Merge remote-tracking branch 'remotes/stsquad/tags/pull-mttcg-240217-1' into staging

This is the MTTCG pull-request as posted yesterday.

# gpg: Signature made Fri 24 Feb 2017 11:17:51 GMT
# gpg:                using RSA key 0xFBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>"
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-mttcg-240217-1: (24 commits)
  tcg: enable MTTCG by default for ARM on x86 hosts
  hw/misc/imx6_src: defer clearing of SRC_SCR reset bits
  target-arm: ensure all cross vCPUs TLB flushes complete
  target-arm: don't generate WFE/YIELD calls for MTTCG
  target-arm/powerctl: defer cpu reset work to CPU context
  cputlb: introduce tlb_flush_*_all_cpus[_synced]
  cputlb: atomically update tlb fields used by tlb_reset_dirty
  cputlb: add tlb_flush_by_mmuidx async routines
  cputlb and arm/sparc targets: convert mmuidx flushes from varg to bitmap
  cputlb: introduce tlb_flush_* async work.
  cputlb: tweak qemu_ram_addr_from_host_nofail reporting
  cputlb: add assert_cpu_is_self checks
  tcg: handle EXCP_ATOMIC exception for system emulation
  tcg: enable thread-per-vCPU
  tcg: enable tb_lock() for SoftMMU
  tcg: remove global exit_request
  tcg: drop global lock during TCG code execution
  tcg: rename tcg_current_cpu to tcg_current_rr_cpu
  tcg: add kick timer for single-threaded vCPU emulation
  tcg: add options for enabling MTTCG
  ...

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

4 files changed, 138 insertions, 14 deletions

diff --git a/include/exec/cputlb.h b/include/exec/cputlb.h
index d454c005b7..3f941783c5 100644
--- a/include/exec/cputlb.h
+++ b/include/exec/cputlb.h
@@ -23,8 +23,6 @@
 /* cputlb.c */
 void tlb_protect_code(ram_addr_t ram_addr);
 void tlb_unprotect_code(ram_addr_t ram_addr);
-void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry, uintptr_t start,
-                           uintptr_t length);
 extern int tlb_flush_count;
 
 #endif
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 21ab7bf3fd..bcde1e6a14 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -93,6 +93,27 @@ void cpu_address_space_init(CPUState *cpu, AddressSpace *as, int asidx);
  */
 void tlb_flush_page(CPUState *cpu, target_ulong addr);
 /**
+ * tlb_flush_page_all_cpus:
+ * @cpu: src CPU of the flush
+ * @addr: virtual address of page to be flushed
+ *
+ * Flush one page from the TLB of the specified CPU, for all
+ * MMU indexes.
+ */
+void tlb_flush_page_all_cpus(CPUState *src, target_ulong addr);
+/**
+ * tlb_flush_page_all_cpus_synced:
+ * @cpu: src CPU of the flush
+ * @addr: virtual address of page to be flushed
+ *
+ * Flush one page from the TLB of the specified CPU, for all MMU
+ * indexes like tlb_flush_page_all_cpus except the source vCPUs work
+ * is scheduled as safe work meaning all flushes will be complete once
+ * the source vCPUs safe work is complete. This will depend on when
+ * the guests translation ends the TB.
+ */
+void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr);
+/**
  * tlb_flush:
  * @cpu: CPU whose TLB should be flushed
  *
@@ -103,24 +124,87 @@ void tlb_flush_page(CPUState *cpu, target_ulong addr);
  */
 void tlb_flush(CPUState *cpu);
 /**
+ * tlb_flush_all_cpus:
+ * @cpu: src CPU of the flush
+ */
+void tlb_flush_all_cpus(CPUState *src_cpu);
+/**
+ * tlb_flush_all_cpus_synced:
+ * @cpu: src CPU of the flush
+ *
+ * Like tlb_flush_all_cpus except this except the source vCPUs work is
+ * scheduled as safe work meaning all flushes will be complete once
+ * the source vCPUs safe work is complete. This will depend on when
+ * the guests translation ends the TB.
+ */
+void tlb_flush_all_cpus_synced(CPUState *src_cpu);
+/**
  * tlb_flush_page_by_mmuidx:
  * @cpu: CPU whose TLB should be flushed
  * @addr: virtual address of page to be flushed
- * @...: list of MMU indexes to flush, terminated by a negative value
+ * @idxmap: bitmap of MMU indexes to flush
  *
  * Flush one page from the TLB of the specified CPU, for the specified
  * MMU indexes.
  */
-void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, ...);
+void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr,
+                              uint16_t idxmap);
+/**
+ * tlb_flush_page_by_mmuidx_all_cpus:
+ * @cpu: Originating CPU of the flush
+ * @addr: virtual address of page to be flushed
+ * @idxmap: bitmap of MMU indexes to flush
+ *
+ * Flush one page from the TLB of all CPUs, for the specified
+ * MMU indexes.
+ */
+void tlb_flush_page_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr,
+                                       uint16_t idxmap);
+/**
+ * tlb_flush_page_by_mmuidx_all_cpus_synced:
+ * @cpu: Originating CPU of the flush
+ * @addr: virtual address of page to be flushed
+ * @idxmap: bitmap of MMU indexes to flush
+ *
+ * Flush one page from the TLB of all CPUs, for the specified MMU
+ * indexes like tlb_flush_page_by_mmuidx_all_cpus except the source
+ * vCPUs work is scheduled as safe work meaning all flushes will be
+ * complete once  the source vCPUs safe work is complete. This will
+ * depend on when the guests translation ends the TB.
+ */
+void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, target_ulong addr,
+                                              uint16_t idxmap);
 /**
  * tlb_flush_by_mmuidx:
  * @cpu: CPU whose TLB should be flushed
- * @...: list of MMU indexes to flush, terminated by a negative value
+ * @wait: If true ensure synchronisation by exiting the cpu_loop
+ * @idxmap: bitmap of MMU indexes to flush
  *
  * Flush all entries from the TLB of the specified CPU, for the specified
  * MMU indexes.
  */
-void tlb_flush_by_mmuidx(CPUState *cpu, ...);
+void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap);
+/**
+ * tlb_flush_by_mmuidx_all_cpus:
+ * @cpu: Originating CPU of the flush
+ * @idxmap: bitmap of MMU indexes to flush
+ *
+ * Flush all entries from all TLBs of all CPUs, for the specified
+ * MMU indexes.
+ */
+void tlb_flush_by_mmuidx_all_cpus(CPUState *cpu, uint16_t idxmap);
+/**
+ * tlb_flush_by_mmuidx_all_cpus_synced:
+ * @cpu: Originating CPU of the flush
+ * @idxmap: bitmap of MMU indexes to flush
+ *
+ * Flush all entries from all TLBs of all CPUs, for the specified
+ * MMU indexes like tlb_flush_by_mmuidx_all_cpus except except the source
+ * vCPUs work is scheduled as safe work meaning all flushes will be
+ * complete once  the source vCPUs safe work is complete. This will
+ * depend on when the guests translation ends the TB.
+ */
+void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap);
 /**
  * tlb_set_page_with_attrs:
  * @cpu: CPU to add this TLB entry for
@@ -162,17 +246,45 @@ void probe_write(CPUArchState *env, target_ulong addr, int mmu_idx,
 static inline void tlb_flush_page(CPUState *cpu, target_ulong addr)
 {
 }
-
+static inline void tlb_flush_page_all_cpus(CPUState *src, target_ulong addr)
+{
+}
+static inline void tlb_flush_page_all_cpus_synced(CPUState *src,
+                                                  target_ulong addr)
+{
+}
 static inline void tlb_flush(CPUState *cpu)
 {
 }
-
+static inline void tlb_flush_all_cpus(CPUState *src_cpu)
+{
+}
+static inline void tlb_flush_all_cpus_synced(CPUState *src_cpu)
+{
+}
 static inline void tlb_flush_page_by_mmuidx(CPUState *cpu,
-                                            target_ulong addr, ...)
+                                            target_ulong addr, uint16_t idxmap)
 {
 }
 
-static inline void tlb_flush_by_mmuidx(CPUState *cpu, ...)
+static inline void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap)
+{
+}
+static inline void tlb_flush_page_by_mmuidx_all_cpus(CPUState *cpu,
+                                                     target_ulong addr,
+                                                     uint16_t idxmap)
+{
+}
+static inline void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu,
+                                                            target_ulong addr,
+                                                            uint16_t idxmap)
+{
+}
+static inline void tlb_flush_by_mmuidx_all_cpus(CPUState *cpu, uint16_t idxmap)
+{
+}
+static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu,
+                                                       uint16_t idxmap)
 {
 }
 #endif
@@ -404,8 +516,4 @@ bool memory_region_is_unassigned(MemoryRegion *mr);
 /* vl.c */
 extern int singlestep;
 
-/* cpu-exec.c, accessed with atomic_mb_read/atomic_mb_set */
-extern CPUState *tcg_current_cpu;
-extern bool exit_request;
-
 #endif
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index f69b2407ea..3e61c880da 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -329,6 +329,7 @@ struct CPUState {
     bool unplug;
     bool crash_occurred;
     bool exit_request;
+    /* updates protected by BQL */
     uint32_t interrupt_request;
     int singlestep_enabled;
     int64_t icount_extra;
@@ -401,6 +402,12 @@ struct CPUState {
 
     bool hax_vcpu_dirty;
     struct hax_vcpu_state *hax_vcpu;
+
+    /* The pending_tlb_flush flag is set and cleared atomically to
+     * avoid potential races. The aim of the flag is to avoid
+     * unnecessary flushes.
+     */
+    uint16_t pending_tlb_flush;
 };
 
 QTAILQ_HEAD(CPUTailQ, CPUState);
@@ -416,6 +423,15 @@ extern struct CPUTailQ cpus;
 extern __thread CPUState *current_cpu;
 
 /**
+ * qemu_tcg_mttcg_enabled:
+ * Check whether we are running MultiThread TCG or not.
+ *
+ * Returns: %true if we are in MTTCG mode %false otherwise.
+ */
+extern bool mttcg_enabled;
+#define qemu_tcg_mttcg_enabled() (mttcg_enabled)
+
+/**
  * cpu_paging_enabled:
  * @cpu: The CPU whose state is to be inspected.
  *
diff --git a/include/sysemu/cpus.h b/include/sysemu/cpus.h
index 3728a1ea7e..a73b5d4bce 100644
--- a/include/sysemu/cpus.h
+++ b/include/sysemu/cpus.h
@@ -36,4 +36,6 @@ extern int smp_threads;
 
 void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg);
 
+void qemu_tcg_configure(QemuOpts *opts, Error **errp);
+
 #endif