Resguardo inicial

linux-7.2.3/arch/x86/entry/vdso/.gitignore

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+*.lds
+*.so
+*.so.dbg
+vdso*-image*.c
+vdso2c

linux-7.2.3/arch/x86/entry/vdso/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Building vDSO images for x86.
+#
+
+# Regular kernel objects
+obj-y				:= vma.o extable.o
+obj-$(CONFIG_COMPAT_32)		+= vdso32-setup.o
+
+# vDSO directories
+obj-$(CONFIG_X86_64)		+= vdso64/
+obj-$(CONFIG_COMPAT_32)		+= vdso32/

linux-7.2.3/arch/x86/entry/vdso/common/Makefile.include

@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Building vDSO images for x86.
+#
+
+# Include the generic Makefile to check the built vDSO:
+include $(srctree)/lib/vdso/Makefile.include
+
+obj-y    += $(foreach x,$(vdsos-y),vdso$(x)-image.o)
+
+targets  += $(foreach x,$(vdsos-y),vdso$(x)-image.c vdso$(x).so vdso$(x).so.dbg vdso$(x).lds)
+targets  += $(vobjs-y)
+
+# vobjs-y with $(obj)/ prepended
+vobjs := $(addprefix $(obj)/,$(vobjs-y))
+
+# Options for vdso*.lds
+CPPFLAGS_VDSO_LDS := -P -C -I$(src)/..
+$(obj)/%.lds : KBUILD_CPPFLAGS += $(CPPFLAGS_VDSO_LDS)
+
+#
+# Options from KBUILD_[AC]FLAGS that should *NOT* be kept
+#
+flags-remove-y += \
+	-D__KERNEL__ -mcmodel=kernel -mregparm=3 \
+	-fno-pic -fno-PIC -fno-pie -fno-PIE \
+	-mfentry -pg \
+	$(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(KSTACK_ERASE_CFLAGS) \
+	$(RETPOLINE_CFLAGS) $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) \
+	$(PADDING_CFLAGS)
+
+#
+# Don't omit frame pointers for ease of userspace debugging, but do
+# optimize sibling calls.
+#
+flags-y += -D__DISABLE_EXPORTS
+flags-y += -DDISABLE_BRANCH_PROFILING
+flags-y += -DBUILD_VDSO
+flags-y += -I$(src)/.. -I$(srctree)
+flags-y += -O2 -fpic
+flags-y += -fno-stack-protector
+flags-y += -fno-omit-frame-pointer
+flags-y += -foptimize-sibling-calls
+flags-y += -fasynchronous-unwind-tables
+
+# Reset cf protections enabled by compiler default
+flags-y += $(call cc-option, -fcf-protection=none)
+flags-$(X86_USER_SHADOW_STACK) += $(call cc-option, -fcf-protection=return)
+# When user space IBT is supported, enable this.
+# flags-$(CONFIG_USER_IBT) += $(call cc-option, -fcf-protection=branch)
+
+flags-$(CONFIG_MITIGATION_RETPOLINE) += $(RETPOLINE_VDSO_CFLAGS)
+
+# These need to be conditional on $(vobjs) as they do not apply to
+# the output vdso*-image.o files which are standard kernel objects.
+$(vobjs) : KBUILD_AFLAGS := \
+	$(filter-out $(flags-remove-y),$(KBUILD_AFLAGS)) $(flags-y)
+$(vobjs) : KBUILD_CFLAGS := \
+	$(filter-out $(flags-remove-y),$(KBUILD_CFLAGS)) $(flags-y)
+
+#
+# The VDSO images are built using a special linker script.
+#
+VDSO_LDFLAGS := -shared --hash-style=both --build-id=sha1 --no-undefined \
+	$(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack
+
+quiet_cmd_vdso = VDSO    $@
+      cmd_vdso = $(LD) -o $@ \
+		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$*) \
+		       -T $(filter %.lds,$^) $(filter %.o,$^)
+quiet_cmd_vdso_and_check = VDSO    $@
+      cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check)
+
+$(obj)/vdso%.so.dbg: $(obj)/vdso%.lds FORCE
+	$(call if_changed,vdso_and_check)
+
+$(obj)/%.so: OBJCOPYFLAGS := -S --remove-section __ex_table
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+VDSO2C = $(objtree)/arch/x86/tools/vdso2c
+
+quiet_cmd_vdso2c = VDSO2C  $@
+      cmd_vdso2c = $(VDSO2C) $< $(<:%.dbg=%) $@
+
+$(obj)/%-image.c: $(obj)/%.so.dbg $(obj)/%.so $(VDSO2C) FORCE
+	$(call if_changed,vdso2c)
+
+$(obj)/%-image.o: $(obj)/%-image.c

linux-7.2.3/arch/x86/entry/vdso/common/note.S

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/build-salt.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+/* Ideally this would use UTS_NAME, but using a quoted string here
+   doesn't work. Remember to change this when changing the
+   kernel's name. */
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
+
+BUILD_SALT

linux-7.2.3/arch/x86/entry/vdso/common/vclock_gettime.c

@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Copyright 2019 ARM Limited
+ *
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ *  sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ */
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <vdso/gettime.h>
+
+#include "lib/vdso/gettimeofday.c"
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int gettimeofday(struct __kernel_old_timeval *, struct timezone *)
+	__attribute__((weak, alias("__vdso_gettimeofday")));
+
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
+{
+	return __cvdso_time(t);
+}
+
+__kernel_old_time_t time(__kernel_old_time_t *t)	__attribute__((weak, alias("__vdso_time")));
+
+
+#if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
+/* both 64-bit and x32 use these */
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int clock_gettime(clockid_t, struct __kernel_timespec *)
+	__attribute__((weak, alias("__vdso_clock_gettime")));
+
+int __vdso_clock_getres(clockid_t clock,
+			struct __kernel_timespec *res)
+{
+	return __cvdso_clock_getres(clock, res);
+}
+int clock_getres(clockid_t, struct __kernel_timespec *)
+	__attribute__((weak, alias("__vdso_clock_getres")));
+
+#else
+/* i386 only */
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
+{
+	return __cvdso_clock_gettime32(clock, ts);
+}
+
+int clock_gettime(clockid_t, struct old_timespec32 *)
+	__attribute__((weak, alias("__vdso_clock_gettime")));
+
+int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int clock_gettime64(clockid_t, struct __kernel_timespec *)
+	__attribute__((weak, alias("__vdso_clock_gettime64")));
+
+int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res)
+{
+	return __cvdso_clock_getres_time32(clock, res);
+}
+
+int clock_getres(clockid_t, struct old_timespec32 *)
+	__attribute__((weak, alias("__vdso_clock_getres")));
+
+int __vdso_clock_getres_time64(clockid_t clock, struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_getres(clock, ts);
+}
+
+int clock_getres_time64(clockid_t, struct __kernel_timespec *)
+	__attribute__((weak, alias("__vdso_clock_getres_time64")));
+#endif

linux-7.2.3/arch/x86/entry/vdso/common/vdso-layout.lds.S

@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/vdso.h>
+#include <asm/vdso/vsyscall.h>
+#include <vdso/datapage.h>
+
+/*
+ * Linker script for vDSO.  This is an ELF shared object prelinked to
+ * its virtual address, and with only one read-only segment.
+ * This script controls its layout.
+ */
+
+SECTIONS
+{
+	/*
+	 * User/kernel shared data is before the vDSO.  This may be a little
+	 * uglier than putting it after the vDSO, but it avoids issues with
+	 * non-allocatable things that dangle past the end of the PT_LOAD
+	 * segment.
+	 */
+
+	VDSO_VVAR_SYMS
+
+	vclock_pages = VDSO_VCLOCK_PAGES_START(vdso_u_data);
+	pvclock_page = vclock_pages + VDSO_PAGE_PVCLOCK_OFFSET * PAGE_SIZE;
+	hvclock_page = vclock_pages + VDSO_PAGE_HVCLOCK_OFFSET * PAGE_SIZE;
+
+	. = SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.rodata		: {
+		*(.rodata*)
+		*(.data*)
+		*(.sdata*)
+		*(.got.plt) *(.got)
+		*(.gnu.linkonce.d.*)
+		*(.bss*)
+		*(.dynbss*)
+		*(.gnu.linkonce.b.*)
+	}						:text
+
+	.note.gnu.property : {
+		*(.note.gnu.property)
+	}					:text :note :gnu_property
+	.note		: {
+		*(.note*)
+	}					:text :note
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }	:text :eh_frame_hdr
+	.eh_frame	: {
+		KEEP (*(.eh_frame))
+		*(.eh_frame.*)
+	}					:text
+
+	/*
+	 * Text is well-separated from actual data: there's plenty of
+	 * stuff that isn't used at runtime in between.
+	 */
+
+	.text		: {
+		*(.text*)
+	}						:text	=0x90909090,
+
+
+
+	.altinstructions	: { *(.altinstructions) }	:text
+	.altinstr_replacement	: { *(.altinstr_replacement) }	:text
+
+	__ex_table		: { *(__ex_table) }		:text
+
+	/DISCARD/ : {
+		*(.discard)
+		*(.discard.*)
+		*(__bug_table)
+	}
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME	0x6474e550
+#define PT_GNU_STACK	0x6474e551
+#define PT_GNU_PROPERTY	0x6474e553
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+*/
+#define PF_R	FLAGS(4)
+#define PF_RW	FLAGS(6)
+#define PF_RX	FLAGS(5)
+
+PHDRS
+{
+	text		PT_LOAD		PF_RX FILEHDR PHDRS;
+	dynamic		PT_DYNAMIC	PF_R;
+	note		PT_NOTE		PF_R;
+	eh_frame_hdr	PT_GNU_EH_FRAME PF_R;
+	gnu_stack	PT_GNU_STACK	PF_RW;
+	gnu_property	PT_GNU_PROPERTY	PF_R;
+}

linux-7.2.3/arch/x86/entry/vdso/common/vfutex.c

@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <vdso/futex.h>
+
+/*
+ * Assembly template for the try unlock functions. The basic functionality is:
+ *
+ *		mov		esi, %eax	Move the TID into EAX
+ *		xor		%ecx, %ecx	Clear ECX
+ *		lock_cmpxchgl	%ecx, (%rdi)	Attempt the TID -> 0 transition
+ * .Lcs_start:					Start of the critical section
+ *		jnz		.Lcs_end	If cmpxchl failed jump to the end
+ * .Lcs_success:				Start of the success section
+ *		movq		%rcx, (%rdx)	Set the pending op pointer to 0
+ * .Lcs_end:					End of the critical section
+ *
+ * .Lcs_start and .Lcs_end establish the critical section range. .Lcs_success is
+ * technically not required, but there for illustration, debugging and testing.
+ *
+ * When CONFIG_COMPAT is enabled then the 64-bit VDSO provides two functions.
+ * One for the regular 64-bit sized pending operation pointer and one for a
+ * 32-bit sized pointer to support gaming emulators.
+ *
+ * The 32-bit VDSO provides only the one for 32-bit sized pointers.
+ */
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#define LABEL(prefix, which)	__stringify(prefix##_try_unlock_cs_##which:)
+
+#define JNZ_END(prefix)		"jnz " __stringify(prefix) "_try_unlock_cs_end\n"
+
+#define CLEAR_POPQ		"movq	%[zero],  %a[pop]\n"
+#define CLEAR_POPL		"movl	%k[zero], %a[pop]\n"
+
+#define futex_robust_try_unlock(prefix, clear_pop, __lock, __tid, __pop)\
+({									\
+	asm volatile (							\
+		"						\n"	\
+		"	lock cmpxchgl	%k[zero], %a[lock]	\n"	\
+		"						\n"	\
+		LABEL(prefix, start)					\
+		"						\n"	\
+		JNZ_END(prefix)						\
+		"						\n"	\
+		LABEL(prefix, success)					\
+		"						\n"	\
+			clear_pop					\
+		"						\n"	\
+		LABEL(prefix, end)					\
+		: [tid]   "+&a" (__tid)					\
+		: [lock]  "D"   (__lock),				\
+		  [pop]   "d"   (__pop),				\
+		  [zero]  "r"   (0UL)					\
+		: "memory"						\
+	);								\
+	__tid;								\
+})
+
+#ifdef __x86_64__
+__u32 __vdso_futex_robust_list64_try_unlock(__u32 *lock, __u32 tid, __u64 *pop)
+{
+	return futex_robust_try_unlock(__futex_list64, CLEAR_POPQ, lock, tid, pop);
+}
+#endif /* __x86_64__ */
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+__u32 __vdso_futex_robust_list32_try_unlock(__u32 *lock, __u32 tid, __u32 *pop)
+{
+	return futex_robust_try_unlock(__futex_list32, CLEAR_POPL, lock, tid, pop);
+}
+#endif /* CONFIG_X86_32 || CONFIG_COMPAT */

linux-7.2.3/arch/x86/entry/vdso/common/vgetcpu.c

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ *
+ * Fast user context implementation of getcpu()
+ */
+
+#include <linux/kernel.h>
+#include <asm/segment.h>
+#include <vdso/processor.h>
+
+notrace long
+__vdso_getcpu(unsigned *cpu, unsigned *node, void *unused)
+{
+	vdso_read_cpunode(cpu, node);
+
+	return 0;
+}
+
+long getcpu(unsigned *cpu, unsigned *node, void *tcache)
+	__attribute__((weak, alias("__vdso_getcpu")));

linux-7.2.3/arch/x86/entry/vdso/extable.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <asm/current.h>
+#include <asm/traps.h>
+#include <asm/vdso.h>
+
+struct vdso_exception_table_entry {
+	int insn, fixup;
+};
+
+bool fixup_vdso_exception(struct pt_regs *regs, int trapnr,
+			  unsigned long error_code, unsigned long fault_addr)
+{
+	const struct vdso_image *image = current->mm->context.vdso_image;
+	const struct vdso_exception_table_entry *extable;
+	unsigned int nr_entries, i;
+	unsigned long base;
+
+	/*
+	 * Do not attempt to fixup #DB or #BP.  It's impossible to identify
+	 * whether or not a #DB/#BP originated from within an SGX enclave and
+	 * SGX enclaves are currently the only use case for vDSO fixup.
+	 */
+	if (trapnr == X86_TRAP_DB || trapnr == X86_TRAP_BP)
+		return false;
+
+	if (!current->mm->context.vdso)
+		return false;
+
+	base =  (unsigned long)current->mm->context.vdso + image->extable_base;
+	nr_entries = image->extable_len / (sizeof(*extable));
+	extable = image->extable;
+
+	for (i = 0; i < nr_entries; i++) {
+		if (regs->ip == base + extable[i].insn) {
+			regs->ip = base + extable[i].fixup;
+			regs->di = trapnr;
+			regs->si = error_code;
+			regs->dx = fault_addr;
+			return true;
+		}
+	}
+
+	return false;
+}

linux-7.2.3/arch/x86/entry/vdso/extable.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_EXTABLE_H
+#define __VDSO_EXTABLE_H
+
+/*
+ * Inject exception fixup for vDSO code.  Unlike normal exception fixup,
+ * vDSO uses a dedicated handler the addresses are relative to the overall
+ * exception table, not each individual entry.
+ */
+#ifdef __ASSEMBLER__
+#define _ASM_VDSO_EXTABLE_HANDLE(from, to)	\
+	ASM_VDSO_EXTABLE_HANDLE from to
+
+.macro ASM_VDSO_EXTABLE_HANDLE from:req to:req
+	.pushsection __ex_table, "a"
+	.long (\from) - __ex_table
+	.long (\to) - __ex_table
+	.popsection
+.endm
+#else
+#define _ASM_VDSO_EXTABLE_HANDLE(from, to)	\
+	".pushsection __ex_table, \"a\"\n"      \
+	".long (" #from ") - __ex_table\n"      \
+	".long (" #to ") - __ex_table\n"        \
+	".popsection\n"
+#endif
+
+#endif /* __VDSO_EXTABLE_H */

linux-7.2.3/arch/x86/entry/vdso/vdso32-setup.c

@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * (C) Copyright 2002 Linus Torvalds
+ * Portions based on the vdso-randomization code from exec-shield:
+ * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This file contains the needed initializations to support sysenter.
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/mm_types.h>
+#include <linux/elf.h>
+
+#include <asm/processor.h>
+#include <asm/vdso.h>
+
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_DEFAULT	0
+#else
+#define VDSO_DEFAULT	1
+#endif
+
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT;
+
+static int __init vdso32_setup(char *s)
+{
+	vdso32_enabled = simple_strtoul(s, NULL, 0);
+
+	if (vdso32_enabled > 1) {
+		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+		vdso32_enabled = 0;
+	}
+
+	return 1;
+}
+
+/*
+ * For consistency, the argument vdso32=[012] affects the 32-bit vDSO
+ * behavior on both 64-bit and 32-bit kernels.
+ * On 32-bit kernels, vdso=[012] means the same thing.
+ */
+__setup("vdso32=", vdso32_setup);
+
+#ifdef CONFIG_X86_32
+__setup_param("vdso=", vdso_setup, vdso32_setup, 0);
+#endif
+
+
+#ifdef CONFIG_SYSCTL
+#include <linux/sysctl.h>
+
+static const struct ctl_table vdso_table[] = {
+	{
+#ifdef CONFIG_X86_64
+		.procname	= "vsyscall32",
+#else
+		.procname	= "vdso_enabled",
+#endif
+		.data		= &vdso32_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
+static __init int ia32_binfmt_init(void)
+{
+#ifdef CONFIG_X86_64
+	/* Register vsyscall32 into the ABI table */
+	register_sysctl("abi", vdso_table);
+#else
+	register_sysctl_init("vm", vdso_table);
+#endif
+	return 0;
+}
+__initcall(ia32_binfmt_init);
+#endif /* CONFIG_SYSCTL */
+

linux-7.2.3/arch/x86/entry/vdso/vdso32/.gitignore

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vdso32.lds

linux-7.2.3/arch/x86/entry/vdso/vdso32/Makefile

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# 32-bit vDSO images for x86.
+#
+
+# The vDSOs built in this directory
+vdsos-y			:= 32
+
+# Files to link into the vDSO:
+vobjs-y					:= note.o vclock_gettime.o vgetcpu.o
+vobjs-y					+= system_call.o sigreturn.o
+vobjs-$(CONFIG_FUTEX_ROBUST_UNLOCK)	+= vfutex.o
+
+# Compilation flags
+flags-y			:= -DBUILD_VDSO32 -m32 -mregparm=0
+flags-$(CONFIG_X86_64)	+= -include $(src)/fake_32bit_build.h
+flags-remove-y          := -m64
+
+# Checker flags
+CHECKFLAGS := $(subst -m64,-m32,$(CHECKFLAGS))
+CHECKFLAGS := $(subst -D__x86_64__,-D__i386__,$(CHECKFLAGS))
+
+# The location of this include matters!
+include $(src)/../common/Makefile.include
+
+# Linker options for the vdso
+VDSO_LDFLAGS_32		:= -m elf_i386 -soname linux-gate.so.1
+
+$(obj)/vdso32.so.dbg: $(vobjs)

linux-7.2.3/arch/x86/entry/vdso/vdso32/fake_32bit_build.h

@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef CONFIG_X86_64
+
+/*
+ * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
+ * configuration
+ */
+#undef CONFIG_64BIT
+#undef CONFIG_X86_64
+#undef CONFIG_COMPAT
+#undef CONFIG_PGTABLE_LEVELS
+#undef CONFIG_ILLEGAL_POINTER_VALUE
+#undef CONFIG_SPARSEMEM_VMEMMAP
+#undef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+#undef CONFIG_NR_CPUS
+#undef CONFIG_PARAVIRT_XXL
+
+#define CONFIG_X86_32 1
+#define CONFIG_PGTABLE_LEVELS 2
+#define CONFIG_PAGE_OFFSET 0
+#define CONFIG_ILLEGAL_POINTER_VALUE 0
+#define CONFIG_NR_CPUS 1
+
+#define BUILD_VDSO32_64
+
+#endif

linux-7.2.3/arch/x86/entry/vdso/vdso32/note.S

@@ -0,0 +1 @@
+#include "common/note.S"

linux-7.2.3/arch/x86/entry/vdso/vdso32/sigreturn.S

@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/unistd_32.h>
+#include <asm/dwarf2.h>
+#include <asm/asm-offsets.h>
+
+.macro STARTPROC_SIGNAL_FRAME sc
+	CFI_STARTPROC	simple
+	CFI_SIGNAL_FRAME
+	/* -4 as pretcode has already been popped */
+	CFI_DEF_CFA	esp,	\sc - 4
+	CFI_OFFSET	eip,    IA32_SIGCONTEXT_ip
+	CFI_OFFSET	eax,    IA32_SIGCONTEXT_ax
+	CFI_OFFSET	ebx,    IA32_SIGCONTEXT_bx
+	CFI_OFFSET	ecx,    IA32_SIGCONTEXT_cx
+	CFI_OFFSET	edx,    IA32_SIGCONTEXT_dx
+	CFI_OFFSET	esp,    IA32_SIGCONTEXT_sp
+	CFI_OFFSET	ebp,    IA32_SIGCONTEXT_bp
+	CFI_OFFSET	esi,    IA32_SIGCONTEXT_si
+	CFI_OFFSET	edi,    IA32_SIGCONTEXT_di
+	CFI_OFFSET	es,     IA32_SIGCONTEXT_es
+	CFI_OFFSET	cs,     IA32_SIGCONTEXT_cs
+	CFI_OFFSET	ss,     IA32_SIGCONTEXT_ss
+	CFI_OFFSET	ds,     IA32_SIGCONTEXT_ds
+	CFI_OFFSET	eflags, IA32_SIGCONTEXT_flags
+.endm
+
+/*
+ * WARNING:
+ *
+ * A bug in the libgcc unwinder as of at least gcc 15.2 (2026) means that
+ * the unwinder fails to recognize the signal frame flag.
+ *
+ * There is a hacky legacy fallback path in libgcc which ends up
+ * getting invoked instead. It happens to work as long as BOTH of the
+ * following conditions are true:
+ *
+ * 1. There is at least one byte before the each of the sigreturn
+ *    functions which falls outside any function. This is enforced by
+ *    an explicit nop instruction before the ALIGN.
+ * 2. The code sequences between the entry point up to and including
+ *    the int $0x80 below need to match EXACTLY. Do not change them
+ *    in any way. The exact byte sequences are:
+ *
+ *    __kernel_sigreturn:
+ *        0:   58                      pop    %eax
+ *        1:   b8 77 00 00 00          mov    $0x77,%eax
+ *        6:   cd 80                   int    $0x80
+ *
+ *    __kernel_rt_sigreturn:
+ *        0:   b8 ad 00 00 00          mov    $0xad,%eax
+ *        5:   cd 80                   int    $0x80
+ *
+ * For details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050
+ */
+	.text
+	.globl __kernel_sigreturn
+	.type __kernel_sigreturn,@function
+	nop			/* libgcc hack: see comment above */
+	ALIGN
+__kernel_sigreturn:
+	STARTPROC_SIGNAL_FRAME IA32_SIGFRAME_sigcontext
+	popl %eax
+	CFI_ADJUST_CFA_OFFSET -4
+	movl $__NR_sigreturn, %eax
+	int $0x80
+SYM_INNER_LABEL(vdso32_sigreturn_landing_pad, SYM_L_GLOBAL)
+	ud2a
+	CFI_ENDPROC
+	.size __kernel_sigreturn,.-__kernel_sigreturn
+
+	.globl __kernel_rt_sigreturn
+	.type __kernel_rt_sigreturn,@function
+	nop			/* libgcc hack: see comment above */
+	ALIGN
+__kernel_rt_sigreturn:
+	STARTPROC_SIGNAL_FRAME IA32_RT_SIGFRAME_sigcontext
+	movl $__NR_rt_sigreturn, %eax
+	int $0x80
+SYM_INNER_LABEL(vdso32_rt_sigreturn_landing_pad, SYM_L_GLOBAL)
+	ud2a
+	CFI_ENDPROC
+	.size __kernel_rt_sigreturn,.-__kernel_rt_sigreturn
+	.previous

linux-7.2.3/arch/x86/entry/vdso/vdso32/system_call.S

@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AT_SYSINFO entry point
+*/
+
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+
+	.text
+	.globl __kernel_vsyscall
+	.type __kernel_vsyscall,@function
+	ALIGN
+__kernel_vsyscall:
+	CFI_STARTPROC
+
+	/*
+	 * If using int $0x80, there is no reason to muck about with the
+	 * stack here. Unfortunately just overwriting the push instructions
+	 * would mess up the CFI annotations, but it is only a 3-byte
+	 * NOP in that case. This could be avoided by patching the
+	 * vdso symbol table (not the code) and entry point, but that
+	 * would a fair bit of tooling work or by simply compiling
+	 * two different vDSO images, but that doesn't seem worth it.
+	 */
+	ALTERNATIVE "int $0x80; ret", "", X86_FEATURE_SYSFAST32
+
+	/*
+	 * Reshuffle regs so that all of any of the entry instructions
+	 * will preserve enough state.
+	 *
+	 * A really nice entry sequence would be:
+	 *  pushl %edx
+	 *  pushl %ecx
+	 *  movl  %esp, %ecx
+	 *
+	 * Unfortunately, naughty Android versions between July and December
+	 * 2015 actually hardcode the traditional Linux SYSENTER entry
+	 * sequence.  That is severely broken for a number of reasons (ask
+	 * anyone with an AMD CPU, for example).  Nonetheless, we try to keep
+	 * it working approximately as well as it ever worked.
+	 *
+	 * This link may elucidate some of the history:
+	 *   https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7
+	 * personally, I find it hard to understand what's going on there.
+	 *
+	 * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE.
+	 * Execute an indirect call to the address in the AT_SYSINFO auxv
+	 * entry.  That is the ONLY correct way to make a fast 32-bit system
+	 * call on Linux.  (Open-coding int $0x80 is also fine, but it's
+	 * slow.)
+	 */
+	pushl	%ecx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		ecx, 0
+	pushl	%edx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		edx, 0
+	pushl	%ebp
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		ebp, 0
+
+	#define SYSENTER_SEQUENCE	"movl %esp, %ebp; sysenter"
+	#define SYSCALL_SEQUENCE	"movl %ecx, %ebp; syscall"
+
+	ALTERNATIVE SYSENTER_SEQUENCE, SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32
+
+	/* Re-enter using int $0x80 */
+	int	$0x80
+SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL)
+
+	/*
+	 * Restore EDX and ECX in case they were clobbered.  EBP is not
+	 * clobbered (the kernel restores it), but it's cleaner and
+	 * probably faster to pop it than to adjust ESP using addl.
+	 */
+	popl	%ebp
+	CFI_RESTORE		ebp
+	CFI_ADJUST_CFA_OFFSET	-4
+	popl	%edx
+	CFI_RESTORE		edx
+	CFI_ADJUST_CFA_OFFSET	-4
+	popl	%ecx
+	CFI_RESTORE		ecx
+	CFI_ADJUST_CFA_OFFSET	-4
+	RET
+	CFI_ENDPROC
+
+	.size __kernel_vsyscall,.-__kernel_vsyscall
+	.previous

linux-7.2.3/arch/x86/entry/vdso/vdso32/vclock_gettime.c

@@ -0,0 +1 @@
+#include "common/vclock_gettime.c"

linux-7.2.3/arch/x86/entry/vdso/vdso32/vdso32.lds.S

@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linker script for 32-bit vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#include <asm/page.h>
+
+#define BUILD_VDSO32
+
+#include "common/vdso-layout.lds.S"
+
+/* The ELF entry point can be used to set the AT_SYSINFO value.  */
+ENTRY(__kernel_vsyscall);
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION
+{
+	LINUX_2.6 {
+	global:
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_time;
+		__vdso_clock_getres;
+		__vdso_clock_gettime64;
+		__vdso_clock_getres_time64;
+		__vdso_getcpu;
+#ifdef CONFIG_FUTEX_ROBUST_UNLOCK
+		__vdso_futex_robust_list32_try_unlock;
+#endif
+	};
+
+	LINUX_2.5 {
+	global:
+		__kernel_vsyscall;
+		__kernel_sigreturn;
+		__kernel_rt_sigreturn;
+	local: *;
+	};
+}

linux-7.2.3/arch/x86/entry/vdso/vdso32/vfutex.c

@@ -0,0 +1 @@
+#include "common/vfutex.c"

linux-7.2.3/arch/x86/entry/vdso/vdso32/vgetcpu.c

@@ -0,0 +1 @@
+#include "common/vgetcpu.c"

linux-7.2.3/arch/x86/entry/vdso/vdso64/Makefile

@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# 64-bit vDSO images for x86.
+#
+
+# The vDSOs built in this directory
+vdsos-y				:= 64
+vdsos-$(CONFIG_X86_X32_ABI)	+= x32
+
+# Files to link into the vDSO:
+vobjs-y					:= note.o vclock_gettime.o vgetcpu.o
+vobjs-y					+= vgetrandom.o vgetrandom-chacha.o
+vobjs-$(CONFIG_X86_SGX)			+= vsgx.o
+vobjs-$(CONFIG_FUTEX_ROBUST_UNLOCK)	+= vfutex.o
+
+# Compilation flags
+flags-y				:= -DBUILD_VDSO64 -m64 -mcmodel=small
+
+# The location of this include matters!
+include $(src)/../common/Makefile.include
+
+#
+# X32 processes use x32 vDSO to access 64bit kernel data.
+#
+# Build x32 vDSO image:
+# 1. Compile x32 vDSO as 64bit.
+# 2. Convert object files to x32.
+# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes
+# so that it can reach 64bit address space with 64bit pointers.
+#
+
+# Convert 64bit object file to x32 for x32 vDSO.
+quiet_cmd_x32 = X32     $@
+      cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@
+
+$(obj)/%-x32.o: $(obj)/%.o FORCE
+	$(call if_changed,x32)
+
+vobjsx32 = $(patsubst %.o,%-x32.o,$(vobjs))
+targets += $(patsubst %.o,%-x32.o,$(vobjs-y))
+
+# Linker options for the vdso
+VDSO_LDFLAGS_64  := -m elf_x86_64 -soname linux-vdso.so.1 -z max-page-size=4096
+VDSO_LDFLAGS_x32 := $(subst elf_x86_64,elf32_x86_64,$(VDSO_LDFLAGS_64))
+
+$(obj)/vdso64.so.dbg:	$(vobjs)
+$(obj)/vdsox32.so.dbg:	$(vobjsx32)

linux-7.2.3/arch/x86/entry/vdso/vdso64/note.S

@@ -0,0 +1 @@
+#include "common/note.S"

linux-7.2.3/arch/x86/entry/vdso/vdso64/vclock_gettime.c

@@ -0,0 +1 @@
+#include "common/vclock_gettime.c"

linux-7.2.3/arch/x86/entry/vdso/vdso64/vdso64.lds.S

@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linker script for 64-bit vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#define BUILD_VDSO64
+
+#include "common/vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+	LINUX_2.6 {
+	global:
+		clock_gettime;
+		__vdso_clock_gettime;
+		gettimeofday;
+		__vdso_gettimeofday;
+		getcpu;
+		__vdso_getcpu;
+		time;
+		__vdso_time;
+		clock_getres;
+		__vdso_clock_getres;
+#ifdef CONFIG_X86_SGX
+		__vdso_sgx_enter_enclave;
+#endif
+		getrandom;
+		__vdso_getrandom;
+
+#ifdef CONFIG_FUTEX_ROBUST_UNLOCK
+		__vdso_futex_robust_list64_try_unlock;
+#ifdef CONFIG_COMPAT
+		__vdso_futex_robust_list32_try_unlock;
+#endif
+#endif
+	local: *;
+	};
+}

linux-7.2.3/arch/x86/entry/vdso/vdso64/vdsox32.lds.S

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linker script for x32 vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#define BUILD_VDSOX32
+
+#include "common/vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+	LINUX_2.6 {
+	global:
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_getcpu;
+		__vdso_time;
+		__vdso_clock_getres;
+
+#ifdef CONFIG_FUTEX_ROBUST_UNLOCK
+		__vdso_futex_robust_list64_try_unlock;
+#ifdef CONFIG_COMPAT
+		__vdso_futex_robust_list32_try_unlock;
+#endif
+#endif
+	local: *;
+	};
+}

linux-7.2.3/arch/x86/entry/vdso/vdso64/vfutex.c

@@ -0,0 +1 @@
+#include "common/vfutex.c"

linux-7.2.3/arch/x86/entry/vdso/vdso64/vgetcpu.c

@@ -0,0 +1 @@
+#include "common/vgetcpu.c"

linux-7.2.3/arch/x86/entry/vdso/vdso64/vgetrandom-chacha.S

@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+
+.section	.rodata, "a"
+.align 16
+CONSTANTS:	.octa 0x6b20657479622d323320646e61707865
+.text
+
+/*
+ * Very basic SSE2 implementation of ChaCha20. Produces a given positive number
+ * of blocks of output with a nonce of 0, taking an input key and 8-byte
+ * counter. Importantly does not spill to the stack. Its arguments are:
+ *
+ *	rdi: output bytes
+ *	rsi: 32-byte key input
+ *	rdx: 8-byte counter input/output
+ *	rcx: number of 64-byte blocks to write to output
+ */
+SYM_FUNC_START(__arch_chacha20_blocks_nostack)
+
+.set	output,		%rdi
+.set	key,		%rsi
+.set	counter,	%rdx
+.set	nblocks,	%rcx
+.set	i,		%al
+/* xmm registers are *not* callee-save. */
+.set	temp,		%xmm0
+.set	state0,		%xmm1
+.set	state1,		%xmm2
+.set	state2,		%xmm3
+.set	state3,		%xmm4
+.set	copy0,		%xmm5
+.set	copy1,		%xmm6
+.set	copy2,		%xmm7
+.set	copy3,		%xmm8
+.set	one,		%xmm9
+
+	/* copy0 = "expand 32-byte k" */
+	movaps		CONSTANTS(%rip),copy0
+	/* copy1,copy2 = key */
+	movups		0x00(key),copy1
+	movups		0x10(key),copy2
+	/* copy3 = counter || zero nonce */
+	movq		0x00(counter),copy3
+	/* one = 1 || 0 */
+	movq		$1,%rax
+	movq		%rax,one
+
+.Lblock:
+	/* state0,state1,state2,state3 = copy0,copy1,copy2,copy3 */
+	movdqa		copy0,state0
+	movdqa		copy1,state1
+	movdqa		copy2,state2
+	movdqa		copy3,state3
+
+	movb		$10,i
+.Lpermute:
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$16,temp
+	psrld		$16,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$12,temp
+	psrld		$20,state1
+	por		temp,state1
+
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$8,temp
+	psrld		$24,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$7,temp
+	psrld		$25,state1
+	por		temp,state1
+
+	/* state1[0,1,2,3] = state1[1,2,3,0] */
+	pshufd		$0x39,state1,state1
+	/* state2[0,1,2,3] = state2[2,3,0,1] */
+	pshufd		$0x4e,state2,state2
+	/* state3[0,1,2,3] = state3[3,0,1,2] */
+	pshufd		$0x93,state3,state3
+
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 16) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$16,temp
+	psrld		$16,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 12) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$12,temp
+	psrld		$20,state1
+	por		temp,state1
+
+	/* state0 += state1, state3 = rotl32(state3 ^ state0, 8) */
+	paddd		state1,state0
+	pxor		state0,state3
+	movdqa		state3,temp
+	pslld		$8,temp
+	psrld		$24,state3
+	por		temp,state3
+
+	/* state2 += state3, state1 = rotl32(state1 ^ state2, 7) */
+	paddd		state3,state2
+	pxor		state2,state1
+	movdqa		state1,temp
+	pslld		$7,temp
+	psrld		$25,state1
+	por		temp,state1
+
+	/* state1[0,1,2,3] = state1[3,0,1,2] */
+	pshufd		$0x93,state1,state1
+	/* state2[0,1,2,3] = state2[2,3,0,1] */
+	pshufd		$0x4e,state2,state2
+	/* state3[0,1,2,3] = state3[1,2,3,0] */
+	pshufd		$0x39,state3,state3
+
+	decb		i
+	jnz		.Lpermute
+
+	/* output0 = state0 + copy0 */
+	paddd		copy0,state0
+	movups		state0,0x00(output)
+	/* output1 = state1 + copy1 */
+	paddd		copy1,state1
+	movups		state1,0x10(output)
+	/* output2 = state2 + copy2 */
+	paddd		copy2,state2
+	movups		state2,0x20(output)
+	/* output3 = state3 + copy3 */
+	paddd		copy3,state3
+	movups		state3,0x30(output)
+
+	/* ++copy3.counter */
+	paddq		one,copy3
+
+	/* output += 64, --nblocks */
+	addq		$64,output
+	decq		nblocks
+	jnz		.Lblock
+
+	/* counter = copy3.counter */
+	movq		copy3,0x00(counter)
+
+	/* Zero out the potentially sensitive regs, in case nothing uses these again. */
+	pxor		state0,state0
+	pxor		state1,state1
+	pxor		state2,state2
+	pxor		state3,state3
+	pxor		copy1,copy1
+	pxor		copy2,copy2
+	pxor		temp,temp
+
+	ret
+SYM_FUNC_END(__arch_chacha20_blocks_nostack)

linux-7.2.3/arch/x86/entry/vdso/vdso64/vgetrandom.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+#include <linux/types.h>
+
+#include "lib/vdso/getrandom.c"
+
+ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+	return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len);
+}
+
+ssize_t getrandom(void *, size_t, unsigned int, void *, size_t)
+	__attribute__((weak, alias("__vdso_getrandom")));

linux-7.2.3/arch/x86/entry/vdso/vdso64/vsgx.S

@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/enclu.h>
+
+#include "extable.h"
+
+/* Relative to %rbp. */
+#define SGX_ENCLAVE_OFFSET_OF_RUN		16
+
+/* The offsets relative to struct sgx_enclave_run. */
+#define SGX_ENCLAVE_RUN_TCS			0
+#define SGX_ENCLAVE_RUN_LEAF			8
+#define SGX_ENCLAVE_RUN_EXCEPTION_VECTOR	12
+#define SGX_ENCLAVE_RUN_EXCEPTION_ERROR_CODE	14
+#define SGX_ENCLAVE_RUN_EXCEPTION_ADDR		16
+#define SGX_ENCLAVE_RUN_USER_HANDLER		24
+#define SGX_ENCLAVE_RUN_USER_DATA		32	/* not used */
+#define SGX_ENCLAVE_RUN_RESERVED_START		40
+#define SGX_ENCLAVE_RUN_RESERVED_END		256
+
+.code64
+.section .text, "ax"
+
+SYM_FUNC_START(__vdso_sgx_enter_enclave)
+	/* Prolog */
+	.cfi_startproc
+	push	%rbp
+	.cfi_adjust_cfa_offset	8
+	.cfi_rel_offset		%rbp, 0
+	mov	%rsp, %rbp
+	.cfi_def_cfa_register	%rbp
+	push	%rbx
+	.cfi_rel_offset		%rbx, -8
+
+	mov	%ecx, %eax
+.Lenter_enclave:
+	/* EENTER <= function <= ERESUME */
+	cmp	$EENTER, %eax
+	jb	.Linvalid_input
+	cmp	$ERESUME, %eax
+	ja	.Linvalid_input
+
+	mov	SGX_ENCLAVE_OFFSET_OF_RUN(%rbp), %rcx
+
+	/* Validate that the reserved area contains only zeros. */
+	mov	$SGX_ENCLAVE_RUN_RESERVED_START, %rbx
+1:
+	cmpq	$0, (%rcx, %rbx)
+	jne	.Linvalid_input
+	add	$8, %rbx
+	cmpq	$SGX_ENCLAVE_RUN_RESERVED_END, %rbx
+	jne	1b
+
+	/* Load TCS and AEP */
+	mov	SGX_ENCLAVE_RUN_TCS(%rcx), %rbx
+	lea	.Lasync_exit_pointer(%rip), %rcx
+
+	/* Single ENCLU serving as both EENTER and AEP (ERESUME) */
+.Lasync_exit_pointer:
+.Lenclu_eenter_eresume:
+	enclu
+
+	/* EEXIT jumps here unless the enclave is doing something fancy. */
+	mov	SGX_ENCLAVE_OFFSET_OF_RUN(%rbp), %rbx
+
+	/* Set exit_reason. */
+	movl	$EEXIT, SGX_ENCLAVE_RUN_LEAF(%rbx)
+
+	/* Invoke userspace's exit handler if one was provided. */
+.Lhandle_exit:
+	cmpq	$0, SGX_ENCLAVE_RUN_USER_HANDLER(%rbx)
+	jne	.Linvoke_userspace_handler
+
+	/* Success, in the sense that ENCLU was attempted. */
+	xor	%eax, %eax
+
+.Lout:
+	pop	%rbx
+	leave
+	.cfi_def_cfa		%rsp, 8
+	RET
+
+	/* The out-of-line code runs with the pre-leave stack frame. */
+	.cfi_def_cfa		%rbp, 16
+
+.Linvalid_input:
+	mov	$(-EINVAL), %eax
+	jmp	.Lout
+
+.Lhandle_exception:
+	mov	SGX_ENCLAVE_OFFSET_OF_RUN(%rbp), %rbx
+
+	/* Set the exception info. */
+	mov	%eax, (SGX_ENCLAVE_RUN_LEAF)(%rbx)
+	mov	%di,  (SGX_ENCLAVE_RUN_EXCEPTION_VECTOR)(%rbx)
+	mov	%si,  (SGX_ENCLAVE_RUN_EXCEPTION_ERROR_CODE)(%rbx)
+	mov	%rdx, (SGX_ENCLAVE_RUN_EXCEPTION_ADDR)(%rbx)
+	jmp	.Lhandle_exit
+
+.Linvoke_userspace_handler:
+	/* Pass the untrusted RSP (at exit) to the callback via %rcx. */
+	mov	%rsp, %rcx
+
+	/* Save struct sgx_enclave_exception %rbx is about to be clobbered. */
+	mov	%rbx, %rax
+
+	/* Save the untrusted RSP offset in %rbx (non-volatile register). */
+	mov	%rsp, %rbx
+	and	$0xf, %rbx
+
+	/*
+	 * Align stack per x86_64 ABI. Note, %rsp needs to be 16-byte aligned
+	 * _after_ pushing the parameters on the stack, hence the bonus push.
+	 */
+	and	$-0x10, %rsp
+	push	%rax
+
+	/* Push struct sgx_enclave_exception as a param to the callback. */
+	push	%rax
+
+	/* Clear RFLAGS.DF per x86_64 ABI */
+	cld
+
+	/*
+	 * Load the callback pointer to %rax and lfence for LVI (load value
+	 * injection) protection before making the call.
+	 */
+	mov	SGX_ENCLAVE_RUN_USER_HANDLER(%rax), %rax
+	lfence
+	call	*%rax
+
+	/* Undo the post-exit %rsp adjustment. */
+	lea	0x10(%rsp, %rbx), %rsp
+
+	/*
+	 * If the return from callback is zero or negative, return immediately,
+	 * else re-execute ENCLU with the positive return value interpreted as
+	 * the requested ENCLU function.
+	 */
+	cmp	$0, %eax
+	jle	.Lout
+	jmp	.Lenter_enclave
+
+	.cfi_endproc
+
+_ASM_VDSO_EXTABLE_HANDLE(.Lenclu_eenter_eresume, .Lhandle_exception)
+
+SYM_FUNC_END(__vdso_sgx_enter_enclave)

linux-7.2.3/arch/x86/entry/vdso/vma.c

@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2007 Andi Kleen, SUSE Labs.
+ *
+ * This contains most of the x86 vDSO kernel-side code.
+ */
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/futex.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <linux/elf.h>
+#include <linux/cpu.h>
+#include <linux/ptrace.h>
+#include <linux/vdso_datastore.h>
+
+#include <asm/pvclock.h>
+#include <asm/vgtod.h>
+#include <asm/proto.h>
+#include <asm/vdso.h>
+#include <asm/tlb.h>
+#include <asm/page.h>
+#include <asm/desc.h>
+#include <asm/cpufeature.h>
+#include <asm/vdso/vsyscall.h>
+#include <clocksource/hyperv_timer.h>
+
+static_assert(VDSO_NR_PAGES + VDSO_NR_VCLOCK_PAGES == __VDSO_PAGES);
+
+unsigned int vclocks_used __read_mostly;
+
+#if defined(CONFIG_X86_64)
+unsigned int __read_mostly vdso64_enabled = 1;
+#endif
+
+int __init init_vdso_image(const struct vdso_image *image)
+{
+	BUILD_BUG_ON(VDSO_CLOCKMODE_MAX >= 32);
+	BUG_ON(image->size % PAGE_SIZE != 0);
+
+	apply_alternatives((struct alt_instr *)(image->data + image->alt),
+			   (struct alt_instr *)(image->data + image->alt +
+						image->alt_len));
+
+	return 0;
+}
+
+struct linux_binprm;
+
+static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+
+	if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
+	get_page(vmf->page);
+	return 0;
+}
+
+static void vdso_fix_landing(const struct vdso_image *image,
+		struct vm_area_struct *new_vma)
+{
+	struct pt_regs *regs = current_pt_regs();
+	unsigned long ipoffset = regs->ip -
+		(unsigned long)current->mm->context.vdso;
+
+	if (ipoffset < image->size)
+		regs->ip = new_vma->vm_start + ipoffset;
+}
+
+#ifdef CONFIG_FUTEX_ROBUST_UNLOCK
+static void vdso_futex_robust_unlock_update_ips(void)
+{
+	const struct vdso_image *image = current->mm->context.vdso_image;
+	unsigned long vdso = (unsigned long) current->mm->context.vdso;
+	struct futex_mm_data *fd = &current->mm->futex;
+	unsigned int idx = 0;
+
+	futex_reset_cs_ranges(fd);
+
+#ifdef CONFIG_X86_64
+	futex_set_vdso_cs_range(fd, idx, vdso + image->sym___futex_list64_try_unlock_cs_start,
+				vdso + image->sym___futex_list64_try_unlock_cs_end, false);
+	idx++;
+#endif /* CONFIG_X86_64 */
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+	futex_set_vdso_cs_range(fd, idx, vdso + image->sym___futex_list32_try_unlock_cs_start,
+				vdso + image->sym___futex_list32_try_unlock_cs_end, true);
+#endif /* CONFIG_X86_32 || CONFIG_COMPAT */
+}
+#else
+static inline void vdso_futex_robust_unlock_update_ips(void) { }
+#endif
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
+{
+	const struct vdso_image *image = current->mm->context.vdso_image;
+
+	vdso_fix_landing(image, new_vma);
+	current->mm->context.vdso = (void __user *)new_vma->vm_start;
+	vdso_futex_robust_unlock_update_ips();
+
+	return 0;
+}
+
+static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm,
+				    struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	switch (vmf->pgoff) {
+	case VDSO_PAGE_PVCLOCK_OFFSET:
+	{
+		struct pvclock_vsyscall_time_info *pvti =
+			pvclock_get_pvti_cpu0_va();
+
+		if (pvti && vclock_was_used(VDSO_CLOCKMODE_PVCLOCK))
+			return vmf_insert_pfn_prot(vma, vmf->address,
+					__pa(pvti) >> PAGE_SHIFT,
+					pgprot_decrypted(vma->vm_page_prot));
+		break;
+	}
+	case VDSO_PAGE_HVCLOCK_OFFSET:
+	{
+		unsigned long pfn = hv_get_tsc_pfn();
+		if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK))
+			return vmf_insert_pfn(vma, vmf->address, pfn);
+		break;
+	}
+	}
+
+	return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_special_mapping vdso_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+	.mremap = vdso_mremap,
+};
+static const struct vm_special_mapping vvar_vclock_mapping = {
+	.name = "[vvar_vclock]",
+	.fault = vvar_vclock_fault,
+};
+
+/*
+ * Add vdso and vvar mappings to current process.
+ * @image          - blob to map
+ * @addr           - request a specific address (zero to map at free addr)
+ */
+static int map_vdso(const struct vdso_image *image, unsigned long addr)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long text_start;
+	int ret = 0;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	addr = get_unmapped_area(NULL, addr,
+				 image->size + __VDSO_PAGES * PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	text_start = addr + __VDSO_PAGES * PAGE_SIZE;
+
+	/*
+	 * MAYWRITE to allow gdb to COW and set breakpoints
+	 */
+	vma = _install_special_mapping(mm,
+				       text_start,
+				       image->size,
+				       VM_READ|VM_EXEC|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				       VM_SEALED_SYSMAP,
+				       &vdso_mapping);
+
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto up_fail;
+	}
+
+	vma = vdso_install_vvar_mapping(mm, addr);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		do_munmap(mm, text_start, image->size, NULL);
+		goto up_fail;
+	}
+
+	vma = _install_special_mapping(mm,
+				       VDSO_VCLOCK_PAGES_START(addr),
+				       VDSO_NR_VCLOCK_PAGES * PAGE_SIZE,
+				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+				       VM_PFNMAP|VM_SEALED_SYSMAP,
+				       &vvar_vclock_mapping);
+
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		do_munmap(mm, text_start, image->size, NULL);
+		do_munmap(mm, addr, VDSO_NR_PAGES * PAGE_SIZE, NULL);
+		goto up_fail;
+	}
+
+	current->mm->context.vdso = (void __user *)text_start;
+	current->mm->context.vdso_image = image;
+
+	vdso_futex_robust_unlock_update_ips();
+
+up_fail:
+	mmap_write_unlock(mm);
+	return ret;
+}
+
+int map_vdso_once(const struct vdso_image *image, unsigned long addr)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	mmap_write_lock(mm);
+	/*
+	 * Check if we have already mapped vdso blob - fail to prevent
+	 * abusing from userspace install_special_mapping, which may
+	 * not do accounting and rlimit right.
+	 * We could search vma near context.vdso, but it's a slowpath,
+	 * so let's explicitly check all VMAs to be completely sure.
+	 */
+	for_each_vma(vmi, vma) {
+		if (vma_is_special_mapping(vma, &vdso_mapping) ||
+				vma_is_special_mapping(vma, &vdso_vvar_mapping) ||
+				vma_is_special_mapping(vma, &vvar_vclock_mapping)) {
+			mmap_write_unlock(mm);
+			return -EEXIST;
+		}
+	}
+	mmap_write_unlock(mm);
+
+	return map_vdso(image, addr);
+}
+
+static int load_vdso32(void)
+{
+	if (vdso32_enabled != 1)  /* Other values all mean "disabled" */
+		return 0;
+
+	return map_vdso(&vdso32_image, 0);
+}
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		if (!vdso64_enabled)
+			return 0;
+
+		return map_vdso(&vdso64_image, 0);
+	}
+
+	return load_vdso32();
+}
+
+#ifdef CONFIG_COMPAT
+int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp, bool x32)
+{
+	if (IS_ENABLED(CONFIG_X86_X32_ABI) && x32) {
+		if (!vdso64_enabled)
+			return 0;
+		return map_vdso(&vdsox32_image, 0);
+	}
+
+	if (IS_ENABLED(CONFIG_IA32_EMULATION))
+		return load_vdso32();
+
+	return 0;
+}
+#endif
+
+bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
+{
+	const struct vdso_image *image = current->mm->context.vdso_image;
+	unsigned long vdso = (unsigned long) current->mm->context.vdso;
+
+	if (in_ia32_syscall() && image == &vdso32_image) {
+		if (regs->ip == vdso + image->sym_vdso32_sigreturn_landing_pad ||
+		    regs->ip == vdso + image->sym_vdso32_rt_sigreturn_landing_pad)
+			return true;
+	}
+	return false;
+}
+
+#ifdef CONFIG_X86_64
+static __init int vdso_setup(char *s)
+{
+	vdso64_enabled = simple_strtoul(s, NULL, 0);
+	return 1;
+}
+__setup("vdso=", vdso_setup);
+#endif /* CONFIG_X86_64 */