u32 full;
};
-struct amd_l3_cache {
- struct amd_northbridge *nb;
- unsigned indices;
- u8 subcaches[4];
-};
-
-struct _cpuid4_info {
+struct _cpuid4_info_regs {
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- struct amd_l3_cache *l3;
- DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+ struct amd_northbridge *nb;
};
-/* subset of above _cpuid4_info w/o shared_cpu_map */
-struct _cpuid4_info_regs {
- union _cpuid4_leaf_eax eax;
- union _cpuid4_leaf_ebx ebx;
- union _cpuid4_leaf_ecx ecx;
- unsigned long size;
- struct amd_l3_cache *l3;
+struct _cpuid4_info {
+ struct _cpuid4_info_regs base;
+ DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
};
unsigned short num_cache_leaves;
/*
* L3 cache descriptors
*/
-static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
+static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb)
{
+ struct amd_l3_cache *l3 = &nb->l3_cache;
unsigned int sc0, sc1, sc2, sc3;
u32 val = 0;
- pci_read_config_dword(l3->nb->misc, 0x1C4, &val);
+ pci_read_config_dword(nb->misc, 0x1C4, &val);
/* calculate subcache sizes */
l3->subcaches[0] = sc0 = !(val & BIT(0));
l3->subcaches[1] = sc1 = !(val & BIT(4));
+
+ if (boot_cpu_data.x86 == 0x15) {
+ l3->subcaches[0] = sc0 += !(val & BIT(1));
+ l3->subcaches[1] = sc1 += !(val & BIT(5));
+ }
+
l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9));
l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
int index)
{
- static struct amd_l3_cache *__cpuinitdata l3_caches;
int node;
/* only for L3, and not in virtualized environments */
- if (index < 3 || amd_nb_num() == 0)
+ if (index < 3)
return;
- /*
- * Strictly speaking, the amount in @size below is leaked since it is
- * never freed but this is done only on shutdown so it doesn't matter.
- */
- if (!l3_caches) {
- int size = amd_nb_num() * sizeof(struct amd_l3_cache);
-
- l3_caches = kzalloc(size, GFP_ATOMIC);
- if (!l3_caches)
- return;
- }
-
node = amd_get_nb_id(smp_processor_id());
-
- if (!l3_caches[node].nb) {
- l3_caches[node].nb = node_to_amd_nb(node);
- amd_calc_l3_indices(&l3_caches[node]);
- }
-
- this_leaf->l3 = &l3_caches[node];
+ this_leaf->nb = node_to_amd_nb(node);
+ if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
+ amd_calc_l3_indices(this_leaf->nb);
}
/*
*
* @returns: the disabled index if used or negative value if slot free.
*/
-int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
+int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
{
unsigned int reg = 0;
- pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, ®);
+ pci_read_config_dword(nb->misc, 0x1BC + slot * 4, ®);
/* check whether this slot is activated already */
if (reg & (3UL << 30))
{
int index;
- if (!this_leaf->l3 ||
- !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
return -EINVAL;
- index = amd_get_l3_disable_slot(this_leaf->l3, slot);
+ index = amd_get_l3_disable_slot(this_leaf->base.nb, slot);
if (index >= 0)
return sprintf(buf, "%d\n", index);
SHOW_CACHE_DISABLE(0)
SHOW_CACHE_DISABLE(1)
-static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
+static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
unsigned slot, unsigned long idx)
{
int i;
for (i = 0; i < 4; i++) {
u32 reg = idx | (i << 20);
- if (!l3->subcaches[i])
+ if (!nb->l3_cache.subcaches[i])
continue;
- pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
+ pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
/*
* We need to WBINVD on a core on the node containing the L3
wbinvd_on_cpu(cpu);
reg |= BIT(31);
- pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
+ pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
}
}
*
* @return: 0 on success, error status on failure
*/
-int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot,
+int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
unsigned long index)
{
int ret = 0;
/* check if @slot is already used or the index is already disabled */
- ret = amd_get_l3_disable_slot(l3, slot);
+ ret = amd_get_l3_disable_slot(nb, slot);
if (ret >= 0)
return -EINVAL;
- if (index > l3->indices)
+ if (index > nb->l3_cache.indices)
return -EINVAL;
/* check whether the other slot has disabled the same index already */
- if (index == amd_get_l3_disable_slot(l3, !slot))
+ if (index == amd_get_l3_disable_slot(nb, !slot))
return -EINVAL;
- amd_l3_disable_index(l3, cpu, slot, index);
+ amd_l3_disable_index(nb, cpu, slot, index);
return 0;
}
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!this_leaf->l3 ||
- !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
return -EINVAL;
cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
if (strict_strtoul(buf, 10, &val) < 0)
return -EINVAL;
- err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val);
+ err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val);
if (err) {
if (err == -EEXIST)
printk(KERN_WARNING "L3 disable slot %d in use!\n",
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))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
return -EINVAL;
return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
return -EINVAL;
if (strict_strtoul(buf, 16, &val) < 0)
return;
}
this_leaf = CPUID4_INFO_IDX(cpu, index);
- num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
+ num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
for (i = 0; i < num_cache_leaves; i++)
cache_remove_shared_cpu_map(cpu, i);
- kfree(per_cpu(ici_cpuid4_info, cpu)->l3);
kfree(per_cpu(ici_cpuid4_info, cpu));
per_cpu(ici_cpuid4_info, cpu) = NULL;
}
-static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
-{
- struct _cpuid4_info_regs *leaf_regs =
- (struct _cpuid4_info_regs *)this_leaf;
-
- return cpuid4_cache_lookup_regs(index, leaf_regs);
-}
-
static void __cpuinit get_cpu_leaves(void *_retval)
{
int j, *retval = _retval, cpu = smp_processor_id();
/* Do cpuid and store the results */
for (j = 0; j < num_cache_leaves; j++) {
- struct _cpuid4_info *this_leaf;
- this_leaf = CPUID4_INFO_IDX(cpu, j);
- *retval = cpuid4_cache_lookup(j, this_leaf);
+ struct _cpuid4_info *this_leaf = CPUID4_INFO_IDX(cpu, j);
+
+ *retval = cpuid4_cache_lookup_regs(j, &this_leaf->base);
if (unlikely(*retval < 0)) {
int i;
return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \
}
-show_one_plus(level, eax.split.level, 0);
-show_one_plus(coherency_line_size, ebx.split.coherency_line_size, 1);
-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);
+show_one_plus(level, base.eax.split.level, 0);
+show_one_plus(coherency_line_size, base.ebx.split.coherency_line_size, 1);
+show_one_plus(physical_line_partition, base.ebx.split.physical_line_partition, 1);
+show_one_plus(ways_of_associativity, base.ebx.split.ways_of_associativity, 1);
+show_one_plus(number_of_sets, base.ecx.split.number_of_sets, 1);
static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf,
unsigned int cpu)
{
- return sprintf(buf, "%luK\n", this_leaf->size / 1024);
+ return sprintf(buf, "%luK\n", this_leaf->base.size / 1024);
}
static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf,
unsigned int cpu)
{
- switch (this_leaf->eax.split.type) {
+ switch (this_leaf->base.eax.split.type) {
case CACHE_TYPE_DATA:
return sprintf(buf, "Data\n");
case CACHE_TYPE_INST:
ktype_cache.default_attrs = default_attrs;
#ifdef CONFIG_AMD_NB
- if (this_leaf->l3)
+ if (this_leaf->base.nb)
ktype_cache.default_attrs = amd_l3_attrs();
#endif
retval = kobject_init_and_add(&(this_object->kobj),
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/uaccess.h>
+#include <linux/elf.h>
#include <asm/ia32.h>
#include <asm/syscalls.h>
+/*
+ * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
+ *
+ * @flags denotes the allocation direction - bottomup or topdown -
+ * or vDSO; see call sites below.
+ */
+unsigned long align_addr(unsigned long addr, struct file *filp,
+ enum align_flags flags)
+{
+ unsigned long tmp_addr;
+
+ /* handle 32- and 64-bit case with a single conditional */
+ if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
+ return addr;
+
+ if (!(current->flags & PF_RANDOMIZE))
+ return addr;
+
+ if (!((flags & ALIGN_VDSO) || filp))
+ return addr;
+
+ tmp_addr = addr;
+
+ /*
+ * We need an address which is <= than the original
+ * one only when in topdown direction.
+ */
+ if (!(flags & ALIGN_TOPDOWN))
+ tmp_addr += va_align.mask;
+
+ tmp_addr &= ~va_align.mask;
+
+ return tmp_addr;
+}
+
+static int __init control_va_addr_alignment(char *str)
+{
+ /* guard against enabling this on other CPU families */
+ if (va_align.flags < 0)
+ return 1;
+
+ if (*str == 0)
+ return 1;
+
+ if (*str == '=')
+ str++;
+
+ if (!strcmp(str, "32"))
+ va_align.flags = ALIGN_VA_32;
+ else if (!strcmp(str, "64"))
+ va_align.flags = ALIGN_VA_64;
+ else if (!strcmp(str, "off"))
+ va_align.flags = 0;
+ else if (!strcmp(str, "on"))
+ va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
+ else
+ return 0;
+
+ return 1;
+}
+__setup("align_va_addr", control_va_addr_alignment);
+
SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
unsigned long, fd, unsigned long, off)
start_addr = addr;
full_search:
+
+ addr = align_addr(addr, filp, 0);
+
for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
/* At this point: (!vma || addr < vma->vm_end). */
if (end - len < addr) {
mm->cached_hole_size = vma->vm_start - addr;
addr = vma->vm_end;
+ addr = align_addr(addr, filp, 0);
}
}
/* make sure it can fit in the remaining address space */
if (addr > len) {
- vma = find_vma(mm, addr-len);
- if (!vma || addr <= vma->vm_start)
+ unsigned long tmp_addr = align_addr(addr - len, filp,
+ ALIGN_TOPDOWN);
+
+ vma = find_vma(mm, tmp_addr);
+ if (!vma || tmp_addr + len <= vma->vm_start)
/* remember the address as a hint for next time */
- return mm->free_area_cache = addr-len;
+ return mm->free_area_cache = tmp_addr;
}
if (mm->mmap_base < len)
addr = mm->mmap_base-len;
do {
+ addr = align_addr(addr, filp, ALIGN_TOPDOWN);
+
/*
* Lookup failure means no vma is above this address,
* else if new region fits below vma->vm_start,
git.openpandora.org / pandora-kernel.git / commitdiff