Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:3 as permitted sender) client-ip=2620:137:e000::3:3;
From:   Sumanth Korikkar <sumanthk@linux.ibm.com>
To:     linux-mm <linux-mm@kvack.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        David Hildenbrand <david@redhat.com>
Cc:     Oscar Salvador <osalvador@suse.de>, Michal Hocko <mhocko@suse.com>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
        Anshuman Khandual <anshuman.khandual@arm.com>,
        Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
        Sumanth Korikkar <sumanthk@linux.ibm.com>,
        Alexander Gordeev <agordeev@linux.ibm.com>,
        Heiko Carstens <hca@linux.ibm.com>,
        Vasily Gorbik <gor@linux.ibm.com>,
        linux-s390 <linux-s390@vger.kernel.org>,
        LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH v3 4/5] s390/mm: implement MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers
Date:   Mon, 27 Nov 2023 09:20:22 +0100
Message-Id: <20231127082023.2079810-5-sumanthk@linux.ibm.com>
In-Reply-To: <20231127082023.2079810-1-sumanthk@linux.ibm.com>
References: <20231127082023.2079810-1-sumanthk@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

MEM_PREPARE_ONLINE memory notifier makes memory block physical
accessible via sclp assign command. The notifier ensures self-contained
memory maps are accessible and hence enabling the "memmap on memory" on
s390.

MEM_FINISH_OFFLINE memory notifier shifts the memory block to an
inaccessible state via sclp unassign command.

Implementation considerations:
* When MHP_MEMMAP_ON_MEMORY is disabled, the system retains the old
  behavior. This means the memory map is allocated from default memory.
* If MACHINE_HAS_EDAT1 is unavailable, MHP_MEMMAP_ON_MEMORY is
  automatically disabled. This ensures that vmemmap pagetables do not
  consume additional memory from the default memory allocator.
* The MEM_GOING_ONLINE notifier has been modified to perform no
  operation, as MEM_PREPARE_ONLINE already executes the sclp assign
  command.
* The MEM_CANCEL_ONLINE/MEM_OFFLINE notifier now performs no operation, as
  MEM_FINISH_OFFLINE already executes the sclp unassign command.

Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
---
 drivers/s390/char/sclp_cmd.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 355e63e44e95..30b829e4c052 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/memory.h>
+#include <linux/memory_hotplug.h>
 #include <linux/module.h>
 #include <asm/ctlreg.h>
 #include <asm/chpid.h>
@@ -26,6 +27,7 @@
 #include <asm/sclp.h>
 #include <asm/numa.h>
 #include <asm/facility.h>
+#include <asm/page-states.h>
 
 #include "sclp.h"
 
@@ -319,6 +321,7 @@ static bool contains_standby_increment(unsigned long start, unsigned long end)
 static int sclp_mem_notifier(struct notifier_block *nb,
 			     unsigned long action, void *data)
 {
+	struct memory_block *memory_block;
 	unsigned long start, size;
 	struct memory_notify *arg;
 	unsigned char id;
@@ -340,18 +343,29 @@ static int sclp_mem_notifier(struct notifier_block *nb,
 		if (contains_standby_increment(start, start + size))
 			rc = -EPERM;
 		break;
-	case MEM_GOING_ONLINE:
+	case MEM_PREPARE_ONLINE:
+		memory_block = find_memory_block(pfn_to_section_nr(arg->start_pfn));
+		if (!memory_block) {
+			rc = -EINVAL;
+			goto out;
+		}
 		rc = sclp_mem_change_state(start, size, 1);
+		if (rc || !memory_block->altmap)
+			goto out;
+		/*
+		 * Set CMMA state to nodat here, since the struct page memory
+		 * at the beginning of the memory block will not go through the
+		 * buddy allocator later.
+		 */
+		__arch_set_page_nodat((void *)__va(start), memory_block->altmap->free);
 		break;
-	case MEM_CANCEL_ONLINE:
-		sclp_mem_change_state(start, size, 0);
-		break;
-	case MEM_OFFLINE:
+	case MEM_FINISH_OFFLINE:
 		sclp_mem_change_state(start, size, 0);
 		break;
 	default:
 		break;
 	}
+out:
 	mutex_unlock(&sclp_mem_mutex);
 	return rc ? NOTIFY_BAD : NOTIFY_OK;
 }
@@ -397,7 +411,9 @@ static void __init add_memory_merged(u16 rn)
 	if (!size)
 		goto skip_add;
 	for (addr = start; addr < start + size; addr += block_size)
-		add_memory(0, addr, block_size, MHP_NONE);
+		add_memory(0, addr, block_size,
+			   MACHINE_HAS_EDAT1 ?
+			   MHP_MEMMAP_ON_MEMORY | MHP_OFFLINE_INACCESSIBLE : MHP_NONE);
 skip_add:
 	first_rn = rn;
 	num = 1;
-- 
2.41.0