Skip to contentSkip to conversation

i386/tcg: implement x2APIC registers MSR access

PATCH Superseded Bui Quang Minh 1 participant 5 messages Apr 9, 2023

v3 of 12 Superseded Latest is v12 →

lore
Share & tools
lore
#0 lore raw

PATCH v3 1/5 i386/tcg: implement x2APIC registers MSR access

This commit refactors apic_mem_read/write to support both MMIO access in xAPIC and MSR access in x2APIC.

---
 hw/intc/apic.c                       | 79 ++++++++++++++++++----------
 hw/intc/trace-events                 |  4 +-
 include/hw/i386/apic.h               |  3 ++
 target/i386/cpu.h                    |  3 ++
 target/i386/tcg/sysemu/misc_helper.c | 27 ++++++++++
 5 files changed, 86 insertions(+), 30 deletions(-)
hw/intc/apic.c +51 -28
index 20b5a94073..61b494b20a 100644
@@ -288,6 +288,13 @@ void apic_deliver_irq(uint8_t dest, uint8_t dest_mode, uint8_t delivery_mode,
     apic_bus_deliver(deliver_bitmask, delivery_mode, vector_num, trigger_mode);
 }
 
+bool is_x2apic_mode(DeviceState *dev)
+{
+    APICCommonState *s = APIC(dev);
+
+    return s->apicbase & MSR_IA32_APICBASE_EXTD;
+}
+
 static void apic_set_base(APICCommonState *s, uint64_t val)
 {
     s->apicbase = (val & 0xfffff000) |
@@ -636,16 +643,11 @@ static void apic_timer(void *opaque)
     apic_timer_update(s, s->next_time);
 }
 
-static uint64_t apic_mem_read(void *opaque, hwaddr addr, unsigned size)
+uint64_t apic_register_read(int index)
 {
     DeviceState *dev;
     APICCommonState *s;
-    uint32_t val;
-    int index;
-
-    if (size < 4) {
-        return 0;
-    }
+    uint64_t val;
 
     dev = cpu_get_current_apic();
     if (!dev) {
@@ -653,7 +655,6 @@ static uint64_t apic_mem_read(void *opaque, hwaddr addr, unsigned size)
     }
     s = APIC(dev);
 
-    index = (addr >> 4) & 0xff;
     switch(index) {
     case 0x02: /* id */
         val = s->id << 24;
@@ -720,7 +721,23 @@ static uint64_t apic_mem_read(void *opaque, hwaddr addr, unsigned size)
         val = 0;
         break;
     }
-    trace_apic_mem_readl(addr, val);
+
+    trace_apic_register_read(index, val);
+    return val;
+}
+
+static uint64_t apic_mem_read(void *opaque, hwaddr addr, unsigned size)
+{
+    uint32_t val;
+    int index;
+
+    if (size < 4) {
+        return 0;
+    }
+
+    index = (addr >> 4) & 0xff;
+    val = (uint32_t)apic_register_read(index);
+
     return val;
 }
 
@@ -737,27 +754,10 @@ static void apic_send_msi(MSIMessage *msi)
     apic_deliver_irq(dest, dest_mode, delivery, vector, trigger_mode);
 }
 
-static void apic_mem_write(void *opaque, hwaddr addr, uint64_t val,
-                           unsigned size)
+void apic_register_write(int index, uint64_t val)
 {
     DeviceState *dev;
     APICCommonState *s;
-    int index = (addr >> 4) & 0xff;
-
-    if (size < 4) {
-        return;
-    }
-
-    if (addr > 0xfff || !index) {
-        /* MSI and MMIO APIC are at the same memory location,
-         * but actually not on the global bus: MSI is on PCI bus
-         * APIC is connected directly to the CPU.
-         * Mapping them on the global bus happens to work because
-         * MSI registers are reserved in APIC MMIO and vice versa. */
-        MSIMessage msi = { .address = addr, .data = val };
-        apic_send_msi(&msi);
-        return;
-    }
 
     dev = cpu_get_current_apic();
     if (!dev) {
@@ -765,7 +765,7 @@ static void apic_mem_write(void *opaque, hwaddr addr, uint64_t val,
     }
     s = APIC(dev);
 
-    trace_apic_mem_writel(addr, val);
+    trace_apic_register_write(index, val);
 
     switch(index) {
     case 0x02:
@@ -843,6 +843,29 @@ static void apic_mem_write(void *opaque, hwaddr addr, uint64_t val,
     }
 }
 
+static void apic_mem_write(void *opaque, hwaddr addr, uint64_t val,
+                           unsigned size)
+{
+    int index = (addr >> 4) & 0xff;
+
+    if (size < 4) {
+        return;
+    }
+
+    if (addr > 0xfff || !index) {
+        /* MSI and MMIO APIC are at the same memory location,
+         * but actually not on the global bus: MSI is on PCI bus
+         * APIC is connected directly to the CPU.
+         * Mapping them on the global bus happens to work because
+         * MSI registers are reserved in APIC MMIO and vice versa. */
+        MSIMessage msi = { .address = addr, .data = val };
+        apic_send_msi(&msi);
+        return;
+    }
+
+    apic_register_write(index, val);
+}
+
 static void apic_pre_save(APICCommonState *s)
 {
     apic_sync_vapic(s, SYNC_FROM_VAPIC);
hw/intc/trace-events +2 -2
index 50cadfb996..9d4e7a67be 100644
@@ -14,8 +14,8 @@ cpu_get_apic_base(uint64_t val) "0x%016"PRIx64
 # apic.c
 apic_local_deliver(int vector, uint32_t lvt) "vector %d delivery mode %d"
 apic_deliver_irq(uint8_t dest, uint8_t dest_mode, uint8_t delivery_mode, uint8_t vector_num, uint8_t trigger_mode) "dest %d dest_mode %d delivery_mode %d vector %d trigger_mode %d"
-apic_mem_readl(uint64_t addr, uint32_t val)  "0x%"PRIx64" = 0x%08x"
-apic_mem_writel(uint64_t addr, uint32_t val) "0x%"PRIx64" = 0x%08x"
+apic_register_read(uint8_t reg, uint64_t val) "register 0x%02x = 0x%"PRIx64
+apic_register_write(uint8_t reg, uint64_t val) "register 0x%02x = 0x%"PRIx64
 
 # ioapic.c
 ioapic_set_remote_irr(int n) "set remote irr for pin %d"
include/hw/i386/apic.h +3 -0
index bdc15a7a73..2cebeb4faf 100644
@@ -18,6 +18,9 @@ void apic_sipi(DeviceState *s);
 void apic_poll_irq(DeviceState *d);
 void apic_designate_bsp(DeviceState *d, bool bsp);
 int apic_get_highest_priority_irr(DeviceState *dev);
+uint64_t apic_register_read(int index);
+void apic_register_write(int index, uint64_t val);
+bool is_x2apic_mode(DeviceState *d);
 
 /* pc.c */
 DeviceState *cpu_get_current_apic(void);
target/i386/cpu.h +3 -0
index d243e290d3..02165a5ad2 100644
@@ -545,6 +545,9 @@ typedef enum X86Seg {
 #define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
 #define MSR_IA32_VMX_VMFUNC             0x00000491
 
+#define MSR_APIC_START                  0x00000800
+#define MSR_APIC_END                    0x000008ff
+
 #define XSTATE_FP_BIT                   0
 #define XSTATE_SSE_BIT                  1
 #define XSTATE_YMM_BIT                  2
target/i386/tcg/sysemu/misc_helper.c +27 -0
index e1528b7f80..1fce2076a3 100644
@@ -25,6 +25,7 @@
 #include "exec/address-spaces.h"
 #include "exec/exec-all.h"
 #include "tcg/helper-tcg.h"
+#include "hw/i386/apic.h"
 
 void helper_outb(CPUX86State *env, uint32_t port, uint32_t data)
 {
@@ -289,6 +290,19 @@ void helper_wrmsr(CPUX86State *env)
         env->msr_bndcfgs = val;
         cpu_sync_bndcs_hflags(env);
         break;
+    case MSR_APIC_START ... MSR_APIC_END: {
+        int index = (uint32_t)env->regs[R_ECX] - MSR_APIC_START;
+
+        if (!is_x2apic_mode(env_archcpu(env)->apic_state)) {
+            goto error;
+        }
+
+        qemu_mutex_lock_iothread();
+        apic_register_write(index, val);
+        qemu_mutex_unlock_iothread();
+
+        break;
+    }
     default:
         if ((uint32_t)env->regs[R_ECX] >= MSR_MC0_CTL
             && (uint32_t)env->regs[R_ECX] < MSR_MC0_CTL +
@@ -455,6 +469,19 @@ void helper_rdmsr(CPUX86State *env)
         val = (cs->nr_threads * cs->nr_cores) | (cs->nr_cores << 16);
         break;
     }
+    case MSR_APIC_START ... MSR_APIC_END: {
+        int index = (uint32_t)env->regs[R_ECX] - MSR_APIC_START;
+
+        if (!is_x2apic_mode(env_archcpu(env)->apic_state)) {
+            raise_exception_ra(env, EXCP0D_GPF, GETPC());
+        }
+
+        qemu_mutex_lock_iothread();
+        val = apic_register_read(index);
+        qemu_mutex_unlock_iothread();
+
+        break;
+    }
     default:
         if ((uint32_t)env->regs[R_ECX] >= MSR_MC0_CTL
             && (uint32_t)env->regs[R_ECX] < MSR_MC0_CTL +
Signature · 1 line
2.25.1
#1 lore raw

PATCH v3 2/5 apic: add support for x2APIC mode

This commit extends the APIC ID to 32-bit long and remove the 255 max APIC ID limit in userspace APIC. The array that manages local APICs is now dynamically allocated based on the max APIC ID of created x86 machine. Also, new x2APIC IPI destination determination scheme, self IPI and x2APIC mode register access are supported.

---
Version 3 changes:
- Allow APIC ID > 255 only when x2APIC feature is supported on CPU
- Make physical destination mode IPI which has destination id 0xffffffff a broadcast to xAPIC CPUs
- Make cluster address 0xf in cluster model of xAPIC logical destination mode a broadcast to all clusters
- Create new extended_log_dest to store APIC_LDR information in x2APIC instead of extending log_dest for backward compatibility in vmstate

 hw/i386/x86.c                   |   8 +-
 hw/intc/apic.c                  | 266 ++++++++++++++++++++++++--------
 hw/intc/apic_common.c           |   9 ++
 include/hw/i386/apic.h          |   3 +-
 include/hw/i386/apic_internal.h |   7 +-
 target/i386/cpu-sysemu.c        |   8 +-
 6 files changed, 231 insertions(+), 70 deletions(-)
hw/i386/x86.c +6 -2
index a88a126123..8b70f0a6ea 100644
@@ -132,11 +132,11 @@ void x86_cpus_init(X86MachineState *x86ms, int default_cpu_version)
      * Can we support APIC ID 255 or higher?
      *
      * Under Xen: yes.
-     * With userspace emulated lapic: no
+     * With userspace emulated lapic: checked later in apic_common_set_id.
      * With KVM's in-kernel lapic: only if X2APIC API is enabled.
      */
     if (x86ms->apic_id_limit > 255 && !xen_enabled() &&
-        (!kvm_irqchip_in_kernel() || !kvm_enable_x2apic())) {
+        kvm_irqchip_in_kernel() && !kvm_enable_x2apic()) {
         error_report("current -smp configuration requires kernel "
                      "irqchip and X2APIC API support.");
         exit(EXIT_FAILURE);
@@ -146,6 +146,10 @@ void x86_cpus_init(X86MachineState *x86ms, int default_cpu_version)
         kvm_set_max_apic_id(x86ms->apic_id_limit);
     }
 
+    if (!kvm_irqchip_in_kernel()) {
+        apic_set_max_apic_id(x86ms->apic_id_limit);
+    }
+
     possible_cpus = mc->possible_cpu_arch_ids(ms);
     for (i = 0; i < ms->smp.cpus; i++) {
         x86_cpu_new(x86ms, possible_cpus->cpus[i].arch_id, &error_fatal);
hw/intc/apic.c +203 -63

430 lines not on this page · raw message

hw/intc/apic_common.c +9 -0
index 4a34f03047..d95914066e 100644
@@ -284,6 +284,10 @@ static void apic_common_realize(DeviceState *dev, Error **errp)
     }
     vmstate_register_with_alias_id(NULL, instance_id, &vmstate_apic_common,
                                    s, -1, 0, NULL);
+
+    /* APIC LDR in x2APIC mode */
+    s->extended_log_dest = ((s->initial_apic_id & 0xffff0) << 16) |
+                            (1 << (s->initial_apic_id & 0xf));
 }
 
 static void apic_common_unrealize(DeviceState *dev)
@@ -424,6 +428,11 @@ static void apic_common_set_id(Object *obj, Visitor *v, const char *name,
         return;
     }
 
+    if (value >= 255 && !cpu_has_x2apic_feature(&s->cpu->env)) {
+        error_setg(errp, "APIC ID %d requires x2APIC feature in CPU", value);
+        return;
+    }
+
     s->initial_apic_id = value;
     s->id = (uint8_t)value;
 }
include/hw/i386/apic.h +1 -2
index 2cebeb4faf..12aad09f4c 100644
@@ -3,8 +3,7 @@
 
 
 /* apic.c */
-void apic_deliver_irq(uint8_t dest, uint8_t dest_mode, uint8_t delivery_mode,
-                      uint8_t vector_num, uint8_t trigger_mode);
+void apic_set_max_apic_id(uint32_t max_apic_id);
 int apic_accept_pic_intr(DeviceState *s);
 void apic_deliver_pic_intr(DeviceState *s, int level);
 void apic_deliver_nmi(DeviceState *d);
include/hw/i386/apic_internal.h +5 -2
index 5f2ba24bfc..e796e6cae3 100644
@@ -46,8 +46,10 @@
 #define APIC_DM_EXTINT                  7
 
 /* APIC destination mode */
-#define APIC_DESTMODE_FLAT              0xf
-#define APIC_DESTMODE_CLUSTER           1
+#define APIC_DESTMODE_PHYSICAL          0
+#define APIC_DESTMODE_LOGICAL           1
+#define APIC_DESTMODE_LOGICAL_FLAT      0xf
+#define APIC_DESTMODE_LOGICAL_CLUSTER   0
 
 #define APIC_TRIGGER_EDGE               0
 #define APIC_TRIGGER_LEVEL              1
@@ -187,6 +189,7 @@ struct APICCommonState {
     DeviceState *vapic;
     hwaddr vapic_paddr; /* note: persistence via kvmvapic */
     bool legacy_instance_id;
+    uint32_t extended_log_dest;
 };
 
 typedef struct VAPICState {
target/i386/cpu-sysemu.c +7 -1
index 28115edf44..a9ff10c517 100644
@@ -281,11 +281,17 @@ void x86_cpu_apic_create(X86CPU *cpu, Error **errp)
                               OBJECT(cpu->apic_state));
     object_unref(OBJECT(cpu->apic_state));
 
-    qdev_prop_set_uint32(cpu->apic_state, "id", cpu->apic_id);
     /* TODO: convert to link<> */
     apic = APIC_COMMON(cpu->apic_state);
     apic->cpu = cpu;
     apic->apicbase = APIC_DEFAULT_ADDRESS | MSR_IA32_APICBASE_ENABLE;
+
+    /*
+     * apic_common_set_id needs to check if the CPU has x2APIC
+     * feature in case APIC ID >= 255, so we need to set apic->cpu
+     * before setting APIC ID
+     */
+    qdev_prop_set_uint32(cpu->apic_state, "id", cpu->apic_id);
 }
 
 void x86_cpu_apic_realize(X86CPU *cpu, Error **errp)
Signature · 1 line
2.25.1
#2 lore raw

PATCH v3 3/5 apic, i386/tcg: add x2apic transitions

In reply to Bui Quang Minh

This commit adds support for x2APIC transitions when writing to MSR_IA32_APICBASE register and finally adds CPUID_EXT_X2APIC to TCG_EXT_FEATURES.

---
 hw/intc/apic.c                       | 50 ++++++++++++++++++++++++++++
 hw/intc/apic_common.c                |  7 ++--
 target/i386/cpu-sysemu.c             | 10 ++++++
 target/i386/cpu.c                    |  5 +--
 target/i386/cpu.h                    |  6 ++++
 target/i386/tcg/sysemu/misc_helper.c |  4 +++
 6 files changed, 75 insertions(+), 7 deletions(-)
hw/intc/apic.c +50 -0
index 0f2f29e679..716fe865d7 100644
@@ -309,8 +309,41 @@ bool is_x2apic_mode(DeviceState *dev)
     return s->apicbase & MSR_IA32_APICBASE_EXTD;
 }
 
+static void apic_set_base_check(APICCommonState *s, uint64_t val)
+{
+    /* Enable x2apic when x2apic is not supported by CPU */
+    if (!cpu_has_x2apic_feature(&s->cpu->env) &&
+        val & MSR_IA32_APICBASE_EXTD)
+        raise_exception_ra(&s->cpu->env, EXCP0D_GPF, GETPC());
+
+    /*
+     * Transition into invalid state
+     * (s->apicbase & MSR_IA32_APICBASE_ENABLE == 0) &&
+     * (s->apicbase & MSR_IA32_APICBASE_EXTD) == 1
+     */
+    if (!(val & MSR_IA32_APICBASE_ENABLE) &&
+        (val & MSR_IA32_APICBASE_EXTD))
+        raise_exception_ra(&s->cpu->env, EXCP0D_GPF, GETPC());
+
+    /* Invalid transition from disabled mode to x2APIC */
+    if (!(s->apicbase & MSR_IA32_APICBASE_ENABLE) &&
+        !(s->apicbase & MSR_IA32_APICBASE_EXTD) &&
+        (val & MSR_IA32_APICBASE_ENABLE) &&
+        (val & MSR_IA32_APICBASE_EXTD))
+        raise_exception_ra(&s->cpu->env, EXCP0D_GPF, GETPC());
+
+    /* Invalid transition from x2APIC to xAPIC */
+    if ((s->apicbase & MSR_IA32_APICBASE_ENABLE) &&
+        (s->apicbase & MSR_IA32_APICBASE_EXTD) &&
+        (val & MSR_IA32_APICBASE_ENABLE) &&
+        !(val & MSR_IA32_APICBASE_EXTD))
+        raise_exception_ra(&s->cpu->env, EXCP0D_GPF, GETPC());
+}
+
 static void apic_set_base(APICCommonState *s, uint64_t val)
 {
+    apic_set_base_check(s, val);
+
     s->apicbase = (val & 0xfffff000) |
         (s->apicbase & (MSR_IA32_APICBASE_BSP | MSR_IA32_APICBASE_ENABLE));
     /* if disabled, cannot be enabled again */
@@ -319,6 +352,23 @@ static void apic_set_base(APICCommonState *s, uint64_t val)
         cpu_clear_apic_feature(&s->cpu->env);
         s->spurious_vec &= ~APIC_SV_ENABLE;
     }
+
+    /* Transition from disabled mode to xAPIC */
+    if (!(s->apicbase & MSR_IA32_APICBASE_ENABLE) &&
+        (val & MSR_IA32_APICBASE_ENABLE)) {
+        s->apicbase |= MSR_IA32_APICBASE_ENABLE;
+        cpu_set_apic_feature(&s->cpu->env);
+    }
+
+    /* Transition from xAPIC to x2APIC */
+    if (cpu_has_x2apic_feature(&s->cpu->env) &&
+        !(s->apicbase & MSR_IA32_APICBASE_EXTD) &&
+        (val & MSR_IA32_APICBASE_EXTD)) {
+        s->apicbase |= MSR_IA32_APICBASE_EXTD;
+
+        s->log_dest = ((s->initial_apic_id & 0xffff0) << 16) |
+                      (1 << (s->initial_apic_id & 0xf));
+    }
 }
 
 static void apic_set_tpr(APICCommonState *s, uint8_t val)
hw/intc/apic_common.c +2 -5
index d95914066e..396f828be8 100644
@@ -43,11 +43,8 @@ void cpu_set_apic_base(DeviceState *dev, uint64_t val)
     if (dev) {
         APICCommonState *s = APIC_COMMON(dev);
         APICCommonClass *info = APIC_COMMON_GET_CLASS(s);
-        /* switching to x2APIC, reset possibly modified xAPIC ID */
-        if (!(s->apicbase & MSR_IA32_APICBASE_EXTD) &&
-            (val & MSR_IA32_APICBASE_EXTD)) {
-            s->id = s->initial_apic_id;
-        }
+        /* Reset possibly modified xAPIC ID */
+        s->id = s->initial_apic_id;
         info->set_base(s, val);
     }
 }
target/i386/cpu-sysemu.c +10 -0
index a9ff10c517..f6bbe33372 100644
@@ -235,6 +235,16 @@ void cpu_clear_apic_feature(CPUX86State *env)
     env->features[FEAT_1_EDX] &= ~CPUID_APIC;
 }
 
+void cpu_set_apic_feature(CPUX86State *env)
+{
+    env->features[FEAT_1_EDX] |= CPUID_APIC;
+}
+
+bool cpu_has_x2apic_feature(CPUX86State *env)
+{
+    return env->features[FEAT_1_ECX] & CPUID_EXT_X2APIC;
+}
+
 bool cpu_is_bsp(X86CPU *cpu)
 {
     return cpu_get_apic_base(cpu->apic_state) & MSR_IA32_APICBASE_BSP;
target/i386/cpu.c +3 -2
index 6576287e5b..6847b2ae02 100644
@@ -627,12 +627,13 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1,
           CPUID_EXT_XSAVE | /* CPUID_EXT_OSXSAVE is dynamic */   \
           CPUID_EXT_MOVBE | CPUID_EXT_AES | CPUID_EXT_HYPERVISOR | \
           CPUID_EXT_RDRAND | CPUID_EXT_AVX | CPUID_EXT_F16C | \
-          CPUID_EXT_FMA)
+          CPUID_EXT_FMA | CPUID_EXT_X2APIC)
           /* missing:
           CPUID_EXT_DTES64, CPUID_EXT_DSCPL, CPUID_EXT_VMX, CPUID_EXT_SMX,
           CPUID_EXT_EST, CPUID_EXT_TM2, CPUID_EXT_CID,
           CPUID_EXT_XTPR, CPUID_EXT_PDCM, CPUID_EXT_PCID, CPUID_EXT_DCA,
-          CPUID_EXT_X2APIC, CPUID_EXT_TSC_DEADLINE_TIMER */
+          CPUID_EXT_TSC_DEADLINE_TIMER
+          */
 
 #ifdef TARGET_X86_64
 #define TCG_EXT2_X86_64_FEATURES (CPUID_EXT2_SYSCALL | CPUID_EXT2_LM)
target/i386/cpu.h +6 -0
index 02165a5ad2..53cd8f01dd 100644
@@ -379,6 +379,10 @@ typedef enum X86Seg {
 #define MSR_IA32_APICBASE_ENABLE        (1<<11)
 #define MSR_IA32_APICBASE_EXTD          (1 << 10)
 #define MSR_IA32_APICBASE_BASE          (0xfffffU<<12)
+#define MSR_IA32_APICBASE_RESERVED \
+        (~(uint64_t)(MSR_IA32_APICBASE_BSP | MSR_IA32_APICBASE_ENABLE \
+                     | MSR_IA32_APICBASE_EXTD | MSR_IA32_APICBASE_BASE))
+
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
 #define MSR_TSC_ADJUST                  0x0000003b
 #define MSR_IA32_SPEC_CTRL              0x48
@@ -2158,8 +2162,10 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                    uint32_t *eax, uint32_t *ebx,
                    uint32_t *ecx, uint32_t *edx);
 void cpu_clear_apic_feature(CPUX86State *env);
+void cpu_set_apic_feature(CPUX86State *env);
 void host_cpuid(uint32_t function, uint32_t count,
                 uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx);
+bool cpu_has_x2apic_feature(CPUX86State *env);
 
 /* helper.c */
 void x86_cpu_set_a20(X86CPU *cpu, int a20_state);
target/i386/tcg/sysemu/misc_helper.c +4 -0
index 1fce2076a3..91a58d4d97 100644
@@ -159,6 +159,10 @@ void helper_wrmsr(CPUX86State *env)
         env->sysenter_eip = val;
         break;
     case MSR_IA32_APICBASE:
+        if (val & MSR_IA32_APICBASE_RESERVED) {
+            goto error;
+        }
+
         cpu_set_apic_base(env_archcpu(env)->apic_state, val);
         break;
     case MSR_EFER:
Signature · 1 line
2.25.1
#3 lore raw

PATCH v3 4/5 intel_iommu: allow Extended Interrupt Mode when using userspace APIC

In reply to Bui Quang Minh

As userspace APIC now supports x2APIC, intel interrupt remapping hardware can be set to EIM mode when userspace local APIC is used.

---
 hw/i386/intel_iommu.c | 11 -----------
 1 file changed, 11 deletions(-)
hw/i386/intel_iommu.c +0 -11
index a62896759c..fd7c16b852 100644
@@ -4045,17 +4045,6 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
                       && x86_iommu_ir_supported(x86_iommu) ?
                                               ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
     }
-    if (s->intr_eim == ON_OFF_AUTO_ON && !s->buggy_eim) {
-        if (!kvm_irqchip_is_split()) {
-            error_setg(errp, "eim=on requires accel=kvm,kernel-irqchip=split");
-            return false;
-        }
-        if (!kvm_enable_x2apic()) {
-            error_setg(errp, "eim=on requires support on the KVM side"
-                             "(X2APIC_API, first shipped in v4.7)");
-            return false;
-        }
-    }
 
     /* Currently only address widths supported are 39 and 48 bits */
     if ((s->aw_bits != VTD_HOST_AW_39BIT) &&
Signature · 1 line
2.25.1
#4 lore raw

PATCH v3 5/5 amd_iommu: report x2APIC support to the operating system

In reply to Bui Quang Minh

This commit adds XTSup configuration to let user choose to whether enable this feature or not. When XTSup is enabled, additional bytes in IRTE with enabled guest virtual VAPIC are used to support 32-bit destination id.

Additionally, this commit changes to use IVHD type 0x11 in ACPI table for feature report to operating system. This is because Linux does not use XTSup in IOMMU Feature Reporting field of IVHD type 0x10 but only use XTSup bit in EFR Register Image of IVHD 0x11 to indicate x2APIC support (see init_iommu_one in linux/drivers/iommu/amd/init.c)

---
 hw/i386/acpi-build.c | 28 ++++++++++++++--------------
 hw/i386/amd_iommu.c  | 21 +++++++++++++++++++--
 hw/i386/amd_iommu.h  | 16 +++++++++++-----
 3 files changed, 44 insertions(+), 21 deletions(-)
hw/i386/acpi-build.c +14 -14
index ec857a117e..72d6bb2892 100644
@@ -2339,7 +2339,7 @@ static void
 build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
                 const char *oem_table_id)
 {
-    int ivhd_table_len = 24;
+    int ivhd_table_len = 40;
     AMDVIState *s = AMD_IOMMU_DEVICE(x86_iommu_get_default());
     GArray *ivhd_blob = g_array_new(false, true, 1);
     AcpiTable table = { .sig = "IVRS", .rev = 1, .oem_id = oem_id,
@@ -2349,18 +2349,19 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
     /* IVinfo - IO virtualization information common to all
      * IOMMU units in a system
      */
-    build_append_int_noprefix(table_data, 40UL << 8/* PASize */, 4);
+    build_append_int_noprefix(table_data,
+                             (1UL << 0) | /* EFRSup */
+                             (40UL << 8), /* PASize */
+                             4);
     /* reserved */
     build_append_int_noprefix(table_data, 0, 8);
 
-    /* IVHD definition - type 10h */
-    build_append_int_noprefix(table_data, 0x10, 1);
+    /* IVHD definition - type 11h */
+    build_append_int_noprefix(table_data, 0x11, 1);
     /* virtualization flags */
     build_append_int_noprefix(table_data,
                              (1UL << 0) | /* HtTunEn      */
-                             (1UL << 4) | /* iotblSup     */
-                             (1UL << 6) | /* PrefSup      */
-                             (1UL << 7),  /* PPRSup       */
+                             (1UL << 4),  /* iotblSup     */
                              1);
 
     /*
@@ -2404,13 +2405,12 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id,
     build_append_int_noprefix(table_data, 0, 2);
     /* IOMMU info */
     build_append_int_noprefix(table_data, 0, 2);
-    /* IOMMU Feature Reporting */
-    build_append_int_noprefix(table_data,
-                             (48UL << 30) | /* HATS   */
-                             (48UL << 28) | /* GATS   */
-                             (1UL << 2)   | /* GTSup  */
-                             (1UL << 6),    /* GASup  */
-                             4);
+    /* IOMMU Attributes */
+    build_append_int_noprefix(table_data, 0, 4);
+    /* EFR Register Image */
+    build_append_int_noprefix(table_data, s->efr_reg, 8);
+    /* EFR Register Image 2 */
+    build_append_int_noprefix(table_data, 0, 8);
 
     /* IVHD entries as found above */
     g_array_append_vals(table_data, ivhd_blob->data, ivhd_blob->len);
hw/i386/amd_iommu.c +19 -2
index bcd016f5c5..5dfa93d945 100644
@@ -31,6 +31,7 @@
 #include "hw/i386/apic_internal.h"
 #include "trace.h"
 #include "hw/i386/apic-msidef.h"
+#include "hw/qdev-properties.h"
 
 /* used AMD-Vi MMIO registers */
 const char *amdvi_mmio_low[] = {
@@ -1155,7 +1156,12 @@ static int amdvi_int_remap_ga(AMDVIState *iommu,
     irq->vector = irte.hi.fields.vector;
     irq->dest_mode = irte.lo.fields_remap.dm;
     irq->redir_hint = irte.lo.fields_remap.rq_eoi;
-    irq->dest = irte.lo.fields_remap.destination;
+    if (!iommu->xtsup) {
+        irq->dest = irte.lo.fields_remap.destination & 0xff;
+    } else {
+        irq->dest = irte.lo.fields_remap.destination |
+                    (irte.hi.fields.destination_hi << 24);
+    }
 
     return 0;
 }
@@ -1503,10 +1509,15 @@ static void amdvi_init(AMDVIState *s)
     s->enabled = false;
     s->ats_enabled = false;
     s->cmdbuf_enabled = false;
+    s->efr_reg = AMDVI_DEFAULT_EXT_FEATURES;
+
+    if (s->xtsup) {
+        s->efr_reg |= AMDVI_FEATURE_XT;
+    }
 
     /* reset MMIO */
     memset(s->mmior, 0, AMDVI_MMIO_SIZE);
-    amdvi_set_quad(s, AMDVI_MMIO_EXT_FEATURES, AMDVI_EXT_FEATURES,
+    amdvi_set_quad(s, AMDVI_MMIO_EXT_FEATURES, s->efr_reg,
             0xffffffffffffffef, 0);
     amdvi_set_quad(s, AMDVI_MMIO_STATUS, 0, 0x98, 0x67);
 
@@ -1586,6 +1597,11 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp)
     amdvi_init(s);
 }
 
+static Property amdvi_properties[] = {
+    DEFINE_PROP_BOOL("xtsup", AMDVIState, xtsup, false),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static const VMStateDescription vmstate_amdvi_sysbus = {
     .name = "amd-iommu",
     .unmigratable = 1
@@ -1612,6 +1628,7 @@ static void amdvi_sysbus_class_init(ObjectClass *klass, void *data)
     dc->user_creatable = true;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->desc = "AMD IOMMU (AMD-Vi) DMA Remapping device";
+    device_class_set_props(dc, amdvi_properties);
 }
 
 static const TypeInfo amdvi_sysbus = {
hw/i386/amd_iommu.h +11 -5
index 79d38a3e41..96df7b0400 100644
@@ -154,6 +154,7 @@
 
 #define AMDVI_FEATURE_PREFETCH            (1ULL << 0) /* page prefetch       */
 #define AMDVI_FEATURE_PPR                 (1ULL << 1) /* PPR Support         */
+#define AMDVI_FEATURE_XT                  (1ULL << 2) /* x2APIC Support      */
 #define AMDVI_FEATURE_GT                  (1ULL << 4) /* Guest Translation   */
 #define AMDVI_FEATURE_IA                  (1ULL << 6) /* inval all support   */
 #define AMDVI_FEATURE_GA                  (1ULL << 7) /* guest VAPIC support */
@@ -173,8 +174,9 @@
 #define AMDVI_IOTLB_MAX_SIZE 1024
 #define AMDVI_DEVID_SHIFT    36
 
-/* extended feature support */
-#define AMDVI_EXT_FEATURES (AMDVI_FEATURE_PREFETCH | AMDVI_FEATURE_PPR | \
+/* default extended feature */
+#define AMDVI_DEFAULT_EXT_FEATURES \
+        (AMDVI_FEATURE_PREFETCH | AMDVI_FEATURE_PPR | \
         AMDVI_FEATURE_IA | AMDVI_FEATURE_GT | AMDVI_FEATURE_HE | \
         AMDVI_GATS_MODE | AMDVI_HATS_MODE | AMDVI_FEATURE_GA)
 
@@ -278,8 +280,8 @@ union irte_ga_lo {
                 dm:1,
                 /* ------ */
                 guest_mode:1,
-                destination:8,
-                rsvd_1:48;
+                destination:24,
+                rsvd_1:32;
   } fields_remap;
 };
 
@@ -287,7 +289,8 @@ union irte_ga_hi {
   uint64_t val;
   struct {
       uint64_t  vector:8,
-                rsvd_2:56;
+                rsvd_2:48,
+                destination_hi:8;
   } fields;
 };
 
@@ -367,6 +370,9 @@ struct AMDVIState {
 
     /* Interrupt remapping */
     bool ga_enabled;
+    bool xtsup;
+
+    uint64_t efr_reg;            /* extended feature register */
 };
 
 #endif
Signature · 1 line
2.25.1