LinuxPPC-Dev Archive on lore.kernel.org
 help / color / Atom feed
From: Hari Bathini <hbathini@linux.ibm.com>
To: linuxppc-dev <linuxppc-dev@ozlabs.org>
Cc: Ananth N Mavinakayanahalli <ananth@linux.ibm.com>,
	Mahesh J Salgaonkar <mahesh@linux.ibm.com>,
	Vasant Hegde <hegdevasant@linux.ibm.com>,
	Oliver <oohall@gmail.com>, Nicholas Piggin <npiggin@gmail.com>,
	Daniel Axtens <dja@axtens.net>
Subject: [PATCH v6 27/36] powerpc/fadump: consider reserved ranges while releasing memory
Date: Wed, 11 Sep 2019 20:25:36 +0530
Message-ID: <156821371358.5656.6061214942558818661.stgit@hbathini.in.ibm.com> (raw)
In-Reply-To: <156821308145.5656.2233728784001623843.stgit@hbathini.in.ibm.com>

Commit 0962e8004e97 ("powerpc/prom: Scan reserved-ranges node for
memory reservations") enabled support to parse 'reserved-ranges' DT
node to reserve kernel memory falling in these ranges for firmware
purposes. Along with the preserved area memory, ensure memory in
reserved ranges is not overlapped with memory released by capture
kernel aftering saving vmcore. Also, fix the off-by-one error in
fadump_release_reserved_area function while releasing memory.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---

Changes in v6:
  * Use kernel types where possible.


 arch/powerpc/kernel/fadump.c |  167 +++++++++++++++++++++++++++++++++++++-----
 1 file changed, 146 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index f95ec1f..502e49a 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -36,6 +36,7 @@ static struct fw_dump fw_dump;
 
 static DEFINE_MUTEX(fadump_mutex);
 struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0 };
+struct fadump_mrange_info reserved_mrange_info = { "reserved", NULL, 0, 0, 0 };
 
 #ifdef CONFIG_CMA
 static struct cma *fadump_cma;
@@ -1009,49 +1010,173 @@ static void fadump_free_reserved_memory(unsigned long start_pfn,
 /*
  * Skip memory holes and free memory that was actually reserved.
  */
-static void fadump_release_reserved_area(unsigned long start, unsigned long end)
+static void fadump_release_reserved_area(u64 start, u64 end)
 {
+	u64 tstart, tend, spfn, epfn;
 	struct memblock_region *reg;
-	unsigned long tstart, tend;
-	unsigned long start_pfn = PHYS_PFN(start);
-	unsigned long end_pfn = PHYS_PFN(end);
 
+	spfn = PHYS_PFN(start);
+	epfn = PHYS_PFN(end);
 	for_each_memblock(memory, reg) {
-		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
-		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
+		tstart = max_t(u64, spfn, memblock_region_memory_base_pfn(reg));
+		tend   = min_t(u64, epfn, memblock_region_memory_end_pfn(reg));
 		if (tstart < tend) {
 			fadump_free_reserved_memory(tstart, tend);
 
-			if (tend == end_pfn)
+			if (tend == epfn)
 				break;
 
-			start_pfn = tend + 1;
+			spfn = tend;
 		}
 	}
 }
 
 /*
- * Release the memory that was reserved in early boot to preserve the memory
- * contents. The released memory will be available for general use.
+ * Sort the mem ranges in-place and merge adjacent ranges
+ * to minimize the memory ranges count.
  */
-static void fadump_release_memory(unsigned long begin, unsigned long end)
+static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info)
 {
-	unsigned long ra_start, ra_end;
+	struct fadump_memory_range *mem_ranges;
+	struct fadump_memory_range tmp_range;
+	u64 base, size;
+	int i, j, idx;
+
+	if (!reserved_mrange_info.mem_range_cnt)
+		return;
+
+	/* Sort the memory ranges */
+	mem_ranges = mrange_info->mem_ranges;
+	for (i = 0; i < mrange_info->mem_range_cnt; i++) {
+		idx = i;
+		for (j = (i + 1); j < mrange_info->mem_range_cnt; j++) {
+			if (mem_ranges[idx].base > mem_ranges[j].base)
+				idx = j;
+		}
+		if (idx != i) {
+			tmp_range = mem_ranges[idx];
+			mem_ranges[idx] = mem_ranges[i];
+			mem_ranges[i] = tmp_range;
+		}
+	}
+
+	/* Merge adjacent reserved ranges */
+	idx = 0;
+	for (i = 1; i < mrange_info->mem_range_cnt; i++) {
+		base = mem_ranges[i-1].base;
+		size = mem_ranges[i-1].size;
+		if (mem_ranges[i].base == (base + size))
+			mem_ranges[idx].size += mem_ranges[i].size;
+		else {
+			idx++;
+			if (i == idx)
+				continue;
+
+			mem_ranges[idx] = mem_ranges[i];
+		}
+	}
+	mrange_info->mem_range_cnt = idx + 1;
+}
+
+/*
+ * Scan reserved-ranges to consider them while reserving/releasing
+ * memory for FADump.
+ */
+static inline int fadump_scan_reserved_mem_ranges(void)
+{
+	struct device_node *root;
+	const __be32 *prop;
+	int len, ret = -1;
+	unsigned long i;
+
+	root = of_find_node_by_path("/");
+	if (!root)
+		return ret;
+
+	prop = of_get_property(root, "reserved-ranges", &len);
+	if (!prop)
+		return ret;
+
+	/*
+	 * Each reserved range is an (address,size) pair, 2 cells each,
+	 * totalling 4 cells per range.
+	 */
+	for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+		u64 base, size;
+
+		base = of_read_number(prop + (i * 4) + 0, 2);
+		size = of_read_number(prop + (i * 4) + 2, 2);
+
+		if (size) {
+			ret = fadump_add_mem_range(&reserved_mrange_info,
+						   base, base + size);
+			if (ret < 0) {
+				pr_warn("some reserved ranges are ignored!\n");
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Release the memory that was reserved during early boot to preserve the
+ * crash'ed kernel's memory contents except reserved dump area (permanent
+ * reservation) and reserved ranges used by F/W. The released memory will
+ * be available for general use.
+ */
+static void fadump_release_memory(u64 begin, u64 end)
+{
+	u64 ra_start, ra_end, tstart;
+	int i, ret;
+
+	fadump_scan_reserved_mem_ranges();
 
 	ra_start = fw_dump.reserve_dump_area_start;
 	ra_end = ra_start + fw_dump.reserve_dump_area_size;
 
 	/*
-	 * exclude the dump reserve area. Will reuse it for next
-	 * fadump registration.
+	 * Add reserved dump area to reserved ranges list
+	 * and exclude all these ranges while releasing memory.
 	 */
-	if (begin < ra_end && end > ra_start) {
-		if (begin < ra_start)
-			fadump_release_reserved_area(begin, ra_start);
-		if (end > ra_end)
-			fadump_release_reserved_area(ra_end, end);
-	} else
-		fadump_release_reserved_area(begin, end);
+	ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end);
+	if (ret != 0) {
+		/*
+		 * Not enough memory to setup reserved ranges but the system is
+		 * running shortage of memory. So, release all the memory except
+		 * Reserved dump area (reused for next fadump registration).
+		 */
+		if (begin < ra_end && end > ra_start) {
+			if (begin < ra_start)
+				fadump_release_reserved_area(begin, ra_start);
+			if (end > ra_end)
+				fadump_release_reserved_area(ra_end, end);
+		} else
+			fadump_release_reserved_area(begin, end);
+
+		return;
+	}
+
+	/* Get the reserved ranges list in order first. */
+	sort_and_merge_mem_ranges(&reserved_mrange_info);
+
+	/* Exclude reserved ranges and release remaining memory */
+	tstart = begin;
+	for (i = 0; i < reserved_mrange_info.mem_range_cnt; i++) {
+		ra_start = reserved_mrange_info.mem_ranges[i].base;
+		ra_end = ra_start + reserved_mrange_info.mem_ranges[i].size;
+
+		if (tstart >= ra_end)
+			continue;
+
+		if (tstart < ra_start)
+			fadump_release_reserved_area(tstart, ra_start);
+		tstart = ra_end;
+	}
+
+	if (tstart < end)
+		fadump_release_reserved_area(tstart, end);
 }
 
 static void fadump_invalidate_release_mem(void)


  parent reply index

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-11 14:45 [PATCH v6 00/36] Add FADump support on PowerNV platform Hari Bathini
2019-09-11 14:46 ` [PATCH v6 01/36] powerpc/fadump: move internal macros/definitions to a new header Hari Bathini
2019-09-19 10:25   ` Michael Ellerman
2019-09-11 14:46 ` [PATCH v6 02/36] powerpc/fadump: add helper functions Hari Bathini
2019-09-11 14:46 ` [PATCH v6 03/36] powerpc/fadump: declare helper functions in internal header file Hari Bathini
2019-09-11 14:47 ` [PATCH v6 04/36] powerpc/fadump: Improve fadump documentation Hari Bathini
2019-09-11 14:47 ` [PATCH v6 05/36] powerpc/fadump: use helper functions to reserve/release cpu notes buffer Hari Bathini
2019-09-11 14:48 ` [PATCH v6 06/36] pseries/fadump: move rtas specific definitions to platform code Hari Bathini
2019-09-11 14:48 ` [PATCH v6 07/36] pseries/fadump: introduce callbacks for platform specific operations Hari Bathini
2019-09-11 14:48 ` [PATCH v6 08/36] pseries/fadump: define RTAS register/un-register callback functions Hari Bathini
2019-09-11 14:49 ` [PATCH v6 09/36] pseries/fadump: add source info while displaying region contents Hari Bathini
2019-09-11 14:49 ` [PATCH v6 10/36] powerpc/fadump: release all the memory above boot memory size Hari Bathini
2019-09-11 14:49 ` [PATCH v6 11/36] pseries/fadump: move out platform specific support from generic code Hari Bathini
2019-09-11 14:49 ` [PATCH v6 12/36] powerpc/fadump: use FADump instead of fadump for how it is pronounced Hari Bathini
2019-09-11 14:50 ` [PATCH v6 13/36] opal: add MPIPL interface definitions Hari Bathini
2019-09-11 14:50 ` [PATCH v6 14/36] powernv/fadump: add fadump support on powernv Hari Bathini
2019-09-11 14:50 ` [PATCH v6 15/36] powerpc/fadump: improve fadump_reserve_mem() Hari Bathini
2019-09-11 14:50 ` [PATCH v6 16/36] powernv/fadump: register kernel metadata address with opal Hari Bathini
2019-09-11 14:51 ` [PATCH v6 17/36] powernv/fadump: reset metadata address during clean up Hari Bathini
2019-09-11 14:51 ` [PATCH v6 18/36] powernv/fadump: define OPAL register/un-register callback functions Hari Bathini
2019-09-11 14:51 ` [PATCH v6 19/36] powernv/fadump: support copying multiple kernel boot memory regions Hari Bathini
2019-09-11 14:51 ` [PATCH v6 20/36] powernv/fadump: process the crashdump by exporting it as /proc/vmcore Hari Bathini
2019-09-11 14:52 ` [PATCH v6 21/36] powernv/fadump: Warn before processing partial crashdump Hari Bathini
2019-09-11 14:53 ` [PATCH v6 22/36] powernv/fadump: handle invalidation of crashdump and re-registraion Hari Bathini
2019-09-11 14:53 ` [PATCH v6 23/36] powerpc/fadump: Update documentation about OPAL platform support Hari Bathini
2019-09-11 14:54 ` [PATCH v6 24/36] powerpc/fadump: make use of memblock's bottom up allocation mode Hari Bathini
2019-09-11 14:54 ` [PATCH v6 25/36] powernv/fadump: process architected register state data provided by firmware Hari Bathini
2019-09-11 14:55 ` [PATCH v6 26/36] powerpc/fadump: make crash memory ranges array allocation generic Hari Bathini
2019-09-11 14:55 ` Hari Bathini [this message]
2019-09-11 14:55 ` [PATCH v6 28/36] powerpc/fadump: improve how crashed kernel's memory is reserved Hari Bathini
2019-09-11 14:56 ` [PATCH v6 29/36] powernv/fadump: add support to preserve crash data on FADUMP disabled kernel Hari Bathini
2019-09-11 14:56 ` [PATCH v6 30/36] powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP Hari Bathini
2019-09-11 14:56 ` [PATCH v6 31/36] powernv/opalcore: export /sys/firmware/opal/core for analysing opal crashes Hari Bathini
2019-09-11 14:56 ` [PATCH v6 32/36] powernv/opalcore: provide an option to invalidate /sys/firmware/opal/core file Hari Bathini
2019-09-11 14:56 ` [PATCH v6 33/36] powerpc/fadump: consider f/w load area Hari Bathini
2019-09-11 14:57 ` [PATCH v6 34/36] powernv/fadump: update documentation about option to release opalcore Hari Bathini
2019-09-11 14:57 ` [PATCH v6 35/36] powerpc/fadump: remove RMA_START and RMA_END macros Hari Bathini
2019-09-11 14:57 ` [PATCH v6 36/36] powernv/fadump: support holes in kernel boot memory area Hari Bathini

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=156821371358.5656.6061214942558818661.stgit@hbathini.in.ibm.com \
    --to=hbathini@linux.ibm.com \
    --cc=ananth@linux.ibm.com \
    --cc=dja@axtens.net \
    --cc=hegdevasant@linux.ibm.com \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=mahesh@linux.ibm.com \
    --cc=npiggin@gmail.com \
    --cc=oohall@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LinuxPPC-Dev Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linuxppc-dev/0 linuxppc-dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linuxppc-dev linuxppc-dev/ https://lore.kernel.org/linuxppc-dev \
		linuxppc-dev@lists.ozlabs.org linuxppc-dev@ozlabs.org linuxppc-dev@archiver.kernel.org
	public-inbox-index linuxppc-dev

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.ozlabs.lists.linuxppc-dev


AGPL code for this site: git clone https://public-inbox.org/ public-inbox