Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Thomas Tai <thomas.tai@oracle.com>
To:     tony.luck@intel.com, dave.hansen@linux.intel.com,
        jarkko@kernel.org, reinette.chatre@intel.com, linmiaohe@huawei.com,
        akpm@linux-foundation.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, naoya.horiguchi@nec.com,
        thomas.tai@oracle.com
Subject: [PATCH V3 1/1] x86/sgx: Add code to inject hwpoison into SGX memory
Date:   Mon, 17 Oct 2022 18:33:05 -0400
Message-Id: <20221017223305.578073-2-thomas.tai@oracle.com>
In-Reply-To: <20221017223305.578073-1-thomas.tai@oracle.com>
References: <20221017223305.578073-1-thomas.tai@oracle.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Inspired by commit c6acb1e7bf46 ("x86/sgx: Add hook to error injection
address validation"), add a similar code in hwpoison_inject function to
check if the address is located in SGX Memory. The error will then be
handled by the arch_memory_failure function in the SGX driver. After
injection, the action_result() will print out the page type and the
action taken.

Signed-off-by: Thomas Tai <thomas.tai@oracle.com>
---
 Documentation/mm/hwpoison.rst | 24 ++++++++++++++++++++++++
 include/linux/mm.h            |  1 +
 include/ras/ras_event.h       |  1 +
 mm/hwpoison-inject.c          |  4 ++++
 mm/memory-failure.c           |  5 ++++-
 5 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/Documentation/mm/hwpoison.rst b/Documentation/mm/hwpoison.rst
index b9d5253c1305..100894bb020c 100644
--- a/Documentation/mm/hwpoison.rst
+++ b/Documentation/mm/hwpoison.rst
@@ -162,6 +162,30 @@ Testing
 
   Some portable hwpoison test programs in mce-test, see below.
 
+* Special notes for injection into SGX enclaves
+
+  1) Determine physical address of enclave page
+
+	dmesg | grep "sgx: EPC"
+
+	sgx: EPC section 0x8000c00000-0x807f7fffff
+	sgx: EPC section 0x10000c00000-0x1007fffffff
+
+  2) Convert the EPC address to page frame number.
+
+	For 4K page size, the page frame number for 0x8000c00000 is
+	0x8000c00000 / 0x1000 = 0x8000c00.
+
+  3) Inject a memory error
+
+	modprobe hwpoison-inject
+	echo "0x8000c00" > /sys/kernel/debug/hwpoison/corrupt-pfn
+
+  4) Check dmesg output
+
+        dmesg | grep "Memory failure"
+        Memory failure: 0x8000c00: recovery action for sgx page: Recovered
+
 References
 ==========
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 21f8b27bd9fd..cdca3ff1418c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3248,6 +3248,7 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
+	MF_MSG_SGX,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index cbd3ddd7c33d..ee3a925c1e9d 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -373,6 +373,7 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_BUDDY, "free buddy page" )				\
 	EM ( MF_MSG_DAX, "dax page" )					\
 	EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" )			\
+	EM ( MF_MSG_SGX, "sgx page" )					\
 	EMe ( MF_MSG_UNKNOWN, "unknown page" )
 
 /*
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index 65e242b5a432..141eeeb793b1 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -21,6 +21,10 @@ static int hwpoison_inject(void *data, u64 val)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/* Inject the error if the page is part of the processor reserved memory */
+	if (arch_is_platform_page(pfn << PAGE_SHIFT))
+		goto inject;
+
 	if (!pfn_valid(pfn))
 		return -ENXIO;
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 14439806b5ef..40a22b23b50a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -781,6 +781,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_DAX]			= "dax page",
 	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
+	[MF_MSG_SGX]			= "sgx page",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1990,8 +1991,10 @@ int memory_failure(unsigned long pfn, int flags)
 	p = pfn_to_online_page(pfn);
 	if (!p) {
 		res = arch_memory_failure(pfn, flags);
-		if (res == 0)
+		if (res == 0) {
+			action_result(pfn, MF_MSG_SGX, MF_RECOVERED);
 			goto unlock_mutex;
+		}
 
 		if (pfn_valid(pfn)) {
 			pgmap = get_dev_pagemap(pfn, NULL);
-- 
2.31.1