From mboxrd@z Thu Jan  1 00:00:00 1970
From: Robin Holt <holt@sgi.com>
Date: Thu, 13 Apr 2006 13:14:42 +0000
Subject: Make show_mem() skip holes in a pgdat.
Message-Id: <20060413131441.GA16615@lnx-holt.americas.sgi.com>
List-Id: <linux-ia64.vger.kernel.org>
References: <20060413031519.GB2678@lnx-holt.americas.sgi.com>
In-Reply-To: <20060413031519.GB2678@lnx-holt.americas.sgi.com>
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
To: linux-ia64@vger.kernel.org


This patch modifies ia64's show_mem() to walk the vmem_map page tables and
rapidly skip forward across regions where the page tables are missing.
This prevents the pfn_valid() check from causing numerous unnecessary
page faults.

Without this patch on a 512 node 512 cpu system where every node has four
memory holes, the show_mem() call takes 1 hour 18 minutes.  With this
patch, it takes less than 3 seconds.

Signed-off-by: Robin Holt <holt@sgi.com>

---
Fixed.


Index: linux-2.6/arch/ia64/mm/discontig.c
=================================--- linux-2.6.orig/arch/ia64/mm/discontig.c	2006-04-13 06:16:00.500029306 -0500
+++ linux-2.6/arch/ia64/mm/discontig.c	2006-04-13 07:01:31.668069891 -0500
@@ -519,6 +519,69 @@ void __cpuinit *per_cpu_init(void)
 }
 #endif /* CONFIG_SMP */
 
+
+static int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i)
+{
+	unsigned long end_address, hole_next_pfn;
+	unsigned long stop_address;
+
+	end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
+	end_address = PAGE_ALIGN(end_address);
+
+	stop_address = (unsigned long) &vmem_map[
+		pgdat->node_start_pfn + pgdat->node_spanned_pages];
+
+	do {
+		pgd_t *pgd;
+		pud_t *pud;
+		pmd_t *pmd;
+		pte_t *pte;
+
+		pgd = pgd_offset_k(end_address);
+		if (pgd_none(*pgd)) {
+			end_address += PTRS_PER_PUD *
+				       PTRS_PER_PMD *
+				       PTRS_PER_PTE *
+				       PAGE_SIZE;
+			continue;
+		}
+
+		pud = pud_offset(pgd, end_address);
+		if (pud_none(*pud)) {
+			end_address += PTRS_PER_PMD *
+				       PTRS_PER_PTE *
+				       PAGE_SIZE;
+			continue;
+		}
+
+		pmd = pmd_offset(pud, end_address);
+		if (pmd_none(*pmd)) {
+			end_address += PTRS_PER_PTE *
+				       PAGE_SIZE;
+			continue;
+		}
+
+		pte = pte_offset_kernel(pmd, end_address);
+retry_pte:
+		if (pte_none(*pte)) {
+			end_address += PAGE_SIZE;
+			pte++;
+			if ((end_address < stop_address) &&
+			    (end_address != ALIGN(end_address, 1UL << PMD_SHIFT)))
+				goto retry_pte;
+			continue;
+		}
+		/* Found next valid vmem_map page */
+		break;
+	} while (end_address < stop_address);
+
+	end_address = min(end_address, stop_address);
+	end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1;
+	hole_next_pfn = end_address / sizeof(struct page);
+	return hole_next_pfn - pgdat->node_start_pfn;
+}
+
+
 /**
  * show_mem - give short summary of memory stats
  *
@@ -547,8 +610,10 @@ void show_mem(void)
 			struct page *page;
 			if (pfn_valid(pgdat->node_start_pfn + i))
 				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else
+			else {
+				i = find_next_valid_pfn_for_pgdat(pgdat, i) - 1;
 				continue;
+			}
 			if (PageReserved(page))
 				reserved++;
 			else if (PageSwapCache(page))