From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 70d3b8ddcd20d3c859676f56c43c7b2360c70266 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Define the SGX architectural data structures used by various SGX functions. This is not an exhaustive representation of all SGX data structures but only those needed by the kernel.

The goal is to sequester hardware structures in "sgx/arch.h" and keep them separate from kernel-internal or uapi structures.

The data structures are described in Intel SDM section 37.6.

Intel-SIG: commit 70d3b8ddcd20 x86/sgx: Add SGX architectural data structures Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-2-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/arch.h | 338 +++++++++++++++++++++++++++++++++ 1 file changed, 338 insertions(+) create mode 100644 arch/x86/kernel/cpu/sgx/arch.h

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 */

From: Sean Christopherson sean.j.christopherson@intel.com

mainline inclusion from mainline-v5.11-rc1 commit e7b6385b01d8e9fb7a97887c3ea649abb95bb8c8 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Populate X86_FEATURE_SGX feature from CPUID and tie it to the Kconfig option with disabled-features.h.

IA32_FEATURE_CONTROL.SGX_ENABLE must be examined in addition to the CPUID bits to enable full SGX support. The BIOS must both set this bit and lock IA32_FEATURE_CONTROL for SGX to be supported (Intel SDM section 36.7.1). The setting or clearing of this bit has no impact on the CPUID bits above, which is why it needs to be detected separately.

Intel-SIG: commit e7b6385b01d8 x86/cpufeatures: Add Intel SGX hardware bits Backport for SGX Foundations support

Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Co-developed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-4-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/disabled-features.h | 8 +++++++- arch/x86/include/asm/msr-index.h | 1 + 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index dad350d42ecf..1181f5c7bbef 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 */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 09db5b8f1444..018654e65c60 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -59,6 +59,12 @@ /* Force disable because it's broken beyond repair */ #define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))

+#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 */ @@ -71,7 +77,7 @@ #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/msr-index.h b/arch/x86/include/asm/msr-index.h index c36a083c8ec0..1a333c4d2079 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -610,6 +610,7 @@ #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_ENABLED BIT(18) #define FEAT_CTL_LMCE_ENABLED BIT(20)

#define MSR_IA32_TSC_ADJUST 0x0000003b

From: Sean Christopherson sean.j.christopherson@intel.com

mainline inclusion from mainline-v5.11-rc1 commit e7e0545299d8cb0fd6fe3ba50401b7f5c3937362 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Although carved out of normal DRAM, enclave memory is marked in the system memory map as reserved and is not managed by the core mm. There may be several regions spread across the system. Each contiguous region is called an Enclave Page Cache (EPC) section. EPC sections are enumerated via CPUID

Enclave pages can only be accessed when they are mapped as part of an enclave, by a hardware thread running inside the enclave.

Parse CPUID data, create metadata for EPC pages and populate a simple EPC page allocator. Although much smaller, ‘struct sgx_epc_page’ metadata is the SGX analog of the core mm ‘struct page’.

Similar to how the core mm’s page->flags encode zone and NUMA information, embed the EPC section index to the first eight bits of sgx_epc_page->desc. This allows a quick reverse lookup from EPC page to EPC section. Existing client hardware supports only a single section, while upcoming server hardware will support at most eight sections. Thus, eight bits should be enough for long term needs.

Intel-SIG: commit e7e0545299d8 x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Backport for SGX Foundations support

Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Co-developed-by: Serge Ayoun serge.ayoun@intel.com Signed-off-by: Serge Ayoun serge.ayoun@intel.com Co-developed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-6-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/Kconfig | 17 +++ arch/x86/kernel/cpu/Makefile | 1 + arch/x86/kernel/cpu/sgx/Makefile | 2 + arch/x86/kernel/cpu/sgx/main.c | 190 +++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/sgx/sgx.h | 60 ++++++++++ 5 files changed, 270 insertions(+) create mode 100644 arch/x86/kernel/cpu/sgx/Makefile create mode 100644 arch/x86/kernel/cpu/sgx/main.c create mode 100644 arch/x86/kernel/cpu/sgx/sgx.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d3176a41a29..5cccb82ca62f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1959,6 +1959,23 @@ 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/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/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile new file mode 100644 index 000000000000..79510ce01b3b --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/Makefile @@ -0,0 +1,2 @@ +obj-y += \ + main.o diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c new file mode 100644 index 000000000000..187a237eec38 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -0,0 +1,190 @@ +// 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 "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; + +/* + * 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; + + while (!list_empty(&section->laundry_list)) { + if (kthread_should_stop()) + return; + + spin_lock(&section->lock); + + page = list_first_entry(&section->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->laundry_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].laundry_list)) + WARN(1, "EPC section %d has unsanitized pages.\n", i); + } + + 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 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->laundry_list); + + for (i = 0; i < nr_pages; i++) { + section->pages[i].section = index; + list_add_tail(&section->pages[i].list, &section->laundry_list); + } + + 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 i; + + if (!boot_cpu_has(X86_FEATURE_SGX)) + return; + + if (!sgx_page_cache_init()) + return; + + if (!sgx_page_reclaimer_init()) + goto err_page_cache; + + return; + +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..02afa84dd8fd --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -0,0 +1,60 @@ +/* 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 + +struct sgx_epc_page { + unsigned int section; + 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. + */ +struct sgx_epc_section { + unsigned long phys_addr; + void *virt_addr; + struct list_head page_list; + struct list_head laundry_list; + struct sgx_epc_page *pages; + spinlock_t lock; +}; + +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; +} + +#endif /* _X86_SGX_H */

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 38853a303982e3be3eccb1a1132399a5c5e2d806 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Add a kernel parameter to disable SGX kernel support and document it.

[ bp: Massage. ]

Intel-SIG: commit 38853a303982 x86/cpu/intel: Add a nosgx kernel parameter Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Sean Christopherson sean.j.christopherson@intel.com Acked-by: Jethro Beekman jethro@fortanix.com Tested-by: Sean Christopherson sean.j.christopherson@intel.com Link: https://lkml.kernel.org/r/20201112220135.165028-9-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- Documentation/admin-guide/kernel-parameters.txt | 2 ++ arch/x86/kernel/cpu/feat_ctl.c | 9 +++++++++ 2 files changed, 11 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b73108a82f18..a4e5614bee12 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3498,6 +3498,8 @@

nosep [BUGS=X86-32] Disables x86 SYSENTER/SYSEXIT support.

+ nosgx [X86-64,SGX] Disables Intel SGX kernel support. + nosmp [SMP] Tells an SMP kernel to act as a UP kernel, and disable the IO APIC. legacy for "maxcpus=0".

diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index d38e97325018..3b1b01f2b248 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -99,6 +99,15 @@ static void clear_sgx_caps(void) 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();

From: Sean Christopherson sean.j.christopherson@intel.com

mainline inclusion from mainline-v5.11-rc1 commit 95bb7c42ac8a94ce3d0eb059ad64430390351ccb category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Background ==========

1. SGX enclave pages are populated with data by copying from normal memory via ioctl() (SGX_IOC_ENCLAVE_ADD_PAGES), which will be added later in this series. 2. It is desirable to be able to restrict those normal memory data sources. For instance, to ensure that the source data is executable before copying data to an executable enclave page. 3. Enclave page permissions are dynamic (just like normal permissions) and can be adjusted at runtime with mprotect().

This creates a problem because the original data source may have long since vanished at the time when enclave page permissions are established (mmap() or mprotect()).

The solution (elsewhere in this series) is to force enclave creators to declare their paging permission *intent* up front to the ioctl(). This intent can be immediately compared to the source data’s mapping and rejected if necessary.

The “intent” is also stashed off for later comparison with enclave PTEs. This ensures that any future mmap()/mprotect() operations performed by the enclave creator or done on behalf of the enclave can be compared with the earlier declared permissions.

Problem =======

There is an existing mmap() hook which allows SGX to perform this permission comparison at mmap() time. However, there is no corresponding ->mprotect() hook.

Solution ========

Add a vm_ops->mprotect() hook so that mprotect() operations which are inconsistent with any page's stashed intent can be rejected by the driver.

Intel-SIG: commit 95bb7c42ac8a mm: Add 'mprotect' hook to struct vm_operations_struct Backport for SGX Foundations support

Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Co-developed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Acked-by: Dave Hansen dave.hansen@intel.com Acked-by: Mel Gorman mgorman@techsingularity.net Acked-by: Hillf Danton hdanton@sina.com Cc: linux-mm@kvack.org Link: https://lkml.kernel.org/r/20201112220135.165028-11-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- include/linux/mm.h | 7 +++++++ mm/mprotect.c | 7 +++++++ 2 files changed, 14 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 4831348f31e9..2db253209f81 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -595,6 +595,13 @@ struct vm_operations_struct { void (*close)(struct vm_area_struct * area); int (*split)(struct vm_area_struct * area, unsigned long addr); int (*mremap)(struct vm_area_struct * area); + /* + * Called by mprotect() to make driver-specific permission + * checks before mprotect() is finalised. The VMA must not + * be modified. Returns 0 if eprotect() can proceed. + */ + int (*mprotect)(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); diff --git a/mm/mprotect.c b/mm/mprotect.c index 56c02beb6041..ab709023e9aa 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -616,9 +616,16 @@ static int do_mprotect_pkey(unsigned long start, size_t len, tmp = vma->vm_end; if (tmp > end) tmp = end; + + if (vma->vm_ops && vma->vm_ops->mprotect) + error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags); + if (error) + goto out; + error = mprotect_fixup(vma, &prev, nstart, tmp, newflags); if (error) goto out; + nstart = tmp;

if (nstart < prev->vm_end)

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 888d249117876239593fe3039b6ead8ad6849035 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Add an ioctl() that performs the ECREATE function of the ENCLS instruction, which creates an SGX Enclave Control Structure (SECS).

Although the SECS is an in-memory data structure, it is present in enclave memory and is not directly accessible by software.

Intel-SIG: commit 888d24911787 x86/sgx: Add SGX_IOC_ENCLAVE_CREATE Backport for SGX Foundations support

Co-developed-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Tested-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-13-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- .../userspace-api/ioctl/ioctl-number.rst | 1 + arch/x86/include/uapi/asm/sgx.h | 25 ++++ arch/x86/kernel/cpu/sgx/Makefile | 1 + arch/x86/kernel/cpu/sgx/driver.c | 12 ++ arch/x86/kernel/cpu/sgx/driver.h | 3 + arch/x86/kernel/cpu/sgx/encl.c | 8 ++ arch/x86/kernel/cpu/sgx/encl.h | 7 + arch/x86/kernel/cpu/sgx/ioctl.c | 123 ++++++++++++++++++ 8 files changed, 180 insertions(+) create mode 100644 arch/x86/include/uapi/asm/sgx.h create mode 100644 arch/x86/kernel/cpu/sgx/ioctl.c

diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 55a2d9b2ce33..a4c75a28c839 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -323,6 +323,7 @@ Code Seq# Include File Comments mailto:tlewis@mindspring.com 0xA3 90-9F linux/dtlk.h 0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem +0xA4 00-1F uapi/asm/sgx.h mailto:linux-sgx@vger.kernel.org 0xAA 00-3F linux/uapi/linux/userfaultfd.h 0xAB 00-1F linux/nbd.h 0xAC 00-1F linux/raw.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..f31bb17e27c3 --- /dev/null +++ b/arch/x86/include/uapi/asm/sgx.h @@ -0,0 +1,25 @@ +/* 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> + +#define SGX_MAGIC 0xA4 + +#define SGX_IOC_ENCLAVE_CREATE \ + _IOW(SGX_MAGIC, 0x00, struct sgx_enclave_create) + +/** + * 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; +}; + +#endif /* _UAPI_ASM_X86_SGX_H */ diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile index 3fc451120735..91d3dc784a29 100644 --- a/arch/x86/kernel/cpu/sgx/Makefile +++ b/arch/x86/kernel/cpu/sgx/Makefile @@ -1,4 +1,5 @@ obj-y += \ driver.o \ encl.o \ + ioctl.o \ main.o diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index c2810e1c7cf1..ee947b721d8d 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -88,10 +88,22 @@ static unsigned long sgx_get_unmapped_area(struct file *file, 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, }; diff --git a/arch/x86/kernel/cpu/sgx/driver.h b/arch/x86/kernel/cpu/sgx/driver.h index cda9c43b7543..a728e8e848bd 100644 --- a/arch/x86/kernel/cpu/sgx/driver.h +++ b/arch/x86/kernel/cpu/sgx/driver.h @@ -9,8 +9,11 @@ #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/workqueue.h> +#include <uapi/asm/sgx.h> #include "sgx.h"

+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 index b9d445db7ff1..57eff300f487 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -46,6 +46,7 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf) 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; @@ -61,6 +62,13 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)

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); diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index 1df8011fa23d..7cc175825b01 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -26,9 +26,16 @@ struct sgx_encl_page { struct sgx_encl *encl; };

+enum sgx_encl_flags { + SGX_ENCL_IOCTL = BIT(0), + SGX_ENCL_DEBUG = BIT(1), + SGX_ENCL_CREATED = BIT(2), +}; + struct sgx_encl { unsigned long base; unsigned long size; + unsigned long flags; unsigned int page_cnt; unsigned int secs_child_cnt; struct mutex lock; diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c new file mode 100644 index 000000000000..1355490843d1 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -0,0 +1,123 @@ +// 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 int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) +{ + struct sgx_epc_page *secs_epc; + struct sgx_pageinfo pginfo; + struct sgx_secinfo secinfo; + unsigned long encl_size; + long ret; + + /* The extra page goes to SECS. */ + encl_size = secs->size + PAGE_SIZE; + + secs_epc = __sgx_alloc_epc_page(); + if (IS_ERR(secs_epc)) + return PTR_ERR(secs_epc); + + 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; + + /* 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; + + 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; +} + +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; + default: + ret = -ENOIOCTLCMD; + break; + } + + clear_bit(SGX_ENCL_IOCTL, &encl->flags); + return ret; +}

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 9d0c151b41fed7b879030f4e533143d098781701 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Enclaves have two basic states. They are either being built and are malleable and can be modified by doing things like adding pages. Or, they are locked down and not accepting changes. They can only be run after they have been locked down. The ENCLS[EINIT] function induces the transition from being malleable to locked-down.

Add an ioctl() that performs ENCLS[EINIT]. After this, new pages can no longer be added with ENCLS[EADD]. This is also the time where the enclave can be measured to verify its integrity.

Intel-SIG: commit 9d0c151b41fe x86/sgx: Add SGX_IOC_ENCLAVE_INIT Backport for SGX Foundations support

Co-developed-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Tested-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-15-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/include/uapi/asm/sgx.h | 11 ++ arch/x86/kernel/cpu/sgx/driver.c | 27 +++++ arch/x86/kernel/cpu/sgx/driver.h | 8 ++ arch/x86/kernel/cpu/sgx/encl.h | 3 + arch/x86/kernel/cpu/sgx/ioctl.c | 193 ++++++++++++++++++++++++++++++- 5 files changed, 241 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/uapi/asm/sgx.h b/arch/x86/include/uapi/asm/sgx.h index 835f7e588f0d..66f2d32cb4d7 100644 --- a/arch/x86/include/uapi/asm/sgx.h +++ b/arch/x86/include/uapi/asm/sgx.h @@ -23,6 +23,8 @@ enum sgx_page_flags { _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)

/** * struct sgx_enclave_create - parameter structure for the @@ -52,4 +54,13 @@ struct sgx_enclave_add_pages { __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; +}; + #endif /* _UAPI_ASM_X86_SGX_H */ diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index ee947b721d8d..bf5c4a36a548 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -10,6 +10,10 @@ #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; @@ -117,8 +121,31 @@ static struct miscdevice sgx_dev_enclave = {

int __init sgx_drv_init(void) { + unsigned int eax, ebx, ecx, edx; + u64 attr_mask; + u64 xfrm_mask; + 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; + } + return misc_register(&sgx_dev_enclave); } diff --git a/arch/x86/kernel/cpu/sgx/driver.h b/arch/x86/kernel/cpu/sgx/driver.h index a728e8e848bd..6b0063221659 100644 --- a/arch/x86/kernel/cpu/sgx/driver.h +++ b/arch/x86/kernel/cpu/sgx/driver.h @@ -12,6 +12,14 @@ #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; + long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);

int sgx_drv_init(void); diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index 7cc175825b01..8a4d1edded68 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -30,6 +30,7 @@ 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 { @@ -41,6 +42,8 @@ struct sgx_encl { struct mutex lock; struct xarray page_array; struct sgx_encl_page secs; + unsigned long attributes; + unsigned long attributes_mask; };

extern const struct vm_operations_struct sgx_vm_ops; diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 82acff7bda60..e036819ea5c1 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -51,6 +51,8 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) 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); @@ -334,7 +336,8 @@ static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg) unsigned long c; int ret;

- if (!test_bit(SGX_ENCL_CREATED, &encl->flags)) + 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))) @@ -382,6 +385,191 @@ static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg) 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; +} + + long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct sgx_encl *encl = filep->private_data; @@ -397,6 +585,9 @@ long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) 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; default: ret = -ENOIOCTLCMD; break;

From: Sean Christopherson sean.j.christopherson@intel.com

mainline inclusion from mainline-v5.11-rc1 commit 8382c668ce4f367d902f4a340a1bfa9e46096ec1 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Signals are a horrid little mechanism. They are especially nasty in multi-threaded environments because signal state like handlers is global across the entire process. But, signals are basically the only way that userspace can “gracefully” handle and recover from exceptions.

The kernel generally does not like exceptions to occur during execution. But, exceptions are a fact of life and must be handled in some circumstances. The kernel handles them by keeping a list of individual instructions which may cause exceptions. Instead of truly handling the exception and returning to the instruction that caused it, the kernel instead restarts execution at a *different* instruction. This makes it obvious to that thread of execution that the exception occurred and lets *that* code handle the exception instead of the handler.

This is not dissimilar to the try/catch exceptions mechanisms that some programming languages have, but applied *very* surgically to single instructions. It effectively changes the visible architecture of the instruction.

Problem =======

SGX generates a lot of signals, and the code to enter and exit enclaves and muck with signal handling is truly horrid. At the same time, an approach like kernel exception fixup can not be easily applied to userspace instructions because it changes the visible instruction architecture.

Solution ========

The vDSO is a special page of kernel-provided instructions that run in userspace. Any userspace calling into the vDSO knows that it is special. This allows the kernel a place to legitimately rewrite the user/kernel contract and change instruction behavior.

Add support for fixing up exceptions that occur while executing in the vDSO. This replaces what could traditionally only be done with signal handling.

This new mechanism will be used to replace previously direct use of SGX instructions by userspace.

Just introduce the vDSO infrastructure. Later patches will actually replace signal generation with vDSO exception fixup.

Intel-SIG: commit 8382c668ce4f x86/vdso: Add support for exception fixup in vDSO functions Backport for SGX Foundations support

Suggested-by: Andy Lutomirski luto@amacapital.net Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-17-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/entry/vdso/Makefile | 6 ++-- arch/x86/entry/vdso/extable.c | 46 ++++++++++++++++++++++++ arch/x86/entry/vdso/extable.h | 28 +++++++++++++++ arch/x86/entry/vdso/vdso-layout.lds.S | 9 ++++- arch/x86/entry/vdso/vdso2c.h | 50 ++++++++++++++++++++++++++- arch/x86/include/asm/vdso.h | 5 +++ 6 files changed, 139 insertions(+), 5 deletions(-) create mode 100644 arch/x86/entry/vdso/extable.c create mode 100644 arch/x86/entry/vdso/extable.h

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 21243747965d..2ad757fb3c23 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -29,7 +29,7 @@ vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o vobjs32-y += vdso32/vclock_gettime.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 @@ -128,8 +128,8 @@ $(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/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/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 */

From: Sean Christopherson sean.j.christopherson@intel.com

mainline inclusion from mainline-v5.11-rc1 commit 334872a0919890a70cccd00b8e11931020a819be category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

vDSO functions can now leverage an exception fixup mechanism similar to kernel exception fixup. For vDSO exception fixup, the initial user is Intel's Software Guard Extensions (SGX), which will wrap the low-level transitions to/from the enclave, i.e. EENTER and ERESUME instructions, in a vDSO function and leverage fixup to intercept exceptions that would otherwise generate a signal. This allows the vDSO wrapper to return the fault information directly to its caller, obviating the need for SGX applications and libraries to juggle signal handlers.

Attempt to fixup vDSO exceptions immediately prior to populating and sending signal information. Except for the delivery mechanism, an exception in a vDSO function should be treated like any other exception in userspace, e.g. any fault that is successfully handled by the kernel should not be directly visible to userspace.

Although it's debatable whether or not all exceptions are of interest to enclaves, defer to the vDSO fixup to decide whether to do fixup or generate a signal. Future users of vDSO fixup, if there ever are any, will undoubtedly have different requirements than SGX enclaves, e.g. the fixup vs. signal logic can be made function specific if/when necessary.

Suggested-by: Andy Lutomirski luto@amacapital.net Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-19-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/traps.c | 10 ++++++++++ arch/x86/mm/fault.c | 7 +++++++ 2 files changed, 17 insertions(+)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 2d4ecd50e69b..5da01819fb47 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; }

/* @@ -585,6 +589,9 @@ 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; @@ -1083,6 +1090,9 @@ 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 e86cdbb9692e..34112c63b347 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -31,6 +31,7 @@ #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> @@ -827,6 +828,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,

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);

@@ -946,6 +950,9 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,

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

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 2adcba79e69d4a4c0ac3bb86f466d8b5df301608 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Add a selftest for SGX. It is a trivial test where a simple enclave copies one 64-bit word of memory between two memory locations, but ensures that all SGX hardware and software infrastructure is functioning.

Intel-SIG: commit 2adcba79e69d selftests/x86: Add a selftest for SGX Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Cc: linux-kselftest@vger.kernel.org Link: https://lkml.kernel.org/r/20201112220135.165028-21-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/sgx/.gitignore | 2 + tools/testing/selftests/sgx/Makefile | 53 +++ tools/testing/selftests/sgx/call.S | 44 ++ tools/testing/selftests/sgx/defines.h | 21 + tools/testing/selftests/sgx/load.c | 277 +++++++++++++ tools/testing/selftests/sgx/main.c | 246 +++++++++++ tools/testing/selftests/sgx/main.h | 38 ++ tools/testing/selftests/sgx/sigstruct.c | 391 ++++++++++++++++++ tools/testing/selftests/sgx/test_encl.c | 20 + tools/testing/selftests/sgx/test_encl.lds | 40 ++ .../selftests/sgx/test_encl_bootstrap.S | 89 ++++ 12 files changed, 1222 insertions(+) create mode 100644 tools/testing/selftests/sgx/.gitignore create mode 100644 tools/testing/selftests/sgx/Makefile create mode 100644 tools/testing/selftests/sgx/call.S create mode 100644 tools/testing/selftests/sgx/defines.h create mode 100644 tools/testing/selftests/sgx/load.c create mode 100644 tools/testing/selftests/sgx/main.c create mode 100644 tools/testing/selftests/sgx/main.h create mode 100644 tools/testing/selftests/sgx/sigstruct.c create mode 100644 tools/testing/selftests/sgx/test_encl.c create mode 100644 tools/testing/selftests/sgx/test_encl.lds create mode 100644 tools/testing/selftests/sgx/test_encl_bootstrap.S

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index d9c283503159..2e20e30a6faa 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -50,6 +50,7 @@ TARGETS += openat2 TARGETS += rseq TARGETS += rtc TARGETS += seccomp +TARGETS += sgx TARGETS += sigaltstack TARGETS += size TARGETS += sparc64 diff --git a/tools/testing/selftests/sgx/.gitignore b/tools/testing/selftests/sgx/.gitignore new file mode 100644 index 000000000000..fbaf0bda9a92 --- /dev/null +++ b/tools/testing/selftests/sgx/.gitignore @@ -0,0 +1,2 @@ +test_sgx +test_encl.elf diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile new file mode 100644 index 000000000000..d51c90663943 --- /dev/null +++ b/tools/testing/selftests/sgx/Makefile @@ -0,0 +1,53 @@ +top_srcdir = ../../../.. + +include ../lib.mk + +.PHONY: all clean + +CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh $(CC) \ + ../x86/trivial_64bit_program.c) + +ifndef OBJCOPY +OBJCOPY := $(CROSS_COMPILE)objcopy +endif + +INCLUDES := -I$(top_srcdir)/tools/include +HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack +ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ + -fno-stack-protector -mrdrnd $(INCLUDES) + +TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx + +ifeq ($(CAN_BUILD_X86_64), 1) +all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf +endif + +$(OUTPUT)/test_sgx: $(OUTPUT)/main.o \ + $(OUTPUT)/load.o \ + $(OUTPUT)/sigstruct.o \ + $(OUTPUT)/call.o + $(CC) $(HOST_CFLAGS) -o $@ $^ -lcrypto + +$(OUTPUT)/main.o: main.c + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/load.o: load.c + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/sigstruct.o: sigstruct.c + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/call.o: call.S + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S + $(CC) $(ENCL_CFLAGS) -T $^ -o $@ + +EXTRA_CLEAN := \ + $(OUTPUT)/test_encl.elf \ + $(OUTPUT)/load.o \ + $(OUTPUT)/call.o \ + $(OUTPUT)/main.o \ + $(OUTPUT)/sigstruct.o \ + $(OUTPUT)/test_sgx \ + $(OUTPUT)/test_sgx.o \ diff --git a/tools/testing/selftests/sgx/call.S b/tools/testing/selftests/sgx/call.S new file mode 100644 index 000000000000..4ecadc7490f4 --- /dev/null +++ b/tools/testing/selftests/sgx/call.S @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/** +* Copyright(c) 2016-20 Intel Corporation. +*/ + + .text + + .global sgx_call_vdso +sgx_call_vdso: + .cfi_startproc + push %r15 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r15, 0 + push %r14 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r14, 0 + push %r13 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r13, 0 + push %r12 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r12, 0 + push %rbx + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %rbx, 0 + push $0 + .cfi_adjust_cfa_offset 8 + push 0x38(%rsp) + .cfi_adjust_cfa_offset 8 + call *eenter(%rip) + add $0x10, %rsp + .cfi_adjust_cfa_offset -0x10 + pop %rbx + .cfi_adjust_cfa_offset -8 + pop %r12 + .cfi_adjust_cfa_offset -8 + pop %r13 + .cfi_adjust_cfa_offset -8 + pop %r14 + .cfi_adjust_cfa_offset -8 + pop %r15 + .cfi_adjust_cfa_offset -8 + ret + .cfi_endproc diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h new file mode 100644 index 000000000000..592c1ccf4576 --- /dev/null +++ b/tools/testing/selftests/sgx/defines.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-20 Intel Corporation. + */ + +#ifndef DEFINES_H +#define DEFINES_H + +#include <stdint.h> + +#define PAGE_SIZE 4096 +#define PAGE_MASK (~(PAGE_SIZE - 1)) + +#define __aligned(x) __attribute__((__aligned__(x))) +#define __packed __attribute__((packed)) + +#include "../../../../arch/x86/kernel/cpu/sgx/arch.h" +#include "../../../../arch/x86/include/asm/enclu.h" +#include "../../../../arch/x86/include/uapi/asm/sgx.h" + +#endif /* DEFINES_H */ diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c new file mode 100644 index 000000000000..9d43b75aaa55 --- /dev/null +++ b/tools/testing/selftests/sgx/load.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <assert.h> +#include <elf.h> +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include "defines.h" +#include "main.h" + +void encl_delete(struct encl *encl) +{ + if (encl->encl_base) + munmap((void *)encl->encl_base, encl->encl_size); + + if (encl->bin) + munmap(encl->bin, encl->bin_size); + + if (encl->fd) + close(encl->fd); + + if (encl->segment_tbl) + free(encl->segment_tbl); + + memset(encl, 0, sizeof(*encl)); +} + +static bool encl_map_bin(const char *path, struct encl *encl) +{ + struct stat sb; + void *bin; + int ret; + int fd; + + fd = open(path, O_RDONLY); + if (fd == -1) { + perror("open()"); + return false; + } + + ret = stat(path, &sb); + if (ret) { + perror("stat()"); + goto err; + } + + bin = mmap(NULL, sb.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (bin == MAP_FAILED) { + perror("mmap()"); + goto err; + } + + encl->bin = bin; + encl->bin_size = sb.st_size; + + close(fd); + return true; + +err: + close(fd); + return false; +} + +static bool encl_ioc_create(struct encl *encl) +{ + struct sgx_secs *secs = &encl->secs; + struct sgx_enclave_create ioc; + int rc; + + assert(encl->encl_base != 0); + + memset(secs, 0, sizeof(*secs)); + secs->ssa_frame_size = 1; + secs->attributes = SGX_ATTR_MODE64BIT; + secs->xfrm = 3; + secs->base = encl->encl_base; + secs->size = encl->encl_size; + + ioc.src = (unsigned long)secs; + rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_CREATE, &ioc); + if (rc) { + fprintf(stderr, "SGX_IOC_ENCLAVE_CREATE failed: errno=%d\n", + errno); + munmap((void *)secs->base, encl->encl_size); + return false; + } + + return true; +} + +static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg) +{ + struct sgx_enclave_add_pages ioc; + struct sgx_secinfo secinfo; + int rc; + + memset(&secinfo, 0, sizeof(secinfo)); + secinfo.flags = seg->flags; + + ioc.src = (uint64_t)encl->src + seg->offset; + ioc.offset = seg->offset; + ioc.length = seg->size; + ioc.secinfo = (unsigned long)&secinfo; + ioc.flags = SGX_PAGE_MEASURE; + + rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc); + if (rc < 0) { + fprintf(stderr, "SGX_IOC_ENCLAVE_ADD_PAGES failed: errno=%d.\n", + errno); + return false; + } + + return true; +} + +bool encl_load(const char *path, struct encl *encl) +{ + Elf64_Phdr *phdr_tbl; + off_t src_offset; + Elf64_Ehdr *ehdr; + int i, j; + int ret; + + memset(encl, 0, sizeof(*encl)); + + ret = open("/dev/sgx_enclave", O_RDWR); + if (ret < 0) { + fprintf(stderr, "Unable to open /dev/sgx_enclave\n"); + goto err; + } + + encl->fd = ret; + + if (!encl_map_bin(path, encl)) + goto err; + + ehdr = encl->bin; + phdr_tbl = encl->bin + ehdr->e_phoff; + + for (i = 0; i < ehdr->e_phnum; i++) { + Elf64_Phdr *phdr = &phdr_tbl[i]; + + if (phdr->p_type == PT_LOAD) + encl->nr_segments++; + } + + encl->segment_tbl = calloc(encl->nr_segments, + sizeof(struct encl_segment)); + if (!encl->segment_tbl) + goto err; + + for (i = 0, j = 0; i < ehdr->e_phnum; i++) { + Elf64_Phdr *phdr = &phdr_tbl[i]; + unsigned int flags = phdr->p_flags; + struct encl_segment *seg; + + if (phdr->p_type != PT_LOAD) + continue; + + seg = &encl->segment_tbl[j]; + + if (!!(flags & ~(PF_R | PF_W | PF_X))) { + fprintf(stderr, + "%d has invalid segment flags 0x%02x.\n", i, + phdr->p_flags); + goto err; + } + + if (j == 0 && flags != (PF_R | PF_W)) { + fprintf(stderr, + "TCS has invalid segment flags 0x%02x.\n", + phdr->p_flags); + goto err; + } + + if (j == 0) { + src_offset = phdr->p_offset & PAGE_MASK; + + seg->prot = PROT_READ | PROT_WRITE; + seg->flags = SGX_PAGE_TYPE_TCS << 8; + } else { + seg->prot = (phdr->p_flags & PF_R) ? PROT_READ : 0; + seg->prot |= (phdr->p_flags & PF_W) ? PROT_WRITE : 0; + seg->prot |= (phdr->p_flags & PF_X) ? PROT_EXEC : 0; + seg->flags = (SGX_PAGE_TYPE_REG << 8) | seg->prot; + } + + seg->offset = (phdr->p_offset & PAGE_MASK) - src_offset; + seg->size = (phdr->p_filesz + PAGE_SIZE - 1) & PAGE_MASK; + + printf("0x%016lx 0x%016lx 0x%02x\n", seg->offset, seg->size, + seg->prot); + + j++; + } + + assert(j == encl->nr_segments); + + encl->src = encl->bin + src_offset; + encl->src_size = encl->segment_tbl[j - 1].offset + + encl->segment_tbl[j - 1].size; + + for (encl->encl_size = 4096; encl->encl_size < encl->src_size; ) + encl->encl_size <<= 1; + + return true; + +err: + encl_delete(encl); + return false; +} + +static bool encl_map_area(struct encl *encl) +{ + size_t encl_size = encl->encl_size; + void *area; + + area = mmap(NULL, encl_size * 2, PROT_NONE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (area == MAP_FAILED) { + perror("mmap"); + return false; + } + + encl->encl_base = ((uint64_t)area + encl_size - 1) & ~(encl_size - 1); + + munmap(area, encl->encl_base - (uint64_t)area); + munmap((void *)(encl->encl_base + encl_size), + (uint64_t)area + encl_size - encl->encl_base); + + return true; +} + +bool encl_build(struct encl *encl) +{ + struct sgx_enclave_init ioc; + int ret; + int i; + + if (!encl_map_area(encl)) + return false; + + if (!encl_ioc_create(encl)) + return false; + + /* + * Pages must be added before mapping VMAs because their permissions + * cap the VMA permissions. + */ + for (i = 0; i < encl->nr_segments; i++) { + struct encl_segment *seg = &encl->segment_tbl[i]; + + if (!encl_ioc_add_pages(encl, seg)) + return false; + } + + ioc.sigstruct = (uint64_t)&encl->sigstruct; + ret = ioctl(encl->fd, SGX_IOC_ENCLAVE_INIT, &ioc); + if (ret) { + fprintf(stderr, "SGX_IOC_ENCLAVE_INIT failed: errno=%d\n", + errno); + return false; + } + + return true; +} diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c new file mode 100644 index 000000000000..724cec700926 --- /dev/null +++ b/tools/testing/selftests/sgx/main.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <elf.h> +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include "defines.h" +#include "main.h" +#include "../kselftest.h" + +static const uint64_t MAGIC = 0x1122334455667788ULL; +vdso_sgx_enter_enclave_t eenter; + +struct vdso_symtab { + Elf64_Sym *elf_symtab; + const char *elf_symstrtab; + Elf64_Word *elf_hashtab; +}; + +static void *vdso_get_base_addr(char *envp[]) +{ + Elf64_auxv_t *auxv; + int i; + + for (i = 0; envp[i]; i++) + ; + + auxv = (Elf64_auxv_t *)&envp[i + 1]; + + for (i = 0; auxv[i].a_type != AT_NULL; i++) { + if (auxv[i].a_type == AT_SYSINFO_EHDR) + return (void *)auxv[i].a_un.a_val; + } + + return NULL; +} + +static Elf64_Dyn *vdso_get_dyntab(void *addr) +{ + Elf64_Ehdr *ehdr = addr; + Elf64_Phdr *phdrtab = addr + ehdr->e_phoff; + int i; + + for (i = 0; i < ehdr->e_phnum; i++) + if (phdrtab[i].p_type == PT_DYNAMIC) + return addr + phdrtab[i].p_offset; + + return NULL; +} + +static void *vdso_get_dyn(void *addr, Elf64_Dyn *dyntab, Elf64_Sxword tag) +{ + int i; + + for (i = 0; dyntab[i].d_tag != DT_NULL; i++) + if (dyntab[i].d_tag == tag) + return addr + dyntab[i].d_un.d_ptr; + + return NULL; +} + +static bool vdso_get_symtab(void *addr, struct vdso_symtab *symtab) +{ + Elf64_Dyn *dyntab = vdso_get_dyntab(addr); + + symtab->elf_symtab = vdso_get_dyn(addr, dyntab, DT_SYMTAB); + if (!symtab->elf_symtab) + return false; + + symtab->elf_symstrtab = vdso_get_dyn(addr, dyntab, DT_STRTAB); + if (!symtab->elf_symstrtab) + return false; + + symtab->elf_hashtab = vdso_get_dyn(addr, dyntab, DT_HASH); + if (!symtab->elf_hashtab) + return false; + + return true; +} + +static unsigned long elf_sym_hash(const char *name) +{ + unsigned long h = 0, high; + + while (*name) { + h = (h << 4) + *name++; + high = h & 0xf0000000; + + if (high) + h ^= high >> 24; + + h &= ~high; + } + + return h; +} + +static Elf64_Sym *vdso_symtab_get(struct vdso_symtab *symtab, const char *name) +{ + Elf64_Word bucketnum = symtab->elf_hashtab[0]; + Elf64_Word *buckettab = &symtab->elf_hashtab[2]; + Elf64_Word *chaintab = &symtab->elf_hashtab[2 + bucketnum]; + Elf64_Sym *sym; + Elf64_Word i; + + for (i = buckettab[elf_sym_hash(name) % bucketnum]; i != STN_UNDEF; + i = chaintab[i]) { + sym = &symtab->elf_symtab[i]; + if (!strcmp(name, &symtab->elf_symstrtab[sym->st_name])) + return sym; + } + + return NULL; +} + +bool report_results(struct sgx_enclave_run *run, int ret, uint64_t result, + const char *test) +{ + bool valid = true; + + if (ret) { + printf("FAIL: %s() returned: %d\n", test, ret); + valid = false; + } + + if (run->function != EEXIT) { + printf("FAIL: %s() function, expected: %u, got: %u\n", test, EEXIT, + run->function); + valid = false; + } + + if (result != MAGIC) { + printf("FAIL: %s(), expected: 0x%lx, got: 0x%lx\n", test, MAGIC, + result); + valid = false; + } + + if (run->user_data) { + printf("FAIL: %s() user data, expected: 0x0, got: 0x%llx\n", + test, run->user_data); + valid = false; + } + + return valid; +} + +static int user_handler(long rdi, long rsi, long rdx, long ursp, long r8, long r9, + struct sgx_enclave_run *run) +{ + run->user_data = 0; + return 0; +} + +int main(int argc, char *argv[], char *envp[]) +{ + struct sgx_enclave_run run; + struct vdso_symtab symtab; + Elf64_Sym *eenter_sym; + uint64_t result = 0; + struct encl encl; + unsigned int i; + void *addr; + int ret; + + memset(&run, 0, sizeof(run)); + + if (!encl_load("test_encl.elf", &encl)) { + encl_delete(&encl); + ksft_exit_skip("cannot load enclaves\n"); + } + + if (!encl_measure(&encl)) + goto err; + + if (!encl_build(&encl)) + goto err; + + /* + * An enclave consumer only must do this. + */ + for (i = 0; i < encl.nr_segments; i++) { + struct encl_segment *seg = &encl.segment_tbl[i]; + + addr = mmap((void *)encl.encl_base + seg->offset, seg->size, + seg->prot, MAP_SHARED | MAP_FIXED, encl.fd, 0); + if (addr == MAP_FAILED) { + fprintf(stderr, "mmap() failed, errno=%d.\n", errno); + exit(KSFT_FAIL); + } + } + + memset(&run, 0, sizeof(run)); + run.tcs = encl.encl_base; + + addr = vdso_get_base_addr(envp); + if (!addr) + goto err; + + if (!vdso_get_symtab(addr, &symtab)) + goto err; + + eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); + if (!eenter_sym) + goto err; + + eenter = addr + eenter_sym->st_value; + + ret = sgx_call_vdso((void *)&MAGIC, &result, 0, EENTER, NULL, NULL, &run); + if (!report_results(&run, ret, result, "sgx_call_vdso")) + goto err; + + + /* Invoke the vDSO directly. */ + result = 0; + ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, + 0, 0, &run); + if (!report_results(&run, ret, result, "eenter")) + goto err; + + /* And with an exit handler. */ + run.user_handler = (__u64)user_handler; + run.user_data = 0xdeadbeef; + ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER, + 0, 0, &run); + if (!report_results(&run, ret, result, "user_handler")) + goto err; + + printf("SUCCESS\n"); + encl_delete(&encl); + exit(KSFT_PASS); + +err: + encl_delete(&encl); + exit(KSFT_FAIL); +} diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h new file mode 100644 index 000000000000..45e6ab65442a --- /dev/null +++ b/tools/testing/selftests/sgx/main.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-20 Intel Corporation. + */ + +#ifndef MAIN_H +#define MAIN_H + +struct encl_segment { + off_t offset; + size_t size; + unsigned int prot; + unsigned int flags; +}; + +struct encl { + int fd; + void *bin; + off_t bin_size; + void *src; + size_t src_size; + size_t encl_size; + off_t encl_base; + unsigned int nr_segments; + struct encl_segment *segment_tbl; + struct sgx_secs secs; + struct sgx_sigstruct sigstruct; +}; + +void encl_delete(struct encl *ctx); +bool encl_load(const char *path, struct encl *encl); +bool encl_measure(struct encl *encl); +bool encl_build(struct encl *encl); + +int sgx_call_vdso(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9, + struct sgx_enclave_run *run); + +#endif /* MAIN_H */ diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c new file mode 100644 index 000000000000..cc06f108bae7 --- /dev/null +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -0,0 +1,391 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#define _GNU_SOURCE +#include <assert.h> +#include <getopt.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <openssl/err.h> +#include <openssl/pem.h> +#include "defines.h" +#include "main.h" + +struct q1q2_ctx { + BN_CTX *bn_ctx; + BIGNUM *m; + BIGNUM *s; + BIGNUM *q1; + BIGNUM *qr; + BIGNUM *q2; +}; + +static void free_q1q2_ctx(struct q1q2_ctx *ctx) +{ + BN_CTX_free(ctx->bn_ctx); + BN_free(ctx->m); + BN_free(ctx->s); + BN_free(ctx->q1); + BN_free(ctx->qr); + BN_free(ctx->q2); +} + +static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, + struct q1q2_ctx *ctx) +{ + ctx->bn_ctx = BN_CTX_new(); + ctx->s = BN_bin2bn(s, SGX_MODULUS_SIZE, NULL); + ctx->m = BN_bin2bn(m, SGX_MODULUS_SIZE, NULL); + ctx->q1 = BN_new(); + ctx->qr = BN_new(); + ctx->q2 = BN_new(); + + if (!ctx->bn_ctx || !ctx->s || !ctx->m || !ctx->q1 || !ctx->qr || + !ctx->q2) { + free_q1q2_ctx(ctx); + return false; + } + + return true; +} + +static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, + uint8_t *q2) +{ + struct q1q2_ctx ctx; + + if (!alloc_q1q2_ctx(s, m, &ctx)) { + fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); + return false; + } + + if (!BN_mul(ctx.q1, ctx.s, ctx.s, ctx.bn_ctx)) + goto out; + + if (!BN_div(ctx.q1, ctx.qr, ctx.q1, ctx.m, ctx.bn_ctx)) + goto out; + + if (BN_num_bytes(ctx.q1) > SGX_MODULUS_SIZE) { + fprintf(stderr, "Too large Q1 %d bytes\n", + BN_num_bytes(ctx.q1)); + goto out; + } + + if (!BN_mul(ctx.q2, ctx.s, ctx.qr, ctx.bn_ctx)) + goto out; + + if (!BN_div(ctx.q2, NULL, ctx.q2, ctx.m, ctx.bn_ctx)) + goto out; + + if (BN_num_bytes(ctx.q2) > SGX_MODULUS_SIZE) { + fprintf(stderr, "Too large Q2 %d bytes\n", + BN_num_bytes(ctx.q2)); + goto out; + } + + BN_bn2bin(ctx.q1, q1); + BN_bn2bin(ctx.q2, q2); + + free_q1q2_ctx(&ctx); + return true; +out: + free_q1q2_ctx(&ctx); + return false; +} + +struct sgx_sigstruct_payload { + struct sgx_sigstruct_header header; + struct sgx_sigstruct_body body; +}; + +static bool check_crypto_errors(void) +{ + int err; + bool had_errors = false; + const char *filename; + int line; + char str[256]; + + for ( ; ; ) { + if (ERR_peek_error() == 0) + break; + + had_errors = true; + err = ERR_get_error_line(&filename, &line); + ERR_error_string_n(err, str, sizeof(str)); + fprintf(stderr, "crypto: %s: %s:%d\n", str, filename, line); + } + + return had_errors; +} + +static inline const BIGNUM *get_modulus(RSA *key) +{ + const BIGNUM *n; + + RSA_get0_key(key, &n, NULL, NULL); + return n; +} + +static RSA *gen_sign_key(void) +{ + BIGNUM *e; + RSA *key; + int ret; + + e = BN_new(); + key = RSA_new(); + + if (!e || !key) + goto err; + + ret = BN_set_word(e, RSA_3); + if (ret != 1) + goto err; + + ret = RSA_generate_key_ex(key, 3072, e, NULL); + if (ret != 1) + goto err; + + BN_free(e); + + return key; + +err: + RSA_free(key); + BN_free(e); + + return NULL; +} + +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + +enum mrtags { + MRECREATE = 0x0045544145524345, + MREADD = 0x0000000044444145, + MREEXTEND = 0x00444E4554584545, +}; + +static bool mrenclave_update(EVP_MD_CTX *ctx, const void *data) +{ + if (!EVP_DigestUpdate(ctx, data, 64)) { + fprintf(stderr, "digest update failed\n"); + return false; + } + + return true; +} + +static bool mrenclave_commit(EVP_MD_CTX *ctx, uint8_t *mrenclave) +{ + unsigned int size; + + if (!EVP_DigestFinal_ex(ctx, (unsigned char *)mrenclave, &size)) { + fprintf(stderr, "digest commit failed\n"); + return false; + } + + if (size != 32) { + fprintf(stderr, "invalid digest size = %u\n", size); + return false; + } + + return true; +} + +struct mrecreate { + uint64_t tag; + uint32_t ssaframesize; + uint64_t size; + uint8_t reserved[44]; +} __attribute__((__packed__)); + + +static bool mrenclave_ecreate(EVP_MD_CTX *ctx, uint64_t blob_size) +{ + struct mrecreate mrecreate; + uint64_t encl_size; + + for (encl_size = 0x1000; encl_size < blob_size; ) + encl_size <<= 1; + + memset(&mrecreate, 0, sizeof(mrecreate)); + mrecreate.tag = MRECREATE; + mrecreate.ssaframesize = 1; + mrecreate.size = encl_size; + + if (!EVP_DigestInit_ex(ctx, EVP_sha256(), NULL)) + return false; + + return mrenclave_update(ctx, &mrecreate); +} + +struct mreadd { + uint64_t tag; + uint64_t offset; + uint64_t flags; /* SECINFO flags */ + uint8_t reserved[40]; +} __attribute__((__packed__)); + +static bool mrenclave_eadd(EVP_MD_CTX *ctx, uint64_t offset, uint64_t flags) +{ + struct mreadd mreadd; + + memset(&mreadd, 0, sizeof(mreadd)); + mreadd.tag = MREADD; + mreadd.offset = offset; + mreadd.flags = flags; + + return mrenclave_update(ctx, &mreadd); +} + +struct mreextend { + uint64_t tag; + uint64_t offset; + uint8_t reserved[48]; +} __attribute__((__packed__)); + +static bool mrenclave_eextend(EVP_MD_CTX *ctx, uint64_t offset, + const uint8_t *data) +{ + struct mreextend mreextend; + int i; + + for (i = 0; i < 0x1000; i += 0x100) { + memset(&mreextend, 0, sizeof(mreextend)); + mreextend.tag = MREEXTEND; + mreextend.offset = offset + i; + + if (!mrenclave_update(ctx, &mreextend)) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x00])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x40])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x80])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0xC0])) + return false; + } + + return true; +} + +static bool mrenclave_segment(EVP_MD_CTX *ctx, struct encl *encl, + struct encl_segment *seg) +{ + uint64_t end = seg->offset + seg->size; + uint64_t offset; + + for (offset = seg->offset; offset < end; offset += PAGE_SIZE) { + if (!mrenclave_eadd(ctx, offset, seg->flags)) + return false; + + if (!mrenclave_eextend(ctx, offset, encl->src + offset)) + return false; + } + + return true; +} + +bool encl_measure(struct encl *encl) +{ + uint64_t header1[2] = {0x000000E100000006, 0x0000000000010000}; + uint64_t header2[2] = {0x0000006000000101, 0x0000000100000060}; + struct sgx_sigstruct *sigstruct = &encl->sigstruct; + struct sgx_sigstruct_payload payload; + uint8_t digest[SHA256_DIGEST_LENGTH]; + unsigned int siglen; + RSA *key = NULL; + EVP_MD_CTX *ctx; + int i; + + memset(sigstruct, 0, sizeof(*sigstruct)); + + sigstruct->header.header1[0] = header1[0]; + sigstruct->header.header1[1] = header1[1]; + sigstruct->header.header2[0] = header2[0]; + sigstruct->header.header2[1] = header2[1]; + sigstruct->exponent = 3; + sigstruct->body.attributes = SGX_ATTR_MODE64BIT; + sigstruct->body.xfrm = 3; + + /* sanity check */ + if (check_crypto_errors()) + goto err; + + key = gen_sign_key(); + if (!key) + goto err; + + BN_bn2bin(get_modulus(key), sigstruct->modulus); + + ctx = EVP_MD_CTX_create(); + if (!ctx) + goto err; + + if (!mrenclave_ecreate(ctx, encl->src_size)) + goto err; + + for (i = 0; i < encl->nr_segments; i++) { + struct encl_segment *seg = &encl->segment_tbl[i]; + + if (!mrenclave_segment(ctx, encl, seg)) + goto err; + } + + if (!mrenclave_commit(ctx, sigstruct->body.mrenclave)) + goto err; + + memcpy(&payload.header, &sigstruct->header, sizeof(sigstruct->header)); + memcpy(&payload.body, &sigstruct->body, sizeof(sigstruct->body)); + + SHA256((unsigned char *)&payload, sizeof(payload), digest); + + if (!RSA_sign(NID_sha256, digest, SHA256_DIGEST_LENGTH, + sigstruct->signature, &siglen, key)) + goto err; + + if (!calc_q1q2(sigstruct->signature, sigstruct->modulus, sigstruct->q1, + sigstruct->q2)) + goto err; + + /* BE -> LE */ + reverse_bytes(sigstruct->signature, SGX_MODULUS_SIZE); + reverse_bytes(sigstruct->modulus, SGX_MODULUS_SIZE); + reverse_bytes(sigstruct->q1, SGX_MODULUS_SIZE); + reverse_bytes(sigstruct->q2, SGX_MODULUS_SIZE); + + EVP_MD_CTX_destroy(ctx); + RSA_free(key); + return true; + +err: + EVP_MD_CTX_destroy(ctx); + RSA_free(key); + return false; +} diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c new file mode 100644 index 000000000000..cf25b5dc1e03 --- /dev/null +++ b/tools/testing/selftests/sgx/test_encl.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <stddef.h> +#include "defines.h" + +static void *memcpy(void *dest, const void *src, size_t n) +{ + size_t i; + + for (i = 0; i < n; i++) + ((char *)dest)[i] = ((char *)src)[i]; + + return dest; +} + +void encl_body(void *rdi, void *rsi) +{ + memcpy(rsi, rdi, 8); +} diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds new file mode 100644 index 000000000000..0fbbda7e665e --- /dev/null +++ b/tools/testing/selftests/sgx/test_encl.lds @@ -0,0 +1,40 @@ +OUTPUT_FORMAT(elf64-x86-64) + +PHDRS +{ + tcs PT_LOAD; + text PT_LOAD; + data PT_LOAD; +} + +SECTIONS +{ + . = 0; + .tcs : { + *(.tcs*) + } : tcs + + . = ALIGN(4096); + .text : { + *(.text*) + *(.rodata*) + } : text + + . = ALIGN(4096); + .data : { + *(.data*) + } : data + + /DISCARD/ : { + *(.comment*) + *(.note*) + *(.debug*) + *(.eh_frame*) + } +} + +ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves") diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S new file mode 100644 index 000000000000..5d5680d4ea39 --- /dev/null +++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-20 Intel Corporation. + */ + + .macro ENCLU + .byte 0x0f, 0x01, 0xd7 + .endm + + .section ".tcs", "aw" + .balign 4096 + + .fill 1, 8, 0 # STATE (set by CPU) + .fill 1, 8, 0 # FLAGS + .quad encl_ssa # OSSA + .fill 1, 4, 0 # CSSA (set by CPU) + .fill 1, 4, 1 # NSSA + .quad encl_entry # OENTRY + .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) + .fill 1, 8, 0 # OFSBASE + .fill 1, 8, 0 # OGSBASE + .fill 1, 4, 0xFFFFFFFF # FSLIMIT + .fill 1, 4, 0xFFFFFFFF # GSLIMIT + .fill 4024, 1, 0 # Reserved + + # Identical to the previous TCS. + .fill 1, 8, 0 # STATE (set by CPU) + .fill 1, 8, 0 # FLAGS + .quad encl_ssa # OSSA + .fill 1, 4, 0 # CSSA (set by CPU) + .fill 1, 4, 1 # NSSA + .quad encl_entry # OENTRY + .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) + .fill 1, 8, 0 # OFSBASE + .fill 1, 8, 0 # OGSBASE + .fill 1, 4, 0xFFFFFFFF # FSLIMIT + .fill 1, 4, 0xFFFFFFFF # GSLIMIT + .fill 4024, 1, 0 # Reserved + + .text + +encl_entry: + # RBX contains the base address for TCS, which is also the first address + # inside the enclave. By adding the value of le_stack_end to it, we get + # the absolute address for the stack. + lea (encl_stack)(%rbx), %rax + xchg %rsp, %rax + push %rax + + push %rcx # push the address after EENTER + push %rbx # push the enclave base address + + call encl_body + + pop %rbx # pop the enclave base address + + /* Clear volatile GPRs, except RAX (EEXIT function). */ + xor %rcx, %rcx + xor %rdx, %rdx + xor %rdi, %rdi + xor %rsi, %rsi + xor %r8, %r8 + xor %r9, %r9 + xor %r10, %r10 + xor %r11, %r11 + + # Reset status flags. + add %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1 + + # Prepare EEXIT target by popping the address of the instruction after + # EENTER to RBX. + pop %rbx + + # Restore the caller stack. + pop %rax + mov %rax, %rsp + + # EEXIT + mov $4, %rax + enclu + + .section ".data", "aw" + +encl_ssa: + .space 4096 + + .balign 4096 + .space 8192 +encl_stack:

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 1728ab54b4be94aed89276eeb8e750a345659765 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Just like normal RAM, there is a limited amount of enclave memory available and overcommitting it is a very valuable tool to reduce resource use. Introduce a simple reclaim mechanism for enclave pages.

In contrast to normal page reclaim, the kernel cannot directly access enclave memory. To get around this, the SGX architecture provides a set of functions to help. Among other things, these functions copy enclave memory to and from normal memory, encrypting it and protecting its integrity in the process.

Implement a page reclaimer by using these functions. Picks victim pages in LRU fashion from all the enclaves running in the system. A new kernel thread (ksgxswapd) reclaims pages in the background based on watermarks, similar to normal kswapd.

All enclave pages can be reclaimed, architecturally. But, there are some limits to this, such as the special SECS metadata page which must be reclaimed last. The page version array (used to mitigate replaying old reclaimed pages) is also architecturally reclaimable, but not yet implemented. The end result is that the vast majority of enclave pages are currently reclaimable.

Intel-SIG: commit 1728ab54b4be x86/sgx: Add a page reclaimer Backport for SGX Foundations support

Co-developed-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-22-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/driver.c | 59 ++-- arch/x86/kernel/cpu/sgx/encl.c | 483 ++++++++++++++++++++++++++++++- arch/x86/kernel/cpu/sgx/encl.h | 51 ++++ arch/x86/kernel/cpu/sgx/ioctl.c | 89 +++++- arch/x86/kernel/cpu/sgx/main.c | 466 +++++++++++++++++++++++++++++ arch/x86/kernel/cpu/sgx/sgx.h | 13 + 6 files changed, 1134 insertions(+), 27 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index 899c18499d1a..f2eac41bb4ff 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -17,13 +17,24 @@ 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;

@@ -33,31 +44,37 @@ static int sgx_open(struct inode *inode, struct file *file) static int sgx_release(struct inode *inode, struct file *file) { struct sgx_encl *encl = file->private_data; - struct sgx_encl_page *entry; - unsigned long index; - - xa_for_each(&encl->page_array, index, entry) { - if (entry->epc_page) { - sgx_free_epc_page(entry->epc_page); - encl->secs_child_cnt--; - entry->epc_page = NULL; + 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); }

- kfree(entry); - } + spin_unlock(&encl->mm_lock);

- xa_destroy(&encl->page_array); + /* The enclave is no longer mapped by any mm. */ + if (!encl_mm) + break;

- if (!encl->secs_child_cnt && encl->secs.epc_page) { - sgx_free_epc_page(encl->secs.epc_page); - encl->secs.epc_page = NULL; + synchronize_srcu(&encl->srcu); + mmu_notifier_unregister(&encl_mm->mmu_notifier, encl_mm->mm); + kfree(encl_mm); }

- /* Detect EPC page leaks. */ - WARN_ON_ONCE(encl->secs_child_cnt); - WARN_ON_ONCE(encl->secs.epc_page); - - kfree(encl); + kref_put(&encl->refcount, sgx_encl_release); return 0; }

@@ -70,6 +87,10 @@ static int sgx_mmap(struct file *file, struct vm_area_struct *vma) 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; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 57eff300f487..b74dadf85989 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,11 +12,90 @@ #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)); @@ -31,11 +110,27 @@ static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl, if ((entry->vm_max_prot_bits & vm_prot_bits) != vm_prot_bits) return ERR_PTR(-EFAULT);

- /* No page found. */ - if (!entry->epc_page) - 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; }

@@ -51,12 +146,23 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)

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; }

@@ -76,11 +182,29 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf) 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 @@ -151,4 +275,355 @@ static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start, const struct vm_operations_struct sgx_vm_ops = { .fault = sgx_vma_fault, .mprotect = sgx_vma_mprotect, + .open = sgx_vma_open, +}; + +/** + * 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 index 8a4d1edded68..d8d30ccbef4c 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -19,11 +19,18 @@ #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 { @@ -33,6 +40,13 @@ enum sgx_encl_flags { 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; @@ -44,6 +58,30 @@ struct sgx_encl { 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; @@ -65,4 +103,17 @@ static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr, 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/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 0ba0e670e2f0..6d37117ac8a0 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -16,20 +16,77 @@ #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;

- secs_epc = __sgx_alloc_epc_page(); - if (IS_ERR(secs_epc)) - return PTR_ERR(secs_epc); + 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;

@@ -63,6 +120,13 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) 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; }

@@ -228,21 +292,35 @@ static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src, { 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(); + 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 @@ -273,6 +351,7 @@ static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src, goto err_out; }

+ sgx_mark_page_reclaimable(encl_page->epc_page); mutex_unlock(&encl->lock); mmap_read_unlock(current->mm); return ret; @@ -281,9 +360,11 @@ static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src, 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);

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 38f2e80cc31a..3426785df457 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -16,6 +16,15 @@ 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 @@ -50,6 +59,348 @@ static void sgx_sanitize_section(struct sgx_epc_section *section) list_splice(&dirty, &section->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; @@ -71,6 +422,20 @@ static int ksgxd(void *p) 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; }

@@ -100,6 +465,7 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_sec

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; @@ -132,6 +498,100 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void) 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 @@ -143,12 +603,15 @@ 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); }

@@ -176,9 +639,12 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,

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->laundry_list); }

+ section->free_cnt = nr_pages; return true; }

diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index 91234f425b89..a188a683ffb6 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -15,9 +15,17 @@

#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; };

@@ -33,6 +41,7 @@ struct sgx_epc_section { struct list_head page_list; struct list_head laundry_list; struct sgx_epc_page *pages; + unsigned long free_cnt; spinlock_t lock; };

@@ -61,4 +70,8 @@ static inline void *sgx_get_epc_virt_addr(struct sgx_epc_page *page) 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 */

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 947c6e11fa4310b31c10016ae9816cdca3f1694e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Enclave memory is normally inaccessible from outside the enclave. This makes enclaves hard to debug. However, enclaves can be put in a debug mode when they are being built. In that mode, enclave data *can* be read and/or written by using the ENCLS[EDBGRD] and ENCLS[EDBGWR] functions.

This is obviously only for debugging and destroys all the protections present with normal enclaves. But, enclaves know their own debug status and can adjust their behavior appropriately.

Add a vm_ops->access() implementation which can be used to read and write memory inside debug enclaves. This is typically used via ptrace() APIs.

[ bp: Massage. ]

Intel-SIG: commit 947c6e11fa43 x86/sgx: Add ptrace() support for the SGX driver Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Tested-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-23-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/encl.c | 111 +++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+)

diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index b74dadf85989..ee50a5010277 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -272,10 +272,121 @@ static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start, 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, };

/**

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 3fa97bf001262a1d88ec9b4ac5ae6abe0ed1356c category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Document the Intel SGX kernel architecture. The fine-grained architecture details can be looked up from Intel SDM Volume 3D.

Intel-SIG: commit 3fa97bf00126 Documentation/x86: Document SGX kernel architecture Backport for SGX Foundations support

Co-developed-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Cc: linux-doc@vger.kernel.org Link: https://lkml.kernel.org/r/20201112220135.165028-24-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- Documentation/x86/index.rst | 1 + Documentation/x86/sgx.rst | 211 ++++++++++++++++++++++++++++++++++++ 2 files changed, 212 insertions(+) create mode 100644 Documentation/x86/sgx.rst

diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index b224d12c880b..647a570d4931 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -33,3 +33,4 @@ x86-specific Documentation i386/index x86_64/index sva + sgx diff --git a/Documentation/x86/sgx.rst b/Documentation/x86/sgx.rst new file mode 100644 index 000000000000..eaee1368b4fd --- /dev/null +++ b/Documentation/x86/sgx.rst @@ -0,0 +1,211 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============================== +Software Guard eXtensions (SGX) +=============================== + +Overview +======== + +Software Guard eXtensions (SGX) hardware enables for user space applications +to set aside private memory regions of code and data: + +* Privileged (ring-0) ENCLS functions orchestrate the construction of the. + regions. +* Unprivileged (ring-3) ENCLU functions allow an application to enter and + execute inside the regions. + +These memory regions are called enclaves. An enclave can be only entered at a +fixed set of entry points. Each entry point can hold a single hardware thread +at a time. While the enclave is loaded from a regular binary file by using +ENCLS functions, only the threads inside the enclave can access its memory. The +region is denied from outside access by the CPU, and encrypted before it leaves +from LLC. + +The support can be determined by + + ``grep sgx /proc/cpuinfo`` + +SGX must both be supported in the processor and enabled by the BIOS. If SGX +appears to be unsupported on a system which has hardware support, ensure +support is enabled in the BIOS. If a BIOS presents a choice between "Enabled" +and "Software Enabled" modes for SGX, choose "Enabled". + +Enclave Page Cache +================== + +SGX utilizes an *Enclave Page Cache (EPC)* to store pages that are associated +with an enclave. It is contained in a BIOS-reserved region of physical memory. +Unlike pages used for regular memory, pages can only be accessed from outside of +the enclave during enclave construction with special, limited SGX instructions. + +Only a CPU executing inside an enclave can directly access enclave memory. +However, a CPU executing inside an enclave may access normal memory outside the +enclave. + +The kernel manages enclave memory similar to how it treats device memory. + +Enclave Page Types +------------------ + +**SGX Enclave Control Structure (SECS)** + Enclave's address range, attributes and other global data are defined + by this structure. + +**Regular (REG)** + Regular EPC pages contain the code and data of an enclave. + +**Thread Control Structure (TCS)** + Thread Control Structure pages define the entry points to an enclave and + track the execution state of an enclave thread. + +**Version Array (VA)** + Version Array pages contain 512 slots, each of which can contain a version + number for a page evicted from the EPC. + +Enclave Page Cache Map +---------------------- + +The processor tracks EPC pages in a hardware metadata structure called the +*Enclave Page Cache Map (EPCM)*. The EPCM contains an entry for each EPC page +which describes the owning enclave, access rights and page type among the other +things. + +EPCM permissions are separate from the normal page tables. This prevents the +kernel from, for instance, allowing writes to data which an enclave wishes to +remain read-only. EPCM permissions may only impose additional restrictions on +top of normal x86 page permissions. + +For all intents and purposes, the SGX architecture allows the processor to +invalidate all EPCM entries at will. This requires that software be prepared to +handle an EPCM fault at any time. In practice, this can happen on events like +power transitions when the ephemeral key that encrypts enclave memory is lost. + +Application interface +===================== + +Enclave build functions +----------------------- + +In addition to the traditional compiler and linker build process, SGX has a +separate enclave “build” process. Enclaves must be built before they can be +executed (entered). The first step in building an enclave is opening the +**/dev/sgx_enclave** device. Since enclave memory is protected from direct +access, special privileged instructions are Then used to copy data into enclave +pages and establish enclave page permissions. + +.. kernel-doc:: arch/x86/kernel/cpu/sgx/ioctl.c + :functions: sgx_ioc_enclave_create + sgx_ioc_enclave_add_pages + sgx_ioc_enclave_init + sgx_ioc_enclave_provision + +Enclave vDSO +------------ + +Entering an enclave can only be done through SGX-specific EENTER and ERESUME +functions, and is a non-trivial process. Because of the complexity of +transitioning to and from an enclave, enclaves typically utilize a library to +handle the actual transitions. This is roughly analogous to how glibc +implementations are used by most applications to wrap system calls. + +Another crucial characteristic of enclaves is that they can generate exceptions +as part of their normal operation that need to be handled in the enclave or are +unique to SGX. + +Instead of the traditional signal mechanism to handle these exceptions, SGX +can leverage special exception fixup provided by the vDSO. The kernel-provided +vDSO function wraps low-level transitions to/from the enclave like EENTER and +ERESUME. The vDSO function intercepts exceptions that would otherwise generate +a signal and return the fault information directly to its caller. This avoids +the need to juggle signal handlers. + +.. kernel-doc:: arch/x86/include/uapi/asm/sgx.h + :functions: vdso_sgx_enter_enclave_t + +ksgxd +===== + +SGX support includes a kernel thread called *ksgxwapd*. + +EPC sanitization +---------------- + +ksgxd is started when SGX initializes. Enclave memory is typically ready +For use when the processor powers on or resets. However, if SGX has been in +use since the reset, enclave pages may be in an inconsistent state. This might +occur after a crash and kexec() cycle, for instance. At boot, ksgxd +reinitializes all enclave pages so that they can be allocated and re-used. + +The sanitization is done by going through EPC address space and applying the +EREMOVE function to each physical page. Some enclave pages like SECS pages have +hardware dependencies on other pages which prevents EREMOVE from functioning. +Executing two EREMOVE passes removes the dependencies. + +Page reclaimer +-------------- + +Similar to the core kswapd, ksgxd, is responsible for managing the +overcommitment of enclave memory. If the system runs out of enclave memory, +*ksgxwapd* “swaps” enclave memory to normal memory. + +Launch Control +============== + +SGX provides a launch control mechanism. After all enclave pages have been +copied, kernel executes EINIT function, which initializes the enclave. Only after +this the CPU can execute inside the enclave. + +ENIT function takes an RSA-3072 signature of the enclave measurement. The function +checks that the measurement is correct and signature is signed with the key +hashed to the four **IA32_SGXLEPUBKEYHASH{0, 1, 2, 3}** MSRs representing the +SHA256 of a public key. + +Those MSRs can be configured by the BIOS to be either readable or writable. +Linux supports only writable configuration in order to give full control to the +kernel on launch control policy. Before calling EINIT function, the driver sets +the MSRs to match the enclave's signing key. + +Encryption engines +================== + +In order to conceal the enclave data while it is out of the CPU package, the +memory controller has an encryption engine to transparently encrypt and decrypt +enclave memory. + +In CPUs prior to Ice Lake, the Memory Encryption Engine (MEE) is used to +encrypt pages leaving the CPU caches. MEE uses a n-ary Merkle tree with root in +SRAM to maintain integrity of the encrypted data. This provides integrity and +anti-replay protection but does not scale to large memory sizes because the time +required to update the Merkle tree grows logarithmically in relation to the +memory size. + +CPUs starting from Icelake use Total Memory Encryption (TME) in the place of +MEE. TME-based SGX implementations do not have an integrity Merkle tree, which +means integrity and replay-attacks are not mitigated. B, it includes +additional changes to prevent cipher text from being returned and SW memory +aliases from being Created. + +DMA to enclave memory is blocked by range registers on both MEE and TME systems +(SDM section 41.10). + +Usage Models +============ + +Shared Library +-------------- + +Sensitive data and the code that acts on it is partitioned from the application +into a separate library. The library is then linked as a DSO which can be loaded +into an enclave. The application can then make individual function calls into +the enclave through special SGX instructions. A run-time within the enclave is +configured to marshal function parameters into and out of the enclave and to +call the correct library function. + +Application Container +--------------------- + +An application may be loaded into a container enclave which is specially +configured with a library OS and run-time which permits the application to run. +The enclave run-time and library OS work together to execute the application +when a thread enters the enclave.

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit bc4bac2ecef0e47fd5c02f9c6f9585fd477f9beb category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Add the maintainer information for the SGX subsystem.

Intel-SIG: commit bc4bac2ecef0 x86/sgx: Update MAINTAINERS Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Jethro Beekman jethro@fortanix.com Link: https://lkml.kernel.org/r/20201112220135.165028-25-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- MAINTAINERS | 13 +++++++++++++ 1 file changed, 13 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS index 342cc197d0ca..9b5ee13d1373 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9159,6 +9159,19 @@ F: Documentation/x86/intel_txt.rst F: arch/x86/kernel/tboot.c F: include/linux/tboot.h

+INTEL SGX +M: Jarkko Sakkinen jarkko@kernel.org +L: linux-sgx@vger.kernel.org +S: Supported +Q: https://patchwork.kernel.org/project/intel-sgx/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-sgx.git +F: Documentation/x86/sgx.rst +F: arch/x86/entry/vdso/vsgx.S +F: arch/x86/include/uapi/asm/sgx.h +F: arch/x86/kernel/cpu/sgx/* +F: tools/testing/selftests/sgx/* +K: \bSGX_ + INTERCONNECT API M: Georgi Djakov georgi.djakov@linaro.org L: linux-pm@vger.kernel.org

From: Dave Hansen dave.hansen@linux.intel.com

mainline inclusion from mainline-v5.11-rc1 commit 67655b57f8f59467506463055d9a8398d2836377 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Short Version:

The SGX section->laundry_list structure is effectively thread-local, but declared next to some shared structures. Its semantics are clear as mud. Fix that. No functional changes. Compile tested only.

Long Version:

The SGX hardware keeps per-page metadata. This can provide things like permissions, integrity and replay protection. It also prevents things like having an enclave page mapped multiple times or shared between enclaves.

But, that presents a problem for kexec()'d kernels (or any other kernel that does not run immediately after a hardware reset). This is because the last kernel may have been rude and forgotten to reset pages, which would trigger the "shared page" sanity check.

To fix this, the SGX code "launders" the pages by running the EREMOVE instruction on all pages at boot. This is slow and can take a long time, so it is performed off in the SGX-specific ksgxd instead of being synchronous at boot. The init code hands the list of pages to launder in a per-SGX-section list: ->laundry_list. The only code to touch this list is the init code and ksgxd. This means that no locking is necessary for ->laundry_list.

However, a lock is required for section->page_list, which is accessed while creating enclaves and by ksgxd. This lock (section->lock) is acquired by ksgxd while also processing ->laundry_list. It is easy to confuse the purpose of the locking as being for ->laundry_list and ->page_list.

Rename ->laundry_list to ->init_laundry_list to make it clear that this is not normally used at runtime. Also add some comments clarifying the locking, and reorganize 'sgx_epc_section' to put 'lock' near the things it protects.

Note: init_laundry_list is 128 bytes of wasted space at runtime. It could theoretically be dynamically allocated and then freed after the laundering process. But it would take nearly 128 bytes of extra instructions to do that.

Intel-SIG: commit 67655b57f8f5 x86/sgx: Clarify 'laundry_list' locking Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20201116222531.4834-1-dave.hansen@intel.com Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/main.c | 14 ++++++++------ arch/x86/kernel/cpu/sgx/sgx.h | 15 ++++++++++++--- 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 3426785df457..c519fc5f6948 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -36,13 +36,15 @@ static void sgx_sanitize_section(struct sgx_epc_section *section) LIST_HEAD(dirty); int ret;

- while (!list_empty(&section->laundry_list)) { + /* 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->laundry_list, + page = list_first_entry(&section->init_laundry_list, struct sgx_epc_page, list);

ret = __eremove(sgx_get_epc_virt_addr(page)); @@ -56,7 +58,7 @@ static void sgx_sanitize_section(struct sgx_epc_section *section) cond_resched(); }

- list_splice(&dirty, &section->laundry_list); + list_splice(&dirty, &section->init_laundry_list); }

static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) @@ -418,7 +420,7 @@ static int ksgxd(void *p) sgx_sanitize_section(&sgx_epc_sections[i]);

/* Should never happen. */ - if (!list_empty(&sgx_epc_sections[i].laundry_list)) + if (!list_empty(&sgx_epc_sections[i].init_laundry_list)) WARN(1, "EPC section %d has unsanitized pages.\n", i); }

@@ -635,13 +637,13 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, section->phys_addr = phys_addr; spin_lock_init(&section->lock); INIT_LIST_HEAD(&section->page_list); - INIT_LIST_HEAD(&section->laundry_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->laundry_list); + list_add_tail(&section->pages[i].list, &section->init_laundry_list); }

section->free_cnt = nr_pages; diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index a188a683ffb6..5fa42d143feb 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -34,15 +34,24 @@ struct sgx_epc_page { * 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 list_head page_list; - struct list_head laundry_list; struct sgx_epc_page *pages; - unsigned long free_cnt; + 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];

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit 14132a5b807bb5caf778fe7ae1597e630971e949 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Return -ERESTARTSYS instead of -EINTR in sgx_ioc_enclave_add_pages() when interrupted before any pages have been processed. At this point ioctl can be obviously safely restarted.

Intel-SIG: commit 14132a5b807b x86/sgx: Return -ERESTARTSYS in sgx_ioc_enclave_add_pages() Backport for SGX Foundations support

Reported-by: Haitao Huang haitao.huang@intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20201118213932.63341-1-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 6d37117ac8a0..30aefc93a31d 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -444,7 +444,7 @@ static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg) for (c = 0 ; c < add_arg.length; c += PAGE_SIZE) { if (signal_pending(current)) { if (!c) - ret = -EINTR; + ret = -ERESTARTSYS;

break; }

From: Borislav Petkov bp@suse.de

mainline inclusion from mainline-v5.11-rc1 commit afe76eca862ccde2a0c30105fc97a46a0b59339b category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Fix

./arch/x86/kernel/cpu/sgx/ioctl.c:666: warning: Function parameter or member \ 'encl' not described in 'sgx_ioc_enclave_provision' ./arch/x86/kernel/cpu/sgx/ioctl.c:666: warning: Excess function parameter \ 'enclave' description in 'sgx_ioc_enclave_provision'

Intel-SIG: commit afe76eca862c x86/sgx: Fix sgx_ioc_enclave_provision() kernel-doc comment Backport for SGX Foundations support

Reported-by: Stephen Rothwell sfr@canb.auug.org.au Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20201123181922.0c009406@canb.auug.org.au Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 30aefc93a31d..c206aee80a04 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -652,7 +652,7 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg)

/** * sgx_ioc_enclave_provision() - handler for %SGX_IOC_ENCLAVE_PROVISION - * @enclave: an enclave pointer + * @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

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11-rc1 commit a4b9c48b96517ff4780b22a784e7537eac5dc21b category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

The sgx_enclave_add_pages.length field is documented as

* @length: length of the data (multiple of the page size)

Fail with -EINVAL, when the caller gives a zero length buffer of data to be added as pages to an enclave. Right now 'ret' is returned as uninitialized in that case.

[ bp: Flesh out commit message. ]

Intel-SIG: commit a4b9c48b9651 x86/sgx: Return -EINVAL on a zero length buffer in sgx_ioc_enclave_add_pages() Backport for SGX Foundations support

Fixes: c6d26d370767 ("x86/sgx: Add SGX_IOC_ENCLAVE_ADD_PAGES") Reported-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Link: https://lore.kernel.org/linux-sgx/X8ehQssnslm194ld@mwanda/ Link: https://lkml.kernel.org/r/20201203183527.139317-1-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index c206aee80a04..90a5caf76939 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -428,7 +428,7 @@ static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg) !IS_ALIGNED(add_arg.src, PAGE_SIZE)) return -EINVAL;

- if (add_arg.length & (PAGE_SIZE - 1)) + if (!add_arg.length || add_arg.length & (PAGE_SIZE - 1)) return -EINVAL;

if (add_arg.offset + add_arg.length - PAGE_SIZE >= encl->size)

From: Sami Tolvanen samitolvanen@google.com

mainline inclusion from mainline-v5.12-rc1-dontuse commit 31bf92881714fe9962d43d097b5114a9b4ad0a12 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

device_initcall() expects a function of type initcall_t, which returns an integer. Change the signature of sgx_init() to match.

Intel-SIG: commit 31bf92881714 x86/sgx: Fix the return type of sgx_init() Backport for SGX Foundations support

Fixes: e7e0545299d8c ("x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections") Signed-off-by: Sami Tolvanen samitolvanen@google.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Darren Kenny darren.kenny@oracle.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Link: https://lkml.kernel.org/r/20210113232311.277302-1-samitolvanen@google.com Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/main.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index c519fc5f6948..8df81a3ed945 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -700,25 +700,27 @@ static bool __init sgx_page_cache_init(void) return true; }

-static void __init sgx_init(void) +static int __init sgx_init(void) { int ret; int i;

if (!cpu_feature_enabled(X86_FEATURE_SGX)) - return; + return -ENODEV;

if (!sgx_page_cache_init()) - return; + return -ENOMEM;

- if (!sgx_page_reclaimer_init()) + if (!sgx_page_reclaimer_init()) { + ret = -ENOMEM; goto err_page_cache; + }

ret = sgx_drv_init(); if (ret) goto err_kthread;

- return; + return 0;

err_kthread: kthread_stop(ksgxd_tsk); @@ -728,6 +730,8 @@ static void __init sgx_init(void) vfree(sgx_epc_sections[i].pages); memunmap(sgx_epc_sections[i].virt_addr); } + + return ret; }

device_initcall(sgx_init);

From: Daniel Vetter daniel.vetter@ffwll.ch

mainline inclusion from mainline-v5.12-rc1-dontuse commit dc9b7be557ca94301ea5c06c0d72307e642ffb18 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

PTE insertion is fundamentally racy, and this check doesn't do anything useful. Quoting Sean:

"Yeah, it can be whacked. The original, never-upstreamed code asserted that the resolved PFN matched the PFN being installed by the fault handler as a sanity check on the SGX driver's EPC management. The WARN assertion got dropped for whatever reason, leaving that useless chunk."

Jason stumbled over this as a new user of follow_pfn(), and I'm trying to get rid of unsafe callers of that function so it can be locked down further.

This is independent prep work for the referenced patch series:

https://lore.kernel.org/dri-devel/20201127164131.2244124-1-daniel.vetter@ffw...

Intel-SIG: commit dc9b7be557ca x86/sgx: Drop racy follow_pfn() check Backport for SGX Foundations support

Fixes: 947c6e11fa43 ("x86/sgx: Add ptrace() support for the SGX driver") Reported-by: Jason Gunthorpe jgg@ziepe.ca Signed-off-by: Daniel Vetter daniel.vetter@intel.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Link: https://lkml.kernel.org/r/20210204184519.2809313-1-daniel.vetter@ffwll.ch Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/encl.c | 8 -------- 1 file changed, 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index ee50a5010277..20a2dd5ba2b4 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -141,7 +141,6 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf) 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; @@ -168,13 +167,6 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)

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);

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.11 commit 2ade0d60939bcd54197c133b03b460fe62a4ec47 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

This has been shown in tests:

[ +0.000008] WARNING: CPU: 3 PID: 7620 at kernel/rcu/srcutree.c:374 cleanup_srcu_struct+0xed/0x100

This is essentially a use-after free, although SRCU notices it as an SRCU cleanup in an invalid context.

== Background ==

SGX has a data structure (struct sgx_encl_mm) which keeps per-mm SGX metadata. This is separate from struct sgx_encl because, in theory, an enclave can be mapped from more than one mm. sgx_encl_mm includes a pointer back to the sgx_encl.

This means that sgx_encl must have a longer lifetime than all of the sgx_encl_mm's that point to it. That's usually the case: sgx_encl_mm is freed only after the mmu_notifier is unregistered in sgx_release().

However, there's a race. If the process is exiting, sgx_mmu_notifier_release() can be called in parallel with sgx_release() instead of being called *by* it. The mmu_notifier path keeps encl_mm alive past when sgx_encl can be freed. This inverts the lifetime rules and means that sgx_mmu_notifier_release() can access a freed sgx_encl.

== Fix ==

Increase encl->refcount when encl_mm->encl is established. Release this reference when encl_mm is freed. This ensures that encl outlives encl_mm.

[ bp: Massage commit message. ]

Intel-SIG: commit 2ade0d60939b x86/sgx: Maintain encl->refcount for each encl->mm_list entry Backport for SGX Foundations support

Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer") Reported-by: Haitao Huang haitao.huang@linux.intel.com Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Dave Hansen dave.hansen@linux.intel.com Link: https://lkml.kernel.org/r/20210207221401.29933-1-jarkko@kernel.org Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/driver.c | 3 +++ arch/x86/kernel/cpu/sgx/encl.c | 5 +++++ 2 files changed, 8 insertions(+)

diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index f2eac41bb4ff..8ce6d8371cfb 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -72,6 +72,9 @@ static int sgx_release(struct inode *inode, struct file *file) synchronize_srcu(&encl->srcu); mmu_notifier_unregister(&encl_mm->mmu_notifier, encl_mm->mm); kfree(encl_mm); + + /* 'encl_mm' is gone, put encl_mm->encl reference: */ + kref_put(&encl->refcount, sgx_encl_release); }

kref_put(&encl->refcount, sgx_encl_release); diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 20a2dd5ba2b4..7449ef33f081 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -473,6 +473,9 @@ 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);

+ /* 'encl_mm' is going away, put encl_mm->encl reference: */ + kref_put(&encl_mm->encl->refcount, sgx_encl_release); + kfree(encl_mm); }

@@ -526,6 +529,8 @@ int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm) if (!encl_mm) return -ENOMEM;

+ /* Grab a refcount for the encl_mm->encl reference: */ + kref_get(&encl->refcount); encl_mm->encl = encl; encl_mm->mm = mm; encl_mm->mmu_notifier.ops = &sgx_mmu_notifier_ops;

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.13-rc1 commit 51ab30eb2ad4c4a61f827dc18863cd70dc46dc32 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

During normal runtime, the "ksgxd" daemon behaves like a version of kswapd just for SGX. But, before it starts acting like kswapd, its first job is to initialize enclave memory.

Currently, the SGX boot code places each enclave page on a epc_section->init_laundry_list. Once it starts up, the ksgxd code walks over that list and populates the actual SGX page allocator.

However, the per-section structures are going away to make way for the SGX NUMA allocator. There's also little need to have a per-section structure; the enclave pages are all treated identically, and they can be placed on the correct allocator list from metadata stored in the enclave page (struct sgx_epc_page) itself.

Modify sgx_sanitize_section() to take a single page list instead of taking a section and deriving the list from there.

Intel-SIG: commit 51ab30eb2ad4 x86/sgx: Replace section->init_laundry_list with sgx_dirty_page_list Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Dave Hansen dave.hansen@linux.intel.com Link: https://lkml.kernel.org/r/20210317235332.362001-1-jarkko.sakkinen@intel.com Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/main.c | 54 ++++++++++++++++------------------ arch/x86/kernel/cpu/sgx/sgx.h | 7 ----- 2 files changed, 25 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 8df81a3ed945..f3a5cd2d27ef 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -26,39 +26,43 @@ static LIST_HEAD(sgx_active_page_list);

static DEFINE_SPINLOCK(sgx_reclaimer_lock);

+static LIST_HEAD(sgx_dirty_page_list); + /* - * Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS - * pages whose child pages blocked EREMOVE. + * Reset post-kexec EPC pages to the uninitialized state. The pages are removed + * from the input list, and made available for the page allocator. SECS pages + * prepending their children in the input list are left intact. */ -static void sgx_sanitize_section(struct sgx_epc_section *section) +static void __sgx_sanitize_pages(struct list_head *dirty_page_list) { 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)) { + /* dirty_page_list is thread-local, no need for a lock: */ + while (!list_empty(dirty_page_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); + page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);

ret = __eremove(sgx_get_epc_virt_addr(page)); - if (!ret) - list_move(&page->list, &section->page_list); - else + if (!ret) { + /* + * page is now sanitized. Make it available via the SGX + * page allocator: + */ + list_del(&page->list); + sgx_free_epc_page(page); + } else { + /* The page is not yet clean - move to the dirty list. */ list_move_tail(&page->list, &dirty); - - spin_unlock(&section->lock); + }

cond_resched(); }

- list_splice(&dirty, &section->init_laundry_list); + list_splice(&dirty, dirty_page_list); }

static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) @@ -405,24 +409,17 @@ static bool sgx_should_reclaim(unsigned long watermark)

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]); + __sgx_sanitize_pages(&sgx_dirty_page_list); + __sgx_sanitize_pages(&sgx_dirty_page_list);

- /* Should never happen. */ - if (!list_empty(&sgx_epc_sections[i].init_laundry_list)) - WARN(1, "EPC section %d has unsanitized pages.\n", i); - } + /* sanity check: */ + WARN_ON(!list_empty(&sgx_dirty_page_list));

while (!kthread_should_stop()) { if (try_to_freeze()) @@ -637,13 +634,12 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, 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); + list_add_tail(&section->pages[i].list, &sgx_dirty_page_list); }

section->free_cnt = nr_pages; diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index 5fa42d143feb..bc8af0428640 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -45,13 +45,6 @@ struct sgx_epc_section { 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];

From: Jarkko Sakkinen jarkko@kernel.org

mainline inclusion from mainline-v5.13-rc1 commit 901ddbb9ecf5425183ea0c09d10c2fd7868dce54 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

Background ==========

SGX enclave memory is enumerated by the processor in contiguous physical ranges called Enclave Page Cache (EPC) sections. Currently, there is a free list per section, but allocations simply target the lowest-numbered sections. This is functional, but has no NUMA awareness.

Fortunately, EPC sections are covered by entries in the ACPI SRAT table. These entries allow each EPC section to be associated with a NUMA node, just like normal RAM.

Solution ========

Implement a NUMA-aware enclave page allocator. Mirror the buddy allocator and maintain a list of enclave pages for each NUMA node. Attempt to allocate enclave memory first from local nodes, then fall back to other nodes.

Note that the fallback is not as sophisticated as the buddy allocator and is itself not aware of NUMA distances. When a node's free list is empty, it searches for the next-highest node with enclave pages (and will wrap if necessary). This could be improved in the future.

Other =====

NUMA_KEEP_MEMINFO dependency is required for phys_to_target_node().

[ Kai Huang: Do not return NULL from __sgx_alloc_epc_page() because callers do not expect that and that leads to a NULL ptr deref. ]

[ dhansen: Fix an uninitialized 'nid' variable in __sgx_alloc_epc_page() as

Reported-by: kernel test robot lkp@intel.com

to avoid any potential allocations from the wrong NUMA node or even premature allocation failures. ]

Intel-SIG: commit 901ddbb9ecf5 x86/sgx: Add a basic NUMA allocation scheme to sgx_alloc_epc_page() Backport for SGX Foundations support

Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Kai Huang kai.huang@intel.com Signed-off-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Dave Hansen dave.hansen@linux.intel.com Link: https://lore.kernel.org/lkml/158188326978.894464.217282995221175417.stgit@dw... Link: https://lkml.kernel.org/r/20210319040602.178558-1-kai.huang@intel.com Link: https://lkml.kernel.org/r/20210318214933.29341-1-dave.hansen@intel.com Link: https://lkml.kernel.org/r/20210317235332.362001-2-jarkko.sakkinen@intel.com Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/Kconfig | 1 + arch/x86/kernel/cpu/sgx/main.c | 119 +++++++++++++++++++++------------ arch/x86/kernel/cpu/sgx/sgx.h | 16 +++-- 3 files changed, 88 insertions(+), 48 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5cccb82ca62f..040fb77366dd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1966,6 +1966,7 @@ config X86_SGX depends on CRYPTO_SHA256=y select SRCU select MMU_NOTIFIER + select NUMA_KEEP_MEMINFO if NUMA 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 diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index f3a5cd2d27ef..13a7599ce7d4 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -23,9 +23,21 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); * with sgx_reclaimer_lock acquired. */ static LIST_HEAD(sgx_active_page_list); - static DEFINE_SPINLOCK(sgx_reclaimer_lock);

+/* The free page list lock protected variables prepend the lock. */ +static unsigned long sgx_nr_free_pages; + +/* Nodes with one or more EPC sections. */ +static nodemask_t sgx_numa_mask; + +/* + * Array with one list_head for each possible NUMA node. Each + * list contains all the sgx_epc_section's which are on that + * node. + */ +static struct sgx_numa_node *sgx_numa_nodes; + static LIST_HEAD(sgx_dirty_page_list);

/* @@ -312,6 +324,7 @@ static void sgx_reclaim_pages(void) struct sgx_epc_section *section; struct sgx_encl_page *encl_page; struct sgx_epc_page *epc_page; + struct sgx_numa_node *node; pgoff_t page_index; int cnt = 0; int ret; @@ -383,28 +396,18 @@ static void sgx_reclaim_pages(void) 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; + node = section->node;

- return cnt; + spin_lock(&node->lock); + list_add_tail(&epc_page->list, &node->free_page_list); + sgx_nr_free_pages++; + spin_unlock(&node->lock); + } }

static bool sgx_should_reclaim(unsigned long watermark) { - return sgx_nr_free_pages() < watermark && - !list_empty(&sgx_active_page_list); + return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list); }

static int ksgxd(void *p) @@ -451,45 +454,56 @@ static bool __init sgx_page_reclaimer_init(void) return true; }

-static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_section *section) +static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) { - struct sgx_epc_page *page; + struct sgx_numa_node *node = &sgx_numa_nodes[nid]; + struct sgx_epc_page *page = NULL;

- spin_lock(&section->lock); + spin_lock(&node->lock);

- if (list_empty(&section->page_list)) { - spin_unlock(&section->lock); + if (list_empty(&node->free_page_list)) { + spin_unlock(&node->lock); return NULL; }

- page = list_first_entry(&section->page_list, struct sgx_epc_page, list); + page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); - section->free_cnt--; + sgx_nr_free_pages--; + + spin_unlock(&node->lock);

- 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(). + * Iterate through NUMA nodes and reserve ia free EPC page to the caller. Start + * from the NUMA node, where the caller is executing. * * Return: - * an EPC page, - * -errno on error + * - an EPC page: A borrowed EPC pages were available. + * - NULL: Out of EPC pages. */ struct sgx_epc_page *__sgx_alloc_epc_page(void) { - struct sgx_epc_section *section; struct sgx_epc_page *page; - int i; + int nid_of_current = numa_node_id(); + int nid = nid_of_current;

- for (i = 0; i < sgx_nr_epc_sections; i++) { - section = &sgx_epc_sections[i]; + if (node_isset(nid_of_current, sgx_numa_mask)) { + page = __sgx_alloc_epc_page_from_node(nid_of_current); + if (page) + return page; + } + + /* Fall back to the non-local NUMA nodes: */ + while (true) { + nid = next_node_in(nid, sgx_numa_mask); + if (nid == nid_of_current) + break;

- page = __sgx_alloc_epc_page_from_section(section); + page = __sgx_alloc_epc_page_from_node(nid); if (page) return page; } @@ -600,6 +614,7 @@ struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim) void sgx_free_epc_page(struct sgx_epc_page *page) { struct sgx_epc_section *section = &sgx_epc_sections[page->section]; + struct sgx_numa_node *node = section->node; int ret;

WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED); @@ -608,10 +623,12 @@ void sgx_free_epc_page(struct sgx_epc_page *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); + spin_lock(&node->lock); + + list_add_tail(&page->list, &node->free_page_list); + sgx_nr_free_pages++; + + spin_unlock(&node->lock); }

static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, @@ -632,8 +649,6 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, }

section->phys_addr = phys_addr; - spin_lock_init(&section->lock); - INIT_LIST_HEAD(&section->page_list);

for (i = 0; i < nr_pages; i++) { section->pages[i].section = index; @@ -642,7 +657,7 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, list_add_tail(&section->pages[i].list, &sgx_dirty_page_list); }

- section->free_cnt = nr_pages; + sgx_nr_free_pages += nr_pages; return true; }

@@ -661,8 +676,13 @@ static bool __init sgx_page_cache_init(void) { u32 eax, ebx, ecx, edx, type; u64 pa, size; + int nid; int i;

+ sgx_numa_nodes = kmalloc_array(num_possible_nodes(), sizeof(*sgx_numa_nodes), GFP_KERNEL); + if (!sgx_numa_nodes) + return false; + for (i = 0; i < ARRAY_SIZE(sgx_epc_sections); i++) { cpuid_count(SGX_CPUID, i + SGX_CPUID_EPC, &eax, &ebx, &ecx, &edx);

@@ -685,6 +705,21 @@ static bool __init sgx_page_cache_init(void) break; }

+ nid = numa_map_to_online_node(phys_to_target_node(pa)); + if (nid == NUMA_NO_NODE) { + /* The physical address is already printed above. */ + pr_warn(FW_BUG "Unable to map EPC section to online node. Fallback to the NUMA node 0.\n"); + nid = 0; + } + + if (!node_isset(nid, sgx_numa_mask)) { + spin_lock_init(&sgx_numa_nodes[nid].lock); + INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list); + node_set(nid, sgx_numa_mask); + } + + sgx_epc_sections[i].node = &sgx_numa_nodes[nid]; + sgx_nr_epc_sections++; }

diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index bc8af0428640..653af8ca1a25 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -29,22 +29,26 @@ struct sgx_epc_page { struct list_head list; };

+/* + * Contains the tracking data for NUMA nodes having EPC pages. Most importantly, + * the free page list local to the node is stored here. + */ +struct sgx_numa_node { + struct list_head free_page_list; + spinlock_t lock; +}; + /* * 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; + struct sgx_numa_node *node; };

extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];

From: Ira Weiny ira.weiny@intel.com

mainline inclusion from mainline-v5.13-rc1 commit 633b0616cfe085679471a4c0fae02e8c3a1a9866 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SIGI CVE: NA

--------------------------------

kmap() is inefficient and is being replaced by kmap_local_page(), if possible. There is no readily apparent reason why initp_page needs to be allocated and kmap'ed() except that 'sigstruct' needs to be page-aligned and 'token' 512 byte-aligned.

Rather than change it to kmap_local_page(), use kmalloc() instead because kmalloc() can give this alignment when allocating PAGE_SIZE bytes.

Remove the alloc_page()/kmap() and replace with kmalloc(PAGE_SIZE, ...) to get a page aligned kernel address.

In addition, add a comment to document the alignment requirements so that others don't attempt to 'fix' this again.

[ bp: Massage commit message. ]

Intel-SIG: commit 633b0616cfe0 x86/sgx: Remove unnecessary kmap() from sgx_ioc_enclave_init() Backport for SGX Foundations support

Signed-off-by: Ira Weiny ira.weiny@intel.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20210324182246.2484875-1-ira.weiny@intel.com Signed-off-by: Fan Du fan.du@intel.com #openEuler_contributor Signed-off-by: Laibin Qiu qiulaibin@huawei.com --- arch/x86/kernel/cpu/sgx/ioctl.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 90a5caf76939..2e10367ea66c 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -604,7 +604,6 @@ 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;

@@ -615,11 +614,15 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg) if (copy_from_user(&init_arg, arg, sizeof(init_arg))) return -EFAULT;

- initp_page = alloc_page(GFP_KERNEL); - if (!initp_page) + /* + * 'sigstruct' must be on a page boundary and 'token' on a 512 byte + * boundary. kmalloc() will give this alignment when allocating + * PAGE_SIZE bytes. + */ + sigstruct = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!sigstruct) return -ENOMEM;

- sigstruct = kmap(initp_page); token = (void *)((unsigned long)sigstruct + PAGE_SIZE / 2); memset(token, 0, SGX_LAUNCH_TOKEN_SIZE);

@@ -645,8 +648,7 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg) ret = sgx_encl_init(encl, sigstruct, token);

out: - kunmap(initp_page); - __free_page(initp_page); + kfree(sigstruct); return ret; }