Auto merge of #34832 - vadimcn:rusty-personality, r=alexcrichton

Implement rust_eh_personality in Rust, remove rust_eh_personality_catch.

Well, not quite: ARM EHABI platforms still use the old scheme -- for now.

r? @alexcrichton

Author: bors

src/libpanic_unwind/dwarf/eh.rs

@@ -45,16 +45,25 @@ pub const DW_EH_PE_aligned: u8 = 0x50;
 pub const DW_EH_PE_indirect: u8 = 0x80;
 
 #[derive(Copy, Clone)]
-pub struct EHContext {
+pub struct EHContext<'a> {
     pub ip: usize, // Current instruction pointer
     pub func_start: usize, // Address of the current function
-    pub text_start: usize, // Address of the code section
-    pub data_start: usize, // Address of the data section
+    pub get_text_start: &'a Fn() -> usize, // Get address of the code section
+    pub get_data_start: &'a Fn() -> usize, // Get address of the data section
 }
 
-pub unsafe fn find_landing_pad(lsda: *const u8, context: &EHContext) -> Option<usize> {
+pub enum EHAction {
+    None,
+    Cleanup(usize),
+    Catch(usize),
+    Terminate,
+}
+
+pub const USING_SJLJ_EXCEPTIONS: bool = cfg!(all(target_os = "ios", target_arch = "arm"));
+
+pub unsafe fn find_eh_action(lsda: *const u8, context: &EHContext) -> EHAction {
     if lsda.is_null() {
-        return None;
+        return EHAction::None;
     }
 
     let func_start = context.func_start;
@@ -77,32 +86,62 @@ pub unsafe fn find_landing_pad(lsda: *const u8, context: &EHContext) -> Option<u
     let call_site_encoding = reader.read::<u8>();
     let call_site_table_length = reader.read_uleb128();
     let action_table = reader.ptr.offset(call_site_table_length as isize);
-    // Return addresses point 1 byte past the call instruction, which could
-    // be in the next IP range.
-    let ip = context.ip - 1;
-
-    while reader.ptr < action_table {
-        let cs_start = read_encoded_pointer(&mut reader, context, call_site_encoding);
-        let cs_len = read_encoded_pointer(&mut reader, context, call_site_encoding);
-        let cs_lpad = read_encoded_pointer(&mut reader, context, call_site_encoding);
-        let cs_action = reader.read_uleb128();
-        // Callsite table is sorted by cs_start, so if we've passed the ip, we
-        // may stop searching.
-        if ip < func_start + cs_start {
-            break;
+    let ip = context.ip;
+
+    if !USING_SJLJ_EXCEPTIONS {
+        while reader.ptr < action_table {
+            let cs_start = read_encoded_pointer(&mut reader, context, call_site_encoding);
+            let cs_len = read_encoded_pointer(&mut reader, context, call_site_encoding);
+            let cs_lpad = read_encoded_pointer(&mut reader, context, call_site_encoding);
+            let cs_action = reader.read_uleb128();
+            // Callsite table is sorted by cs_start, so if we've passed the ip, we
+            // may stop searching.
+            if ip < func_start + cs_start {
+                break;
+            }
+            if ip < func_start + cs_start + cs_len {
+                if cs_lpad == 0 {
+                    return EHAction::None;
+                } else {
+                    let lpad = lpad_base + cs_lpad;
+                    return interpret_cs_action(cs_action, lpad);
+                }
+            }
         }
-        if ip < func_start + cs_start + cs_len {
-            if cs_lpad != 0 {
-                return Some(lpad_base + cs_lpad);
-            } else {
-                return None;
+        // If ip is not present in the table, call terminate.  This is for
+        // a destructor inside a cleanup, or a library routine the compiler
+        // was not expecting to throw
+        EHAction::Terminate
+    } else {
+        // SjLj version:
+        // The "IP" is an index into the call-site table, with two exceptions:
+        // -1 means 'no-action', and 0 means 'terminate'.
+        match ip as isize {
+           -1 => return EHAction::None,
+            0 => return EHAction::Terminate,
+            _ => (),
+        }
+        let mut idx = ip;
+        loop {
+            let cs_lpad = reader.read_uleb128();
+            let cs_action = reader.read_uleb128();
+            idx -= 1;
+            if idx == 0 {
+                // Can never have null landing pad for sjlj -- that would have
+                // been indicated by a -1 call site index.
+                let lpad = (cs_lpad + 1) as usize;
+                return interpret_cs_action(cs_action, lpad);
             }
         }
     }
-    // IP range not found: gcc's C++ personality calls terminate() here,
-    // however the rest of the languages treat this the same as cs_lpad == 0.
-    // We follow this suit.
-    None
+}
+
+fn interpret_cs_action(cs_action: u64, lpad: usize) -> EHAction {
+    if cs_action == 0 {
+        EHAction::Cleanup(lpad)
+    } else {
+        EHAction::Catch(lpad)
+    }
 }
 
 #[inline]
@@ -140,18 +179,16 @@ unsafe fn read_encoded_pointer(reader: &mut DwarfReader,
         DW_EH_PE_absptr => 0,
         // relative to address of the encoded value, despite the name
         DW_EH_PE_pcrel => reader.ptr as usize,
-        DW_EH_PE_textrel => {
-            assert!(context.text_start != 0);
-            context.text_start
-        }
-        DW_EH_PE_datarel => {
-            assert!(context.data_start != 0);
-            context.data_start
-        }
         DW_EH_PE_funcrel => {
             assert!(context.func_start != 0);
             context.func_start
         }
+        DW_EH_PE_textrel => {
+            (*context.get_text_start)()
+        }
+        DW_EH_PE_datarel => {
+            (*context.get_data_start)()
+        }
         _ => panic!(),
     };
 

src/libpanic_unwind/gcc.rs

@@ -106,117 +106,96 @@ fn rust_exception_class() -> uw::_Unwind_Exception_Class {
     0x4d4f5a_00_52555354
 }
 
-// We could implement our personality routine in Rust, however exception
-// info decoding is tedious.  More importantly, personality routines have to
-// handle various platform quirks, which are not fun to maintain.  For this
-// reason, we attempt to reuse personality routine of the C language:
-// __gcc_personality_v0.
-//
-// Since C does not support exception catching, __gcc_personality_v0 simply
-// always returns _URC_CONTINUE_UNWIND in search phase, and always returns
-// _URC_INSTALL_CONTEXT (i.e. "invoke cleanup code") in cleanup phase.
-//
-// This is pretty close to Rust's exception handling approach, except that Rust
-// does have a single "catch-all" handler at the bottom of each thread's stack.
-// So we have two versions of the personality routine:
-// - rust_eh_personality, used by all cleanup landing pads, which never catches,
-//   so the behavior of __gcc_personality_v0 is perfectly adequate there, and
-// - rust_eh_personality_catch, used only by rust_try(), which always catches.
-//
-// See also: rustc_trans::trans::intrinsic::trans_gnu_try
-
-#[cfg(all(not(target_arch = "arm"),
-          not(all(windows, target_arch = "x86_64"))))]
+// All targets, except ARM which uses a slightly different ABI (however, iOS goes here as it uses
+// SjLj unwinding).  Also, 64-bit Windows implementation lives in seh64_gnu.rs
+#[cfg(all(any(target_os = "ios", not(target_arch = "arm"))))]
 pub mod eabi {
     use unwind as uw;
-    use libc::c_int;
+    use libc::{c_int, uintptr_t};
+    use dwarf::eh::{EHContext, EHAction, find_eh_action};
 
-    extern "C" {
-        fn __gcc_personality_v0(version: c_int,
-                                actions: uw::_Unwind_Action,
-                                exception_class: uw::_Unwind_Exception_Class,
-                                ue_header: *mut uw::_Unwind_Exception,
-                                context: *mut uw::_Unwind_Context)
-                                -> uw::_Unwind_Reason_Code;
-    }
+    // Register ids were lifted from LLVM's TargetLowering::getExceptionPointerRegister()
+    // and TargetLowering::getExceptionSelectorRegister() for each architecture,
+    // then mapped to DWARF register numbers via register definition tables
+    // (typically <arch>RegisterInfo.td, search for "DwarfRegNum").
+    // See also http://llvm.org/docs/WritingAnLLVMBackend.html#defining-a-register.
 
-    #[lang = "eh_personality"]
-    #[no_mangle]
-    extern "C" fn rust_eh_personality(version: c_int,
-                                      actions: uw::_Unwind_Action,
-                                      exception_class: uw::_Unwind_Exception_Class,
-                                      ue_header: *mut uw::_Unwind_Exception,
-                                      context: *mut uw::_Unwind_Context)
-                                      -> uw::_Unwind_Reason_Code {
-        unsafe { __gcc_personality_v0(version, actions, exception_class, ue_header, context) }
-    }
+    #[cfg(target_arch = "x86")]
+    const UNWIND_DATA_REG: (i32, i32) = (0, 2); // EAX, EDX
 
-    #[lang = "eh_personality_catch"]
-    #[no_mangle]
-    pub extern "C" fn rust_eh_personality_catch(version: c_int,
-                                                actions: uw::_Unwind_Action,
-                                                exception_class: uw::_Unwind_Exception_Class,
-                                                ue_header: *mut uw::_Unwind_Exception,
-                                                context: *mut uw::_Unwind_Context)
-                                                -> uw::_Unwind_Reason_Code {
+    #[cfg(target_arch = "x86_64")]
+    const UNWIND_DATA_REG: (i32, i32) = (0, 1); // RAX, RDX
 
-        if (actions as c_int & uw::_UA_SEARCH_PHASE as c_int) != 0 {
-            // search phase
-            uw::_URC_HANDLER_FOUND // catch!
-        } else {
-            // cleanup phase
-            unsafe { __gcc_personality_v0(version, actions, exception_class, ue_header, context) }
-        }
-    }
-}
-
-// iOS on armv7 is using SjLj exceptions and therefore requires to use
-// a specialized personality routine: __gcc_personality_sj0
+    #[cfg(any(target_arch = "arm", target_arch = "aarch64"))]
+    const UNWIND_DATA_REG: (i32, i32) = (0, 1); // R0, R1 / X0, X1
 
-#[cfg(all(target_os = "ios", target_arch = "arm"))]
-pub mod eabi {
-    use unwind as uw;
-    use libc::c_int;
+    #[cfg(any(target_arch = "mips", target_arch = "mipsel"))]
+    const UNWIND_DATA_REG: (i32, i32) = (4, 5); // A0, A1
 
-    extern "C" {
-        fn __gcc_personality_sj0(version: c_int,
-                                 actions: uw::_Unwind_Action,
-                                 exception_class: uw::_Unwind_Exception_Class,
-                                 ue_header: *mut uw::_Unwind_Exception,
-                                 context: *mut uw::_Unwind_Context)
-                                 -> uw::_Unwind_Reason_Code;
-    }
+    #[cfg(any(target_arch = "powerpc", target_arch = "powerpc64"))]
+    const UNWIND_DATA_REG: (i32, i32) = (3, 4); // R3, R4 / X3, X4
 
+    // Based on GCC's C and C++ personality routines.  For reference, see:
+    // https://github.com/gcc-mirror/gcc/blob/master/libstdc++-v3/libsupc++/eh_personality.cc
+    // https://github.com/gcc-mirror/gcc/blob/trunk/libgcc/unwind-c.c
     #[lang = "eh_personality"]
     #[no_mangle]
-    pub extern "C" fn rust_eh_personality(version: c_int,
-                                          actions: uw::_Unwind_Action,
-                                          exception_class: uw::_Unwind_Exception_Class,
-                                          ue_header: *mut uw::_Unwind_Exception,
-                                          context: *mut uw::_Unwind_Context)
-                                          -> uw::_Unwind_Reason_Code {
-        unsafe { __gcc_personality_sj0(version, actions, exception_class, ue_header, context) }
+    #[allow(unused)]
+    unsafe extern "C" fn rust_eh_personality(version: c_int,
+                                             actions: uw::_Unwind_Action,
+                                             exception_class: uw::_Unwind_Exception_Class,
+                                             exception_object: *mut uw::_Unwind_Exception,
+                                             context: *mut uw::_Unwind_Context)
+                                             -> uw::_Unwind_Reason_Code {
+        if version != 1 {
+            return uw::_URC_FATAL_PHASE1_ERROR;
+        }
+        let lsda = uw::_Unwind_GetLanguageSpecificData(context) as *const u8;
+        let mut ip_before_instr: c_int = 0;
+        let ip = uw::_Unwind_GetIPInfo(context, &mut ip_before_instr);
+        let eh_context = EHContext {
+            // The return address points 1 byte past the call instruction,
+            // which could be in the next IP range in LSDA range table.
+            ip: if ip_before_instr != 0 { ip } else { ip - 1 },
+            func_start: uw::_Unwind_GetRegionStart(context),
+            get_text_start: &|| uw::_Unwind_GetTextRelBase(context),
+            get_data_start: &|| uw::_Unwind_GetDataRelBase(context),
+        };
+        let eh_action = find_eh_action(lsda, &eh_context);
+
+        if actions as i32 & uw::_UA_SEARCH_PHASE as i32 != 0 {
+            match eh_action {
+                EHAction::None | EHAction::Cleanup(_) => return uw::_URC_CONTINUE_UNWIND,
+                EHAction::Catch(_) => return uw::_URC_HANDLER_FOUND,
+                EHAction::Terminate => return uw::_URC_FATAL_PHASE1_ERROR,
+            }
+        } else {
+            match eh_action {
+                EHAction::None => return uw::_URC_CONTINUE_UNWIND,
+                EHAction::Cleanup(lpad) | EHAction::Catch(lpad) => {
+                    uw::_Unwind_SetGR(context, UNWIND_DATA_REG.0, exception_object as uintptr_t);
+                    uw::_Unwind_SetGR(context, UNWIND_DATA_REG.1, 0);
+                    uw::_Unwind_SetIP(context, lpad);
+                    return uw::_URC_INSTALL_CONTEXT;
+                }
+                EHAction::Terminate => return uw::_URC_FATAL_PHASE2_ERROR,
+            }
+        }
     }
 
+    #[cfg(stage0)]
     #[lang = "eh_personality_catch"]
     #[no_mangle]
-    pub extern "C" fn rust_eh_personality_catch(version: c_int,
-                                                actions: uw::_Unwind_Action,
-                                                exception_class: uw::_Unwind_Exception_Class,
-                                                ue_header: *mut uw::_Unwind_Exception,
-                                                context: *mut uw::_Unwind_Context)
-                                                -> uw::_Unwind_Reason_Code {
-        if (actions as c_int & uw::_UA_SEARCH_PHASE as c_int) != 0 {
-            // search phase
-            uw::_URC_HANDLER_FOUND // catch!
-        } else {
-            // cleanup phase
-            unsafe { __gcc_personality_sj0(version, actions, exception_class, ue_header, context) }
-        }
+    pub unsafe extern "C" fn rust_eh_personality_catch(version: c_int,
+                                                       actions: uw::_Unwind_Action,
+                                                       exception_class: uw::_Unwind_Exception_Class,
+                                                       ue_header: *mut uw::_Unwind_Exception,
+                                                       context: *mut uw::_Unwind_Context)
+                                                       -> uw::_Unwind_Reason_Code {
+        rust_eh_personality(version, actions, exception_class, ue_header, context)
     }
 }
 
-
 // ARM EHABI uses a slightly different personality routine signature,
 // but otherwise works the same.
 #[cfg(all(target_arch = "arm", not(target_os = "ios")))]

src/libpanic_unwind/lib.rs

@@ -101,6 +101,7 @@ pub unsafe extern "C" fn __rust_maybe_catch_panic(f: fn(*mut u8),
 // Entry point for raising an exception, just delegates to the platform-specific
 // implementation.
 #[no_mangle]
+#[unwind]
 pub unsafe extern "C" fn __rust_start_panic(data: usize, vtable: usize) -> u32 {
     imp::panic(mem::transmute(raw::TraitObject {
         data: data as *mut (),

src/libpanic_unwind/seh64_gnu.rs

@@ -19,7 +19,7 @@ use alloc::boxed::Box;
 use core::any::Any;
 use core::intrinsics;
 use core::ptr;
-use dwarf::eh;
+use dwarf::eh::{EHContext, EHAction, find_eh_action};
 use windows as c;
 
 // Define our exception codes:
@@ -81,6 +81,7 @@ pub unsafe fn cleanup(ptr: *mut u8) -> Box<Any + Send> {
 // This is considered acceptable, because the behavior of throwing exceptions
 // through a C ABI boundary is undefined.
 
+#[cfg(stage0)]
 #[lang = "eh_personality_catch"]
 #[cfg(not(test))]
 unsafe extern "C" fn rust_eh_personality_catch(exceptionRecord: *mut c::EXCEPTION_RECORD,
@@ -132,11 +133,17 @@ unsafe extern "C" fn rust_eh_unwind_resume(panic_ctx: c::LPVOID) -> ! {
 }
 
 unsafe fn find_landing_pad(dc: &c::DISPATCHER_CONTEXT) -> Option<usize> {
-    let eh_ctx = eh::EHContext {
-        ip: dc.ControlPc as usize,
+    let eh_ctx = EHContext {
+        // The return address points 1 byte past the call instruction,
+        // which could be in the next IP range in LSDA range table.
+        ip: dc.ControlPc as usize - 1,
         func_start: dc.ImageBase as usize + (*dc.FunctionEntry).BeginAddress as usize,
-        text_start: dc.ImageBase as usize,
-        data_start: 0,
+        get_text_start: &|| dc.ImageBase as usize,
+        get_data_start: &|| unimplemented!(),
     };
-    eh::find_landing_pad(dc.HandlerData, &eh_ctx)
+    match find_eh_action(dc.HandlerData, &eh_ctx) {
+        EHAction::None => None,
+        EHAction::Cleanup(lpad) | EHAction::Catch(lpad) => Some(lpad),
+        EHAction::Terminate => intrinsics::abort(),
+    }
 }