Merge tag 'x86_sgx_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SGX updates from Borislav Petkov:

 - Add support for handling hw errors in SGX pages: poisoning,
   recovering from poison memory and error injection into SGX pages

 - A bunch of changes to the SGX selftests to simplify and allow of SGX
   features testing without the need of a whole SGX software stack

 - Add a sysfs attribute which is supposed to show the amount of SGX
   memory in a NUMA node, similar to what /proc/meminfo is to normal
   memory

 - The usual bunch of fixes and cleanups too

* tag 'x86_sgx_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/sgx: Fix NULL pointer dereference on non-SGX systems
  selftests/sgx: Fix corrupted cpuid macro invocation
  x86/sgx: Add an attribute for the amount of SGX memory in a NUMA node
  x86/sgx: Fix minor documentation issues
  selftests/sgx: Add test for multiple TCS entry
  selftests/sgx: Enable multiple thread support
  selftests/sgx: Add page permission and exception test
  selftests/sgx: Rename test properties in preparation for more enclave tests
  selftests/sgx: Provide per-op parameter structs for the test enclave
  selftests/sgx: Add a new kselftest: Unclobbered_vdso_oversubscribed
  selftests/sgx: Move setup_test_encl() to each TEST_F()
  selftests/sgx: Encpsulate the test enclave creation
  selftests/sgx: Dump segments and /proc/self/maps only on failure
  selftests/sgx: Create a heap for the test enclave
  selftests/sgx: Make data measurement for an enclave segment optional
  selftests/sgx: Assign source for each segment
  selftests/sgx: Fix a benign linker warning
  x86/sgx: Add check for SGX pages to ghes_do_memory_failure()
  x86/sgx: Add hook to error injection address validation
  x86/sgx: Hook arch_memory_failure() into mainline code
  ...

6 files changed, 186 insertions, 2 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index d3c4ab249e9c..847fde3d22cd 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1312,6 +1312,10 @@ config ARCH_HAS_PARANOID_L1D_FLUSH
 config DYNAMIC_SIGFRAME
 	bool
 
+# Select, if arch has a named attribute group bound to NUMA device nodes.
+config HAVE_ARCH_NODE_DEV_GROUP
+	bool
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4e0fb37cee16..8910b09b5601 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -269,6 +269,7 @@ config X86
 	select HAVE_ARCH_KCSAN			if X86_64
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
+	select HAVE_ARCH_NODE_DEV_GROUP		if X86_SGX
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 
 config INSTRUCTION_DECODER
@@ -1921,6 +1922,7 @@ config X86_SGX
 	select SRCU
 	select MMU_NOTIFIER
 	select NUMA_KEEP_MEMINFO if NUMA
+	select XARRAY_MULTI
 	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/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 355d38c0cf60..2c5f12ae7d04 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -855,4 +855,12 @@ enum mds_mitigations {
 	MDS_MITIGATION_VMWERV,
 };
 
+#ifdef CONFIG_X86_SGX
+int arch_memory_failure(unsigned long pfn, int flags);
+#define arch_memory_failure arch_memory_failure
+
+bool arch_is_platform_page(u64 paddr);
+#define arch_is_platform_page arch_is_platform_page
+#endif
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 872617542bbc..ff0f2d90338a 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_SET_MEMORY_H
 #define _ASM_X86_SET_MEMORY_H
 
+#include <linux/mm.h>
 #include <asm/page.h>
 #include <asm-generic/set_memory.h>
 
@@ -99,6 +100,9 @@ static inline int set_mce_nospec(unsigned long pfn, bool unmap)
 	unsigned long decoy_addr;
 	int rc;
 
+	/* SGX pages are not in the 1:1 map */
+	if (arch_is_platform_page(pfn << PAGE_SHIFT))
+		return 0;
 	/*
 	 * We would like to just call:
 	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 8471a8b9b48e..4b41efc9e367 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -6,11 +6,13 @@
 #include <linux/highmem.h>
 #include <linux/kthread.h>
 #include <linux/miscdevice.h>
+#include <linux/node.h>
 #include <linux/pagemap.h>
 #include <linux/ratelimit.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
+#include <linux/sysfs.h>
 #include <asm/sgx.h>
 #include "driver.h"
 #include "encl.h"
@@ -20,6 +22,7 @@ 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);
+static DEFINE_XARRAY(sgx_epc_address_space);
 
 /*
  * These variables are part of the state of the reclaimer, and must be accessed
@@ -60,6 +63,24 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
 
 		page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
 
+		/*
+		 * Checking page->poison without holding the node->lock
+		 * is racy, but losing the race (i.e. poison is set just
+		 * after the check) just means __eremove() will be uselessly
+		 * called for a page that sgx_free_epc_page() will put onto
+		 * the node->sgx_poison_page_list later.
+		 */
+		if (page->poison) {
+			struct sgx_epc_section *section = &sgx_epc_sections[page->section];
+			struct sgx_numa_node *node = section->node;
+
+			spin_lock(&node->lock);
+			list_move(&page->list, &node->sgx_poison_page_list);
+			spin_unlock(&node->lock);
+
+			continue;
+		}
+
 		ret = __eremove(sgx_get_epc_virt_addr(page));
 		if (!ret) {
 			/*
@@ -471,6 +492,7 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
 
 	page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list);
 	list_del_init(&page->list);
+	page->flags = 0;
 
 	spin_unlock(&node->lock);
 	atomic_long_dec(&sgx_nr_free_pages);
@@ -624,7 +646,12 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
 
 	spin_lock(&node->lock);
 
-	list_add_tail(&page->list, &node->free_page_list);
+	page->owner = NULL;
+	if (page->poison)
+		list_add(&page->list, &node->sgx_poison_page_list);
+	else
+		list_add_tail(&page->list, &node->free_page_list);
+	page->flags = SGX_EPC_PAGE_IS_FREE;
 
 	spin_unlock(&node->lock);
 	atomic_long_inc(&sgx_nr_free_pages);
@@ -648,17 +675,102 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
 	}
 
 	section->phys_addr = phys_addr;
+	xa_store_range(&sgx_epc_address_space, section->phys_addr,
+		       phys_addr + size - 1, section, GFP_KERNEL);
 
 	for (i = 0; i < nr_pages; i++) {
 		section->pages[i].section = index;
 		section->pages[i].flags = 0;
 		section->pages[i].owner = NULL;
+		section->pages[i].poison = 0;
 		list_add_tail(&section->pages[i].list, &sgx_dirty_page_list);
 	}
 
 	return true;
 }
 
+bool arch_is_platform_page(u64 paddr)
+{
+	return !!xa_load(&sgx_epc_address_space, paddr);
+}
+EXPORT_SYMBOL_GPL(arch_is_platform_page);
+
+static struct sgx_epc_page *sgx_paddr_to_page(u64 paddr)
+{
+	struct sgx_epc_section *section;
+
+	section = xa_load(&sgx_epc_address_space, paddr);
+	if (!section)
+		return NULL;
+
+	return &section->pages[PFN_DOWN(paddr - section->phys_addr)];
+}
+
+/*
+ * Called in process context to handle a hardware reported
+ * error in an SGX EPC page.
+ * If the MF_ACTION_REQUIRED bit is set in flags, then the
+ * context is the task that consumed the poison data. Otherwise
+ * this is called from a kernel thread unrelated to the page.
+ */
+int arch_memory_failure(unsigned long pfn, int flags)
+{
+	struct sgx_epc_page *page = sgx_paddr_to_page(pfn << PAGE_SHIFT);
+	struct sgx_epc_section *section;
+	struct sgx_numa_node *node;
+
+	/*
+	 * mm/memory-failure.c calls this routine for all errors
+	 * where there isn't a "struct page" for the address. But that
+	 * includes other address ranges besides SGX.
+	 */
+	if (!page)
+		return -ENXIO;
+
+	/*
+	 * If poison was consumed synchronously. Send a SIGBUS to
+	 * the task. Hardware has already exited the SGX enclave and
+	 * will not allow re-entry to an enclave that has a memory
+	 * error. The signal may help the task understand why the
+	 * enclave is broken.
+	 */
+	if (flags & MF_ACTION_REQUIRED)
+		force_sig(SIGBUS);
+
+	section = &sgx_epc_sections[page->section];
+	node = section->node;
+
+	spin_lock(&node->lock);
+
+	/* Already poisoned? Nothing more to do */
+	if (page->poison)
+		goto out;
+
+	page->poison = 1;
+
+	/*
+	 * If the page is on a free list, move it to the per-node
+	 * poison page list.
+	 */
+	if (page->flags & SGX_EPC_PAGE_IS_FREE) {
+		list_move(&page->list, &node->sgx_poison_page_list);
+		goto out;
+	}
+
+	/*
+	 * TBD: Add additional plumbing to enable pre-emptive
+	 * action for asynchronous poison notification. Until
+	 * then just hope that the poison:
+	 * a) is not accessed - sgx_free_epc_page() will deal with it
+	 *    when the user gives it back
+	 * b) results in a recoverable machine check rather than
+	 *    a fatal one
+	 */
+out:
+	spin_unlock(&node->lock);
+	return 0;
+}
+
 /**
  * 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
@@ -670,6 +782,48 @@ static inline u64 __init sgx_calc_section_metric(u64 low, u64 high)
 	       ((high & GENMASK_ULL(19, 0)) << 32);
 }
 
+#ifdef CONFIG_NUMA
+static ssize_t sgx_total_bytes_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%lu\n", sgx_numa_nodes[dev->id].size);
+}
+static DEVICE_ATTR_RO(sgx_total_bytes);
+
+static umode_t arch_node_attr_is_visible(struct kobject *kobj,
+		struct attribute *attr, int idx)
+{
+	/* Make all x86/ attributes invisible when SGX is not initialized: */
+	if (nodes_empty(sgx_numa_mask))
+		return 0;
+
+	return attr->mode;
+}
+
+static struct attribute *arch_node_dev_attrs[] = {
+	&dev_attr_sgx_total_bytes.attr,
+	NULL,
+};
+
+const struct attribute_group arch_node_dev_group = {
+	.name = "x86",
+	.attrs = arch_node_dev_attrs,
+	.is_visible = arch_node_attr_is_visible,
+};
+
+static void __init arch_update_sysfs_visibility(int nid)
+{
+	struct node *node = node_devices[nid];
+	int ret;
+
+	ret = sysfs_update_group(&node->dev.kobj, &arch_node_dev_group);
+
+	if (ret)
+		pr_err("sysfs update failed (%d), files may be invisible", ret);
+}
+#else /* !CONFIG_NUMA */
+static void __init arch_update_sysfs_visibility(int nid) {}
+#endif
+
 static bool __init sgx_page_cache_init(void)
 {
 	u32 eax, ebx, ecx, edx, type;
@@ -713,10 +867,16 @@ static bool __init sgx_page_cache_init(void)
 		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);
+			INIT_LIST_HEAD(&sgx_numa_nodes[nid].sgx_poison_page_list);
 			node_set(nid, sgx_numa_mask);
+			sgx_numa_nodes[nid].size = 0;
+
+			/* Make SGX-specific node sysfs files visible: */
+			arch_update_sysfs_visibility(nid);
 		}
 
 		sgx_epc_sections[i].node =  &sgx_numa_nodes[nid];
+		sgx_numa_nodes[nid].size += size;
 
 		sgx_nr_epc_sections++;
 	}
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 4628acec0009..0f17def9fe6f 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -26,9 +26,13 @@
 /* Pages, which are being tracked by the page reclaimer. */
 #define SGX_EPC_PAGE_RECLAIMER_TRACKED	BIT(0)
 
+/* Pages on free list */
+#define SGX_EPC_PAGE_IS_FREE		BIT(1)
+
 struct sgx_epc_page {
 	unsigned int section;
-	unsigned int flags;
+	u16 flags;
+	u16 poison;
 	struct sgx_encl_page *owner;
 	struct list_head list;
 };
@@ -39,6 +43,8 @@ struct sgx_epc_page {
  */
 struct sgx_numa_node {
 	struct list_head free_page_list;
+	struct list_head sgx_poison_page_list;
+	unsigned long size;
 	spinlock_t lock;
 };