[RFC PATCH 6/6] sparc64: use early_res and nobootmem

From: Yinghai Lu
Date: Wed Mar 10 2010 - 16:26:29 EST

use early_res/fw_memmap to replace lmb, so could use early_res replace bootme
later.

Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>

---
arch/sparc/Kconfig | 17 ++
arch/sparc/configs/sparc64_defconfig | 1
arch/sparc/include/asm/lmb.h | 10 -
arch/sparc/include/asm/pgtable_64.h | 2
arch/sparc/kernel/mdesc.c | 18 +-
arch/sparc/kernel/prom_64.c | 7
arch/sparc/kernel/setup_64.c | 19 --
arch/sparc/mm/init_64.c | 247 ++++++++++++++++-------------------
8 files changed, 155 insertions(+), 166 deletions(-)

Index: linux-2.6/arch/sparc/Kconfig
===================================================================
--- linux-2.6.orig/arch/sparc/Kconfig
+++ linux-2.6/arch/sparc/Kconfig
@@ -39,7 +39,6 @@ config SPARC64
select HAVE_FUNCTION_TRACER
select HAVE_KRETPROBES
select HAVE_KPROBES
- select HAVE_LMB
select HAVE_SYSCALL_WRAPPERS
select HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
@@ -90,6 +89,10 @@ config STACKTRACE_SUPPORT
bool
default y if SPARC64

+config HAVE_EARLY_RES
+ bool
+ default y if SPARC64
+
config LOCKDEP_SUPPORT
bool
default y if SPARC64
@@ -284,6 +287,18 @@ config GENERIC_HARDIRQS
source "kernel/time/Kconfig"

if SPARC64
+
+config NO_BOOTMEM
+ default y
+ bool "Disable Bootmem code"
+ ---help---
+ Use early_res directly instead of bootmem before slab is ready.
+ - allocator (buddy) [generic]
+ - early allocator (bootmem) [generic]
+ - very early allocator (reserve_early*()) [generic]
+ So reduce one layer between early allocator to final allocator
+
+
source "drivers/cpufreq/Kconfig"

config US3_FREQ
Index: linux-2.6/arch/sparc/include/asm/pgtable_64.h
===================================================================
--- linux-2.6.orig/arch/sparc/include/asm/pgtable_64.h
+++ linux-2.6/arch/sparc/include/asm/pgtable_64.h
@@ -752,6 +752,8 @@ extern int io_remap_pfn_range(struct vm_
#define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4))
#define GET_PFN(pfn) (pfn & 0x0fffffffffffffffUL)

+#define MAXMEM _AC(__AC(1,UL)<<60, UL)
+
#include <asm-generic/pgtable.h>

/* We provide our own get_unmapped_area to cope with VA holes and
Index: linux-2.6/arch/sparc/kernel/mdesc.c
===================================================================
--- linux-2.6.orig/arch/sparc/kernel/mdesc.c
+++ linux-2.6/arch/sparc/kernel/mdesc.c
@@ -4,7 +4,8 @@
*/
#include <linux/kernel.h>
#include <linux/types.h>
-#include <linux/lmb.h>
+#include <linux/fw_memmap.h>
+#include <linux/early_res.h>
#include <linux/log2.h>
#include <linux/list.h>
#include <linux/slab.h>
@@ -86,7 +87,7 @@ static void mdesc_handle_init(struct mde
hp->handle_size = handle_size;
}

-static struct mdesc_handle * __init mdesc_lmb_alloc(unsigned int mdesc_size)
+static struct mdesc_handle * __init mdesc_early_alloc(unsigned int mdesc_size)
{
unsigned int handle_size, alloc_size;
struct mdesc_handle *hp;
@@ -97,17 +98,18 @@ static struct mdesc_handle * __init mdes
mdesc_size);
alloc_size = PAGE_ALIGN(handle_size);

- paddr = lmb_alloc(alloc_size, PAGE_SIZE);
+ paddr = find_e820_area(0, -1UL, alloc_size, PAGE_SIZE);

hp = NULL;
if (paddr) {
+ reserve_early(paddr, paddr + alloc_size, "mdesc");
hp = __va(paddr);
mdesc_handle_init(hp, handle_size, hp);
}
return hp;
}

-static void mdesc_lmb_free(struct mdesc_handle *hp)
+static void mdesc_early_free(struct mdesc_handle *hp)
{
unsigned int alloc_size;
unsigned long start;
@@ -120,9 +122,9 @@ static void mdesc_lmb_free(struct mdesc_
free_bootmem_late(start, alloc_size);
}

-static struct mdesc_mem_ops lmb_mdesc_ops = {
- .alloc = mdesc_lmb_alloc,
- .free = mdesc_lmb_free,
+static struct mdesc_mem_ops early_mdesc_ops = {
+ .alloc = mdesc_early_alloc,
+ .free = mdesc_early_free,
};

static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
@@ -914,7 +916,7 @@ void __init sun4v_mdesc_init(void)

printk("MDESC: Size is %lu bytes.\n", len);

- hp = mdesc_alloc(len, &lmb_mdesc_ops);
+ hp = mdesc_alloc(len, &early_mdesc_ops);
if (hp == NULL) {
prom_printf("MDESC: alloc of %lu bytes failed.\n", len);
prom_halt();
Index: linux-2.6/arch/sparc/kernel/prom_64.c
===================================================================
--- linux-2.6.orig/arch/sparc/kernel/prom_64.c
+++ linux-2.6/arch/sparc/kernel/prom_64.c
@@ -20,7 +20,8 @@
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/module.h>
-#include <linux/lmb.h>
+#include <linux/fw_memmap.h>
+#include <linux/early_res.h>
#include <linux/of_device.h>

#include <asm/prom.h>
@@ -34,14 +35,14 @@

void * __init prom_early_alloc(unsigned long size)
{
- unsigned long paddr = lmb_alloc(size, SMP_CACHE_BYTES);
+ unsigned long paddr = find_e820_area(0, -1UL, size, SMP_CACHE_BYTES);
void *ret;

if (!paddr) {
prom_printf("prom_early_alloc(%lu) failed\n");
prom_halt();
}
-
+ reserve_early(paddr, paddr + size, "prom_alloc");
ret = __va(paddr);
memset(ret, 0, size);
prom_early_allocated += size;
Index: linux-2.6/arch/sparc/kernel/setup_64.c
===================================================================
--- linux-2.6.orig/arch/sparc/kernel/setup_64.c
+++ linux-2.6/arch/sparc/kernel/setup_64.c
@@ -139,21 +139,7 @@ static void __init boot_flags_init(char
process_switch(*commands++);
continue;
}
- if (!strncmp(commands, "mem=", 4)) {
- /*
- * "mem=XXX[kKmM]" overrides the PROM-reported
- * memory size.
- */
- cmdline_memory_size = simple_strtoul(commands + 4,
- &commands, 0);
- if (*commands == 'K' || *commands == 'k') {
- cmdline_memory_size <<= 10;
- commands++;
- } else if (*commands=='M' || *commands=='m') {
- cmdline_memory_size <<= 20;
- commands++;
- }
- }
+
while (*commands && *commands != ' ')
commands++;
}
@@ -279,11 +265,14 @@ void __init boot_cpu_id_too_large(int cp
}
#endif

+void __init setup_memory_map(void);
+
void __init setup_arch(char **cmdline_p)
{
/* Initialize PROM console and command line. */
*cmdline_p = prom_getbootargs();
strcpy(boot_command_line, *cmdline_p);
+ setup_memory_map();
parse_early_param();

boot_flags_init(*cmdline_p);
Index: linux-2.6/arch/sparc/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/sparc/mm/init_64.c
+++ linux-2.6/arch/sparc/mm/init_64.c
@@ -24,7 +24,8 @@
#include <linux/cache.h>
#include <linux/sort.h>
#include <linux/percpu.h>
-#include <linux/lmb.h>
+#include <linux/fw_memmap.h>
+#include <linux/early_res.h>
#include <linux/mmzone.h>

#include <asm/head.h>
@@ -726,7 +727,7 @@ static void __init find_ramdisk(unsigned
initrd_start = ramdisk_image;
initrd_end = ramdisk_image + sparc_ramdisk_size;

- lmb_reserve(initrd_start, sparc_ramdisk_size);
+ reserve_early(initrd_start, initrd_end, "initrd");

initrd_start += PAGE_OFFSET;
initrd_end += PAGE_OFFSET;
@@ -737,7 +738,9 @@ static void __init find_ramdisk(unsigned
struct node_mem_mask {
unsigned long mask;
unsigned long val;
+#ifndef CONFIG_NO_BOOTMEM
unsigned long bootmem_paddr;
+#endif
};
static struct node_mem_mask node_masks[MAX_NUMNODES];
static int num_node_masks;
@@ -818,40 +821,51 @@ static unsigned long long nid_range(unsi
*/
static void __init allocate_node_data(int nid)
{
- unsigned long paddr, num_pages, start_pfn, end_pfn;
+ unsigned long paddr, start_pfn, end_pfn;
struct pglist_data *p;

+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+
#ifdef CONFIG_NEED_MULTIPLE_NODES
- paddr = lmb_alloc_nid(sizeof(struct pglist_data),
- SMP_CACHE_BYTES, nid, nid_range);
+ paddr = find_e820_area(start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT,
+ sizeof(struct pglist_data), SMP_CACHE_BYTES);
if (!paddr) {
prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
prom_halt();
}
+ reserve_early(paddr, paddr + sizeof(struct pglist_data), "NODEDATA");
NODE_DATA(nid) = __va(paddr);
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));

+#ifndef CONFIG_NO_BOOTMEM
NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
#endif
+#endif

p = NODE_DATA(nid);

- get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ p->node_id = nid;
p->node_start_pfn = start_pfn;
p->node_spanned_pages = end_pfn - start_pfn;

+#ifndef CONFIG_NO_BOOTMEM
if (p->node_spanned_pages) {
+ unsigned long num_pages;
num_pages = bootmem_bootmap_pages(p->node_spanned_pages);

- paddr = lmb_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid,
- nid_range);
+ paddr = find_e820_area(start_pfn << PAGE_SHIFT,
+ end_pfn << PAGE_SHIFT,
+ num_pages << PAGE_SHIFT, PAGE_SIZE);
if (!paddr) {
prom_printf("Cannot allocate bootmap for nid[%d]\n",
nid);
prom_halt();
}
+ reserve_early(paddr, paddr + (num_pages << PAGE_SHIFT),
+ "BOOTMAP");
node_masks[nid].bootmem_paddr = paddr;
}
+#endif
}

static void init_node_masks_nonnuma(void)
@@ -972,30 +986,27 @@ int of_node_to_nid(struct device_node *d

static void __init add_node_ranges(void)
{
- int i;

- for (i = 0; i < lmb.memory.cnt; i++) {
- unsigned long size = lmb_size_bytes(&lmb.memory, i);
- unsigned long start, end;
+ unsigned long size = max_pfn << PAGE_SHIFT;
+ unsigned long start, end;
+
+ start = 0;
+ end = start + size;
+ while (start < end) {
+ unsigned long this_end;
+ int nid;

- start = lmb.memory.region[i].base;
- end = start + size;
- while (start < end) {
- unsigned long this_end;
- int nid;
-
- this_end = nid_range(start, end, &nid);
-
- numadbg("Adding active range nid[%d] "
- "start[%lx] end[%lx]\n",
- nid, start, this_end);
-
- add_active_range(nid,
- start >> PAGE_SHIFT,
- this_end >> PAGE_SHIFT);
+ this_end = nid_range(start, end, &nid);

- start = this_end;
- }
+ numadbg("Adding active range nid[%d] "
+ "start[%lx] end[%lx]\n",
+ nid, start, this_end);
+
+ e820_register_active_regions(nid,
+ start >> PAGE_SHIFT,
+ this_end >> PAGE_SHIFT);
+
+ start = this_end;
}
}

@@ -1010,11 +1021,13 @@ static int __init grab_mlgroups(struct m
if (!count)
return -ENOENT;

- paddr = lmb_alloc(count * sizeof(struct mdesc_mlgroup),
+ paddr = find_e820_area(0, -1UL, count * sizeof(struct mdesc_mlgroup),
SMP_CACHE_BYTES);
if (!paddr)
return -ENOMEM;

+ reserve_early(paddr, paddr + count * sizeof(struct mdesc_mlgroup),
+ "mlgroups");
mlgroups = __va(paddr);
num_mlgroups = count;

@@ -1051,10 +1064,11 @@ static int __init grab_mblocks(struct md
if (!count)
return -ENOENT;

- paddr = lmb_alloc(count * sizeof(struct mdesc_mblock),
+ paddr = find_e820_area(0, -1UL, count * sizeof(struct mdesc_mblock),
SMP_CACHE_BYTES);
if (!paddr)
return -ENOMEM;
+ reserve_early(paddr, count * sizeof(struct mdesc_mblock), "mblocks");

mblocks = __va(paddr);
num_mblocks = count;
@@ -1279,9 +1293,8 @@ static int bootmem_init_numa(void)

static void __init bootmem_init_nonnuma(void)
{
- unsigned long top_of_ram = lmb_end_of_DRAM();
- unsigned long total_ram = lmb_phys_mem_size();
- unsigned int i;
+ unsigned long top_of_ram = max_pfn << PAGE_SHIFT;
+ unsigned long total_ram = top_of_ram - e820_hole_size(0, top_of_ram);

numadbg("bootmem_init_nonnuma()\n");

@@ -1292,61 +1305,21 @@ static void __init bootmem_init_nonnuma(

init_node_masks_nonnuma();

- for (i = 0; i < lmb.memory.cnt; i++) {
- unsigned long size = lmb_size_bytes(&lmb.memory, i);
- unsigned long start_pfn, end_pfn;
-
- if (!size)
- continue;
-
- start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT;
- end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i);
- add_active_range(0, start_pfn, end_pfn);
- }
+ remove_all_active_ranges();
+ e820_register_active_regions(0, 0, top_of_ram);

allocate_node_data(0);

node_set_online(0);
}

-static void __init reserve_range_in_node(int nid, unsigned long start,
- unsigned long end)
-{
- numadbg(" reserve_range_in_node(nid[%d],start[%lx],end[%lx]\n",
- nid, start, end);
- while (start < end) {
- unsigned long this_end;
- int n;
-
- this_end = nid_range(start, end, &n);
- if (n == nid) {
- numadbg(" MATCH reserving range [%lx:%lx]\n",
- start, this_end);
- reserve_bootmem_node(NODE_DATA(nid), start,
- (this_end - start), BOOTMEM_DEFAULT);
- } else
- numadbg(" NO MATCH, advancing start to %lx\n",
- this_end);
-
- start = this_end;
- }
-}
-
-static void __init trim_reserved_in_node(int nid)
+int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+ int flags)
{
- int i;
-
- numadbg(" trim_reserved_in_node(%d)\n", nid);
-
- for (i = 0; i < lmb.reserved.cnt; i++) {
- unsigned long start = lmb.reserved.region[i].base;
- unsigned long size = lmb_size_bytes(&lmb.reserved, i);
- unsigned long end = start + size;
-
- reserve_range_in_node(nid, start, end);
- }
+ return reserve_bootmem(phys, len, flags);
}

+#ifndef CONFIG_NO_BOOTMEM
static void __init bootmem_init_one_node(int nid)
{
struct pglist_data *p;
@@ -1371,20 +1344,26 @@ static void __init bootmem_init_one_node
nid, end_pfn);
free_bootmem_with_active_regions(nid, end_pfn);

- trim_reserved_in_node(nid);
-
- numadbg(" sparse_memory_present_with_active_regions(%d)\n",
- nid);
- sparse_memory_present_with_active_regions(nid);
}
}
+#endif
+
+u64 __init get_max_mapped(void)
+{
+ /* what is max_pfn_mapped for sparc64 ? */
+ u64 end = max_pfn;
+
+ end <<= PAGE_SHIFT;
+
+ return end;
+}

static unsigned long __init bootmem_init(unsigned long phys_base)
{
unsigned long end_pfn;
int nid;

- end_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
+ end_pfn = e820_end_of_ram_pfn();
max_pfn = max_low_pfn = end_pfn;
min_low_pfn = (phys_base >> PAGE_SHIFT);

@@ -1392,10 +1371,23 @@ static unsigned long __init bootmem_init
bootmem_init_nonnuma();

/* XXX cpu notifier XXX */
-
+#ifndef CONFIG_NO_BOOTMEM
for_each_online_node(nid)
bootmem_init_one_node(nid);

+ early_res_to_bootmem(0, end_pfn << PAGE_SHIFT);
+#endif
+
+ for_each_online_node(nid) {
+ struct pglist_data *p;
+ p = NODE_DATA(nid);
+ if (p->node_spanned_pages) {
+ numadbg(" sparse_memory_present_with_active_regions(%d)\n",
+ nid);
+ sparse_memory_present_with_active_regions(nid);
+ }
+ }
+
sparse_init();

return end_pfn;
@@ -1681,9 +1673,36 @@ pgd_t swapper_pg_dir[2048];
static void sun4u_pgprot_init(void);
static void sun4v_pgprot_init(void);

+void __init setup_memory_map(void)
+{
+ int i;
+ unsigned long phys_base;
+ /* Find available physical memory...
+ *
+ * Read it twice in order to work around a bug in openfirmware.
+ * The call to grab this table itself can cause openfirmware to
+ * allocate memory, which in turn can take away some space from
+ * the list of available memory. Reading it twice makes sure
+ * we really do get the final value.
+ */
+ read_obp_translations();
+ read_obp_memory("reg", &pall[0], &pall_ents);
+ read_obp_memory("available", &pavail[0], &pavail_ents);
+ read_obp_memory("available", &pavail[0], &pavail_ents);
+
+ phys_base = 0xffffffffffffffffUL;
+ for (i = 0; i < pavail_ents; i++) {
+ phys_base = min(phys_base, pavail[i].phys_addr);
+ e820_add_region(pavail[i].phys_addr, pavail[i].reg_size,
+ E820_RAM);
+ }
+
+ find_ramdisk(phys_base);
+}
+
void __init paging_init(void)
{
- unsigned long end_pfn, shift, phys_base;
+ unsigned long end_pfn, shift;
unsigned long real_end, i;

/* These build time checkes make sure that the dcache_dirty_cpu()
@@ -1734,35 +1753,7 @@ void __init paging_init(void)
sun4v_ktsb_init();
}

- lmb_init();
-
- /* Find available physical memory...
- *
- * Read it twice in order to work around a bug in openfirmware.
- * The call to grab this table itself can cause openfirmware to
- * allocate memory, which in turn can take away some space from
- * the list of available memory. Reading it twice makes sure
- * we really do get the final value.
- */
- read_obp_translations();
- read_obp_memory("reg", &pall[0], &pall_ents);
- read_obp_memory("available", &pavail[0], &pavail_ents);
- read_obp_memory("available", &pavail[0], &pavail_ents);
-
- phys_base = 0xffffffffffffffffUL;
- for (i = 0; i < pavail_ents; i++) {
- phys_base = min(phys_base, pavail[i].phys_addr);
- lmb_add(pavail[i].phys_addr, pavail[i].reg_size);
- }
-
- lmb_reserve(kern_base, kern_size);
-
- find_ramdisk(phys_base);
-
- lmb_enforce_memory_limit(cmdline_memory_size);
-
- lmb_analyze();
- lmb_dump_all();
+ reserve_early(kern_base, kern_base + kern_size, "Kernel");

set_bit(0, mmu_context_bmap);

@@ -1815,13 +1806,18 @@ void __init paging_init(void)
* IRQ stacks.
*/
for_each_possible_cpu(i) {
+ unsigned long paddr;
/* XXX Use node local allocations... XXX */
- softirq_stack[i] = __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
- hardirq_stack[i] = __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+ paddr = find_e820_area(0, -1UL, THREAD_SIZE, THREAD_SIZE);
+ reserve_early(paddr, paddr + THREAD_SIZE, "softirq_stack");
+ softirq_stack[i] = __va(paddr);
+ paddr = find_e820_area(0, -1UL, THREAD_SIZE, THREAD_SIZE);
+ reserve_early(paddr, paddr + THREAD_SIZE, "hardirq_stack");
+ hardirq_stack[i] = __va(paddr);
}

/* Setup bootmem... */
- last_valid_pfn = end_pfn = bootmem_init(phys_base);
+ last_valid_pfn = end_pfn = bootmem_init(0);

#ifndef CONFIG_NEED_MULTIPLE_NODES
max_mapnr = last_valid_pfn;
@@ -1957,6 +1953,9 @@ void __init mem_init(void)
free_all_bootmem_node(NODE_DATA(i));
}
}
+# ifdef CONFIG_NO_BOOTMEM
+ totalram_pages += free_all_memory_core_early(MAX_NUMNODES);
+# endif
}
#else
totalram_pages = free_all_bootmem();
@@ -2002,14 +2001,6 @@ void free_initmem(void)
unsigned long addr, initend;
int do_free = 1;

- /* If the physical memory maps were trimmed by kernel command
- * line options, don't even try freeing this initmem stuff up.
- * The kernel image could have been in the trimmed out region
- * and if so the freeing below will free invalid page structs.
- */
- if (cmdline_memory_size)
- do_free = 0;
-
/*
* The init section is aligned to 8k in vmlinux.lds. Page align for >8k pagesizes.
*/
Index: linux-2.6/arch/sparc/configs/sparc64_defconfig
===================================================================
--- linux-2.6.orig/arch/sparc/configs/sparc64_defconfig
+++ linux-2.6/arch/sparc/configs/sparc64_defconfig
@@ -1916,5 +1916,4 @@ CONFIG_DECOMPRESS_LZO=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT=y
CONFIG_HAS_DMA=y
-CONFIG_HAVE_LMB=y
CONFIG_NLATTR=y
Index: linux-2.6/arch/sparc/include/asm/lmb.h
===================================================================
--- linux-2.6.orig/arch/sparc/include/asm/lmb.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _SPARC64_LMB_H
-#define _SPARC64_LMB_H
-
-#include <asm/oplib.h>
-
-#define LMB_DBG(fmt...) prom_printf(fmt)
-
-#define LMB_REAL_LIMIT 0
-
-#endif /* !(_SPARC64_LMB_H) */
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/