From f62f1fc9ef94f74fda2b456d935ba2da69fa0a40 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Fri, 7 Mar 2008 15:02:50 -0800
Subject: [PATCH] x86: reserve dma32 early for gart

a system with 256 GB of RAM, when NUMA is disabled crashes the
following way:

Your BIOS doesn't leave a aperture memory hole
Please enable the IOMMU option in the BIOS setup
This costs you 64 MB of RAM
Cannot allocate aperture memory hole (ffff8101c0000000,65536K)
Kernel panic - not syncing: Not enough memory for aperture
Pid: 0, comm: swapper Not tainted 2.6.25-rc4-x86-latest.git #33

Call Trace:
 [<ffffffff84037c62>] panic+0xb2/0x190
 [<ffffffff840381fc>] ? release_console_sem+0x7c/0x250
 [<ffffffff847b1628>] ? __alloc_bootmem_nopanic+0x48/0x90
 [<ffffffff847b0ac9>] ? free_bootmem+0x29/0x50
 [<ffffffff847ac1f7>] gart_iommu_hole_init+0x5e7/0x680
 [<ffffffff847b255b>] ? alloc_large_system_hash+0x16b/0x310
 [<ffffffff84506a2f>] ? _etext+0x0/0x1
 [<ffffffff847a2e8c>] pci_iommu_alloc+0x1c/0x40
 [<ffffffff847ac795>] mem_init+0x45/0x1a0
 [<ffffffff8479ff35>] start_kernel+0x295/0x380
 [<ffffffff8479f1c2>] _sinittext+0x1c2/0x230

the root cause is : memmap PMD is too big,
[ffffe200e0600000-ffffe200e07fffff] PMD ->ffff81383c000000 on node 0
almost near 4G..., and vmemmap_alloc_block will use up the ram under 4G.

solution will be:
1. make memmap allocation get memory above 4G...
2. reserve some dma32 range early before we try to set up memmap for all.
and release that before pci_iommu_alloc, so gart or swiotlb could get some
range under 4g limit for sure.

the patch is using method 2.
because method1 may need more code to handle SPARSEMEM and SPASEMEM_VMEMMAP

will get
Your BIOS doesn't leave a aperture memory hole
Please enable the IOMMU option in the BIOS setup
This costs you 64 MB of RAM
Mapping aperture over 65536 KB of RAM @ 4000000
Memory: 264245736k/268959744k available (8484k kernel code, 4187464k reserved, 4004k data, 724k init)

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/pci-dma_64.c | 49 ++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/setup_64.c   |  2 ++
 include/asm-x86/pci_64.h     |  1 +
 3 files changed, 52 insertions(+)

diff --git a/arch/x86/kernel/pci-dma_64.c b/arch/x86/kernel/pci-dma_64.c
index 375cb2bc45be..8bc1e185e557 100644
--- a/arch/x86/kernel/pci-dma_64.c
+++ b/arch/x86/kernel/pci-dma_64.c
@@ -8,6 +8,8 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/dmar.h>
+#include <linux/bootmem.h>
+#include <asm/proto.h>
 #include <asm/io.h>
 #include <asm/gart.h>
 #include <asm/calgary.h>
@@ -286,8 +288,55 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
+static __initdata void *dma32_bootmem_ptr;
+static unsigned long dma32_bootmem_size __initdata = (128ULL<<20);
+
+static int __init parse_dma32_size_opt(char *p)
+{
+	if (!p)
+		return -EINVAL;
+	dma32_bootmem_size = memparse(p, &p);
+	return 0;
+}
+early_param("dma32_size", parse_dma32_size_opt);
+
+void __init dma32_reserve_bootmem(void)
+{
+	unsigned long size, align;
+	if (end_pfn <= MAX_DMA32_PFN)
+		return;
+
+	align = 64ULL<<20;
+	size = round_up(dma32_bootmem_size, align);
+	dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
+				 __pa(MAX_DMA_ADDRESS));
+	if (dma32_bootmem_ptr)
+		dma32_bootmem_size = size;
+	else
+		dma32_bootmem_size = 0;
+}
+static void __init dma32_free_bootmem(void)
+{
+	int node;
+
+	if (end_pfn <= MAX_DMA32_PFN)
+		return;
+
+	if (!dma32_bootmem_ptr)
+		return;
+
+	for_each_online_node(node)
+		free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr),
+				  dma32_bootmem_size);
+
+	dma32_bootmem_ptr = NULL;
+	dma32_bootmem_size = 0;
+}
+
 void __init pci_iommu_alloc(void)
 {
+	/* free the range so iommu could get some range less than 4G */
+	dma32_free_bootmem();
 	/*
 	 * The order of these functions is important for
 	 * fall-back/fail-over reasons
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 7637dc91c79b..a775fe3de955 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -389,6 +389,8 @@ void __init setup_arch(char **cmdline_p)
 
 	early_res_to_bootmem();
 
+	dma32_reserve_bootmem();
+
 #ifdef CONFIG_ACPI_SLEEP
 	/*
 	 * Reserve low memory region for sleep support.
diff --git a/include/asm-x86/pci_64.h b/include/asm-x86/pci_64.h
index 374690314539..da8266a08005 100644
--- a/include/asm-x86/pci_64.h
+++ b/include/asm-x86/pci_64.h
@@ -25,6 +25,7 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int l
 
 
 
+extern void dma32_reserve_bootmem(void);
 extern void pci_iommu_alloc(void);
 
 /* The PCI address space does equal the physical memory
-- 
GitLab