From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
To: linux-kernel@vger.kernel.org, x86@kernel.org, linux-sgx@vger.kernel.org
Cc: akpm@linux-foundation.org, dave.hansen@intel.com,
sean.j.christopherson@intel.com, nhorman@redhat.com,
npmccallum@redhat.com, serge.ayoun@intel.com,
shay.katz-zamir@intel.com, haitao.huang@intel.com,
andriy.shevchenko@linux.intel.com, tglx@linutronix.de,
kai.svahn@intel.com, bp@alien8.de, josh@joshtriplett.org,
luto@kernel.org, kai.huang@intel.com, rientjes@google.com,
cedric.xing@intel.com,
Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>,
Suresh Siddha <suresh.b.siddha@intel.com>
Subject: [PATCH v21 12/28] x86/sgx: Enumerate and track EPC sections
Date: Sat, 13 Jul 2019 20:07:48 +0300 [thread overview]
Message-ID: <20190713170804.2340-13-jarkko.sakkinen@linux.intel.com> (raw)
In-Reply-To: <20190713170804.2340-1-jarkko.sakkinen@linux.intel.com>
From: Sean Christopherson <sean.j.christopherson@intel.com>
Enumerate Enclave Page Cache (EPC) sections via CPUID and add the data
structures necessary to track EPC pages so that they can be allocated,
freed and managed. As a system may have multiple EPC sections, invoke
CPUID on SGX sub-leafs until an invalid leaf is encountered.
On NUMA systems, a node can have at most one bank. A bank can be at
most part of two nodes. SGX supports both nodes with a single memory
controller and also sub-cluster nodes with severals memory controllers
on a single die.
For simplicity, support a maximum of eight EPC sections. Current
client hardware supports only a single section, while upcoming server
hardware will support at most eight sections. Bounding the number of
sections also allows the section ID to be embedded along with a page's
offset in a single unsigned long, enabling easy retrieval of both the
VA and PA for a given page.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Co-developed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Co-developed-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Co-developed-by: Serge Ayoun <serge.ayoun@intel.com>
Signed-off-by: Serge Ayoun <serge.ayoun@intel.com>
---
arch/x86/Kconfig | 12 +++
arch/x86/kernel/cpu/Makefile | 1 +
arch/x86/kernel/cpu/sgx/Makefile | 2 +-
arch/x86/kernel/cpu/sgx/main.c | 158 ++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/sgx/reclaim.c | 84 ++++++++++++++++
arch/x86/kernel/cpu/sgx/sgx.h | 67 +++++++++++++
6 files changed, 323 insertions(+), 1 deletion(-)
create mode 100644 arch/x86/kernel/cpu/sgx/main.c
create mode 100644 arch/x86/kernel/cpu/sgx/reclaim.c
create mode 100644 arch/x86/kernel/cpu/sgx/sgx.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dce10b18f4bc..815328adf561 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1933,6 +1933,18 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS
If unsure, say y.
+config INTEL_SGX
+ bool "Intel SGX core functionality"
+ depends on X86_64 && CPU_SUP_INTEL
+ ---help---
+ Intel(R) 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 d7a1e5a9331c..97deac5108df 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_X86_MCE) += mce/
obj-$(CONFIG_MTRR) += mtrr/
obj-$(CONFIG_MICROCODE) += microcode/
obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/
+obj-$(CONFIG_INTEL_SGX) += sgx/
obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile
index 4432d935894e..fa930e292110 100644
--- a/arch/x86/kernel/cpu/sgx/Makefile
+++ b/arch/x86/kernel/cpu/sgx/Makefile
@@ -1 +1 @@
-obj-y += encls.o
+obj-y += encls.o main.o reclaim.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..e2317f6e4374
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+// Copyright(c) 2016-17 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/signal.h>
+#include <linux/slab.h>
+#include "arch.h"
+#include "sgx.h"
+
+struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
+EXPORT_SYMBOL_GPL(sgx_epc_sections);
+
+int sgx_nr_epc_sections;
+
+static __init void sgx_free_epc_section(struct sgx_epc_section *section)
+{
+ struct sgx_epc_page *page;
+
+ while (!list_empty(§ion->page_list)) {
+ page = list_first_entry(§ion->page_list,
+ struct sgx_epc_page, list);
+ list_del(&page->list);
+ kfree(page);
+ }
+
+ while (!list_empty(§ion->unsanitized_page_list)) {
+ page = list_first_entry(§ion->unsanitized_page_list,
+ struct sgx_epc_page, list);
+ list_del(&page->list);
+ kfree(page);
+ }
+
+ memunmap(section->va);
+}
+
+static __init int sgx_init_epc_section(u64 addr, u64 size, unsigned long index,
+ struct sgx_epc_section *section)
+{
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+ struct sgx_epc_page *page;
+ unsigned long i;
+
+ section->va = memremap(addr, size, MEMREMAP_WB);
+ if (!section->va)
+ return -ENOMEM;
+
+ section->pa = addr;
+ spin_lock_init(§ion->lock);
+ INIT_LIST_HEAD(§ion->page_list);
+ INIT_LIST_HEAD(§ion->unsanitized_page_list);
+
+ for (i = 0; i < nr_pages; i++) {
+ page = kzalloc(sizeof(*page), GFP_KERNEL);
+ if (!page)
+ goto out;
+ page->desc = (addr + (i << PAGE_SHIFT)) | index;
+ list_add_tail(&page->list, §ion->unsanitized_page_list);
+ section->free_cnt++;
+ }
+
+ return 0;
+out:
+ sgx_free_epc_section(section);
+ return -ENOMEM;
+}
+
+static __init void sgx_page_cache_teardown(void)
+{
+ int i;
+
+ for (i = 0; i < sgx_nr_epc_sections; i++)
+ sgx_free_epc_section(&sgx_epc_sections[i]);
+}
+
+/**
+ * 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 sgx_calc_section_metric(u64 low, u64 high)
+{
+ return (low & GENMASK_ULL(31, 12)) +
+ ((high & GENMASK_ULL(19, 0)) << 32);
+}
+
+static __init int sgx_page_cache_init(void)
+{
+ u32 eax, ebx, ecx, edx, type;
+ u64 pa, size;
+ int ret;
+ int i;
+
+ BUILD_BUG_ON(SGX_MAX_EPC_SECTIONS > (SGX_EPC_SECTION_MASK + 1));
+
+ for (i = 0; i < (SGX_MAX_EPC_SECTIONS + 1); i++) {
+ cpuid_count(SGX_CPUID, i + SGX_CPUID_FIRST_VARIABLE_SUB_LEAF,
+ &eax, &ebx, &ecx, &edx);
+
+ type = eax & SGX_CPUID_SUB_LEAF_TYPE_MASK;
+ if (type == SGX_CPUID_SUB_LEAF_INVALID)
+ break;
+ if (type != SGX_CPUID_SUB_LEAF_EPC_SECTION) {
+ pr_err_once("sgx: Unknown sub-leaf type: %u\n", type);
+ return -ENODEV;
+ }
+ if (i == SGX_MAX_EPC_SECTIONS) {
+ pr_warn("sgx: More than "
+ __stringify(SGX_MAX_EPC_SECTIONS)
+ " EPC sections\n");
+ break;
+ }
+
+ pa = sgx_calc_section_metric(eax, ebx);
+ size = sgx_calc_section_metric(ecx, edx);
+ pr_info("sgx: EPC section 0x%llx-0x%llx\n", pa, pa + size - 1);
+
+ ret = sgx_init_epc_section(pa, size, i, &sgx_epc_sections[i]);
+ if (ret) {
+ sgx_page_cache_teardown();
+ return ret;
+ }
+
+ sgx_nr_epc_sections++;
+ }
+
+ if (!sgx_nr_epc_sections) {
+ pr_err("sgx: There are zero EPC sections.\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static __init int sgx_init(void)
+{
+ int ret;
+
+ if (!boot_cpu_has(X86_FEATURE_SGX))
+ return false;
+
+ ret = sgx_page_cache_init();
+ if (ret)
+ return ret;
+
+ ret = sgx_page_reclaimer_init();
+ if (ret) {
+ sgx_page_cache_teardown();
+ return ret;
+ }
+
+ return 0;
+}
+
+arch_initcall(sgx_init);
diff --git a/arch/x86/kernel/cpu/sgx/reclaim.c b/arch/x86/kernel/cpu/sgx/reclaim.c
new file mode 100644
index 000000000000..042769f03be9
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/reclaim.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+// Copyright(c) 2016-19 Intel Corporation.
+
+#include <linux/freezer.h>
+#include <linux/highmem.h>
+#include <linux/kthread.h>
+#include <linux/pagemap.h>
+#include <linux/ratelimit.h>
+#include <linux/slab.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include "encls.h"
+#include "sgx.h"
+
+static struct task_struct *ksgxswapd_tsk;
+
+static void sgx_sanitize_section(struct sgx_epc_section *section)
+{
+ struct sgx_epc_page *page, *tmp;
+ LIST_HEAD(secs_list);
+ int ret;
+
+ while (!list_empty(§ion->unsanitized_page_list)) {
+ if (kthread_should_stop())
+ return;
+
+ spin_lock(§ion->lock);
+
+ page = list_first_entry(§ion->unsanitized_page_list,
+ struct sgx_epc_page, list);
+
+ ret = __eremove(sgx_epc_addr(page));
+ if (!ret)
+ list_move(&page->list, §ion->page_list);
+ else
+ list_move_tail(&page->list, &secs_list);
+
+ spin_unlock(§ion->lock);
+
+ cond_resched();
+ }
+
+ list_for_each_entry_safe(page, tmp, &secs_list, list) {
+ if (kthread_should_stop())
+ return;
+
+ ret = __eremove(sgx_epc_addr(page));
+ if (!WARN_ON_ONCE(ret)) {
+ spin_lock(§ion->lock);
+ list_move(&page->list, §ion->page_list);
+ spin_unlock(§ion->lock);
+ } else {
+ list_del(&page->list);
+ kfree(page);
+ }
+
+ cond_resched();
+ }
+}
+
+static int ksgxswapd(void *p)
+{
+ int i;
+
+ set_freezable();
+
+ for (i = 0; i < sgx_nr_epc_sections; i++)
+ sgx_sanitize_section(&sgx_epc_sections[i]);
+
+ return 0;
+}
+
+int sgx_page_reclaimer_init(void)
+{
+ struct task_struct *tsk;
+
+ tsk = kthread_run(ksgxswapd, NULL, "ksgxswapd");
+ if (IS_ERR(tsk))
+ return PTR_ERR(tsk);
+
+ ksgxswapd_tsk = tsk;
+
+ return 0;
+}
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
new file mode 100644
index 000000000000..3009ec816339
--- /dev/null
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+#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 <uapi/asm/sgx_errno.h>
+
+struct sgx_epc_page {
+ unsigned long desc;
+ struct list_head list;
+};
+
+/**
+ * struct sgx_epc_section
+ *
+ * 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 pa;
+ void *va;
+ struct list_head page_list;
+ struct list_head unsanitized_page_list;
+ unsigned long free_cnt;
+ spinlock_t lock;
+};
+
+#define SGX_MAX_EPC_SECTIONS 8
+
+extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
+
+/**
+ * enum sgx_epc_page_desc - bits and masks for an EPC page's descriptor
+ * %SGX_EPC_SECTION_MASK: SGX allows to have multiple EPC sections in the
+ * physical memory. The existing and near-future
+ * hardware defines at most eight sections, hence
+ * three bits to hold a section.
+ */
+enum sgx_epc_page_desc {
+ SGX_EPC_SECTION_MASK = GENMASK_ULL(3, 0),
+ /* bits 12-63 are reserved for the physical page address of the page */
+};
+
+static inline struct sgx_epc_section *sgx_epc_section(struct sgx_epc_page *page)
+{
+ return &sgx_epc_sections[page->desc & SGX_EPC_SECTION_MASK];
+}
+
+static inline void *sgx_epc_addr(struct sgx_epc_page *page)
+{
+ struct sgx_epc_section *section = sgx_epc_section(page);
+
+ return section->va + (page->desc & PAGE_MASK) - section->pa;
+}
+
+extern int sgx_nr_epc_sections;
+
+int sgx_page_reclaimer_init(void);
+
+#endif /* _X86_SGX_H */
--
2.20.1
next prev parent reply other threads:[~2019-07-13 17:10 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-13 17:07 [PATCH v21 00/28] Intel SGX foundations Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 01/28] x86/cpufeatures: Add Intel-defined SGX feature bit Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 02/28] x86/cpufeatures: Add SGX sub-features (as Linux-defined bits) Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 03/28] x86/msr: Add IA32_FEATURE_CONTROL.SGX_ENABLE definition Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 04/28] x86/cpufeatures: Add Intel-defined SGX_LC feature bit Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 05/28] x86/msr: Add SGX Launch Control MSR definitions Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 06/28] x86/mm: x86/sgx: Add new 'PF_SGX' page fault error code bit Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 07/28] x86/mm: x86/sgx: Signal SIGSEGV for userspace #PFs w/ PF_SGX Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 08/28] x86/cpu/intel: Detect SGX support and update caps appropriately Jarkko Sakkinen
2019-07-24 19:35 ` Sean Christopherson
2019-08-02 20:48 ` Jarkko Sakkinen
2019-08-07 15:17 ` Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 09/28] x86/sgx: Add ENCLS architectural error codes Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 10/28] x86/sgx: Add SGX1 and SGX2 architectural data structures Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 11/28] x86/sgx: Add wrappers for ENCLS leaf functions Jarkko Sakkinen
2019-07-13 17:07 ` Jarkko Sakkinen [this message]
2019-07-13 17:07 ` [PATCH v21 13/28] x86/sgx: Add functions to allocate and free EPC pages Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 14/28] x86/sgx: Add sgx_einit() for initializing enclaves Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 15/28] mm: Introduce vm_ops->may_mprotect() Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 16/28] x86/sgx: Add the Linux SGX Enclave Driver Jarkko Sakkinen
2019-07-29 11:17 ` Ayoun, Serge
2019-08-07 15:15 ` Jarkko Sakkinen
2019-08-07 15:17 ` Jarkko Sakkinen
2019-08-07 16:45 ` Jethro Beekman
2019-08-08 15:40 ` Sean Christopherson
2019-08-09 15:02 ` Jarkko Sakkinen
2019-08-09 15:24 ` Sean Christopherson
2019-08-05 16:16 ` Sean Christopherson
2019-08-05 21:39 ` Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 17/28] x86/sgx: Add provisioning Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 18/28] x86/sgx: Add swapping code to the core and SGX driver Jarkko Sakkinen
2019-08-07 6:33 ` Jethro Beekman
2019-08-07 19:12 ` Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 19/28] x86/sgx: ptrace() support for the " Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 20/28] x86/vdso: Add support for exception fixup in vDSO functions Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 21/28] x86/fault: Add helper function to sanitize error code Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 22/28] x86/traps: Attempt to fixup exceptions in vDSO before signaling Jarkko Sakkinen
2019-07-13 17:07 ` [PATCH v21 23/28] x86/vdso: Add __vdso_sgx_enter_enclave() to wrap SGX enclave transitions Jarkko Sakkinen
2019-07-17 22:07 ` Xing, Cedric
2019-07-13 17:08 ` [PATCH v21 24/28] selftests/x86: Add a selftest for SGX Jarkko Sakkinen
2019-07-17 22:37 ` Xing, Cedric
2019-08-02 20:46 ` Jarkko Sakkinen
2019-08-16 15:43 ` Jarkko Sakkinen
2019-08-16 15:51 ` Jarkko Sakkinen
2019-08-16 16:56 ` Jarkko Sakkinen
2019-07-13 17:08 ` [PATCH v21 25/28] x86/sgx: Update MAINTAINERS Jarkko Sakkinen
2019-07-13 17:08 ` [PATCH v21 26/28] docs: x86/sgx: Add Architecture documentation Jarkko Sakkinen
2019-07-13 17:08 ` [PATCH v21 27/28] docs: x86/sgx: Document kernel internals Jarkko Sakkinen
2019-07-13 17:08 ` [PATCH v21 28/28] docs: x86/sgx: Document the enclave API Jarkko Sakkinen
2019-07-14 14:36 ` [PATCH v21 00/28] Intel SGX foundations Jarkko Sakkinen
2019-08-07 6:40 ` Jethro Beekman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190713170804.2340-13-jarkko.sakkinen@linux.intel.com \
--to=jarkko.sakkinen@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=andriy.shevchenko@linux.intel.com \
--cc=bp@alien8.de \
--cc=cedric.xing@intel.com \
--cc=dave.hansen@intel.com \
--cc=haitao.huang@intel.com \
--cc=josh@joshtriplett.org \
--cc=kai.huang@intel.com \
--cc=kai.svahn@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-sgx@vger.kernel.org \
--cc=luto@kernel.org \
--cc=nhorman@redhat.com \
--cc=npmccallum@redhat.com \
--cc=rientjes@google.com \
--cc=sean.j.christopherson@intel.com \
--cc=serge.ayoun@intel.com \
--cc=shay.katz-zamir@intel.com \
--cc=suresh.b.siddha@intel.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).