Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* core support for MemoryRegionCache from myself
* rules.mak speedup and cleanups from myself and Marc-Adnré
* multiboot command line fix from Vlad
* SCSI fixes from myself
* small qemu-timer speedup from myself
* x86 debugging improvements from Doug
* configurable Q35 devices from  Chao
* x86 5-level paging support from Kirill
* x86 SHA_NI support for KVM from Yi Sun
* improved kvmclock migration logic from Marcelo
* bugfixes and doc fixes from others

# gpg: Signature made Thu 22 Dec 2016 15:01:13 GMT
# gpg:                using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream: (25 commits)
  x86: implement la57 paging mode
  target-i386: Fix eflags.TF/#DB handling of syscall/sysret insns
  kvmclock: reduce kvmclock difference on migration
  kvm: sync linux headers
  scsi-disk: fix VERIFY for scsi-block
  hw/block/pflash_cfi*.c: fix confusing assert fail message
  multiboot: copy the cmdline verbatim, unescape module strings
  x86: Fix x86_64 'g' packet response to gdb from 32-bit mode.
  pc: make pit configurable
  pc: make sata configurable
  pc: make smbus configurable
  target-i386: Add Intel SHA_NI instruction support.
  block: drop remaining legacy aio functions in comment
  main-loop: update comment for qemu_mutex_lock/unlock_iothread
  timer: fix misleading comment in timer.h
  qemu-timer: check active_timers outside lock/event
  virtio-scsi: introduce virtio_scsi_acquire/release
  build-sys: remove libtool left-over
  rules.mak: add more rules to avoid chaining
  rules.mak: speedup save-vars load-vars
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

10 files changed, 222 insertions, 21 deletions

diff --git a/include/block/aio.h b/include/block/aio.h
index c7ae27c..ca551e3 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -195,8 +195,8 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
  * aio_notify: Force processing of pending events.
  *
  * Similar to signaling a condition variable, aio_notify forces
- * aio_wait to exit, so that the next call will re-examine pending events.
- * The caller of aio_notify will usually call aio_wait again very soon,
+ * aio_poll to exit, so that the next call will re-examine pending events.
+ * The caller of aio_notify will usually call aio_poll again very soon,
  * or go through another iteration of the GLib main loop.  Hence, aio_notify
  * also has the side effect of recalculating the sets of file descriptors
  * that the main loop waits for.
diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h
index e9004e5..ffe43d5 100644
--- a/include/exec/cpu-all.h
+++ b/include/exec/cpu-all.h
@@ -186,6 +186,29 @@ void address_space_stl(AddressSpace *as, hwaddr addr, uint32_t val,
                             MemTxAttrs attrs, MemTxResult *result);
 void address_space_stq(AddressSpace *as, hwaddr addr, uint64_t val,
                             MemTxAttrs attrs, MemTxResult *result);
+
+uint32_t lduw_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t ldl_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint64_t ldq_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+void stl_phys_notdirty_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stw_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stl_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stq_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+
+uint32_t address_space_lduw_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_ldl_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint64_t address_space_ldq_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_notdirty_cached(MemoryRegionCache *cache, hwaddr addr,
+                            uint32_t val, MemTxAttrs attrs, MemTxResult *result);
+void address_space_stw_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stq_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
 #endif
 
 /* page related stuff */
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index cffdc13..bd15853 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -94,21 +94,6 @@ bool cpu_physical_memory_is_io(hwaddr phys_addr);
  */
 void qemu_flush_coalesced_mmio_buffer(void);
 
-uint32_t ldub_phys(AddressSpace *as, hwaddr addr);
-uint32_t lduw_le_phys(AddressSpace *as, hwaddr addr);
-uint32_t lduw_be_phys(AddressSpace *as, hwaddr addr);
-uint32_t ldl_le_phys(AddressSpace *as, hwaddr addr);
-uint32_t ldl_be_phys(AddressSpace *as, hwaddr addr);
-uint64_t ldq_le_phys(AddressSpace *as, hwaddr addr);
-uint64_t ldq_be_phys(AddressSpace *as, hwaddr addr);
-void stb_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stw_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stw_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stl_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stl_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stq_le_phys(AddressSpace *as, hwaddr addr, uint64_t val);
-void stq_be_phys(AddressSpace *as, hwaddr addr, uint64_t val);
-
 void cpu_physical_memory_write_rom(AddressSpace *as, hwaddr addr,
                                    const uint8_t *buf, int len);
 void cpu_flush_icache_range(hwaddr start, int len);
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 9728a2f..64560f6 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -1404,6 +1404,140 @@ void address_space_stq_le(AddressSpace *as, hwaddr addr, uint64_t val,
 void address_space_stq_be(AddressSpace *as, hwaddr addr, uint64_t val,
                             MemTxAttrs attrs, MemTxResult *result);
 
+uint32_t ldub_phys(AddressSpace *as, hwaddr addr);
+uint32_t lduw_le_phys(AddressSpace *as, hwaddr addr);
+uint32_t lduw_be_phys(AddressSpace *as, hwaddr addr);
+uint32_t ldl_le_phys(AddressSpace *as, hwaddr addr);
+uint32_t ldl_be_phys(AddressSpace *as, hwaddr addr);
+uint64_t ldq_le_phys(AddressSpace *as, hwaddr addr);
+uint64_t ldq_be_phys(AddressSpace *as, hwaddr addr);
+void stb_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stw_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stw_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stl_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stl_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stq_le_phys(AddressSpace *as, hwaddr addr, uint64_t val);
+void stq_be_phys(AddressSpace *as, hwaddr addr, uint64_t val);
+
+struct MemoryRegionCache {
+    hwaddr xlat;
+    void *ptr;
+    hwaddr len;
+    MemoryRegion *mr;
+    bool is_write;
+};
+
+/* address_space_cache_init: prepare for repeated access to a physical
+ * memory region
+ *
+ * @cache: #MemoryRegionCache to be filled
+ * @as: #AddressSpace to be accessed
+ * @addr: address within that address space
+ * @len: length of buffer
+ * @is_write: indicates the transfer direction
+ *
+ * Will only work with RAM, and may map a subset of the requested range by
+ * returning a value that is less than @len.  On failure, return a negative
+ * errno value.
+ *
+ * Because it only works with RAM, this function can be used for
+ * read-modify-write operations.  In this case, is_write should be %true.
+ *
+ * Note that addresses passed to the address_space_*_cached functions
+ * are relative to @addr.
+ */
+int64_t address_space_cache_init(MemoryRegionCache *cache,
+                                 AddressSpace *as,
+                                 hwaddr addr,
+                                 hwaddr len,
+                                 bool is_write);
+
+/**
+ * address_space_cache_invalidate: complete a write to a #MemoryRegionCache
+ *
+ * @cache: The #MemoryRegionCache to operate on.
+ * @addr: The first physical address that was written, relative to the
+ * address that was passed to @address_space_cache_init.
+ * @access_len: The number of bytes that were written starting at @addr.
+ */
+void address_space_cache_invalidate(MemoryRegionCache *cache,
+                                    hwaddr addr,
+                                    hwaddr access_len);
+
+/**
+ * address_space_cache_destroy: free a #MemoryRegionCache
+ *
+ * @cache: The #MemoryRegionCache whose memory should be released.
+ */
+void address_space_cache_destroy(MemoryRegionCache *cache);
+
+/* address_space_ld*_cached: load from a cached #MemoryRegion
+ * address_space_st*_cached: store into a cached #MemoryRegion
+ *
+ * These functions perform a load or store of the byte, word,
+ * longword or quad to the specified address.  The address is
+ * a physical address in the AddressSpace, but it must lie within
+ * a #MemoryRegion that was mapped with address_space_cache_init.
+ *
+ * The _le suffixed functions treat the data as little endian;
+ * _be indicates big endian; no suffix indicates "same endianness
+ * as guest CPU".
+ *
+ * The "guest CPU endianness" accessors are deprecated for use outside
+ * target-* code; devices should be CPU-agnostic and use either the LE
+ * or the BE accessors.
+ *
+ * @cache: previously initialized #MemoryRegionCache to be accessed
+ * @addr: address within the address space
+ * @val: data value, for stores
+ * @attrs: memory transaction attributes
+ * @result: location to write the success/failure of the transaction;
+ *   if NULL, this information is discarded
+ */
+uint32_t address_space_ldub_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_lduw_le_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_lduw_be_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_ldl_le_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_ldl_be_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint64_t address_space_ldq_le_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint64_t address_space_ldq_be_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stb_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stw_le_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stw_be_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_le_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_be_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stq_le_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stq_be_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+
+uint32_t ldub_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t lduw_le_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t lduw_be_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t ldl_le_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t ldl_be_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint64_t ldq_le_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint64_t ldq_be_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+void stb_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stw_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stw_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stl_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stl_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stq_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+void stq_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+
 /* address_space_translate: translate an address range into an address space
  * into a MemoryRegion and an address range into that section.  Should be
  * called from an RCU critical section, to avoid that the last reference
@@ -1529,6 +1663,38 @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
     return result;
 }
 
+/**
+ * address_space_read_cached: read from a cached RAM region
+ *
+ * @cache: Cached region to be addressed
+ * @addr: address relative to the base of the RAM region
+ * @buf: buffer with the data transferred
+ * @len: length of the data transferred
+ */
+static inline void
+address_space_read_cached(MemoryRegionCache *cache, hwaddr addr,
+                          void *buf, int len)
+{
+    assert(addr < cache->len && len <= cache->len - addr);
+    memcpy(buf, cache->ptr + addr, len);
+}
+
+/**
+ * address_space_write_cached: write to a cached RAM region
+ *
+ * @cache: Cached region to be addressed
+ * @addr: address relative to the base of the RAM region
+ * @buf: buffer with the data transferred
+ * @len: length of the data transferred
+ */
+static inline void
+address_space_write_cached(MemoryRegionCache *cache, hwaddr addr,
+                           void *buf, int len)
+{
+    assert(addr < cache->len && len <= cache->len - addr);
+    memcpy(cache->ptr + addr, buf, len);
+}
+
 #endif
 
 #endif
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 4b74130..b22e699 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -63,6 +63,9 @@ struct PCMachineState {
     AcpiNVDIMMState acpi_nvdimm_state;
 
     bool acpi_build_enabled;
+    bool smbus;
+    bool sata;
+    bool pit;
 
     /* RAM information (sizes, addresses, configuration): */
     ram_addr_t below_4g_mem_size, above_4g_mem_size;
@@ -88,6 +91,9 @@ struct PCMachineState {
 #define PC_MACHINE_VMPORT           "vmport"
 #define PC_MACHINE_SMM              "smm"
 #define PC_MACHINE_NVDIMM           "nvdimm"
+#define PC_MACHINE_SMBUS            "smbus"
+#define PC_MACHINE_SATA             "sata"
+#define PC_MACHINE_PIT              "pit"
 
 /**
  * PCMachineClass:
@@ -260,6 +266,7 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,
                           ISADevice **rtc_state,
                           bool create_fdctrl,
                           bool no_vmport,
+                          bool has_pit,
                           uint32_t hpet_irqs);
 void pc_init_ne2k_isa(ISABus *bus, NICInfo *nd);
 void pc_cmos_init(PCMachineState *pcms,
@@ -372,6 +379,11 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);
 #define PC_COMPAT_2_7 \
     HW_COMPAT_2_7 \
     {\
+        .driver   = "kvmclock",\
+        .property = "x-mach-use-reliable-get-clock",\
+        .value    = "off",\
+    },\
+    {\
         .driver   = TYPE_X86_CPU,\
         .property = "l3-cache",\
         .value    = "off",\
diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h
index 470f600..a9d4f23 100644
--- a/include/qemu/main-loop.h
+++ b/include/qemu/main-loop.h
@@ -238,7 +238,7 @@ bool qemu_mutex_iothread_locked(void);
  * qemu_mutex_lock_iothread: Lock the main loop mutex.
  *
  * This function locks the main loop mutex.  The mutex is taken by
- * qemu_init_main_loop and always taken except while waiting on
+ * main() in vl.c and always taken except while waiting on
  * external events (such as with select).  The mutex should be taken
  * by threads other than the main loop thread when calling
  * qemu_bh_new(), qemu_set_fd_handler() and basically all other
@@ -253,7 +253,7 @@ void qemu_mutex_lock_iothread(void);
  * qemu_mutex_unlock_iothread: Unlock the main loop mutex.
  *
  * This function unlocks the main loop mutex.  The mutex is taken by
- * qemu_init_main_loop and always taken except while waiting on
+ * main() in vl.c and always taken except while waiting on
  * external events (such as with select).  The mutex should be unlocked
  * as soon as possible by threads other than the main loop thread,
  * because it prevents the main loop from processing callbacks,
diff --git a/include/qemu/timer.h b/include/qemu/timer.h
index bdfae00..9abed51 100644
--- a/include/qemu/timer.h
+++ b/include/qemu/timer.h
@@ -133,7 +133,7 @@ bool qemu_clock_has_timers(QEMUClockType type);
  * @type: the clock type
  *
  * Determines whether a clock's default timer list
- * has an expired clock.
+ * has an expired timer.
  *
  * Returns: true if the clock's default timer list has
  * an expired timer
diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h
index 1b8c30a..9a8bcbd 100644
--- a/include/qemu/typedefs.h
+++ b/include/qemu/typedefs.h
@@ -45,6 +45,7 @@ typedef struct MachineState MachineState;
 typedef struct MemoryListener MemoryListener;
 typedef struct MemoryMappingList MemoryMappingList;
 typedef struct MemoryRegion MemoryRegion;
+typedef struct MemoryRegionCache MemoryRegionCache;
 typedef struct MemoryRegionSection MemoryRegionSection;
 typedef struct MigrationIncomingState MigrationIncomingState;
 typedef struct MigrationParams MigrationParams;
diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h
index 7361a16..b472b85 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -245,6 +245,7 @@ struct input_mask {
 #define BUS_SPI			0x1C
 #define BUS_RMI			0x1D
 #define BUS_CEC			0x1E
+#define BUS_INTEL_ISHTP		0x1F
 
 /*
  * MT_TOOL types
diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h
index 4040951..e5a2e68 100644
--- a/include/standard-headers/linux/pci_regs.h
+++ b/include/standard-headers/linux/pci_regs.h
@@ -612,6 +612,8 @@
  */
 #define PCI_EXP_DEVCAP2		36	/* Device Capabilities 2 */
 #define  PCI_EXP_DEVCAP2_ARI		0x00000020 /* Alternative Routing-ID */
+#define  PCI_EXP_DEVCAP2_ATOMIC_ROUTE	0x00000040 /* Atomic Op routing */
+#define PCI_EXP_DEVCAP2_ATOMIC_COMP64	0x00000100 /* Atomic 64-bit compare */
 #define  PCI_EXP_DEVCAP2_LTR		0x00000800 /* Latency tolerance reporting */
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
@@ -619,6 +621,7 @@
 #define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
 #define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
 #define  PCI_EXP_DEVCTL2_ARI		0x0020	/* Alternative Routing-ID */
+#define PCI_EXP_DEVCTL2_ATOMIC_REQ	0x0040	/* Set Atomic requests */
 #define  PCI_EXP_DEVCTL2_IDO_REQ_EN	0x0100	/* Allow IDO for requests */
 #define  PCI_EXP_DEVCTL2_IDO_CMP_EN	0x0200	/* Allow IDO for completions */
 #define  PCI_EXP_DEVCTL2_LTR_EN		0x0400	/* Enable LTR mechanism */
@@ -671,7 +674,8 @@
 #define PCI_EXT_CAP_ID_PMUX	0x1A	/* Protocol Multiplexing */
 #define PCI_EXT_CAP_ID_PASID	0x1B	/* Process Address Space ID */
 #define PCI_EXT_CAP_ID_DPC	0x1D	/* Downstream Port Containment */
-#define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_DPC
+#define PCI_EXT_CAP_ID_PTM	0x1F	/* Precision Time Measurement */
+#define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_PTM
 
 #define PCI_EXT_CAP_DSN_SIZEOF	12
 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40
@@ -964,4 +968,13 @@
 
 #define PCI_EXP_DPC_SOURCE_ID		10	/* DPC Source Identifier */
 
+/* Precision Time Measurement */
+#define PCI_PTM_CAP			0x04	    /* PTM Capability */
+#define  PCI_PTM_CAP_REQ		0x00000001  /* Requester capable */
+#define  PCI_PTM_CAP_ROOT		0x00000004  /* Root capable */
+#define  PCI_PTM_GRANULARITY_MASK	0x0000FF00  /* Clock granularity */
+#define PCI_PTM_CTRL			0x08	    /* PTM Control */
+#define  PCI_PTM_CTRL_ENABLE		0x00000001  /* PTM enable */
+#define  PCI_PTM_CTRL_ROOT		0x00000002  /* Root select */
+
 #endif /* LINUX_PCI_REGS_H */