eal: add write combining store

Add rte_write32_wc and rte_write32_wc_relaxed functions
that implement 32bit stores using write combining memory protocol.
Provided generic stubs and x86 implementation.

Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>

diff --git a/doc/guides/rel_notes/release_20_11.rst b/doc/guides/rel_notes/release_20_11.rst
index 57e3edc..48e4dfd 100644 (file)
--- a/doc/guides/rel_notes/release_20_11.rst
+++ b/doc/guides/rel_notes/release_20_11.rst
@@ -55,6 +55,13 @@ New Features
      Also, make sure to start the actual text at the margin.
      =======================================================
 
+* **Added write combining store APIs.**
+
+  Added ``rte_write32_wc`` and ``rte_write32_wc_relaxed`` APIs
+  that enable write combining stores (depending on architecture).
+  The functions are provided as a generic stubs and
+  x86 specific implementation.
+
 * **Added the FEC API, for a generic FEC query and config.**
 
   Added the FEC API which provides functions for query FEC capabilities and

diff --git a/lib/librte_eal/arm/include/rte_io_64.h b/lib/librte_eal/arm/include/rte_io_64.h
index e534624..d07d9cb 100644 (file)
--- a/lib/librte_eal/arm/include/rte_io_64.h
+++ b/lib/librte_eal/arm/include/rte_io_64.h
@@ -164,6 +164,18 @@ rte_write64(uint64_t value, volatile void *addr)
        rte_write64_relaxed(value, addr);
 }
 
+static __rte_always_inline void
+rte_write32_wc(uint32_t value, volatile void *addr)
+{
+       rte_write32(value, addr);
+}
+
+static __rte_always_inline void
+rte_write32_wc_relaxed(uint32_t value, volatile void *addr)
+{
+       rte_write32_relaxed(value, addr);
+}
+
 #ifdef __cplusplus
 }
 #endif

diff --git a/lib/librte_eal/include/generic/rte_io.h b/lib/librte_eal/include/generic/rte_io.h
index da457f7..0669baa 100644 (file)
--- a/lib/librte_eal/include/generic/rte_io.h
+++ b/lib/librte_eal/include/generic/rte_io.h
@@ -229,6 +229,40 @@ rte_write32(uint32_t value, volatile void *addr);
 static inline void
 rte_write64(uint64_t value, volatile void *addr);
 
+/**
+ * Write a 32-bit value to I/O device memory address addr using write
+ * combining memory write protocol. Depending on the platform write combining
+ * may not be available and/or may be treated as a hint and the behavior may
+ * fallback to a regular store.
+ *
+ * @param value
+ *  Value to write
+ * @param addr
+ *  I/O memory address to write the value to
+ */
+__rte_experimental
+static inline void
+rte_write32_wc(uint32_t value, volatile void *addr);
+
+/**
+ * Write a 32-bit value to I/O device memory address addr using write
+ * combining memory write protocol. Depending on the platform write combining
+ * may not be available and/or may be treated as a hint and the behavior may
+ * fallback to a regular store.
+ *
+ * The relaxed version does not have additional I/O memory barrier, useful in
+ * accessing the device registers of integrated controllers which implicitly
+ * strongly ordered with respect to memory access.
+ *
+ * @param value
+ *  Value to write
+ * @param addr
+ *  I/O memory address to write the value to
+ */
+__rte_experimental
+static inline void
+rte_write32_wc_relaxed(uint32_t value, volatile void *addr);
+
 #endif /* __DOXYGEN__ */
 
 #ifndef RTE_OVERRIDE_IO_H
@@ -345,6 +379,20 @@ rte_write64(uint64_t value, volatile void *addr)
        rte_write64_relaxed(value, addr);
 }
 
+#ifndef RTE_NATIVE_WRITE32_WC
+static __rte_always_inline void
+rte_write32_wc(uint32_t value, volatile void *addr)
+{
+       rte_write32(value, addr);
+}
+
+static __rte_always_inline void
+rte_write32_wc_relaxed(uint32_t value, volatile void *addr)
+{
+       rte_write32_relaxed(value, addr);
+}
+#endif /* RTE_NATIVE_WRITE32_WC */
+
 #endif /* RTE_OVERRIDE_IO_H */
 
 #endif /* _RTE_IO_H_ */

diff --git a/lib/librte_eal/x86/include/rte_io.h b/lib/librte_eal/x86/include/rte_io.h
index 2db71b1..c035eec 100644 (file)
--- a/lib/librte_eal/x86/include/rte_io.h
+++ b/lib/librte_eal/x86/include/rte_io.h
@@ -9,8 +9,51 @@
 extern "C" {
 #endif
 
+#include "rte_cpuflags.h"
+
+#define RTE_NATIVE_WRITE32_WC
 #include "generic/rte_io.h"
 
+/**
+ * @internal
+ * MOVDIRI wrapper.
+ */
+static __rte_always_inline void
+__rte_x86_movdiri(uint32_t value, volatile void *addr)
+{
+       asm volatile(
+               /* MOVDIRI */
+               ".byte 0x40, 0x0f, 0x38, 0xf9, 0x02"
+               :
+               : "a" (value), "d" (addr));
+}
+
+static __rte_always_inline void
+rte_write32_wc_relaxed(uint32_t value, volatile void *addr)
+{
+       static int _x86_movdiri_flag = -1;
+
+       if (_x86_movdiri_flag == 1) {
+               __rte_x86_movdiri(value, addr);
+       } else if (_x86_movdiri_flag == 0) {
+               rte_write32_relaxed(value, addr);
+       } else {
+               _x86_movdiri_flag =
+                       (rte_cpu_get_flag_enabled(RTE_CPUFLAG_MOVDIRI) > 0);
+               if (_x86_movdiri_flag == 1)
+                       __rte_x86_movdiri(value, addr);
+               else
+                       rte_write32_relaxed(value, addr);
+       }
+}
+
+static __rte_always_inline void
+rte_write32_wc(uint32_t value, volatile void *addr)
+{
+       rte_wmb();
+       rte_write32_wc_relaxed(value, addr);
+}
+
 #ifdef __cplusplus
 }
 #endif