 32 byte line size */
-        { 0x85, LVL_2,    2048 },       /* 8-way set assoc, 32 byte line size */
-        { 0x86, LVL_2,     512 },       /* 4-way set assoc, 64 byte line size */
-        { 0x87, LVL_2,    1024 },       /* 8-way set assoc, 64 byte line size */
-        { 0xd0, LVL_3,     512 },       /* 4-way set assoc, 64 byte line size */
-        { 0xd1, LVL_3,    1024 },       /* 4-way set assoc, 64 byte line size */
-        { 0xd2, LVL_3,    2048 },       /* 4-way set assoc, 64 byte line size */
-        { 0xd6, LVL_3,    1024 },       /* 8-way set assoc, 64 byte line size */
-        { 0xd7, LVL_3,    2048 },       /* 8-way set assoc, 64 byte line size */
-        { 0xd8, LVL_3,    4096 },       /* 12-way set assoc, 64 byte line size */
-        { 0xdc, LVL_3,    2048 },       /* 12-way set assoc, 64 byte line size */
-        { 0xdd, LVL_3,    4096 },       /* 12-way set assoc, 64 byte line size */
-        { 0xde, LVL_3,    8192 },       /* 12-way set assoc, 64 byte line size */
-        { 0xe2, LVL_3,    2048 },       /* 16-way set assoc, 64 byte line size */
-        { 0xe3, LVL_3,    4096 },       /* 16-way set assoc, 64 byte line size */
-        { 0xe4, LVL_3,    8192 },       /* 16-way set assoc, 64 byte line size */
-        { 0xea, LVL_3,    12288 },      /* 24-way set assoc, 64 byte line size */
-        { 0xeb, LVL_3,    18432 },      /* 24-way set assoc, 64 byte line size */
-        { 0xec, LVL_3,    24576 },      /* 24-way set assoc, 64 byte line size */
+        { 0x78, LVL_2,      MB(1) },    /* 4-way set assoc, 64 byte line size */
+        { 0x79, LVL_2,      128 },      /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x7a, LVL_2,      256 },      /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x7b, LVL_2,      512 },      /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x7c, LVL_2,      MB(1) },    /* 8-way set assoc, sectored cache, 64 byte line size */
+        { 0x7d, LVL_2,      MB(2) },    /* 8-way set assoc, 64 byte line size */
+        { 0x7f, LVL_2,      512 },      /* 2-way set assoc, 64 byte line size */
+        { 0x82, LVL_2,      256 },      /* 8-way set assoc, 32 byte line size */
+        { 0x83, LVL_2,      512 },      /* 8-way set assoc, 32 byte line size */
+        { 0x84, LVL_2,      MB(1) },    /* 8-way set assoc, 32 byte line size */
+        { 0x85, LVL_2,      MB(2) },    /* 8-way set assoc, 32 byte line size */
+        { 0x86, LVL_2,      512 },      /* 4-way set assoc, 64 byte line size */
+        { 0x87, LVL_2,      MB(1) },    /* 8-way set assoc, 64 byte line size */
+        { 0xd0, LVL_3,      512 },      /* 4-way set assoc, 64 byte line size */
+        { 0xd1, LVL_3,      MB(1) },    /* 4-way set assoc, 64 byte line size */
+        { 0xd2, LVL_3,      MB(2) },    /* 4-way set assoc, 64 byte line size */
+        { 0xd6, LVL_3,      MB(1) },    /* 8-way set assoc, 64 byte line size */
+        { 0xd7, LVL_3,      MB(2) },    /* 8-way set assoc, 64 byte line size */
+        { 0xd8, LVL_3,      MB(4) },    /* 12-way set assoc, 64 byte line size */
+        { 0xdc, LVL_3,      MB(2) },    /* 12-way set assoc, 64 byte line size */
+        { 0xdd, LVL_3,      MB(4) },    /* 12-way set assoc, 64 byte line size */
+        { 0xde, LVL_3,      MB(8) },    /* 12-way set assoc, 64 byte line size */
+        { 0xe2, LVL_3,      MB(2) },    /* 16-way set assoc, 64 byte line size */
+        { 0xe3, LVL_3,      MB(4) },    /* 16-way set assoc, 64 byte line size */
+        { 0xe4, LVL_3,      MB(8) },    /* 16-way set assoc, 64 byte line size */
+        { 0xea, LVL_3,      MB(12) },   /* 24-way set assoc, 64 byte line size */
+        { 0xeb, LVL_3,      MB(18) },   /* 24-way set assoc, 64 byte line size */
+        { 0xec, LVL_3,      MB(24) },   /* 24-way set assoc, 64 byte line size */
         { 0x00, 0, 0}
 };
 
@@ -150,7 +153,8 @@ struct _cpuid4_info {
         union _cpuid4_leaf_ebx ebx;
         union _cpuid4_leaf_ecx ecx;
         unsigned long size;
-        unsigned long can_disable;
+        bool can_disable;
+        unsigned int l3_indices;
         DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
 };
 
@@ -160,7 +164,8 @@ struct _cpuid4_info_regs {
         union _cpuid4_leaf_ebx ebx;
         union _cpuid4_leaf_ecx ecx;
         unsigned long size;
-        unsigned long can_disable;
+        bool can_disable;
+        unsigned int l3_indices;
 };
 
 unsigned short                  num_cache_leaves;
@@ -290,6 +295,36 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
                 (ebx->split.ways_of_associativity + 1) - 1;
 }
 
+struct _cache_attr {
+        struct attribute attr;
+        ssize_t (*show)(struct _cpuid4_info *, char *);
+        ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+};
+
+#ifdef CONFIG_CPU_SUP_AMD
+static unsigned int __cpuinit amd_calc_l3_indices(void)
+{
+        /*
+         * We're called over smp_call_function_single() and therefore
+         * are on the correct cpu.
+         */
+        int cpu = smp_processor_id();
+        int node = cpu_to_node(cpu);
+        struct pci_dev *dev = node_to_k8_nb_misc(node);
+        unsigned int sc0, sc1, sc2, sc3;
+        u32 val = 0;
+
+        pci_read_config_dword(dev, 0x1C4, &val);
+
+        /* calculate subcache sizes */
+        sc0 = !(val & BIT(0));
+        sc1 = !(val & BIT(4));
+        sc2 = !(val & BIT(8))  + !(val & BIT(9));
+        sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+        return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+}
+
 static void __cpuinit
 amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 {
@@ -299,12 +334,103 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
         if (boot_cpu_data.x86 == 0x11)
                 return;
 
-        /* see erratum #382 */
-        if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+        /* see errata #382 and #388 */
+        if ((boot_cpu_data.x86 == 0x10) &&
+            ((boot_cpu_data.x86_model < 0x8) ||
+             (boot_cpu_data.x86_mask  < 0x1)))
                 return;
 
-        this_leaf->can_disable = 1;
+        this_leaf->can_disable = true;
+        this_leaf->l3_indices  = amd_calc_l3_indices();
+}
+
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+                                  unsigned int index)
+{
+        int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+        int node = amd_get_nb_id(cpu);
+        struct pci_dev *dev = node_to_k8_nb_misc(node);
+        unsigned int reg = 0;
+
+        if (!this_leaf->can_disable)
+                return -EINVAL;
+
+        if (!dev)
+                return -EINVAL;
+
+        pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+        return sprintf(buf, "0x%08x\n", reg);
+}
+
+#define SHOW_CACHE_DISABLE(index)                                       \
+static ssize_t                                                          \
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)   \
+{                                                                       \
+        return show_cache_disable(this_leaf, buf, index);               \
 }
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+        const char *buf, size_t count, unsigned int index)
+{
+        int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+        int node = amd_get_nb_id(cpu);
+        struct pci_dev *dev = node_to_k8_nb_misc(node);
+        unsigned long val = 0;
+
+#define SUBCACHE_MASK   (3UL << 20)
+#define SUBCACHE_INDEX  0xfff
+
+        if (!this_leaf->can_disable)
+                return -EINVAL;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        if (!dev)
+                return -EINVAL;
+
+        if (strict_strtoul(buf, 10, &val) < 0)
+                return -EINVAL;
+
+        /* do not allow writes outside of allowed bits */
+        if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
+            ((val & SUBCACHE_INDEX) > this_leaf->l3_indices))
+                return -EINVAL;
+
+        val |= BIT(30);
+        pci_write_config_dword(dev, 0x1BC + index * 4, val);
+        /*
+         * We need to WBINVD on a core on the node containing the L3 cache which
+         * indices we disable therefore a simple wbinvd() is not sufficient.
+         */
+        wbinvd_on_cpu(cpu);
+        pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31));
+        return count;
+}
+
+#define STORE_CACHE_DISABLE(index)                                      \
+static ssize_t                                                          \
+store_cache_disable_##index(struct _cpuid4_info *this_leaf,             \
+                            const char *buf, size_t count)              \
+{                                                                       \
+        return store_cache_disable(this_leaf, buf, count, index);       \
+}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+                show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+                show_cache_disable_1, store_cache_disable_1);
+
+#else   /* CONFIG_CPU_SUP_AMD */
+static void __cpuinit
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+{
+};
+#endif /* CONFIG_CPU_SUP_AMD */
 
 static int
 __cpuinit cpuid4_cache_lookup_regs(int index,
@@ -711,82 +837,6 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
 #define to_object(k)    container_of(k, struct _index_kobject, kobj)
 #define to_attr(a)      container_of(a, struct _cache_attr, attr)
 
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
-                                  unsigned int index)
-{
-        int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-        int node = cpu_to_node(cpu);
-        struct pci_dev *dev = node_to_k8_nb_misc(node);
-        unsigned int reg = 0;
-
-        if (!this_leaf->can_disable)
-                return -EINVAL;
-
-        if (!dev)
-                return -EINVAL;
-
-        pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
-        return sprintf(buf, "%x\n", reg);
-}
-
-#define SHOW_CACHE_DISABLE(index)                                       \
-static ssize_t                                                          \
-show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)   \
-{                                                                       \
-        return show_cache_disable(this_leaf, buf, index);               \
-}
-SHOW_CACHE_DISABLE(0)
-SHOW_CACHE_DISABLE(1)
-
-static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
-        const char *buf, size_t count, unsigned int index)
-{
-        int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-        int node = cpu_to_node(cpu);
-        struct pci_dev *dev = node_to_k8_nb_misc(node);
-        unsigned long val = 0;
-        unsigned int scrubber = 0;
-
-        if (!this_leaf->can_disable)
-                return -EINVAL;
-
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
-
-        if (!dev)
-                return -EINVAL;
-
-        if (strict_strtoul(buf, 10, &val) < 0)
-                return -EINVAL;
-
-        val |= 0xc0000000;
-
-        pci_read_config_dword(dev, 0x58, &scrubber);
-        scrubber &= ~0x1f000000;
-        pci_write_config_dword(dev, 0x58, scrubber);
-
-        pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
-        wbinvd();
-        pci_write_config_dword(dev, 0x1BC + index * 4, val);
-        return count;
-}
-
-#define STORE_CACHE_DISABLE(index)                                      \
-static ssize_t                                                          \
-store_cache_disable_##index(struct _cpuid4_info *this_leaf,             \
-                            const char *buf, size_t count)              \
-{                                                                       \
-        return store_cache_disable(this_leaf, buf, count, index);       \
-}
-STORE_CACHE_DISABLE(0)
-STORE_CACHE_DISABLE(1)
-
-struct _cache_attr {
-        struct attribute attr;
-        ssize_t (*show)(struct _cpuid4_info *, char *);
-        ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
-};
-
 #define define_one_ro(_name) \
 static struct _cache_attr _name = \
         __ATTR(_name, 0444, show_##_name, NULL)
@@ -801,23 +851,28 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
-                show_cache_disable_0, store_cache_disable_0);
-static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
-                show_cache_disable_1, store_cache_disable_1);
+#define DEFAULT_SYSFS_CACHE_ATTRS       \
+        &type.attr,                     \
+        &level.attr,                    \
+        &coherency_line_size.attr,      \
+        &physical_line_partition.attr,  \
+        &ways_of_associativity.attr,    \
+        &number_of_sets.attr,           \
+        &size.attr,                     \
+        &shared_cpu_map.attr,           \
+        &shared_cpu_list.attr
 
 static struct attribute *default_attrs[] = {
-        &type.attr,
-        &level.attr,
-        &coherency_line_size.attr,
-        &physical_line_partition.attr,
-        &ways_of_associativity.attr,
-        &number_of_sets.attr,
-        &size.attr,
-        &shared_cpu_map.attr,
-        &shared_cpu_list.attr,
+        DEFAULT_SYSFS_CACHE_ATTRS,
+        NULL
+};
+
+static struct attribute *default_l3_attrs[] = {
+        DEFAULT_SYSFS_CACHE_ATTRS,
+#ifdef CONFIG_CPU_SUP_AMD
         &cache_disable_0.attr,
         &cache_disable_1.attr,
+#endif
         NULL
 };
 
@@ -848,7 +903,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
         return ret;
 }
 
-static struct sysfs_ops sysfs_ops = {
+static const struct sysfs_ops sysfs_ops = {
         .show   = show,
         .store  = store,
 };
@@ -908,6 +963,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
         unsigned int cpu = sys_dev->id;
         unsigned long i, j;
         struct _index_kobject *this_object;
+        struct _cpuid4_info   *this_leaf;
         int retval;
 
         retval = cpuid4_cache_sysfs_init(cpu);
@@ -926,6 +982,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
                 this_object = INDEX_KOBJECT_PTR(cpu, i);
                 this_object->cpu = cpu;
                 this_object->index = i;
+
+                this_leaf = CPUID4_INFO_IDX(cpu, i);
+
+                if (this_leaf->can_disable)
+                        ktype_cache.default_attrs = default_l3_attrs;
+                else
+                        ktype_cache.default_attrs = default_attrs;
+
                 retval = kobject_init_and_add(&(this_object->kobj),
                                               &ktype_cache,
                                               per_cpu(ici_cache_kobject, cpu),