aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorLinus Torvalds2020-12-14 13:14:57 -0800
committerLinus Torvalds2020-12-14 13:14:57 -0800
commit5583ff677b3108cde989b6d4fd1958e091420c0c (patch)
treee332c763919d1952b1ae57836f9393c766d27266 /arch/x86
parent85fe40cad2dae9e0439ea6f92fde9c5e9c58f09b (diff)
parenta4b9c48b96517ff4780b22a784e7537eac5dc21b (diff)
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 ...
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig17
-rw-r--r--arch/x86/entry/vdso/Makefile8
-rw-r--r--arch/x86/entry/vdso/extable.c46
-rw-r--r--arch/x86/entry/vdso/extable.h28
-rw-r--r--arch/x86/entry/vdso/vdso-layout.lds.S9
-rw-r--r--arch/x86/entry/vdso/vdso.lds.S1
-rw-r--r--arch/x86/entry/vdso/vdso2c.h50
-rw-r--r--arch/x86/entry/vdso/vsgx.S151
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/disabled-features.h8
-rw-r--r--arch/x86/include/asm/enclu.h9
-rw-r--r--arch/x86/include/asm/msr-index.h8
-rw-r--r--arch/x86/include/asm/trap_pf.h2
-rw-r--r--arch/x86/include/asm/vdso.h5
-rw-r--r--arch/x86/include/uapi/asm/sgx.h168
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/feat_ctl.c38
-rw-r--r--arch/x86/kernel/cpu/sgx/Makefile5
-rw-r--r--arch/x86/kernel/cpu/sgx/arch.h338
-rw-r--r--arch/x86/kernel/cpu/sgx/driver.c194
-rw-r--r--arch/x86/kernel/cpu/sgx/driver.h29
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.c740
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.h119
-rw-r--r--arch/x86/kernel/cpu/sgx/encls.h231
-rw-r--r--arch/x86/kernel/cpu/sgx/ioctl.c716
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c733
-rw-r--r--arch/x86/kernel/cpu/sgx/sgx.h86
-rw-r--r--arch/x86/kernel/traps.c10
-rw-r--r--arch/x86/mm/fault.c45
29 files changed, 3778 insertions, 19 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fbf26e0f7a6a..52e36adb5112 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1931,6 +1931,23 @@ config X86_INTEL_TSX_MODE_AUTO
side channel attacks- equals the tsx=auto command line parameter.
endchoice
+config X86_SGX
+ bool "Software Guard eXtensions (SGX)"
+ depends on X86_64 && CPU_SUP_INTEL
+ depends on CRYPTO=y
+ depends on CRYPTO_SHA256=y
+ select SRCU
+ select MMU_NOTIFIER
+ help
+ Intel(R) Software Guard eXtensions (SGX) is a set of CPU instructions
+ that can be used by applications to set aside private regions of code
+ and data, referred to as enclaves. An enclave's private memory can
+ only be accessed by code running within the enclave. Accesses from
+ outside the enclave, including other enclaves, are disallowed by
+ hardware.
+
+ If unsure, say N.
+
config EFI
bool "EFI runtime service support"
depends on ACPI
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)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index dad350d42ecf..f5ef2d5b9231 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -241,6 +241,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */
#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
@@ -356,6 +357,7 @@
#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */
+#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 5861d34f9771..7947cb1782da 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -62,6 +62,12 @@
# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
#endif
+#ifdef CONFIG_X86_SGX
+# define DISABLE_SGX 0
+#else
+# define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -74,7 +80,7 @@
#define DISABLED_MASK6 0
#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
-#define DISABLED_MASK9 (DISABLE_SMAP)
+#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX)
#define DISABLED_MASK10 0
#define DISABLED_MASK11 0
#define DISABLED_MASK12 0
diff --git a/arch/x86/include/asm/enclu.h b/arch/x86/include/asm/enclu.h
new file mode 100644
index 000000000000..b1314e41a744
--- /dev/null
+++ b/arch/x86/include/asm/enclu.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_ENCLU_H
+#define _ASM_X86_ENCLU_H
+
+#define EENTER 0x02
+#define ERESUME 0x03
+#define EEXIT 0x04
+
+#endif /* _ASM_X86_ENCLU_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b2dd2648c0e2..6a5085a5f9d8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -610,6 +610,8 @@
#define FEAT_CTL_LOCKED BIT(0)
#define FEAT_CTL_VMX_ENABLED_INSIDE_SMX BIT(1)
#define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX BIT(2)
+#define FEAT_CTL_SGX_LC_ENABLED BIT(17)
+#define FEAT_CTL_SGX_ENABLED BIT(18)
#define FEAT_CTL_LMCE_ENABLED BIT(20)
#define MSR_IA32_TSC_ADJUST 0x0000003b
@@ -629,6 +631,12 @@
#define MSR_IA32_UCODE_WRITE 0x00000079
#define MSR_IA32_UCODE_REV 0x0000008b
+/* Intel SGX Launch Enclave Public Key Hash MSRs */
+#define MSR_IA32_SGXLEPUBKEYHASH0 0x0000008C
+#define MSR_IA32_SGXLEPUBKEYHASH1 0x0000008D
+#define MSR_IA32_SGXLEPUBKEYHASH2 0x0000008E
+#define MSR_IA32_SGXLEPUBKEYHASH3 0x0000008F
+
#define MSR_IA32_SMM_MONITOR_CTL 0x0000009b
#define MSR_IA32_SMBASE 0x0000009e
diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h
index 305bc1214aef..10b1de500ab1 100644
--- a/arch/x86/include/asm/trap_pf.h
+++ b/arch/x86/include/asm/trap_pf.h
@@ -11,6 +11,7 @@
* bit 3 == 1: use of reserved bit detected
* bit 4 == 1: fault was an instruction fetch
* bit 5 == 1: protection keys block access
+ * bit 15 == 1: SGX MMU page-fault
*/
enum x86_pf_error_code {
X86_PF_PROT = 1 << 0,
@@ -19,6 +20,7 @@ enum x86_pf_error_code {
X86_PF_RSVD = 1 << 3,
X86_PF_INSTR = 1 << 4,
X86_PF_PK = 1 << 5,
+ X86_PF_SGX = 1 << 15,
};
#endif /* _ASM_X86_TRAP_PF_H */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index bbcdc7b8f963..b5d23470f56b 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -15,6 +15,8 @@ struct vdso_image {
unsigned long size; /* Always a multiple of PAGE_SIZE */
unsigned long alt, alt_len;
+ unsigned long extable_base, extable_len;
+ const void *extable;
long sym_vvar_start; /* Negative offset to the vvar area */
@@ -45,6 +47,9 @@ extern void __init init_vdso_image(const struct vdso_image *image);
extern int map_vdso_once(const struct vdso_image *image, unsigned long addr);
+extern bool fixup_vdso_exception(struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr);
#endif /* __ASSEMBLER__ */
#endif /* _ASM_X86_VDSO_H */
diff --git a/arch/x86/include/uapi/asm/sgx.h b/arch/x86/include/uapi/asm/sgx.h
new file mode 100644
index 000000000000..9034f3007c4e
--- /dev/null
+++ b/arch/x86/include/uapi/asm/sgx.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright(c) 2016-20 Intel Corporation.
+ */
+#ifndef _UAPI_ASM_X86_SGX_H
+#define _UAPI_ASM_X86_SGX_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/**
+ * enum sgx_page_flags - page control flags
+ * %SGX_PAGE_MEASURE: Measure the page contents with a sequence of
+ * ENCLS[EEXTEND] operations.
+ */
+enum sgx_page_flags {
+ SGX_PAGE_MEASURE = 0x01,
+};
+
+#define SGX_MAGIC 0xA4
+
+#define SGX_IOC_ENCLAVE_CREATE \
+ _IOW(SGX_MAGIC, 0x00, struct sgx_enclave_create)
+#define SGX_IOC_ENCLAVE_ADD_PAGES \
+ _IOWR(SGX_MAGIC, 0x01, struct sgx_enclave_add_pages)
+#define SGX_IOC_ENCLAVE_INIT \
+ _IOW(SGX_MAGIC, 0x02, struct sgx_enclave_init)
+#define SGX_IOC_ENCLAVE_PROVISION \
+ _IOW(SGX_MAGIC, 0x03, struct sgx_enclave_provision)
+
+/**
+ * struct sgx_enclave_create - parameter structure for the
+ * %SGX_IOC_ENCLAVE_CREATE ioctl
+ * @src: address for the SECS page data
+ */
+struct sgx_enclave_create {
+ __u64 src;
+};
+
+/**
+ * struct sgx_enclave_add_pages - parameter structure for the
+ * %SGX_IOC_ENCLAVE_ADD_PAGE ioctl
+ * @src: start address for the page data
+ * @offset: starting page offset
+ * @length: length of the data (multiple of the page size)
+ * @secinfo: address for the SECINFO data
+ * @flags: page control flags
+ * @count: number of bytes added (multiple of the page size)
+ */
+struct sgx_enclave_add_pages {
+ __u64 src;
+ __u64 offset;
+ __u64 length;
+ __u64 secinfo;
+ __u64 flags;
+ __u64 count;
+};
+
+/**
+ * struct sgx_enclave_init - parameter structure for the
+ * %SGX_IOC_ENCLAVE_INIT ioctl
+ * @sigstruct: address for the SIGSTRUCT data
+ */
+struct sgx_enclave_init {
+ __u64 sigstruct;
+};
+
+/**
+ * struct sgx_enclave_provision - parameter structure for the
+ * %SGX_IOC_ENCLAVE_PROVISION ioctl
+ * @fd: file handle of /dev/sgx_provision
+ */
+struct sgx_enclave_provision {
+ __u64 fd;
+};
+
+struct sgx_enclave_run;
+
+/**
+ * typedef sgx_enclave_user_handler_t - Exit handler function accepted by
+ * __vdso_sgx_enter_enclave()
+ * @run: The run instance given by the caller
+ *
+ * The register parameters contain the snapshot of their values at enclave
+ * exit. An invalid ENCLU function number will cause -EINVAL to be returned
+ * to the caller.
+ *
+ * Return:
+ * - <= 0: The given value is returned back to the caller.
+ * - > 0: ENCLU function to invoke, either EENTER or ERESUME.
+ */
+typedef int (*sgx_enclave_user_handler_t)(long rdi, long rsi, long rdx,
+ long rsp, long r8, long r9,
+ struct sgx_enclave_run *run);
+
+/**
+ * struct sgx_enclave_run - the execution context of __vdso_sgx_enter_enclave()
+ * @tcs: TCS used to enter the enclave
+ * @function: The last seen ENCLU function (EENTER, ERESUME or EEXIT)
+ * @exception_vector: The interrupt vector of the exception
+ * @exception_error_code: The exception error code pulled out of the stack
+ * @exception_addr: The address that triggered the exception
+ * @user_handler: User provided callback run on exception
+ * @user_data: Data passed to the user handler
+ * @reserved Reserved for future extensions
+ *
+ * If @user_handler is provided, the handler will be invoked on all return paths
+ * of the normal flow. The user handler may transfer control, e.g. via a
+ * longjmp() call or a C++ exception, without returning to
+ * __vdso_sgx_enter_enclave().
+ */
+struct sgx_enclave_run {
+ __u64 tcs;
+ __u32 function;
+ __u16 exception_vector;
+ __u16 exception_error_code;
+ __u64 exception_addr;
+ __u64 user_handler;
+ __u64 user_data;
+ __u8 reserved[216];
+};
+
+/**
+ * typedef vdso_sgx_enter_enclave_t - Prototype for __vdso_sgx_enter_enclave(),
+ * a vDSO function to enter an SGX enclave.
+ * @rdi: Pass-through value for RDI
+ * @rsi: Pass-through value for RSI
+ * @rdx: Pass-through value for RDX
+ * @function: ENCLU function, must be EENTER or ERESUME
+ * @r8: Pass-through value for R8
+ * @r9: Pass-through value for R9
+ * @run: struct sgx_enclave_run, must be non-NULL
+ *
+ * NOTE: __vdso_sgx_enter_enclave() does not ensure full compliance with the
+ * x86-64 ABI, e.g. doesn't handle XSAVE state. Except for non-volatile
+ * general purpose registers, EFLAGS.DF, and RSP alignment, preserving/setting
+ * state in accordance with the x86-64 ABI is the responsibility of the enclave
+ * and its runtime, i.e. __vdso_sgx_enter_enclave() cannot be called from C
+ * code without careful consideration by both the enclave and its runtime.
+ *
+ * All general purpose registers except RAX, RBX and RCX are passed as-is to the
+ * enclave. RAX, RBX and RCX are consumed by EENTER and ERESUME and are loaded
+ * with @function, asynchronous exit pointer, and @run.tcs respectively.
+ *
+ * RBP and the stack are used to anchor __vdso_sgx_enter_enclave() to the
+ * pre-enclave state, e.g. to retrieve @run.exception and @run.user_handler
+ * after an enclave exit. All other registers are available for use by the
+ * enclave and its runtime, e.g. an enclave can push additional data onto the
+ * stack (and modify RSP) to pass information to the optional user handler (see
+ * below).
+ *
+ * Most exceptions reported on ENCLU, including those that occur within the
+ * enclave, are fixed up and reported synchronously instead of being delivered
+ * via a standard signal. Debug Exceptions (#DB) and Breakpoints (#BP) are
+ * never fixed up and are always delivered via standard signals. On synchrously
+ * reported exceptions, -EFAULT is returned and details about the exception are
+ * recorded in @run.exception, the optional sgx_enclave_exception struct.
+ *
+ * Return:
+ * - 0: ENCLU function was successfully executed.
+ * - -EINVAL: Invalid ENCL number (neither EENTER nor ERESUME).
+ */
+typedef int (*vdso_sgx_enter_enclave_t)(unsigned long rdi, unsigned long rsi,
+ unsigned long rdx, unsigned int function,
+ unsigned long r8, unsigned long r9,
+ struct sgx_enclave_run *run);
+
+#endif /* _UAPI_ASM_X86_SGX_H */
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 93792b457b81..637b499450d1 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_X86_MCE) += mce/
obj-$(CONFIG_MTRR) += mtrr/
obj-$(CONFIG_MICROCODE) += microcode/
obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/
+obj-$(CONFIG_X86_SGX) += sgx/
obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 29a3bedabd06..3b1b01f2b248 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -93,16 +93,41 @@ static void init_vmx_capabilities(struct cpuinfo_x86 *c)
}
#endif /* CONFIG_X86_VMX_FEATURE_NAMES */
+static void clear_sgx_caps(void)
+{
+ setup_clear_cpu_cap(X86_FEATURE_SGX);
+ setup_clear_cpu_cap(X86_FEATURE_SGX_LC);
+}
+
+static int __init nosgx(char *str)
+{
+ clear_sgx_caps();
+
+ return 0;
+}
+
+early_param("nosgx", nosgx);
+
void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
{
bool tboot = tboot_enabled();
+ bool enable_sgx;
u64 msr;
if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) {
clear_cpu_cap(c, X86_FEATURE_VMX);
+ clear_sgx_caps();
return;
}
+ /*
+ * Enable SGX if and only if the kernel supports SGX and Launch Control
+ * is supported, i.e. disable SGX if the LE hash MSRs can't be written.
+ */
+ enable_sgx = cpu_has(c, X86_FEATURE_SGX) &&
+ cpu_has(c, X86_FEATURE_SGX_LC) &&
+ IS_ENABLED(CONFIG_X86_SGX);
+
if (msr & FEAT_CTL_LOCKED)
goto update_caps;
@@ -124,13 +149,16 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX;
}
+ if (enable_sgx)
+ msr |= FEAT_CTL_SGX_ENABLED | FEAT_CTL_SGX_LC_ENABLED;
+
wrmsrl(MSR_IA32_FEAT_CTL, msr);
update_caps:
set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL);
if (!cpu_has(c, X86_FEATURE_VMX))
- return;
+ goto update_sgx;
if ( (tboot && !(msr & FEAT_CTL_VMX_ENABLED_INSIDE_SMX)) ||
(!tboot && !(msr & FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX))) {
@@ -143,4 +171,12 @@ update_caps:
init_vmx_capabilities(c);
#endif
}
+
+update_sgx:
+ if (!(msr & FEAT_CTL_SGX_ENABLED) ||
+ !(msr & FEAT_CTL_SGX_LC_ENABLED) || !enable_sgx) {
+ if (enable_sgx)
+ pr_err_once("SGX disabled by BIOS\n");
+ clear_sgx_caps();
+ }
}
diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile
new file mode 100644
index 000000000000..91d3dc784a29
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/Makefile
@@ -0,0 +1,5 @@
+obj-y += \
+ driver.o \
+ encl.o \
+ ioctl.o \
+ main.o
diff --git a/arch/x86/kernel/cpu/sgx/arch.h b/arch/x86/kernel/cpu/sgx/arch.h
new file mode 100644
index 000000000000..dd7602c44c72
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/arch.h
@@ -0,0 +1,338 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+ * Copyright(c) 2016-20 Intel Corporation.
+ *
+ * Contains data structures defined by the SGX architecture. Data structures
+ * defined by the Linux software stack should not be placed here.
+ */
+#ifndef _ASM_X86_SGX_ARCH_H
+#define _ASM_X86_SGX_ARCH_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+/* The SGX specific CPUID function. */
+#define SGX_CPUID 0x12
+/* EPC enumeration. */
+#define SGX_CPUID_EPC 2
+/* An invalid EPC section, i.e. the end marker. */
+#define SGX_CPUID_EPC_INVALID 0x0
+/* A valid EPC section. */
+#define SGX_CPUID_EPC_SECTION 0x1
+/* The bitmask for the EPC section type. */
+#define SGX_CPUID_EPC_MASK GENMASK(3, 0)
+
+/**
+ * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
+ * %SGX_NOT_TRACKED: Previous ETRACK's shootdown sequence has not
+ * been completed yet.
+ * %SGX_INVALID_EINITTOKEN: EINITTOKEN is invalid and enclave signer's
+ * public key does not match IA32_SGXLEPUBKEYHASH.
+ * %SGX_UNMASKED_EVENT: An unmasked event, e.g. INTR, was received
+ */
+enum sgx_return_code {
+ SGX_NOT_TRACKED = 11,
+ SGX_INVALID_EINITTOKEN = 16,
+ SGX_UNMASKED_EVENT = 128,
+};
+
+/* The modulus size for 3072-bit RSA keys. */
+#define SGX_MODULUS_SIZE 384
+
+/**
+ * enum sgx_miscselect - additional information to an SSA frame
+ * %SGX_MISC_EXINFO: Report #PF or #GP to the SSA frame.
+ *
+ * Save State Area (SSA) is a stack inside the enclave used to store processor
+ * state when an exception or interrupt occurs. This enum defines additional
+ * information stored to an SSA frame.
+ */
+enum sgx_miscselect {
+ SGX_MISC_EXINFO = BIT(0),
+};
+
+#define SGX_MISC_RESERVED_MASK GENMASK_ULL(63, 1)
+
+#define SGX_SSA_GPRS_SIZE 184
+#define SGX_SSA_MISC_EXINFO_SIZE 16
+
+/**
+ * enum sgx_attributes - the attributes field in &struct sgx_secs
+ * %SGX_ATTR_INIT: Enclave can be entered (is initialized).
+ * %SGX_ATTR_DEBUG: Allow ENCLS(EDBGRD) and ENCLS(EDBGWR).
+ * %SGX_ATTR_MODE64BIT: Tell that this a 64-bit enclave.
+ * %SGX_ATTR_PROVISIONKEY: Allow to use provisioning keys for remote
+ * attestation.
+ * %SGX_ATTR_KSS: Allow to use key separation and sharing (KSS).
+ * %SGX_ATTR_EINITTOKENKEY: Allow to use token signing key that is used to
+ * sign cryptographic tokens that can be passed to
+ * EINIT as an authorization to run an enclave.
+ */
+enum sgx_attribute {
+ SGX_ATTR_INIT = BIT(0),
+ SGX_ATTR_DEBUG = BIT(1),
+ SGX_ATTR_MODE64BIT = BIT(2),
+ SGX_ATTR_PROVISIONKEY = BIT(4),
+ SGX_ATTR_EINITTOKENKEY = BIT(5),
+ SGX_ATTR_KSS = BIT(7),
+};
+
+#define SGX_ATTR_RESERVED_MASK (BIT_ULL(3) | BIT_ULL(6) | GENMASK_ULL(63, 8))
+
+/**
+ * struct sgx_secs - SGX Enclave Control Structure (SECS)
+ * @size: size of the address space
+ * @base: base address of the address space
+ * @ssa_frame_size: size of an SSA frame
+ * @miscselect: additional information stored to an SSA frame
+ * @attributes: attributes for enclave
+ * @xfrm: XSave-Feature Request Mask (subset of XCR0)
+ * @mrenclave: SHA256-hash of the enclave contents
+ * @mrsigner: SHA256-hash of the public key used to sign the SIGSTRUCT
+ * @config_id: a user-defined value that is used in key derivation
+ * @isv_prod_id: a user-defined value that is used in key derivation
+ * @isv_svn: a user-defined value that is used in key derivation
+ * @config_svn: a user-defined value that is used in key derivation
+ *
+ * SGX Enclave Control Structure (SECS) is a special enclave page that is not
+ * visible in the address space. In fact, this structure defines the address
+ * range and other global attributes for the enclave and it is the first EPC
+ * page created for any enclave. It is moved from a temporary buffer to an EPC
+ * by the means of ENCLS[ECREATE] function.
+ */
+struct sgx_secs {
+ u64 size;
+ u64 base;
+ u32 ssa_frame_size;
+ u32 miscselect;
+ u8 reserved1[24];
+ u64 attributes;
+ u64 xfrm;
+ u32 mrenclave[8];
+ u8 reserved2[32];
+ u32 mrsigner[8];
+ u8 reserved3[32];
+ u32 config_id[16];
+ u16 isv_prod_id;
+ u16 isv_svn;
+ u16 config_svn;
+ u8 reserved4[3834];
+} __packed;
+
+/**
+ * enum sgx_tcs_flags - execution flags for TCS
+ * %SGX_TCS_DBGOPTIN: If enabled allows single-stepping and breakpoints
+ * inside an enclave. It is cleared by EADD but can
+ * be set later with EDBGWR.
+ */
+enum sgx_tcs_flags {
+ SGX_TCS_DBGOPTIN = 0x01,
+};
+
+#define SGX_TCS_RESERVED_MASK GENMASK_ULL(63, 1)
+#define SGX_TCS_RESERVED_SIZE 4024
+
+/**
+ * struct sgx_tcs - Thread Control Structure (TCS)
+ * @state: used to mark an entered TCS
+ * @flags: execution flags (cleared by EADD)
+ * @ssa_offset: SSA stack offset relative to the enclave base
+ * @ssa_index: the current SSA frame index (cleard by EADD)
+ * @nr_ssa_frames: the number of frame in the SSA stack
+ * @entry_offset: entry point offset relative to the enclave base
+ * @exit_addr: address outside the enclave to exit on an exception or
+ * interrupt
+ * @fs_offset: offset relative to the enclave base to become FS
+ * segment inside the enclave
+ * @gs_offset: offset relative to the enclave base to become GS
+ * segment inside the enclave
+ * @fs_limit: size to become a new FS-limit (only 32-bit enclaves)
+ * @gs_limit: size to become a new GS-limit (only 32-bit enclaves)
+ *
+ * Thread Control Structure (TCS) is an enclave page visible in its address
+ * space that defines an entry point inside the enclave. A thread enters inside
+ * an enclave by supplying address of TCS to ENCLU(EENTER). A TCS can be entered
+ * by only one thread at a time.
+ */
+struct sgx_tcs {
+ u64 state;
+ u64 flags;
+ u64 ssa_offset;
+ u32 ssa_index;
+ u32 nr_ssa_frames;
+ u64 entry_offset;
+ u64 exit_addr;
+ u64 fs_offset;
+ u64 gs_offset;
+ u32 fs_limit;
+ u32 gs_limit;
+ u8 reserved[SGX_TCS_RESERVED_SIZE];
+} __packed;
+
+/**
+ * struct sgx_pageinfo - an enclave page descriptor
+ * @addr: address of the enclave page
+ * @contents: pointer to the page contents
+ * @metadata: pointer either to a SECINFO or PCMD instance
+ * @secs: address of the SECS page
+ */
+struct sgx_pageinfo {
+ u64 addr;
+ u64 contents;
+ u64 metadata;
+ u64 secs;
+} __packed __aligned(32);
+
+
+/**
+ * enum sgx_page_type - bits in the SECINFO flags defining the page type
+ * %SGX_PAGE_TYPE_SECS: a SECS page
+ * %SGX_PAGE_TYPE_TCS: a TCS page
+ * %SGX_PAGE_TYPE_REG: a regular page
+ * %SGX_PAGE_TYPE_VA: a VA page
+ * %SGX_PAGE_TYPE_TRIM: a page in trimmed state
+ */
+enum sgx_page_type {
+ SGX_PAGE_TYPE_SECS,
+ SGX_PAGE_TYPE_TCS,
+ SGX_PAGE_TYPE_REG,
+ SGX_PAGE_TYPE_VA,
+ SGX_PAGE_TYPE_TRIM,
+};
+
+#define SGX_NR_PAGE_TYPES 5
+#define SGX_PAGE_TYPE_MASK GENMASK(7, 0)
+
+/**
+ * enum sgx_secinfo_flags - the flags field in &struct sgx_secinfo
+ * %SGX_SECINFO_R: allow read
+ * %SGX_SECINFO_W: allow write
+ * %SGX_SECINFO_X: allow execution
+ * %SGX_SECINFO_SECS: a SECS page
+ * %SGX_SECINFO_TCS: a TCS page
+ * %SGX_SECINFO_REG: a regular page
+ * %SGX_SECINFO_VA: a VA page
+ * %SGX_SECINFO_TRIM: a page in trimmed state
+ */
+enum sgx_secinfo_flags {
+ SGX_SECINFO_R = BIT(0),
+ SGX_SECINFO_W = BIT(1),
+ SGX_SECINFO_X = BIT(2),
+ SGX_SECINFO_SECS = (SGX_PAGE_TYPE_SECS << 8),
+ SGX_SECINFO_TCS = (SGX_PAGE_TYPE_TCS << 8),
+ SGX_SECINFO_REG = (SGX_PAGE_TYPE_REG << 8),
+ SGX_SECINFO_VA = (SGX_PAGE_TYPE_VA << 8),
+ SGX_SECINFO_TRIM = (SGX_PAGE_TYPE_TRIM << 8),
+};
+
+#define SGX_SECINFO_PERMISSION_MASK GENMASK_ULL(2, 0)
+#define SGX_SECINFO_PAGE_TYPE_MASK (SGX_PAGE_TYPE_MASK << 8)
+#define SGX_SECINFO_RESERVED_MASK ~(SGX_SECINFO_PERMISSION_MASK | \
+ SGX_SECINFO_PAGE_TYPE_MASK)
+
+/**
+ * struct sgx_secinfo - describes attributes of an EPC page
+ * @flags: permissions and type
+ *
+ * Used together with ENCLS leaves that add or modify an EPC page to an
+ * enclave to define page permissions and type.
+ */
+struct sgx_secinfo {
+ u64 flags;
+ u8 reserved[56];
+} __packed __aligned(64);
+
+#define SGX_PCMD_RESERVED_SIZE 40
+
+/**
+ * struct sgx_pcmd - Paging Crypto Metadata (PCMD)
+ * @enclave_id: enclave identifier
+ * @mac: MAC over PCMD, page contents and isvsvn
+ *
+ * PCMD is stored for every swapped page to the regular memory. When ELDU loads
+ * the page back it recalculates the MAC by using a isvsvn number stored in a
+ * VA page. Together these two structures bring integrity and rollback
+ * protection.
+ */
+struct sgx_pcmd {
+ struct sgx_secinfo secinfo;
+ u64 enclave_id;
+ u8 reserved[SGX_PCMD_RESERVED_SIZE];
+ u8 mac[16];
+} __packed __aligned(128);
+
+#define SGX_SIGSTRUCT_RESERVED1_SIZE 84
+#define SGX_SIGSTRUCT_RESERVED2_SIZE 20
+#define SGX_SIGSTRUCT_RESERVED3_SIZE 32
+#define SGX_SIGSTRUCT_RESERVED4_SIZE 12
+
+/**
+ * struct sgx_sigstruct_header - defines author of the enclave
+ * @header1: constant byte string
+ * @vendor: must be either 0x0000 or 0x8086
+ * @date: YYYYMMDD in BCD
+ * @header2: costant byte string
+ * @swdefined: software defined value
+ */
+struct sgx_sigstruct_header {
+ u64 header1[2];
+ u32 vendor;
+ u32 date;
+ u64 header2[2];
+ u32 swdefined;
+ u8 reserved1[84];
+} __packed;
+
+/**
+ * struct sgx_sigstruct_body - defines contents of the enclave
+ * @miscselect: additional information stored to an SSA frame
+ * @misc_mask: required miscselect in SECS
+ * @attributes: attributes for enclave
+ * @xfrm: XSave-Feature Request Mask (subset of XCR0)
+ * @attributes_mask: required attributes in SECS
+ * @xfrm_mask: required XFRM in SECS
+ * @mrenclave: SHA256-hash of the enclave contents
+ * @isvprodid: a user-defined value that is used in key derivation
+ * @isvsvn: a user-defined value that is used in key derivation
+ */
+struct sgx_sigstruct_body {
+ u32 miscselect;
+ u32 misc_mask;
+ u8 reserved2[20];
+ u64 attributes;
+ u64 xfrm;
+ u64 attributes_mask;
+ u64 xfrm_mask;
+ u8 mrenclave[32];
+ u8 reserved3[32];
+ u16 isvprodid;
+ u16 isvsvn;
+} __packed;
+
+/**
+ * struct sgx_sigstruct - an enclave signature
+ * @header: defines author of the enclave
+ * @modulus: the modulus of the public key
+ * @exponent: the exponent of the public key
+ * @signature: the signature calculated over the fields except modulus,
+ * @body: defines contents of the enclave
+ * @q1: a value used in RSA signature verification
+ * @q2: a value used in RSA signature verification
+ *
+ * Header and body are the parts that are actual signed. The remaining fields
+ * define the signature of the enclave.
+ */
+struct sgx_sigstruct {
+ struct sgx_sigstruct_header header;
+ u8 modulus[SGX_MODULUS_SIZE];
+ u32 exponent;
+ u8 signature[SGX_MODULUS_SIZE];
+ struct sgx_sigstruct_body body;
+ u8 reserved4[12];
+ u8 q1[SGX_MODULUS_SIZE];
+ u8 q2[SGX_MODULUS_SIZE];
+} __packed;
+
+#define SGX_LAUNCH_TOKEN_SIZE 304
+
+#endif /* _ASM_X86_SGX_ARCH_H */
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
new file mode 100644
index 000000000000..f2eac41bb4ff
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <linux/acpi.h>
+#include <linux/miscdevice.h>
+#include <linux/mman.h>
+#include <linux/security.h>
+#include <linux/suspend.h>
+#include <asm/traps.h>
+#include "driver.h"
+#include "encl.h"
+
+u64 sgx_attributes_reserved_mask;
+u64 sgx_xfrm_reserved_mask = ~0x3;
+u32 sgx_misc_reserved_mask;
+
+static int sgx_open(struct inode *inode, struct file *file)
+{
+ struct sgx_encl *encl;
+ int ret;
+
+ encl = kzalloc(sizeof(*encl), GFP_KERNEL);
+ if (!encl)
+ return -ENOMEM;
+
+ kref_init(&encl->refcount);
+ xa_init(&encl->page_array);
+ mutex_init(&encl->lock);
+ INIT_LIST_HEAD(&encl->va_pages);
+ INIT_LIST_HEAD(&encl->mm_list);
+ spin_lock_init(&encl->mm_lock);
+
+ ret = init_srcu_struct(&encl->srcu);
+ if (ret) {
+ kfree(encl);
+ return ret;
+ }
+
+ file->private_data = encl;
+
+ return 0;
+}
+
+static int sgx_release(struct inode *inode, struct file *file)
+{
+ struct sgx_encl *encl = file->private_data;
+ struct sgx_encl_mm *encl_mm;
+
+ /*
+ * Drain the remaining mm_list entries. At this point the list contains
+ * entries for processes, which have closed the enclave file but have
+ * not exited yet. The processes, which have exited, are gone from the
+ * list by sgx_mmu_notifier_release().
+ */
+ for ( ; ; ) {
+ spin_lock(&encl->mm_lock);
+
+ if (list_empty(&encl->mm_list)) {
+ encl_mm = NULL;
+ } else {
+ encl_mm = list_first_entry(&encl->mm_list,
+ struct sgx_encl_mm, list);
+ list_del_rcu(&encl_mm->list);
+ }
+
+ spin_unlock(&encl->mm_lock);
+
+ /* The enclave is no longer mapped by any mm. */
+ if (!encl_mm)
+ break;
+
+ synchronize_srcu(&encl->srcu);
+ mmu_notifier_unregister(&encl_mm->mmu_notifier, encl_mm->mm);
+ kfree(encl_mm);
+ }
+
+ kref_put(&encl->refcount, sgx_encl_release);
+ return 0;
+}
+
+static int sgx_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct sgx_encl *encl = file->private_data;
+ int ret;
+
+ ret = sgx_encl_may_map(encl, vma->vm_start, vma->vm_end, vma->vm_flags);
+ if (ret)
+ return ret;
+
+ ret = sgx_encl_mm_add(encl, vma->vm_mm);
+ if (ret)
+ return ret;
+
+ vma->vm_ops = &sgx_vm_ops;
+ vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
+ vma->vm_private_data = encl;
+
+ return 0;
+}
+
+static unsigned long sgx_get_unmapped_area(struct file *file,
+ unsigned long addr,
+ unsigned long len,
+ unsigned long pgoff,
+ unsigned long flags)
+{
+ if ((flags & MAP_TYPE) == MAP_PRIVATE)
+ return -EINVAL;
+
+ if (flags & MAP_FIXED)
+ return addr;
+
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
+#ifdef CONFIG_COMPAT
+static long sgx_compat_ioctl(struct file *filep, unsigned int cmd,
+ unsigned long arg)
+{
+ return sgx_ioctl(filep, cmd, arg);
+}
+#endif
+
+static const struct file_operations sgx_encl_fops = {
+ .owner = THIS_MODULE,
+ .open = sgx_open,
+ .release = sgx_release,
+ .unlocked_ioctl = sgx_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = sgx_compat_ioctl,
+#endif
+ .mmap = sgx_mmap,
+ .get_unmapped_area = sgx_get_unmapped_area,
+};
+
+const struct file_operations sgx_provision_fops = {
+ .owner = THIS_MODULE,
+};
+
+static struct miscdevice sgx_dev_enclave = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "sgx_enclave",
+ .nodename = "sgx_enclave",
+ .fops = &sgx_encl_fops,
+};
+
+static struct miscdevice sgx_dev_provision = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "sgx_provision",
+ .nodename = "sgx_provision",
+ .fops = &sgx_provision_fops,
+};
+
+int __init sgx_drv_init(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ u64 attr_mask;
+ u64 xfrm_mask;
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SGX_LC))
+ return -ENODEV;
+
+ cpuid_count(SGX_CPUID, 0, &eax, &ebx, &ecx, &edx);
+
+ if (!(eax & 1)) {
+ pr_err("SGX disabled: SGX1 instruction support not available.\n");
+ return -ENODEV;
+ }
+
+ sgx_misc_reserved_mask = ~ebx | SGX_MISC_RESERVED_MASK;
+
+ cpuid_count(SGX_CPUID, 1, &eax, &ebx, &ecx, &edx);
+
+ attr_mask = (((u64)ebx) << 32) + (u64)eax;
+ sgx_attributes_reserved_mask = ~attr_mask | SGX_ATTR_RESERVED_MASK;
+
+ if (cpu_feature_enabled(X86_FEATURE_OSXSAVE)) {
+ xfrm_mask = (((u64)edx) << 32) + (u64)ecx;
+ sgx_xfrm_reserved_mask = ~xfrm_mask;
+ }
+
+ ret = misc_register(&sgx_dev_enclave);
+ if (ret)
+ return ret;
+
+ ret = misc_register(&sgx_dev_provision);
+ if (ret) {
+ misc_deregister(&sgx_dev_enclave);
+ return ret;
+ }
+
+ return 0;
+}
diff --git a/arch/x86/kernel/cpu/sgx/driver.h b/arch/x86/kernel/cpu/sgx/driver.h
new file mode 100644
index 000000000000..4eddb4d571ef
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/driver.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_SGX_DRIVER_H__
+#define __ARCH_SGX_DRIVER_H__
+
+#include <crypto/hash.h>
+#include <linux/kref.h>
+#include <linux/mmu_notifier.h>
+#include <linux/radix-tree.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <uapi/asm/sgx.h>
+#include "sgx.h"
+
+#define SGX_EINIT_SPIN_COUNT 20
+#define SGX_EINIT_SLEEP_COUNT 50
+#define SGX_EINIT_SLEEP_TIME 20
+
+extern u64 sgx_attributes_reserved_mask;
+extern u64 sgx_xfrm_reserved_mask;
+extern u32 sgx_misc_reserved_mask;
+
+extern const struct file_operations sgx_provision_fops;
+
+long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
+
+int sgx_drv_init(void);
+
+#endif /* __ARCH_X86_SGX_DRIVER_H__ */
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
new file mode 100644
index 000000000000..ee50a5010277
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -0,0 +1,740 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <linux/lockdep.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/shmem_fs.h>
+#include <linux/suspend.h>
+#include <linux/sched/mm.h>
+#include "arch.h"
+#include "encl.h"
+#include "encls.h"
+#include "sgx.h"
+
+/*
+ * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC
+ * Pages" in the SDM.
+ */
+static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
+ struct sgx_epc_page *epc_page,
+ struct sgx_epc_page *secs_page)
+{
+ unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK;
+ struct sgx_encl *encl = encl_page->encl;
+ struct sgx_pageinfo pginfo;
+ struct sgx_backing b;
+ pgoff_t page_index;
+ int ret;
+
+ if (secs_page)
+ page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
+ else
+ page_index = PFN_DOWN(encl->size);
+
+ ret = sgx_encl_get_backing(encl, page_index, &b);
+ if (ret)
+ return ret;
+
+ pginfo.addr = encl_page->desc & PAGE_MASK;
+ pginfo.contents = (unsigned long)kmap_atomic(b.contents);
+ pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) +
+ b.pcmd_offset;
+
+ if (secs_page)
+ pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page);
+ else
+ pginfo.secs = 0;
+
+ ret = __eldu(&pginfo, sgx_get_epc_virt_addr(epc_page),
+ sgx_get_epc_virt_addr(encl_page->va_page->epc_page) + va_offset);
+ if (ret) {
+ if (encls_failed(ret))
+ ENCLS_WARN(ret, "ELDU");
+
+ ret = -EFAULT;
+ }
+
+ kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset));
+ kunmap_atomic((void *)(unsigned long)pginfo.contents);
+
+ sgx_encl_put_backing(&b, false);
+
+ return ret;
+}
+
+static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
+ struct sgx_epc_page *secs_page)
+{
+
+ unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK;
+ struct sgx_encl *encl = encl_page->encl;
+ struct sgx_epc_page *epc_page;
+ int ret;
+
+ epc_page = sgx_alloc_epc_page(encl_page, false);
+ if (IS_ERR(epc_page))
+ return epc_page;
+
+ ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
+ if (ret) {
+ sgx_free_epc_page(epc_page);
+ return ERR_PTR(ret);
+ }
+
+ sgx_free_va_slot(encl_page->va_page, va_offset);
+ list_move(&encl_page->va_page->list, &encl->va_pages);
+ encl_page->desc &= ~SGX_ENCL_PAGE_VA_OFFSET_MASK;
+ encl_page->epc_page = epc_page;
+
+ return epc_page;
+}
+
+static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
+ unsigned long addr,
+ unsigned long vm_flags)
+{
+ unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
+ struct sgx_epc_page *epc_page;
+ struct sgx_encl_page *entry;
+
+ entry = xa_load(&encl->page_array, PFN_DOWN(addr));
+ if (!entry)
+ return ERR_PTR(-EFAULT);
+
+ /*
+ * Verify that the faulted page has equal or higher build time
+ * permissions than the VMA permissions (i.e. the subset of {VM_READ,
+ * VM_WRITE, VM_EXECUTE} in vma->vm_flags).
+ */
+ if ((entry->vm_max_prot_bits & vm_prot_bits) != vm_prot_bits)
+ return ERR_PTR(-EFAULT);
+
+ /* Entry successfully located. */
+ if (entry->epc_page) {
+ if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)
+ return ERR_PTR(-EBUSY);
+
+ return entry;
+ }
+
+ if (!(encl->secs.epc_page)) {
+ epc_page = sgx_encl_eldu(&encl->secs, NULL);
+ if (IS_ERR(epc_page))
+ return ERR_CAST(epc_page);
+ }
+
+ epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
+ if (IS_ERR(epc_page))
+ return ERR_CAST(epc_page);
+
+ encl->secs_child_cnt++;
+ sgx_mark_page_reclaimable(entry->epc_page);
+
+ return entry;
+}
+
+static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
+{
+ unsigned long addr = (unsigned long)vmf->address;
+ struct vm_area_struct *vma = vmf->vma;
+ struct sgx_encl_page *entry;
+ unsigned long phys_addr;
+ struct sgx_encl *encl;
+ unsigned long pfn;
+ vm_fault_t ret;
+
+ encl = vma->vm_private_data;
+
+ /*
+ * It's very unlikely but possible that allocating memory for the
+ * mm_list entry of a forked process failed in sgx_vma_open(). When
+ * this happens, vm_private_data is set to NULL.
+ */
+ if (unlikely(!encl))
+ return VM_FAULT_SIGBUS;
+
+ mutex_lock(&encl->lock);
+
+ entry = sgx_encl_load_page(encl, addr, vma->vm_flags);
+ if (IS_ERR(entry)) {
+ mutex_unlock(&encl->lock);
+
+ if (PTR_ERR(entry) == -EBUSY)
+ return VM_FAULT_NOPAGE;
+
+ return VM_FAULT_SIGBUS;
+ }
+
+ phys_addr = sgx_get_epc_phys_addr(entry->epc_page);
+
+ /* Check if another thread got here first to insert the PTE. */
+ if (!follow_pfn(vma, addr, &pfn)) {
+ mutex_unlock(&encl->lock);
+
+ return VM_FAULT_NOPAGE;
+ }
+
+ ret = vmf_insert_pfn(vma, addr, PFN_DOWN(phys_addr));
+ if (ret != VM_FAULT_NOPAGE) {
+ mutex_unlock(&encl->lock);
+
+ return VM_FAULT_SIGBUS;
+ }
+
+ sgx_encl_test_and_clear_young(vma->vm_mm, entry);
+ mutex_unlock(&encl->lock);
+
+ return VM_FAULT_NOPAGE;
+}
+
+static void sgx_vma_open(struct vm_area_struct *vma)
+{
+ struct sgx_encl *encl = vma->vm_private_data;
+
+ /*
+ * It's possible but unlikely that vm_private_data is NULL. This can
+ * happen in a grandchild of a process, when sgx_encl_mm_add() had
+ * failed to allocate memory in this callback.
+ */
+ if (unlikely(!encl))
+ return;
+
+ if (sgx_encl_mm_add(encl, vma->vm_mm))
+ vma->vm_private_data = NULL;
+}
+
+
+/**
+ * sgx_encl_may_map() - Check if a requested VMA mapping is allowed
+ * @encl: an enclave pointer
+ * @start: lower bound of the address range, inclusive
+ * @end: upper bound of the address range, exclusive
+ * @vm_flags: VMA flags
+ *
+ * Iterate through the enclave pages contained within [@start, @end) to verify
+ * that the permissions requested by a subset of {VM_READ, VM_WRITE, VM_EXEC}
+ * do not contain any permissions that are not contained in the build time
+ * permissions of any of the enclave pages within the given address range.
+ *
+ * An enclave creator must declare the strongest permissions that will be
+ * needed for each enclave page. This ensures that mappings have the identical
+ * or weaker permissions than the earlier declared permissions.
+ *
+ * Return: 0 on success, -EACCES otherwise
+ */
+int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
+ unsigned long end, unsigned long vm_flags)
+{
+ unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
+ struct sgx_encl_page *page;
+ unsigned long count = 0;
+ int ret = 0;
+
+ XA_STATE(xas, &encl->page_array, PFN_DOWN(start));
+
+ /*
+ * Disallow READ_IMPLIES_EXEC tasks as their VMA permissions might
+ * conflict with the enclave page permissions.
+ */
+ if (current->personality & READ_IMPLIES_EXEC)
+ return -EACCES;
+
+ mutex_lock(&encl->lock);
+ xas_lock(&xas);
+ xas_for_each(&xas, page, PFN_DOWN(end - 1)) {
+ if (~page->vm_max_prot_bits & vm_prot_bits) {
+ ret = -EACCES;
+ break;
+ }
+
+ /* Reschedule on every XA_CHECK_SCHED iteration. */
+ if (!(++count % XA_CHECK_SCHED)) {
+ xas_pause(&xas);
+ xas_unlock(&xas);
+ mutex_unlock(&encl->lock);
+
+ cond_resched();
+
+ mutex_lock(&encl->lock);
+ xas_lock(&xas);
+ }
+ }
+ xas_unlock(&xas);
+ mutex_unlock(&encl->lock);
+
+ return ret;
+}
+
+static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, unsigned long newflags)
+{
+ return sgx_encl_may_map(vma->vm_private_data, start, end, newflags);
+}
+
+static int sgx_encl_debug_read(struct sgx_encl *encl, struct sgx_encl_page *page,
+ unsigned long addr, void *data)
+{
+ unsigned long offset = addr & ~PAGE_MASK;
+ int ret;
+
+
+ ret = __edbgrd(sgx_get_epc_virt_addr(page->epc_page) + offset, data);
+ if (ret)
+ return -EIO;
+
+ return 0;
+}
+
+static int sgx_encl_debug_write(struct sgx_encl *encl, struct sgx_encl_page *page,
+ unsigned long addr, void *data)
+{
+ unsigned long offset = addr & ~PAGE_MASK;
+ int ret;
+
+ ret = __edbgwr(sgx_get_epc_virt_addr(page->epc_page) + offset, data);
+ if (ret)
+ return -EIO;
+
+ return 0;
+}
+
+/*
+ * Load an enclave page to EPC if required, and take encl->lock.
+ */
+static struct sgx_encl_page *sgx_encl_reserve_page(struct sgx_encl *encl,
+ unsigned long addr,
+ unsigned long vm_flags)
+{
+ struct sgx_encl_page *entry;
+
+ for ( ; ; ) {
+ mutex_lock(&encl->lock);
+
+ entry = sgx_encl_load_page(encl, addr, vm_flags);
+ if (PTR_ERR(entry) != -EBUSY)
+ break;
+
+ mutex_unlock(&encl->lock);
+ }
+
+ if (IS_ERR(entry))
+ mutex_unlock(&encl->lock);
+
+ return entry;
+}
+
+static int sgx_vma_access(struct vm_area_struct *vma, unsigned long addr,
+ void *buf, int len, int write)
+{
+ struct sgx_encl *encl = vma->vm_private_data;
+ struct sgx_encl_page *entry = NULL;
+ char data[sizeof(unsigned long)];
+ unsigned long align;
+ int offset;
+ int cnt;
+ int ret = 0;
+ int i;
+
+ /*
+ * If process was forked, VMA is still there but vm_private_data is set
+ * to NULL.
+ */
+ if (!encl)
+ return -EFAULT;
+
+ if (!test_bit(SGX_ENCL_DEBUG, &encl->flags))
+ return -EFAULT;
+
+ for (i = 0; i < len; i += cnt) {
+ entry = sgx_encl_reserve_page(encl, (addr + i) & PAGE_MASK,
+ vma->vm_flags);
+ if (IS_ERR(entry)) {
+ ret = PTR_ERR(entry);
+ break;
+ }
+
+ align = ALIGN_DOWN(addr + i, sizeof(unsigned long));
+ offset = (addr + i) & (sizeof(unsigned long) - 1);
+ cnt = sizeof(unsigned long) - offset;
+ cnt = min(cnt, len - i);
+
+ ret = sgx_encl_debug_read(encl, entry, align, data);
+ if (ret)
+ goto out;
+
+ if (write) {
+ memcpy(data + offset, buf + i, cnt);
+ ret = sgx_encl_debug_write(encl, entry, align, data);
+ if (ret)
+ goto out;
+ } else {
+ memcpy(buf + i, data + offset, cnt);
+ }
+
+out:
+ mutex_unlock(&encl->lock);
+
+ if (ret)
+ break;
+ }
+
+ return ret < 0 ? ret : i;
+}
+
+const struct vm_operations_struct sgx_vm_ops = {
+ .fault = sgx_vma_fault,
+ .mprotect = sgx_vma_mprotect,
+ .open = sgx_vma_open,
+ .access = sgx_vma_access,
+};
+
+/**
+ * sgx_encl_release - Destroy an enclave instance
+ * @kref: address of a kref inside &sgx_encl
+ *
+ * Used together with kref_put(). Frees all the resources associated with the
+ * enclave and the instance itself.
+ */
+void sgx_encl_release(struct kref *ref)
+{
+ struct sgx_encl *encl = container_of(ref, struct sgx_encl, refcount);
+ struct sgx_va_page *va_page;
+ struct sgx_encl_page *entry;
+ unsigned long index;
+
+ xa_for_each(&encl->page_array, index, entry) {
+ if (entry->epc_page) {
+ /*
+ * The page and its radix tree entry cannot be freed
+ * if the page is being held by the reclaimer.
+ */
+ if (sgx_unmark_page_reclaimable(entry->epc_page))
+ continue;
+
+ sgx_free_epc_page(entry->epc_page);
+ encl->secs_child_cnt--;
+ entry->epc_page = NULL;
+ }
+
+ kfree(entry);
+ }
+
+ xa_destroy(&encl->page_array);
+
+ if (!encl->secs_child_cnt && encl->secs.epc_page) {
+ sgx_free_epc_page(encl->secs.epc_page);
+ encl->secs.epc_page = NULL;
+ }
+
+ while (!list_empty(&encl->va_pages)) {
+ va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
+ list);
+ list_del(&va_page->list);
+ sgx_free_epc_page(va_page->epc_page);
+ kfree(va_page);
+ }
+
+ if (encl->backing)
+ fput(encl->backing);
+
+ cleanup_srcu_struct(&encl->srcu);
+
+ WARN_ON_ONCE(!list_empty(&encl->mm_list));
+
+ /* Detect EPC page leak's. */
+ WARN_ON_ONCE(encl->secs_child_cnt);
+ WARN_ON_ONCE(encl->secs.epc_page);
+
+ kfree(encl);
+}
+
+/*
+ * 'mm' is exiting and no longer needs mmu notifications.
+ */
+static void sgx_mmu_notifier_release(struct mmu_notifier *mn,
+ struct mm_struct *mm)
+{
+ struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
+ struct sgx_encl_mm *tmp = NULL;
+
+ /*
+ * The enclave itself can remove encl_mm. Note, objects can't be moved
+ * off an RCU protected list, but deletion is ok.
+ */
+ spin_lock(&encl_mm->encl->mm_lock);
+ list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) {
+ if (tmp == encl_mm) {
+ list_del_rcu(&encl_mm->list);
+ break;
+ }
+ }
+ spin_unlock(&encl_mm->encl->mm_lock);
+
+ if (tmp == encl_mm) {
+ synchronize_srcu(&encl_mm->encl->srcu);
+ mmu_notifier_put(mn);
+ }
+}
+
+static void sgx_mmu_notifier_free(struct mmu_notifier *mn)
+{
+ struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
+
+ kfree(encl_mm);
+}
+
+static const struct mmu_notifier_ops sgx_mmu_notifier_ops = {
+ .release = sgx_mmu_notifier_release,
+ .free_notifier = sgx_mmu_notifier_free,
+};
+
+static struct sgx_encl_mm *sgx_encl_find_mm(struct sgx_encl *encl,
+ struct mm_struct *mm)
+{
+ struct sgx_encl_mm *encl_mm = NULL;
+ struct sgx_encl_mm *tmp;
+ int idx;
+
+ idx = srcu_read_lock(&encl->srcu);
+
+ list_for_each_entry_rcu(tmp, &encl->mm_list, list) {
+ if (tmp->mm == mm) {
+ encl_mm = tmp;
+ break;
+ }
+ }
+
+ srcu_read_unlock(&encl->srcu, idx);
+
+ return encl_mm;
+}
+
+int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
+{
+ struct sgx_encl_mm *encl_mm;
+ int ret;
+
+ /*
+ * Even though a single enclave may be mapped into an mm more than once,
+ * each 'mm' only appears once on encl->mm_list. This is guaranteed by
+ * holding the mm's mmap lock for write before an mm can be added or
+ * remove to an encl->mm_list.
+ */
+ mmap_assert_write_locked(mm);
+
+ /*
+ * It's possible that an entry already exists in the mm_list, because it
+ * is removed only on VFS release or process exit.
+ */
+ if (sgx_encl_find_mm(encl, mm))
+ return 0;
+
+ encl_mm = kzalloc(sizeof(*encl_mm), GFP_KERNEL);
+ if (!encl_mm)
+ return -ENOMEM;
+
+ encl_mm->encl = encl;
+ encl_mm->mm = mm;
+ encl_mm->mmu_notifier.ops = &sgx_mmu_notifier_ops;
+
+ ret = __mmu_notifier_register(&encl_mm->mmu_notifier, mm);
+ if (ret) {
+ kfree(encl_mm);
+ return ret;
+ }
+
+ spin_lock(&encl->mm_lock);
+ list_add_rcu(&encl_mm->list, &encl->mm_list);
+ /* Pairs with smp_rmb() in sgx_reclaimer_block(). */
+ smp_wmb();
+ encl->mm_list_version++;
+ spin_unlock(&encl->mm_lock);
+
+ return 0;
+}
+
+static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
+ pgoff_t index)
+{
+ struct inode *inode = encl->backing->f_path.dentry->d_inode;
+ struct address_space *mapping = inode->i_mapping;
+ gfp_t gfpmask = mapping_gfp_mask(mapping);
+
+ return shmem_read_mapping_page_gfp(mapping, index, gfpmask);
+}
+
+/**
+ * sgx_encl_get_backing() - Pin the backing storage
+ * @encl: an enclave pointer
+ * @page_index: enclave page index
+ * @backing: data for accessing backing storage for the page
+ *
+ * Pin the backing storage pages for storing the encrypted contents and Paging
+ * Crypto MetaData (PCMD) of an enclave page.
+ *
+ * Return:
+ * 0 on success,
+ * -errno otherwise.
+ */
+int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+ struct sgx_backing *backing)
+{
+ pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5);
+ struct page *contents;
+ struct page *pcmd;
+
+ contents = sgx_encl_get_backing_page(encl, page_index);
+ if (IS_ERR(contents))
+ return PTR_ERR(contents);
+
+ pcmd = sgx_encl_get_backing_page(encl, pcmd_index);
+ if (IS_ERR(pcmd)) {
+ put_page(contents);
+ return PTR_ERR(pcmd);
+ }
+
+ backing->page_index = page_index;
+ backing->contents = contents;
+ backing->pcmd = pcmd;
+ backing->pcmd_offset =
+ (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) *
+ sizeof(struct sgx_pcmd);
+
+ return 0;
+}
+
+/**
+ * sgx_encl_put_backing() - Unpin the backing storage
+ * @backing: data for accessing backing storage for the page
+ * @do_write: mark pages dirty
+ */
+void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write)
+{
+ if (do_write) {
+ set_page_dirty(backing->pcmd);
+ set_page_dirty(backing->contents);
+ }
+
+ put_page(backing->pcmd);
+ put_page(backing->contents);
+}
+
+static int sgx_encl_test_and_clear_young_cb(pte_t *ptep, unsigned long addr,
+ void *data)
+{
+ pte_t pte;
+ int ret;
+
+ ret = pte_young(*ptep);
+ if (ret) {
+ pte = pte_mkold(*ptep);
+ set_pte_at((struct mm_struct *)data, addr, ptep, pte);
+ }
+
+ return ret;
+}
+
+/**
+ * sgx_encl_test_and_clear_young() - Test and reset the accessed bit
+ * @mm: mm_struct that is checked
+ * @page: enclave page to be tested for recent access
+ *
+ * Checks the Access (A) bit from the PTE corresponding to the enclave page and
+ * clears it.
+ *
+ * Return: 1 if the page has been recently accessed and 0 if not.
+ */
+int sgx_encl_test_and_clear_young(struct mm_struct *mm,
+ struct sgx_encl_page *page)
+{
+ unsigned long addr = page->desc & PAGE_MASK;
+ struct sgx_encl *encl = page->encl;
+ struct vm_area_struct *vma;
+ int ret;
+
+ ret = sgx_encl_find(mm, addr, &vma);
+ if (ret)
+ return 0;
+
+ if (encl != vma->vm_private_data)
+ return 0;
+
+ ret = apply_to_page_range(vma->vm_mm, addr, PAGE_SIZE,
+ sgx_encl_test_and_clear_young_cb, vma->vm_mm);
+ if (ret < 0)
+ return 0;
+
+ return ret;
+}
+
+/**
+ * sgx_alloc_va_page() - Allocate a Version Array (VA) page
+ *
+ * Allocate a free EPC page and convert it to a Version Array (VA) page.
+ *
+ * Return:
+ * a VA page,
+ * -errno otherwise
+ */
+struct sgx_epc_page *sgx_alloc_va_page(void)
+{
+ struct sgx_epc_page *epc_page;
+ int ret;
+
+ epc_page = sgx_alloc_epc_page(NULL, true);
+ if (IS_ERR(epc_page))
+ return ERR_CAST(epc_page);
+
+ ret = __epa(sgx_get_epc_virt_addr(epc_page));
+ if (ret) {
+ WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret);
+ sgx_free_epc_page(epc_page);
+ return ERR_PTR(-EFAULT);
+ }
+
+ return epc_page;
+}
+
+/**
+ * sgx_alloc_va_slot - allocate a VA slot
+ * @va_page: a &struct sgx_va_page instance
+ *
+ * Allocates a slot from a &struct sgx_va_page instance.
+ *
+ * Return: offset of the slot inside the VA page
+ */
+unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page)
+{
+ int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);
+
+ if (slot < SGX_VA_SLOT_COUNT)
+ set_bit(slot, va_page->slots);
+
+ return slot << 3;
+}
+
+/**
+ * sgx_free_va_slot - free a VA slot
+ * @va_page: a &struct sgx_va_page instance
+ * @offset: offset of the slot inside the VA page
+ *
+ * Frees a slot from a &struct sgx_va_page instance.
+ */
+void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset)
+{
+ clear_bit(offset >> 3, va_page->slots);
+}
+
+/**
+ * sgx_va_page_full - is the VA page full?
+ * @va_page: a &struct sgx_va_page instance
+ *
+ * Return: true if all slots have been taken
+ */
+bool sgx_va_page_full(struct sgx_va_page *va_page)
+{
+ int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);
+
+ return slot == SGX_VA_SLOT_COUNT;
+}
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
new file mode 100644
index 000000000000..d8d30ccbef4c
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+ * Copyright(c) 2016-20 Intel Corporation.
+ *
+ * Contains the software defined data structures for enclaves.
+ */
+#ifndef _X86_ENCL_H
+#define _X86_ENCL_H
+
+#include <linux/cpumask.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/mm_types.h>
+#include <linux/mmu_notifier.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/srcu.h>
+#include <linux/workqueue.h>
+#include <linux/xarray.h>
+#include "sgx.h"
+
+/* 'desc' bits holding the offset in the VA (version array) page. */
+#define SGX_ENCL_PAGE_VA_OFFSET_MASK GENMASK_ULL(11, 3)
+
+/* 'desc' bit marking that the page is being reclaimed. */
+#define SGX_ENCL_PAGE_BEING_RECLAIMED BIT(3)
+
+struct sgx_encl_page {
+ unsigned long desc;
+ unsigned long vm_max_prot_bits;
+ struct sgx_epc_page *epc_page;
+ struct sgx_encl *encl;
+ struct sgx_va_page *va_page;
+};
+
+enum sgx_encl_flags {
+ SGX_ENCL_IOCTL = BIT(0),
+ SGX_ENCL_DEBUG = BIT(1),
+ SGX_ENCL_CREATED = BIT(2),
+ SGX_ENCL_INITIALIZED = BIT(3),
+};
+
+struct sgx_encl_mm {
+ struct sgx_encl *encl;
+ struct mm_struct *mm;
+ struct list_head list;
+ struct mmu_notifier mmu_notifier;
+};
+
+struct sgx_encl {
+ unsigned long base;
+ unsigned long size;
+ unsigned long flags;
+ unsigned int page_cnt;
+ unsigned int secs_child_cnt;
+ struct mutex lock;
+ struct xarray page_array;
+ struct sgx_encl_page secs;
+ unsigned long attributes;
+ unsigned long attributes_mask;
+
+ cpumask_t cpumask;
+ struct file *backing;
+ struct kref refcount;
+ struct list_head va_pages;
+ unsigned long mm_list_version;
+ struct list_head mm_list;
+ spinlock_t mm_lock;
+ struct srcu_struct srcu;
+};
+
+#define SGX_VA_SLOT_COUNT 512
+
+struct sgx_va_page {
+ struct sgx_epc_page *epc_page;
+ DECLARE_BITMAP(slots, SGX_VA_SLOT_COUNT);
+ struct list_head list;
+};
+
+struct sgx_backing {
+ pgoff_t page_index;
+ struct page *contents;
+ struct page *pcmd;
+ unsigned long pcmd_offset;
+};
+
+extern const struct vm_operations_struct sgx_vm_ops;
+
+static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
+ struct vm_area_struct **vma)
+{
+ struct vm_area_struct *result;
+
+ result = find_vma(mm, addr);
+ if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start)
+ return -EINVAL;
+
+ *vma = result;
+
+ return 0;
+}
+
+int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
+ unsigned long end, unsigned long vm_flags);
+
+void sgx_encl_release(struct kref *ref);
+int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
+int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+ struct sgx_backing *backing);
+void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write);
+int sgx_encl_test_and_clear_young(struct mm_struct *mm,
+ struct sgx_encl_page *page);
+
+struct sgx_epc_page *sgx_alloc_va_page(void);
+unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page);
+void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset);
+bool sgx_va_page_full(struct sgx_va_page *va_page);
+
+#endif /* _X86_ENCL_H */
diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h
new file mode 100644
index 000000000000..443188fe7e70
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/encls.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_ENCLS_H
+#define _X86_ENCLS_H
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/rwsem.h>
+#include <linux/types.h>
+#include <asm/asm.h>
+#include <asm/traps.h>
+#include "sgx.h"
+
+enum sgx_encls_function {
+ ECREATE = 0x00,
+ EADD = 0x01,
+ EINIT = 0x02,
+ EREMOVE = 0x03,
+ EDGBRD = 0x04,
+ EDGBWR = 0x05,
+ EEXTEND = 0x06,
+ ELDU = 0x08,
+ EBLOCK = 0x09,
+ EPA = 0x0A,
+ EWB = 0x0B,
+ ETRACK = 0x0C,
+};
+
+/**
+ * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
+ *
+ * ENCLS has its own (positive value) error codes and also generates
+ * ENCLS specific #GP and #PF faults. And the ENCLS values get munged
+ * with system error codes as everything percolates back up the stack.
+ * Unfortunately (for us), we need to precisely identify each unique
+ * error code, e.g. the action taken if EWB fails varies based on the
+ * type of fault and on the exact SGX error code, i.e. we can't simply
+ * convert all faults to -EFAULT.
+ *
+ * To make all three error types coexist, we set bit 30 to identify an
+ * ENCLS fault. Bit 31 (technically bits N:31) is used to differentiate
+ * between positive (faults and SGX error codes) and negative (system
+ * error codes) values.
+ */
+#define ENCLS_FAULT_FLAG 0x40000000
+
+/* Retrieve the encoded trapnr from the specified return code. */
+#define ENCLS_TRAPNR(r) ((r) & ~ENCLS_FAULT_FLAG)
+
+/* Issue a WARN() about an ENCLS function. */
+#define ENCLS_WARN(r, name) { \
+ do { \
+ int _r = (r); \
+ WARN_ONCE(_r, "%s returned %d (0x%x)\n", (name), _r, _r); \
+ } while (0); \
+}
+
+/**
+ * encls_failed() - Check if an ENCLS function failed
+ * @ret: the return value of an ENCLS function call
+ *
+ * Check if an ENCLS function failed. This happens when the function causes a
+ * fault that is not caused by an EPCM conflict or when the function returns a
+ * non-zero value.
+ */
+static inline bool encls_failed(int ret)
+{
+ if (ret & ENCLS_FAULT_FLAG)
+ return ENCLS_TRAPNR(ret) != X86_TRAP_PF;
+
+ return !!ret;
+}
+
+/**
+ * __encls_ret_N - encode an ENCLS function that returns an error code in EAX
+ * @rax: function number
+ * @inputs: asm inputs for the function
+ *
+ * Emit assembly for an ENCLS function that returns an error code, e.g. EREMOVE.
+ * And because SGX isn't complex enough as it is, function that return an error
+ * code also modify flags.
+ *
+ * Return:
+ * 0 on success,
+ * SGX error code on failure
+ */
+#define __encls_ret_N(rax, inputs...) \
+ ({ \
+ int ret; \
+ asm volatile( \
+ "1: .byte 0x0f, 0x01, 0xcf;\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE_FAULT(1b, 3b) \
+ : "=a"(ret) \
+ : "a"(rax), inputs \
+ : "memory", "cc"); \
+ ret; \
+ })
+
+#define __encls_ret_1(rax, rcx) \
+ ({ \
+ __encls_ret_N(rax, "c"(rcx)); \
+ })
+
+#define __encls_ret_2(rax, rbx, rcx) \
+ ({ \
+ __encls_ret_N(rax, "b"(rbx), "c"(rcx)); \
+ })
+
+#define __encls_ret_3(rax, rbx, rcx, rdx) \
+ ({ \
+ __encls_ret_N(rax, "b"(rbx), "c"(rcx), "d"(rdx)); \
+ })
+
+/**
+ * __encls_N - encode an ENCLS function that doesn't return an error code
+ * @rax: function number
+ * @rbx_out: optional output variable
+ * @inputs: asm inputs for the function
+ *
+ * Emit assembly for an ENCLS function that does not return an error code, e.g.
+ * ECREATE. Leaves without error codes either succeed or fault. @rbx_out is an
+ * optional parameter for use by EDGBRD, which returns the requested value in
+ * RBX.
+ *
+ * Return:
+ * 0 on success,
+ * trapnr with ENCLS_FAULT_FLAG set on fault
+ */
+#define __encls_N(rax, rbx_out, inputs...) \
+ ({ \
+ int ret; \
+ asm volatile( \
+ "1: .byte 0x0f, 0x01, 0xcf;\n\t" \
+ " xor %%eax,%%eax;\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE_FAULT(1b, 3b) \
+ : "=a"(ret), "=b"(rbx_out) \
+ : "a"(rax), inputs \
+ : "memory"); \
+ ret; \
+ })
+
+#define __encls_2(rax, rbx, rcx) \
+ ({ \
+ unsigned long ign_rbx_out; \
+ __encls_N(rax, ign_rbx_out, "b"(rbx), "c"(rcx)); \
+ })
+
+#define __encls_1_1(rax, data, rcx) \
+ ({ \
+ unsigned long rbx_out; \
+ int ret = __encls_N(rax, rbx_out, "c"(rcx)); \
+ if (!ret) \
+ data = rbx_out; \
+ ret; \
+ })
+
+static inline int __ecreate(struct sgx_pageinfo *pginfo, void *secs)
+{
+ return __encls_2(ECREATE, pginfo, secs);
+}
+
+static inline int __eextend(void *secs, void *addr)
+{
+ return __encls_2(EEXTEND, secs, addr);
+}
+
+static inline int __eadd(struct sgx_pageinfo *pginfo, void *addr)
+{
+ return __encls_2(EADD, pginfo, addr);
+}
+
+static inline int __einit(void *sigstruct, void *token, void *secs)
+{
+ return __encls_ret_3(EINIT, sigstruct, secs, token);
+}
+
+static inline int __eremove(void *addr)
+{
+ return __encls_ret_1(EREMOVE, addr);
+}
+
+static inline int __edbgwr(void *addr, unsigned long *data)
+{
+ return __encls_2(EDGBWR, *data, addr);
+}
+
+static inline int __edbgrd(void *addr, unsigned long *data)
+{
+ return __encls_1_1(EDGBRD, *data, addr);
+}
+
+static inline int __etrack(void *addr)
+{
+ return __encls_ret_1(ETRACK, addr);
+}
+
+static inline int __eldu(struct sgx_pageinfo *pginfo, void *addr,
+ void *va)
+{
+ return __encls_ret_3(ELDU, pginfo, addr, va);
+}
+
+static inline int __eblock(void *addr)
+{
+ return __encls_ret_1(EBLOCK, addr);
+}
+
+static inline int __epa(void *addr)
+{
+ unsigned long rbx = SGX_PAGE_TYPE_VA;
+
+ return __encls_2(EPA, rbx, addr);
+}
+
+static inline int __ewb(struct sgx_pageinfo *pginfo, void *addr,
+ void *va)
+{
+ return __encls_ret_3(EWB, pginfo, addr, va);
+}
+
+#endif /* _X86_ENCLS_H */
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
new file mode 100644
index 000000000000..90a5caf76939
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -0,0 +1,716 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <asm/mman.h>
+#include <linux/mman.h>
+#include <linux/delay.h>
+#include <linux/file.h>
+#include <linux/hashtable.h>
+#include <linux/highmem.h>
+#include <linux/ratelimit.h>
+#include <linux/sched/signal.h>
+#include <linux/shmem_fs.h>
+#include <linux/slab.h>
+#include <linux/suspend.h>
+#include "driver.h"
+#include "encl.h"
+#include "encls.h"
+
+static struct sgx_va_page *sgx_encl_grow(struct sgx_encl *encl)
+{
+ struct sgx_va_page *va_page = NULL;
+ void *err;
+
+ BUILD_BUG_ON(SGX_VA_SLOT_COUNT !=
+ (SGX_ENCL_PAGE_VA_OFFSET_MASK >> 3) + 1);
+
+ if (!(encl->page_cnt % SGX_VA_SLOT_COUNT)) {
+ va_page = kzalloc(sizeof(*va_page), GFP_KERNEL);
+ if (!va_page)
+ return ERR_PTR(-ENOMEM);
+
+ va_page->epc_page = sgx_alloc_va_page();
+ if (IS_ERR(va_page->epc_page)) {
+ err = ERR_CAST(va_page->epc_page);
+ kfree(va_page);
+ return err;
+ }
+
+ WARN_ON_ONCE(encl->page_cnt % SGX_VA_SLOT_COUNT);
+ }
+ encl->page_cnt++;
+ return va_page;
+}
+
+static void sgx_encl_shrink(struct sgx_encl *encl, struct sgx_va_page *va_page)
+{
+ encl->page_cnt--;
+
+ if (va_page) {
+ sgx_free_epc_page(va_page->epc_page);
+ list_del(&va_page->list);
+ kfree(va_page);
+ }
+}
+
+static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
+{
+ struct sgx_epc_page *secs_epc;
+ struct sgx_va_page *va_page;
+ struct sgx_pageinfo pginfo;
+ struct sgx_secinfo secinfo;
+ unsigned long encl_size;
+ struct file *backing;
+ long ret;
+
+ va_page = sgx_encl_grow(encl);
+ if (IS_ERR(va_page))
+ return PTR_ERR(va_page);
+ else if (va_page)
+ list_add(&va_page->list, &encl->va_pages);
+ /* else the tail page of the VA page list had free slots. */
+
+ /* The extra page goes to SECS. */
+ encl_size = secs->size + PAGE_SIZE;
+
+ backing = shmem_file_setup("SGX backing", encl_size + (encl_size >> 5),
+ VM_NORESERVE);
+ if (IS_ERR(backing)) {
+ ret = PTR_ERR(backing);
+ goto err_out_shrink;
+ }
+
+ encl->backing = backing;
+
+ secs_epc = sgx_alloc_epc_page(&encl->secs, true);
+ if (IS_ERR(secs_epc)) {
+ ret = PTR_ERR(secs_epc);
+ goto err_out_backing;
+ }
+
+ encl->secs.epc_page = secs_epc;
+
+ pginfo.addr = 0;
+ pginfo.contents = (unsigned long)secs;
+ pginfo.metadata = (unsigned long)&secinfo;
+ pginfo.secs = 0;
+ memset(&secinfo, 0, sizeof(secinfo));
+
+ ret = __ecreate((void *)&pginfo, sgx_get_epc_virt_addr(secs_epc));
+ if (ret) {
+ ret = -EIO;
+ goto err_out;
+ }
+
+ if (secs->attributes & SGX_ATTR_DEBUG)
+ set_bit(SGX_ENCL_DEBUG, &encl->flags);
+
+ encl->secs.encl = encl;
+ encl->base = secs->base;
+ encl->size = secs->size;
+ encl->attributes = secs->attributes;
+ encl->attributes_mask = SGX_ATTR_DEBUG | SGX_ATTR_MODE64BIT | SGX_ATTR_KSS;
+
+ /* Set only after completion, as encl->lock has not been taken. */
+ set_bit(SGX_ENCL_CREATED, &encl->flags);
+
+ return 0;
+
+err_out:
+ sgx_free_epc_page(encl->secs.epc_page);
+ encl->secs.epc_page = NULL;
+
+err_out_backing:
+ fput(encl->backing);
+ encl->backing = NULL;
+
+err_out_shrink:
+ sgx_encl_shrink(encl, va_page);
+
+ return ret;
+}
+
+/**
+ * sgx_ioc_enclave_create() - handler for %SGX_IOC_ENCLAVE_CREATE
+ * @encl: An enclave pointer.
+ * @arg: The ioctl argument.
+ *
+ * Allocate kernel data structures for the enclave and invoke ECREATE.
+ *
+ * Return:
+ * - 0: Success.
+ * - -EIO: ECREATE failed.
+ * - -errno: POSIX error.
+ */
+static long sgx_ioc_enclave_create(struct sgx_encl *encl, void __user *arg)
+{
+ struct sgx_enclave_create create_arg;
+ void *secs;
+ int ret;
+
+ if (test_bit(SGX_ENCL_CREATED, &encl->flags))
+ return -EINVAL;
+
+ if (copy_from_user(&create_arg, arg, sizeof(create_arg)))
+ return -EFAULT;
+
+ secs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!secs)
+ return -ENOMEM;
+
+ if (copy_from_user(secs, (void __user *)create_arg.src, PAGE_SIZE))
+ ret = -EFAULT;
+ else
+ ret = sgx_encl_create(encl, secs);
+
+ kfree(secs);
+ return ret;
+}
+
+static struct sgx_encl_page *sgx_encl_page_alloc(struct sgx_encl *encl,
+ unsigned long offset,
+ u64 secinfo_flags)
+{
+ struct sgx_encl_page *encl_page;
+ unsigned long prot;
+
+ encl_page = kzalloc(sizeof(*encl_page), GFP_KERNEL);
+ if (!encl_page)
+ return ERR_PTR(-ENOMEM);
+
+ encl_page->desc = encl->base + offset;
+ encl_page->encl = encl;
+
+ prot = _calc_vm_trans(secinfo_flags, SGX_SECINFO_R, PROT_READ) |
+ _calc_vm_trans(secinfo_flags, SGX_SECINFO_W, PROT_WRITE) |
+ _calc_vm_trans(secinfo_flags, SGX_SECINFO_X, PROT_EXEC);
+
+ /*
+ * TCS pages must always RW set for CPU access while the SECINFO
+ * permissions are *always* zero - the CPU ignores the user provided
+ * values and silently overwrites them with zero permissions.
+ */
+ if ((secinfo_flags & SGX_SECINFO_PAGE_TYPE_MASK) == SGX_SECINFO_TCS)
+ prot |= PROT_READ | PROT_WRITE;
+
+ /* Calculate maximum of the VM flags for the page. */
+ encl_page->vm_max_prot_bits = calc_vm_prot_bits(prot, 0);
+
+ return encl_page;
+}
+
+static int sgx_validate_secinfo(struct sgx_secinfo *secinfo)
+{
+ u64 perm = secinfo->flags & SGX_SECINFO_PERMISSION_MASK;
+ u64 pt = secinfo->flags & SGX_SECINFO_PAGE_TYPE_MASK;
+
+ if (pt != SGX_SECINFO_REG && pt != SGX_SECINFO_TCS)
+ return -EINVAL;
+
+ if ((perm & SGX_SECINFO_W) && !(perm & SGX_SECINFO_R))
+ return -EINVAL;
+
+ /*
+ * CPU will silently overwrite the permissions as zero, which means
+ * that we need to validate it ourselves.
+ */
+ if (pt == SGX_SECINFO_TCS && perm)
+ return -EINVAL;
+
+ if (secinfo->flags & SGX_SECINFO_RESERVED_MASK)
+ return -EINVAL;
+
+ if (memchr_inv(secinfo->reserved, 0, sizeof(secinfo->reserved)))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int __sgx_encl_add_page(struct sgx_encl *encl,
+ struct sgx_encl_page *encl_page,
+ struct sgx_epc_page *epc_page,
+ struct sgx_secinfo *secinfo, unsigned long src)
+{
+ struct sgx_pageinfo pginfo;
+ struct vm_area_struct *vma;
+ struct page *src_page;
+ int ret;
+
+ /* Deny noexec. */
+ vma = find_vma(current->mm, src);
+ if (!vma)
+ return -EFAULT;
+
+ if (!(vma->vm_flags & VM_MAYEXEC))
+ return -EACCES;
+
+ ret = get_user_pages(src, 1, 0, &src_page, NULL);
+ if (ret < 1)
+ return -EFAULT;
+
+ pginfo.secs = (unsigned long)sgx_get_epc_virt_addr(encl->secs.epc_page);
+ pginfo.addr = encl_page->desc & PAGE_MASK;
+ pginfo.metadata = (unsigned long)secinfo;
+ pginfo.contents = (unsigned long)kmap_atomic(src_page);
+
+ ret = __eadd(&pginfo, sgx_get_epc_virt_addr(epc_page));
+
+ kunmap_atomic((void *)pginfo.contents);
+ put_page(src_page);
+
+ return ret ? -EIO : 0;
+}
+
+/*
+ * If the caller requires measurement of the page as a proof for the content,
+ * use EEXTEND to add a measurement for 256 bytes of the page. Repeat this
+ * operation until the entire page is measured."
+ */
+static int __sgx_encl_extend(struct sgx_encl *encl,
+ struct sgx_epc_page *epc_page)
+{
+ unsigned long offset;
+ int ret;
+
+ for (offset = 0; offset < PAGE_SIZE; offset += SGX_EEXTEND_BLOCK_SIZE) {
+ ret = __eextend(sgx_get_epc_virt_addr(encl->secs.epc_page),
+ sgx_get_epc_virt_addr(epc_page) + offset);
+ if (ret) {
+ if (encls_failed(ret))
+ ENCLS_WARN(ret, "EEXTEND");
+
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
+static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src,
+ unsigned long offset, struct sgx_secinfo *secinfo,
+ unsigned long flags)
+{
+ struct sgx_encl_page *encl_page;
+ struct sgx_epc_page *epc_page;
+ struct sgx_va_page *va_page;
+ int ret;
+
+ encl_page = sgx_encl_page_alloc(encl, offset, secinfo->flags);
+ if (IS_ERR(encl_page))
+ return PTR_ERR(encl_page);
+
+ epc_page = sgx_alloc_epc_page(encl_page, true);
+ if (IS_ERR(epc_page)) {
+ kfree(encl_page);
+ return PTR_ERR(epc_page);
+ }
+
+ va_page = sgx_encl_grow(encl);
+ if (IS_ERR(va_page)) {
+ ret = PTR_ERR(va_page);
+ goto err_out_free;
+ }
+
+ mmap_read_lock(current->mm);
+ mutex_lock(&encl->lock);
+
+ /*
+ * Adding to encl->va_pages must be done under encl->lock. Ditto for
+ * deleting (via sgx_encl_shrink()) in the error path.
+ */
+ if (va_page)
+ list_add(&va_page->list, &encl->va_pages);
+
+ /*
+ * Insert prior to EADD in case of OOM. EADD modifies MRENCLAVE, i.e.
+ * can't be gracefully unwound, while failure on EADD/EXTEND is limited
+ * to userspace errors (or kernel/hardware bugs).
+ */
+ ret = xa_insert(&encl->page_array, PFN_DOWN(encl_page->desc),
+ encl_page, GFP_KERNEL);
+ if (ret)
+ goto err_out_unlock;
+
+ ret = __sgx_encl_add_page(encl, encl_page, epc_page, secinfo,
+ src);
+ if (ret)
+ goto err_out;
+
+ /*
+ * Complete the "add" before doing the "extend" so that the "add"
+ * isn't in a half-baked state in the extremely unlikely scenario
+ * the enclave will be destroyed in response to EEXTEND failure.
+ */
+ encl_page->encl = encl;
+ encl_page->epc_page = epc_page;
+ encl->secs_child_cnt++;
+
+ if (flags & SGX_PAGE_MEASURE) {
+ ret = __sgx_encl_extend(encl, epc_page);
+ if (ret)
+ goto err_out;
+ }
+
+ sgx_mark_page_reclaimable(encl_page->epc_page);
+ mutex_unlock(&encl->lock);
+ mmap_read_unlock(current->mm);
+ return ret;
+
+err_out:
+ xa_erase(&encl->page_array, PFN_DOWN(encl_page->desc));
+
+err_out_unlock:
+ sgx_encl_shrink(encl, va_page);
+ mutex_unlock(&encl->lock);
+ mmap_read_unlock(current->mm);
+
+err_out_free:
+ sgx_free_epc_page(epc_page);
+ kfree(encl_page);
+
+ return ret;
+}
+
+/**
+ * sgx_ioc_enclave_add_pages() - The handler for %SGX_IOC_ENCLAVE_ADD_PAGES
+ * @encl: an enclave pointer
+ * @arg: a user pointer to a struct sgx_enclave_add_pages instance
+ *
+ * Add one or more pages to an uninitialized enclave, and optionally extend the
+ * measurement with the contents of the page. The SECINFO and measurement mask
+ * are applied to all pages.
+ *
+ * A SECINFO for a TCS is required to always contain zero permissions because
+ * CPU silently zeros them. Allowing anything else would cause a mismatch in
+ * the measurement.
+ *
+ * mmap()'s protection bits are capped by the page permissions. For each page
+ * address, the maximum protection bits are computed with the following
+ * heuristics:
+ *
+ * 1. A regular page: PROT_R, PROT_W and PROT_X match the SECINFO permissions.
+ * 2. A TCS page: PROT_R | PROT_W.
+ *
+ * mmap() is not allowed to surpass the minimum of the maximum protection bits
+ * within the given address range.
+ *
+ * The function deinitializes kernel data structures for enclave and returns
+ * -EIO in any of the following conditions:
+ *
+ * - Enclave Page Cache (EPC), the physical memory holding enclaves, has
+ * been invalidated. This will cause EADD and EEXTEND to fail.
+ * - If the source address is corrupted somehow when executing EADD.
+ *
+ * Return:
+ * - 0: Success.
+ * - -EACCES: The source page is located in a noexec partition.
+ * - -ENOMEM: Out of EPC pages.
+ * - -EINTR: The call was interrupted before data was processed.
+ * - -EIO: Either EADD or EEXTEND failed because invalid source address
+ * or power cycle.
+ * - -errno: POSIX error.
+ */
+static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg)
+{
+ struct sgx_enclave_add_pages add_arg;
+ struct sgx_secinfo secinfo;
+ unsigned long c;
+ int ret;
+
+ if (!test_bit(SGX_ENCL_CREATED, &encl->flags) ||
+ test_bit(SGX_ENCL_INITIALIZED, &encl->flags))
+ return -EINVAL;
+
+ if (copy_from_user(&add_arg, arg, sizeof(add_arg)))
+ return -EFAULT;
+
+ if (!IS_ALIGNED(add_arg.offset, PAGE_SIZE) ||
+ !IS_ALIGNED(add_arg.src, PAGE_SIZE))
+ return -EINVAL;
+
+ if (!add_arg.length || add_arg.length & (PAGE_SIZE - 1))
+ return -EINVAL;
+
+ if (add_arg.offset + add_arg.length - PAGE_SIZE >= encl->size)
+ return -EINVAL;
+
+ if (copy_from_user(&secinfo, (void __user *)add_arg.secinfo,
+ sizeof(secinfo)))
+ return -EFAULT;
+
+ if (sgx_validate_secinfo(&secinfo))
+ return -EINVAL;
+
+ for (c = 0 ; c < add_arg.length; c += PAGE_SIZE) {
+ if (signal_pending(current)) {
+ if (!c)
+ ret = -ERESTARTSYS;
+
+ break;
+ }
+
+ if (need_resched())
+ cond_resched();
+
+ ret = sgx_encl_add_page(encl, add_arg.src + c, add_arg.offset + c,
+ &secinfo, add_arg.flags);
+ if (ret)
+ break;
+ }
+
+ add_arg.count = c;
+
+ if (copy_to_user(arg, &add_arg, sizeof(add_arg)))
+ return -EFAULT;
+
+ return ret;
+}
+
+static int __sgx_get_key_hash(struct crypto_shash *tfm, const void *modulus,
+ void *hash)
+{
+ SHASH_DESC_ON_STACK(shash, tfm);
+
+ shash->tfm = tfm;
+
+ return crypto_shash_digest(shash, modulus, SGX_MODULUS_SIZE, hash);
+}
+
+static int sgx_get_key_hash(const void *modulus, void *hash)
+{
+ struct crypto_shash *tfm;
+ int ret;
+
+ tfm = crypto_alloc_shash("sha256", 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ ret = __sgx_get_key_hash(tfm, modulus, hash);
+
+ crypto_free_shash(tfm);
+ return ret;
+}
+
+static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
+ void *token)
+{
+ u64 mrsigner[4];
+ int i, j, k;
+ void *addr;
+ int ret;
+
+ /*
+ * Deny initializing enclaves with attributes (namely provisioning)
+ * that have not been explicitly allowed.
+ */
+ if (encl->attributes & ~encl->attributes_mask)
+ return -EACCES;
+
+ /*
+ * Attributes should not be enforced *only* against what's available on
+ * platform (done in sgx_encl_create) but checked and enforced against
+ * the mask for enforcement in sigstruct. For example an enclave could
+ * opt to sign with AVX bit in xfrm, but still be loadable on a platform
+ * without it if the sigstruct->body.attributes_mask does not turn that
+ * bit on.
+ */
+ if (sigstruct->body.attributes & sigstruct->body.attributes_mask &
+ sgx_attributes_reserved_mask)
+ return -EINVAL;
+
+ if (sigstruct->body.miscselect & sigstruct->body.misc_mask &
+ sgx_misc_reserved_mask)
+ return -EINVAL;
+
+ if (sigstruct->body.xfrm & sigstruct->body.xfrm_mask &
+ sgx_xfrm_reserved_mask)
+ return -EINVAL;
+
+ ret = sgx_get_key_hash(sigstruct->modulus, mrsigner);
+ if (ret)
+ return ret;
+
+ mutex_lock(&encl->lock);
+
+ /*
+ * ENCLS[EINIT] is interruptible because it has such a high latency,
+ * e.g. 50k+ cycles on success. If an IRQ/NMI/SMI becomes pending,
+ * EINIT may fail with SGX_UNMASKED_EVENT so that the event can be
+ * serviced.
+ */
+ for (i = 0; i < SGX_EINIT_SLEEP_COUNT; i++) {
+ for (j = 0; j < SGX_EINIT_SPIN_COUNT; j++) {
+ addr = sgx_get_epc_virt_addr(encl->secs.epc_page);
+
+ preempt_disable();
+
+ for (k = 0; k < 4; k++)
+ wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + k, mrsigner[k]);
+
+ ret = __einit(sigstruct, token, addr);
+
+ preempt_enable();
+
+ if (ret == SGX_UNMASKED_EVENT)
+ continue;
+ else
+ break;
+ }
+
+ if (ret != SGX_UNMASKED_EVENT)
+ break;
+
+ msleep_interruptible(SGX_EINIT_SLEEP_TIME);
+
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ goto err_out;
+ }
+ }
+
+ if (ret & ENCLS_FAULT_FLAG) {
+ if (encls_failed(ret))
+ ENCLS_WARN(ret, "EINIT");
+
+ ret = -EIO;
+ } else if (ret) {
+ pr_debug("EINIT returned %d\n", ret);
+ ret = -EPERM;
+ } else {
+ set_bit(SGX_ENCL_INITIALIZED, &encl->flags);
+ }
+
+err_out:
+ mutex_unlock(&encl->lock);
+ return ret;
+}
+
+/**
+ * sgx_ioc_enclave_init() - handler for %SGX_IOC_ENCLAVE_INIT
+ * @encl: an enclave pointer
+ * @arg: userspace pointer to a struct sgx_enclave_init instance
+ *
+ * Flush any outstanding enqueued EADD operations and perform EINIT. The
+ * Launch Enclave Public Key Hash MSRs are rewritten as necessary to match
+ * the enclave's MRSIGNER, which is caculated from the provided sigstruct.
+ *
+ * Return:
+ * - 0: Success.
+ * - -EPERM: Invalid SIGSTRUCT.
+ * - -EIO: EINIT failed because of a power cycle.
+ * - -errno: POSIX error.
+ */
+static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg)
+{
+ struct sgx_sigstruct *sigstruct;
+ struct sgx_enclave_init init_arg;
+ struct page *initp_page;
+ void *token;
+ int ret;
+
+ if (!test_bit(SGX_ENCL_CREATED, &encl->flags) ||
+ test_bit(SGX_ENCL_INITIALIZED, &encl->flags))
+ return -EINVAL;
+
+ if (copy_from_user(&init_arg, arg, sizeof(init_arg)))
+ return -EFAULT;
+
+ initp_page = alloc_page(GFP_KERNEL);
+ if (!initp_page)
+ return -ENOMEM;
+
+ sigstruct = kmap(initp_page);
+ token = (void *)((unsigned long)sigstruct + PAGE_SIZE / 2);
+ memset(token, 0, SGX_LAUNCH_TOKEN_SIZE);
+
+ if (copy_from_user(sigstruct, (void __user *)init_arg.sigstruct,
+ sizeof(*sigstruct))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ /*
+ * A legacy field used with Intel signed enclaves. These used to mean
+ * regular and architectural enclaves. The CPU only accepts these values
+ * but they do not have any other meaning.
+ *
+ * Thus, reject any other values.
+ */
+ if (sigstruct->header.vendor != 0x0000 &&
+ sigstruct->header.vendor != 0x8086) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = sgx_encl_init(encl, sigstruct, token);
+
+out:
+ kunmap(initp_page);
+ __free_page(initp_page);
+ return ret;
+}
+
+/**
+ * sgx_ioc_enclave_provision() - handler for %SGX_IOC_ENCLAVE_PROVISION
+ * @encl: an enclave pointer
+ * @arg: userspace pointer to a struct sgx_enclave_provision instance
+ *
+ * Allow ATTRIBUTE.PROVISION_KEY for an enclave by providing a file handle to
+ * /dev/sgx_provision.
+ *
+ * Return:
+ * - 0: Success.
+ * - -errno: Otherwise.
+ */
+static long sgx_ioc_enclave_provision(struct sgx_encl *encl, void __user *arg)
+{
+ struct sgx_enclave_provision params;
+ struct file *file;
+
+ if (copy_from_user(&params, arg, sizeof(params)))
+ return -EFAULT;
+
+ file = fget(params.fd);
+ if (!file)
+ return -EINVAL;
+
+ if (file->f_op != &sgx_provision_fops) {
+ fput(file);
+ return -EINVAL;
+ }
+
+ encl->attributes_mask |= SGX_ATTR_PROVISIONKEY;
+
+ fput(file);
+ return 0;
+}
+
+long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+ struct sgx_encl *encl = filep->private_data;
+ int ret;
+
+ if (test_and_set_bit(SGX_ENCL_IOCTL, &encl->flags))
+ return -EBUSY;
+
+ switch (cmd) {
+ case SGX_IOC_ENCLAVE_CREATE:
+ ret = sgx_ioc_enclave_create(encl, (void __user *)arg);
+ break;
+ case SGX_IOC_ENCLAVE_ADD_PAGES:
+ ret = sgx_ioc_enclave_add_pages(encl, (void __user *)arg);
+ break;
+ case SGX_IOC_ENCLAVE_INIT:
+ ret = sgx_ioc_enclave_init(encl, (void __user *)arg);
+ break;
+ case SGX_IOC_ENCLAVE_PROVISION:
+ ret = sgx_ioc_enclave_provision(encl, (void __user *)arg);
+ break;
+ default:
+ ret = -ENOIOCTLCMD;
+ break;
+ }
+
+ clear_bit(SGX_ENCL_IOCTL, &encl->flags);
+ return ret;
+}
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
new file mode 100644
index 000000000000..c519fc5f6948
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -0,0 +1,733 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <linux/freezer.h>
+#include <linux/highmem.h>
+#include <linux/kthread.h>
+#include <linux/pagemap.h>
+#include <linux/ratelimit.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include "driver.h"
+#include "encl.h"
+#include "encls.h"
+
+struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
+static int sgx_nr_epc_sections;
+static struct task_struct *ksgxd_tsk;
+static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq);
+
+/*
+ * These variables are part of the state of the reclaimer, and must be accessed
+ * with sgx_reclaimer_lock acquired.
+ */
+static LIST_HEAD(sgx_active_page_list);
+
+static DEFINE_SPINLOCK(sgx_reclaimer_lock);
+
+/*
+ * Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS
+ * pages whose child pages blocked EREMOVE.
+ */
+static void sgx_sanitize_section(struct sgx_epc_section *section)
+{
+ struct sgx_epc_page *page;
+ LIST_HEAD(dirty);
+ int ret;
+
+ /* init_laundry_list is thread-local, no need for a lock: */
+ while (!list_empty(&section->init_laundry_list)) {
+ if (kthread_should_stop())
+ return;
+
+ /* needed for access to ->page_list: */
+ spin_lock(&section->lock);
+
+ page = list_first_entry(&section->init_laundry_list,
+ struct sgx_epc_page, list);
+
+ ret = __eremove(sgx_get_epc_virt_addr(page));
+ if (!ret)
+ list_move(&page->list, &section->page_list);
+ else
+ list_move_tail(&page->list, &dirty);
+
+ spin_unlock(&section->lock);
+
+ cond_resched();
+ }
+
+ list_splice(&dirty, &section->init_laundry_list);
+}
+
+static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
+{
+ struct sgx_encl_page *page = epc_page->owner;
+ struct sgx_encl *encl = page->encl;
+ struct sgx_encl_mm *encl_mm;
+ bool ret = true;
+ int idx;
+
+ idx = srcu_read_lock(&encl->srcu);
+
+ list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+ if (!mmget_not_zero(encl_mm->mm))
+ continue;
+
+ mmap_read_lock(encl_mm->mm);
+ ret = !sgx_encl_test_and_clear_young(encl_mm->mm, page);
+ mmap_read_unlock(encl_mm->mm);
+
+ mmput_async(encl_mm->mm);
+
+ if (!ret)
+ break;
+ }
+
+ srcu_read_unlock(&encl->srcu, idx);
+
+ if (!ret)
+ return false;
+
+ return true;
+}
+
+static void sgx_reclaimer_block(struct sgx_epc_page *epc_page)
+{
+ struct sgx_encl_page *page = epc_page->owner;
+ unsigned long addr = page->desc & PAGE_MASK;
+ struct sgx_encl *encl = page->encl;
+ unsigned long mm_list_version;
+ struct sgx_encl_mm *encl_mm;
+ struct vm_area_struct *vma;
+ int idx, ret;
+
+ do {
+ mm_list_version = encl->mm_list_version;
+
+ /* Pairs with smp_rmb() in sgx_encl_mm_add(). */
+ smp_rmb();
+
+ idx = srcu_read_lock(&encl->srcu);
+
+ list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+ if (!mmget_not_zero(encl_mm->mm))
+ continue;
+
+ mmap_read_lock(encl_mm->mm);
+
+ ret = sgx_encl_find(encl_mm->mm, addr, &vma);
+ if (!ret && encl == vma->vm_private_data)
+ zap_vma_ptes(vma, addr, PAGE_SIZE);
+
+ mmap_read_unlock(encl_mm->mm);
+
+ mmput_async(encl_mm->mm);
+ }
+
+ srcu_read_unlock(&encl->srcu, idx);
+ } while (unlikely(encl->mm_list_version != mm_list_version));
+
+ mutex_lock(&encl->lock);
+
+ ret = __eblock(sgx_get_epc_virt_addr(epc_page));
+ if (encls_failed(ret))
+ ENCLS_WARN(ret, "EBLOCK");
+
+ mutex_unlock(&encl->lock);
+}
+
+static int __sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot,
+ struct sgx_backing *backing)
+{
+ struct sgx_pageinfo pginfo;
+ int ret;
+
+ pginfo.addr = 0;
+ pginfo.secs = 0;
+
+ pginfo.contents = (unsigned long)kmap_atomic(backing->contents);
+ pginfo.metadata = (unsigned long)kmap_atomic(backing->pcmd) +
+ backing->pcmd_offset;
+
+ ret = __ewb(&pginfo, sgx_get_epc_virt_addr(epc_page), va_slot);
+
+ kunmap_atomic((void *)(unsigned long)(pginfo.metadata -
+ backing->pcmd_offset));
+ kunmap_atomic((void *)(unsigned long)pginfo.contents);
+
+ return ret;
+}
+
+static void sgx_ipi_cb(void *info)
+{
+}
+
+static const cpumask_t *sgx_encl_ewb_cpumask(struct sgx_encl *encl)
+{
+ cpumask_t *cpumask = &encl->cpumask;
+ struct sgx_encl_mm *encl_mm;
+ int idx;
+
+ /*
+ * Can race with sgx_encl_mm_add(), but ETRACK has already been
+ * executed, which means that the CPUs running in the new mm will enter
+ * into the enclave with a fresh epoch.
+ */
+ cpumask_clear(cpumask);
+
+ idx = srcu_read_lock(&encl->srcu);
+
+ list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+ if (!mmget_not_zero(encl_mm->mm))
+ continue;
+
+ cpumask_or(cpumask, cpumask, mm_cpumask(encl_mm->mm));
+
+ mmput_async(encl_mm->mm);
+ }
+
+ srcu_read_unlock(&encl->srcu, idx);
+
+ return cpumask;
+}
+
+/*
+ * Swap page to the regular memory transformed to the blocked state by using
+ * EBLOCK, which means that it can no loger be referenced (no new TLB entries).
+ *
+ * The first trial just tries to write the page assuming that some other thread
+ * has reset the count for threads inside the enlave by using ETRACK, and
+ * previous thread count has been zeroed out. The second trial calls ETRACK
+ * before EWB. If that fails we kick all the HW threads out, and then do EWB,
+ * which should be guaranteed the succeed.
+ */
+static void sgx_encl_ewb(struct sgx_epc_page *epc_page,
+ struct sgx_backing *backing)
+{
+ struct sgx_encl_page *encl_page = epc_page->owner;
+ struct sgx_encl *encl = encl_page->encl;
+ struct sgx_va_page *va_page;
+ unsigned int va_offset;
+ void *va_slot;
+ int ret;
+
+ encl_page->desc &= ~SGX_ENCL_PAGE_BEING_RECLAIMED;
+
+ va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
+ list);
+ va_offset = sgx_alloc_va_slot(va_page);
+ va_slot = sgx_get_epc_virt_addr(va_page->epc_page) + va_offset;
+ if (sgx_va_page_full(va_page))
+ list_move_tail(&va_page->list, &encl->va_pages);
+
+ ret = __sgx_encl_ewb(epc_page, va_slot, backing);
+ if (ret == SGX_NOT_TRACKED) {
+ ret = __etrack(sgx_get_epc_virt_addr(encl->secs.epc_page));
+ if (ret) {
+ if (encls_failed(ret))
+ ENCLS_WARN(ret, "ETRACK");
+ }
+
+ ret = __sgx_encl_ewb(epc_page, va_slot, backing);
+ if (ret == SGX_NOT_TRACKED) {
+ /*
+ * Slow path, send IPIs to kick cpus out of the
+ * enclave. Note, it's imperative that the cpu
+ * mask is generated *after* ETRACK, else we'll
+ * miss cpus that entered the enclave between
+ * generating the mask and incrementing epoch.
+ */
+ on_each_cpu_mask(sgx_encl_ewb_cpumask(encl),
+ sgx_ipi_cb, NULL, 1);
+ ret = __sgx_encl_ewb(epc_page, va_slot, backing);
+ }
+ }
+
+ if (ret) {
+ if (encls_failed(ret))
+ ENCLS_WARN(ret, "EWB");
+
+ sgx_free_va_slot(va_page, va_offset);
+ } else {
+ encl_page->desc |= va_offset;
+ encl_page->va_page = va_page;
+ }
+}
+
+static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
+ struct sgx_backing *backing)
+{
+ struct sgx_encl_page *encl_page = epc_page->owner;
+ struct sgx_encl *encl = encl_page->encl;
+ struct sgx_backing secs_backing;
+ int ret;
+
+ mutex_lock(&encl->lock);
+
+ sgx_encl_ewb(epc_page, backing);
+ encl_page->epc_page = NULL;
+ encl->secs_child_cnt--;
+
+ if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) {
+ ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size),
+ &secs_backing);
+ if (ret)
+ goto out;
+
+ sgx_encl_ewb(encl->secs.epc_page, &secs_backing);
+
+ sgx_free_epc_page(encl->secs.epc_page);
+ encl->secs.epc_page = NULL;
+
+ sgx_encl_put_backing(&secs_backing, true);
+ }
+
+out:
+ mutex_unlock(&encl->lock);
+}
+
+/*
+ * Take a fixed number of pages from the head of the active page pool and
+ * reclaim them to the enclave's private shmem files. Skip the pages, which have
+ * been accessed since the last scan. Move those pages to the tail of active
+ * page pool so that the pages get scanned in LRU like fashion.
+ *
+ * Batch process a chunk of pages (at the moment 16) in order to degrade amount
+ * of IPI's and ETRACK's potentially required. sgx_encl_ewb() does degrade a bit
+ * among the HW threads with three stage EWB pipeline (EWB, ETRACK + EWB and IPI
+ * + EWB) but not sufficiently. Reclaiming one page at a time would also be
+ * problematic as it would increase the lock contention too much, which would
+ * halt forward progress.
+ */
+static void sgx_reclaim_pages(void)
+{
+ struct sgx_epc_page *chunk[SGX_NR_TO_SCAN];
+ struct sgx_backing backing[SGX_NR_TO_SCAN];
+ struct sgx_epc_section *section;
+ struct sgx_encl_page *encl_page;
+ struct sgx_epc_page *epc_page;
+ pgoff_t page_index;
+ int cnt = 0;
+ int ret;
+ int i;
+
+ spin_lock(&sgx_reclaimer_lock);
+ for (i = 0; i < SGX_NR_TO_SCAN; i++) {
+ if (list_empty(&sgx_active_page_list))
+ break;
+
+ epc_page = list_first_entry(&sgx_active_page_list,
+ struct sgx_epc_page, list);
+ list_del_init(&epc_page->list);
+ encl_page = epc_page->owner;
+
+ if (kref_get_unless_zero(&encl_page->encl->refcount) != 0)
+ chunk[cnt++] = epc_page;
+ else
+ /* The owner is freeing the page. No need to add the
+ * page back to the list of reclaimable pages.
+ */
+ epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
+ }
+ spin_unlock(&sgx_reclaimer_lock);
+
+ for (i = 0; i < cnt; i++) {
+ epc_page = chunk[i];
+ encl_page = epc_page->owner;
+
+ if (!sgx_reclaimer_age(epc_page))
+ goto skip;
+
+ page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
+ ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]);
+ if (ret)
+ goto skip;
+
+ mutex_lock(&encl_page->encl->lock);
+ encl_page->desc |= SGX_ENCL_PAGE_BEING_RECLAIMED;
+ mutex_unlock(&encl_page->encl->lock);
+ continue;
+
+skip:
+ spin_lock(&sgx_reclaimer_lock);
+ list_add_tail(&epc_page->list, &sgx_active_page_list);
+ spin_unlock(&sgx_reclaimer_lock);
+
+ kref_put(&encl_page->encl->refcount, sgx_encl_release);
+
+ chunk[i] = NULL;
+ }
+
+ for (i = 0; i < cnt; i++) {
+ epc_page = chunk[i];
+ if (epc_page)
+ sgx_reclaimer_block(epc_page);
+ }
+
+ for (i = 0; i < cnt; i++) {
+ epc_page = chunk[i];
+ if (!epc_page)
+ continue;
+
+ encl_page = epc_page->owner;
+ sgx_reclaimer_write(epc_page, &backing[i]);
+ sgx_encl_put_backing(&backing[i], true);
+
+ kref_put(&encl_page->encl->refcount, sgx_encl_release);
+ epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
+
+ section = &sgx_epc_sections[epc_page->section];
+ spin_lock(&section->lock);
+ list_add_tail(&epc_page->list, &section->page_list);
+ section->free_cnt++;
+ spin_unlock(&section->lock);
+ }
+}
+
+static unsigned long sgx_nr_free_pages(void)
+{
+ unsigned long cnt = 0;
+ int i;
+
+ for (i = 0; i < sgx_nr_epc_sections; i++)
+ cnt += sgx_epc_sections[i].free_cnt;
+
+ return cnt;
+}
+
+static bool sgx_should_reclaim(unsigned long watermark)
+{
+ return sgx_nr_free_pages() < watermark &&
+ !list_empty(&sgx_active_page_list);
+}
+
+static int ksgxd(void *p)
+{
+ int i;
+
+ set_freezable();
+
+ /*
+ * Sanitize pages in order to recover from kexec(). The 2nd pass is
+ * required for SECS pages, whose child pages blocked EREMOVE.
+ */
+ for (i = 0; i < sgx_nr_epc_sections; i++)
+ sgx_sanitize_section(&sgx_epc_sections[i]);
+
+ for (i = 0; i < sgx_nr_epc_sections; i++) {
+ sgx_sanitize_section(&sgx_epc_sections[i]);
+
+ /* Should never happen. */
+ if (!list_empty(&sgx_epc_sections[i].init_laundry_list))
+ WARN(1, "EPC section %d has unsanitized pages.\n", i);
+ }
+
+ while (!kthread_should_stop()) {
+ if (try_to_freeze())
+ continue;
+
+ wait_event_freezable(ksgxd_waitq,
+ kthread_should_stop() ||
+ sgx_should_reclaim(SGX_NR_HIGH_PAGES));
+
+ if (sgx_should_reclaim(SGX_NR_HIGH_PAGES))
+ sgx_reclaim_pages();
+
+ cond_resched();
+ }
+
+ return 0;
+}
+
+static bool __init sgx_page_reclaimer_init(void)
+{
+ struct task_struct *tsk;
+
+ tsk = kthread_run(ksgxd, NULL, "ksgxd");
+ if (IS_ERR(tsk))
+ return false;
+
+ ksgxd_tsk = tsk;
+
+ return true;
+}
+
+static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_section *section)
+{
+ struct sgx_epc_page *page;
+
+ spin_lock(&section->lock);
+
+ if (list_empty(&section->page_list)) {
+ spin_unlock(&section->lock);
+ return NULL;
+ }
+
+ page = list_first_entry(&section->page_list, struct sgx_epc_page, list);
+ list_del_init(&page->list);
+ section->free_cnt--;
+
+ spin_unlock(&section->lock);
+ return page;
+}
+
+/**
+ * __sgx_alloc_epc_page() - Allocate an EPC page
+ *
+ * Iterate through EPC sections and borrow a free EPC page to the caller. When a
+ * page is no longer needed it must be released with sgx_free_epc_page().
+ *
+ * Return:
+ * an EPC page,
+ * -errno on error
+ */
+struct sgx_epc_page *__sgx_alloc_epc_page(void)
+{
+ struct sgx_epc_section *section;
+ struct sgx_epc_page *page;
+ int i;
+
+ for (i = 0; i < sgx_nr_epc_sections; i++) {
+ section = &sgx_epc_sections[i];
+
+ page = __sgx_alloc_epc_page_from_section(section);
+ if (page)
+ return page;
+ }
+
+ return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * sgx_mark_page_reclaimable() - Mark a page as reclaimable
+ * @page: EPC page
+ *
+ * Mark a page as reclaimable and add it to the active page list. Pages
+ * are automatically removed from the active list when freed.
+ */
+void sgx_mark_page_reclaimable(struct sgx_epc_page *page)
+{
+ spin_lock(&sgx_reclaimer_lock);
+ page->flags |= SGX_EPC_PAGE_RECLAIMER_TRACKED;
+ list_add_tail(&page->list, &sgx_active_page_list);
+ spin_unlock(&sgx_reclaimer_lock);
+}
+
+/**
+ * sgx_unmark_page_reclaimable() - Remove a page from the reclaim list
+ * @page: EPC page
+ *
+ * Clear the reclaimable flag and remove the page from the active page list.
+ *
+ * Return:
+ * 0 on success,
+ * -EBUSY if the page is in the process of being reclaimed
+ */
+int sgx_unmark_page_reclaimable(struct sgx_epc_page *page)
+{
+ spin_lock(&sgx_reclaimer_lock);
+ if (page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED) {
+ /* The page is being reclaimed. */
+ if (list_empty(&page->list)) {
+ spin_unlock(&sgx_reclaimer_lock);
+ return -EBUSY;
+ }
+
+ list_del(&page->list);
+ page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
+ }
+ spin_unlock(&sgx_reclaimer_lock);
+
+ return 0;
+}
+
+/**
+ * sgx_alloc_epc_page() - Allocate an EPC page
+ * @owner: the owner of the EPC page
+ * @reclaim: reclaim pages if necessary
+ *
+ * Iterate through EPC sections and borrow a free EPC page to the caller. When a
+ * page is no longer needed it must be released with sgx_free_epc_page(). If
+ * @reclaim is set to true, directly reclaim pages when we are out of pages. No
+ * mm's can be locked when @reclaim is set to true.
+ *
+ * Finally, wake up ksgxd when the number of pages goes below the watermark
+ * before returning back to the caller.
+ *
+ * Return:
+ * an EPC page,
+ * -errno on error
+ */
+struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim)
+{
+ struct sgx_epc_page *page;
+
+ for ( ; ; ) {
+ page = __sgx_alloc_epc_page();
+ if (!IS_ERR(page)) {
+ page->owner = owner;
+ break;
+ }
+
+ if (list_empty(&sgx_active_page_list))
+ return ERR_PTR(-ENOMEM);
+
+ if (!reclaim) {
+ page = ERR_PTR(-EBUSY);
+ break;
+ }
+
+ if (signal_pending(current)) {
+ page = ERR_PTR(-ERESTARTSYS);
+ break;
+ }
+
+ sgx_reclaim_pages();
+ cond_resched();
+ }
+
+ if (sgx_should_reclaim(SGX_NR_LOW_PAGES))
+ wake_up(&ksgxd_waitq);
+
+ return page;
+}
+
+/**
+ * sgx_free_epc_page() - Free an EPC page
+ * @page: an EPC page
+ *
+ * Call EREMOVE for an EPC page and insert it back to the list of free pages.
+ */
+void sgx_free_epc_page(struct sgx_epc_page *page)
+{
+ struct sgx_epc_section *section = &sgx_epc_sections[page->section];
+ int ret;
+
+ WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+
+ ret = __eremove(sgx_get_epc_virt_addr(page));
+ if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret))
+ return;
+
+ spin_lock(&section->lock);
+ list_add_tail(&page->list, &section->page_list);
+ section->free_cnt++;
+ spin_unlock(&section->lock);
+}
+
+static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
+ unsigned long index,
+ struct sgx_epc_section *section)
+{
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+ unsigned long i;
+
+ section->virt_addr = memremap(phys_addr, size, MEMREMAP_WB);
+ if (!section->virt_addr)
+ return false;
+
+ section->pages = vmalloc(nr_pages * sizeof(struct sgx_epc_page));
+ if (!section->pages) {
+ memunmap(section->virt_addr);
+ return false;
+ }
+
+ section->phys_addr = phys_addr;
+ spin_lock_init(&section->lock);
+ INIT_LIST_HEAD(&section->page_list);
+ INIT_LIST_HEAD(&section->init_laundry_list);
+
+ for (i = 0; i < nr_pages; i++) {
+ section->pages[i].section = index;
+ section->pages[i].flags = 0;
+ section->pages[i].owner = NULL;
+ list_add_tail(&section->pages[i].list, &section->init_laundry_list);
+ }
+
+ section->free_cnt = nr_pages;
+ return true;
+}
+
+/**
+ * A section metric is concatenated in a way that @low bits 12-31 define the
+ * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the
+ * metric.
+ */
+static inline u64 __init sgx_calc_section_metric(u64 low, u64 high)
+{
+ return (low & GENMASK_ULL(31, 12)) +
+ ((high & GENMASK_ULL(19, 0)) << 32);
+}
+
+static bool __init sgx_page_cache_init(void)
+{
+ u32 eax, ebx, ecx, edx, type;
+ u64 pa, size;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(sgx_epc_sections); i++) {
+ cpuid_count(SGX_CPUID, i + SGX_CPUID_EPC, &eax, &ebx, &ecx, &edx);
+
+ type = eax & SGX_CPUID_EPC_MASK;
+ if (type == SGX_CPUID_EPC_INVALID)
+ break;
+
+ if (type != SGX_CPUID_EPC_SECTION) {
+ pr_err_once("Unknown EPC section type: %u\n", type);
+ break;
+ }
+
+ pa = sgx_calc_section_metric(eax, ebx);
+ size = sgx_calc_section_metric(ecx, edx);
+
+ pr_info("EPC section 0x%llx-0x%llx\n", pa, pa + size - 1);
+
+ if (!sgx_setup_epc_section(pa, size, i, &sgx_epc_sections[i])) {
+ pr_err("No free memory for an EPC section\n");
+ break;
+ }
+
+ sgx_nr_epc_sections++;
+ }
+
+ if (!sgx_nr_epc_sections) {
+ pr_err("There are zero EPC sections.\n");
+ return false;
+ }
+
+ return true;
+}
+
+static void __init sgx_init(void)
+{
+ int ret;
+ int i;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SGX))
+ return;
+
+ if (!sgx_page_cache_init())
+ return;
+
+ if (!sgx_page_reclaimer_init())
+ goto err_page_cache;
+
+ ret = sgx_drv_init();
+ if (ret)
+ goto err_kthread;
+
+ return;
+
+err_kthread:
+ kthread_stop(ksgxd_tsk);
+
+err_page_cache:
+ for (i = 0; i < sgx_nr_epc_sections; i++) {
+ vfree(sgx_epc_sections[i].pages);
+ memunmap(sgx_epc_sections[i].virt_addr);
+ }
+}
+
+device_initcall(sgx_init);
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
new file mode 100644
index 000000000000..5fa42d143feb
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_SGX_H
+#define _X86_SGX_H
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/rwsem.h>
+#include <linux/types.h>
+#include <asm/asm.h>
+#include "arch.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "sgx: " fmt
+
+#define SGX_MAX_EPC_SECTIONS 8
+#define SGX_EEXTEND_BLOCK_SIZE 256
+#define SGX_NR_TO_SCAN 16
+#define SGX_NR_LOW_PAGES 32
+#define SGX_NR_HIGH_PAGES 64
+
+/* Pages, which are being tracked by the page reclaimer. */
+#define SGX_EPC_PAGE_RECLAIMER_TRACKED BIT(0)
+
+struct sgx_epc_page {
+ unsigned int section;
+ unsigned int flags;
+ struct sgx_encl_page *owner;
+ struct list_head list;
+};
+
+/*
+ * The firmware can define multiple chunks of EPC to the different areas of the
+ * physical memory e.g. for memory areas of the each node. This structure is
+ * used to store EPC pages for one EPC section and virtual memory area where
+ * the pages have been mapped.
+ *
+ * 'lock' must be held before accessing 'page_list' or 'free_cnt'.
+ */
+struct sgx_epc_section {
+ unsigned long phys_addr;
+ void *virt_addr;
+ struct sgx_epc_page *pages;
+
+ spinlock_t lock;
+ struct list_head page_list;
+ unsigned long free_cnt;
+
+ /*
+ * Pages which need EREMOVE run on them before they can be
+ * used. Only safe to be accessed in ksgxd and init code.
+ * Not protected by locks.
+ */
+ struct list_head init_laundry_list;
+};
+
+extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
+
+static inline unsigned long sgx_get_epc_phys_addr(struct sgx_epc_page *page)
+{
+ struct sgx_epc_section *section = &sgx_epc_sections[page->section];
+ unsigned long index;
+
+ index = ((unsigned long)page - (unsigned long)section->pages) / sizeof(*page);
+
+ return section->phys_addr + index * PAGE_SIZE;
+}
+
+static inline void *sgx_get_epc_virt_addr(struct sgx_epc_page *page)
+{
+ struct sgx_epc_section *section = &sgx_epc_sections[page->section];
+ unsigned long index;
+
+ index = ((unsigned long)page - (unsigned long)section->pages) / sizeof(*page);
+
+ return section->virt_addr + index * PAGE_SIZE;
+}
+
+struct sgx_epc_page *__sgx_alloc_epc_page(void);
+void sgx_free_epc_page(struct sgx_epc_page *page);
+
+void sgx_mark_page_reclaimable(struct sgx_epc_page *page);
+int sgx_unmark_page_reclaimable(struct sgx_epc_page *page);
+struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim);
+
+#endif /* _X86_SGX_H */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e19df6cde35d..7798d862983f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -60,6 +60,7 @@
#include <asm/umip.h>
#include <asm/insn.h>
#include <asm/insn-eval.h>
+#include <asm/vdso.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -117,6 +118,9 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str,
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = trapnr;
die(str, regs, error_code);
+ } else {
+ if (fixup_vdso_exception(regs, trapnr, error_code, 0))
+ return 0;
}
/*
@@ -550,6 +554,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
+ if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0))
+ return;
+
show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
force_sig(SIGSEGV);
goto exit;
@@ -1048,6 +1055,9 @@ static void math_error(struct pt_regs *regs, int trapnr)
if (!si_code)
goto exit;
+ if (fixup_vdso_exception(regs, trapnr, 0, 0))
+ return;
+
force_sig_fault(SIGFPE, si_code,
(void __user *)uprobe_get_trap_addr(regs));
exit:
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 82bf37a5c9ec..f1f1b5a0956a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -30,6 +30,7 @@
#include <asm/cpu_entry_area.h> /* exception stack */
#include <asm/pgtable_areas.h> /* VMALLOC_START, ... */
#include <asm/kvm_para.h> /* kvm_handle_async_pf */
+#include <asm/vdso.h> /* fixup_vdso_exception() */
#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>
@@ -602,11 +603,9 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code,
oops_end(flags, regs, sig);
}
-static void set_signal_archinfo(unsigned long address,
- unsigned long error_code)
+static void sanitize_error_code(unsigned long address,
+ unsigned long *error_code)
{
- struct task_struct *tsk = current;
-
/*
* To avoid leaking information about the kernel page
* table layout, pretend that user-mode accesses to
@@ -617,7 +616,13 @@ static void set_signal_archinfo(unsigned long address,
* information and does not appear to cause any problems.
*/
if (address >= TASK_SIZE_MAX)
- error_code |= X86_PF_PROT;
+ *error_code |= X86_PF_PROT;
+}
+
+static void set_signal_archinfo(unsigned long address,
+ unsigned long error_code)
+{
+ struct task_struct *tsk = current;
tsk->thread.trap_nr = X86_TRAP_PF;
tsk->thread.error_code = error_code | X86_PF_USER;
@@ -658,6 +663,8 @@ no_context(struct pt_regs *regs, unsigned long error_code,
* faulting through the emulate_vsyscall() logic.
*/
if (current->thread.sig_on_uaccess_err && signal) {
+ sanitize_error_code(address, &error_code);
+
set_signal_archinfo(address, error_code);
/* XXX: hwpoison faults will set the wrong code. */
@@ -806,13 +813,10 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
if (is_errata100(regs, address))
return;
- /*
- * To avoid leaking information about the kernel page table
- * layout, pretend that user-mode accesses to kernel addresses
- * are always protection faults.
- */
- if (address >= TASK_SIZE_MAX)
- error_code |= X86_PF_PROT;
+ sanitize_error_code(address, &error_code);
+
+ if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
+ return;
if (likely(show_unhandled_signals))
show_signal_msg(regs, error_code, address, tsk);
@@ -931,6 +935,11 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
if (is_prefetch(regs, error_code, address))
return;
+ sanitize_error_code(address, &error_code);
+
+ if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
+ return;
+
set_signal_archinfo(address, error_code);
#ifdef CONFIG_MEMORY_FAILURE
@@ -1102,6 +1111,18 @@ access_error(unsigned long error_code, struct vm_area_struct *vma)
return 1;
/*
+ * SGX hardware blocked the access. This usually happens
+ * when the enclave memory contents have been destroyed, like
+ * after a suspend/resume cycle. In any case, the kernel can't
+ * fix the cause of the fault. Handle the fault as an access
+ * error even in cases where no actual access violation
+ * occurred. This allows userspace to rebuild the enclave in
+ * response to the signal.
+ */
+ if (unlikely(error_code & X86_PF_SGX))
+ return 1;
+
+ /*
* Make sure to check the VMA so that we do not perform
* faults just to hit a X86_PF_PK as soon as we fill in a
* page.