[GIT PULL] x86 fixes

From: Ingo Molnar
Date: Wed Mar 16 2011 - 12:21:51 EST

Linus,

Please pull the latest x86-fixes-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-fixes-for-linus


out-of-topic modifications in x86-fixes-for-linus:
--------------------------------------------------
include/linux/pci_ids.h # 41b2610: x86, amd: Extend AMD northbridge

Thanks,

Ingo

------------------>
Andreas Herrmann (2):
x86, amd: Normalize compute unit IDs on multi-node processors
x86, quirk: Fix SB600 revision check

Boris Ostrovsky (1):
x86, AMD: Set ARAT feature on AMD processors

Borislav Petkov (2):
x86, amd: Initialize variable properly
x86, amd-nb: Misc cleanliness fixes

Hans Rosenfeld (3):
x86, amd: Enable L3 cache index disable on family 0x15
x86, amd: Extend AMD northbridge caching code to support "Link Control" devices
x86, amd: Support L3 Cache Partitioning on AMD family 0x15 CPUs

Jan Beulich (1):
x86: Adjust section placement in AMD northbridge related code

Mathieu Desnoyers (1):
x86: stop_machine_text_poke() should issue sync_core()


arch/x86/include/asm/amd_nb.h | 16 +++--
arch/x86/kernel/alternative.c | 7 ++-
arch/x86/kernel/amd_nb.c | 100 +++++++++++++++++++++++++++++----
arch/x86/kernel/cpu/amd.c | 14 ++++-
arch/x86/kernel/cpu/intel_cacheinfo.c | 76 ++++++++++++++++++++-----
arch/x86/kernel/early-quirks.c | 7 ++-
arch/x86/kernel/smpboot.c | 1 +
arch/x86/pci/amd_bus.c | 2 +-
include/linux/pci_ids.h | 1 +
9 files changed, 185 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 64dc82e..527fb96 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -9,15 +9,17 @@ struct amd_nb_bus_dev_range {
u8 dev_limit;
};

-extern struct pci_device_id amd_nb_misc_ids[];
+extern const struct pci_device_id amd_nb_misc_ids[];
extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
struct bootnode;

-extern int early_is_amd_nb(u32 value);
+extern bool early_is_amd_nb(u32 value);
extern int amd_cache_northbridges(void);
extern void amd_flush_garts(void);
extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn);
extern int amd_scan_nodes(void);
+extern int amd_get_subcaches(int);
+extern int amd_set_subcaches(int, int);

#ifdef CONFIG_NUMA_EMU
extern void amd_fake_nodes(const struct bootnode *nodes, int nr_nodes);
@@ -26,6 +28,7 @@ extern void amd_get_nodes(struct bootnode *nodes);

struct amd_northbridge {
struct pci_dev *misc;
+ struct pci_dev *link;
};

struct amd_northbridge_info {
@@ -35,17 +38,18 @@ struct amd_northbridge_info {
};
extern struct amd_northbridge_info amd_northbridges;

-#define AMD_NB_GART 0x1
-#define AMD_NB_L3_INDEX_DISABLE 0x2
+#define AMD_NB_GART BIT(0)
+#define AMD_NB_L3_INDEX_DISABLE BIT(1)
+#define AMD_NB_L3_PARTITIONING BIT(2)

#ifdef CONFIG_AMD_NB

-static inline int amd_nb_num(void)
+static inline u16 amd_nb_num(void)
{
return amd_northbridges.num;
}

-static inline int amd_nb_has_feature(int feature)
+static inline bool amd_nb_has_feature(unsigned feature)
{
return ((amd_northbridges.flags & feature) == feature);
}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7038b95..4db3554 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -620,7 +620,12 @@ static int __kprobes stop_machine_text_poke(void *data)
flush_icache_range((unsigned long)p->addr,
(unsigned long)p->addr + p->len);
}
-
+ /*
+ * Intel Archiecture Software Developer's Manual section 7.1.3 specifies
+ * that a core serializing instruction such as "cpuid" should be
+ * executed on _each_ core before the new instruction is made visible.
+ */
+ sync_core();
return 0;
}

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 0a99f71..6563419 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -12,7 +12,7 @@

static u32 *flush_words;

-struct pci_device_id amd_nb_misc_ids[] = {
+const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
@@ -20,6 +20,11 @@ struct pci_device_id amd_nb_misc_ids[] = {
};
EXPORT_SYMBOL(amd_nb_misc_ids);

+static struct pci_device_id amd_nb_link_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_LINK) },
+ {}
+};
+
const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
{ 0x00, 0x18, 0x20 },
{ 0xff, 0x00, 0x20 },
@@ -31,7 +36,7 @@ struct amd_northbridge_info amd_northbridges;
EXPORT_SYMBOL(amd_northbridges);

static struct pci_dev *next_northbridge(struct pci_dev *dev,
- struct pci_device_id *ids)
+ const struct pci_device_id *ids)
{
do {
dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
@@ -43,9 +48,9 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev,

int amd_cache_northbridges(void)
{
- int i = 0;
+ u16 i = 0;
struct amd_northbridge *nb;
- struct pci_dev *misc;
+ struct pci_dev *misc, *link;

if (amd_nb_num())
return 0;
@@ -64,10 +69,12 @@ int amd_cache_northbridges(void)
amd_northbridges.nb = nb;
amd_northbridges.num = i;

- misc = NULL;
+ link = misc = NULL;
for (i = 0; i != amd_nb_num(); i++) {
node_to_amd_nb(i)->misc = misc =
next_northbridge(misc, amd_nb_misc_ids);
+ node_to_amd_nb(i)->link = link =
+ next_northbridge(link, amd_nb_link_ids);
}

/* some CPU families (e.g. family 0x11) do not support GART */
@@ -85,26 +92,95 @@ int amd_cache_northbridges(void)
boot_cpu_data.x86_mask >= 0x1))
amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;

+ if (boot_cpu_data.x86 == 0x15)
+ amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
+
+ /* L3 cache partitioning is supported on family 0x15 */
+ if (boot_cpu_data.x86 == 0x15)
+ amd_northbridges.flags |= AMD_NB_L3_PARTITIONING;
+
return 0;
}
EXPORT_SYMBOL_GPL(amd_cache_northbridges);

-/* Ignores subdevice/subvendor but as far as I can figure out
- they're useless anyways */
-int __init early_is_amd_nb(u32 device)
+/*
+ * Ignores subdevice/subvendor but as far as I can figure out
+ * they're useless anyways
+ */
+bool __init early_is_amd_nb(u32 device)
{
- struct pci_device_id *id;
+ const struct pci_device_id *id;
u32 vendor = device & 0xffff;
+
device >>= 16;
for (id = amd_nb_misc_ids; id->vendor; id++)
if (vendor == id->vendor && device == id->device)
- return 1;
+ return true;
+ return false;
+}
+
+int amd_get_subcaches(int cpu)
+{
+ struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
+ unsigned int mask;
+ int cuid = 0;
+
+ if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return 0;
+
+ pci_read_config_dword(link, 0x1d4, &mask);
+
+#ifdef CONFIG_SMP
+ cuid = cpu_data(cpu).compute_unit_id;
+#endif
+ return (mask >> (4 * cuid)) & 0xf;
+}
+
+int amd_set_subcaches(int cpu, int mask)
+{
+ static unsigned int reset, ban;
+ struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
+ unsigned int reg;
+ int cuid = 0;
+
+ if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf)
+ return -EINVAL;
+
+ /* if necessary, collect reset state of L3 partitioning and BAN mode */
+ if (reset == 0) {
+ pci_read_config_dword(nb->link, 0x1d4, &reset);
+ pci_read_config_dword(nb->misc, 0x1b8, &ban);
+ ban &= 0x180000;
+ }
+
+ /* deactivate BAN mode if any subcaches are to be disabled */
+ if (mask != 0xf) {
+ pci_read_config_dword(nb->misc, 0x1b8, &reg);
+ pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
+ }
+
+#ifdef CONFIG_SMP
+ cuid = cpu_data(cpu).compute_unit_id;
+#endif
+ mask <<= 4 * cuid;
+ mask |= (0xf ^ (1 << cuid)) << 26;
+
+ pci_write_config_dword(nb->link, 0x1d4, mask);
+
+ /* reset BAN mode if L3 partitioning returned to reset state */
+ pci_read_config_dword(nb->link, 0x1d4, &reg);
+ if (reg == reset) {
+ pci_read_config_dword(nb->misc, 0x1b8, &reg);
+ reg &= ~0x180000;
+ pci_write_config_dword(nb->misc, 0x1b8, reg | ban);
+ }
+
return 0;
}

-int amd_cache_gart(void)
+static int amd_cache_gart(void)
{
- int i;
+ u16 i;

if (!amd_nb_has_feature(AMD_NB_GART))
return 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7c7bedb..58f1b01 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -261,7 +261,7 @@ static int __cpuinit nearby_node(int apicid)
#ifdef CONFIG_X86_HT
static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
{
- u32 nodes;
+ u32 nodes, cores_per_cu = 1;
u8 node_id;
int cpu = smp_processor_id();

@@ -276,6 +276,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
/* get compute unit information */
smp_num_siblings = ((ebx >> 8) & 3) + 1;
c->compute_unit_id = ebx & 0xff;
+ cores_per_cu += ((ebx >> 8) & 3);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;

@@ -288,15 +289,18 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
/* fixup multi-node processor information */
if (nodes > 1) {
u32 cores_per_node;
+ u32 cus_per_node;

set_cpu_cap(c, X86_FEATURE_AMD_DCM);
cores_per_node = c->x86_max_cores / nodes;
+ cus_per_node = cores_per_node / cores_per_cu;

/* store NodeID, use llc_shared_map to store sibling info */
per_cpu(cpu_llc_id, cpu) = node_id;

- /* core id to be in range from 0 to (cores_per_node - 1) */
- c->cpu_core_id = c->cpu_core_id % cores_per_node;
+ /* core id has to be in the [0 .. cores_per_node - 1] range */
+ c->cpu_core_id %= cores_per_node;
+ c->compute_unit_id %= cus_per_node;
}
}
#endif
@@ -594,6 +598,10 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
#endif
+
+ /* As a rule processors have APIC timer running in deep C states */
+ if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+ set_cpu_cap(c, X86_FEATURE_ARAT);
}

#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index ec2c19a..90cc675 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -304,8 +304,9 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,

struct _cache_attr {
struct attribute attr;
- ssize_t (*show)(struct _cpuid4_info *, char *);
- ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+ ssize_t (*show)(struct _cpuid4_info *, char *, unsigned int);
+ ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count,
+ unsigned int);
};

#ifdef CONFIG_AMD_NB
@@ -400,7 +401,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,

#define SHOW_CACHE_DISABLE(slot) \
static ssize_t \
-show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf) \
+show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf, \
+ unsigned int cpu) \
{ \
return show_cache_disable(this_leaf, buf, slot); \
}
@@ -512,7 +514,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
#define STORE_CACHE_DISABLE(slot) \
static ssize_t \
store_cache_disable_##slot(struct _cpuid4_info *this_leaf, \
- const char *buf, size_t count) \
+ const char *buf, size_t count, \
+ unsigned int cpu) \
{ \
return store_cache_disable(this_leaf, buf, count, slot); \
}
@@ -524,6 +527,39 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
show_cache_disable_1, store_cache_disable_1);

+static ssize_t
+show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu)
+{
+ if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return -EINVAL;
+
+ return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
+}
+
+static ssize_t
+store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count,
+ unsigned int cpu)
+{
+ unsigned long val;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return -EINVAL;
+
+ if (strict_strtoul(buf, 16, &val) < 0)
+ return -EINVAL;
+
+ if (amd_set_subcaches(cpu, val))
+ return -EINVAL;
+
+ return count;
+}
+
+static struct _cache_attr subcaches =
+ __ATTR(subcaches, 0644, show_subcaches, store_subcaches);
+
#else /* CONFIG_AMD_NB */
#define amd_init_l3_cache(x, y)
#endif /* CONFIG_AMD_NB */
@@ -532,9 +568,9 @@ static int
__cpuinit cpuid4_cache_lookup_regs(int index,
struct _cpuid4_info_regs *this_leaf)
{
- union _cpuid4_leaf_eax eax;
- union _cpuid4_leaf_ebx ebx;
- union _cpuid4_leaf_ecx ecx;
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
unsigned edx;

if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
@@ -870,8 +906,8 @@ static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject);
#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(ici_index_kobject, x))[y]))

#define show_one_plus(file_name, object, val) \
-static ssize_t show_##file_name \
- (struct _cpuid4_info *this_leaf, char *buf) \
+static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \
+ unsigned int cpu) \
{ \
return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \
}
@@ -882,7 +918,8 @@ show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1);
show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1);
show_one_plus(number_of_sets, ecx.split.number_of_sets, 1);

-static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int cpu)
{
return sprintf(buf, "%luK\n", this_leaf->size / 1024);
}
@@ -906,17 +943,20 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
return n;
}

-static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf)
+static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf,
+ unsigned int cpu)
{
return show_shared_cpu_map_func(leaf, 0, buf);
}

-static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
+static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf,
+ unsigned int cpu)
{
return show_shared_cpu_map_func(leaf, 1, buf);
}

-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int cpu)
{
switch (this_leaf->eax.split.type) {
case CACHE_TYPE_DATA:
@@ -974,6 +1014,9 @@ static struct attribute ** __cpuinit amd_l3_attrs(void)
if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
n += 2;

+ if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ n += 1;
+
attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
if (attrs == NULL)
return attrs = default_attrs;
@@ -986,6 +1029,9 @@ static struct attribute ** __cpuinit amd_l3_attrs(void)
attrs[n++] = &cache_disable_1.attr;
}

+ if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ attrs[n++] = &subcaches.attr;
+
return attrs;
}
#endif
@@ -998,7 +1044,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)

ret = fattr->show ?
fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
- buf) :
+ buf, this_leaf->cpu) :
0;
return ret;
}
@@ -1012,7 +1058,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,

ret = fattr->store ?
fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index),
- buf, count) :
+ buf, count, this_leaf->cpu) :
0;
return ret;
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 9efbdcc..3755ef4 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -159,7 +159,12 @@ static void __init ati_bugs_contd(int num, int slot, int func)
if (rev >= 0x40)
acpi_fix_pin2_polarity = 1;

- if (rev > 0x13)
+ /*
+ * SB600: revisions 0x11, 0x12, 0x13, 0x14, ...
+ * SB700: revisions 0x39, 0x3a, ...
+ * SB800: revisions 0x40, 0x41, ...
+ */
+ if (rev >= 0x39)
return;

if (acpi_use_timer_override)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 08776a9..1bfb1c6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -414,6 +414,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)

if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
if (c->phys_proc_id == o->phys_proc_id &&
+ per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
c->compute_unit_id == o->compute_unit_id)
link_thread_siblings(cpu, i);
} else if (c->phys_proc_id == o->phys_proc_id &&
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index e27dffbb..026e493 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -350,7 +350,7 @@ static int __init early_fill_mp_bus_info(void)

#define ENABLE_CF8_EXT_CFG (1ULL << 46)

-static void enable_pci_io_ecs(void *unused)
+static void __cpuinit enable_pci_io_ecs(void *unused)
{
u64 reg;
rdmsrl(MSR_AMD64_NB_CFG, reg);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 3adb06e..580de67 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -518,6 +518,7 @@
#define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303
#define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304
#define PCI_DEVICE_ID_AMD_15H_NB_MISC 0x1603
+#define PCI_DEVICE_ID_AMD_15H_NB_LINK 0x1604
#define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703
#define PCI_DEVICE_ID_AMD_LANCE 0x2000
#define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/