[PATCH v4 4/7] powerpc/fadump: Reservationless firmware assisted dump

[Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com>]

From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>

One of the primary issues with Firmware Assisted Dump (fadump) on Power
is that it needs a large amount of memory to be reserved. On large
systems with TeraBytes of memory, this reservation can be quite
significant.

In some cases, fadump fails if the memory reserved is insufficient, or
if the reserved memory was DLPAR hot-removed.

In the normal case, post reboot, the preserved memory is filtered to
extract only relevant areas of interest using the makedumpfile tool.
While the tool provides flexibility to determine what needs to be part
of the dump and what memory to filter out, all supported distributions
default this to "Capture only kernel data and nothing else".

We take advantage of this default and the Linux kernel's Contiguous
Memory Allocator (CMA) to fundamentally change the memory reservation
model for fadump.

Instead of setting aside a significant chunk of memory nobody can use,
this patch uses CMA instead, to reserve a significant chunk of memory
that the kernel is prevented from using (due to MIGRATE_CMA), but
applications are free to use it. With this fadump will still be able
to capture all of the kernel memory and most of the user space memory
except the user pages that were present in CMA region.

Essentially, on a P9 LPAR with 2 cores, 8GB RAM and current upstream:
[root@zzxx-yy10 ~]# free -m
              total        used        free      shared  buff/cache   available
Mem:           7557         193        6822          12         541        6725
Swap:          4095           0        4095

With this patch:
[root@zzxx-yy10 ~]# free -m
              total        used        free      shared  buff/cache   available
Mem:           8133         194        7464          12         475        7338
Swap:          4095           0        4095

Changes made here are completely transparent to how fadump has
traditionally worked.

Thanks to Aneesh Kumar and Anshuman Khandual for helping us understand
CMA and its usage.

TODO:
- Handle case where CMA reservation spans nodes.

Signed-off-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
 arch/powerpc/kernel/fadump.c |  120 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 103 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 16b3e8c5cae0..7f76924ab190 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -34,6 +34,7 @@
 #include <linux/crash_dump.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
+#include <linux/cma.h>
 
 #include <asm/debugfs.h>
 #include <asm/page.h>
@@ -45,11 +46,57 @@
 static struct fw_dump fw_dump;
 static struct fadump_mem_struct fdm;
 static const struct fadump_mem_struct *fdm_active;
+static struct cma *fadump_cma;
 
 static DEFINE_MUTEX(fadump_mutex);
 struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES];
 int crash_mem_ranges;
 
+/*
+ * fadump_cma_reserve() - reserve area for fadump memory reservation
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the memblock allocator
+ * has been activated.
+ */
+int __init fadump_cma_reserve(void)
+{
+	unsigned long long base, size;
+	int rc;
+
+	if (!fw_dump.fadump_enabled)
+		return 0;
+
+	base = fw_dump.reserve_dump_area_start;
+	size = fw_dump.reserve_dump_area_size;
+	pr_debug("Original reserve area base %ld, size %ld\n",
+				(unsigned long)base >> 20,
+				(unsigned long)size >> 20);
+	if (!size)
+		return 0;
+
+	rc = cma_declare_contiguous(base, size, 0, 0, 0, false,
+						"fadump_cma", &fadump_cma);
+	if (rc) {
+		printk(KERN_ERR "fadump: Failed to reserve cma area for "
+				"firmware-assisted dump, %d\n", rc);
+		fw_dump.reserve_dump_area_size = 0;
+		return 0;
+	}
+	/*
+	 * So we now have cma area reserved for fadump. base may be different
+	 * from what we requested.
+	 */
+	fw_dump.reserve_dump_area_start = cma_get_base(fadump_cma);
+	fw_dump.reserve_dump_area_size = cma_get_size(fadump_cma);
+	printk("Reserved %ldMB cma area at %ldMB for firmware-assisted dump "
+			"(System RAM: %ldMB)\n",
+			cma_get_size(fadump_cma) >> 20,
+			(unsigned long)cma_get_base(fadump_cma) >> 20,
+			(unsigned long)(memblock_phys_mem_size() >> 20));
+	return 1;
+}
+
 /* Scan the Firmware Assisted dump configuration details. */
 int __init early_init_dt_scan_fw_dump(unsigned long node,
 			const char *uname, int depth, void *data)
@@ -496,8 +543,9 @@ int __init fadump_reserve_mem(void)
 		pr_info("Number of kernel Dump sections: %d\n",
 			be16_to_cpu(fdm_active->header.dump_num_sections));
 		fw_dump.fadumphdr_addr = get_fadump_metadata_base(fdm_active);
-		pr_debug("fadumphdr_addr = %p\n",
-				(void *) fw_dump.fadumphdr_addr);
+		pr_debug("fadumphdr_addr = %pa\n", &fw_dump.fadumphdr_addr);
+		fw_dump.reserve_dump_area_start = base;
+		fw_dump.reserve_dump_area_size = size;
 	} else {
 		size = get_fadump_area_size();
 
@@ -514,21 +562,10 @@ int __init fadump_reserve_mem(void)
 			    !memblock_is_region_reserved(base, size))
 				break;
 		}
-		if ((base > (memory_boundary - size)) ||
-		    memblock_reserve(base, size)) {
-			pr_err("Failed to reserve memory\n");
-			return 0;
-		}
-
-		pr_info("Reserved %ldMB of memory at %ldMB for firmware-"
-			"assisted dump (System RAM: %ldMB)\n",
-			(unsigned long)(size >> 20),
-			(unsigned long)(base >> 20),
-			(unsigned long)(memblock_phys_mem_size() >> 20));
+		fw_dump.reserve_dump_area_start = base;
+		fw_dump.reserve_dump_area_size = size;
+		return fadump_cma_reserve();
 	}
-
-	fw_dump.reserve_dump_area_start = base;
-	fw_dump.reserve_dump_area_size = size;
 	return 1;
 }
 
@@ -1191,6 +1228,39 @@ static unsigned long init_fadump_header(unsigned long addr)
 	return addr;
 }
 
+static unsigned long allocate_metadata_area(void)
+{
+	int nr_pages;
+	unsigned long size;
+	struct page *page = NULL;
+
+	/*
+	 * Check if fadump cma region is activated.
+	 * fadump_cma->count == 0 means cma activation has failed. This means
+	 * that the fadump reserved memory now will not be visible/available
+	 * for user applications to use. It will be as good as old fadump
+	 * behaviour of blocking this memory chunk from production system
+	 * use. CMA activation failure does not mean that fadump will not
+	 * work. Will continue to setup fadump.
+	 */
+	if (!fadump_cma || !cma_get_size(fadump_cma)) {
+		pr_warn("fadump cma region activation failed.\n");
+		return 0;
+	}
+
+	size = get_fadump_metadata_size();
+	nr_pages = ALIGN(size, PAGE_SIZE) >> PAGE_SHIFT;
+	pr_info("Fadump metadata size = %ld (nr_pages = %d)\n", size, nr_pages);
+
+	page = cma_alloc(fadump_cma, nr_pages, 0, GFP_KERNEL);
+	if (page) {
+		pr_debug("Allocated fadump metadata area at %ldMB (cma)\n",
+				(unsigned long)page_to_phys(page) >> 20);
+		return page_to_phys(page);
+	}
+	return 0;
+}
+
 static int register_fadump(void)
 {
 	unsigned long addr;
@@ -1643,8 +1713,24 @@ int __init setup_fadump(void)
 			fadump_invalidate_release_mem();
 	}
 	/* Initialize the kernel dump memory structure for FAD registration. */
-	else if (fw_dump.reserve_dump_area_size)
+	else if (fw_dump.reserve_dump_area_size) {
+		/*
+		 * By this time cma area has been activated. Allocate memory
+		 * for metadata from fadump cma region. Since this is very
+		 * early during boot we are guaranteed to get metadata cma
+		 * allocation at address fw_dump.reserve_dump_area_start.
+		 *
+		 * During fadump registration, metadata region is used
+		 * to setup fadump header and ELF core header. We don't want
+		 * this region to be touched by anyone. Allocating metadata
+		 * region memory from fadump cma will make sure that this
+		 * region will not given to any user space application.
+		 * However the rest of the fadump cma memory is still free
+		 * to be used by user applications.
+		 */
+		allocate_metadata_area();
 		init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+	}
 	fadump_init_files();
 
 	return 1;