Merge tag 'x86_sgx_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SGC support from Borislav Petkov:
 "Intel Software Guard eXtensions enablement. This has been long in the
  making, we were one revision number short of 42. :)

  Intel SGX is new hardware functionality that can be used by
  applications to populate protected regions of user code and data
  called enclaves. Once activated, the new hardware protects enclave
  code and data from outside access and modification.

  Enclaves provide a place to store secrets and process data with those
  secrets. SGX has been used, for example, to decrypt video without
  exposing the decryption keys to nosy debuggers that might be used to
  subvert DRM. Software has generally been rewritten specifically to run
  in enclaves, but there are also projects that try to run limited
  unmodified software in enclaves.

  Most of the functionality is concentrated into arch/x86/kernel/cpu/sgx/
  except the addition of a new mprotect() hook to control enclave page
  permissions and support for vDSO exceptions fixup which will is used
  by SGX enclaves.

  All this work by Sean Christopherson, Jarkko Sakkinen and many others"

* tag 'x86_sgx_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  x86/sgx: Return -EINVAL on a zero length buffer in sgx_ioc_enclave_add_pages()
  x86/sgx: Fix a typo in kernel-doc markup
  x86/sgx: Fix sgx_ioc_enclave_provision() kernel-doc comment
  x86/sgx: Return -ERESTARTSYS in sgx_ioc_enclave_add_pages()
  selftests/sgx: Use a statically generated 3072-bit RSA key
  x86/sgx: Clarify 'laundry_list' locking
  x86/sgx: Update MAINTAINERS
  Documentation/x86: Document SGX kernel architecture
  x86/sgx: Add ptrace() support for the SGX driver
  x86/sgx: Add a page reclaimer
  selftests/x86: Add a selftest for SGX
  x86/vdso: Implement a vDSO for Intel SGX enclave call
  x86/traps: Attempt to fixup exceptions in vDSO before signaling
  x86/fault: Add a helper function to sanitize error code
  x86/vdso: Add support for exception fixup in vDSO functions
  x86/sgx: Add SGX_IOC_ENCLAVE_PROVISION
  x86/sgx: Add SGX_IOC_ENCLAVE_INIT
  x86/sgx: Add SGX_IOC_ENCLAVE_ADD_PAGES
  x86/sgx: Add SGX_IOC_ENCLAVE_CREATE
  x86/sgx: Add an SGX misc driver interface
  ...

7 files changed, 288 insertions, 5 deletions

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 21243747965d..02e3e42f380b 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -27,9 +27,10 @@ VDSO32-$(CONFIG_IA32_EMULATION)	:= y
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
 vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
 vobjs32-y += vdso32/vclock_gettime.o
+vobjs-$(CONFIG_X86_SGX)	+= vsgx.o
 
 # files to link into kernel
-obj-y				+= vma.o
+obj-y				+= vma.o extable.o
 KASAN_SANITIZE_vma.o		:= y
 UBSAN_SANITIZE_vma.o		:= y
 KCSAN_SANITIZE_vma.o		:= y
@@ -98,6 +99,7 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS
 CFLAGS_REMOVE_vclock_gettime.o = -pg
 CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg
 CFLAGS_REMOVE_vgetcpu.o = -pg
+CFLAGS_REMOVE_vsgx.o = -pg
 
 #
 # X32 processes use x32 vDSO to access 64bit kernel data.
@@ -128,8 +130,8 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE
 
 targets += vdsox32.lds $(vobjx32s-y)
 
-$(obj)/%.so: OBJCOPYFLAGS := -S
-$(obj)/%.so: $(obj)/%.so.dbg FORCE
+$(obj)/%.so: OBJCOPYFLAGS := -S --remove-section __ex_table
+$(obj)/%.so: $(obj)/%.so.dbg
 	$(call if_changed,objcopy)
 
 $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
diff --git a/arch/x86/entry/vdso/extable.c b/arch/x86/entry/vdso/extable.c
new file mode 100644
index 000000000000..afcf5b65beef
--- /dev/null
+++ b/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;
+}
diff --git a/arch/x86/entry/vdso/extable.h b/arch/x86/entry/vdso/extable.h
new file mode 100644
index 000000000000..b56f6b012941
--- /dev/null
+++ b/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 __ASSEMBLY__
+#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 */
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 4d152933547d..dc8da7695859 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -75,11 +75,18 @@ SECTIONS
 	 * stuff that isn't used at runtime in between.
 	 */
 
-	.text		: { *(.text*) }			:text	=0x90909090,
+	.text		: {
+		*(.text*)
+		*(.fixup)
+	}						:text	=0x90909090,
+
+
 
 	.altinstructions	: { *(.altinstructions) }	:text
 	.altinstr_replacement	: { *(.altinstr_replacement) }	:text
 
+	__ex_table		: { *(__ex_table) }		:text
+
 	/DISCARD/ : {
 		*(.discard)
 		*(.discard.*)
diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
index 36b644e16272..4bf48462fca7 100644
--- a/arch/x86/entry/vdso/vdso.lds.S
+++ b/arch/x86/entry/vdso/vdso.lds.S
@@ -27,6 +27,7 @@ VERSION {
 		__vdso_time;
 		clock_getres;
 		__vdso_clock_getres;
+		__vdso_sgx_enter_enclave;
 	local: *;
 	};
 }
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 6f46e11ce539..1c7cfac7e64a 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -5,6 +5,41 @@
  * are built for 32-bit userspace.
  */
 
+static void BITSFUNC(copy)(FILE *outfile, const unsigned char *data, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (i % 10 == 0)
+			fprintf(outfile, "\n\t");
+		fprintf(outfile, "0x%02X, ", (int)(data)[i]);
+	}
+}
+
+
+/*
+ * Extract a section from the input data into a standalone blob.  Used to
+ * capture kernel-only data that needs to persist indefinitely, e.g. the
+ * exception fixup tables, but only in the kernel, i.e. the section can
+ * be stripped from the final vDSO image.
+ */
+static void BITSFUNC(extract)(const unsigned char *data, size_t data_len,
+			      FILE *outfile, ELF(Shdr) *sec, const char *name)
+{
+	unsigned long offset;
+	size_t len;
+
+	offset = (unsigned long)GET_LE(&sec->sh_offset);
+	len = (size_t)GET_LE(&sec->sh_size);
+
+	if (offset + len > data_len)
+		fail("section to extract overruns input data");
+
+	fprintf(outfile, "static const unsigned char %s[%lu] = {", name, len);
+	BITSFUNC(copy)(outfile, data + offset, len);
+	fprintf(outfile, "\n};\n\n");
+}
+
 static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 			 void *stripped_addr, size_t stripped_len,
 			 FILE *outfile, const char *image_name)
@@ -15,7 +50,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
 	unsigned long i, syms_nr;
 	ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
-		*alt_sec = NULL;
+		*alt_sec = NULL, *extable_sec = NULL;
 	ELF(Dyn) *dyn = 0, *dyn_end = 0;
 	const char *secstrings;
 	INT_BITS syms[NSYMS] = {};
@@ -77,6 +112,8 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		if (!strcmp(secstrings + GET_LE(&sh->sh_name),
 			    ".altinstructions"))
 			alt_sec = sh;
+		if (!strcmp(secstrings + GET_LE(&sh->sh_name), "__ex_table"))
+			extable_sec = sh;
 	}
 
 	if (!symtab_hdr)
@@ -155,6 +192,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 			(int)((unsigned char *)stripped_addr)[i]);
 	}
 	fprintf(outfile, "\n};\n\n");
+	if (extable_sec)
+		BITSFUNC(extract)(raw_addr, raw_len, outfile,
+				  extable_sec, "extable");
 
 	fprintf(outfile, "const struct vdso_image %s = {\n", image_name);
 	fprintf(outfile, "\t.data = raw_data,\n");
@@ -165,6 +205,14 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		fprintf(outfile, "\t.alt_len = %lu,\n",
 			(unsigned long)GET_LE(&alt_sec->sh_size));
 	}
+	if (extable_sec) {
+		fprintf(outfile, "\t.extable_base = %lu,\n",
+			(unsigned long)GET_LE(&extable_sec->sh_offset));
+		fprintf(outfile, "\t.extable_len = %lu,\n",
+			(unsigned long)GET_LE(&extable_sec->sh_size));
+		fprintf(outfile, "\t.extable = extable,\n");
+	}
+
 	for (i = 0; i < NSYMS; i++) {
 		if (required_syms[i].export && syms[i])
 			fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n",
diff --git a/arch/x86/entry/vdso/vsgx.S b/arch/x86/entry/vdso/vsgx.S
new file mode 100644
index 000000000000..86a0e94f68df
--- /dev/null
+++ b/arch/x86/entry/vdso/vsgx.S
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/export.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 postive 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)