msb_14154
/
wasi-sdk
mirror of https://github.com/WebAssembly/wasi-sdk
1
0
Code Issues Projects Releases Wiki Activity

Prepare for 34-rc.2

Browse Source 
* Update LLVM to 23.1.0-rc.2
* Update wasi-libc to tip
* Manually add in wasm-ld fixes
* Update wasm-component-ld
pull/644/head
Alex Crichton 2 months ago
parent 358113409c
commit 380a06abce
5 changed files with 969 additions and 3 deletions
Show Stats Download Patch File Download Diff File

8
cmake/wasi-sdk-toolchain.cmake
Unescape View File

@ -255,6 +255,12 @@ ExternalProject_Add(llvm-build
USES_TERMINAL_CONFIGURE ON
USES_TERMINAL_BUILD ON
USES_TERMINAL_INSTALL ON
PATCH_COMMAND
${CMAKE_COMMAND} -E chdir .. bash -c
"git apply ${CMAKE_SOURCE_DIR}/src/llvm-pr-206831.patch || git apply ${CMAKE_SOURCE_DIR}/src/llvm-pr-206831.patch -R --check"
COMMAND
${CMAKE_COMMAND} -E chdir .. bash -c
"git apply ${CMAKE_SOURCE_DIR}/src/llvm-prs-208263-208332-208597.patch || git apply ${CMAKE_SOURCE_DIR}/src/llvm-prs-208263-208332-208597.patch -R --check"
)
add_custom_target(build ALL DEPENDS llvm-build)
@ -269,7 +275,7 @@ install(DIRECTORY ${wasi_tmp_install}/bin ${wasi_tmp_install}/lib ${wasi_tmp_ins
# Build logic for `wasm-component-ld` installed from Rust code.
set(wasm_component_ld_root ${CMAKE_CURRENT_BINARY_DIR}/wasm-component-ld)
set(wasm_component_ld ${wasm_component_ld_root}/bin/wasm-component-ld${CMAKE_EXECUTABLE_SUFFIX})
set(wasm_component_ld_version 0.5.26)
set(wasm_component_ld_version 0.5.27)
if(RUST_TARGET)
set(rust_target_flag --target=${RUST_TARGET})
endif()

88
src/llvm-pr-206831.patch
Unescape View File

@ -0,0 +1,88 @@
diff --git a/lld/test/wasm/cooperative-threading-gc.s b/lld/test/wasm/cooperative-threading-gc.s
new file mode 100644
index 0000000000000..2af2460939aad
--- /dev/null
+++ b/lld/test/wasm/cooperative-threading-gc.s
@@ -0,0 +1,57 @@
+# Verify that --gc-sections preserves functions reachable only through the
+# thread-context accessors __wasm_{get,set}_tls_base. These accessors are
+# invoked by synthetic init functions (e.g. __wasm_init_tls) via `call`
+# instructions that carry no relocations, so the linker marks the accessors
+# live explicitly. Their own relocations must still be followed during GC,
+# otherwise functions they call (here modeling the cooperative-threading
+# context.set builtin) are incorrectly collected and the call is mis-resolved.
+
+# RUN: llvm-mc -filetype=obj -triple=wasm32-unknown-unknown -o %t.o %s
+# RUN: wasm-ld --cooperative-threading --gc-sections -o %t.wasm %t.o
+# RUN: obj2yaml %t.wasm | FileCheck %s
+
+ .functype set_helper (i32) -> ()
+ .import_module set_helper, "env"
+ .import_name set_helper, "set_helper"
+
+.globl __wasm_get_tls_base
+__wasm_get_tls_base:
+ .functype __wasm_get_tls_base () -> (i32)
+ i32.const 0
+ end_function
+
+# Reachable only via the synthetic __wasm_init_tls. Its call to `set_helper`
+# must keep `set_helper` live.
+.globl __wasm_set_tls_base
+__wasm_set_tls_base:
+ .functype __wasm_set_tls_base (i32) -> ()
+ local.get 0
+ call set_helper
+ end_function
+
+.globl _start
+_start:
+ .functype _start () -> (i32)
+ call __wasm_get_tls_base
+ i32.const tls1@TLSREL
+ i32.add
+ i32.load 0
+ end_function
+
+.section .tdata.tls1,"",@
+.globl tls1
+tls1:
+ .int32 1
+ .size tls1, 4
+
+.section .custom_section.target_features,"",@
+ .int8 2
+ .int8 43
+ .int8 11
+ .ascii "bulk-memory"
+ .int8 43
+ .int8 7
+ .ascii "atomics"
+
+# The imported helper called by __wasm_set_tls_base must survive GC.
+# CHECK: Field: set_helper
diff --git a/lld/wasm/MarkLive.cpp b/lld/wasm/MarkLive.cpp
index 2b2cf19f14b30..3364be006ca24 100644
--- a/lld/wasm/MarkLive.cpp
+++ b/lld/wasm/MarkLive.cpp
@@ -126,6 +126,20 @@ void MarkLive::run() {
enqueueRetainedSegments(obj);
}
+ // `__wasm_{get,set}_tls_base` are called from synthetic init functions (e.g.
+ // `__wasm_init_tls`, `__wasm_init_memory`) via raw `call` instructions that
+ // carry no relocations, so the mark phase below cannot discover the functions
+ // they in turn call (e.g. the cooperative-threading
+ // `context.get`/`context.set` builtins). They are already marked live, but
+ // their defining chunks were never enqueued; enqueue them here so their
+ // relocations are followed. This mirrors the handling of ctor functions
+ // reached via `__wasm_call_ctors`.
+ for (Symbol *sym : {static_cast<Symbol *>(ctx.sym.getTLSBase),
+ static_cast<Symbol *>(ctx.sym.setTLSBase)})
+ if (sym)
+ if (InputChunk *c = sym->getChunk())
+ enqueue(c);
+
mark();
// If we have any non-discarded init functions, mark `__wasm_call_ctors` as

2
src/llvm-project

@ -1 +1 @@
Subproject commit 1b7c3e57bbc8e367ff8203e8818b018337319d7e
Subproject commit 278c31bfb8ceb7ea17dbfd11a4fb21e6634af957

872
src/llvm-prs-208263-208332-208597.patch
Unescape View File

@ -0,0 +1,872 @@
diff --git a/lld/test/wasm/compress-relocs.s b/lld/test/wasm/compress-relocs.s
index 37f1b3b170ff..e872b941416a 100644
--- a/lld/test/wasm/compress-relocs.s
+++ b/lld/test/wasm/compress-relocs.s
@@ -47,16 +47,16 @@ test_memory_and_indirect_call_relocs:
end_function
# CHECK: test_memory_and_indirect_call_relocs
-# CHECK: 41 90 80 84 80 00 i32.const 65552
+# CHECK: 41 80 80 84 80 00 i32.const 65536
# CHECK: 11 80 80 80 80 00 80 80 80 80 00 call_indirect 0
-# CHECK: 28 02 94 80 84 80 00 i32.load 65556
+# CHECK: 28 02 84 80 84 80 00 i32.load 65540
# CHECK: 11 81 80 80 80 00 80 80 80 80 00 call_indirect 1
# CHECK: 41 81 80 80 80 00 i32.const 1
# CHECK: 11 80 80 80 80 00 80 80 80 80 00 call_indirect 0
# COMPRESS: test_memory_and_indirect_call_relocs
-# COMPRESS: 41 90 80 04 i32.const 65552
+# COMPRESS: 41 80 80 04 i32.const 65536
# COMPRESS: 11 00 00 call_indirect 0
-# COMPRESS: 28 02 94 80 04 i32.load 65556
+# COMPRESS: 28 02 84 80 04 i32.load 65540
# COMPRESS: 11 01 00 call_indirect 1
# COMPRESS: 41 01 i32.const 1
# COMPRESS: 11 00 00 call_indirect 0
@@ -91,11 +91,11 @@ test_relative_relocs:
end_function
# CHECK: test_relative_relocs
-# CHECK: 41 90 80 84 80 00 i32.const 65552
+# CHECK: 41 80 80 84 80 00 i32.const 65536
# CHECK: 41 81 80 80 80 00 i32.const 1
# CHECK: 41 83 80 80 80 00 i32.const 3
# COMPRESS: test_relative_relocs
-# COMPRESS: 41 90 80 04 i32.const 65552
+# COMPRESS: 41 80 80 04 i32.const 65536
# COMPRESS: 41 01 i32.const 1
# COMPRESS: 41 03 i32.const 3
diff --git a/lld/test/wasm/compress-relocs64.s b/lld/test/wasm/compress-relocs64.s
index f3ff646cc3b1..2dd18d604df4 100644
--- a/lld/test/wasm/compress-relocs64.s
+++ b/lld/test/wasm/compress-relocs64.s
@@ -36,12 +36,12 @@ test_memory_and_indirect_call_relocs:
end_function
# CHECK: test_memory_and_indirect_call_relocs
-# CHECK: 42 90 80 84 80 80 80 80 80 80 00 i64.const 65552
-# CHECK: 29 03 98 80 84 80 80 80 80 80 80 00 i64.load 65560
+# CHECK: 42 80 80 84 80 80 80 80 80 80 00 i64.const 65536
+# CHECK: 29 03 88 80 84 80 80 80 80 80 80 00 i64.load 65544
# CHECK: 42 81 80 80 80 80 80 80 80 80 00 i64.const 1
# COMPRESS: test_memory_and_indirect_call_relocs
-# COMPRESS: 42 90 80 04 i64.const 65552
-# COMPRESS: 29 03 98 80 04 i64.load 65560
+# COMPRESS: 42 80 80 04 i64.const 65536
+# COMPRESS: 29 03 88 80 04 i64.load 65544
# COMPRESS: 42 01 i64.const 1
.globl test_relative_relocs
@@ -56,11 +56,11 @@ test_relative_relocs:
end_function
# CHECK: test_relative_relocs
-# CHECK: 42 90 80 84 80 80 80 80 80 80 00 i64.const 65552
+# CHECK: 42 80 80 84 80 80 80 80 80 80 00 i64.const 65536
# CHECK: 42 81 80 80 80 80 80 80 80 80 00 i64.const 1
# CHECK: 42 83 80 80 80 80 80 80 80 80 00 i64.const 3
# COMPRESS: test_relative_relocs
-# COMPRESS: 42 90 80 04 i64.const 65552
+# COMPRESS: 42 80 80 04 i64.const 65536
# COMPRESS: 42 01 i64.const 1
# COMPRESS: 42 03 i64.const 3
diff --git a/lld/test/wasm/cooperative-threading.s b/lld/test/wasm/cooperative-threading.s
index 8b0f7eb1c256..0db72053692b 100644
--- a/lld/test/wasm/cooperative-threading.s
+++ b/lld/test/wasm/cooperative-threading.s
@@ -2,7 +2,7 @@
# thread-context globals (__init_stack_pointer, __init_tls_base, etc.) and
# works without --shared-memory and atomics.
-# RUN: llvm-mc -filetype=obj -triple=wasm32-unknown-unknown -o %t.o %s
+# RUN: llvm-mc -mattr=+call-indirect-overlong -filetype=obj -triple=wasm32-unknown-unknown -o %t.o %s
# RUN: wasm-ld --cooperative-threading -no-gc-sections -o %t.wasm %t.o
# RUN: obj2yaml %t.wasm | FileCheck %s
# RUN: llvm-objdump -d --no-print-imm-hex --no-show-raw-insn %t.wasm | FileCheck %s --check-prefix=DIS
@@ -11,12 +11,22 @@
# RUN: not wasm-ld --cooperative-threading --shared-memory %t.o -o %t2.wasm 2>&1 | FileCheck %s --check-prefix=INCOMPAT
# INCOMPAT: --cooperative-threading is incompatible with --shared-memory
+.globl __indirect_function_table
+.tabletype __indirect_function_table, funcref
+
.globl __wasm_get_tls_base
__wasm_get_tls_base:
.functype __wasm_get_tls_base () -> (i32)
i32.const 0
end_function
+.globl do_call_indirect
+do_call_indirect:
+ .functype do_call_indirect () -> ()
+ i32.const 1
+ call_indirect __indirect_function_table, () -> ()
+ end_function
+
.globl _start
_start:
.functype _start () -> (i32)
@@ -57,6 +67,13 @@ foo:
.int32 0
.size foo, 4
+.section .rodata.baz,"",@
+.globl baz
+.p2align 2
+baz:
+ .int32 1
+ .size baz, 4
+
.section .custom_section.target_features,"",@
.int8 2
.int8 43
@@ -66,28 +83,68 @@ foo:
.int8 7
.ascii "atomics"
+# CHECK: - Type: TABLE
+# CHECK-NEXT: Tables:
+# CHECK-NEXT: - Index: 0
+# CHECK-NEXT: ElemType: FUNCREF
+
# Memory must NOT be marked as shared.
# CHECK: - Type: MEMORY
# CHECK-NEXT: Memories:
# CHECK-NEXT: - Minimum: 0x2
# CHECK-NOT: Shared
-# Only TLS needs a passive data segment; .data stays active and .bss gets no
-# segment at all since memory is only instantiated once and starts zeroed.
+# The function table is exported by default.
+# CHECK: - Type: EXPORT
+# CHECK: - Name: __indirect_function_table
+# CHECK-NEXT: Kind: TABLE
+# CHECK-NEXT: Index: 0
+
+# Ensure __init_stack_pointer, __init_tls_base, and __tls_size are all correct.
+# CHECK: - Type: GLOBAL
+# CHECK-NEXT: Globals:
+# CHECK-NEXT: - Index: 0
+# CHECK-NEXT: Type: I32
+# CHECK-NEXT: Mutable: false
+# CHECK-NEXT: InitExpr:
+# CHECK-NEXT: Opcode: I32_CONST
+# CHECK-NEXT: Value: 65536
+# CHECK-NEXT: - Index: 1
+# CHECK-NEXT: Type: I32
+# CHECK-NEXT: Mutable: false
+# CHECK-NEXT: InitExpr:
+# CHECK-NEXT: Opcode: I32_CONST
+# CHECK-NEXT: Value: 65544
+# CHECK-NEXT: - Index: 2
+# CHECK-NEXT: Type: I32
+# CHECK-NEXT: Mutable: false
+# CHECK-NEXT: InitExpr:
+# CHECK-NEXT: Opcode: I32_CONST
+# CHECK-NEXT: Value: 8
+
+# Only TLS needs a passive data segment; .rodata and .data stay active and
+# .bss gets no segment at all since memory is only instantiated once and
+# starts zeroed. The TLS segment is sorted last.
# CHECK: - Type: DATACOUNT
-# CHECK-NEXT: Count: 2
+# CHECK-NEXT: Count: 3
# CHECK: - Type: DATA{{$}}
# CHECK-NEXT: Segments:
-# CHECK-NEXT: - SectionOffset: 3
-# CHECK-NEXT: InitFlags: 1
-# CHECK-NEXT: Content: '0100000002000000'
-# CHECK-NEXT: - SectionOffset: 18
+# CHECK-NEXT: - SectionOffset: 8
# CHECK-NEXT: InitFlags: 0
# CHECK-NEXT: Offset:
# CHECK-NEXT: Opcode: I32_CONST
-# CHECK-NEXT: Value: {{[0-9]+}}
+# CHECK-NEXT: Value: 65536
+# CHECK-NEXT: Content: '01000000'
+# CHECK-NEXT: - SectionOffset: 19
+# CHECK-NEXT: InitFlags: 0
+# CHECK-NEXT: Offset:
+# CHECK-NEXT: Opcode: I32_CONST
+# CHECK-NEXT: Value: 65540
# CHECK-NEXT: Content: 2A000000
+# CHECK-NEXT: - SectionOffset: 25
+# CHECK-NEXT: InitFlags: 1
+# CHECK-NEXT: Content: '0100000002000000'
# CHECK-NEXT: - Type: CUSTOM
# Globals should use the libcall ABI naming, not the global ABI.
@@ -102,9 +159,14 @@ foo:
# CHECK-NEXT: Name: __tls_align
# DIS-LABEL: <__wasm_init_memory>:
-# DIS: memory.init 0, 0
-# DIS-NOT: memory.fill
-# DIS-NOT: memory.init
+# DIS-EMPTY:
+# DIS-NEXT: i32.const 65544
+# DIS-NEXT: i32.const 65544
+# DIS-NEXT: call 0
+# DIS-NEXT: i32.const 0
+# DIS-NEXT: i32.const 8
+# DIS-NEXT: memory.init 2, 0
+# DIS-NEXT: end
# DIS-LABEL: <_start>:
# DIS-EMPTY:
@@ -118,3 +180,104 @@ foo:
# DIS-NEXT: i32.load 0
# DIS-NEXT: i32.add
# DIS-NEXT: end
+
+# When the table is imported instead there is no need to also export it.
+# RUN: wasm-ld --cooperative-threading --import-table -no-gc-sections -o %t3.wasm %t.o
+# RUN: obj2yaml %t3.wasm | FileCheck %s --check-prefix=IMPORT-TABLE
+
+# When the table is imported instead there is no need to also export it.
+# IMPORT-TABLE: - Type: IMPORT
+# IMPORT-TABLE: - Module: env
+# IMPORT-TABLE-NEXT: Field: __indirect_function_table
+# IMPORT-TABLE-NEXT: Kind: TABLE
+# IMPORT-TABLE-NOT: Kind: TABLE
+
+# Test --cooperative-threading combined with PIC output.
+# RUN: wasm-ld -shared --cooperative-threading -no-gc-sections -o %t.so %t.o
+# RUN: obj2yaml %t.so | FileCheck %s --check-prefix=PIC
+# RUN: llvm-objdump --disassemble-symbols=__wasm_init_memory --no-show-raw-insn --no-leading-addr %t.so | FileCheck %s --check-prefix=PIC-DIS
+
+# The stack pointer is imported under the libcall ABI name and
+# __wasm_set_tls_base is imported for TLS initialization.
+# PIC: - Type: IMPORT
+# PIC: Field: __init_stack_pointer
+# PIC-NEXT: Kind: GLOBAL
+# PIC-NEXT: GlobalType: I32
+# PIC-NEXT: GlobalMutable: false
+# PIC: Field: __memory_base
+# PIC: Field: __table_base
+# PIC: Field: __wasm_set_tls_base
+# PIC-NEXT: Kind: FUNCTION
+
+# The PIC `__init_tls_base` global (global 3) is mutable and initialized ot
+# 0 since its final value is calculated once `__memory_base` is provided.
+# PIC: - Type: GLOBAL
+# PIC-NEXT: Globals:
+# PIC-NEXT: - Index: 3
+# PIC-NEXT: Type: I32
+# PIC-NEXT: Mutable: true
+# PIC-NEXT: InitExpr:
+# PIC-NEXT: Opcode: I32_CONST
+# PIC-NEXT: Value: 0
+# PIC-NEXT: - Index: 4
+# PIC-NEXT: Type: I32
+# PIC-NEXT: Mutable: false
+# PIC-NEXT: InitExpr:
+# PIC-NEXT: Opcode: I32_CONST
+# PIC-NEXT: Value: 8
+
+# In PIC mode the active .rodata and .data segments are combined into a single
+# active segment at __memory_base; the TLS segment remains passive.
+# PIC: - Type: DATACOUNT
+# PIC-NEXT: Count: 2
+# PIC: - Type: DATA{{$}}
+# PIC-NEXT: Segments:
+# PIC-NEXT: - SectionOffset: 6
+# PIC-NEXT: InitFlags: 0
+# PIC-NEXT: Offset:
+# PIC-NEXT: Opcode: GLOBAL_GET
+# PIC-NEXT: Index: {{[0-9]+}}
+# PIC-NEXT: Content: 010000002A000000
+# PIC-NEXT: - SectionOffset: {{[0-9]+}}
+# PIC-NEXT: InitFlags: 1
+# PIC-NEXT: Content: '0100000002000000'
+# PIC-NEXT: - Type: CUSTOM
+
+# PIC: GlobalNames:
+# PIC-NEXT: - Index: 0
+# PIC-NEXT: Name: __init_stack_pointer
+# PIC-NEXT: - Index: 1
+# PIC-NEXT: Name: __memory_base
+# PIC-NEXT: - Index: 2
+# PIC-NEXT: Name: __table_base
+# PIC-NEXT: - Index: 3
+# PIC-NEXT: Name: __init_tls_base
+# PIC-NEXT: - Index: 4
+# PIC-NEXT: Name: __tls_size
+# PIC-NEXT: - Index: 5
+# PIC-NEXT: Name: __tls_align
+
+# Memory initialization in PIC mode has a few responsibilities: it calculates
+# the TLS address and puts it in a local, stores it into the __init_tls_base
+# global, `__wasm_set_tls_base` is called, TLS is initialized, and then finally
+# BSS is zero'd out.
+# PIC-DIS: <__wasm_init_memory>:
+# PIC-DIS-NEXT: .local i32
+# PIC-DIS-NEXT: i32.const 8
+# PIC-DIS-NEXT: global.get 1
+# PIC-DIS-NEXT: i32.add
+# PIC-DIS-NEXT: local.tee 0
+# PIC-DIS-NEXT: global.set 3
+# PIC-DIS-NEXT: local.get 0
+# PIC-DIS-NEXT: call {{[0-9]+}}
+# PIC-DIS-NEXT: local.get 0
+# PIC-DIS-NEXT: i32.const 0
+# PIC-DIS-NEXT: i32.const 8
+# PIC-DIS-NEXT: memory.init 1, 0
+# PIC-DIS-NEXT: i32.const 16
+# PIC-DIS-NEXT: global.get {{[0-9]+}}
+# PIC-DIS-NEXT: i32.add
+# PIC-DIS-NEXT: i32.const 0
+# PIC-DIS-NEXT: i32.const 4
+# PIC-DIS-NEXT: memory.fill 0
+# PIC-DIS-NEXT: end
diff --git a/lld/test/wasm/data-segments.ll b/lld/test/wasm/data-segments.ll
index 7a18fd5efb65..5073e9c4cc8d 100644
--- a/lld/test/wasm/data-segments.ll
+++ b/lld/test/wasm/data-segments.ll
@@ -93,7 +93,7 @@
; ACTIVE-PIC-NEXT: Offset:
; ACTIVE-PIC-NEXT: Opcode: GLOBAL_GET
; ACTIVE-PIC-NEXT: Index: 1
-; ACTIVE-PIC-NEXT: Content: 63000000636F6E7374616E74000000002B00000068656C6C6F00676F6F646279650000002A000000
+; ACTIVE-PIC-NEXT: Content: 636F6E7374616E74000000002B00000068656C6C6F00676F6F646279650000002A00000063000000
; PASSIVE-LABEL: - Type: START
; PASSIVE-NEXT: StartFunction: 2
@@ -114,13 +114,13 @@
; PASSIVE-NEXT: Segments:
; PASSIVE-NEXT: - SectionOffset: 3
; PASSIVE-NEXT: InitFlags: 1
-; PASSIVE-NEXT: Content: '63000000'
-; PASSIVE-NEXT: - SectionOffset: 9
-; PASSIVE-NEXT: InitFlags: 1
; PASSIVE-NEXT: Content: 636F6E7374616E74000000002B
-; PASSIVE-NEXT: - SectionOffset: 24
+; PASSIVE-NEXT: - SectionOffset: 18
; PASSIVE-NEXT: InitFlags: 1
; PASSIVE-NEXT: Content: 68656C6C6F00676F6F646279650000002A000000
+; PASSIVE-NEXT: - SectionOffset: 40
+; PASSIVE-NEXT: InitFlags: 1
+; PASSIVE-NEXT: Content: '63000000'
; PASSIVE-NEXT: - Type: CUSTOM
; PASSIVE-NEXT: Name: name
; PASSIVE-NEXT: FunctionNames:
@@ -153,13 +153,13 @@
; PASSIVE-PIC-NEXT: Segments:
; PASSIVE-PIC-NEXT: - SectionOffset: 3
; PASSIVE-PIC-NEXT: InitFlags: 1
-; PASSIVE-PIC-NEXT: Content: '63000000'
-; PASSIVE-PIC-NEXT: - SectionOffset: 9
-; PASSIVE-PIC-NEXT: InitFlags: 1
; PASSIVE-PIC-NEXT: Content: 636F6E7374616E74000000002B
-; PASSIVE-PIC-NEXT: - SectionOffset: 24
+; PASSIVE-PIC-NEXT: - SectionOffset: 18
; PASSIVE-PIC-NEXT: InitFlags: 1
; PASSIVE-PIC-NEXT: Content: 68656C6C6F00676F6F646279650000002A000000
+; PASSIVE-PIC-NEXT: - SectionOffset: 40
+; PASSIVE-PIC-NEXT: InitFlags: 1
+; PASSIVE-PIC-NEXT: Content: '63000000'
; PASSIVE-PIC-NEXT: - Type: CUSTOM
; PASSIVE-PIC-NEXT: Name: name
; PASSIVE-PIC-NEXT: FunctionNames:
@@ -212,34 +212,34 @@
; DIS-NEXT: end
; NOPIC-DIS-NEXT: [[PTR]].const 65536
-; NOPIC-DIS-NEXT: [[PTR]].const 65536
-; NOPIC-DIS-NEXT: global.set 1
; PIC-DIS-NEXT: [[PTR]].const 0
; PIC-DIS-NEXT: global.get 1
; PIC-DIS-NEXT: [[PTR]].add
-; PIC-DIS-NEXT: local.tee 1
-; PIC-DIS-NEXT: global.set {{\d*}}
-; PIC-DIS-NEXT: local.get 1
+
; DIS-NEXT: i32.const 0
-; DIS-NEXT: i32.const 4
-; DIS-NEXT: memory.init 0, 0
+; DIS-NEXT: i32.const 13
+; DIS-NEXT: memory.init 0, 0
-; NOPIC-DIS-NEXT: [[PTR]].const 65540
-; PIC-DIS-NEXT: [[PTR]].const 4
+; NOPIC-DIS-NEXT: [[PTR]].const 65552
+; PIC-DIS-NEXT: [[PTR]].const 16
; PIC-DIS-NEXT: global.get 1
; PIC-DIS-NEXT: [[PTR]].add
; DIS-NEXT: i32.const 0
-; DIS-NEXT: i32.const 13
+; DIS-NEXT: i32.const 20
; DIS-NEXT: memory.init 1, 0
-; NOPIC-DIS-NEXT: [[PTR]].const 65556
-; PIC-DIS-NEXT: [[PTR]].const 20
+; NOPIC-DIS-NEXT: [[PTR]].const 65572
+; NOPIC-DIS-NEXT: [[PTR]].const 65572
+; NOPIC-DIS-NEXT: global.set 1
+; PIC-DIS-NEXT: [[PTR]].const 36
; PIC-DIS-NEXT: global.get 1
; PIC-DIS-NEXT: [[PTR]].add
-
+; PIC-DIS-NEXT: local.tee 1
+; PIC-DIS-NEXT: global.set {{\d*}}
+; PIC-DIS-NEXT: local.get 1
; DIS-NEXT: i32.const 0
-; DIS-NEXT: i32.const 20
+; DIS-NEXT: i32.const 4
; DIS-NEXT: memory.init 2, 0
; NOPIC-DIS-NEXT: [[PTR]].const 65576
; PIC-DIS-NEXT: [[PTR]].const 40
@@ -272,6 +272,6 @@
; DIS-NEXT: memory.atomic.wait32 0
; DIS-NEXT: drop
; DIS-NEXT: end
+; DIS-NEXT: data.drop 0
; DIS-NEXT: data.drop 1
-; DIS-NEXT: data.drop 2
; DIS-NEXT: end
diff --git a/lld/test/wasm/runtime-relocations-himem.s b/lld/test/wasm/runtime-relocations-himem.s
index 2d39a204c790..2026e62a5af8 100644
--- a/lld/test/wasm/runtime-relocations-himem.s
+++ b/lld/test/wasm/runtime-relocations-himem.s
@@ -47,14 +47,14 @@ data_sym:
# CHECK: <__wasm_apply_data_relocs>:
# CHECK-EMPTY:
-# CHECK-NEXT: i32.const -2147483636
+# CHECK-NEXT: i32.const -2147483644
# CHECK-NEXT: global.get 0
# CHECK-NEXT: i32.store 0
# CHECK-NEXT: end
# CHECK: <__wasm_apply_tls_relocs>:
# CHECK-EMPTY:
-# CHECK-NEXT: i32.const -2147483644
+# CHECK-NEXT: i32.const -2147483636
# CHECK-NEXT: global.get 0
# CHECK-NEXT: i32.store 0
# CHECK-NEXT: end
diff --git a/lld/test/wasm/tls-non-shared-memory.s b/lld/test/wasm/tls-non-shared-memory.s
index 0a87ade7efb2..21082a5603e7 100644
--- a/lld/test/wasm/tls-non-shared-memory.s
+++ b/lld/test/wasm/tls-non-shared-memory.s
@@ -70,14 +70,14 @@ tls1:
# CHECK-NEXT: Mutable: false
# CHECK-NEXT: InitExpr:
# CHECK-NEXT: Opcode: I32_CONST
-# CHECK-NEXT: Value: 65536
+# CHECK-NEXT: Value: 65540
# GOT.data.internal.tls1
# CHECK-NEXT: - Index: 2
# CHECK-NEXT: Type: I32
# CHECK-NEXT: Mutable: false
# CHECK-NEXT: InitExpr:
# CHECK-NEXT: Opcode: I32_CONST
-# CHECK-NEXT: Value: 65536
+# CHECK-NEXT: Value: 65540
# CHECK-NEXT: - Type: EXPORT
# CHECK: - Type: DATA
@@ -88,14 +88,14 @@ tls1:
# CHECK-NEXT: Offset:
# CHECK-NEXT: Opcode: I32_CONST
# CHECK-NEXT: Value: 65536
-# CHECK-NEXT: Content: 2B000000
+# CHECK-NEXT: Content: 2A000000
# .tdata
# CHECK-NEXT: - SectionOffset: 19
# CHECK-NEXT: InitFlags: 0
# CHECK-NEXT: Offset:
# CHECK-NEXT: Opcode: I32_CONST
# CHECK-NEXT: Value: 65540
-# CHECK-NEXT: Content: 2A000000
+# CHECK-NEXT: Content: 2B000000
# CHECK-NEXT: - Type: CUSTOM
# The constant value here which we add to `__tls_base` should not be absolute
@@ -146,7 +146,7 @@ tls1:
# PIC-NEXT: Offset:
# PIC-NEXT: Opcode: GLOBAL_GET
# PIC-NEXT: Index: {{\d*}}
-# PIC-NEXT: Content: 2B0000002A000000
+# PIC-NEXT: Content: 2A0000002B000000
# PIC-NEXT: - Type: CUSTOM
# Unless we have extended-const, in which case the merging is not needed.
@@ -160,7 +160,7 @@ tls1:
# EXT-CONST-NEXT: Offset:
# EXT-CONST-NEXT: Opcode: GLOBAL_GET
# EXT-CONST-NEXT: Index: 1
-# EXT-CONST-NEXT: Content: 2B000000
+# EXT-CONST-NEXT: Content: 2A000000
# EXT-CONST-NEXT: - SectionOffset: 18
# EXT-CONST-NEXT: InitFlags: 0
# EXT-CONST-NEXT: Offset:
@@ -168,4 +168,4 @@ tls1:
# This instruction sequence decodes to:
# (global.get[0x23] 0x1 i32.const[0x41] 0x04 i32.add[0x6A] end[0x0b])
# EXT-CONST-NEXT: Body: 230141046A0B
-# EXT-CONST-NEXT: Content: 2A000000
+# EXT-CONST-NEXT: Content: 2B000000
diff --git a/lld/test/wasm/tls-relocations.s b/lld/test/wasm/tls-relocations.s
index 9679074d6a0d..b5d130417774 100644
--- a/lld/test/wasm/tls-relocations.s
+++ b/lld/test/wasm/tls-relocations.s
@@ -64,7 +64,7 @@ tls_sym:
# ASM-NEXT: local.get 0
# ASM-NEXT: i32.const 0
# ASM-NEXT: i32.const 16
-# ASM-NEXT: memory.init 0, 0
+# ASM-NEXT: memory.init 1, 0
# call to __wasm_apply_tls_relocs
# ASM-NEXT: call 3
# ASM-NEXT: end
@@ -75,7 +75,7 @@ tls_sym:
# ASM-NEXT: global.get 3
# ASM-NEXT: i32.add
# ASM-NEXT: global.get 1
-# ASM-NEXT: i32.const 20
+# ASM-NEXT: i32.const 4
# ASM-NEXT: i32.add
# ASM-NEXT: i32.store 0
# ASM-NEXT: i32.const 12
diff --git a/lld/wasm/Driver.cpp b/lld/wasm/Driver.cpp
index 9a2e3a82a927..35892c283897 100644
--- a/lld/wasm/Driver.cpp
+++ b/lld/wasm/Driver.cpp
@@ -759,6 +759,14 @@ static void setConfigs() {
if (ctx.arg.sharedMemory)
error("--cooperative-threading is incompatible with --shared-memory");
ctx.arg.libcallThreadContext = true;
+
+ // Cooperative threading requires the table is either imported or exported
+ // or otherwise there's no way for embedders to read spawned functions from
+ // the table. If we've gotten this far and the table isn't otherwise
+ // imported (e.g in `isPic` mode) then export the table instead to ensure
+ // that it's visible to the outside world.
+ if (!ctx.arg.importTable)
+ ctx.arg.exportTable = true;
}
}
@@ -970,12 +978,20 @@ static void createSyntheticSymbols() {
}
if (ctx.arg.isMultithreaded()) {
- // TLS symbols are all hidden/dso-local
+ // TLS symbols are all hidden/dso-local, and note that the `tlsBase` global
+ // serves a different purpose depending on `libcallThreadContext`. If
+ // `libcallThreadContext` is `false` it's the base address of TLS and it's
+ // initialized fresh by each thread. This requires a mutable global.
+ //
+ // If `libcallThreadContext` is `true`, however, then it records the
+ // initial thread's TLS address at `start`-time. In non-PIC mode this is a
+ // constant determined during linking, but in PIC mode it's calculated
+ // during instantiation.
auto tls_base_name =
ctx.arg.libcallThreadContext ? "__init_tls_base" : "__tls_base";
- ctx.sym.tlsBase =
- createGlobalVariable(tls_base_name, !ctx.arg.libcallThreadContext,
- WASM_SYMBOL_VISIBILITY_HIDDEN);
+ ctx.sym.tlsBase = createGlobalVariable(
+ tls_base_name, !ctx.arg.libcallThreadContext || ctx.isPic,
+ WASM_SYMBOL_VISIBILITY_HIDDEN);
ctx.sym.tlsSize = createGlobalVariable("__tls_size", false,
WASM_SYMBOL_VISIBILITY_HIDDEN);
ctx.sym.tlsAlign = createGlobalVariable("__tls_align", false,
diff --git a/lld/wasm/InputChunks.cpp b/lld/wasm/InputChunks.cpp
index 99623e7c9aef..79cfb7878d07 100644
--- a/lld/wasm/InputChunks.cpp
+++ b/lld/wasm/InputChunks.cpp
@@ -406,6 +406,13 @@ uint64_t InputChunk::getOffset(uint64_t offset) const {
}
uint64_t InputChunk::getVA(uint64_t offset) const {
+ // In multithreaded PIC builds TLS chunks are never assigned an absolute
+ // virtual address; at runtime they live at an offset from `__tls_base`, so
+ // their VA is that relative offset. In single-threaded builds TLS is instead
+ // lowered to normal data with a fixed base and so is assigned addresses as
+ // usual.
+ if (ctx.isPic && ctx.arg.isMultithreaded() && isTLS())
+ return getChunkOffset(offset);
return (outputSeg ? outputSeg->startVA : 0) + getChunkOffset(offset);
}
diff --git a/lld/wasm/OutputSections.cpp b/lld/wasm/OutputSections.cpp
index 22c001eaa43b..d9017fefffdd 100644
--- a/lld/wasm/OutputSections.cpp
+++ b/lld/wasm/OutputSections.cpp
@@ -104,13 +104,11 @@ void DataSection::finalizeContents() {
});
#ifndef NDEBUG
unsigned activeCount = llvm::count_if(segments, [](OutputSegment *segment) {
- return segment->requiredInBinary() &&
- (segment->initFlags & WASM_DATA_SEGMENT_IS_PASSIVE) == 0;
+ return segment->requiredInBinary() && segment->isActive();
});
#endif
- assert((ctx.arg.sharedMemory || !ctx.isPic || ctx.arg.extendedConst ||
- activeCount <= 1) &&
+ assert((!ctx.isPic || ctx.arg.extendedConst || activeCount <= 1) &&
"output segments should have been combined by now");
writeUleb128(os, segmentCount, "data segment count");
@@ -124,7 +122,7 @@ void DataSection::finalizeContents() {
writeUleb128(os, segment->initFlags, "init flags");
if (segment->initFlags & WASM_DATA_SEGMENT_HAS_MEMINDEX)
writeUleb128(os, 0, "memory index");
- if ((segment->initFlags & WASM_DATA_SEGMENT_IS_PASSIVE) == 0) {
+ if (segment->isActive()) {
if (ctx.isPic && ctx.arg.extendedConst) {
writeU8(os, WASM_OPCODE_GLOBAL_GET, "global get");
writeUleb128(os, ctx.sym.memoryBase->getGlobalIndex(),
diff --git a/lld/wasm/OutputSegment.h b/lld/wasm/OutputSegment.h
index 701df1fecc4b..10049aecdada 100644
--- a/lld/wasm/OutputSegment.h
+++ b/lld/wasm/OutputSegment.h
@@ -11,6 +11,7 @@
#include "InputChunks.h"
#include "lld/Common/ErrorHandler.h"
+#include "llvm/BinaryFormat/Wasm.h"
#include "llvm/Object/Wasm.h"
namespace lld::wasm {
@@ -46,6 +47,16 @@ public:
// Segment header
std::string header;
+
+ /// Returns whether this is destined to become a passive data segment in the
+ /// final output.
+ bool isPassive() const {
+ return (initFlags & llvm::wasm::WASM_DATA_SEGMENT_IS_PASSIVE) != 0;
+ }
+
+ /// Returns whether this is destined to become a active data segment in the
+ /// final output.
+ bool isActive() const { return !isPassive(); }
};
} // namespace lld::wasm
diff --git a/lld/wasm/Writer.cpp b/lld/wasm/Writer.cpp
index 7ceff0e14413..06be15029460 100644
--- a/lld/wasm/Writer.cpp
+++ b/lld/wasm/Writer.cpp
@@ -85,7 +85,7 @@ private:
void calculateTypes();
void createOutputSegments();
OutputSegment *createOutputSegment(StringRef name);
- void combineOutputSegments();
+ void combineActiveOutputSegments();
void layoutMemory();
void createHeader();
@@ -1092,16 +1092,20 @@ void Writer::createOutputSegments() {
}
}
- // Sort segments by type, placing .bss last
+ // Sort segments by type, placing .bss last. Note that one requirement of
+ // this sort is that all eventually-active segments must come first in
+ // case `combineActiveOutputSegments` is used. When combined the relative
+ // address of the data segment must be 0 (to be compatible with PIC and a
+ // lack of extended-const).
llvm::stable_sort(segments,
[](const OutputSegment *a, const OutputSegment *b) {
auto order = [](StringRef name) {
return StringSwitch<int>(name)
- .StartsWith(".tdata", 0)
- .StartsWith(".rodata", 1)
- .StartsWith(".data", 2)
+ .StartsWith(".rodata", 0)
+ .StartsWith(".data", 1)
+ .StartsWith(".tdata", 3)
.StartsWith(".bss", 4)
- .Default(3);
+ .Default(2);
};
return order(a->name) < order(b->name);
});
@@ -1115,24 +1119,28 @@ void Writer::createOutputSegments() {
seg->finalizeInputSegments();
}
-void Writer::combineOutputSegments() {
+void Writer::combineActiveOutputSegments() {
// With PIC code we currently only support a single active data segment since
// we only have a single __memory_base to use as our base address. This pass
- // combines all data segments into a single .data segment.
+ // combines all active data segments into a single .data segment.
// This restriction does not apply when the extended const extension is
// available: https://github.com/WebAssembly/extended-const
assert(!ctx.arg.extendedConst);
- assert(ctx.isPic && !ctx.arg.isMultithreaded());
- if (segments.size() <= 1)
+ assert(ctx.isPic);
+ auto isActive = [](const OutputSegment *s) {
+ return s->requiredInBinary() && s->isActive();
+ };
+ if (llvm::count_if(segments, isActive) <= 1)
return;
OutputSegment *combined = make<OutputSegment>(".data");
- combined->startVA = segments[0]->startVA;
std::vector<OutputSegment *> newSegments = {combined};
for (OutputSegment *s : segments) {
- if (!s->requiredInBinary()) {
+ if (!isActive(s)) {
newSegments.push_back(s);
continue;
}
+ if (combined->inputSegments.empty())
+ combined->startVA = s->startVA;
bool first = true;
for (InputChunk *inSeg : s->inputSegments) {
if (first)
@@ -1152,6 +1160,10 @@ void Writer::combineOutputSegments() {
}
segments = std::move(newSegments);
+
+ // Fixup indices for any segments that have moved around.
+ for (size_t i = 0; i < segments.size(); ++i)
+ segments[i]->index = i;
}
static void createFunction(DefinedFunction *func, StringRef bodyContent) {
@@ -1170,7 +1182,7 @@ bool Writer::needsPassiveInitialization(const OutputSegment *segment) {
// (via memory.fill) during `__wasm_init_memory`.
if (ctx.arg.memoryImport.has_value() && !segment->requiredInBinary())
return true;
- return segment->initFlags & WASM_DATA_SEGMENT_IS_PASSIVE;
+ return segment->isPassive();
}
bool Writer::hasPassiveInitializedSegments() {
@@ -1315,29 +1327,48 @@ void Writer::createInitMemoryFunction() {
// (i32.const $__init_memory_flag)
// (i32.const 1)
+ // First figure out what locals need to be emitted for this function. Locals
+ // aren't always needed, though. Map them out here where they're allocated
+ // based on the same conditions that they're used in various situations
+ // below. For now all locals have the same type which makes the declaration
+ // side a bit simpler, and this'll have to get fancier if multiple types of
+ // locals are ever needed in the future.
+ unsigned numAddressLocals = 0;
+ unsigned tlsAddressLocal = -1;
+ unsigned flagAddressLocal = -1;
+ if (ctx.isPic && ctx.arg.sharedMemory)
+ flagAddressLocal = numAddressLocals++;
+ bool needsTLSAddressLocal =
+ ctx.isPic && ctx.arg.isMultithreaded() &&
+ llvm::any_of(segments, [this](const OutputSegment *s) {
+ return s->isTLS() && needsPassiveInitialization(s);
+ });
+ if (needsTLSAddressLocal)
+ tlsAddressLocal = numAddressLocals++;
+ writeUleb128(os, numAddressLocals ? 1 : 0, "num local groups");
+ if (numAddressLocals > 0) {
+ writeUleb128(os, numAddressLocals, "num address locals");
+ writeU8(os, is64 ? WASM_TYPE_I64 : WASM_TYPE_I32, "address type");
+ }
+
auto writeGetFlagAddress = [&]() {
if (ctx.isPic) {
writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
- writeUleb128(os, 0, "local 0");
+ writeUleb128(os, flagAddressLocal, "flag address local index");
} else {
writePtrConst(os, flagAddress, is64, "flag address");
}
};
if (ctx.arg.sharedMemory) {
- // With PIC code we cache the flag address in local 0
+ // With PIC code we cache the flag address in a local.
if (ctx.isPic) {
- writeUleb128(os, 1, "num local decls");
- writeUleb128(os, 2, "local count");
- writeU8(os, is64 ? WASM_TYPE_I64 : WASM_TYPE_I32, "address type");
writeU8(os, WASM_OPCODE_GLOBAL_GET, "GLOBAL_GET");
writeUleb128(os, ctx.sym.memoryBase->getGlobalIndex(), "memory_base");
writePtrConst(os, flagAddress, is64, "flag address");
writeU8(os, is64 ? WASM_OPCODE_I64_ADD : WASM_OPCODE_I32_ADD, "add");
writeU8(os, WASM_OPCODE_LOCAL_SET, "local.set");
- writeUleb128(os, 0, "local 0");
- } else {
- writeUleb128(os, 0, "num locals");
+ writeUleb128(os, flagAddressLocal, "flag address local index");
}
// Set up destination blocks
@@ -1365,8 +1396,6 @@ void Writer::createInitMemoryFunction() {
// Initialize passive data segments
writeU8(os, WASM_OPCODE_END, "end $init");
- } else {
- writeUleb128(os, 0, "num local decls");
}
for (const OutputSegment *s : segments) {
@@ -1387,18 +1416,37 @@ void Writer::createInitMemoryFunction() {
// When we initialize the TLS segment we also set the TLS base.
// This allows the runtime to use this static copy of the TLS data
// for the first/main thread.
+ //
+ // Note that for `--cooperative-threading` this additionally configures
+ // the `__init_tls_base` global which is the initial TLS value that can
+ // be used for all new component model tasks. For non-PIC builds this
+ // global's statically known value is now calculated, so it's updated
+ // here. For PIC builds the result of the address computation above is
+ // what's stored into the global.
+ //
+ // Finally, note that a temporary local is used here to ensure that the
+ // result of the addition above can be reused a number of times.
if (ctx.arg.isMultithreaded() && s->isTLS()) {
if (ctx.isPic) {
- // Cache the result of the addionion in local 0
+ // Cache the result of the addition in the TLS address local
writeU8(os, WASM_OPCODE_LOCAL_TEE, "local.tee");
- writeUleb128(os, 1, "local 1");
+ writeUleb128(os, tlsAddressLocal, "tls address local");
+ if (ctx.arg.libcallThreadContext) {
+ writeU8(os, WASM_OPCODE_GLOBAL_SET, "GLOBAL_SET");
+ writeUleb128(os, ctx.sym.tlsBase->getGlobalIndex(),
+ "__init_tls_base");
+ writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
+ writeUleb128(os, tlsAddressLocal, "tls address local");
+ }
} else {
writePtrConst(os, s->startVA, is64, "destination address");
+ if (ctx.arg.libcallThreadContext)
+ ctx.sym.tlsBase->global->setPointerValue(s->startVA);
}
writeSetTLSBase(ctx, os);
if (ctx.isPic) {
- writeU8(os, WASM_OPCODE_LOCAL_GET, "local.tee");
- writeUleb128(os, 1, "local 1");
+ writeU8(os, WASM_OPCODE_LOCAL_GET, "local.get");
+ writeUleb128(os, tlsAddressLocal, "tls address local");
}
}
@@ -1799,11 +1847,9 @@ void Writer::run() {
// `__memory_base` import. Unless we support the extended const expression we
// can't do addition inside the constant expression, so we much combine the
// segments into a single one that can live at `__memory_base`.
- if (ctx.isPic && !ctx.arg.extendedConst && !ctx.arg.isMultithreaded()) {
- // In multithreaded modes (shared or cooperative), data segments may be
- // passive and must not be combined into a single active segment.
- log("-- combineOutputSegments");
- combineOutputSegments();
+ if (ctx.isPic && !ctx.arg.extendedConst) {
+ log("-- combineActiveOutputSegments");
+ combineActiveOutputSegments();
}
log("-- createSyntheticSectionsPostLayout");

2
src/wasi-libc

@ -1 +1 @@
Subproject commit e2507dd1d4a4fa2d1163efadede8c75cb2d5ed07
Subproject commit fb2edcef33395cd18f5921041f9c40d6127adc68
Write Preview
Loading…
Cancel
Save