summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--accel/tcg/cputlb.c287
-rw-r--r--docs/specs/acpi_cpu_hotplug.txt89
-rw-r--r--hw/9pfs/virtio-9p-device.c1
-rw-r--r--hw/acpi/cpu.c18
-rw-r--r--hw/acpi/trace-events1
-rw-r--r--hw/i386/acpi-build.c1
-rw-r--r--hw/i386/pc.c4
-rw-r--r--hw/pci-host/q35.c84
-rw-r--r--hw/scsi/virtio-scsi.c6
-rw-r--r--hw/virtio/vhost-vsock.c12
-rw-r--r--hw/virtio/vhost.c39
-rw-r--r--include/exec/cpu_ldst.h5
-rw-r--r--include/hw/pci-host/q35.h10
-rw-r--r--include/hw/virtio/vhost-vsock.h2
-rw-r--r--scripts/git.orderfile3
-rw-r--r--tests/data/acpi/q35/DSDTbin7879 -> 7869 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.acpihmatbin9203 -> 9193 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.bridgebin7896 -> 7886 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.cphpbin8342 -> 8332 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.dimmpxmbin9532 -> 9522 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.ipmibtbin7954 -> 7944 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.memhpbin9238 -> 9228 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.mmio64bin9009 -> 8999 bytes
-rw-r--r--tests/data/acpi/q35/DSDT.numamembin7885 -> 7875 bytes
-rw-r--r--tests/qtest/bios-tables-test.c23
-rw-r--r--tests/qtest/q35-test.c105
-rw-r--r--util/cacheinfo.c10
-rw-r--r--vl.c27
28 files changed, 567 insertions, 160 deletions
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index a991ea2964..e3b5750c3b 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -80,9 +80,14 @@ QEMU_BUILD_BUG_ON(sizeof(target_ulong) > sizeof(run_on_cpu_data));
QEMU_BUILD_BUG_ON(NB_MMU_MODES > 16);
#define ALL_MMUIDX_BITS ((1 << NB_MMU_MODES) - 1)
-static inline size_t sizeof_tlb(CPUArchState *env, uintptr_t mmu_idx)
+static inline size_t tlb_n_entries(CPUTLBDescFast *fast)
{
- return env_tlb(env)->f[mmu_idx].mask + (1 << CPU_TLB_ENTRY_BITS);
+ return (fast->mask >> CPU_TLB_ENTRY_BITS) + 1;
+}
+
+static inline size_t sizeof_tlb(CPUTLBDescFast *fast)
+{
+ return fast->mask + (1 << CPU_TLB_ENTRY_BITS);
}
static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,
@@ -92,26 +97,10 @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,
desc->window_max_entries = max_entries;
}
-static void tlb_dyn_init(CPUArchState *env)
-{
- int i;
-
- for (i = 0; i < NB_MMU_MODES; i++) {
- CPUTLBDesc *desc = &env_tlb(env)->d[i];
- size_t n_entries = 1 << CPU_TLB_DYN_DEFAULT_BITS;
-
- tlb_window_reset(desc, get_clock_realtime(), 0);
- desc->n_used_entries = 0;
- env_tlb(env)->f[i].mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS;
- env_tlb(env)->f[i].table = g_new(CPUTLBEntry, n_entries);
- env_tlb(env)->d[i].iotlb = g_new(CPUIOTLBEntry, n_entries);
- }
-}
-
/**
* tlb_mmu_resize_locked() - perform TLB resize bookkeeping; resize if necessary
- * @env: CPU that owns the TLB
- * @mmu_idx: MMU index of the TLB
+ * @desc: The CPUTLBDesc portion of the TLB
+ * @fast: The CPUTLBDescFast portion of the same TLB
*
* Called with tlb_lock_held.
*
@@ -148,13 +137,12 @@ static void tlb_dyn_init(CPUArchState *env)
* high), since otherwise we are likely to have a significant amount of
* conflict misses.
*/
-static void tlb_mmu_resize_locked(CPUArchState *env, int mmu_idx)
+static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,
+ int64_t now)
{
- CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];
- size_t old_size = tlb_n_entries(env, mmu_idx);
+ size_t old_size = tlb_n_entries(fast);
size_t rate;
size_t new_size = old_size;
- int64_t now = get_clock_realtime();
int64_t window_len_ms = 100;
int64_t window_len_ns = window_len_ms * 1000 * 1000;
bool window_expired = now > desc->window_begin_ns + window_len_ns;
@@ -193,14 +181,15 @@ static void tlb_mmu_resize_locked(CPUArchState *env, int mmu_idx)
return;
}
- g_free(env_tlb(env)->f[mmu_idx].table);
- g_free(env_tlb(env)->d[mmu_idx].iotlb);
+ g_free(fast->table);
+ g_free(desc->iotlb);
tlb_window_reset(desc, now, 0);
/* desc->n_used_entries is cleared by the caller */
- env_tlb(env)->f[mmu_idx].mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
- env_tlb(env)->f[mmu_idx].table = g_try_new(CPUTLBEntry, new_size);
- env_tlb(env)->d[mmu_idx].iotlb = g_try_new(CPUIOTLBEntry, new_size);
+ fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
+ fast->table = g_try_new(CPUTLBEntry, new_size);
+ desc->iotlb = g_try_new(CPUIOTLBEntry, new_size);
+
/*
* If the allocations fail, try smaller sizes. We just freed some
* memory, so going back to half of new_size has a good chance of working.
@@ -208,27 +197,51 @@ static void tlb_mmu_resize_locked(CPUArchState *env, int mmu_idx)
* allocations to fail though, so we progressively reduce the allocation
* size, aborting if we cannot even allocate the smallest TLB we support.
*/
- while (env_tlb(env)->f[mmu_idx].table == NULL ||
- env_tlb(env)->d[mmu_idx].iotlb == NULL) {
+ while (fast->table == NULL || desc->iotlb == NULL) {
if (new_size == (1 << CPU_TLB_DYN_MIN_BITS)) {
error_report("%s: %s", __func__, strerror(errno));
abort();
}
new_size = MAX(new_size >> 1, 1 << CPU_TLB_DYN_MIN_BITS);
- env_tlb(env)->f[mmu_idx].mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
+ fast->mask = (new_size - 1) << CPU_TLB_ENTRY_BITS;
- g_free(env_tlb(env)->f[mmu_idx].table);
- g_free(env_tlb(env)->d[mmu_idx].iotlb);
- env_tlb(env)->f[mmu_idx].table = g_try_new(CPUTLBEntry, new_size);
- env_tlb(env)->d[mmu_idx].iotlb = g_try_new(CPUIOTLBEntry, new_size);
+ g_free(fast->table);
+ g_free(desc->iotlb);
+ fast->table = g_try_new(CPUTLBEntry, new_size);
+ desc->iotlb = g_try_new(CPUIOTLBEntry, new_size);
}
}
-static inline void tlb_table_flush_by_mmuidx(CPUArchState *env, int mmu_idx)
+static void tlb_mmu_flush_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast)
{
- tlb_mmu_resize_locked(env, mmu_idx);
- memset(env_tlb(env)->f[mmu_idx].table, -1, sizeof_tlb(env, mmu_idx));
- env_tlb(env)->d[mmu_idx].n_used_entries = 0;
+ desc->n_used_entries = 0;
+ desc->large_page_addr = -1;
+ desc->large_page_mask = -1;
+ desc->vindex = 0;
+ memset(fast->table, -1, sizeof_tlb(fast));
+ memset(desc->vtable, -1, sizeof(desc->vtable));
+}
+
+static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx,
+ int64_t now)
+{
+ CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];
+ CPUTLBDescFast *fast = &env_tlb(env)->f[mmu_idx];
+
+ tlb_mmu_resize_locked(desc, fast, now);
+ tlb_mmu_flush_locked(desc, fast);
+}
+
+static void tlb_mmu_init(CPUTLBDesc *desc, CPUTLBDescFast *fast, int64_t now)
+{
+ size_t n_entries = 1 << CPU_TLB_DYN_DEFAULT_BITS;
+
+ tlb_window_reset(desc, now, 0);
+ desc->n_used_entries = 0;
+ fast->mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS;
+ fast->table = g_new(CPUTLBEntry, n_entries);
+ desc->iotlb = g_new(CPUIOTLBEntry, n_entries);
+ tlb_mmu_flush_locked(desc, fast);
}
static inline void tlb_n_used_entries_inc(CPUArchState *env, uintptr_t mmu_idx)
@@ -244,13 +257,17 @@ static inline void tlb_n_used_entries_dec(CPUArchState *env, uintptr_t mmu_idx)
void tlb_init(CPUState *cpu)
{
CPUArchState *env = cpu->env_ptr;
+ int64_t now = get_clock_realtime();
+ int i;
qemu_spin_init(&env_tlb(env)->c.lock);
- /* Ensure that cpu_reset performs a full flush. */
- env_tlb(env)->c.dirty = ALL_MMUIDX_BITS;
+ /* All tlbs are initialized flushed. */
+ env_tlb(env)->c.dirty = 0;
- tlb_dyn_init(env);
+ for (i = 0; i < NB_MMU_MODES; i++) {
+ tlb_mmu_init(&env_tlb(env)->d[i], &env_tlb(env)->f[i], now);
+ }
}
/* flush_all_helper: run fn across all cpus
@@ -289,21 +306,12 @@ void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)
*pelide = elide;
}
-static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)
-{
- tlb_table_flush_by_mmuidx(env, mmu_idx);
- env_tlb(env)->d[mmu_idx].large_page_addr = -1;
- env_tlb(env)->d[mmu_idx].large_page_mask = -1;
- env_tlb(env)->d[mmu_idx].vindex = 0;
- memset(env_tlb(env)->d[mmu_idx].vtable, -1,
- sizeof(env_tlb(env)->d[0].vtable));
-}
-
static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
{
CPUArchState *env = cpu->env_ptr;
uint16_t asked = data.host_int;
uint16_t all_dirty, work, to_clean;
+ int64_t now = get_clock_realtime();
assert_cpu_is_self(cpu);
@@ -318,7 +326,7 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
for (work = to_clean; work != 0; work &= work - 1) {
int mmu_idx = ctz32(work);
- tlb_flush_one_mmuidx_locked(env, mmu_idx);
+ tlb_flush_one_mmuidx_locked(env, mmu_idx, now);
}
qemu_spin_unlock(&env_tlb(env)->c.lock);
@@ -440,7 +448,7 @@ static void tlb_flush_page_locked(CPUArchState *env, int midx,
tlb_debug("forcing full flush midx %d ("
TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
midx, lp_addr, lp_mask);
- tlb_flush_one_mmuidx_locked(env, midx);
+ tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
} else {
if (tlb_flush_entry_locked(tlb_entry(env, midx, page), page)) {
tlb_n_used_entries_dec(env, midx);
@@ -449,28 +457,29 @@ static void tlb_flush_page_locked(CPUArchState *env, int midx,
}
}
-/* As we are going to hijack the bottom bits of the page address for a
- * mmuidx bit mask we need to fail to build if we can't do that
+/**
+ * tlb_flush_page_by_mmuidx_async_0:
+ * @cpu: cpu on which to flush
+ * @addr: page of virtual address to flush
+ * @idxmap: set of mmu_idx to flush
+ *
+ * Helper for tlb_flush_page_by_mmuidx and friends, flush one page
+ * at @addr from the tlbs indicated by @idxmap from @cpu.
*/
-QEMU_BUILD_BUG_ON(NB_MMU_MODES > TARGET_PAGE_BITS_MIN);
-
-static void tlb_flush_page_by_mmuidx_async_work(CPUState *cpu,
- run_on_cpu_data data)
+static void tlb_flush_page_by_mmuidx_async_0(CPUState *cpu,
+ target_ulong addr,
+ uint16_t idxmap)
{
CPUArchState *env = cpu->env_ptr;
- target_ulong addr_and_mmuidx = (target_ulong) data.target_ptr;
- target_ulong addr = addr_and_mmuidx & TARGET_PAGE_MASK;
- unsigned long mmu_idx_bitmap = addr_and_mmuidx & ALL_MMUIDX_BITS;
int mmu_idx;
assert_cpu_is_self(cpu);
- tlb_debug("page addr:" TARGET_FMT_lx " mmu_map:0x%lx\n",
- addr, mmu_idx_bitmap);
+ tlb_debug("page addr:" TARGET_FMT_lx " mmu_map:0x%x\n", addr, idxmap);
qemu_spin_lock(&env_tlb(env)->c.lock);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
- if (test_bit(mmu_idx, &mmu_idx_bitmap)) {
+ if ((idxmap >> mmu_idx) & 1) {
tlb_flush_page_locked(env, mmu_idx, addr);
}
}
@@ -479,22 +488,75 @@ static void tlb_flush_page_by_mmuidx_async_work(CPUState *cpu,
tb_flush_jmp_cache(cpu, addr);
}
-void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, uint16_t idxmap)
+/**
+ * tlb_flush_page_by_mmuidx_async_1:
+ * @cpu: cpu on which to flush
+ * @data: encoded addr + idxmap
+ *
+ * Helper for tlb_flush_page_by_mmuidx and friends, called through
+ * async_run_on_cpu. The idxmap parameter is encoded in the page
+ * offset of the target_ptr field. This limits the set of mmu_idx
+ * that can be passed via this method.
+ */
+static void tlb_flush_page_by_mmuidx_async_1(CPUState *cpu,
+ run_on_cpu_data data)
+{
+ target_ulong addr_and_idxmap = (target_ulong) data.target_ptr;
+ target_ulong addr = addr_and_idxmap & TARGET_PAGE_MASK;
+ uint16_t idxmap = addr_and_idxmap & ~TARGET_PAGE_MASK;
+
+ tlb_flush_page_by_mmuidx_async_0(cpu, addr, idxmap);
+}
+
+typedef struct {
+ target_ulong addr;
+ uint16_t idxmap;
+} TLBFlushPageByMMUIdxData;
+
+/**
+ * tlb_flush_page_by_mmuidx_async_2:
+ * @cpu: cpu on which to flush
+ * @data: allocated addr + idxmap
+ *
+ * Helper for tlb_flush_page_by_mmuidx and friends, called through
+ * async_run_on_cpu. The addr+idxmap parameters are stored in a
+ * TLBFlushPageByMMUIdxData structure that has been allocated
+ * specifically for this helper. Free the structure when done.
+ */
+static void tlb_flush_page_by_mmuidx_async_2(CPUState *cpu,
+ run_on_cpu_data data)
{
- target_ulong addr_and_mmu_idx;
+ TLBFlushPageByMMUIdxData *d = data.host_ptr;
+
+ tlb_flush_page_by_mmuidx_async_0(cpu, d->addr, d->idxmap);
+ g_free(d);
+}
+void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, uint16_t idxmap)
+{
tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%" PRIx16 "\n", addr, idxmap);
/* This should already be page aligned */
- addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
- addr_and_mmu_idx |= idxmap;
+ addr &= TARGET_PAGE_MASK;
- if (!qemu_cpu_is_self(cpu)) {
- async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_work,
- RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
+ if (qemu_cpu_is_self(cpu)) {
+ tlb_flush_page_by_mmuidx_async_0(cpu, addr, idxmap);
+ } else if (idxmap < TARGET_PAGE_SIZE) {
+ /*
+ * Most targets have only a few mmu_idx. In the case where
+ * we can stuff idxmap into the low TARGET_PAGE_BITS, avoid
+ * allocating memory for this operation.
+ */
+ async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_1,
+ RUN_ON_CPU_TARGET_PTR(addr | idxmap));
} else {
- tlb_flush_page_by_mmuidx_async_work(
- cpu, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
+ TLBFlushPageByMMUIdxData *d = g_new(TLBFlushPageByMMUIdxData, 1);
+
+ /* Otherwise allocate a structure, freed by the worker. */
+ d->addr = addr;
+ d->idxmap = idxmap;
+ async_run_on_cpu(cpu, tlb_flush_page_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
}
}
@@ -506,17 +568,36 @@ void tlb_flush_page(CPUState *cpu, target_ulong addr)
void tlb_flush_page_by_mmuidx_all_cpus(CPUState *src_cpu, target_ulong addr,
uint16_t idxmap)
{
- const run_on_cpu_func fn = tlb_flush_page_by_mmuidx_async_work;
- target_ulong addr_and_mmu_idx;
-
tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%"PRIx16"\n", addr, idxmap);
/* This should already be page aligned */
- addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
- addr_and_mmu_idx |= idxmap;
+ addr &= TARGET_PAGE_MASK;
+
+ /*
+ * Allocate memory to hold addr+idxmap only when needed.
+ * See tlb_flush_page_by_mmuidx for details.
+ */
+ if (idxmap < TARGET_PAGE_SIZE) {
+ flush_all_helper(src_cpu, tlb_flush_page_by_mmuidx_async_1,
+ RUN_ON_CPU_TARGET_PTR(addr | idxmap));
+ } else {
+ CPUState *dst_cpu;
+
+ /* Allocate a separate data block for each destination cpu. */
+ CPU_FOREACH(dst_cpu) {
+ if (dst_cpu != src_cpu) {
+ TLBFlushPageByMMUIdxData *d
+ = g_new(TLBFlushPageByMMUIdxData, 1);
+
+ d->addr = addr;
+ d->idxmap = idxmap;
+ async_run_on_cpu(dst_cpu, tlb_flush_page_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
+ }
+ }
- flush_all_helper(src_cpu, fn, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
- fn(src_cpu, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
+ tlb_flush_page_by_mmuidx_async_0(src_cpu, addr, idxmap);
}
void tlb_flush_page_all_cpus(CPUState *src, target_ulong addr)
@@ -528,17 +609,41 @@ void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
target_ulong addr,
uint16_t idxmap)
{
- const run_on_cpu_func fn = tlb_flush_page_by_mmuidx_async_work;
- target_ulong addr_and_mmu_idx;
-
tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:%"PRIx16"\n", addr, idxmap);
/* This should already be page aligned */
- addr_and_mmu_idx = addr & TARGET_PAGE_MASK;
- addr_and_mmu_idx |= idxmap;
+ addr &= TARGET_PAGE_MASK;
+
+ /*
+ * Allocate memory to hold addr+idxmap only when needed.
+ * See tlb_flush_page_by_mmuidx for details.
+ */
+ if (idxmap < TARGET_PAGE_SIZE) {
+ flush_all_helper(src_cpu, tlb_flush_page_by_mmuidx_async_1,
+ RUN_ON_CPU_TARGET_PTR(addr | idxmap));
+ async_safe_run_on_cpu(src_cpu, tlb_flush_page_by_mmuidx_async_1,
+ RUN_ON_CPU_TARGET_PTR(addr | idxmap));
+ } else {
+ CPUState *dst_cpu;
+ TLBFlushPageByMMUIdxData *d;
+
+ /* Allocate a separate data block for each destination cpu. */
+ CPU_FOREACH(dst_cpu) {
+ if (dst_cpu != src_cpu) {
+ d = g_new(TLBFlushPageByMMUIdxData, 1);
+ d->addr = addr;
+ d->idxmap = idxmap;
+ async_run_on_cpu(dst_cpu, tlb_flush_page_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
+ }
- flush_all_helper(src_cpu, fn, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
- async_safe_run_on_cpu(src_cpu, fn, RUN_ON_CPU_TARGET_PTR(addr_and_mmu_idx));
+ d = g_new(TLBFlushPageByMMUIdxData, 1);
+ d->addr = addr;
+ d->idxmap = idxmap;
+ async_safe_run_on_cpu(src_cpu, tlb_flush_page_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
}
void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr)
@@ -622,7 +727,7 @@ void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length)
qemu_spin_lock(&env_tlb(env)->c.lock);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
unsigned int i;
- unsigned int n = tlb_n_entries(env, mmu_idx);
+ unsigned int n = tlb_n_entries(&env_tlb(env)->f[mmu_idx]);
for (i = 0; i < n; i++) {
tlb_reset_dirty_range_locked(&env_tlb(env)->f[mmu_idx].table[i],
diff --git a/docs/specs/acpi_cpu_hotplug.txt b/docs/specs/acpi_cpu_hotplug.txt
index ee219c8358..a8ce5e7402 100644
--- a/docs/specs/acpi_cpu_hotplug.txt
+++ b/docs/specs/acpi_cpu_hotplug.txt
@@ -15,14 +15,14 @@ CPU present bitmap for:
PIIX-PM (IO port 0xaf00-0xaf1f, 1-byte access)
One bit per CPU. Bit position reflects corresponding CPU APIC ID. Read-only.
The first DWORD in bitmap is used in write mode to switch from legacy
- to new CPU hotplug interface, write 0 into it to do switch.
+ to modern CPU hotplug interface, write 0 into it to do switch.
---------------------------------------------------------------
QEMU sets corresponding CPU bit on hot-add event and issues SCI
with GPE.2 event set. CPU present map is read by ACPI BIOS GPE.2 handler
to notify OS about CPU hot-add events. CPU hot-remove isn't supported.
=====================================
-ACPI CPU hotplug interface registers:
+Modern ACPI CPU hotplug interface registers:
-------------------------------------
Register block base address:
ICH9-LPC IO port 0x0cd8
@@ -30,9 +30,25 @@ Register block base address:
Register block size:
ACPI_CPU_HOTPLUG_REG_LEN = 12
+All accesses to registers described below, imply little-endian byte order.
+
+Reserved resisters behavior:
+ - write accesses are ignored
+ - read accesses return all bits set to 0.
+
+The last stored value in 'CPU selector' must refer to a possible CPU, otherwise
+ - reads from any register return 0
+ - writes to any other register are ignored until valid value is stored into it
+On QEMU start, 'CPU selector' is initialized to a valid value, on reset it
+keeps the current value.
+
read access:
offset:
- [0x0-0x3] reserved
+ [0x0-0x3] Command data 2: (DWORD access)
+ if value last stored in 'Command field':
+ 0: reads as 0x0
+ 3: upper 32 bits of architecture specific CPU ID value
+ other values: reserved
[0x4] CPU device status fields: (1 byte access)
bits:
0: Device is enabled and may be used by guest
@@ -44,15 +60,17 @@ read access:
3-7: reserved and should be ignored by OSPM
[0x5-0x7] reserved
[0x8] Command data: (DWORD access)
- in case of error or unsupported command reads is 0xFFFFFFFF
- current 'Command field' value:
- 0: returns PXM value corresponding to device
+ contains 0 unless value last stored in 'Command field' is one of:
+ 0: contains 'CPU selector' value of a CPU with pending event[s]
+ 3: lower 32 bits of architecture specific CPU ID value
+ (in x86 case: APIC ID)
write access:
offset:
[0x0-0x3] CPU selector: (DWORD access)
selects active CPU device. All following accesses to other
registers will read/store data from/to selected CPU.
+ Valid values: [0 .. max_cpus)
[0x4] CPU device control fields: (1 byte access)
bits:
0: reserved, OSPM must clear it before writing to register.
@@ -69,9 +87,9 @@ write access:
value:
0: selects a CPU device with inserting/removing events and
following reads from 'Command data' register return
- selected CPU (CPU selector value). If no CPU with events
- found, the current CPU selector doesn't change and
- corresponding insert/remove event flags are not set.
+ selected CPU ('CPU selector' value).
+ If no CPU with events found, the current 'CPU selector' doesn't
+ change and corresponding insert/remove event flags are not modified.
1: following writes to 'Command data' register set OST event
register in QEMU
2: following writes to 'Command data' register set OST status
@@ -79,16 +97,53 @@ write access:
other values: reserved
[0x6-0x7] reserved
[0x8] Command data: (DWORD access)
- current 'Command field' value:
- 0: OSPM reads value of CPU selector
+ if last stored 'Command field' value:
1: stores value into OST event register
2: stores value into OST status register, triggers
ACPI_DEVICE_OST QMP event from QEMU to external applications
with current values of OST event and status registers.
- other values: reserved
+ other values: reserved
+
+Typical usecases:
+ - (x86) Detecting and enabling modern CPU hotplug interface.
+ QEMU starts with legacy CPU hotplug interface enabled. Detecting and
+ switching to modern interface is based on the 2 legacy CPU hotplug features:
+ 1. Writes into CPU bitmap are ignored.
+ 2. CPU bitmap always has bit#0 set, corresponding to boot CPU.
+
+ Use following steps to detect and enable modern CPU hotplug interface:
+ 1. Store 0x0 to the 'CPU selector' register,
+ attempting to switch to modern mode
+ 2. Store 0x0 to the 'CPU selector' register,
+ to ensure valid selector value
+ 3. Store 0x0 to the 'Command field' register,
+ 4. Read the 'Command data 2' register.
+ If read value is 0x0, the modern interface is enabled.
+ Otherwise legacy or no CPU hotplug interface available
+
+ - Get a cpu with pending event
+ 1. Store 0x0 to the 'CPU selector' register.
+ 2. Store 0x0 to the 'Command field' register.
+ 3. Read the 'CPU device status fields' register.
+ 4. If both bit#1 and bit#2 are clear in the value read, there is no CPU
+ with a pending event and selected CPU remains unchanged.
+ 5. Otherwise, read the 'Command data' register. The value read is the
+ selector of the CPU with the pending event (which is already
+ selected).
-Selecting CPU device beyond possible range has no effect on platform:
- - write accesses to CPU hot-plug registers not documented above are
- ignored
- - read accesses to CPU hot-plug registers not documented above return
- all bits set to 0.
+ - Enumerate CPUs present/non present CPUs
+ 01. Set the present CPU count to 0.
+ 02. Set the iterator to 0.
+ 03. Store 0x0 to the 'CPU selector' register, to ensure that it's in
+ a valid state and that access to other registers won't be ignored.
+ 04. Store 0x0 to the 'Command field' register to make 'Command data'
+ register return 'CPU selector' value of selected CPU
+ 05. Read the 'CPU device status fields' register.
+ 06. If bit#0 is set, increment the present CPU count.
+ 07. Increment the iterator.
+ 08. Store the iterator to the 'CPU selector' register.
+ 09. Read the 'Command data' register.
+ 10. If the value read is not zero, goto 05.
+ 11. Otherwise store 0x0 to the 'CPU selector' register, to put it
+ into a valid state and exit.
+ The iterator at this point equals "max_cpus".
diff --git a/hw/9pfs/virtio-9p-device.c b/hw/9pfs/virtio-9p-device.c
index 991e175c82..1d1c50409c 100644
--- a/hw/9pfs/virtio-9p-device.c
+++ b/hw/9pfs/virtio-9p-device.c
@@ -218,6 +218,7 @@ static void virtio_9p_device_unrealize(DeviceState *dev, Error **errp)
V9fsVirtioState *v = VIRTIO_9P(dev);
V9fsState *s = &v->state;
+ virtio_delete_queue(v->vq);
virtio_cleanup(vdev);
v9fs_device_unrealize_common(s, errp);
}
diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c
index 87f30a31d7..e2c957ce00 100644
--- a/hw/acpi/cpu.c
+++ b/hw/acpi/cpu.c
@@ -12,11 +12,13 @@
#define ACPI_CPU_FLAGS_OFFSET_RW 4
#define ACPI_CPU_CMD_OFFSET_WR 5
#define ACPI_CPU_CMD_DATA_OFFSET_RW 8
+#define ACPI_CPU_CMD_DATA2_OFFSET_R 0
enum {
CPHP_GET_NEXT_CPU_WITH_EVENT_CMD = 0,
CPHP_OST_EVENT_CMD = 1,
CPHP_OST_STATUS_CMD = 2,
+ CPHP_GET_CPU_ID_CMD = 3,
CPHP_CMD_MAX
};
@@ -74,11 +76,27 @@ static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size)
case CPHP_GET_NEXT_CPU_WITH_EVENT_CMD:
val = cpu_st->selector;
break;
+ case CPHP_GET_CPU_ID_CMD:
+ val = cdev->arch_id & 0xFFFFFFFF;
+ break;
default:
break;
}
trace_cpuhp_acpi_read_cmd_data(cpu_st->selector, val);
break;
+ case ACPI_CPU_CMD_DATA2_OFFSET_R:
+ switch (cpu_st->command) {
+ case CPHP_GET_NEXT_CPU_WITH_EVENT_CMD:
+ val = 0;
+ break;
+ case CPHP_GET_CPU_ID_CMD:
+ val = cdev->arch_id >> 32;
+ break;
+ default:
+ break;
+ }
+ trace_cpuhp_acpi_read_cmd_data2(cpu_st->selector, val);
+ break;
default:
break;
}
diff --git a/hw/acpi/trace-events b/hw/acpi/trace-events
index 96b8273297..afbc77de1c 100644
--- a/hw/acpi/trace-events
+++ b/hw/acpi/trace-events
@@ -23,6 +23,7 @@ cpuhp_acpi_read_flags(uint32_t idx, uint8_t flags) "idx[0x%"PRIx32"] flags: 0x%"
cpuhp_acpi_write_idx(uint32_t idx) "set active cpu idx: 0x%"PRIx32
cpuhp_acpi_write_cmd(uint32_t idx, uint8_t cmd) "idx[0x%"PRIx32"] cmd: 0x%"PRIx8
cpuhp_acpi_read_cmd_data(uint32_t idx, uint32_t data) "idx[0x%"PRIx32"] data: 0x%"PRIx32
+cpuhp_acpi_read_cmd_data2(uint32_t idx, uint32_t data) "idx[0x%"PRIx32"] data: 0x%"PRIx32
cpuhp_acpi_cpu_has_events(uint32_t idx, bool ins, bool rm) "idx[0x%"PRIx32"] inserting: %d, removing: %d"
cpuhp_acpi_clear_inserting_evt(uint32_t idx) "idx[0x%"PRIx32"]"
cpuhp_acpi_clear_remove_evt(uint32_t idx) "idx[0x%"PRIx32"]"
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index e25df838f0..9c4e46fa74 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -1816,7 +1816,6 @@ static void build_smb0(Aml *table, I2CBus *smbus, int devnr, int func)
Aml *scope = aml_scope("_SB.PCI0");
Aml *dev = aml_device("SMB0");
- aml_append(dev, aml_name_decl("_HID", aml_eisaid("APP0005")));
aml_append(dev, aml_name_decl("_ADR", aml_int(devnr << 16 | func)));
build_acpi_ipmi_devices(dev, BUS(smbus), "\\_SB.PCI0.SMB0");
aml_append(scope, dev);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 8054bc4147..a6302a772d 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -93,7 +93,9 @@
#include "fw_cfg.h"
#include "trace.h"
-GlobalProperty pc_compat_4_2[] = {};
+GlobalProperty pc_compat_4_2[] = {
+ { "mch", "smbase-smram", "off" },
+};
const size_t pc_compat_4_2_len = G_N_ELEMENTS(pc_compat_4_2);
GlobalProperty pc_compat_4_1[] = {};
diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
index 158d270b9f..6342f73b9f 100644
--- a/hw/pci-host/q35.c
+++ b/hw/pci-host/q35.c
@@ -275,20 +275,20 @@ static const TypeInfo q35_host_info = {
* MCH D0:F0
*/
-static uint64_t tseg_blackhole_read(void *ptr, hwaddr reg, unsigned size)
+static uint64_t blackhole_read(void *ptr, hwaddr reg, unsigned size)
{
return 0xffffffff;
}
-static void tseg_blackhole_write(void *opaque, hwaddr addr, uint64_t val,
- unsigned width)
+static void blackhole_write(void *opaque, hwaddr addr, uint64_t val,
+ unsigned width)
{
/* nothing */
}
-static const MemoryRegionOps tseg_blackhole_ops = {
- .read = tseg_blackhole_read,
- .write = tseg_blackhole_write,
+static const MemoryRegionOps blackhole_ops = {
+ .read = blackhole_read,
+ .write = blackhole_write,
.endianness = DEVICE_NATIVE_ENDIAN,
.valid.min_access_size = 1,
.valid.max_access_size = 4,
@@ -430,6 +430,46 @@ static void mch_update_ext_tseg_mbytes(MCHPCIState *mch)
}
}
+static void mch_update_smbase_smram(MCHPCIState *mch)
+{
+ PCIDevice *pd = PCI_DEVICE(mch);
+ uint8_t *reg = pd->config + MCH_HOST_BRIDGE_F_SMBASE;
+ bool lck;
+
+ if (!mch->has_smram_at_smbase) {
+ return;
+ }
+
+ if (*reg == MCH_HOST_BRIDGE_F_SMBASE_QUERY) {
+ pd->wmask[MCH_HOST_BRIDGE_F_SMBASE] =
+ MCH_HOST_BRIDGE_F_SMBASE_LCK;
+ *reg = MCH_HOST_BRIDGE_F_SMBASE_IN_RAM;
+ return;
+ }
+
+ /*
+ * default/reset state, discard written value
+ * which will disable SMRAM balackhole at SMBASE
+ */
+ if (pd->wmask[MCH_HOST_BRIDGE_F_SMBASE] == 0xff) {
+ *reg = 0x00;
+ }
+
+ memory_region_transaction_begin();
+ if (*reg & MCH_HOST_BRIDGE_F_SMBASE_LCK) {
+ /* disable all writes */
+ pd->wmask[MCH_HOST_BRIDGE_F_SMBASE] &=
+ ~MCH_HOST_BRIDGE_F_SMBASE_LCK;
+ *reg = MCH_HOST_BRIDGE_F_SMBASE_LCK;
+ lck = true;
+ } else {
+ lck = false;
+ }
+ memory_region_set_enabled(&mch->smbase_blackhole, lck);
+ memory_region_set_enabled(&mch->smbase_window, lck);
+ memory_region_transaction_commit();
+}
+
static void mch_write_config(PCIDevice *d,
uint32_t address, uint32_t val, int len)
{
@@ -456,6 +496,10 @@ static void mch_write_config(PCIDevice *d,
MCH_HOST_BRIDGE_EXT_TSEG_MBYTES_SIZE)) {
mch_update_ext_tseg_mbytes(mch);
}
+
+ if (ranges_overlap(address, len, MCH_HOST_BRIDGE_F_SMBASE, 1)) {
+ mch_update_smbase_smram(mch);
+ }
}
static void mch_update(MCHPCIState *mch)
@@ -464,6 +508,7 @@ static void mch_update(MCHPCIState *mch)
mch_update_pam(mch);
mch_update_smram(mch);
mch_update_ext_tseg_mbytes(mch);
+ mch_update_smbase_smram(mch);
/*
* pci hole goes from end-of-low-ram to io-apic.
@@ -514,6 +559,9 @@ static void mch_reset(DeviceState *qdev)
MCH_HOST_BRIDGE_EXT_TSEG_MBYTES_QUERY);
}
+ d->config[MCH_HOST_BRIDGE_F_SMBASE] = 0;
+ d->wmask[MCH_HOST_BRIDGE_F_SMBASE] = 0xff;
+
mch_update(mch);
}
@@ -563,7 +611,7 @@ static void mch_realize(PCIDevice *d, Error **errp)
memory_region_add_subregion(&mch->smram, 0xfeda0000, &mch->high_smram);
memory_region_init_io(&mch->tseg_blackhole, OBJECT(mch),
- &tseg_blackhole_ops, NULL,
+ &blackhole_ops, NULL,
"tseg-blackhole", 0);
memory_region_set_enabled(&mch->tseg_blackhole, false);
memory_region_add_subregion_overlap(mch->system_memory,
@@ -575,6 +623,27 @@ static void mch_realize(PCIDevice *d, Error **errp)
memory_region_set_enabled(&mch->tseg_window, false);
memory_region_add_subregion(&mch->smram, mch->below_4g_mem_size,
&mch->tseg_window);
+
+ /*
+ * This is not what hardware does, so it's QEMU specific hack.
+ * See commit message for details.
+ */
+ memory_region_init_io(&mch->smbase_blackhole, OBJECT(mch), &blackhole_ops,
+ NULL, "smbase-blackhole",
+ MCH_HOST_BRIDGE_SMBASE_SIZE);
+ memory_region_set_enabled(&mch->smbase_blackhole, false);
+ memory_region_add_subregion_overlap(mch->system_memory,
+ MCH_HOST_BRIDGE_SMBASE_ADDR,
+ &mch->smbase_blackhole, 1);
+
+ memory_region_init_alias(&mch->smbase_window, OBJECT(mch),
+ "smbase-window", mch->ram_memory,
+ MCH_HOST_BRIDGE_SMBASE_ADDR,
+ MCH_HOST_BRIDGE_SMBASE_SIZE);
+ memory_region_set_enabled(&mch->smbase_window, false);
+ memory_region_add_subregion(&mch->smram, MCH_HOST_BRIDGE_SMBASE_ADDR,
+ &mch->smbase_window);
+
object_property_add_const_link(qdev_get_machine(), "smram",
OBJECT(&mch->smram), &error_abort);
@@ -601,6 +670,7 @@ uint64_t mch_mcfg_base(void)
static Property mch_props[] = {
DEFINE_PROP_UINT16("extended-tseg-mbytes", MCHPCIState, ext_tseg_mbytes,
16),
+ DEFINE_PROP_BOOL("smbase-smram", MCHPCIState, has_smram_at_smbase, true),
DEFINE_PROP_END_OF_LIST(),
};
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 4bc73a370e..d3af42ef92 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -943,7 +943,13 @@ void virtio_scsi_common_unrealize(DeviceState *dev)
{
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
+ int i;
+ virtio_delete_queue(vs->ctrl_vq);
+ virtio_delete_queue(vs->event_vq);
+ for (i = 0; i < vs->conf.num_queues; i++) {
+ virtio_delete_queue(vs->cmd_vqs[i]);
+ }
g_free(vs->cmd_vqs);
virtio_cleanup(vdev);
}
diff --git a/hw/virtio/vhost-vsock.c b/hw/virtio/vhost-vsock.c
index f5744363a8..b6cee479bb 100644
--- a/hw/virtio/vhost-vsock.c
+++ b/hw/virtio/vhost-vsock.c
@@ -335,8 +335,10 @@ static void vhost_vsock_device_realize(DeviceState *dev, Error **errp)
sizeof(struct virtio_vsock_config));
/* Receive and transmit queues belong to vhost */
- virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, vhost_vsock_handle_output);
- virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE, vhost_vsock_handle_output);
+ vsock->recv_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE,
+ vhost_vsock_handle_output);
+ vsock->trans_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE,
+ vhost_vsock_handle_output);
/* The event queue belongs to QEMU */
vsock->event_vq = virtio_add_queue(vdev, VHOST_VSOCK_QUEUE_SIZE,
@@ -363,6 +365,9 @@ static void vhost_vsock_device_realize(DeviceState *dev, Error **errp)
err_vhost_dev:
vhost_dev_cleanup(&vsock->vhost_dev);
err_virtio:
+ virtio_delete_queue(vsock->recv_vq);
+ virtio_delete_queue(vsock->trans_vq);
+ virtio_delete_queue(vsock->event_vq);
virtio_cleanup(vdev);
close(vhostfd);
return;
@@ -379,6 +384,9 @@ static void vhost_vsock_device_unrealize(DeviceState *dev, Error **errp)
vhost_vsock_set_status(vdev, 0);
vhost_dev_cleanup(&vsock->vhost_dev);
+ virtio_delete_queue(vsock->recv_vq);
+ virtio_delete_queue(vsock->trans_vq);
+ virtio_delete_queue(vsock->event_vq);
virtio_cleanup(vdev);
}
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 4da0d5a6c5..9edfadc81d 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -547,26 +547,28 @@ static void vhost_region_add_section(struct vhost_dev *dev,
uintptr_t mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
section->offset_within_region;
RAMBlock *mrs_rb = section->mr->ram_block;
- size_t mrs_page = qemu_ram_pagesize(mrs_rb);
trace_vhost_region_add_section(section->mr->name, mrs_gpa, mrs_size,
mrs_host);
- /* Round the section to it's page size */
- /* First align the start down to a page boundary */
- uint64_t alignage = mrs_host & (mrs_page - 1);
- if (alignage) {
- mrs_host -= alignage;
- mrs_size += alignage;
- mrs_gpa -= alignage;
- }
- /* Now align the size up to a page boundary */
- alignage = mrs_size & (mrs_page - 1);
- if (alignage) {
- mrs_size += mrs_page - alignage;
+ if (dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER) {
+ /* Round the section to it's page size */
+ /* First align the start down to a page boundary */
+ size_t mrs_page = qemu_ram_pagesize(mrs_rb);
+ uint64_t alignage = mrs_host & (mrs_page - 1);
+ if (alignage) {
+ mrs_host -= alignage;
+ mrs_size += alignage;
+ mrs_gpa -= alignage;
+ }
+ /* Now align the size up to a page boundary */
+ alignage = mrs_size & (mrs_page - 1);
+ if (alignage) {
+ mrs_size += mrs_page - alignage;
+ }
+ trace_vhost_region_add_section_aligned(section->mr->name, mrs_gpa,
+ mrs_size, mrs_host);
}
- trace_vhost_region_add_section_aligned(section->mr->name, mrs_gpa, mrs_size,
- mrs_host);
if (dev->n_tmp_sections) {
/* Since we already have at least one section, lets see if
@@ -590,9 +592,10 @@ static void vhost_region_add_section(struct vhost_dev *dev,
* match up in the same RAMBlock if they do.
*/
if (mrs_gpa < prev_gpa_start) {
- error_report("%s:Section rounded to %"PRIx64
- " prior to previous %"PRIx64,
- __func__, mrs_gpa, prev_gpa_start);
+ error_report("%s:Section '%s' rounded to %"PRIx64
+ " prior to previous '%s' %"PRIx64,
+ __func__, section->mr->name, mrs_gpa,
+ prev_sec->mr->name, prev_gpa_start);
/* A way to cleanly fail here would be better */
return;
}
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index a46116167c..53de19753a 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -234,11 +234,6 @@ static inline uintptr_t tlb_index(CPUArchState *env, uintptr_t mmu_idx,
return (addr >> TARGET_PAGE_BITS) & size_mask;
}
-static inline size_t tlb_n_entries(CPUArchState *env, uintptr_t mmu_idx)
-{
- return (env_tlb(env)->f[mmu_idx].mask >> CPU_TLB_ENTRY_BITS) + 1;
-}
-
/* Find the TLB entry corresponding to the mmu_idx + address pair. */
static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx,
target_ulong addr)
diff --git a/include/hw/pci-host/q35.h b/include/hw/pci-host/q35.h
index b3bcf2e632..976fbae599 100644
--- a/include/hw/pci-host/q35.h
+++ b/include/hw/pci-host/q35.h
@@ -32,6 +32,7 @@
#include "hw/acpi/ich9.h"
#include "hw/pci-host/pam.h"
#include "hw/i386/intel_iommu.h"
+#include "qemu/units.h"
#define TYPE_Q35_HOST_DEVICE "q35-pcihost"
#define Q35_HOST_DEVICE(obj) \
@@ -54,6 +55,8 @@ typedef struct MCHPCIState {
MemoryRegion smram_region, open_high_smram;
MemoryRegion smram, low_smram, high_smram;
MemoryRegion tseg_blackhole, tseg_window;
+ MemoryRegion smbase_blackhole, smbase_window;
+ bool has_smram_at_smbase;
Range pci_hole;
uint64_t below_4g_mem_size;
uint64_t above_4g_mem_size;
@@ -97,6 +100,13 @@ typedef struct Q35PCIHost {
#define MCH_HOST_BRIDGE_EXT_TSEG_MBYTES_QUERY 0xffff
#define MCH_HOST_BRIDGE_EXT_TSEG_MBYTES_MAX 0xfff
+#define MCH_HOST_BRIDGE_SMBASE_SIZE (128 * KiB)
+#define MCH_HOST_BRIDGE_SMBASE_ADDR 0x30000
+#define MCH_HOST_BRIDGE_F_SMBASE 0x9c
+#define MCH_HOST_BRIDGE_F_SMBASE_QUERY 0xff
+#define MCH_HOST_BRIDGE_F_SMBASE_IN_RAM 0x01
+#define MCH_HOST_BRIDGE_F_SMBASE_LCK 0x02
+
#define MCH_HOST_BRIDGE_PCIEXBAR 0x60 /* 64bit register */
#define MCH_HOST_BRIDGE_PCIEXBAR_SIZE 8 /* 64bit register */
#define MCH_HOST_BRIDGE_PCIEXBAR_DEFAULT 0xb0000000
diff --git a/include/hw/virtio/vhost-vsock.h b/include/hw/virtio/vhost-vsock.h
index d509d67c4a..bc5a988ee5 100644
--- a/include/hw/virtio/vhost-vsock.h
+++ b/include/hw/virtio/vhost-vsock.h
@@ -33,6 +33,8 @@ typedef struct {
struct vhost_virtqueue vhost_vqs[2];
struct vhost_dev vhost_dev;
VirtQueue *event_vq;
+ VirtQueue *recv_vq;
+ VirtQueue *trans_vq;
QEMUTimer *post_load_timer;
/*< public >*/
diff --git a/scripts/git.orderfile b/scripts/git.orderfile
index e89790941c..1f747b583a 100644
--- a/scripts/git.orderfile
+++ b/scripts/git.orderfile
@@ -25,5 +25,8 @@ qga/*.json
# headers
*.h
+# decoding tree specification
+*.decode
+
# code
*.c
diff --git a/tests/data/acpi/q35/DSDT b/tests/data/acpi/q35/DSDT
index 77ea60ffed..1f91888d7a 100644
--- a/tests/data/acpi/q35/DSDT
+++ b/tests/data/acpi/q35/DSDT
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.acpihmat b/tests/data/acpi/q35/DSDT.acpihmat
index 30e3717b5b..3586f6368a 100644
--- a/tests/data/acpi/q35/DSDT.acpihmat
+++ b/tests/data/acpi/q35/DSDT.acpihmat
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.bridge b/tests/data/acpi/q35/DSDT.bridge
index fbc2d40000..eae3a2a865 100644
--- a/tests/data/acpi/q35/DSDT.bridge
+++ b/tests/data/acpi/q35/DSDT.bridge
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.cphp b/tests/data/acpi/q35/DSDT.cphp
index 6a896cb214..53d735a4de 100644
--- a/tests/data/acpi/q35/DSDT.cphp
+++ b/tests/data/acpi/q35/DSDT.cphp
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.dimmpxm b/tests/data/acpi/q35/DSDT.dimmpxm
index 23fdf5e60a..02ccdd5f38 100644
--- a/tests/data/acpi/q35/DSDT.dimmpxm
+++ b/tests/data/acpi/q35/DSDT.dimmpxm
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.ipmibt b/tests/data/acpi/q35/DSDT.ipmibt
index c3fca0a71e..9e2d4f785c 100644
--- a/tests/data/acpi/q35/DSDT.ipmibt
+++ b/tests/data/acpi/q35/DSDT.ipmibt
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.memhp b/tests/data/acpi/q35/DSDT.memhp
index 2abd0e36cd..baefa611ac 100644
--- a/tests/data/acpi/q35/DSDT.memhp
+++ b/tests/data/acpi/q35/DSDT.memhp
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.mmio64 b/tests/data/acpi/q35/DSDT.mmio64
index b32034a11c..aae0ea2110 100644
--- a/tests/data/acpi/q35/DSDT.mmio64
+++ b/tests/data/acpi/q35/DSDT.mmio64
Binary files differ
diff --git a/tests/data/acpi/q35/DSDT.numamem b/tests/data/acpi/q35/DSDT.numamem
index d8b2b47f8b..859a2e0871 100644
--- a/tests/data/acpi/q35/DSDT.numamem
+++ b/tests/data/acpi/q35/DSDT.numamem
Binary files differ
diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c
index f1ac2d7e96..3ab4872bd7 100644
--- a/tests/qtest/bios-tables-test.c
+++ b/tests/qtest/bios-tables-test.c
@@ -16,7 +16,10 @@
* 1. add empty files for new tables, if any, under tests/data/acpi
* 2. list any changed files in tests/bios-tables-test-allowed-diff.h
* 3. commit the above *before* making changes that affect the tables
- * Maintainer:
+ *
+ * Contributor or ACPI Maintainer (steps 4-7 need to be redone to resolve conflicts
+ * in binary commit created in step 6):
+ *
* After 1-3 above tests will pass but ignore differences with the expected files.
* You will also notice that tests/bios-tables-test-allowed-diff.h lists
* a bunch of files. This is your hint that you need to do the below:
@@ -28,13 +31,23 @@
* output. If not - disassemble them yourself in any way you like.
* Look at the differences - make sure they make sense and match what the
* changes you are merging are supposed to do.
+ * Save the changes, preferably in form of ASL diff for the commit log in
+ * step 6.
*
* 5. From build directory, run:
* $(SRC_PATH)/tests/data/acpi/rebuild-expected-aml.sh
- * 6. Now commit any changes.
- * 7. Before doing a pull request, make sure tests/bios-tables-test-allowed-diff.h
- * is empty - this will ensure following changes to ACPI tables will
- * be noticed.
+ * 6. Now commit any changes to the expected binary, include diff from step 4
+ * in commit log.
+ * 7. Before sending patches to the list (Contributor)
+ * or before doing a pull request (Maintainer), make sure
+ * tests/bios-tables-test-allowed-diff.h is empty - this will ensure
+ * following changes to ACPI tables will be noticed.
+ *
+ * The resulting patchset/pull request then looks like this:
+ * - patch 1: list changed files in tests/bios-tables-test-allowed-diff.h.
+ * - patches 2 - n: real changes, may contain multiple patches.
+ * - patch n + 1: update golden master binaries and empty
+ * tests/bios-tables-test-allowed-diff.h
*/
#include "qemu/osdep.h"
diff --git a/tests/qtest/q35-test.c b/tests/qtest/q35-test.c
index a68183d513..c922d81bc0 100644
--- a/tests/qtest/q35-test.c
+++ b/tests/qtest/q35-test.c
@@ -186,6 +186,109 @@ static void test_tseg_size(const void *data)
qtest_quit(qts);
}
+#define SMBASE 0x30000
+#define SMRAM_TEST_PATTERN 0x32
+#define SMRAM_TEST_RESET_PATTERN 0x23
+
+static void test_smram_smbase_lock(void)
+{
+ QPCIBus *pcibus;
+ QPCIDevice *pcidev;
+ QDict *response;
+ QTestState *qts;
+ int i;
+
+ qts = qtest_init("-M q35");
+
+ pcibus = qpci_new_pc(qts, NULL);
+ g_assert(pcibus != NULL);
+
+ pcidev = qpci_device_find(pcibus, 0);
+ g_assert(pcidev != NULL);
+
+ /* check that SMRAM is not enabled by default */
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == 0);
+ qtest_writeb(qts, SMBASE, SMRAM_TEST_PATTERN);
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, SMRAM_TEST_PATTERN);
+
+ /* check that writing junk to 0x9c before before negotiating is ignored */
+ for (i = 0; i < 0xff; i++) {
+ qpci_config_writeb(pcidev, MCH_HOST_BRIDGE_F_SMBASE, i);
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == 0);
+ }
+
+ /* enable SMRAM at SMBASE */
+ qpci_config_writeb(pcidev, MCH_HOST_BRIDGE_F_SMBASE, 0xff);
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == 0x01);
+ /* lock SMRAM at SMBASE */
+ qpci_config_writeb(pcidev, MCH_HOST_BRIDGE_F_SMBASE, 0x02);
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == 0x02);
+
+ /* check that SMRAM at SMBASE is locked and can't be unlocked */
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, 0xff);
+ for (i = 0; i <= 0xff; i++) {
+ /* make sure register is immutable */
+ qpci_config_writeb(pcidev, MCH_HOST_BRIDGE_F_SMBASE, i);
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == 0x02);
+
+ /* RAM access should go into black hole */
+ qtest_writeb(qts, SMBASE, SMRAM_TEST_PATTERN);
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, 0xff);
+ }
+
+ /* reset */
+ response = qtest_qmp(qts, "{'execute': 'system_reset', 'arguments': {} }");
+ g_assert(response);
+ g_assert(!qdict_haskey(response, "error"));
+ qobject_unref(response);
+
+ /* check RAM at SMBASE is available after reset */
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, SMRAM_TEST_PATTERN);
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == 0);
+ qtest_writeb(qts, SMBASE, SMRAM_TEST_RESET_PATTERN);
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, SMRAM_TEST_RESET_PATTERN);
+
+ g_free(pcidev);
+ qpci_free_pc(pcibus);
+
+ qtest_quit(qts);
+}
+
+static void test_without_smram_base(void)
+{
+ QPCIBus *pcibus;
+ QPCIDevice *pcidev;
+ QTestState *qts;
+ int i;
+
+ qts = qtest_init("-M pc-q35-4.1");
+
+ pcibus = qpci_new_pc(qts, NULL);
+ g_assert(pcibus != NULL);
+
+ pcidev = qpci_device_find(pcibus, 0);
+ g_assert(pcidev != NULL);
+
+ /* check that RAM is accessible */
+ qtest_writeb(qts, SMBASE, SMRAM_TEST_PATTERN);
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, SMRAM_TEST_PATTERN);
+
+ /* check that writing to 0x9c succeeds */
+ for (i = 0; i <= 0xff; i++) {
+ qpci_config_writeb(pcidev, MCH_HOST_BRIDGE_F_SMBASE, i);
+ g_assert(qpci_config_readb(pcidev, MCH_HOST_BRIDGE_F_SMBASE) == i);
+ }
+
+ /* check that RAM is still accessible */
+ qtest_writeb(qts, SMBASE, SMRAM_TEST_PATTERN + 1);
+ g_assert_cmpint(qtest_readb(qts, SMBASE), ==, (SMRAM_TEST_PATTERN + 1));
+
+ g_free(pcidev);
+ qpci_free_pc(pcibus);
+
+ qtest_quit(qts);
+}
+
int main(int argc, char **argv)
{
g_test_init(&argc, &argv, NULL);
@@ -197,5 +300,7 @@ int main(int argc, char **argv)
qtest_add_data_func("/q35/tseg-size/8mb", &tseg_8mb, test_tseg_size);
qtest_add_data_func("/q35/tseg-size/ext/16mb", &tseg_ext_16mb,
test_tseg_size);
+ qtest_add_func("/q35/smram/smbase_lock", test_smram_smbase_lock);
+ qtest_add_func("/q35/smram/legacy_smbase", test_without_smram_base);
return g_test_run();
}
diff --git a/util/cacheinfo.c b/util/cacheinfo.c
index ea6f3e99bf..d94dc6adc8 100644
--- a/util/cacheinfo.c
+++ b/util/cacheinfo.c
@@ -93,10 +93,16 @@ static void sys_cache_info(int *isize, int *dsize)
static void sys_cache_info(int *isize, int *dsize)
{
# ifdef _SC_LEVEL1_ICACHE_LINESIZE
- *isize = sysconf(_SC_LEVEL1_ICACHE_LINESIZE);
+ int tmp_isize = (int) sysconf(_SC_LEVEL1_ICACHE_LINESIZE);
+ if (tmp_isize > 0) {
+ *isize = tmp_isize;
+ }
# endif
# ifdef _SC_LEVEL1_DCACHE_LINESIZE
- *dsize = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+ int tmp_dsize = (int) sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+ if (tmp_dsize > 0) {
+ *dsize = tmp_dsize;
+ }
# endif
}
#endif /* sys_cache_info */
diff --git a/vl.c b/vl.c
index 71d3e7eefb..4c5033842c 100644
--- a/vl.c
+++ b/vl.c
@@ -2755,8 +2755,6 @@ static int do_configure_accelerator(void *opaque, QemuOpts *opts, Error **errp)
static void configure_accelerators(const char *progname)
{
const char *accel;
- char **accel_list, **tmp;
- bool accel_initialised = false;
bool init_failed = false;
qemu_opts_foreach(qemu_find_opts("icount"),
@@ -2764,26 +2762,33 @@ static void configure_accelerators(const char *progname)
accel = qemu_opt_get(qemu_get_machine_opts(), "accel");
if (QTAILQ_EMPTY(&qemu_accel_opts.head)) {
+ char **accel_list, **tmp;
+
if (accel == NULL) {
/* Select the default accelerator */
- if (!accel_find("tcg") && !accel_find("kvm")) {
- error_report("No accelerator selected and"
- " no default accelerator available");
- exit(1);
- } else {
- int pnlen = strlen(progname);
- if (pnlen >= 3 && g_str_equal(&progname[pnlen - 3], "kvm")) {
+ bool have_tcg = accel_find("tcg");
+ bool have_kvm = accel_find("kvm");
+
+ if (have_tcg && have_kvm) {
+ if (g_str_has_suffix(progname, "kvm")) {
/* If the program name ends with "kvm", we prefer KVM */
accel = "kvm:tcg";
} else {
accel = "tcg:kvm";
}
+ } else if (have_kvm) {
+ accel = "kvm";
+ } else if (have_tcg) {
+ accel = "tcg";
+ } else {
+ error_report("No accelerator selected and"
+ " no default accelerator available");
+ exit(1);
}
}
-
accel_list = g_strsplit(accel, ":", 0);
- for (tmp = accel_list; !accel_initialised && tmp && *tmp; tmp++) {
+ for (tmp = accel_list; *tmp; tmp++) {
/*
* Filter invalid accelerators here, to prevent obscenities
* such as "-machine accel=tcg,,thread=single".