linux-user/i386: Add vdso

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1267
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

8 files changed, 271 insertions, 2 deletions

diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index b0723071e2..46f73a4166 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -305,12 +305,27 @@ static void elf_core_copy_regs(target_elf_gregset_t *regs, const CPUX86State *en
     (*regs)[15] = tswapreg(env->regs[R_ESP]);
     (*regs)[16] = tswapreg(env->segs[R_SS].selector & 0xffff);
 }
-#endif
+
+/*
+ * i386 is the only target which supplies AT_SYSINFO for the vdso.
+ * All others only supply AT_SYSINFO_EHDR.
+ */
+#define DLINFO_ARCH_ITEMS (vdso_info != NULL)
+#define ARCH_DLINFO                                     \
+    do {                                                \
+        if (vdso_info) {                                \
+            NEW_AUX_ENT(AT_SYSINFO, vdso_info->entry);  \
+        }                                               \
+    } while (0)
+
+#define VDSO_HEADER "vdso.c.inc"
+
+#endif /* TARGET_X86_64 */
 
 #define USE_ELF_CORE_DUMP
 #define ELF_EXEC_PAGESIZE       4096
 
-#endif
+#endif /* TARGET_I386 */
 
 #ifdef TARGET_ARM
 
diff --git a/linux-user/i386/Makefile.vdso b/linux-user/i386/Makefile.vdso
new file mode 100644
index 0000000000..95bc616f6d
--- /dev/null
+++ b/linux-user/i386/Makefile.vdso
@@ -0,0 +1,11 @@
+include $(BUILD_DIR)/tests/tcg/i386-linux-user/config-target.mak
+
+SUBDIR = $(SRC_PATH)/linux-user/i386
+VPATH += $(SUBDIR)
+
+all: $(SUBDIR)/vdso.so
+
+$(SUBDIR)/vdso.so: vdso.S vdso.ld vdso-asmoffset.h
+	$(CC) -o $@ -m32 -nostdlib -shared -Wl,-h,linux-gate.so.1 \
+	  -Wl,--build-id=sha1 -Wl,--hash-style=both \
+	  -Wl,-T,$(SUBDIR)/vdso.ld $<
diff --git a/linux-user/i386/meson.build b/linux-user/i386/meson.build
index ee523019a5..d42fc6cbc9 100644
--- a/linux-user/i386/meson.build
+++ b/linux-user/i386/meson.build
@@ -3,3 +3,10 @@ syscall_nr_generators += {
                     arguments: [ meson.current_source_dir() / 'syscallhdr.sh', '@INPUT@', '@OUTPUT@', '@EXTRA_ARGS@' ],
                     output: '@BASENAME@_nr.h')
 }
+
+vdso_inc = gen_vdso.process('vdso.so', extra_args: [
+                                '-s', '__kernel_sigreturn',
+                                '-r', '__kernel_rt_sigreturn'
+                            ])
+
+linux_user_ss.add(when: 'TARGET_I386', if_true: vdso_inc)
diff --git a/linux-user/i386/signal.c b/linux-user/i386/signal.c
index 60fa07d6f9..bc5d45302e 100644
--- a/linux-user/i386/signal.c
+++ b/linux-user/i386/signal.c
@@ -214,6 +214,17 @@ struct rt_sigframe {
 };
 #define TARGET_RT_SIGFRAME_FXSAVE_OFFSET (                                 \
     offsetof(struct rt_sigframe, fpstate) + TARGET_FPSTATE_FXSAVE_OFFSET)
+
+/*
+ * Verify that vdso-asmoffset.h constants match.
+ */
+#include "i386/vdso-asmoffset.h"
+
+QEMU_BUILD_BUG_ON(offsetof(struct sigframe, sc.eip)
+                  != SIGFRAME_SIGCONTEXT_eip);
+QEMU_BUILD_BUG_ON(offsetof(struct rt_sigframe, uc.tuc_mcontext.eip)
+                  != RT_SIGFRAME_SIGCONTEXT_eip);
+
 #else
 
 struct rt_sigframe {
diff --git a/linux-user/i386/vdso-asmoffset.h b/linux-user/i386/vdso-asmoffset.h
new file mode 100644
index 0000000000..4e5ee0dd49
--- /dev/null
+++ b/linux-user/i386/vdso-asmoffset.h
@@ -0,0 +1,6 @@
+/*
+ * offsetof(struct sigframe, sc.eip)
+ * offsetof(struct rt_sigframe, uc.tuc_mcontext.eip)
+ */
+#define SIGFRAME_SIGCONTEXT_eip      64
+#define RT_SIGFRAME_SIGCONTEXT_eip  220
diff --git a/linux-user/i386/vdso.S b/linux-user/i386/vdso.S
new file mode 100644
index 0000000000..e7a1f333a1
--- /dev/null
+++ b/linux-user/i386/vdso.S
@@ -0,0 +1,143 @@
+/*
+ * i386 linux replacement vdso.
+ *
+ * Copyright 2023 Linaro, Ltd.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include <asm/unistd.h>
+#include "vdso-asmoffset.h"
+
+.macro endf name
+	.globl	\name
+	.type	\name, @function
+	.size	\name, . - \name
+.endm
+
+.macro vdso_syscall1 name, nr
+\name:
+	.cfi_startproc
+	mov	%ebx, %edx
+	.cfi_register %ebx, %edx
+	mov	4(%esp), %ebx
+	mov	$\nr, %eax
+	int	$0x80
+	mov	%edx, %ebx
+	ret
+	.cfi_endproc
+endf	\name
+.endm
+
+.macro vdso_syscall2 name, nr
+\name:
+	.cfi_startproc
+	mov	%ebx, %edx
+	.cfi_register %ebx, %edx
+	mov	4(%esp), %ebx
+	mov	8(%esp), %ecx
+	mov	$\nr, %eax
+	int	$0x80
+	mov	%edx, %ebx
+	ret
+	.cfi_endproc
+endf	\name
+.endm
+
+.macro vdso_syscall3 name, nr
+\name:
+	.cfi_startproc
+	push	%ebx
+	.cfi_adjust_cfa_offset 4
+	.cfi_rel_offset %ebx, 0
+	mov	8(%esp), %ebx
+	mov	12(%esp), %ecx
+	mov	16(%esp), %edx
+	mov	$\nr, %eax
+	int	$0x80
+	pop	%ebx
+	.cfi_adjust_cfa_offset -4
+	.cfi_restore %ebx
+	ret
+	.cfi_endproc
+endf	\name
+.endm
+
+__kernel_vsyscall:
+	.cfi_startproc
+	int	$0x80
+	ret
+	.cfi_endproc
+endf	__kernel_vsyscall
+
+vdso_syscall2 __vdso_clock_gettime, __NR_clock_gettime
+vdso_syscall2 __vdso_clock_gettime64, __NR_clock_gettime64
+vdso_syscall2 __vdso_clock_getres, __NR_clock_getres
+vdso_syscall2 __vdso_gettimeofday, __NR_gettimeofday
+vdso_syscall1 __vdso_time, __NR_time
+vdso_syscall3 __vdso_getcpu, __NR_gettimeofday
+
+/*
+ * Signal return handlers.
+ */
+
+	.cfi_startproc simple
+	.cfi_signal_frame
+
+/*
+ * For convenience, put the cfa just above eip in sigcontext, and count
+ * offsets backward from there.  Re-compute the cfa in the two contexts
+ * we have for signal unwinding.  This is far simpler than the
+ * DW_CFA_expression form that the kernel uses, and is equally correct.
+ */
+
+	.cfi_def_cfa	%esp, SIGFRAME_SIGCONTEXT_eip + 4
+
+	.cfi_offset	%eip, -4
+			/* err, -8 */
+			/* trapno, -12 */
+	.cfi_offset	%eax, -16
+	.cfi_offset	%ecx, -20
+	.cfi_offset	%edx, -24
+	.cfi_offset	%ebx, -28
+	.cfi_offset	%esp, -32
+	.cfi_offset	%ebp, -36
+	.cfi_offset	%esi, -40
+	.cfi_offset	%edi, -44
+
+/*
+ * While this frame is marked as a signal frame, that only applies to how
+ * the return address is handled for the outer frame.  The return address
+ * that arrived here, from the inner frame, is not marked as a signal frame
+ * and so the unwinder still tries to subtract 1 to examine the presumed
+ * call insn.  Thus we must extend the unwind info to a nop before the start.
+ */
+	nop
+
+__kernel_sigreturn:
+	popl	%eax	/* pop sig */
+	.cfi_adjust_cfa_offset -4
+	movl	$__NR_sigreturn, %eax
+	int	$0x80
+endf	__kernel_sigreturn
+
+	.cfi_def_cfa_offset RT_SIGFRAME_SIGCONTEXT_eip + 4
+	nop
+
+__kernel_rt_sigreturn:
+	movl	$__NR_rt_sigreturn, %eax
+	int	$0x80
+endf	__kernel_rt_sigreturn
+
+	.cfi_endproc
+
+/*
+ * TODO: Add elf notes.  E.g.
+ *
+ * #include <linux/elfnote.h>
+ * ELFNOTE_START(Linux, 0, "a")
+ *   .long LINUX_VERSION_CODE
+ * ELFNOTE_END
+ *
+ * but what version number would we set for QEMU?
+ */
diff --git a/linux-user/i386/vdso.ld b/linux-user/i386/vdso.ld
new file mode 100644
index 0000000000..326b7a8f98
--- /dev/null
+++ b/linux-user/i386/vdso.ld
@@ -0,0 +1,76 @@
+/*
+ * Linker script for linux i386 replacement vdso.
+ *
+ * Copyright 2023 Linaro, Ltd.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+ENTRY(__kernel_vsyscall)
+
+VERSION {
+        LINUX_2.6 {
+        global:
+                __vdso_clock_gettime;
+                __vdso_gettimeofday;
+                __vdso_time;
+                __vdso_clock_getres;
+                __vdso_clock_gettime64;
+                __vdso_getcpu;
+        };
+
+        LINUX_2.5 {
+        global:
+                __kernel_vsyscall;
+                __kernel_sigreturn;
+                __kernel_rt_sigreturn;
+        local: *;
+        };
+}
+
+PHDRS {
+        phdr            PT_PHDR         FLAGS(4) PHDRS;
+        load            PT_LOAD         FLAGS(7) FILEHDR PHDRS; /* FLAGS=RWX */
+        dynamic         PT_DYNAMIC      FLAGS(4);
+        eh_frame_hdr    PT_GNU_EH_FRAME;
+        note            PT_NOTE         FLAGS(4);
+}
+
+SECTIONS {
+        . = SIZEOF_HEADERS;
+
+        /*
+         * The following, including the FILEHDRS and PHDRS, are modified
+         * when we relocate the binary.  We want them to be initially
+         * writable for the relocation; we'll force them read-only after.
+         */
+        .note           : { *(.note*) }         :load :note
+        .dynamic        : { *(.dynamic) }       :load :dynamic
+        .dynsym         : { *(.dynsym) }        :load
+        .data           : {
+                /*
+                 * There ought not be any real read-write data.
+                 * But since we manipulated the segment layout,
+                 * we have to put these sections somewhere.
+                 */
+                *(.data*)
+                *(.sdata*)
+                *(.got.plt) *(.got)
+                *(.gnu.linkonce.d.*)
+                *(.bss*)
+                *(.dynbss*)
+                *(.gnu.linkonce.b.*)
+        }
+
+        .rodata         : { *(.rodata*) }
+        .hash           : { *(.hash) }
+        .gnu.hash       : { *(.gnu.hash) }
+        .dynstr         : { *(.dynstr) }
+        .gnu.version    : { *(.gnu.version) }
+        .gnu.version_d  : { *(.gnu.version_d) }
+        .gnu.version_r  : { *(.gnu.version_r) }
+        .eh_frame_hdr   : { *(.eh_frame_hdr) }  :load :eh_frame_hdr
+        .eh_frame       : { *(.eh_frame) }      :load
+
+        .text           : { *(.text*) }         :load   =0x90909090
+}
diff --git a/linux-user/i386/vdso.so b/linux-user/i386/vdso.so
new file mode 100755
index 0000000000..bdece5dfcf
--- /dev/null
+++ b/linux-user/i386/vdso.so