From:   Eric DeVolder <eric.devolder@oracle.com>
To:     linux-kernel@vger.kernel.org, x86@kernel.org,
        kexec@lists.infradead.org, ebiederm@xmission.com,
        dyoung@redhat.com, bhe@redhat.com, vgoyal@redhat.com
Cc:     tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
        dave.hansen@linux.intel.com, hpa@zytor.com,
        nramas@linux.microsoft.com, thomas.lendacky@amd.com,
        robh@kernel.org, efault@gmx.de, rppt@kernel.org,
        konrad.wilk@oracle.com, boris.ostrovsky@oracle.com,
        eric.devolder@oracle.com
Subject: [RFC v2 4/6] crash hp: generic crash hotplug support infrastructure
Date:   Tue,  7 Dec 2021 14:52:02 -0500
Message-Id: <20211207195204.1582-5-eric.devolder@oracle.com>
In-Reply-To: <20211207195204.1582-1-eric.devolder@oracle.com>
References: <20211207195204.1582-1-eric.devolder@oracle.com>
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?CFzVJTBEVaYUn32ajo4YaU/Wk2EM4DihjD3qIZUmlCJGOAdhs5HBGOjmj0XJ?=
 =?us-ascii?Q?qJxrvJRHN46U8UfuAjOFclMwo9hO0bAw3rLFs3A6Gkanz339LMiwC0hro8LH?=
 =?us-ascii?Q?e9h8I/sos5fScdiyCLZkoHKks9DpAx8pafqNZFJStiKpwf9F/BHw5H8HdbEX?=
 =?us-ascii?Q?V0gv0GYfZk/XehEBsziQiEUXG6/XAltp59XgzOt7NX9yJdxA7bXVxnAG76WG?=
 =?us-ascii?Q?aDUgpnOfh3S7vs1/4v2SA4lZgxdoWBcrfBvKCM/ZDZQnYNubmfNoSshIg1sf?=
 =?us-ascii?Q?5iXmeMq/Po/gQVlnyCS0pTpvBQBi3fwU+rGt6BJproqFNWq/YU7z9v4tXooh?=
 =?us-ascii?Q?mNSRPBixg5sU9amE1+fi7hRQFJURO1QZqyiNnkQNhlfWWY5QbZjG7lVprXoa?=
 =?us-ascii?Q?yULiqF2YCx5fdWXPJWy5KeM2gSwoyp7PBH8JGFKHmB6ScnU1scUGMsr646zE?=
 =?us-ascii?Q?bdPY6O3cQgOXFrynxdi6Pkb7xrkvCtq9KBNEdBXVelPBnbIy1jr1a9TJ5Leo?=
 =?us-ascii?Q?aJUEk2UrMl4oTRwakb5JkAA5FL7Y/kgZ/pRN3b0EHEjFM7Pw5ZWeBsXTtJoy?=
 =?us-ascii?Q?5uBUkXWSeiy0ToKwZWMuLOZOQ3OCD2tOs1AOfafJpJCVyss+fsWPQ4yaqfXR?=
 =?us-ascii?Q?rItCMoJ8eanXvuTZZ8OlvoKo0cBXZTyXpBoXh7ZzKhQ9sovfROv/aY4J6Ths?=
 =?us-ascii?Q?yXmsb6u3KXCGeDu4GWcUNfyQXszGbymhw9PAf56dwa4YVeYD6cFIHRWKzH+y?=
 =?us-ascii?Q?4RE6CPXHglId7267pAMHf7510f1AJwaZpALU5xHwUrMs7ghJHeC14eJNE5HS?=
 =?us-ascii?Q?T/WlO/H5cxoEdf4whiowXYyRGsAqOo3VgnuwvKNcXS9eX9lfgX7Z4WjbEdLw?=
 =?us-ascii?Q?z0DC9xT0QGyNZt96GWvoPEx/GnDN83hpH/zkyoUnctq20FDCwCesHA4FYka6?=
 =?us-ascii?Q?E0CXRoOp2DekfqSERGGto5Kv0wLAyRG80ZUfJLNfVkxleDDwr+f8hPJQIgzo?=
 =?us-ascii?Q?60Rwdy0fB7dDAqzE9xKr2qipet5V7CRCyByj0Osn6VjAz75U6UvqNsdmouRb?=
 =?us-ascii?Q?EXeP38YpxeYclDRgUCLkg2XqVo3nyp0UF+5H8azuF7XslyXU5FMllnhqYxHo?=
 =?us-ascii?Q?UaOXQ32NAmjayqQjiLpXv8gFgi7+3PChMIlC0d3tHNhyyf3t6tOzfzDKhKAB?=
 =?us-ascii?Q?4YHAEn2/1i+85yg1xTkRGWOFoyVuMQZS5T+KLSj1DwjMrvNGqj127w0l0Iec?=
 =?us-ascii?Q?bjPLNyMjwgOZxOsEevFeUSU//hfpfgEDkoduYn9HzIT09IS+4eUef1b5RtCz?=
 =?us-ascii?Q?BfETsuo34T2G8EVBjXVSMbEd0t4WYpOgv3GBucTy3ByY6cR81PIc8tc6jltM?=
 =?us-ascii?Q?uGC9681NlnqpLDQBgU2FuR9R5FgUDALvutvHAa4UYEL+zclyUBkungKPf/G3?=
 =?us-ascii?Q?U+WJbxOPAr+ow41XjFe0P8ODyBC8BuJh3P9DOSOcemXuTppNKEMg608xvjz+?=
 =?us-ascii?Q?UcQRj6CYM4MVOMJ4D0oC00Aw1xwt2pACg2EfKLZEQxvcKIpI9tZphpV+gm1R?=
 =?us-ascii?Q?KFiXwutjUjBhVqDe5FbZFo403oTynqg9DP+7jvYmcIE9C0zOfP/L4Km13KMn?=
 =?us-ascii?Q?v1sVw3g6FHcNjjB2UpPhCYr4eUl6HyxoMEszOOTt5yLxdHTIUrjHlgyaBTSW?=
 =?us-ascii?Q?c/g7NA=3D=3D?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: b800970f-f044-4ea0-78b3-08d9b9bb190f
X-MS-Exchange-CrossTenant-AuthSource: CO1PR10MB4531.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 07 Dec 2021 19:52:28.1821
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: PkQAk+soaIcvO5JUrh53xEHiCo5TixqinSrspll7eo3D3kvjU1kwV3anywQIegevkf3lTB1RT+NzsdpgvFk3Wcg9FCuxNJXp3m8TbDnKuHY=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR10MB1695
X-Proofpoint-Virus-Version: vendor=nai engine=6300 definitions=10191 signatures=668683
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 mlxlogscore=999 mlxscore=0 spamscore=0
 phishscore=0 bulkscore=0 suspectscore=0 malwarescore=0 adultscore=0
 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2110150000
 definitions=main-2112070124
X-Proofpoint-ORIG-GUID: V2-HfuT3p4VaUHlFz0b5yKEkV8w4dmLr
X-Proofpoint-GUID: V2-HfuT3p4VaUHlFz0b5yKEkV8w4dmLr
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

This patch introduces a generic crash hot plug/unplug infrastructure
for CPU and memory changes. Upon CPU and memory changes, a generic
crash_hotplug_handler() obtains the appropriate lock, does some
important house keeping and then dispatches the hot plug/unplug event
to the architecture specific arch_crash_hotplug_handler(), and when
that handler returns, the lock is released.

This patch modifies crash_core.c to implement a subsys_initcall()
function that installs handlers for hot plug/unplug events. If CPU
hotplug is enabled, then cpuhp_setup_state() is invoked to register a
handler for CPU changes. Similarly, if memory hotplug is enabled, then
register_memory_notifier() is invoked to install a handler for memory
changes. These handlers in turn invoke the common generic handler
crash_hotplug_handler().

On the CPU side, cpuhp_setup_state_nocalls() is invoked with parameter
CPUHP_AP_ONLINE_DYN. While this works, when a CPU is being unplugged,
the CPU still shows up in foreach_present_cpu() during the regeneration
of the new CPU list, thus the need to explicitly check and exclude the
soon-to-be offlined CPU in crash_prepare_elf64_headers().

On the memory side, each un/plugged memory block passes through the
handler. For example, if a 1GiB DIMM is hotplugged, that generate 8
memory events, one for each 128MiB memblock.

Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
---
 kernel/crash_core.c | 118 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 118 insertions(+)

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index eb53f5ec62c9..9a30a305b04d 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -8,12 +8,16 @@
 #include <linux/crash_core.h>
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
+#include <linux/memory.h>
+#include <linux/cpuhotplug.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
 
 #include <crypto/sha1.h>
 
+#include "kexec_internal.h"
+
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
@@ -480,3 +484,117 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 subsys_initcall(crash_save_vmcoreinfo_init);
+
+#ifdef CONFIG_CRASH_HOTPLUG
+void __weak arch_crash_hotplug_handler(struct kimage *image,
+	unsigned int hp_action, unsigned long a, unsigned long b)
+{
+	pr_warn("crash hp: %s not implemented", __func__);
+}
+
+static void crash_hotplug_handler(unsigned int hp_action,
+	unsigned long a, unsigned long b)
+{
+	/* Obtain lock while changing crash information */
+	if (!mutex_trylock(&kexec_mutex))
+		return;
+
+	/* Check kdump is loaded */
+	if (kexec_crash_image) {
+		pr_debug("crash hp: hp_action %u, a %lu, b %lu", hp_action,
+			a, b);
+
+		/* Needed in order for the segments to be updated */
+		arch_kexec_unprotect_crashkres();
+
+		/* Flag to differentiate between normal load and hotplug */
+		kexec_crash_image->hotplug_event = true;
+
+		/*
+		 * Due to use of CPUHP_AP_ONLINE_DYN, upon unplug and during
+		 * this callback, the CPU is still in the for_each_present_cpu()
+		 * list. Must explicitly look to exclude this CPU when building
+		 * new list.
+		 */
+		kexec_crash_image->offlinecpu =
+			(hp_action == KEXEC_CRASH_HP_REMOVE_CPU) ?
+				(unsigned int)a : ~0U;
+
+		/* Now invoke arch-specific update handler */
+		arch_crash_hotplug_handler(kexec_crash_image, hp_action, a, b);
+
+		/* No longer handling a hotplug event */
+		kexec_crash_image->hotplug_event = false;
+
+		/* Change back to read-only */
+		arch_kexec_protect_crashkres();
+	}
+
+	/* Release lock now that update complete */
+	mutex_unlock(&kexec_mutex);
+}
+
+#if defined(CONFIG_MEMORY_HOTPLUG)
+static int crash_memhp_notifier(struct notifier_block *nb,
+	unsigned long val, void *v)
+{
+	struct memory_notify *mhp = v;
+	unsigned long start, end;
+
+	start = mhp->start_pfn << PAGE_SHIFT;
+	end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
+
+	switch (val) {
+	case MEM_GOING_ONLINE:
+		crash_hotplug_handler(KEXEC_CRASH_HP_ADD_MEMORY,
+			start, end-start);
+		break;
+
+	case MEM_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+		crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_MEMORY,
+			start, end-start);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block crash_memhp_nb = {
+	.notifier_call = crash_memhp_notifier,
+	.priority = 0
+};
+#endif
+
+#if defined(CONFIG_HOTPLUG_CPU)
+static int crash_cpuhp_online(unsigned int cpu)
+{
+	crash_hotplug_handler(KEXEC_CRASH_HP_ADD_CPU, cpu, 0);
+	return 0;
+}
+
+static int crash_cpuhp_offline(unsigned int cpu)
+{
+	crash_hotplug_handler(KEXEC_CRASH_HP_REMOVE_CPU, cpu, 0);
+	return 0;
+}
+#endif
+
+static int __init crash_hotplug_init(void)
+{
+	int result = 0;
+
+#if defined(CONFIG_MEMORY_HOTPLUG)
+	register_memory_notifier(&crash_memhp_nb);
+#endif
+
+#if defined(CONFIG_HOTPLUG_CPU)
+	result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				"crash/cpuhp",
+				crash_cpuhp_online, crash_cpuhp_offline);
+#endif
+
+	return result;
+}
+
+subsys_initcall(crash_hotplug_init);
+#endif /* CONFIG_CRASH_HOTPLUG */
-- 
2.27.0