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:   Li Zhijian <lizhijian@fujitsu.com>
To:     kexec@lists.infradead.org, nvdimm@lists.linux.dev
Cc:     linux-kernel@vger.kernel.org, dan.j.williams@intel.com,
        bhe@redhat.com, ruansy.fnst@fujitsu.com, y-goto@fujitsu.com,
        yangx.jy@fujitsu.com, Li Zhijian <lizhijian@fujitsu.com>,
        Vivek Goyal <vgoyal@redhat.com>, Dave Young <dyoung@redhat.com>
Subject: [RFC PATCH makedumpfile v3 2/3] makedumpfile.c: Exclude all pmem pages
Date:   Fri,  2 Jun 2023 18:26:55 +0800
Message-Id: <20230602102656.131654-7-lizhijian@fujitsu.com>
In-Reply-To: <20230602102656.131654-1-lizhijian@fujitsu.com>
References: <20230602102656.131654-1-lizhijian@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Generally, the pmem is too large to suitable to be dumped. Further, only
the namespace of the pmem is dumpable, but actually currently we have no
idea the excatly layout of the namespace in pmem. So we exclude all of
them temporarily. And later, we will try to support including/excluding
metadata by specific parameter.

CC: Baoquan He <bhe@redhat.com>
CC: Vivek Goyal <vgoyal@redhat.com>
CC: Dave Young <dyoung@redhat.com>
CC: kexec@lists.infradead.org
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
---
 makedumpfile.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/makedumpfile.c b/makedumpfile.c
index cadc59662bef..f304f752b0ec 100644
--- a/makedumpfile.c
+++ b/makedumpfile.c
@@ -100,6 +100,7 @@ mdf_pfn_t pfn_user;
 mdf_pfn_t pfn_free;
 mdf_pfn_t pfn_hwpoison;
 mdf_pfn_t pfn_offline;
+mdf_pfn_t pfn_pmem_userdata;
 mdf_pfn_t pfn_elf_excluded;
 
 mdf_pfn_t num_dumped;
@@ -6389,6 +6390,7 @@ __exclude_unnecessary_pages(unsigned long mem_map,
 	unsigned int order_offset, dtor_offset;
 	unsigned long flags, mapping, private = 0;
 	unsigned long compound_dtor, compound_head = 0;
+	unsigned int is_pmem;
 
 	/*
 	 * If a multi-page exclusion is pending, do it first
@@ -6443,6 +6445,13 @@ __exclude_unnecessary_pages(unsigned long mem_map,
 				continue;
 		}
 
+		is_pmem = is_pmem_pt_load_range(pfn << PAGESHIFT(), (pfn + 1) << PAGESHIFT());
+		if (is_pmem) {
+			pfn_pmem_userdata++;
+			clear_bit_on_2nd_bitmap_for_kernel(pfn, cycle);
+			continue;
+		}
+
 		index_pg = pfn % PGMM_CACHED;
 		pcache  = page_cache + (index_pg * SIZE(page));
 
@@ -8122,7 +8131,7 @@ write_elf_pages_cyclic(struct cache_data *cd_header, struct cache_data *cd_page)
 	 */
 	if (info->flag_cyclic) {
 		pfn_zero = pfn_cache = pfn_cache_private = 0;
-		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = 0;
+		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = pfn_pmem_userdata = 0;
 		pfn_memhole = info->max_mapnr;
 	}
 
@@ -9460,7 +9469,7 @@ write_kdump_pages_and_bitmap_cyclic(struct cache_data *cd_header, struct cache_d
 		 * Reset counter for debug message.
 		 */
 		pfn_zero = pfn_cache = pfn_cache_private = 0;
-		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = 0;
+		pfn_user = pfn_free = pfn_hwpoison = pfn_offline = pfn_pmem_userdata = 0;
 		pfn_memhole = info->max_mapnr;
 
 		/*
@@ -10408,7 +10417,7 @@ print_report(void)
 	 */
 	pfn_original = info->max_mapnr - pfn_memhole;
 
-	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private
+	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private + pfn_pmem_userdata
 	    + pfn_user + pfn_free + pfn_hwpoison + pfn_offline;
 
 	REPORT_MSG("\n");
@@ -10425,6 +10434,7 @@ print_report(void)
 	REPORT_MSG("    Free pages              : 0x%016llx\n", pfn_free);
 	REPORT_MSG("    Hwpoison pages          : 0x%016llx\n", pfn_hwpoison);
 	REPORT_MSG("    Offline pages           : 0x%016llx\n", pfn_offline);
+	REPORT_MSG("    pmem userdata pages     : 0x%016llx\n", pfn_pmem_userdata);
 	REPORT_MSG("  Remaining pages  : 0x%016llx\n",
 	    pfn_original - pfn_excluded);
 
@@ -10464,7 +10474,7 @@ print_mem_usage(void)
 	*/
 	pfn_original = info->max_mapnr - pfn_memhole;
 
-	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private
+	pfn_excluded = pfn_zero + pfn_cache + pfn_cache_private + pfn_pmem_userdata
 	    + pfn_user + pfn_free + pfn_hwpoison + pfn_offline;
 	shrinking = (pfn_original - pfn_excluded) * 100;
 	shrinking = shrinking / pfn_original;
-- 
2.29.2