Re: [PATCH v8 1/4] bswap: Add the ability to store to an unaligned 24 bit field

[Philippe Mathieu-Daudé]

Hi Ira & Jonathan,

On 26/5/23 19:00, Jonathan Cameron wrote:

From: Ira Weiny <ira.we...@intel.com>

CXL has 24 bit unaligned fields which need to be stored to.  CXL is
specified as little endian.

Define st24_le_p() and the supporting functions to store such a field
from a 32 bit host native value.

The use of b, w, l, q as the size specifier is limiting.  So "24" was
used for the size part of the function name.

Reviewed-by: Fan Ni <fan...@samsung.com>
Reviewed-by: Philippe Mathieu-Daudé <phi...@linaro.org>
Signed-off-by: Ira Weiny <ira.we...@intel.com>
Signed-off-by: Jonathan Cameron <jonathan.came...@huawei.com>
---
  docs/devel/loads-stores.rst |  2 ++
  include/qemu/bswap.h        | 25 +++++++++++++++++++++++++
  2 files changed, 27 insertions(+)

diff --git a/docs/devel/loads-stores.rst b/docs/devel/loads-stores.rst
index d2cefc77a2..dab6dfa0ac 100644
--- a/docs/devel/loads-stores.rst
+++ b/docs/devel/loads-stores.rst
@@ -36,6 +36,7 @@ store: ``st{size}_{endian}_p(ptr, val)``
  ``size``
   - ``b`` : 8 bits
   - ``w`` : 16 bits
+ - ``24`` : 24 bits
   - ``l`` : 32 bits
   - ``q`` : 64 bits

@@ -65,6 +66,7 @@ of size ``sz`` bytes.

  Regexes for git grep
   - ``\<ld[us]\?[bwlq]\(_[hbl]e\)\?_p\>``
   - ``\<st[bwlq]\(_[hbl]e\)\?_p\>``
+ - ``\<st24\(_[hbl]e\)\?_p\>``

Interestingly this regexp mentions st24_be_p() but this patch
only adds st24_le_p() and st24_he_p().

No need to update the regexp, I'll post a patch with st24_be_p()
since I have use for it.

   - ``\<ldn_\([hbl]e\)?_p\>``
   - ``\<stn_\([hbl]e\)?_p\>``

diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h

index 15a78c0db5..933a66ee87 100644
--- a/include/qemu/bswap.h
+++ b/include/qemu/bswap.h
@@ -8,11 +8,23 @@
  #undef  bswap64
  #define bswap64(_x) __builtin_bswap64(_x)

+static inline uint32_t bswap24(uint32_t x)

+{
+    return (((x & 0x000000ffU) << 16) |
+            ((x & 0x0000ff00U) <<  0) |
+            ((x & 0x00ff0000U) >> 16));
+}
+
  static inline void bswap16s(uint16_t *s)
  {
      *s = __builtin_bswap16(*s);
  }

+static inline void bswap24s(uint32_t *s)

+{
+    *s = bswap24(*s & 0x00ffffffU);
+}
+
  static inline void bswap32s(uint32_t *s)
  {
      *s = __builtin_bswap32(*s);
@@ -26,11 +38,13 @@ static inline void bswap64s(uint64_t *s)
  #if HOST_BIG_ENDIAN
  #define be_bswap(v, size) (v)
  #define le_bswap(v, size) glue(__builtin_bswap, size)(v)
+#define le_bswap24(v) bswap24(v)
  #define be_bswaps(v, size)
  #define le_bswaps(p, size) \
              do { *p = glue(__builtin_bswap, size)(*p); } while (0)
  #else
  #define le_bswap(v, size) (v)
+#define le_bswap24(v) (v)
  #define be_bswap(v, size) glue(__builtin_bswap, size)(v)
  #define le_bswaps(v, size)
  #define be_bswaps(p, size) \
@@ -176,6 +190,7 @@ CPU_CONVERT(le, 64, uint64_t)
   * size is:
   *   b: 8 bits
   *   w: 16 bits
+ *   24: 24 bits
   *   l: 32 bits
   *   q: 64 bits
   *
@@ -248,6 +263,11 @@ static inline void stw_he_p(void *ptr, uint16_t v)
      __builtin_memcpy(ptr, &v, sizeof(v));
  }

+static inline void st24_he_p(void *ptr, uint32_t v)

+{
+    __builtin_memcpy(ptr, &v, 3);
+}
+
  static inline int ldl_he_p(const void *ptr)
  {
      int32_t r;
@@ -297,6 +317,11 @@ static inline void stw_le_p(void *ptr, uint16_t v)
      stw_he_p(ptr, le_bswap(v, 16));
  }

+static inline void st24_le_p(void *ptr, uint32_t v)

+{
+    st24_he_p(ptr, le_bswap24(v));
+}
+
  static inline void stl_le_p(void *ptr, uint32_t v)
  {
      stl_he_p(ptr, le_bswap(v, 32));