[libc] [search] implement hcreate(_r)/hsearch(_r)/hdestroy(_r) (#73469)

This patch implements `hcreate(_r)/hsearch(_r)/hdestroy(_r)` as specified in https://man7.org/linux/man-pages/man3/hsearch.3.html. Notice that `neon/asimd` extension is not yet added in this patch. - The implementation is largely simplified from rust's [`hashbrown`](https://github.com/rust-lang/hashbrown/blob/master/src/raw/mod.rs) as we only consider fix-sized insertion-only hashtables. Technical details are provided in code comments. - This patch also contains a portable string hash function, which is derived from [`aHash`](https://github.com/tkaitchuck/aHash)'s fallback routine. Not using any SIMD acceleration, it has a good enough quality (passing all SMHasher tests) and is not too bad in speed. - Some general functionalities are added, such as `memory_size`, `offset_to`(alignment), `next_power_of_two`, `is_power_of_two`. `ctz/clz` are extended to support shorter integers.
llvm · Nov 29, 2023 · 81e3e7e · 81e3e7e
1 parent f7247d5
commit 81e3e7e
Show file tree

Hide file tree

Showing 58 changed files with 2,223 additions and 2 deletions.
diff --git a/libc/cmake/modules/LLVMLibCFlagRules.cmake b/libc/cmake/modules/LLVMLibCFlagRules.cmake
@@ -132,6 +132,8 @@ endfunction(get_fq_dep_list_without_flag)
 # Special flags
 set(FMA_OPT_FLAG "FMA_OPT")
 set(ROUND_OPT_FLAG "ROUND_OPT")
+# SSE2 is the baseline for x86_64, so we add a negative flag to disable it if needed.
+set(DISABLE_SSE2_OPT_FLAG "DISABLE_SSE2_OPT")
 
 # Skip FMA_OPT flag for targets that don't support fma.
 if(NOT((LIBC_TARGET_ARCHITECTURE_IS_X86 AND (LIBC_CPU_FEATURES MATCHES "FMA")) OR
@@ -143,3 +145,8 @@ endif()
 if(NOT(LIBC_TARGET_ARCHITECTURE_IS_X86 AND (LIBC_CPU_FEATURES MATCHES "SSE4_2")))
   set(SKIP_FLAG_EXPANSION_ROUND_OPT TRUE)
 endif()
+
+# Skip DISABLE_SSE2_OPT flag for targets that don't support SSE2.
+if(NOT(LIBC_TARGET_ARCHITECTURE_IS_X86 AND (LIBC_CPU_FEATURES MATCHES "SSE2")))
+  set(SKIP_FLAG_EXPANSION_DISABLE_SSE2_OPT TRUE)
+endif()
diff --git a/libc/cmake/modules/LLVMLibCObjectRules.cmake b/libc/cmake/modules/LLVMLibCObjectRules.cmake
@@ -18,6 +18,14 @@ function(_get_common_compile_options output_var flags)
     set(ADD_SSE4_2_FLAG TRUE)
   endif()
 
+  list(FIND flags ${DISABLE_SSE2_OPT_FLAG} no_sse2)
+  if(${no_sse2} LESS 0)
+    list(FIND flags "${DISABLE_SSE2_OPT_FLAG}__ONLY" no_sse2)
+  endif()
+  if((${no_sse2} GREATER -1) AND (LIBC_CPU_FEATURES MATCHES "SSE2"))
+    set(DISABLE_SSE2_FLAG TRUE)
+  endif()
+
   set(compile_options ${LIBC_COMPILE_OPTIONS_DEFAULT} ${ARGN})
   if(LLVM_COMPILER_IS_GCC_COMPATIBLE)
     list(APPEND compile_options "-fpie")
@@ -58,12 +66,18 @@ function(_get_common_compile_options output_var flags)
     if(ADD_SSE4_2_FLAG)
       list(APPEND compile_options "-msse4.2")
     endif()
+    if(DISABLE_SSE2_FLAG)
+      list(APPEND compile_options "-mno-sse2")
+    endif()
   elseif(MSVC)
     list(APPEND compile_options "/EHs-c-")
     list(APPEND compile_options "/GR-")
     if(ADD_FMA_FLAG)
       list(APPEND compile_options "/arch:AVX2")
     endif()
+    if(DISABLE_SSE2_FLAG)
+      list(APPEND compile_options "/arch:SSE")
+    endif()
   endif()
   if (LIBC_TARGET_ARCHITECTURE_IS_GPU)
     list(APPEND compile_options "-nogpulib")

diff --git a/libc/config/linux/aarch64/entrypoints.txt b/libc/config/linux/aarch64/entrypoints.txt
@@ -130,6 +130,14 @@ set(TARGET_LIBC_ENTRYPOINTS
     #libc.src.stdio.scanf
     #libc.src.stdio.fscanf
 
+    # search.h entrypoints
+    libc.src.search.hcreate
+    libc.src.search.hcreate_r
+    libc.src.search.hsearch
+    libc.src.search.hsearch_r
+    libc.src.search.hdestroy
+    libc.src.search.hdestroy_r
+
     # sys/mman.h entrypoints
     libc.src.sys.mman.madvise
     libc.src.sys.mman.mmap

diff --git a/libc/config/linux/aarch64/headers.txt b/libc/config/linux/aarch64/headers.txt
@@ -12,6 +12,7 @@ set(TARGET_PUBLIC_HEADERS
     libc.include.stdlib
     libc.include.string
     libc.include.strings
+    libc.include.search
     libc.include.sys_mman
     libc.include.sys_socket
     libc.include.sys_syscall

diff --git a/libc/config/linux/api.td b/libc/config/linux/api.td
@@ -248,3 +248,7 @@ def TermiosAPI : PublicAPI<"termios.h"> {
 def SetJmpAPI : PublicAPI<"setjmp.h"> {
   let Types = ["jmp_buf"];
 }
+
+def SearchAPI : PublicAPI<"search.h"> {
+  let Types = ["ACTION", "ENTRY", "struct hsearch_data"];
+}
diff --git a/libc/config/linux/arm/entrypoints.txt b/libc/config/linux/arm/entrypoints.txt
@@ -89,6 +89,14 @@ set(TARGET_LIBC_ENTRYPOINTS
     libc.src.stdlib.strtoul
     libc.src.stdlib.strtoull
 
+    # search.h entrypoints
+    libc.src.search.hcreate
+    libc.src.search.hcreate_r
+    libc.src.search.hsearch
+    libc.src.search.hsearch_r
+    libc.src.search.hdestroy
+    libc.src.search.hdestroy_r
+
     # sys/mman.h entrypoints
     libc.src.sys.mman.mmap
     libc.src.sys.mman.munmap

diff --git a/libc/config/linux/arm/headers.txt b/libc/config/linux/arm/headers.txt
@@ -7,4 +7,5 @@ set(TARGET_PUBLIC_HEADERS
     libc.include.stdlib
     libc.include.string
     libc.include.strings
+    libc.include.search
 )
diff --git a/libc/config/linux/riscv/entrypoints.txt b/libc/config/linux/riscv/entrypoints.txt
@@ -136,6 +136,14 @@ set(TARGET_LIBC_ENTRYPOINTS
     libc.src.stdio.scanf
     libc.src.stdio.fscanf
 
+    # search.h entrypoints
+    libc.src.search.hcreate
+    libc.src.search.hcreate_r
+    libc.src.search.hsearch
+    libc.src.search.hsearch_r
+    libc.src.search.hdestroy
+    libc.src.search.hdestroy_r
+
     # sys/mman.h entrypoints
     libc.src.sys.mman.madvise
     libc.src.sys.mman.mmap

diff --git a/libc/config/linux/riscv/headers.txt b/libc/config/linux/riscv/headers.txt
@@ -17,6 +17,7 @@ set(TARGET_PUBLIC_HEADERS
     libc.include.stdlib
     libc.include.string
     libc.include.strings
+    libc.include.search
     libc.include.termios
     libc.include.threads
     libc.include.time

diff --git a/libc/config/linux/x86_64/entrypoints.txt b/libc/config/linux/x86_64/entrypoints.txt
@@ -497,6 +497,14 @@ if(LLVM_LIBC_FULL_BUILD)
     libc.src.spawn.posix_spawn_file_actions_destroy
     libc.src.spawn.posix_spawn_file_actions_init
 
+    # search.h entrypoints
+    libc.src.search.hcreate
+    libc.src.search.hcreate_r
+    libc.src.search.hsearch
+    libc.src.search.hsearch_r
+    libc.src.search.hdestroy
+    libc.src.search.hdestroy_r
+
     # threads.h entrypoints
     libc.src.threads.call_once
     libc.src.threads.cnd_broadcast

diff --git a/libc/config/linux/x86_64/headers.txt b/libc/config/linux/x86_64/headers.txt
@@ -17,6 +17,7 @@ set(TARGET_PUBLIC_HEADERS
     libc.include.stdlib
     libc.include.string
     libc.include.strings
+    libc.include.search
     libc.include.termios
     libc.include.threads
     libc.include.time

diff --git a/libc/include/CMakeLists.txt b/libc/include/CMakeLists.txt
@@ -133,6 +133,18 @@ add_gen_header(
     .llvm-libc-types.size_t
 )
 
+add_gen_header(
+  search
+  DEF_FILE search.h.def
+  GEN_HDR search.h
+  DEPENDS
+    .llvm_libc_common_h
+    .llvm-libc-types.ACTION
+    .llvm-libc-types.ENTRY
+    .llvm-libc-types.struct_hsearch_data
+    .llvm-libc-types.size_t
+)
+
 add_gen_header(
   time
   DEF_FILE time.h.def

diff --git a/libc/include/llvm-libc-types/ACTION.h b/libc/include/llvm-libc-types/ACTION.h
@@ -0,0 +1,14 @@
+//===-- Definition of ACTION type -----------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef __LLVM_LIBC_TYPES_ACTION_H__
+#define __LLVM_LIBC_TYPES_ACTION_H__
+
+typedef enum { FIND, ENTER } ACTION;
+
+#endif // __LLVM_LIBC_TYPES_ACTION_H__
diff --git a/libc/include/llvm-libc-types/CMakeLists.txt b/libc/include/llvm-libc-types/CMakeLists.txt
@@ -91,3 +91,6 @@ add_header(wint_t HDR wint_t.h)
 add_header(sa_family_t HDR sa_family_t.h)
 add_header(struct_sockaddr HDR struct_sockaddr.h)
 add_header(rpc_opcodes_t HDR rpc_opcodes_t.h)
+add_header(ACTION HDR ACTION.h)
+add_header(ENTRY HDR ENTRY.h)
+add_header(struct_hsearch_data HDR struct_hsearch_data.h)
diff --git a/libc/include/llvm-libc-types/ENTRY.h b/libc/include/llvm-libc-types/ENTRY.h
@@ -0,0 +1,17 @@
+//===-- Definition of ENTRY type ------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef __LLVM_LIBC_TYPES_ENTRY_H__
+#define __LLVM_LIBC_TYPES_ENTRY_H__
+
+typedef struct {
+  char *key;
+  void *data;
+} ENTRY;
+
+#endif // __LLVM_LIBC_TYPES_ENTRY_H__
diff --git a/libc/include/llvm-libc-types/struct_hsearch_data.h b/libc/include/llvm-libc-types/struct_hsearch_data.h
@@ -0,0 +1,17 @@
+//===-- Definition of type struct hsearch_data ----------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef __LLVM_LIBC_TYPES_STRUCT_HSEARCH_DATA_H__
+#define __LLVM_LIBC_TYPES_STRUCT_HSEARCH_DATA_H__
+
+struct hsearch_data {
+  void *__opaque;
+  unsigned int __unused[2];
+};
+
+#endif // __LLVM_LIBC_TYPES_STRUCT_HSEARCH_DATA_H__
diff --git a/libc/include/search.h.def b/libc/include/search.h.def
@@ -0,0 +1,18 @@
+//===-- POSIX header search.h ---------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_SEARCH_H
+#define LLVM_LIBC_SEARCH_H
+
+#include <__llvm-libc-common.h>
+#define __need_size_t
+#include <stddef.h>
+
+%%public_api()
+
+#endif // LLVM_LIBC_SEARCH_H
diff --git a/libc/spec/gnu_ext.td b/libc/spec/gnu_ext.td
@@ -3,6 +3,8 @@ def CpuSetPtr : PtrType<CpuSetT>;
 def ConstCpuSetPtr : ConstType<CpuSetPtr>;
 
 def QSortRCompareT : NamedType<"__qsortrcompare_t">;
+def StructHsearchData : NamedType<"struct hsearch_data">;
+def StructHsearchDataPtr : PtrType<StructHsearchData>;
 
 def GnuExtensions : StandardSpec<"GNUExtensions"> {
   NamedType CookieIOFunctionsT = NamedType<"cookie_io_functions_t">;
@@ -54,7 +56,6 @@ def GnuExtensions : StandardSpec<"GNUExtensions"> {
         >,
       ]
   >;
-
   HeaderSpec String = HeaderSpec<
       "string.h",
       [], // Macros
@@ -89,6 +90,42 @@ def GnuExtensions : StandardSpec<"GNUExtensions"> {
       ]
   >;
 
+  HeaderSpec Search = HeaderSpec<
+    "search.h",
+    [], // Macros
+    [
+        StructHsearchData
+    ],
+    [], // Enumerations
+    [
+        FunctionSpec<
+            "hcreate_r",
+            RetValSpec<IntType>,
+            [  
+                ArgSpec<SizeTType>, 
+                ArgSpec<StructHsearchDataPtr>
+            ]
+        >,
+        FunctionSpec<
+            "hdestroy_r",
+            RetValSpec<VoidType>,
+            [
+                ArgSpec<StructHsearchDataPtr>
+            ]
+        >,
+        FunctionSpec<
+            "hsearch_r",
+            RetValSpec<IntType>,
+            [
+                ArgSpec<EntryType>, 
+                ArgSpec<ActionType>,
+                ArgSpec<EntryTypePtrPtr>,
+                ArgSpec<StructHsearchDataPtr>
+            ]
+        >,
+    ]
+  >;
+
   HeaderSpec FEnv = HeaderSpec<
       "fenv.h",
       [], // Macros
@@ -243,6 +280,7 @@ def GnuExtensions : StandardSpec<"GNUExtensions"> {
     StdIO,
     StdLib,
     String,
+    Search,
     UniStd,
   ];
 }
diff --git a/libc/spec/posix.td b/libc/spec/posix.td
@@ -1269,6 +1269,38 @@ def POSIX : StandardSpec<"POSIX"> {
     ]
   >;
 
+  HeaderSpec Search = HeaderSpec<
+    "search.h",
+    [], // Macros
+    [
+        ActionType,
+        EntryType
+    ], // Types
+    [], // Enumerations
+    [
+        FunctionSpec<
+            "hcreate",
+            RetValSpec<IntType>,
+            [
+                ArgSpec<SizeTType>
+            ]
+        >,
+        FunctionSpec<
+            "hdestroy",
+            RetValSpec<VoidType>,
+            [] // Args
+        >,
+        FunctionSpec<
+            "hsearch",
+            RetValSpec<EntryTypePtr>,
+            [
+                ArgSpec<EntryType>, 
+                ArgSpec<ActionType>
+            ]
+        >,
+    ]
+  >; 
+
   HeaderSpec Termios = HeaderSpec<
     "termios.h",
     [
@@ -1414,6 +1446,7 @@ def POSIX : StandardSpec<"POSIX"> {
     Time,
     Termios,
     UniStd,
-    String
+    String,
+    Search,
   ];
 }
diff --git a/libc/spec/spec.td b/libc/spec/spec.td
@@ -140,6 +140,11 @@ def SuSecondsT : NamedType<"suseconds_t">;
 //added because __assert_fail needs it.
 def UnsignedType : NamedType<"unsigned">;
 
+def ActionType : NamedType<"ACTION">;
+def EntryType : NamedType<"ENTRY">;
+def EntryTypePtr : PtrType<EntryType>;
+def EntryTypePtrPtr : PtrType<EntryTypePtr>;
+
 class Macro<string name> {
   string Name = name;
 }

diff --git a/libc/src/CMakeLists.txt b/libc/src/CMakeLists.txt
@@ -35,3 +35,4 @@ add_subdirectory(signal)
 add_subdirectory(spawn)
 add_subdirectory(threads)
 add_subdirectory(time)
+add_subdirectory(search)