aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/amd.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu/amd.c')
-rw-r--r--arch/x86/kernel/cpu/amd.c494
1 files changed, 386 insertions, 108 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e485825130d..ce8b8ff0e0e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1,21 +1,55 @@
-#include <linux/init.h>
+#include <linux/export.h>
#include <linux/bitops.h>
+#include <linux/elf.h>
#include <linux/mm.h>
#include <linux/io.h>
+#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cpu.h>
#include <asm/pci-direct.h>
#ifdef CONFIG_X86_64
-# include <asm/numa_64.h>
# include <asm/mmconfig.h>
# include <asm/cacheflush.h>
#endif
#include "cpu.h"
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+ u32 gprs[8] = { 0 };
+ int err;
+
+ WARN_ONCE((boot_cpu_data.x86 != 0xf),
+ "%s should only be used on K8!\n", __func__);
+
+ gprs[1] = msr;
+ gprs[7] = 0x9c5a203a;
+
+ err = rdmsr_safe_regs(gprs);
+
+ *p = gprs[0] | ((u64)gprs[2] << 32);
+
+ return err;
+}
+
+static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+{
+ u32 gprs[8] = { 0 };
+
+ WARN_ONCE((boot_cpu_data.x86 != 0xf),
+ "%s should only be used on K8!\n", __func__);
+
+ gprs[0] = (u32)val;
+ gprs[1] = msr;
+ gprs[2] = val >> 32;
+ gprs[7] = 0x9c5a203a;
+
+ return wrmsr_safe_regs(gprs);
+}
+
#ifdef CONFIG_X86_32
/*
* B step AMD K6 before B 9730xxxx have hardware bugs that can cause
@@ -23,17 +57,18 @@
* contact AMD for precise details and a CPU swap.
*
* See http://www.multimania.com/poulot/k6bug.html
- * http://www.amd.com/K6/k6docs/revgd.html
+ * and section 2.6.2 of "AMD-K6 Processor Revision Guide - Model 6"
+ * (Publication # 21266 Issue Date: August 1998)
*
* The following test is erm.. interesting. AMD neglected to up
* the chip setting when fixing the bug but they also tweaked some
* performance at the same time..
*/
-extern void vide(void);
-__asm__(".align 4\nvide: ret");
+extern __visible void vide(void);
+__asm__(".globl vide\n\t.align 4\nvide: ret");
-static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c)
+static void init_amd_k5(struct cpuinfo_x86 *c)
{
/*
* General Systems BIOSen alias the cpu frequency registers
@@ -51,10 +86,10 @@ static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c)
}
-static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
+static void init_amd_k6(struct cpuinfo_x86 *c)
{
u32 l, h;
- int mbytes = num_physpages >> (20-PAGE_SHIFT);
+ int mbytes = get_num_physpages() >> (20-PAGE_SHIFT);
if (c->x86_model < 6) {
/* Based on AMD doc 20734R - June 2000 */
@@ -91,7 +126,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
"system stability may be impaired when more than 32 MB are used.\n");
else
printk(KERN_CONT "probably OK (after B9730xxxx).\n");
- printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
}
/* K6 with old style WHCR */
@@ -144,11 +178,10 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
}
}
-static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
+static void amd_k7_smp_check(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_SMP
/* calling is from identify_secondary_cpu() ? */
- if (c->cpu_index == boot_cpu_id)
+ if (!c->cpu_index)
return;
/*
@@ -158,11 +191,11 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
/* Athlon 660/661 is valid. */
if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
(c->x86_mask == 1)))
- goto valid_k7;
+ return;
/* Duron 670 is valid */
if ((c->x86_model == 7) && (c->x86_mask == 0))
- goto valid_k7;
+ return;
/*
* Athlon 662, Duron 671, and Athlon >model 7 have capability
@@ -175,7 +208,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
((c->x86_model == 7) && (c->x86_mask >= 1)) ||
(c->x86_model > 7))
if (cpu_has_mp)
- goto valid_k7;
+ return;
/* If we get here, not a certified SMP capable AMD system. */
@@ -185,15 +218,10 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
*/
WARN_ONCE(1, "WARNING: This combination of AMD"
" processors is not suitable for SMP.\n");
- if (!test_taint(TAINT_UNSAFE_SMP))
- add_taint(TAINT_UNSAFE_SMP);
-
-valid_k7:
- ;
-#endif
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
}
-static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
+static void init_amd_k7(struct cpuinfo_x86 *c)
{
u32 l, h;
@@ -205,9 +233,7 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
if (c->x86_model >= 6 && c->x86_model <= 10) {
if (!cpu_has(c, X86_FEATURE_XMM)) {
printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
- rdmsr(MSR_K7_HWCR, l, h);
- l &= ~0x00008000;
- wrmsr(MSR_K7_HWCR, l, h);
+ msr_clear_bit(MSR_K7_HWCR, 15);
set_cpu_cap(c, X86_FEATURE_XMM);
}
}
@@ -233,18 +259,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
}
#endif
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
-static int __cpuinit nearby_node(int apicid)
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config. Read the comment in
+ * srat_detect_node().
+ */
+static int nearby_node(int apicid)
{
int i, node;
for (i = apicid - 1; i >= 0; i--) {
- node = apicid_to_node[i];
+ node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
- node = apicid_to_node[i];
+ node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
@@ -253,45 +283,63 @@ static int __cpuinit nearby_node(int apicid)
#endif
/*
- * Fixup core topology information for AMD multi-node processors.
- * Assumption: Number of cores in each internal node is the same.
+ * Fixup core topology information for
+ * (1) AMD multi-node processors
+ * Assumption: Number of cores in each internal node is the same.
+ * (2) AMD processors supporting compute units
*/
#ifdef CONFIG_X86_HT
-static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+static void amd_get_topology(struct cpuinfo_x86 *c)
{
- unsigned long long value;
- u32 nodes, cores_per_node;
+ u32 nodes, cores_per_cu = 1;
+ u8 node_id;
int cpu = smp_processor_id();
- if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
+ /* get information required for multi-node processors */
+ if (cpu_has_topoext) {
+ u32 eax, ebx, ecx, edx;
+
+ cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+ nodes = ((ecx >> 8) & 7) + 1;
+ node_id = ecx & 7;
+
+ /* 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;
+
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+ nodes = ((value >> 3) & 7) + 1;
+ node_id = value & 7;
+ } else
return;
- /* fixup topology information only once for a core */
- if (cpu_has(c, X86_FEATURE_AMD_DCM))
- return;
+ /* fixup multi-node processor information */
+ if (nodes > 1) {
+ u32 cores_per_node;
+ u32 cus_per_node;
- rdmsrl(MSR_FAM10H_NODE_ID, value);
+ 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;
- nodes = ((value >> 3) & 7) + 1;
- if (nodes == 1)
- return;
+ /* store NodeID, use llc_shared_map to store sibling info */
+ per_cpu(cpu_llc_id, cpu) = node_id;
- set_cpu_cap(c, X86_FEATURE_AMD_DCM);
- cores_per_node = c->x86_max_cores / nodes;
-
- /* store NodeID, use llc_shared_map to store sibling info */
- per_cpu(cpu_llc_id, cpu) = value & 7;
-
- /* fixup 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
/*
- * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
+ * On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
* Assumes number of cores is a power of two.
*/
-static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
+static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_HT
unsigned bits;
@@ -304,15 +352,13 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
c->phys_proc_id = c->initial_apicid >> bits;
/* use socket ID also for last level cache */
per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
- /* fixup topology information on multi-node processors */
- if ((c->x86 == 0x10) && (c->x86_model == 9))
- amd_fixup_dcm(c);
+ amd_get_topology(c);
#endif
}
-int amd_get_nb_id(int cpu)
+u16 amd_get_nb_id(int cpu)
{
- int id = 0;
+ u16 id = 0;
#ifdef CONFIG_SMP
id = per_cpu(cpu_llc_id, cpu);
#endif
@@ -320,33 +366,50 @@ int amd_get_nb_id(int cpu)
}
EXPORT_SYMBOL_GPL(amd_get_nb_id);
-static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
+static void srat_detect_node(struct cpuinfo_x86 *c)
{
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
unsigned apicid = c->apicid;
- node = per_cpu(cpu_llc_id, cpu);
+ node = numa_cpu_node(cpu);
+ if (node == NUMA_NO_NODE)
+ node = per_cpu(cpu_llc_id, cpu);
- if (apicid_to_node[apicid] != NUMA_NO_NODE)
- node = apicid_to_node[apicid];
- if (!node_online(node)) {
- /* Two possibilities here:
- - The CPU is missing memory and no node was created.
- In that case try picking one from a nearby CPU
- - The APIC IDs differ from the HyperTransport node IDs
- which the K8 northbridge parsing fills in.
- Assume they are all increased by a constant offset,
- but in the same order as the HT nodeids.
- If that doesn't result in a usable node fall back to the
- path for the previous case. */
+ /*
+ * On multi-fabric platform (e.g. Numascale NumaChip) a
+ * platform-specific handler needs to be called to fixup some
+ * IDs of the CPU.
+ */
+ if (x86_cpuinit.fixup_cpu_id)
+ x86_cpuinit.fixup_cpu_id(c, node);
+ if (!node_online(node)) {
+ /*
+ * Two possibilities here:
+ *
+ * - The CPU is missing memory and no node was created. In
+ * that case try picking one from a nearby CPU.
+ *
+ * - The APIC IDs differ from the HyperTransport node IDs
+ * which the K8 northbridge parsing fills in. Assume
+ * they are all increased by a constant offset, but in
+ * the same order as the HT nodeids. If that doesn't
+ * result in a usable node fall back to the path for the
+ * previous case.
+ *
+ * This workaround operates directly on the mapping between
+ * APIC ID and NUMA node, assuming certain relationship
+ * between APIC ID, HT node ID and NUMA topology. As going
+ * through CPU mapping may alter the outcome, directly
+ * access __apicid_to_node[].
+ */
int ht_nodeid = c->initial_apicid;
if (ht_nodeid >= 0 &&
- apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
- node = apicid_to_node[ht_nodeid];
+ __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+ node = __apicid_to_node[ht_nodeid];
/* Pick a nearby node */
if (!node_online(node))
node = nearby_node(apicid);
@@ -355,7 +418,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
-static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
+static void early_init_amd_mc(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_HT
unsigned bits, ecx;
@@ -381,7 +444,35 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
#endif
}
-static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
+static void bsp_init_amd(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+
+ if (c->x86 > 0x10 ||
+ (c->x86 == 0x10 && c->x86_model >= 0x2)) {
+ u64 val;
+
+ rdmsrl(MSR_K7_HWCR, val);
+ if (!(val & BIT(24)))
+ printk(KERN_WARNING FW_BUG "TSC doesn't count "
+ "with P0 frequency!\n");
+ }
+ }
+
+ if (c->x86 == 0x15) {
+ unsigned long upperbit;
+ u32 cpuid, assoc;
+
+ cpuid = cpuid_edx(0x80000005);
+ assoc = cpuid >> 16 & 0xff;
+ upperbit = ((cpuid >> 24) << 10) / assoc;
+
+ va_align.mask = (upperbit - 1) & PAGE_MASK;
+ va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
+ }
+}
+
+static void early_init_amd(struct cpuinfo_x86 *c)
{
early_init_amd_mc(c);
@@ -392,6 +483,8 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+ if (!check_tsc_unstable())
+ set_sched_clock_stable();
}
#ifdef CONFIG_X86_64
@@ -412,13 +505,22 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
}
#endif
+
+ /* F16h erratum 793, CVE-2013-6885 */
+ if (c->x86 == 0x16 && c->x86_model <= 0xf)
+ msr_set_bit(MSR_AMD64_LS_CFG, 15);
}
-static void __cpuinit init_amd(struct cpuinfo_x86 *c)
+static const int amd_erratum_383[];
+static const int amd_erratum_400[];
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
+
+static void init_amd(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_SMP
+ u32 dummy;
unsigned long long value;
+#ifdef CONFIG_SMP
/*
* Disable TLB flush filter by setting HWCR.FFDIS on K8
* bit 6 of msr C001_0015
@@ -426,11 +528,8 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
* Errata 63 for SH-B3 steppings
* Errata 122 for all steppings (F+ have it disabled by default)
*/
- if (c->x86 == 0xf) {
- rdmsrl(MSR_K7_HWCR, value);
- value |= 1 << 6;
- wrmsrl(MSR_K7_HWCR, value);
- }
+ if (c->x86 == 0xf)
+ msr_set_bit(MSR_K7_HWCR, 6);
#endif
early_init_amd(c);
@@ -456,17 +555,15 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
* (AMD Erratum #110, docId: 25759).
*/
if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
- u64 val;
-
clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
- if (!rdmsrl_amd_safe(0xc001100d, &val)) {
- val &= ~(1ULL << 32);
- wrmsrl_amd_safe(0xc001100d, val);
+ if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+ value &= ~(1ULL << 32);
+ wrmsrl_amd_safe(0xc001100d, value);
}
}
}
- if (c->x86 == 0x10 || c->x86 == 0x11)
+ if (c->x86 >= 0x10)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
/* get apicid instead of initial apic id from cpuid */
@@ -510,6 +607,33 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
}
+ /* re-enable TopologyExtensions if switched off by BIOS */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+ !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+
+ if (msr_set_bit(0xc0011005, 54) > 0) {
+ rdmsrl(0xc0011005, value);
+ if (value & BIT_64(54)) {
+ set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+ pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+ }
+ }
+ }
+
+ /*
+ * The way access filter has a performance penalty on some workloads.
+ * Disable it on the affected CPUs.
+ */
+ if ((c->x86 == 0x15) &&
+ (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+
+ if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) {
+ value |= 0x1E;
+ wrmsrl_safe(0xc0011021, value);
+ }
+ }
+
cpu_detect_cache_sizes(c);
/* Multi core CPU? */
@@ -522,14 +646,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
detect_ht(c);
#endif
- if (c->extended_cpuid_level >= 0x80000006) {
- if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
- num_cache_leaves = 4;
- else
- num_cache_leaves = 3;
- }
+ init_amd_cacheinfo(c);
- if (c->x86 >= 0xf && c->x86 <= 0x11)
+ if (c->x86 >= 0xf)
set_cpu_cap(c, X86_FEATURE_K8);
if (cpu_has_xmm2) {
@@ -546,7 +665,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
fam10h_check_enable_mmcfg();
}
- if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+ if (c == &boot_cpu_data && c->x86 >= 0xf) {
unsigned long long tseg;
/*
@@ -555,21 +674,58 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
* benefit in doing so.
*/
if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ unsigned long pfn = tseg >> PAGE_SHIFT;
+
printk(KERN_DEBUG "tseg: %010llx\n", tseg);
- if ((tseg>>PMD_SHIFT) <
- (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
- ((tseg>>PMD_SHIFT) <
- (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
- (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
+ if (pfn_range_is_mapped(pfn, pfn + 1))
set_memory_4k((unsigned long)__va(tseg), 1);
}
}
#endif
+
+ /*
+ * Family 0x12 and above processors have APIC timer
+ * running in deep C states.
+ */
+ if (c->x86 > 0x11)
+ set_cpu_cap(c, X86_FEATURE_ARAT);
+
+ if (c->x86 == 0x10) {
+ /*
+ * Disable GART TLB Walk Errors on Fam10h. We do this here
+ * because this is always needed when GART is enabled, even in a
+ * kernel which has no MCE support built in.
+ * BIOS should disable GartTlbWlk Errors already. If
+ * it doesn't, do it here as suggested by the BKDG.
+ *
+ * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+ */
+ msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
+
+ /*
+ * On family 10h BIOS may not have properly enabled WC+ support,
+ * causing it to be converted to CD memtype. This may result in
+ * performance degradation for certain nested-paging guests.
+ * Prevent this conversion by clearing bit 24 in
+ * MSR_AMD64_BU_CFG2.
+ *
+ * NOTE: we want to use the _safe accessors so as not to #GP kvm
+ * guests on older kvm hosts.
+ */
+ msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
+
+ if (cpu_has_amd_erratum(c, amd_erratum_383))
+ set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+ }
+
+ if (cpu_has_amd_erratum(c, amd_erratum_400))
+ set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
+
+ rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
}
#ifdef CONFIG_X86_32
-static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c,
- unsigned int size)
+static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
{
/* AMD errata T13 (order #21922) */
if ((c->x86 == 6)) {
@@ -585,12 +741,68 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c,
}
#endif
-static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
+static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
+{
+ tlb_flushall_shift = 6;
+}
+
+static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
+{
+ u32 ebx, eax, ecx, edx;
+ u16 mask = 0xfff;
+
+ if (c->x86 < 0xf)
+ return;
+
+ if (c->extended_cpuid_level < 0x80000006)
+ return;
+
+ cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
+
+ tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
+ tlb_lli_4k[ENTRIES] = ebx & mask;
+
+ /*
+ * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
+ * characteristics from the CPUID function 0x80000005 instead.
+ */
+ if (c->x86 == 0xf) {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ mask = 0xff;
+ }
+
+ /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!((eax >> 16) & mask))
+ tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+ else
+ tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+
+ /* a 4M entry uses two 2M entries */
+ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+
+ /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!(eax & mask)) {
+ /* Erratum 658 */
+ if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
+ tlb_lli_2m[ENTRIES] = 1024;
+ } else {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ tlb_lli_2m[ENTRIES] = eax & 0xff;
+ }
+ } else
+ tlb_lli_2m[ENTRIES] = eax & mask;
+
+ tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+
+ cpu_set_tlb_flushall_shift(c);
+}
+
+static const struct cpu_dev amd_cpu_dev = {
.c_vendor = "AMD",
.c_ident = { "AuthenticAMD" },
#ifdef CONFIG_X86_32
- .c_models = {
- { .vendor = X86_VENDOR_AMD, .family = 4, .model_names =
+ .legacy_models = {
+ { .family = 4, .model_names =
{
[3] = "486 DX/2",
[7] = "486 DX/2-WB",
@@ -601,11 +813,77 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
}
},
},
- .c_size_cache = amd_size_cache,
+ .legacy_cache_size = amd_size_cache,
#endif
.c_early_init = early_init_amd,
+ .c_detect_tlb = cpu_detect_tlb_amd,
+ .c_bsp_init = bsp_init_amd,
.c_init = init_amd,
.c_x86_vendor = X86_VENDOR_AMD,
};
cpu_dev_register(amd_cpu_dev);
+
+/*
+ * AMD errata checking
+ *
+ * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
+ * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
+ * have an OSVW id assigned, which it takes as first argument. Both take a
+ * variable number of family-specific model-stepping ranges created by
+ * AMD_MODEL_RANGE().
+ *
+ * Example:
+ *
+ * const int amd_erratum_319[] =
+ * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
+ * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
+ * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
+ */
+
+#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 }
+#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 }
+#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
+ ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
+#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff)
+#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff)
+#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff)
+
+static const int amd_erratum_400[] =
+ AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+ AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
+
+static const int amd_erratum_383[] =
+ AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
+
+
+static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
+{
+ int osvw_id = *erratum++;
+ u32 range;
+ u32 ms;
+
+ if (osvw_id >= 0 && osvw_id < 65536 &&
+ cpu_has(cpu, X86_FEATURE_OSVW)) {
+ u64 osvw_len;
+
+ rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
+ if (osvw_id < osvw_len) {
+ u64 osvw_bits;
+
+ rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
+ osvw_bits);
+ return osvw_bits & (1ULL << (osvw_id & 0x3f));
+ }
+ }
+
+ /* OSVW unavailable or ID unknown, match family-model-stepping range */
+ ms = (cpu->x86_model << 4) | cpu->x86_mask;
+ while ((range = *erratum++))
+ if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
+ (ms >= AMD_MODEL_RANGE_START(range)) &&
+ (ms <= AMD_MODEL_RANGE_END(range)))
+ return true;
+
+ return false;
+}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 11:48:20 +0000